Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
Claims 1-20 are pending. Claims 1, 17, and 20 are independent.
Claims 2-16 depend from Claim 1.
Claims 18-19 depend from Claim 17.
This Application was published as U.S. 2025/0181846.
Response to Amendment
Examiner thanks Applicant for response filed on 31 Dec 2025 which has been correspondingly accepted and considered in this office action. Claims 1-20 are pending.
Response to Arguments
Applicant's arguments filed 31 Dec 2025 have been fully considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
While Applicant arguments are moot, it is necessary to address the following relevant arguments below:
With regards to 35 USC § 103:
Claims 1, 17, and 20:
Applicant argues that Jia et al. (Jia, Donggang, et al. "Voice: Visual oracle for interaction, conversation, and explanation.” arXiv:2304.04083v1, 8 Apr 2023 pp. 1-18 hereinafter Jia) “fails to teach or suggest "instantiating ... a communication session handler," much less that the instantiation is "in response to the selection of the communication session handler class," with the selection being "based at least in part on contextual information associated with the initial query" as is now recited in amended independent claim 1
MPEP 2111 requires claims must be given their broadest reasonable interpretation in light of the specification. The broadest reasonable interpretation of instantiation is a process to create an object or instance of a specific class, were to instantiate a communication session handler is to create a mechanism to control or handle the session with the communication between entities. Furthermore, applicant defines in the specification “a communication service (such as a chatbot or interactive user platform)” (Par [0009]) which means a reasonable interpretation for the communication service as claimed in claims 1, 17, and 20 is a chatbot or a chatbot management system, and a communication session handler class can be reasonably interpreted as a communication session with a chatbot where the chatbot is able to communicate with the user and the chatbot system, and the particular handler class is the particular chatbot chosen to handle the communication.
Here, each session handler can instantiate and communicate with itself, user, and the chatbot management system to create a process where the object of the specific class is the conversation with the user, chatbot, and the chatbot management system. Then, Jia can instantiate its own specific class consisting of its own bots or pack of bots to communicate with the communication session handler or itself, for use in LLM prompt generation to accomplish the specific visualization task. (Jia Fig 2, page 6) Thus, Jia teaches “instantiating … a communication session handler … for use in prompt generation” (Applicant remarks page 11)
While the above shows how Jia teaches the claimed limitation, another reference is added that better describes how the communication service or chatbot interacts with the DMS for all the amended claim limitations.
Claim 8:
Applicant argues that “Jia does not describe "a response to [a] prompt" that is "[received], by the communication service of the DMS from the LLM," as recited in amended independent claim 1 where "the response includes an indication of whether to call the one or more functions," as recited in dependent claim 8.” (Applicant arguments page 13)
MPEP 2111 requires claims must be given their broadest reasonable interpretation in light of the specification. The broadest reasonable interpretation of “receiving, by the communication service of the DMS from the LLM, a response to the prompt,” as stated in claim 1 is for a response from the LLM to be received by the communication service or chatbot after the LLM was prompted.
In claim 8, the broadest reasonable interpretation for “the prompt includes one or more functions associated with the communication session handler class” is that the LLM prompt includes one or more functions that are associated with the communication session handler class. The claim does not define what functions are associated with the communication session handler class, so any function that is associated with the communication session handler class will suffice. The broadest reasonable interpretation for “the response includes an indication of whether to call the one or more functions, and” is that the LLM response includes any indication, where an indication is a fact that shows something exists or may happen, and the functions as previously described are able to be called or executed.
Here, Applicant acknowledges that “Jia describes a system controlled through voice, as well as prompted or prompt-based GPT models and outputs for different bots” (Applicant arguments page 13) As is understood in the art, a reasonable interpretation for providing a prompt to an LLM such as GPT is to get a response from the LLM. Furthermore, Jia teaches as previously discussed that the chatbot is the communication service of the DMS, and that the chatbots communicate with the LLM or GPT-model to receive the response from the LLM. Thus, Jia teaches “receiving, by the communication service of the DMS from the LLM, a response to the prompt,”
Here, claim 8 does not define what functions are associated with the communication session handler class, nor does the claim define an indication of whether to call the functions. As discussed in the 1 Oct 2025 office action, Jia Fig 2 describes functions associated with the communication session handler class. For example, the functions can be the Explorer bot calling the animated visual transformation function, as depicted in Jia Fig 2. The indication whether to call this function or not as described in the 1 Oct 2025 is the response to the user question or query. Thus, Jia teaches “the response includes an indication of whether to call the one or more functions, and.”
Thus, for all the reasons stated above the arguments must be addressed, even though applicant arguments are moot due to the amended claims.
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.
Claims 1, 5-7, 12-14, 17 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Liang et al.(US2021/0144107 hereinafter Liang) in view of Jia et al. (Jia, Donggang, et al. "Voice: Visual oracle for interaction, conversation, and explanation.” arXiv:2304.04083v1, 8 Apr 2023 pp. 1-18 hereinafter Jia)
With regards to claim 1, Liang teaches:
A method, comprising: receiving, by a communication service of a data management system (DMS) and via a user interface, [Liang Fig 1 teaches data processing (100) or management system that includes a communication service (111) that receives data from user I/O interface (115)] an initial query for a communication session [Liang Fig 8 item 805 teaches receiving user input via chat service interface (Fig 2a item 237, Par [0109]) where Fig 2a is a detailed embodiment of system 100 using chatbot orchestration system (Par [0039]) and communication service (111) “may further allow for a full network protocol stack, enabling communication over network 250 to groups of chatbot orchestration system 201, user system 235, chatbots 241, search engine(s) 238, discovery service(s) 239, human support service(s) 240 and other data processing systems 100 linked together through communication channels of network 250” (Par [0042])]
selecting, by the communication service of the DMS and based at least in part on contextual information associated with the initial query, a communication session handler class from a plurality of communication session handler classes supported by the DMS; [Liang Fig 8 teaches in step 807 that “chat service 225 receiving the user input may analyze the user input for intents, entities, content, tone or sentiment and … analysis module 205 may perform natural language processing using a natural language processor 261 and/or content/artifact analyzer 291 to understand the user input, the context and content thereof” (Par [0109], Fig 2A-2B) which is based on contextual information associated with the initial query. Furthermore, “one or more chatbots 241 selected by orchestrator service 217” (Par [0068]) where chatbot service is part of chatbot orchestration system (201) or session handler class where there are a plurality of chatbots]
instantiating, by the communication service of the DMS in response to the selection of the communication session handler class, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are instantiating a communication handler of the selected communication handler class] generating, by the communication service of the DMS using the communication session handler,
transmitting, by the communication service of the DMS,
receiving, by the communication service of the DMS
transmitting, by the communication service of the DMS to the user interface, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
With regards to claim 1, Liang fails to teach:
an initial query for a communication session with a large language model (LLM);
a communication session handler of the selected communication session handler class for use in prompt generation;
generating, a prompt for the LLM based at least in part on the initial query; transmitting, the prompt to the LLM;
receiving, from the LLM, a response to the prompt; and
transmitting, a message that is based at least in part on the response received from the LLM.
With regards to claim 1, Jia teaches:
an initial query for a communication session with a large language model (LLM); [Jia Fig 2 teaches user provides initial query to a manager of a dialogue system in a DMS which processes the data using GPT-3 mode and GPT-4 models which are LLMs, where manager initiates communication session]
a communication session handler of the selected communication session handler class for use in prompt generation; [Jia Fig 2 teaches Manager instantiating the selected GPT-4 model by passing the task to the selected model (par 3 page 5)]
generating, a prompt for the LLM based at least in part on the initial query; [Jia teaches prompted chatbots (Par 4.2 page 8) where GPT-4 model or communication session handler is prompted according to initial query (see Table 1)]
transmitting, the prompt to the LLM; [Jia Fig 2 Par 4.2 page 8]
receiving, from the LLM, a response to the prompt; and [Jia Table 1 Par 4.2 page 8 where response to the prompt is the output]
transmitting, a message that is based at least in part on the response received from the LLM. [Jia Fig 2 teaches response is a visualization and audio response to the user interface]
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system as taught by Liang with the large language model system using a pack of bots as taught by Jia. The motivation to combine the teachings of Liang with Jia is because Jia teaches “highly modular and easily customizable, and has few dependencies on particular proprietary technology. This means that, for instance, we can seamlessly integrate new bots into our pack-of-bots architecture without requiring any modifications to existing bots“ (Par 7, page 14) which increases the capabilities of the invention of Liang to integrate new bots into the system to provide better user experience]
With regards to claim 5, Liang in view of Jia teaches:
All the limitations of claim 1
further comprising: receiving, by the communication service of the DMS and via the user interface, a request for the communication session; [Liang Fig 1 teaches data processing (100) or management system that includes a communication service (111) that receives data from user I/O interface (115). Liang Fig 8 item 805 teaches receiving user input via chat service interface (Fig 2a item 237, Par [0109]) where Fig 2a is a detailed embodiment of system 100 using chatbot orchestration system (Par [0039]) and communication service (111) “may further allow for a full network protocol stack, enabling communication over network 250 to groups of chatbot orchestration system 201, user system 235, chatbots 241, search engine(s) 238, discovery service(s) 239, human support service(s) 240 and other data processing systems 100 linked together through communication channels of network 250” (Par [0042])]
causing, by the communication service of the DMS and at the user interface in response to the request for the communication session, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) and Liang Fig 2b teaches topic identifier (292) that is part of the content analyzer (291) which are caused to be presented to the user] presentation of a plurality of topics that correspond with respective communication sessions handler classes of the plurality of communication session handler classes; and [Jia Fig 2 shows VOICE framework where “visual oracle, capable of responding to any inquiry with both a verbal and visual answer, focusing on a specific complex object, such as the structure of a biological system. The system will be controlled solely through voice” (Par 3 Page 5) where system response to user request and plurality of topics are visual depicted for the user] receiving, by the communication service of the DMS and via the user interface, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user] an indication of a selected topic of the plurality of topics, wherein the selected communication session handler class corresponds to the selected topic. [Jia Fig 2 teaches that for example “The user might ask a question about the content of what they currently see, which is passed on to the Encyclopedia bot. If the user wants to request minor visualization modifications such as changing a viewpoint or manipulating a clipping plane, the Manager bot passes on the task to the Explorer bot or the Cutting plane animation process” (Par 3 page 5)]
With regards to claim 6, Liang in view of Jia teaches:
All the limitations of claim 1
further comprising: receiving, by the communication service of the DMS and via the user interface, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
a second query for the communication session; [Jia teaches “If the user requests to see another object or see the scene from a different level of detail, the Manager bot passes the task to the Pilot bot DMS receiving another request by the user” (Par 3 page 5) which is a second query from the user] generating by the communication service of the DMS using the communication session handler, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
a second prompt for the LLM based at least in part on the second query, wherein the second prompt is based at least in part on the second query and further based at least in part on the initial query, the response previously received from the LLM, or both; [Jia teaches each chatbot generates prompt (Par 4.2 page 8) and output (Table 1) which is based on second query (i.e. Pilot bot) and in part of first query where “Pilot bot is designed to detect what the user wants to see in the model” (Par 4.2 page 8) where the model is based in part on the initial query]
transmitting, by the communication service of the DMS, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
the second prompt to the LLM; [Jia Fig 2 Par 4.2 page 8]
receiving, from the LLM, a second response to the second prompt; and [Jia Table 1 Par 4.2 page 8 where response to the prompt is the output]
transmitting, by the communication service of the DMS to the user interface, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
a second message that is based at least in part on the second response received from the LLM. [Jia Fig 2 teaches response is a visualization and audio response to the user interface]
With regards to claim 7, Liang in view of Jia teaches:
All the limitations of claim 6
further comprising: storing, by the communication service of the DMS, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
the initial query, the response previously received from the LLM, or both in a database associated with the DMS, wherein the second prompt being based at least in part on the initial query, the response previously received from the LLM, or both is based at least in part on the storing in the database. [Jia Table 1 outlines query from the user and response from the assigned bot. While Jia does not specifically mention storing the table in a database, it would be obvious to one of ordinary skill in the art at the time of applicant’s filing to create and store data in a database from a data table. (see Taylor, A. G. (2003). SQL For Dummies (5th ed.). Wiley)]
With regards to claim 12, Liang in view of Jia teaches:
All the limitations of claim 1
wherein generating the prompt comprises: including in the prompt, by the communication service of the DMS using the communication session handler, an indication of one or more information sources for the LLM to use to generate the response. [Jia Fig 2 teaches VOICE framework which is visual and indicates one or more information sources for the LLM to use to generate the response and where Jia teaches chatbots are the communication service]
With regards to claim 13, Liang in view of Jia teaches:
All the limitations of claim 1
wherein the message comprises the response. [Jia Fig 2 teaches response is a visualization and audio response to the user interface]
With regards to claim 14, Liang in view of Jia teaches:
All the limitations of claim 1
further comprising: including in the message, by the communication service of the DMS, one or more graphics provided by the communication session handler. [Jia Fig 2 teaches response is a visualization and audio response to the user interface, where Jia teaches chatbots are the communication service]
With regards to claim 17, Liang teaches:
An apparatus, comprising: one or more memories storing processor-executable code; and [Liang Fig 1 teaches “memory 105 can include any suitable volatile or non-volatile computer-readable storage media and may comprise firmware or other software programmed into the memory 105” (Par [0034])]
one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the apparatus to: [Liang Fig 1 teaches processors (103) (Par [0033-34])]
receive, by a communication service of a data management system (DMS) and via a user interface, [Liang Fig 1 teaches data processing (100) or management system that includes a communication service (111) that receives data from user I/O interface (115)]
an initial query for a communication session [Liang Fig 8 item 805 teaches receiving user input via chat service interface (Fig 2a item 237, Par [0109]) where Fig 2a is a detailed embodiment of system 100 using chatbot orchestration system (Par [0039]) and communication service (111) “may further allow for a full network protocol stack, enabling communication over network 250 to groups of chatbot orchestration system 201, user system 235, chatbots 241, search engine(s) 238, discovery service(s) 239, human support service(s) 240 and other data processing systems 100 linked together through communication channels of network 250” (Par [0042])]
select, by the communication service of the DMS and based at least in part on contextual information associated with the initial query, a communication session handler class from a plurality of communication session handler classes supported by the DMS; [Liang Fig 8 teaches in step 807 that “chat service 225 receiving the user input may analyze the user input for intents, entities, content, tone or sentiment and … analysis module 205 may perform natural language processing using a natural language processor 261 and/or content/artifact analyzer 291 to understand the user input, the context and content thereof” (Par [0109], Fig 2A-2B) which is based on contextual information associated with the initial query. Furthermore, “one or more chatbots 241 selected by orchestrator service 217” (Par [0068]) where chatbot service is part of chatbot orchestration system (201) or session handler class where there are a plurality of chatbots]
instantiate, by the communication service of the DMS in response to the selection of the communication session handler class, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are instantiating a communication handler of the selected communication handler class]
generate, by the communication service of the DMS using the communication session handler,
transmit, by the communication service of the DMS,
receive, by the communication service of the DMS
transmit, by the communication service of the DMS to the user interface, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
With regards to claim 17, Liang fails to teach:
an initial query for a communication session with a large language model (LLM);
a communication session handler of the selected communication session handler class for use in prompt generation;
generate, a prompt for the LLM based at least in part on the initial query; transmit, the prompt to the LLM;
receive, from the LLM, a response to the prompt; and
transmit, a message that is based at least in part on the response received from the LLM.
With regards to claim 17, Jia teaches:
an initial query for a communication session with a large language model (LLM); [Jia Fig 2 teaches user provides initial query to a manager of a dialogue system in a DMS which processes the data using GPT-3 mode and GPT-4 models which are LLMs, where manager initiates communication session]
a communication session handler of the selected communication session handler class for use in prompt generation; [Jia Fig 2 teaches Manager instantiating the selected GPT-4 model by passing the task to the selected model (par 3 page 5)]
generating, a prompt for the LLM based at least in part on the initial query; [Jia teaches prompted chatbots (Par 4.2 page 8) where GPT-4 model or communication session handler is prompted according to initial query (see Table 1)]
transmitting, the prompt to the LLM; [Jia Fig 2 Par 4.2 page 8]
receiving, from the LLM, a response to the prompt; and [Jia Table 1 Par 4.2 page 8 where response to the prompt is the output]
transmitting, a message that is based at least in part on the response received from the LLM. [Jia Fig 2 teaches response is a visualization and audio response to the user interface]
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system as taught by Liang with the large language model system using a pack of bots as taught by Jia. The motivation to combine the teachings of Liang with Jia is because Jia teaches “highly modular and easily customizable, and has few dependencies on particular proprietary technology. This means that, for instance, we can seamlessly integrate new bots into our pack-of-bots architecture without requiring any modifications to existing bots“ (Par 7, page 14) which increases the capabilities of the invention of Liang to integrate new bots into the system to provide better user experience]
With regards to claim 20, Liang teaches:
A non-transitory computer-readable medium storing code, the code comprising instructions executable by one or more processors to: [Liang teaches “program code configured to implement the orchestrated chat services 225, including the execution of program code directed toward one or more functions or tasks of the natural language classifier 211, and orchestrator service 217” (Par [0067])]
receive, by a communication service of a data management system (DMS) and via a user interface, [Liang Fig 1 teaches data processing (100) or management system that includes a communication service (111) that receives data from user I/O interface (115)]
an initial query for a communication session [Liang Fig 8 item 805 teaches receiving user input via chat service interface (Fig 2a item 237, Par [0109]) where Fig 2a is a detailed embodiment of system 100 using chatbot orchestration system (Par [0039]) and communication service (111) “may further allow for a full network protocol stack, enabling communication over network 250 to groups of chatbot orchestration system 201, user system 235, chatbots 241, search engine(s) 238, discovery service(s) 239, human support service(s) 240 and other data processing systems 100 linked together through communication channels of network 250” (Par [0042])]
select, by the communication service of the DMS and based at least in part on contextual information associated with the initial query, a communication session handler class from a plurality of communication session handler classes supported by the DMS; [Liang Fig 8 teaches in step 807 that “chat service 225 receiving the user input may analyze the user input for intents, entities, content, tone or sentiment and … analysis module 205 may perform natural language processing using a natural language processor 261 and/or content/artifact analyzer 291 to understand the user input, the context and content thereof” (Par [0109], Fig 2A-2B) which is based on contextual information associated with the initial query. Furthermore, “one or more chatbots 241 selected by orchestrator service 217” (Par [0068]) where chatbot service is part of chatbot orchestration system (201) or session handler class where there are a plurality of chatbots]
instantiate, by the communication service of the DMS in response to the selection of the communication session handler class, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are instantiating a communication handler of the selected communication handler class]
generating, by the communication service of the DMS using the communication session handler,
transmitting, by the communication service of the DMS,
receiving, by the communication service of the DMS
transmitting, by the communication service of the DMS to the user interface, [Liang teaches chatbot orchestration system (201) that performs the tasks of “identifying one or more applicable chatbots 241 to respond to user input; requesting a response from one or more registered chatbot 241 and delivering chatbot 241 responses to user system(s) 235” (Par [0067]) which are generating, transmitting, receiving, and transmitting data from the chatbots, DMS, and user]
With regards to claim 20, Liang fails to teach:
an initial query for a communication session with a large language model (LLM);
a communication session handler of the selected communication session handler class for use in prompt generation;
generate, a prompt for the LLM based at least in part on the initial query; transmit, the prompt to the LLM;
receive, from the LLM, a response to the prompt; and
transmit, a message that is based at least in part on the response received from the LLM.
With regards to claim 20, Jia teaches:
an initial query for a communication session with a large language model (LLM); [Jia Fig 2 teaches user provides initial query to a manager of a dialogue system in a DMS which processes the data using GPT-3 mode and GPT-4 models which are LLMs, where manager initiates communication session]
a communication session handler of the selected communication session handler class for use in prompt generation; [Jia Fig 2 teaches Manager instantiating the selected GPT-4 model by passing the task to the selected model (par 3 page 5)]
generating, a prompt for the LLM based at least in part on the initial query; [Jia teaches prompted chatbots (Par 4.2 page 8) where GPT-4 model or communication session handler is prompted according to initial query (see Table 1)]
transmitting, the prompt to the LLM; [Jia Fig 2 Par 4.2 page 8]
receiving, from the LLM, a response to the prompt; and [Jia Table 1 Par 4.2 page 8 where response to the prompt is the output]
transmitting, a message that is based at least in part on the response received from the LLM. [Jia Fig 2 teaches response is a visualization and audio response to the user interface]
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system as taught by Liang with the large language model system using a pack of bots as taught by Jia. The motivation to combine the teachings of Liang with Jia is because Jia teaches “highly modular and easily customizable, and has few dependencies on particular proprietary technology. This means that, for instance, we can seamlessly integrate new bots into our pack-of-bots architecture without requiring any modifications to existing bots“ (Par 7, page 14) which increases the capabilities of the invention of Liang to integrate new bots into the system to provide better user experience]
Claims 2-3, 8-11, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Liang et al.(US2021/0144107) in view of Jia et al. (Jia, Donggang, et al. "Voice: Visual oracle for interaction, conversation, and explanation.” arXiv:2304.04083v1, 8 Apr 2023 pp. 1-18) in further view of Bielke et al. (US2025/0131147 hereinafter Bielke)
With regards to claim 2, Liang in view of Jia teaches:
All the limitations of claim 1
With regards to claim 2, Liang in view of Jia teaches:
further comprising: transmitting, by the DMS to the user interface, a notification, wherein the initial query is responsive to the notification, and wherein the contextual information is based at least in part on the notification.
With regards to claim 2, Bielke teaches:
further comprising: transmitting, by the DMS to the user interface, a notification, wherein the initial query is responsive to the notification, and wherein the contextual information is based at least in part on the notification. [Bielke Fig 1 teaches “artificial intelligence orchestrator 114 uses event data to notify users of significant events, such as system failures, maintenance alerts, and/or upcoming events” (Par [0039])
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system and LLMs as taught by Liang and Jia with the artificial intelligence orchestrator notification system as taught by Bielke. The motivation to combine the teachings of Liang and Jia with Bielke is because Bielke’s system “sends alerts when specific conditions or thresholds are met in the event data, and access past data to help users understand patterns or make informed decisions” (Par [0039]) which increases the capabilities of the invention of Liang and Jia to better understand user’s needs to integrate them into the system to better enhance user experience]
With regards to claim 3, Liang in view of Jia and Bielke teaches:
All the limitations of claim 2
further comprising: identifying an event associated with a customer account associated with the user interface, wherein the notification is responsive to identification of the event. [Bielke teaches a system that manages user historical data which can include customer accounts where “artificial intelligence orchestrator 114 uses event data to notify users of significant events, such as system failures, maintenance alerts, and/or upcoming events” (Par [0039])]
With regards to claim 8, Liang in view of Jia teaches:
All the limitations of claim 1
wherein: the prompt includes one or more functions associated with the communication session handler class, [Jia Fig 2 teaches VOICE framework which is based on voice and visual response to user inquires (Par 3 page 8)]
the response includes an indication of whether to call the one or more functions, and [Jia Par 3, Fig 2, and Table 1 teaches response to user questions indicating whether to call the one or more functions by waiting for user to provide a verbal response]
With regards to claim 8, Liang in view of Jia fails to teach:
the one or more functions cause the DMS to trigger one or more respective actions for a customer account associated with the user interface.
With regards to claim 8, Bielke teaches:
the one or more functions cause the DMS to trigger one or more respective actions for a customer account associated with the user interface. [Bielke teaches a system that manages user historical data which can include customer accounts where “artificial intelligence orchestrator 114 uses event data to notify users of significant events, such as system failures, maintenance alerts, and/or upcoming events” (Par [0039]) where a notification is a trigger one or more respective actions for a customer account associated with the user.
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system and LLMs as taught by Liang and Jia with the artificial intelligence orchestrator notification system as taught by Bielke. The motivation to combine the teachings of Liang and Jia with Bielke is because Bielke’s system “sends alerts when specific conditions or thresholds are met in the event data, and access past data to help users understand patterns or make informed decisions” (Par [0039]) which increases the capabilities of the invention of Liang and Jia to better understand user’s needs to integrate them into the system to better enhance user experience]
With regards to claim 9, Liang in view of Jia and Bielke teaches:
All the limitations of claim 8
wherein: the response indicates for the DMS to call a function of the one or more functions; and [Jia Par 3, Fig 2, and Table 1 teaches response to user questions indicating whether to call the one or more functions by waiting for user to provide a verbal response]
the message includes an indication that the DMS intends to call the function. [Jia Par 3, Fig 2, and Table 1 teaches the message is a visual or visualization response to the user, and indication that the DMS intends to call the function is the attempt to perform the function]
With regards to claim 10, Liang in view of Jia and Bielke teaches:
All the limitations of claim 9
further comprising: based at least in part on the response indicating for the DMS to call the function, calling the function by the DMS. [Jia Par 3, Fig 2, and Table 1 teaches performing the function based on user verbal response]
With regards to claim 11, Liang in view of Jia and Bielke teaches:
All the limitations of claim 10
further comprising: receiving, by the DMS and via the user interface, a command to perform the function in response to the message, wherein calling the function is based at least in part on the command. [Jia Par 3, Fig 2, and Table 1 teaches performing the function based on user verbal response]
Claim 18 is an apparatus claim with limitations corresponding to the limitations of method Claim 2 and is rejected under similar rationale.
Claim 19 is an apparatus claim with limitations corresponding to the limitations of method Claim 3 and is rejected under similar rationale.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Liang et al.(US2021/0144107) in view of Jia et al. (Jia, Donggang, et al. "Voice: Visual oracle for interaction, conversation, and explanation.” arXiv:2304.04083v1, 8 Apr 2023 pp. 1-18) in further view of Gulati et al.(US2025/0138910 hereinafter Gulati)
With regards to claim 4, Liang in view of Jia teaches:
All the limitations of claim 1
With regards to claim 4, Liang in view of Jia fails to teach:
further comprising: identifying one or more keywords in the initial query, wherein the contextual information is based at least in part on the one or more keywords.
With regards to claim 4, Gulati teaches:
further comprising: identifying one or more keywords in the initial query, wherein the contextual information is based at least in part on the one or more keywords. [Gulati teaches “the data request, or keywords thereof, may be compared to the intents (e.g., in the form of queries or keywords) included in a context template and/or context brief” (Par [0063])]
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system and LLMs as taught by Liang and Jia with contextual information based on user intent as taught by Gulati. The motivation to combine the teachings of Liang and Jia with Gulati is because Gia teaches context that “enables the LLM to generate a response that is more suitable or relevant for a user” (Par [004]) which increases the capabilities of the invention of Liang and Jia to integrate context into the system to better enhance user experience]
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Liang et al.(US2021/0144107) in view of Jia et al. (Jia, Donggang, et al. "Voice: Visual oracle for interaction, conversation, and explanation.” arXiv:2304.04083v1, 8 Apr 2023 pp. 1-18) in further view of D’Agostino et al. (US2020/0099633 hereinafter Agostino)
With regards to claim 15, Liang in view of Jia teaches:
All the limitations of claim 1
With regards to claim 15, Liang in view of Jia fails to teach:
further comprising: identifying a user account associated with the user interface; and
instantiating the communication session based at least in part on the user account being authorized by the DMS to communicate with the LLM.
With regards to claim 15, D’Agostino teaches:
further comprising: identifying a user account associated with the user interface; and [D’Agostino Fig 1 teaches “user profile engine 116 to obtain additional information about a particular user profile associated with the received input” (Par [0037])]
instantiating the communication session based at least in part on the user account being authorized by the DMS to communicate with the LLM. [D’Agostino Fig 1 teaches “authentication 162 can be used by the conversational analysis system 102 to identify and/or verify the credentials of the user.”
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system and LLMs as taught by Liang and Jia with authentication of a user account as taught by D’Agostino. The motivation to combine the teachings of Liang and Jia with D’Agostino is because D’Agostino teaches user profile information may be stored or “provide access to financial data 160 associated with the user profile 156, including transactions histories, current account information, stock information associated with the user profile 156, credit and debit cards association with the user profile 156, checking and savings account information, and other similar data” (Par [0037]) which increases the capabilities of the invention of Liang and Jia to integrate context into the system to better enhance user experience]
Claim 16 is rejected under 35 U.S.C. 103 as being unpatentable over Liang et al.(US2021/0144107) in view of Jia et al. (Jia, Donggang, et al. "Voice: Visual oracle for interaction, conversation, and explanation.” arXiv:2304.04083v1, 8 Apr 2023 pp. 1-18) in further view of Ridner et al. (US10496827 hereinafter Ridner)
With regards to claim 16, Liang in view of Jia teaches:
All the limitations of claim 1
With regards to claim 16, Liang in view of Jia fails to teach:
the respective plurality of topics comprise handling of malware, backup operations, restore operations, or a help desk.
With regards to claim 16, Ridner teaches:
the respective plurality of topics comprise handling of malware, backup operations, restore operations, or a help desk. [Ridner Fig 3B teaches “anti-malware software, data backup, encryption of disks (full disk, file based, etc.), operating system patching, and surge protectors. “Anti-malware software” is a program or set of programs that are designed to prevent, search for, detect, and remove software viruses, and other malicious software like worms, trojans, adware, and more. The control “data backup” is the result of copying or archiving files and folders (on-site or off-site) for the purpose of being able to restore them in case of data loss or emergency.” (Fig 3B step 390, Col 24 lines 31-40)
It would be obvious to one of ordinary skill at the time of applicant’s filing to combine the data processing system using the chatbot orchestration system and LLMs as taught by Liang and Jia with the security controls as taught by Ridner. The motivation to combine the teachings of Liang and Jia with Ridner is because Ridner teaches security controls utilized to mitigate and manage cybersecurity threats posed to a component” (Col 4 lines 10-12)) which increases the capabilities of the system taught by Liang and Jia to handle different problems like cybersecurity issues]
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Joseph J Yamamoto whose telephone number is (571)272-4020. The examiner can normally be reached M-F 1000-1800 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, Bhavesh Mehta can be reached at 571-272-7453. 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.
JOSEPH J. YAMAMOTO
Examiner
Art Unit 2656
/BHAVESH M MEHTA/Supervisory Patent Examiner, Art Unit 2656
Prosecution Insights