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 .
Information Disclosure Statement
The information disclosure statement (IDS), submitted on 7/22/2025, is being considered by the examiner.
Objections
The drawings are objected to under 37 CFR 1.83(a). The drawings must show every feature of the invention specified in the claims. Therefore, “named entity”, “a knowledge
graph related to the named entity” must be shown or the feature(s) must be canceled from the claims 1-20. No new matter should be entered.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
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 of this title, 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.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under pre-AIA 35 U.S.C. 103(a) are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims under pre-AIA 35 U.S.C. 103(a), the examiner presumes that the subject matter of the various claims was commonly owned at the time any inventions covered therein were made absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and invention dates of each claim that was not commonly owned at the time a later invention was made in order for the examiner to consider the applicability of pre-AIA 35 U.S.C. 103(c) and potential pre-AIA 35 U.S.C. 102(e), (f) or (g) prior art under pre-AIA 35 U.S.C. 103(a).
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Polleri (WO Patent Application Publication WO 2021/050382), (“Polleri”), in view of Bhasin et al. (US Patent Application Publication US 2025/0124275 A1), (“Bhasin”).
Regarding claim 1, Polleri meets the claim limitations as follow.
A processing system (systems and techniques for machine learning) [Polleri: para. 0002] comprising: one or more memories (memory) [Polleri: para. 0047] comprising processor-executable instructions (executable code) [Polleri: para. 0050]; and one or more processors ((A model composition engine 132 can be executed on one or more computing systems (e.g., infrastructure 128)) [Polleri: para. 0049]; (The infrastructure 128 can include one or more processors) [Polleri: para. 0049]) configured to execute the processor-executable instructions and cause the processing system to ((The model composition engine 132 can output the machine learning application 112 as executable code that be run on various infrastructure 128 through the infrastructure interfaces 124) [Polleri: para. 0050]; (The model execution engine 108 can execute the machine learning application 112 on infrastructure 128 using one or more the infrastructure interfaces 124. The infrastructure 128 can include one or more processors, one or more memories, and one or more network interfaces, one or more buses and control lines that can be used to generate, test, compile, and deploy a machine learning application 112) [Polleri: para. 0051]): receive an input prompt (receiving input) [Polleri: para. 0026; Fig. 10] for machine learning (receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution) [Polleri: para. 0104]; decompose the input prompt (processing input data) [Polleri: para. 0026; Fig. 10] to generate a set of sub-prompts (A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments.) [Polleri: para. 0104]; generate a sequence of requests for sub-prompts of the set of sub-prompts that have sequential dependency ((The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models.) [Polleri: para. 0104; Fig. 1]; (Machine learning models are trained for generating predictive outcomes for code integration requests) [Polleri: para. 0104; Fig. 1] ; (The plurality of instructions may also cause the one or more processors to classify, sequentially by a set of classification models associated with a set of nodes in the tree structure, the input as associated with the class in the plurality of classes. The set of nodes may include one node on each layer of the tree structure and may form a path from the root node to a leaf node. Each node in the set of nodes other than the root node may be a child node of a node on an immediate upper layer of the tree structure.) [Polleri: para. 0217; Fig. 1] – Note: Polleri discloses that the intent of a user can be determined from the one or more text fragments, and the machine learning models are trained for generating predictive outcomes from the requests indicated in the one or more text fragments); generate a parallel request for sub-prompts of the set of sub-prompts that do not have sequential dependency ((The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models) [Polleri: para. 0104; Fig. 1]; (Machine learning models are trained for generating predictive outcomes for code integration requests) [Polleri: para. 0104]; (Intents allow the chatbot to understand what the user wants the chatbot to do. Intents are comprised of permutations of typical user requests and statements, which are also referred to as utterances (e.g., generate a classifier application, determine most efficient employee from employment records, etc.). As used herein, an utterance or a message may refer to a set of words (e.g., one or more sentences) exchanged during a conversation with a chatbot. Intents may be created by providing a name that illustrates some user action (e.g., generate a classifier) and compiling a set of real-life user statements, or utterances that are commonly associated with triggering the action. Because the chatbot's cognition is derived from these intents, each intent may be created from a data set that is robust ( one to two dozen utterances) and varied, so that the chatbot may interpret ambiguous user input) [Polleri: para. 0111; Fig. 1]; based on evaluating the sequence of requests and the parallel request (Intents allow the chatbot to understand what the user wants the chatbot to do. Intents are comprised of permutations of typical user requests and statements, which are also referred to as utterances (e.g., generate a classifier application, determine most efficient employee from employment records, etc.). As used herein, an utterance or a message may refer to a set of words (e.g., one or more sentences) exchanged during a conversation with a chatbot. Intents may be created by providing a name that illustrates some user action (e.g., generate a classifier) and compiling a set of real-life user statements, or utterances that are commonly associated with triggering the action. Because the chatbot's cognition is derived from these intents, each intent may be created from a data set that is robust ( one to two dozen utterances) and varied, so that the chatbot may interpret ambiguous user input) [Polleri: para. 0111], generate an execution plan for using one or more machine learning models to generate a response to the input prompt (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second
input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory.) [Polleri: para. 0104; Fig. 1] – Note: The generated code based on the evaluation of the input requests is the execution plan); and
output the response to the input prompt (generate outputs predictive of code integration requests) [Polleri: para. 0026; Fig. 10] according to the execution plan (The model composition engine 132 can output the machine learning application 112 as executable code that be run on various infrastructure 128 through
the infrastructure interfaces 124) [Polleri: para. 0050; Fig. 1].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
generate a parallel request.
However, in the same field of endeavor Bhasin further discloses the claim limitations and the deficient claim limitations, as follows:
generate a parallel request (Further, one or more operations may be grouped and performed in the form of a single step, or one operation may have several sub-steps that may be performed in parallel or in a sequential manner. Operations of the method 500, and combinations of operations in the method 500 may be implemented by, for example, hardware, firmware, a processor, circuitry, and/or a different device associated with the execution of software that includes one or more computer program instructions.) [Bhasin: para. 0104; Fig. 5]
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claim 2, Polleri meets the claim limitations as set forth in claim 1. Polleri further meets the claim limitations as follow.
wherein, to generate the execution plan, the one or more processors are configured to execute the processor-executable instructions (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory) [Polleri: para. 0104; Fig. 1] – Note: The generated code based on the evaluation of the input requests is the execution plan) and cause the processing system to determine to offload the input prompt to one or more cloud-based machine learning models (Machine-readable ontologies will allow the free exchange information and knowledge. Ontologies enable the sharing of information between disparate systems within the same domain. … This standardization allows for more flexibility, and will enable more rapid development of applications, and sharing of information) [Polleri: para. 0324; Fig. 1]; (In some embodiments, platform services may be provided by the cloud
infrastructure system via a PaaS platform. The PaaS platform may be configured to provide cloud services that fall under the PaaS category. Examples of platform services may include without limitation services that enable organizations (such as Oracle) to consolidate existing applications on a shared, common architecture, as well as the ability to build new applications that leverage the shared services provided by the platform. The PaaS platform may manage and control the underlying software and infrastructure for providing the PaaS services. Customers can acquire the PaaS services provided by the cloud infrastructure system without the need for customers to purchase separate licenses and support. Examples of platform services include, without limitation, Oracle Java Cloud Service (JCS), Oracle Database Cloud Service (DBCS), and others) [Polleri: para. 0403].
In the same field of endeavor Bhasin further discloses the claim limitations as follows:
one or more cloud-based machine learning models ((The database 120 may be incorporated in the server system 102 or may be an individual entity connected to the server system 102 or may be a database stored in cloud storage) [Bhasin: para. 0063; Fig. 2]; (In some embodiments, the server system 200 is embodied as a cloud-based and/or Software as a Service (SaaS) based architecture) [Bhasin: para. 0063; Fig. 2]).
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claim 3, Polleri meets the claim limitations as set forth in claim 2. Polleri further meets the claim limitations as follow.
wherein, to determine to offload the input prompt, the one or more processors are configured to execute the processor-executable instructions (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory) [Polleri: para. 0104; Fig. 1];(Machine-readable ontologies will allow the free exchange information and knowledge. Ontologies enable the sharing of information between disparate systems within the same domain. … This standardization allows for more flexibility, and will enable more rapid development of applications, and sharing of information) [Polleri: para. 0324; Fig. 1] and cause the processing system to determine that a number of the set of sub-prompts satisfies a threshold value (In some embodiments, platform services may be provided by the cloud infrastructure system via a PaaS platform. The PaaS platform may be configured to provide cloud services that fall under the PaaS category. Examples of platform services may include without limitation services that enable organizations (such as Oracle) to consolidate existing applications on a shared, common architecture, as well as the ability to build new applications that leverage the shared services provided by the platform. The PaaS platform may manage and control the underlying software and infrastructure for providing the PaaS services. Customers can acquire the PaaS services provided by the cloud infrastructure system without the need for customers to purchase separate licenses and support. Examples of platform services include, without limitation, Oracle Java Cloud Service (JCS), Oracle Database Cloud Service (DBCS), and others) [Polleri: para. 0403].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
satisfies a threshold value.
However, in the same field of endeavor Bhasin further discloses the claim limitations as follows:
a threshold value ((In various examples, the one or more operating parameters corresponding to each suitable product may include at least a threshold value for each suitable product for performing the task by the entity) [Bhasin: para. 0079]; (In an embodiment, if the output probability is at least equal (i.e., greater than or equal to) than a predefined threshold value then, the query response message may be transmitted to the entity in response to the task-specific query) [Bhasin: para. 0081; Fig. 2]).
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claims 4 and 13, Polleri meets the claim limitations as set forth in claims 2 and 12. Polleri further meets the claim limitations as follow.
wherein, to determine to offload the input prompt, the one or more processors are configured to execute the processor-executable instructions (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory) [Polleri: para. 0104; Fig. 1];(Machine-readable ontologies will allow the free exchange information and knowledge. Ontologies enable the sharing of information between disparate systems within the same domain. … This standardization allows for more flexibility, and will enable more rapid development of applications, and sharing of information) [Polleri: para. 0324; Fig. 1] and cause the processing system to determine that a number of cloud-based data retrievals for the set of sub-prompts satisfies a threshold value (In some embodiments, platform services may be provided by the cloud infrastructure system via a PaaS platform. The PaaS platform may be configured to provide cloud services that fall under the PaaS category. Examples of platform services may include without limitation services that enable organizations (such as Oracle) to consolidate existing applications on a shared, common architecture, as well as the ability to build new applications that leverage the shared services provided by the platform. The PaaS platform may manage and control the underlying software and infrastructure for providing the PaaS services. Customers can acquire the PaaS services provided by the cloud infrastructure system without the need for customers to purchase separate licenses and support. Examples of platform services include, without limitation, Oracle Java Cloud Service (JCS), Oracle Database Cloud Service (DBCS), and others) [Polleri: para. 0403].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
satisfies a threshold value.
However, in the same field of endeavor Bhasin further discloses the claim limitations as follows:
a threshold value ((In various examples, the one or more operating parameters corresponding to each suitable product may include at least a threshold value for each suitable product for performing the task by the entity) [Bhasin: para. 0079]; (In an embodiment, if the output probability is at least equal (i.e., greater than or equal to) than a predefined threshold value then, the query response message may be transmitted to the entity in response to the task-specific query) [Bhasin: para. 0081; Fig. 2]).
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claims 5 and 14, Polleri meets the claim limitations as set forth in claims 2 and 12. Polleri further meets the claim limitations as follow.
wherein, to determine to offload the input prompt, the one or more processors are configured to execute the processor-executable instructions and cause the processing system to (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory) [Polleri: para. 0104; Fig. 1];(Machine-readable ontologies will allow the free exchange information and knowledge. Ontologies enable the sharing of information between disparate systems within the same domain. … This standardization allows for more flexibility, and will enable more rapid development of applications, and sharing of information) [Polleri: para. 0324; Fig. 1]: estimate a time to generate the response to the input prompt ((In some embodiments, the productivity can be determined by number of units produced per unit time worked. The attributes can then include data on number of hours worked, number of units produced, and number of defective units produced) [Polleri: para. 0092]; (A timeout event may be generated when the end user conversation has been inactive for a period of time, which may be configured at the channel) [Polleri: para. 0191]; (Thereafter, the analytic engine of the analytic system may select, using one or more filtering criteria selected by a user, one or more conversations from the set of conversations based upon the one or more attributes for the one or more events collected by the event collector. The one or more filtering criteria may include, for example, conversations ended at a particular state, conversations started from a particular state, completed or incomplete conversations, conversations associated a particular end user intent, conversations from a particular channel or locale, conversations occurred during a certain time period, and the like. For the selected one or more conversations, the analytic engine may calculate statistics of the set of conversations, statistics of the conversations associated with a particular end user intent, statistics of complete conversations, statistics of incomplete conversations, statistics of conversations for which no end user intent is determined, or any combination thereof. The analytic engine may generate options for improving the bot system based on the calculated statistics) [Polleri: para. 0115] based on the sequence of requests (The plurality of instructions may also cause the one or more processors to classify, sequentially by a set of classification models associated with a set of nodes in the tree structure) [Polleri: para. 0217; Fig. 1] and the parallel request; and
determine that the time satisfies a threshold value (In some embodiments, an event collector of the analytic system may collect one or more attributes for one or more events associated with a set of conversations with a bot system The event collector may be reconfigurable to selectively collect desired attributes for desired events. The one or more events may include, for example, at least one of a conversation event, a bot state event, an intent resolution event, an entity resolution event, an error event, a timeout event, or a custom event. Thereafter, the analytic engine of the analytic system may select, using one or more filtering criteria selected by a user, one or more conversations from the set of conversations based upon the one or more attributes for the one or more events collected by the event collector. The one or more filtering criteria may include, for example, conversations ended at a particular state, conversations started from a particular state, completed or incomplete conversations, conversations associated a particular end user intent, conversations from a particular channel or locale, conversations occurred during a certain time period, and the like. For the selected one or more conversations, the analytic engine may calculate statistics of the set of conversations, statistics of the conversations associated with a particular end user intent, statistics of complete conversations, statistics of incomplete conversations, statistics of conversations for which no end user intent is determined, or any combination thereof. The analytic engine may generate options for improving the bot system based on the calculated statistics) [Polleri: para. 0115].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
the parallel request.a threshold value.
However, in the same field of endeavor Bhasin further discloses the claim limitations as follows:
the parallel request (Further, one or more operations may be grouped and performed in the form of a single step, or one operation may have several sub-steps that may be performed in parallel or in a sequential manner. Operations of the method 500, and combinations of operations in the method 500 may be implemented by, for example, hardware, firmware, a processor, circuitry, and/or a different device associated with the execution of software that includes one or more computer program instructions.) [Bhasin: para. 0104; Fig. 5].
a threshold value ((In various examples, the one or more operating parameters corresponding to each suitable product may include at least a threshold value for each suitable product for performing the task by the entity) [Bhasin: para. 0079]; (In an embodiment, if the output probability is at least equal (i.e., greater than or equal to) than a predefined threshold value then, the query response message may be transmitted to the entity in response to the task-specific query) [Bhasin: para. 0081; Fig. 2]).
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claims 6 and 15, Polleri meets the claim limitations as set forth in claims 1 and 12. Polleri further meets the claim limitations as follow.
wherein, to determine to offload the input prompt, the one or more processors are configured to execute the processor-executable instructions and cause the processing system to (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory) [Polleri: para. 0104; Fig. 1];(Machine-readable ontologies will allow the free exchange information and knowledge. Ontologies enable the sharing of information between disparate systems within the same domain. … This standardization allows for more flexibility, and will enable more rapid development of applications, and sharing of information) [Polleri: para. 0324; Fig. 1]: estimate a time to generate the response to the input prompt ((In some embodiments, the productivity can be determined by number of units produced per unit time worked. The attributes can then include data on number of hours worked, number of units produced, and number of defective units produced) [Polleri: para. 0092]; (A timeout event may be generated when the end user conversation has been inactive for a period of time, which may be configured at the channel) [Polleri: para. 0191]; (Thereafter, the analytic engine of the analytic system may select, using one or more filtering criteria selected by a user, one or more conversations from the set of conversations based upon the one or more attributes for the one or more events collected by the event collector. The one or more filtering criteria may include, for example, conversations ended at a particular state, conversations started from a particular state, completed or incomplete conversations, conversations associated a particular end user intent, conversations from a particular channel or locale, conversations occurred during a certain time period, and the like. For the selected one or more conversations, the analytic engine may calculate statistics of the set of conversations, statistics of the conversations associated with a particular end user intent, statistics of complete conversations, statistics of incomplete conversations, statistics of conversations for which no end user intent is determined, or any combination thereof. The analytic engine may generate options for improving the bot system based on the calculated statistics) [Polleri: para. 0115] based on the sequence of requests (The plurality of instructions may also cause the one or more processors to classify, sequentially by a set of classification models associated with a set of nodes in the tree structure) [Polleri: para. 0217; Fig. 1] and the parallel request; determine that the time fails to satisfy a threshold value ((In some embodiments, an event collector of the analytic system may collect one or more attributes for one or more events associated with a set of conversations with a bot system The event collector may be reconfigurable to selectively collect desired attributes for desired events. The one or more events may include, for example, at least one of a conversation event, a bot state event, an intent resolution event, an entity resolution event, an error event, a timeout event, or a custom event) [Polleri: para. 0115]; and locally generate the response to the input prompt according to the execution plan (In some embodiments, the bot system may convert the content into a standardized form (e.g., a REST call against enterprise services with the proper parameters)
and generate a natural language response. The bot system may also prompt the end user for additional input parameters or request other additional information. In some embodiments, the bot system may also initiate communication with the end user) [Polleri: para. 0198].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
the parallel request.a threshold value.
However, in the same field of endeavor Bhasin further discloses the claim limitations as follows:
the parallel request (Further, one or more operations may be grouped and performed in the form of a single step, or one operation may have several sub-steps that may be performed in parallel or in a sequential manner. Operations of the method 500, and combinations of operations in the method 500 may be implemented by, for example, hardware, firmware, a processor, circuitry, and/or a different device associated with the execution of software that includes one or more computer program instructions.) [Bhasin: para. 0104; Fig. 5].
a threshold value ((In various examples, the one or more operating parameters corresponding to each suitable product may include at least a threshold value for each suitable product for performing the task by the entity) [Bhasin: para. 0079]; (In an embodiment, if the output probability is at least equal (i.e., greater than or equal to) than a predefined threshold value then, the query response message may be transmitted to the entity in response to the task-specific query) [Bhasin: para. 0081; Fig. 2]).
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claims 7 and 16, Polleri meets the claim limitations as set forth in claims 1 and 12. Polleri further meets the claim limitations as follow.
transmit (transmitting and retrieving computer-readable information) [Polleri: para. 0430] a first request of the sequence of requests to retrieve data for a first sub-prompt of the set of sub-prompts (As part of a conversation, a user 408 may provide one or more user inputs 410 and get responses 412 back from the digital assistant 406. Via these conversations, a user can request one or more tasks to be performed by the digital assistant 406 and, in response, the digital assistant 406 is configured to perform the user-requested tasks and respond with appropriate responses to the user) [Polleri: para. 0127; Fig. 4]; receive a first sub-response for the first request (In response, the digital assistant 406 is configured to perform the user-requested tasks and respond with appropriate responses to the user)) [Polleri: para. 0127; Fig. 4]; and transmit a second request of the sequence of requests based on the first sub-response (As part of a conversation, a user 408 may provide one or more user inputs 410 and get responses 412 back from the digital assistant 406.) [Polleri: para. 0127; Fig. 4] – Note: Polleri discloses that user can provide more than one request).
Regarding claims 8 and 17, Polleri meets the claim limitations as set forth in claims 1 and 12. Polleri further meets the claim limitations as follow.
transmit (transmitting and retrieving computer-readable information) [Polleri: para. 0430] the parallel request to retrieve data for a plurality of sub-prompts of the set of sub-prompts (As part of a conversation, a user 408 may provide one or more user inputs 410 and get responses 412 back from the digital assistant 406. Via these conversations, a user can request one or more tasks to be performed by the digital assistant 406 and, in response, the digital assistant 406 is configured to perform the user-requested tasks and respond with appropriate responses to the user) [Polleri: para. 0127; Fig. 4]; receive a sub-response for the parallel request (In response, the digital assistant 406 is configured to perform the user-requested tasks and respond with appropriate responses to the user)) [Polleri: para. 0127; Fig. 4]; and generate the response based on the sub-response (In response, the digital assistant 406 is configured to perform the user-requested tasks and respond with appropriate responses to the user)) [Polleri: para. 0127; Fig. 4].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
the parallel request.
However, in the same field of endeavor Bhasin further discloses the claim limitations as follows:
the parallel request (Further, one or more operations may be grouped and performed in the form of a single step, or one operation may have several sub-steps that may be performed in parallel or in a sequential manner. Operations of the method 500, and combinations of operations in the method 500 may be implemented by, for example, hardware, firmware, a processor, circuitry, and/or a different device associated with the execution of software that includes one or more computer program instructions.) [Bhasin: para. 0104; Fig. 5].
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claims 9 and 18, Polleri meets the claim limitations as set forth in claims 1 and 12. Polleri further meets the claim limitations as follow.
identify a named entity in a first sub-prompt of the set of sub-prompts (As part of a conversation, a user 408 may provide one or more user inputs 410 and get responses 412 back from the digital assistant 406. Via these conversations, a user can request one or more tasks to be performed by the digital assistant 406 and, in response, the digital assistant 406 is configured to perform the user-requested tasks and respond with appropriate responses to the user) [Polleri: para. 0127; Fig. 4]; (As part of the NLU processing for a utterance, digital assistant 406 is configured to perform processing to understand the meaning of the utterance, which involves identifying one or more intents and one or more entities corresponding to the utterance.)) [Polleri: para. 0129; Fig. 4]; and transmit a request for data retrieval (transmitting and retrieving computer-readable information) [Polleri: para. 0430] comprising the named entity and a request for a knowledge graph related to the named entity (As part of the NLU processing for a utterance, digital assistant 406 is configured to perform processing to understand the meaning of the utterance, which involves identifying one or more intents and one or more entities corresponding to the utterance. Upon understanding the meaning of an utterance, digital assistant 406 may perform one or more actions or operations responsive to the understood meaning or intents) [Polleri: para. 0129; Fig. 4]; (In certain embodiments, a version of Y AML called OBotML may be used to specify a dialog flow for a skill bot. The dialog flow definition for a skill bot acts as a model for the conversation itself, one that lets the skill bot designer choreograph the interactions between a skill bot and the users that the skill bot services) [Polleri: para. 0148] ; (The ontology can provide a hierarchical organization of the data set to provide a level of expandability. The output of the process is a product graph which is a composition of the model, the pipelines, the features, and the metrics for to generate a machine learning solution.) [Polleri: para. 0325]).
Regarding claims 10 and 19, Polleri meets the claim limitations as set forth in claims 9 and 18. Polleri further meets the claim limitations as follow.
wherein the one or more processors are configured to execute the processor-executable instructions and cause the processing system to request (The model execution engine 108 can execute the machine learning application 112 on infrastructure 128 using one or more the infrastructure interfaces 124. The infrastructure 128 can include one or more processors, one or more memories, and one or more network interfaces, one or more buses and control lines that can be used to generate, test, compile, and deploy a machine learning application 112) [Polleri: para. 0051] a portion of the knowledge graph based on a set of related named entities based on the named entity (As part of the NLU processing for a utterance, digital assistant 406 is configured to perform processing to understand the meaning of the utterance, which involves identifying one or more intents and one or more entities corresponding to the utterance. Upon understanding the meaning of an utterance, digital assistant 406 may perform one or more actions or operations responsive to the understood meaning or intents) [Polleri: para. 0129; Fig. 4]; (In certain embodiments, a version of Y AML called OBotML may be used to specify a dialog flow for a skill bot. The dialog flow definition for a skill bot acts as a model for the conversation itself, one that lets the skill bot designer choreograph the interactions between a skill bot and the users that the skill bot services) [Polleri: para. 0148] ; (The ontology can provide a hierarchical organization of the data set to provide a level of expandability. The output of the process is a product graph which is a composition of the model, the pipelines, the features, and the metrics for to generate a machine learning solution.) [Polleri: para. 0325]).
Regarding claim 11, Polleri meets the claim limitations as set forth in claim 9. Polleri further meets the claim limitations as follow.
receive another input prompt for machine learning (As part of a conversation, a user 408 may provide one or more user inputs 410 and get responses 412 back from the digital assistant 406. Via these conversations, a user can request one or more tasks to be performed by the digital assistant 406 and, in response, the digital assistant 406 is configured to perform the user-requested tasks and respond with appropriate responses to the user) [Polleri: para. 0127; Fig. 4]; and generate another response to the other input prompt using the knowledge graph (As part of the NLU processing for a utterance, digital assistant 406 is configured to perform processing to understand the meaning of the utterance, which involves identifying one or more intents and one or more entities corresponding to the utterance.)) [Polleri: para. 0129; Fig. 4]; (In certain embodiments, a version of Y AML called OBotML may be used to specify a dialog flow for a skill bot. The dialog flow definition for a skill bot acts as a model for the conversation itself, one that lets the skill bot designer choreograph the interactions between a skill bot and the users that the skill bot services) [Polleri: para. 0148] ; (The ontology can provide a hierarchical organization of the data set to provide a level of expandability. The output of the process is a product graph which is a composition of the model, the pipelines, the features, and the metrics for to generate a machine learning solution.) [Polleri: para. 0325]).
Regarding claim 12, Polleri meets the claim limitations as follow.
A processor-implemented method of generative artificial intelligence (AI) ((systems and techniques for machine learning) [Polleri: para. 0002]; (interaction with the artificial intelligence system) [Polleri: para. 0223]), comprising: receiving an input prompt (receiving input) [Polleri: para. 0026; Fig. 10] for machine learning (receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution) [Polleri: para. 0104]; decomposing the input prompt (processing input data) [Polleri: para. 0026; Fig. 10] to generate a set of sub-prompts (A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments.) [Polleri: para. 0104]; generating a sequence of requests for sub-prompts of the set of sub-prompts that have sequential dependency ((The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models.) [Polleri: para. 0104; Fig. 1]; (Machine learning models are trained for generating predictive outcomes for code integration requests) [Polleri: para. 0104; Fig. 1] ; (The plurality of instructions may also cause the one or more processors to classify, sequentially by a set of classification models associated with a set of nodes in the tree structure, the input as associated with the class in the plurality of classes. The set of nodes may include one node on each layer of the tree structure and may form a path from the root node to a leaf node. Each node in the set of nodes other than the root node may be a child node of a node on an immediate upper layer of the tree structure.) [Polleri: para. 0217; Fig. 1] – Note: Polleri discloses that the intent of a user can be determined from the one or more text fragments, and the machine learning models are trained for generating predictive outcomes from the requests indicated in the one or more text fragments); generating a parallel request for sub-prompts of the set of sub-prompts that do not have sequential dependency ((The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models) [Polleri: para. 0104; Fig. 1]; (Machine learning models are trained for generating predictive outcomes for code integration requests) [Polleri: para. 0104]; (Intents allow the chatbot to understand what the user wants the chatbot to do. Intents are comprised of permutations of typical user requests and statements, which are also referred to as utterances (e.g., generate a classifier application, determine most efficient employee from employment records, etc.). As used herein, an utterance or a message may refer to a set of words (e.g., one or more sentences) exchanged during a conversation with a chatbot. Intents may be created by providing a name that illustrates some user action (e.g., generate a classifier) and compiling a set of real-life user statements, or utterances that are commonly associated with triggering the action. Because the chatbot's cognition is derived from these intents, each intent may be created from a data set that is robust ( one to two dozen utterances) and varied, so that the chatbot may interpret ambiguous user input) [Polleri: para. 0111; Fig. 1]; based on evaluating the sequence of requests and the parallel request (Intents allow the chatbot to understand what the user wants the chatbot to do. Intents are comprised of permutations of typical user requests and statements, which are also referred to as utterances (e.g., generate a classifier application, determine most efficient employee from employment records, etc.). As used herein, an utterance or a message may refer to a set of words (e.g., one or more sentences) exchanged during a conversation with a chatbot. Intents may be created by providing a name that illustrates some user action (e.g., generate a classifier) and compiling a set of real-life user statements, or utterances that are commonly associated with triggering the action. Because the chatbot's cognition is derived from these intents, each intent may be created from a data set that is robust ( one to two dozen utterances) and varied, so that the chatbot may interpret ambiguous user input) [Polleri: para. 0111], generating an execution plan for using one or more machine learning models to generate a response to the input prompt (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second
input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory.) [Polleri: para. 0104; Fig. 1] – Note: The generated code based on the evaluation of the input requests is the execution plan); and
outputing the response to the input prompt (generate outputs predictive of code integration requests) [Polleri: para. 0026; Fig. 10] according to the execution plan (The model composition engine 132 can output the machine learning application 112 as executable code that be run on various infrastructure 128 through
the infrastructure interfaces 124) [Polleri: para. 0050; Fig. 1].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
generating a parallel request.
However, in the same field of endeavor Bhasin further discloses the claim limitations and the deficient claim limitations, as follows:
generating a parallel request (Further, one or more operations may be grouped and performed in the form of a single step, or one operation may have several sub-steps that may be performed in parallel or in a sequential manner. Operations of the method 500, and combinations of operations in the method 500 may be implemented by, for example, hardware, firmware, a processor, circuitry, and/or a different device associated with the execution of software that includes one or more computer program instructions.) [Bhasin: para. 0104; Fig. 5]
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Regarding claim 20, Polleri meets the claim limitations as follow.
A processing system (systems and techniques for machine learning) [Polleri: para. 0002] comprising: means for ((A model composition engine 132 can be executed on one or more computing systems (e.g., infrastructure 128)) [Polleri: para. 0049]; (The infrastructure 128 can include one or more processors) [Polleri: para. 0049]) receiving an input prompt (receiving input) [Polleri: para. 0026; Fig. 10] for machine learning (receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution) [Polleri: para. 0104]; means for ((A model composition engine 132 can be executed on one or more computing systems (e.g., infrastructure 128)) [Polleri: para. 0049]; (The infrastructure 128 can include one or more processors) [Polleri: para. 0049]) decomposing the input prompt (processing input data) [Polleri: para. 0026; Fig. 10] to generate a set of sub-prompts (A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments.) [Polleri: para. 0104]; means for ((A model composition engine 132 can be executed on one or more computing systems (e.g., infrastructure 128)) [Polleri: para. 0049]; (The infrastructure 128 can include one or more processors) [Polleri: para. 0049]) generating a sequence of requests for sub-prompts of the set of sub-prompts that have sequential dependency ((The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models.) [Polleri: para. 0104; Fig. 1]; (Machine learning models are trained for generating predictive outcomes for code integration requests) [Polleri: para. 0104; Fig. 1] ; (The plurality of instructions may also cause the one or more processors to classify, sequentially by a set of classification models associated with a set of nodes in the tree structure, the input as associated with the class in the plurality of classes. The set of nodes may include one node on each layer of the tree structure and may form a path from the root node to a leaf node. Each node in the set of nodes other than the root node may be a child node of a node on an immediate upper layer of the tree structure.) [Polleri: para. 0217; Fig. 1] – Note: Polleri discloses that the intent of a user can be determined from the one or more text fragments, and the machine learning models are trained for generating predictive outcomes from the requests indicated in the one or more text fragments); means for ((A model composition engine 132 can be executed on one or more computing systems (e.g., infrastructure 128)) [Polleri: para. 0049]; (The infrastructure 128 can include one or more processors) [Polleri: para. 0049]) generating a parallel request for sub-prompts of the set of sub-prompts that do not have sequential dependency ((The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in
part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models) [Polleri: para. 0104; Fig. 1]; (Machine learning models are trained for generating predictive outcomes for code integration requests) [Polleri: para. 0104]; (Intents allow the chatbot to understand what the user wants the chatbot to do. Intents are comprised of permutations of typical user requests and statements, which are also referred to as utterances (e.g., generate a classifier application, determine most efficient employee from employment records, etc.). As used herein, an utterance or a message may refer to a set of words (e.g., one or more sentences) exchanged during a conversation with a chatbot. Intents may be created by providing a name that illustrates some user action (e.g., generate a classifier) and compiling a set of real-life user statements, or utterances that are commonly associated with triggering the action. Because the chatbot's cognition is derived from these intents, each intent may be created from a data set that is robust ( one to two dozen utterances) and varied, so that the chatbot may interpret ambiguous user input) [Polleri: para. 0111; Fig. 1]; means for generating ((A model composition engine 132 can be executed on one or more computing systems (e.g., infrastructure 128)) [Polleri: para. 0049]; (The infrastructure 128 can include one or more processors) [Polleri: para. 0049]), based on evaluating the sequence of requests and the parallel request (Intents allow the chatbot to understand what the user wants the chatbot to do. Intents are comprised of permutations of typical user requests and statements, which are also referred to as utterances (e.g., generate a classifier application, determine most efficient employee from employment records, etc.). As used herein, an utterance or a message may refer to a set of words (e.g., one or more sentences) exchanged during a conversation with a chatbot. Intents may be created by providing a name that illustrates some user action (e.g., generate a classifier) and compiling a set of real-life user statements, or utterances that are commonly associated with triggering the action. Because the chatbot's cognition is derived from these intents, each intent may be created from a data set that is robust ( one to two dozen utterances) and varied, so that the chatbot may interpret ambiguous user input) [Polleri: para. 0111], an execution plan for using one or more machine learning models to generate a response to the input prompt (Machine learning models are trained for generating predictive outcomes for code integration requests. In one aspect, techniques can be used for defining a machine learning solution, including receiving a first input (e.g., aural, textual, or GUI) describing a problem for the machine learning solution. A model composition engine 132, as shown in FIG. 1, can transcribe the first input into one or more text fragments. The model composition engine 132 can determine an intent of a user to create a machine learning architecture based at least in part on the one or more text fragments. The techniques can include correlating the one or more text fragments to one or more machine learning frameworks of a plurality of models. The techniques can include presenting (e.g., interface or audio) the one or more machine learning model to the user. The model composition engine 132 can receive a selection of one or more machine learning model (e.g., classification, recommender, reinforcement learning). The model composition engine 132 can receive several other user inputs including a second input identifying a data source for the machine learning architecture and a third input of one or more constraints (e.g., resources, location, security, or privacy) for the machine learning architecture. The model composition engine 132 can generate a plurality of code for the machine learning architecture based at least in part on the selected model, the second input identifying the data source, and the third input identifying the one or more constraints. The generated code can be stored in a memory.) [Polleri: para. 0104; Fig. 1] – Note: The generated code based on the evaluation of the input requests is the execution plan); and
means for ((A model composition engine 132 can be executed on one or more computing systems (e.g., infrastructure 128)) [Polleri: para. 0049]; (The infrastructure 128 can include one or more processors) [Polleri: para. 0049]) outputing the response to the input prompt (generate outputs predictive of code integration requests) [Polleri: para. 0026; Fig. 10] according to the execution plan (The model composition engine 132 can output the machine learning application 112 as executable code that be run on various infrastructure 128 through
the infrastructure interfaces 124) [Polleri: para. 0050; Fig. 1].
Polleri does not explicitly disclose the following claim limitations (Emphasis added).
generating a parallel request.
However, in the same field of endeavor Bhasin further discloses the claim limitations and the deficient claim limitations, as follows:
generating a parallel request (Further, one or more operations may be grouped and performed in the form of a single step, or one operation may have several sub-steps that may be performed in parallel or in a sequential manner. Operations of the method 500, and combinations of operations in the method 500 may be implemented by, for example, hardware, firmware, a processor, circuitry, and/or a different device associated with the execution of software that includes one or more computer program instructions.) [Bhasin: para. 0104; Fig. 5]
It would have been obvious to one with an ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Polleri with Bhasin to program the system to implement of Bhasin’s method.
Therefore, the combination of Polleri with Bhasin will enable the system to improve improve the query response message generated by the LLM model [Bhasin: para. 0080].
Reference Notice
Additional prior arts, included in the Notice of Reference Cited, made of record and not relied upon is considered pertinent to applicant's disclosure.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Philip Dang whose telephone number is (408) 918-7529. The examiner can normally be reached on Monday-Thursday between 8:30 am - 5:00 pm (PST).
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, Sath Perungavoor can be reached on 571-272-7455. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000./Philip P. Dang/Primary Examiner, Art Unit 2488
Prosecution Insights