DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Introduction
This office action is in response to communications filed 09/05/2024. Claims 1-20 are pending and likewise have been examined.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 09/05/2024, 09/19/2024, 02/06/2025, 11/24/2025 and 04/09/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Independent Claims 1, 8 and 15 recite the limitations “generating, by a first generative artificial intelligence model, a list comprising one or more executable actions based on a first prompt comprising a natural language utterance provided by a user;”, “creating an execution plan comprising the one or more executable actions;”, “executing the execution plan, wherein executing the execution plan comprises performing an iterative process for each executable action of the one or more executable actions, and wherein the iterative process comprises: identifying an action type for an executable action, invoking one or more states configured to execute the action type, and executing, by the one or more states, the executable action using an asset to obtain an output;”, “generating a second prompt based on the output obtained from executing each of the one or more executable actions;”, “and generating, by a second generative artificial intelligence model, a response to the natural language utterance based on the second prompt”.
Claim 1 also recites “A computer-implemented method comprising:”.
Claim 8 also recites “A system comprising: one or more processors; and one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the system to perform operations comprising:”
Claim 15 also recites “One or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:”
The limitations “generating….a list comprising one or more executable actions based on a first prompt comprising a natural language utterance provided by a user;”, “creating an execution plan comprising the one or more executable actions;”, “executing the execution plan, wherein executing the execution plan comprises performing an iterative process for each executable action of the one or more executable actions, and wherein the iterative process comprises: identifying an action type for an executable action, invoking one or more states configured to execute the action type, and executing, by the one or more states, the executable action using an asset to obtain an output;”, “generating a second prompt based on the output obtained from executing each of the one or more executable actions;”, “and generating…., a response to the natural language utterance based on the second prompt”, are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claim does not recite additional limitations that amount to significantly more than the judicial exception. Claims 1, 8 and 15 recite “generating, by a first generative artificial intelligence model, a list comprising one or more executable actions based on a first prompt comprising a natural language utterance provided by a user;”, “and generating, by a second generative artificial intelligence model, a response to the natural language utterance based on the second prompt”. Claim 1 also recites “A computer-implemented method comprising:”. Claim 8 also recites “A system comprising: one or more processors; and one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the system to perform operations comprising:”. Claim 15 also recites “One or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:”. All of these limitations amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above, regarding Claims 1,8 and 15, the addition of generic computer components do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Claims 1, 8 and 15 do not contain any additional limitations, Thus, the claims as a whole are directed to an abstract idea.
Dependent Claims 2, 9 and 16 recite the additional limitations, “wherein: (“the operation of” added in Claims 9 and 16) creating the execution plan comprises performing an evaluation of the one or more executable actions;”, “the evaluation comprises evaluating the one or more executable actions based on one or more ongoing conversation paths initiated by the user and any currently active execution plans;”, “and (“the operation of” added in Claims 9 and 16)creating the execution plan further comprises: (i) When the evaluation determines that the natural language utterance is part of an ongoing conversation path, incorporating the one or more executable actions into a currently active execution plan associated with the ongoing conversation path, the currently active execution plan comprising an ordered list of the one or more executable actions and one or more prior actions”, “or (ii) when the evaluation determines the natural language utterance is not part of an ongoing conversation path, creating a new execution plan comprising an ordered list of the one or more executable actions”. These limitations are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claims do not recite additional limitations that amount to significantly more than the judicial exception as the claims do not contain any additional limitations.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims do not contain any additional limitations. Thus, the claims as a whole are directed to an abstract idea.
Dependent Claims 3 and 10 recite the additional limitations, “wherein the iterative process further comprises: determining whether one or more parameters are available for the executable action;”, “when the one or more parameters are available, invoking the one or more states and executing the executable action based on the one or more parameters;”, “and when the one or more parameters for the executable action are not available, obtaining the one or more parameters that are not available and then invoking the one or more states and executing the executable action based on the one or more parameters”. These limitations are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claims do not recite additional limitations that amount to significantly more than the judicial exception as the claims do not contain any additional limitations.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims do not contain any additional limitations. Thus, the claims as a whole are directed to an abstract idea.
Dependent Claims 4 and 11 recite the additional limitations, “wherein (“the operation of” added in Claim 11) obtaining the one or more parameters comprises generating a natural language request to the user to obtain the one or more parameters for the executable action, and receiving a response from the user comprising the one or more parameters.”. These limitations are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claims do not recite additional limitations that amount to significantly more than the judicial exception as the claims do not contain any additional limitations.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims do not contain any additional limitations. Thus, the claims as a whole are directed to an abstract idea.
Dependent Claims 5, 12 and 18 recite the additional limitations, “wherein: (“the operation of” added in Claims 12 and 18) invoking one or more states configured to execute the action type comprises:”, “invoking a first state to identify that the executable action has not yet been executed to generate a response, and invoking a second state to determine whether one or more parameters are available for the executable action;”, “(“the operation of” added in Claims 12 and 18) executing the executable action using the asset to obtain the output comprises invoking a third state to generate the output;”, “and the first state, the second state, and the third state are different from one another”. These limitations are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claims do not recite additional limitations that amount to significantly more than the judicial exception as the claims do not contain any additional limitations.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims do not contain any additional limitations. Thus, the claims as a whole are directed to an abstract idea.
Dependent Claims 6, 13 and 19 recite the additional limitations, “ wherein (“the operation of” added in Claims 13 and 19) generating the list comprises selecting the one or more executable actions from a list of candidate agent actions that are determined by using a semantic index, and wherein (“the operation of” added in Claims 13 and 19) creating the execution plan further comprises:”, “identifying, based at least in part on metadata associated with candidate agent actions within the list of candidate agent actions, the one or more executable actions that provide information or knowledge for generating the response to the natural language utterance;”, “and generating a structured output for the execution plan by creating an ordered list of the one or more executable actions and a set of dependencies among the one or more executable actions”. These limitations are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claims do not recite additional limitations that amount to significantly more than the judicial exception as the claims do not contain any additional limitations.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims do not contain any additional limitations. Thus, the claims as a whole are directed to an abstract idea.
Dependent Claims 7, 14 and 20 recite the additional limitations, “wherein the iterative process further comprises determining that one or more dependencies exist between the executable action and at least one other executable action of the one or more executable actions based on the set of dependencies among the one or more executable actions, and wherein the executable action is executed( switched with “executable” in Claims 14 and 20) sequentially in accordance with the one or more dependencies determined to exist between the executable action and the at least one other executable action”. These limitations are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claims do not recite additional limitations that amount to significantly more than the judicial exception as the claims do not contain any additional limitations.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claims do not contain any additional limitations. Thus, the claims as a whole are directed to an abstract idea.
Dependent Claim 17 recites the additional limitations, “determining whether one or more parameters are available for the executable action;”, “when the one or more parameters are available, invoking the one or more states and executing the executable action based on the one or more parameters;”, “and when the one or more parameters for the executable action are not available, obtaining the one or more parameters that are not available and then invoking the one or more states and executing the executable action based on the one or more parameters, wherein obtaining the one or more parameters comprises generating a natural language request to the user to obtain the one or more parameters for the executable action, and receiving a response from the user comprising the one or more parameters”. These limitations are directed towards a mental process, as they could be done mentally, or on pen and paper.
The claim does not recite additional limitations that amount to significantly more than the judicial exception as the claim does not contain any additional limitations.
This judicial exception is not integrated into a practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The claim does not contain any additional limitations. Thus, the claims as a whole are directed to an abstract idea.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1 and 5 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lu et al. “Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models”, hereinafter Lu.
Regarding Claim 1:
Lu teaches a computer-implemented method comprising: generating, by a first generative artificial intelligence model, a list comprising one or more executable actions based on a first prompt comprising a natural language utterance provided by a user(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2);
creating an execution plan comprising the one or more executable actions(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2);
executing the execution plan, wherein executing the execution plan comprises performing an iterative process for each executable action of the one or more executable actions, and wherein the iterative process comprises: identifying an action type for an executable action, invoking one or more states configured to execute the action type, and executing, by the one or more states, the executable action using an asset to obtain an output(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2. Pg 5, Para 2, Ln 1-3, Given the generated plan, the corresponding modules for each step are then executed sequentially. Pg 5, Para 3, Ln 1-3, where xt−1 is the input for the current module Mt, and ct−1 is the cached information (e.g., image semantics, retrieved knowledge, generated programs) resulting from the execution history of modules. Pg 5, 4.1 module inventory, Knowledge retrieval, Bing search);
generating a second prompt based on the output obtained from executing each of the one or more executable actions(Pg 5, Para 3, Ln 1-3, where xt−1 is the input for the current module Mt, and ct−1 is the cached information (e.g., image semantics, retrieved knowledge, generated programs) resulting from the execution history of modules. Pg 5, Para 4, Ln 1-5, The update_input and update_cache functions are hand-designed for each Mt. Specifically, update_input is applied to elements in the input query, including the question, table context, and image. These elements are updated after module execution. update_cache corresponds to the generation of new information, such as a description for the input image or retrieved knowledge from external resources. Finally, the response r to the query is generated by the last module M);
and generating, by a second generative artificial intelligence model, a response to the natural language utterance based on the second prompt(Pg 5, Para 4, Ln 1-5, The update_input and update_cache functions are hand-designed for each Mt. Specifically, update_input is applied to elements in the input query, including the question, table context, and image. These elements are updated after module execution. update_cache corresponds to the generation of new information, such as a description for the input image or retrieved knowledge from external resources. Finally, the response r to the query is generated by the last module M. Pg 3, Fig 2, solution generator and answer generator).
Regarding Claim 5:
Lu teaches the computer-implemented method of claim 1, and Lu teaches wherein: invoking one or more states configured to execute the action type comprises: invoking a first state to identify that the executable action has not yet been executed to generate a response, and invoking a second state to determine whether one or more parameters are available for the executable action(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. Pg 5, 4.1 Module Inventory, Para 2, Knowledge Retrieval (Mkr): This module retrieves additional background knowledge crucial for tackling complex problems.);
executing the executable action using the asset to obtain the output comprises invoking a third state to generate the output(Pg 6, Para 10, Ln 1-4, Solution Generator (Msg): This module generates a detailed solution to the input query using all the cached information. Employing a chain-of-thought prompting approach [53], it ensures coherent and well-structured responses. The planner can directly employ this module instead of other functional modules if it can solve the query independently, especially for simpler ones. See Pg 1, Fig 1, and Pg 3, Fig 2);
and the first state, the second state, and the third state are different from one another(See Pg 1, Fig 1, and Pg 3, Fig 2).
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lu as applied to claim 1 above, and further in view of Mishra et al. (US 12456020 B1).
Regarding Claim 2:
Lu teaches the computer-implemented method of claim 1, but does not teach wherein: creating the execution plan comprises performing an evaluation of the one or more executable actions; the evaluation comprises evaluating the one or more executable actions based on one or more ongoing conversation paths initiated by the user and any currently active execution plans; and creating the execution plan further comprises: (i) When the evaluation determines that the natural language utterance is part of an ongoing conversation path, incorporating the one or more executable actions into a currently active execution plan associated with the ongoing conversation path, the currently active execution plan comprising an ordered list of the one or more executable actions and one or more prior actions, or (ii) when the evaluation determines the natural language utterance is not part of an ongoing conversation path, creating a new execution plan comprising an ordered list of the one or more executable actions.
In the same field of AI agents, Mishra teaches wherein: creating the execution plan comprises performing an evaluation of the one or more executable actions; the evaluation comprises evaluating the one or more executable actions based on one or more ongoing conversation paths initiated by the user and any currently active execution plans(Col 16, Ln 5-21, the user input data 127 is received at the plan prompt generation component 610. The plan prompt generation component 610 processes the user input data 127 to generate prompt data 615 representing a prompt for input to the plan generation language model 620. In some embodiments, the plan prompt generation component 610 may further receive an indication of one or more remaining tasks to be completed with respect to the user input data 127. For example, if the current iteration of processing with respect to the user input data 127 is a subsequent iteration of processing (e.g., the system previously determined that more than one task is to be completed in order to perform an action responsive to the user input data 127 and has previously performed at least a first task of the more than one tasks), then the plan prompt generation component 610 may further receive an indication of the remaining tasks to be completed);
and creating the execution plan further comprises: (i) When the evaluation determines that the natural language utterance is part of an ongoing conversation path, incorporating the one or more executable actions into a currently active execution plan associated with the ongoing conversation path, the currently active execution plan comprising an ordered list of the one or more executable actions and one or more prior actions, or(Col 18, Ln 4-12, the prompt data 615 may be an instruction for the plan generation language model 620 to determine one or more tasks (e.g., steps/actions) that are to be completed in order to perform an action responsive to the user input given the other information (e.g., the personalized context data 567, the indication of the remaining task(s), the indication of the completed task(s), and/or the corresponding response(s)) included in the prompt data. Col 14, Ln 50-59, as the system 100 processes to complete the list of tasks, the plan generation component 535 may (1) incorporate the results of the processing performed to complete the tasks into data provided to other components of the system 100; (2) update the list of tasks to indicate completed (or attempted, in-progress, etc.) tasks; (3) generate an updated prioritization of the tasks remaining to be completed (or tasks to be attempted again); and/or (4) determine an updated current task to be completed)
(ii) when the evaluation determines the natural language utterance is not part of an ongoing conversation path, creating a new execution plan comprising an ordered list of the one or more executable actions(optional limitation).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify Lu with the LLM system of Mishra, as it helps improve accuracy(Col 3, Ln 11-22).
Claim(s) 3 and 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lu as applied to claim 1 above, and further in view of Sharifi et al. (US 20220189474 A1).
Regarding Claim 3:
Lu teaches the computer-implemented method of claim 1, but does not teach wherein the iterative process further comprises: determining whether one or more parameters are available for the executable action; when the one or more parameters are available, invoking the one or more states and executing the executable action based on the one or more parameters; and when the one or more parameters for the executable action are not available, obtaining the one or more parameters that are not available and then invoking the one or more states and executing the executable action based on the one or more parameters.
In the same field of AI agents, Sharifi teaches wherein the iterative process further comprises: determining whether one or more parameters are available for the executable action(Para [0043], Ln 1-10, system determines, based on processing the recognition that corresponds to the spoken utterance, that the spoken utterance is ambiguous. The system determines that the spoken utterance is ambiguous based on determining that the recognition is interpretable as requesting performance of a first particular action exclusively and also being interpretable a second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions);
when the one or more parameters are available, invoking the one or more states and executing the executable action based on the one or more parameters(Para [0049], Ln 1-7, At block 264, the system processes the further user input to determine to perform the first particular action instead of the second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions);
and when the one or more parameters for the executable action are not available, obtaining the one or more parameters that are not available and then invoking the one or more states and executing the executable action based on the one or more parameters(Para [0044], Ln 1-7, At block 258, the system determines to provide an enhanced clarification prompt that renders additional output that is presented instead of or in addition to natural language. Para [0049], Ln 1-7, At block 264, the system processes the further user input to determine to perform the first particular action instead of the second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify Lu with the disambiguation of Sharifi, as it improves user convenience(Para [0006], Ln 24-32).
Regarding Claim 4:
The combination of Lu and Sharifi teaches the computer-implemented method of claim 3, but does not teach wherein obtaining the one or more parameters comprises generating a natural language request to the user to obtain the one or more parameters for the executable action, and receiving a response from the user comprising the one or more parameters.
In the same field of AI agents, Sharifi teaches wherein obtaining the one or more parameters comprises generating a natural language request to the user to obtain the one or more parameters for the executable action, and receiving a response from the user comprising the one or more parameters(Para [0044], Ln 1-7, At block 258, the system determines to provide an enhanced clarification prompt that renders additional output that is presented instead of or in addition to natural language. Para [0049], Ln 1-7, At block 264, the system processes the further user input to determine to perform the first particular action instead of the second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify the combination of Lu and Sharifi with the disambiguation of Sharifi, as it improves user convenience(Para [0006], Ln 24-32).
Claim(s) 6 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lu as applied to claim 1 above, and further in view of Liang et al. “TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs” hereinafter Liang.
Regarding Claim 6:
Lu teaches the computer-implemented method of claim 1, but does not teach wherein generating the list comprises selecting the one or more executable actions from a list of candidate agent actions that are determined by using a semantic index, and wherein creating the execution plan further comprises: identifying, based at least in part on metadata associated with candidate agent actions within the list of candidate agent actions, the one or more executable actions that provide information or knowledge for generating the response to the natural language utterance; and generating a structured output for the execution plan by creating an ordered list of the one or more executable actions and a set of dependencies among the one or more executable actions.
In the same field of AI agents, Liang teaches wherein generating the list comprises selecting the one or more executable actions from a list of candidate agent actions that are determined by using a semantic index(Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture),
and wherein creating the execution plan further comprises: identifying, based at least in part on metadata associated with candidate agent actions within the list of candidate agent actions, the one or more executable actions that provide information or knowledge for generating the response to the natural language utterance(Pg 18, 4.2, Para 1, Ln 1-6, In this study, we emphasize the importance of composition instructions for composing multiple APIs to complete complex user instructions. This is demonstrated through subsequent ablation studies. Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture);
and generating a structured output for the execution plan by creating an ordered list of the one or more executable actions and a set of dependencies among the one or more executable actions(Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture. Pg 19, Fig 11, code for generating slides created based on API specifications in the portion of Fig 11 that is on Pg 18. Pg 20, Para 2, Ln 1-7, The process of decomposing user instructions may vary depending on the API design being used. Thus, it is essential for API developers to provide composition instructions to guide API usage. We have created composition instructions for three APIs: insert_text, select_title, and select_content. The composition instructions for insert_text specify that the content often contains multiple sentences. For select_title and select_content, the composition instructions specify the order in which these APIs should be used with other APIs, such as inserting and deleting text in a text box).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify Lu with the task completion system of Liang, as it improves compatibility with foundation models, improving performance(Pg 1, Abstract, Ln 10-18).
Regarding Claim 7:
The combination of Lu and Liang teaches the computer-implemented method of claim 6, but does not teach wherein the iterative process further comprises determining that one or more dependencies exist between the executable action and at least one other executable action of the one or more executable actions based on the set of dependencies among the one or more executable actions, and wherein the executable action is executed sequentially in accordance with the one or more dependencies determined to exist between the executable action and the at least one other executable action.
In the same field of AI agents, Liang teaches wherein the iterative process further comprises determining that one or more dependencies exist between the executable action and at least one other executable action of the one or more executable actions based on the set of dependencies among the one or more executable actions, and wherein the executable action is executed sequentially in accordance with the one or more dependencies determined to exist between the executable action and the at least one other executable action(Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture. Pg 19, Fig 11, code for generating slides created based on API specifications in the portion of Fig 11 that is on Pg 18. Pg 20, Para 2, Ln 1-7, The process of decomposing user instructions may vary depending on the API design being used. Thus, it is essential for API developers to provide composition instructions to guide API usage. We have created composition instructions for three APIs: insert_text, select_title, and select_content. The composition instructions for insert_text specify that the content often contains multiple sentences. For select_title and select_content, the composition instructions specify the order in which these APIs should be used with other APIs, such as inserting and deleting text in a text box).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify the combination of Lu and Liang with the task completion system of Liang, as it improves compatibility with foundation models, improving performance(Pg 1, Abstract, Ln 10-18).
Claim(s) 8-9, 12, 15-16 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lu, and further in view of Mishra.
Regarding Claim 8:
Lu teaches generating, by a first generative artificial intelligence model, a list comprising one or more executable actions based on a first prompt comprising a natural language utterance provided by a user(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2);
creating an execution plan comprising the one or more executable actions(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2);
executing the execution plan, wherein executing the execution plan comprises performing an iterative process for each executable action of the one or more executable actions, and wherein the iterative process comprises: identifying an action type for an executable action, invoking one or more states configured to execute the action type, and executing, by the one or more states, the executable action using an asset to obtain an output(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2. Pg 5, Para 2, Ln 1-3, Given the generated plan, the corresponding modules for each step are then executed sequentially. Pg 5, Para 3, Ln 1-3, where xt−1 is the input for the current module Mt, and ct−1 is the cached information (e.g., image semantics, retrieved knowledge, generated programs) resulting from the execution history of modules. Pg 5, 4.1 module inventory, Knowledge retrieval, Bing search);
generating a second prompt based on the output obtained from executing each of the one or more executable actions(Pg 5, Para 3, Ln 1-3, where xt−1 is the input for the current module Mt, and ct−1 is the cached information (e.g., image semantics, retrieved knowledge, generated programs) resulting from the execution history of modules. Pg 5, Para 4, Ln 1-5, The update_input and update_cache functions are hand-designed for each Mt. Specifically, update_input is applied to elements in the input query, including the question, table context, and image. These elements are updated after module execution. update_cache corresponds to the generation of new information, such as a description for the input image or retrieved knowledge from external resources. Finally, the response r to the query is generated by the last module M);
and generating, by a second generative artificial intelligence model, a response to the natural language utterance based on the second prompt(Pg 5, Para 4, Ln 1-5, The update_input and update_cache functions are hand-designed for each Mt. Specifically, update_input is applied to elements in the input query, including the question, table context, and image. These elements are updated after module execution. update_cache corresponds to the generation of new information, such as a description for the input image or retrieved knowledge from external resources. Finally, the response r to the query is generated by the last module M. Pg 3, Fig 2, solution generator and answer generator).
Lu does not explicitly teach a system comprising: one or more processors; and one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the system to perform operations comprising.
In the same field of AI agents Mishra teaches a system comprising: one or more processors; and one or more computer-readable media storing instructions which, when executed by the one or more processors, cause the system to perform operations comprising(Col 53, Ln 62-67, processors, memory, instructions).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify Lu with the computer components of Mishra, as it provides an environment for the system to be realized(Col 53, Ln 53-67).
Regarding Claim 9:
The combination of Lu and Mishra teaches the system of claim 8, but does not teach wherein: the operation of creating the execution plan comprises performing an evaluation of the one or more executable actions; the evaluation comprises evaluating the one or more executable actions based on one or more ongoing conversation paths initiated by the user and any currently active execution plans; and the operation of creating the execution plan further comprises: (i) When the evaluation determines that the natural language utterance is part of an ongoing conversation path, incorporating the one or more executable actions into a currently active execution plan associated with the ongoing conversation path, the currently active execution plan comprising an ordered list of the one or more executable actions and one or more prior actions, or (ii) when the evaluation determines the natural language utterance is not part of an ongoing conversation path, creating a new execution plan comprising an ordered list of the one or more executable actions.
In the same field of AI agents, Mishra teaches wherein: the operation of creating the execution plan comprises performing an evaluation of the one or more executable actions; the evaluation comprises evaluating the one or more executable actions based on one or more ongoing conversation paths initiated by the user and any currently active execution plans(Col 16, Ln 5-21, the user input data 127 is received at the plan prompt generation component 610. The plan prompt generation component 610 processes the user input data 127 to generate prompt data 615 representing a prompt for input to the plan generation language model 620. In some embodiments, the plan prompt generation component 610 may further receive an indication of one or more remaining tasks to be completed with respect to the user input data 127. For example, if the current iteration of processing with respect to the user input data 127 is a subsequent iteration of processing (e.g., the system previously determined that more than one task is to be completed in order to perform an action responsive to the user input data 127 and has previously performed at least a first task of the more than one tasks), then the plan prompt generation component 610 may further receive an indication of the remaining tasks to be completed);
and the operation of creating the execution plan further comprises: (i) When the evaluation determines that the natural language utterance is part of an ongoing conversation path, incorporating the one or more executable actions into a currently active execution plan associated with the ongoing conversation path, the currently active execution plan comprising an ordered list of the one or more executable actions and one or more prior actions, or(Col 18, Ln 4-12, the prompt data 615 may be an instruction for the plan generation language model 620 to determine one or more tasks (e.g., steps/actions) that are to be completed in order to perform an action responsive to the user input given the other information (e.g., the personalized context data 567, the indication of the remaining task(s), the indication of the completed task(s), and/or the corresponding response(s)) included in the prompt data. Col 14, Ln 50-59, as the system 100 processes to complete the list of tasks, the plan generation component 535 may (1) incorporate the results of the processing performed to complete the tasks into data provided to other components of the system 100; (2) update the list of tasks to indicate completed (or attempted, in-progress, etc.) tasks; (3) generate an updated prioritization of the tasks remaining to be completed (or tasks to be attempted again); and/or (4) determine an updated current task to be completed)
(ii) when the evaluation determines the natural language utterance is not part of an ongoing conversation path, creating a new execution plan comprising an ordered list of the one or more executable actions(optional limitation).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify the combination of Lu and Mishra with the LLM system of Mishra, as it helps improve accuracy(Col 3, Ln 11-22).
Regarding Claim 12:
The combination of Lu and Mishra teaches the system of claim 8, and Lu teaches wherein: the operation of invoking one or more states configured to execute the action type comprises: invoking a first state to identify that the executable action has not yet been executed to generate a response, and invoking a second state to determine whether one or more parameters are available for the executable action(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. Pg 5, 4.1 Module Inventory, Para 2, Knowledge Retrieval (Mkr): This module retrieves additional background knowledge crucial for tackling complex problems.);
the operation of executing the executable action using the asset to obtain the output comprises invoking a third state to generate the output(Pg 6, Para 10, Ln 1-4, Solution Generator (Msg): This module generates a detailed solution to the input query using all the cached information. Employing a chain-of-thought prompting approach [53], it ensures coherent and well-structured responses. The planner can directly employ this module instead of other functional modules if it can solve the query independently, especially for simpler ones. See Pg 1, Fig 1, and Pg 3, Fig 2);
and the first state, the second state, and the third state are different from one another(See Pg 1, Fig 1, and Pg 3, Fig 2).
Regarding Claim 15:
Lu teaches generating, by a first generative artificial intelligence model, a list comprising one or more executable actions based on a first prompt comprising a natural language utterance provided by a user(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2);
creating an execution plan comprising the one or more executable actions(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2);
executing the execution plan, wherein executing the execution plan comprises performing an iterative process for each executable action of the one or more executable actions, and wherein the iterative process comprises: identifying an action type for an executable action, invoking one or more states configured to execute the action type, and executing, by the one or more states, the executable action using an asset to obtain an output(Pg 4, generative Framework, Para 2, Ln 1 through Pg 5, Para 1, Ln 5, given the input query x0, the module inventory M, and constraints G, the natural language planner P selects a set of modules that can be executed sequentially to answer the query via generating a program in a natural-language-like format. The module inventory M consists of a set of pre-built modules: {Mi}, each corresponding to a tool of various types (Table 2). G are the constraints for the plan generation, for example, the concurrent relations and sequence orders of modules. In our work, the planner P is an LLM prompted to generate a sequence of 4 module names in a few-shot setup. See Pg 3, Fig 2. Pg 5, Para 2, Ln 1-3, Given the generated plan, the corresponding modules for each step are then executed sequentially. Pg 5, Para 3, Ln 1-3, where xt−1 is the input for the current module Mt, and ct−1 is the cached information (e.g., image semantics, retrieved knowledge, generated programs) resulting from the execution history of modules. Pg 5, 4.1 module inventory, Knowledge retrieval, Bing search);
generating a second prompt based on the output obtained from executing each of the one or more executable actions(Pg 5, Para 3, Ln 1-3, where xt−1 is the input for the current module Mt, and ct−1 is the cached information (e.g., image semantics, retrieved knowledge, generated programs) resulting from the execution history of modules. Pg 5, Para 4, Ln 1-5, The update_input and update_cache functions are hand-designed for each Mt. Specifically, update_input is applied to elements in the input query, including the question, table context, and image. These elements are updated after module execution. update_cache corresponds to the generation of new information, such as a description for the input image or retrieved knowledge from external resources. Finally, the response r to the query is generated by the last module M);
and generating, by a second generative artificial intelligence model, a response to the natural language utterance based on the second prompt(Pg 5, Para 4, Ln 1-5, The update_input and update_cache functions are hand-designed for each Mt. Specifically, update_input is applied to elements in the input query, including the question, table context, and image. These elements are updated after module execution. update_cache corresponds to the generation of new information, such as a description for the input image or retrieved knowledge from external resources. Finally, the response r to the query is generated by the last module M. Pg 3, Fig 2, solution generator and answer generator).
Lu does not explicitly teach one or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising.
In the same field of AI agents, Mishra teaches one or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising(Col 53, Ln 62-67, processors, memory, instructions).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify Lu with the computer components of Mishra, as it provides an environment for the system to be realized(Col 53, Ln 53-67).
Regarding Claim 16:
Claim 16 contains similar limitations as Claim 9, and is therefore rejected for the same reasons.
Regarding Claim 18:
Claim 18 contains similar limitations as Claim 12, and is therefore rejected for the same reasons.
Claim(s) 10-11 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Lu and Mishra as applied to claim 8 above, and further in view of Sharifi.
Regarding Claim 10:
The combination of Lu and Mishra teaches the system of claim 8, but does not teach wherein the iterative process further comprises: determining whether one or more parameters are available for the executable action; when the one or more parameters are available, invoking the one or more states and executing the executable action based on the one or more parameters; and when the one or more parameters for the executable action are not available, obtaining the one or more parameters that are not available and then invoking the one or more states and executing the executable action based on the one or more parameters.
In the same field of AI agents, Sharifi teaches wherein the iterative process further comprises: determining whether one or more parameters are available for the executable action(Para [0043], Ln 1-10, system determines, based on processing the recognition that corresponds to the spoken utterance, that the spoken utterance is ambiguous. The system determines that the spoken utterance is ambiguous based on determining that the recognition is interpretable as requesting performance of a first particular action exclusively and also being interpretable a second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions);
when the one or more parameters are available, invoking the one or more states and executing the executable action based on the one or more parameters(Para [0049], Ln 1-7, At block 264, the system processes the further user input to determine to perform the first particular action instead of the second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions);
and when the one or more parameters for the executable action are not available, obtaining the one or more parameters that are not available and then invoking the one or more states and executing the executable action based on the one or more parameters(Para [0044], Ln 1-7, At block 258, the system determines to provide an enhanced clarification prompt that renders additional output that is presented instead of or in addition to natural language. Para [0049], Ln 1-7, At block 264, the system processes the further user input to determine to perform the first particular action instead of the second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify the combination of Lu and Mishra with the disambiguation of Sharifi, as it improves user convenience(Para [0006], Ln 24-32).
Regarding Claim 11:
The combination of Lu and Sharifi teaches the system of claim 10, but does not teach wherein the operation of obtaining the one or more parameters comprises generating a natural language request to the user to obtain the one or more parameters for the executable action, and receiving a response from the user comprising the one or more parameters.
In the same field of AI agents Sharifi teaches wherein the operation of obtaining the one or more parameters comprises generating a natural language request to the user to obtain the one or more parameters for the executable action, and receiving a response from the user comprising the one or more parameters(Para [0044], Ln 1-7, At block 258, the system determines to provide an enhanced clarification prompt that renders additional output that is presented instead of or in addition to natural language. Para [0049], Ln 1-7, At block 264, the system processes the further user input to determine to perform the first particular action instead of the second particular action. Para [0050], Ln 1-7, For some of these forms of further user input, the system can compare one or more properties indicated by the further user input to one or more properties associated with the candidate responsive actions).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify the combination of Lu, Mishra and Sharifi with the disambiguation of Sharifi, as it improves user convenience(Para [0006], Ln 24-32).
Regarding Claim 17:
Claim 17 contains similar limitations as Claim 11 and is therefore rejected for the same reasons.
Claim(s) 13-14 and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination Lu and Mishra as applied to claim 8 above, and further in view of Liang.
Regarding Claim 13:
The combination of Lu and Mishra teaches the system of claim 8, but does not teach wherein the operation of generating the list comprises selecting the one or more executable actions from a list of candidate agent actions that are determined by using a semantic index, and wherein the operation of creating the execution plan further comprises: identifying, based at least in part on metadata associated with candidate agent actions within the list of candidate agent actions, the one or more executable actions that provide information or knowledge for generating the response to the natural language utterance; and generating a structured output for the execution plan by creating an ordered list of the one or more executable actions and a set of dependencies among the one or more executable actions.
In the same field of AI agents, Liang teaches wherein the operation of generating the list comprises selecting the one or more executable actions from a list of candidate agent actions that are determined by using a semantic index(Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture),
and wherein the operation of creating the execution plan further comprises: identifying, based at least in part on metadata associated with candidate agent actions within the list of candidate agent actions, the one or more executable actions that provide information or knowledge for generating the response to the natural language utterance(Pg 18, 4.2, Para 1, Ln 1-6, In this study, we emphasize the importance of composition instructions for composing multiple APIs to complete complex user instructions. This is demonstrated through subsequent ablation studies. Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture);
and generating a structured output for the execution plan by creating an ordered list of the one or more executable actions and a set of dependencies among the one or more executable actions(Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture. Pg 19, Fig 11, code for generating slides created based on API specifications in the portion of Fig 11 that is on Pg 18. Pg 20, Para 2, Ln 1-7, The process of decomposing user instructions may vary depending on the API design being used. Thus, it is essential for API developers to provide composition instructions to guide API usage. We have created composition instructions for three APIs: insert_text, select_title, and select_content. The composition instructions for insert_text specify that the content often contains multiple sentences. For select_title and select_content, the composition instructions specify the order in which these APIs should be used with other APIs, such as inserting and deleting text in a text box).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify the combination of Lu and Mishra with the task completion system of Liang, as it improves compatibility with foundation models, improving performance(Pg 1, Abstract, Ln 10-18).
Regarding Claim 14:
The combination of Lu, Mishra and Liang teaches the system of claim 13, but does not teach wherein the iterative process further comprises determining that one or more dependencies exist between the executable action and at least one other executable action of the one or more executable actions based on the set of dependencies among the one or more executable actions, and wherein the executable action is executable sequentially in accordance with the one or more dependencies determined to exist between the executable action and the at least one other executable action.
In the same field of AI agents, Liang teaches wherein the iterative process further comprises determining that one or more dependencies exist between the executable action and at least one other executable action of the one or more executable actions based on the set of dependencies among the one or more executable actions, and wherein the executable action is executable sequentially in accordance with the one or more dependencies determined to exist between the executable action and the at least one other executable action(Pg 18, 4.2, Para 2, Ln 1-5, The API platform for Power Point consists of a list of APIs, each accompanied by its name, parameter list, description, and composition instructions, as detailed in Section 2.3. These properties are summarized in a single paragraph for ease of understanding. We highlight the composition rules with light green. See Pg 18, 4.2, API documentations picture. Pg 19, Fig 11, code for generating slides created based on API specifications in the portion of Fig 11 that is on Pg 18. Pg 20, Para 2, Ln 1-7, The process of decomposing user instructions may vary depending on the API design being used. Thus, it is essential for API developers to provide composition instructions to guide API usage. We have created composition instructions for three APIs: insert_text, select_title, and select_content. The composition instructions for insert_text specify that the content often contains multiple sentences. For select_title and select_content, the composition instructions specify the order in which these APIs should be used with other APIs, such as inserting and deleting text in a text box).
It would have been obvious for one skilled in the art, at the effective time of filling, to modify the combination of Lu, Mishra and Liang with the task completion system of Liang, as it improves compatibility with foundation models, improving performance(Pg 1, Abstract, Ln 10-18).
Regarding Claim 19:
Claim 19 contains similar limitations as Claim 13 and is therefore rejected for the same reasons.
Regarding Claim 20:
Claim 20 contains similar limitations as Claim 14 and is therefore rejected for the same reasons.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Shi et al. (US 12586578 B1).
Generation of plan for executing user intent using language models. Prior art to instant application, but not prior to the provisional application the instant application claims priority to.
Amatriain-Rubio (US 20250005288 A1).
Generation of multistep plan for executing user intent using language models.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALEXANDER G MARLOW whose telephone number is (571)272-4536. The examiner can normally be reached Monday - Thursday 10:00 am - 8:00 pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Richmond Dorvil can be reached at (571)272-7602. 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.
/ALEXANDER G MARLOW/ Assistant Examiner, Art Unit 2658
/RICHEMOND DORVIL/ Supervisory Patent Examiner, Art Unit 2658
Prosecution Insights