DETAILED ACTION
This office action is in response to the communication filed on March 13, 2026. Claims 1-20 are currently pending.
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 .
Response to Arguments
Applicant's arguments filed on March 13, 2026 have been fully considered but they are not persuasive for the following reasons:
Applicant in Pages 9-10 of the Remarks argues that the amended independent claims, and the claims that depend thereon, are patent eligible under 35 U.S.C. 101, and further argues that the claimed subject matters improves machine learning and reduces the amount of network and computing resources used.
Examiner respectfully disagrees.
It is important to note that the judicial exception alone cannot provide the improvement. The improvement can be provided by one or more additional elements (MPEP 2106.05(a)).
Similarly, "claiming the improved speed or efficiency inherent with applying the abstract idea on a computer" does not integrate a judicial exception into a practical application or provide an inventive concept (MPEP 2106.05(f)).
Independent claim 1 and similarly independent claims 2 and 12 covers several steps, such as the generating and inferring steps in claim 1, the generating, inferring, and determining steps in claim 2, and the generating step in claim 12, that recite an abstract idea within the “Mental Processes” grouping of abstract ideas, because a person can mentally or using a pen and paper perform the limitations recited in said steps, which are discussed in detail in the current 101 rejection below.
The remaining steps in the claims that are identified as reciting additional elements, such as the providing, storing, and updating steps in claim 1, the providing, searching, storing, and updating steps in claim 2, and the obtaining, storing, and updating steps in claim 12, are only adding insignificant extra-solution activity to the judicial exception, and are recognized as a well understood, routine, and conventional activity within the field of computer functions, which is not sufficient to amount to significantly more than the judicial exception and are not directed to any specific improvement in computer technology.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Applicant in Pages 10-11 of the Remarks argues that the cited prior art Tawfiq and Siebel do not teach or even suggest the amended features recited in amended independent claim 1 and similarly recited in amended independent claims 2 and 12.
Examiner respectfully disagrees. The previously cited prior art Tawfiq and Siebel and the newly cited prior art Brenna alone and/or in combination discloses the amended features, as discussed in detail in the 103 rejection of claims 1-20 below.
For the above reasons, Examiner states that rejection of the current Office action is proper.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In claim 1 line 11, the phrase “to the prompt” is indefinite because it is not clear which prompt among “a prompt”, “a set of follow-up prompts”, and “one or more anticipated future prompts” is being referred to.
Claim 2 recites the limitation "the prompt" in 7. There is insufficient antecedent basis for this limitation in the claim.
In claim 2 line 7, the phrase “to the prompt” is also indefinite because it is not clear how “the prompt” is referring to “one or more anticipated future prompts”, which are provided after receiving a response to the prompt.
Claim 12 recites the limitation "the prompt" in 8. There is insufficient antecedent basis for this limitation in the claim.
In claim 12 line 8, the phrase “to the prompt” is also indefinite because it is not clear how “the prompt” is referring to “one or more anticipated future prompts”, which are provided after receiving a response to the prompt.
Claims 3-11 and 13-20 inherit the same deficiencies of their base claims, therefore, they are also indefinite.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
At step 1:
Independent claims 1, 2, and 12 respectively recite a system, a method, and one or more non-transitory machine-readable media, which are directed to a statutory category such as a process, machine, or an article of manufacture.
At step 2A, prong one:
Independent claim 1 recites the limitations:
“generating…and for a large language model (LLM), a combined language model input comprising a prompt obtained…and a predicted language model context comprising a set of follow-up prompts, generated by the prediction model, that represent one or more anticipated future prompts that are likely to be provided after receiving a response, to the prompt, from the LLM”;
A person can mentally or using a pen and paper generate a combined language model input for a large language model comprising an obtained prompt and a predicted language model context comprising a set of follow-up prompts that are generated by a prediction model and represents one or more anticipated future prompts that are likely to be provided after receiving a response to a prompt from the large language model.
“inferring…a set of queries for a set of databases…the set of queries comprising a first query and a second query”;
A person can mentally or using a pen and paper infer a set of queries comprising a first query and a second query for a set of databases.
The limitations, as recited above, are processes that, under their broadest reasonable interpretation, cover steps that can be performed in the human mind or by a human using a pen and paper, but for recitation of generic computer components.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas.
Accordingly, the claim recites an abstract idea.
Independent claim 2 recites the limitations:
“generating…and for a large language model, a combined language model input comprising a first interface interaction value and a language model context comprising a set of follow-up interface interaction values generated by the preliminary prediction model, that correspond to one or more anticipated future prompts that are likely to be provided after receiving a response, to the prompt, from the language model”;
A person can mentally or using a pen and paper generate a combined language model input form a large language model comprising a first interface interaction value and a language model context comprising a set of follow-up interface interaction values generated by a preliminary prediction model that correspond to one or more anticipated future prompts that are likely to be provided after receiving a response to a prompt from the language model.
“inferring…a set of queries for a set of databases…the set of queries comprising a first query associated with the first interface interaction value and a second query associated with the set of follow-up interface interaction values”;
A person can mentally or using a pen and paper infer a set of queries comprising a first query associated with a first interface interaction value and a second query associated with a set of follow-up interface interaction values for a set of databases.
“determining a result indicating that a pattern of a later-obtained interface interaction matches at least one of the set of follow-up interface interaction values”;
A person can mentally or using a pen and paper determine a result indicating that a pattern of a later-obtained interface interaction matches at least one of a set of follow-up interface interaction values.
The limitations, as recited above, are processes that, under their broadest reasonable interpretation, cover steps that can be performed in the human mind or by a human using a pen and paper, but for recitation of generic computer components.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas.
Accordingly, the claim recites an abstract idea.
Independent claim 12 recites the limitations:
“generating…and for a machine learning model, a model input comprising a representation of a first interface interaction value and a set of follow-up interface interaction values, generated by the preliminary prediction model, that represent one or more anticipated future prompts that are likely to be provided after receiving a response, to the prompt, from the machine learning model”;
A person can mentally or using a pen and paper generate a model input for a machine learning model comprising a representation of a first interface interaction value and a set of follow-up interface interaction values generated by a preliminary prediction model that represent one or more anticipated future prompts that are likely to be provided after receiving a response to a prompt from the machine learning model.
The limitations, as recited above, are processes that, under their broadest reasonable interpretation, cover steps that can be performed in the human mind or by a human using a pen and paper, but for recitation of generic computer components.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas.
Accordingly, the claim recites an abstract idea.
At step 2A, prong two:
This judicial exception is not integrated into a practical application.
Independent claim 1 recites the limitations:
“…by providing the combined language model input to the LLM in a single pass, via a network application programming interface, to reduce the network resource consumption…”, which is a step of providing data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“storing, in in-memory storage, first report values and second report values by searching a data store using the set of queries to obtain the first report values for a first report based on the first query and the second report values for a second report based on the second query”, which is a step of storing data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“updating an audio or visual dashboard to present audio or visual content corresponding to the first report values by providing, to the client device, the first report values”, which is a step of updating and providing data. The step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
“in response to matching a pattern of a later-obtained text sequence to at least one sequence of the set of follow-up text sequences, updating the audio or visual dashboard to present audio or visual content corresponding to the second report values…”, which is a step of updating and presenting data. The step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
“…by causing the client device to obtain the second report values stored in the in-memory storage”, which is a step of obtaining or retrieving data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
The additional elements “a system for reducing network resource consumption when generating interactive audio/visual dashboard content by using a predicted language model context, comprising one or more non-transitory media storing program instructions that, when executed by one or more processors, causes the one or more processors to perform operations comprising:”, “with a server”, “using a preliminary prediction model”, “a large language model”, “from a client device”, “a predicted language model”, “using the LLM”, “a set of databases”, “via a network application programming interface”, “in in-memory storage”, “a data store”, “an audio or visual dashboard”, “the client device”, and “the in-memory storage” in the steps in claim 1 are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using generic computer components.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claim a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Independent claim 2 recites the limitations:
“…by providing the combined language model input to the language model in a single message or in a single pass to reduce the network resource consumption…”, which is a step of providing data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“searching a data store based on the set of queries to obtain a first set of report values based on the first query and a second set of report values based on the second query”, which is a step of searching and obtaining data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“storing the second set of report values in a cache”, which is a step of storing data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“updating a rendering of a dashboard to present at least one value of the first set of report values by providing, to a client device, the first set of report values”, which is a step of updating and providing data. The step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
“in response to a determination of the result, updating the rendering of the dashboard to present the second set of report values…”, which is a step of updating and presenting data. The step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
“…by causing the client device to obtain the second set of report values stored in the cache”, which is a step of obtaining or retrieving data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
The additional elements “a method for reducing network resource consumption by using a predicted language model context, comprising:”, “using a preliminary prediction model”, “a language model”, “a first interface”, “from the language model”, “using the language model”, “a set of databases”, “to the language model”, “a data store”, “in a cache”, “a dashboard”, “to a client device”, “the client device”, and “stored in the cache” in the steps in claim 2 are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using generic computer components.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claim a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Independent claim 12 recites the limitations:
“obtaining, using the machine learning mode, a set of queries for a set of databases by providing, to the machine learning model, the model input in a single message or in a single pass to reduce the network resource consumption, wherein the set of queries comprises a first query associated with the first interface interaction value and a second query associated with the set of follow-up interface interaction values”, which is a step of obtaining or retrieving data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“storing a second set of report values in an in-memory storage by searching a data store using the set of queries to obtain a first set of report values and the second set of report values”, which is a step of storing data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“updating an audio or visual dashboard to present audio or visual content corresponding to the first report values by providing, to the client device, the first report values”, which is a step of updating and providing data. The step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
“in response to matching a pattern of a later-obtained interface interaction with at least one interaction of the set of follow-up interface interaction values, updating the interactive interface…”, which is a step of updating and providing data. The step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
“…by causing the client device to obtain the second set of report values stored in the in-memory storage”, which is a step of obtaining or retrieving data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
The additional elements “one or more non-transitory machine-readable media storing program instructions that, when executed by one or more processors, causes the one or more processors to perform operations comprising:”, “using a preliminary prediction model”, “a machine learning model”, “a first interface”, “by the preliminary prediction model”, “from the machine learning model”, “using the machine learning model”, “a set of databases”, “to the machine learning model”, “in an in-memory storage”, “a data store”, “an interactive interface presented on a client device”, “to the client device”, “the client device”, and “stored in the in-memory storage” in the steps in claim 12 are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using generic computer components.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claim a whole, because it does not impose any meaningful limits on practicing the abstract idea.
At step 2B:
Independent claims 1, 2, and 12 recite the same additional elements as identified in step 2A prong two above. These additional elements are not sufficient to amount to significantly more than the judicial exception.
Independent claim 1 recites the limitations:
“…by providing the combined language model input to the LLM in a single pass, via a network application programming interface, to reduce the network resource consumption…”, which is a step of providing data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“storing, in in-memory storage, first report values and second report values by searching a data store using the set of queries to obtain the first report values for a first report based on the first query and the second report values for a second report based on the second query”, which is a step of storing data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“updating an audio or visual dashboard to present audio or visual content corresponding to the first report values by providing, to the client device, the first report values”, which is a step of updating and providing data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
“in response to matching a pattern of a later-obtained text sequence to at least one sequence of the set of follow-up text sequences, updating the audio or visual dashboard to present audio or visual content corresponding to the second report values…”, which is a step of updating and presenting data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
“…by causing the client device to obtain the second report values stored in the in-memory storage”, which is a step of obtaining or retrieving data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional limitations are not sufficient to amount to significantly more than the judicial exception. Therefore, the claim is directed to an abstract idea and is not patent eligible.
Independent claim 2 recites the limitations:
“…by providing the combined language model input to the language model in a single message or in a single pass to reduce the network resource consumption…”, which is a step of providing data. The step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
“searching a data store based on the set of queries to obtain a first set of report values based on the first query and a second set of report values based on the second query”, which is a step of searching and obtaining data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“storing the second set of report values in a cache”, which is a step of storing data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“updating a rendering of a dashboard to present at least one value of the first set of report values by providing, to a client device, the first set of report values”, which is a step of updating and providing data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
“in response to a determination of the result, updating the rendering of the dashboard to present the second set of report values…”, which is a step of updating and presenting data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
“…by causing the client device to obtain the second set of report values stored in the cache”, which is a step of obtaining or retrieving data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional limitations are not sufficient to amount to significantly more than the judicial exception. Therefore, the claim is directed to an abstract idea and is not patent eligible.
Independent claim 12 recites the limitations:
“obtaining, using the machine learning model, a set of queries for a set of databases by providing, to the machine learning model, the model input in a single message or in a single pass to reduce network resource consumption, wherein the set of queries comprises a first query associated with the first interface interaction value and a second query associated with the set of follow-up interface interaction values”, which is a step of obtaining or retrieving data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“storing a second set of report values in an in-memory storage by searching a data store using the set of queries to obtain a first set of report values and the second set of report values”, which is a step of storing data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“updating an audio or visual dashboard to present audio or visual content corresponding to the first report values by providing, to the client device, the first report values”, which is a step of updating and providing data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
“in response to matching a pattern of a later-obtained interface interaction with at least one interaction of the set of follow-up interface interaction values, updating the interactive interface…”, which is a step of updating and providing data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
“…by causing the client device to obtain the second set of report values stored in the in-memory storage”, which is a step of obtaining or retrieving data, and is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional limitations are not sufficient to amount to significantly more than the judicial exception. Therefore, the claim is directed to an abstract idea and is not patent eligible.
Dependent claim 3 recites additional limitations, such as:
“wherein the result is a first result, and wherein searching the data store based on the set of queries comprises:
searching the data store based on the first query;…
searching the data store based on the second query in response to the second result”, which are steps of searching and obtaining data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“determining a predicted computing resource utilization for the second query;
determining a second result indicating that the predicted computing resource utilization satisfies a threshold”;
These limitations are directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper determine a predicted computing resource utilization for a second query and the person can mentally or using a pen and paper determine a second result indicating that the predicted computing resource utilization satisfies a threshold, and because the limitations do not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claim 4 recites additional limitations, such as:
“wherein the set of queries is a first set of queries, and wherein the combined language model input is a first combined language model input”,
These limitations are directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper infer that a set of queries is a first set of queries, and that a combined language model input is a first combined language model input, and because the limitations do not recite any additional elements that are sufficient to amount to significantly more.
further comprising:
“obtaining a second set of queries by providing, to the language model, a second combined language model input comprising the first interface interaction value and the first set of report values”, which is a step of obtaining data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“retrieving a third set of report values by searching the data store using the second set of queries”, which is a step of retrieving data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“updating the dashboard to present the third set of report values”, which is a step of updating and presenting data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claim 5 recites additional limitation, such as:
“retraining the preliminary prediction model to output at least one query of the second set of queries based on the first interface interaction value”, which is a step of outputting data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claim 6 recites additional limitations, such as:
“wherein the result is a first result, and wherein searching the data store based on the set of queries comprises:
searching the data store based on the first query;…
searching the data store based on the second query in response to the second result”, which are steps for searching and retrieving data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“determining a predicted computing resource utilization for the second query;
determining a second result indicating that the predicted computing resource utilization satisfies a threshold”;
These limitations are directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper determine a predicted computing resource utilization for a second query and the person can mentally or using a pen and paper determine a second result indicating that the predicted computing resource utilization satisfies a threshold, and because the limitations do not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 7 recites additional limitation, such as:
“wherein inferring the set of queries comprises inferring a cross-database query of the set of queries”.
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper infer a set of queries by inferring a cross-database query of the set of queries, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 8 recites additional limitations, such as:
“wherein the set of follow-up interface interaction values comprises a first prompt for an external agent that is independent of the data store”,
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper determine a set of follow-up interface interaction values comprising a first prompt for an external agent that is independent of a data store, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
further comprising:
“obtaining an external agent-provided output by providing the first prompt to the external agent”, which is a step of obtaining or retrieving data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“determining an agent-provided report value based on the external agent-provided output”,
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper determine an agent-provided report value based on an external agent-provided output, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
“wherein updating the dashboard to present the first set of report values comprises updating the dashboard to present the agent-provided report value”, which is a step of updating and presenting data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
The additional elements “an external agent that is independent of the data store” and “external agent-provided output” are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using generic computer components.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 9 recites additional limitations, such as:
“wherein providing the first prompt to the external agent comprises providing the language model context and the first prompt to the external agent”, which is a step of providing data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i)).
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claim 10 recites additional limitations, such as:
“wherein the external agent is a first external agent, and wherein the external agent-provided output is a first external agent-provided output,”, which is a step of outputting or presenting data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
“and wherein determining the agent-provided report value comprises:…
determining the agent-provided report value based on the second external agent-provided output”.
These limitations are directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper determine an agent-provided report value by mentally or using a pen and paper determining the agent-provided report value based on a second external agent-provided output, and because the limitations do not recite any additional elements that are sufficient to amount to significantly more.
“obtaining a second external agent-provided output by providing the external agent-provided output to a second external agent”, which is a step of obtaining or retrieving data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
The additional elements “wherein the external agent is a first external agent”, “the external agent-provided output”, “a second external agent-provided output”, and “a second external agent” are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using generic computer components.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 11 recites additional limitations, such as:
“wherein the set of follow-up interface interaction values comprises two different text sequences”;
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper generate a set of follow-up interface interaction values comprising two different text sequences, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 13 recites additional limitations, such as:
“wherein each respective text sequence of the set of follow-up interface interaction values is separated from other text sequences of the set of follow-up interface interaction values by a delimiter”;
These limitations are directed to the same abstract idea under the mental processes grouping as independent claim 12, because a person can mentally or using a pen and paper generate a set of follow-up interface interaction values wherein each respective text sequence of the set of follow-up interface interaction values is separated from other text sequences of the set of follow-up interface interaction values by a delimiter, and because the limitations do not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 14 recites additional limitations, such as:
“detecting that the first interface interaction value is provided by a first user”;
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 12, because a person can mentally or using a pen and paper detect that a first interface interaction value is provided by a first user, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
“configuring model parameters of a preliminary prediction model based on values of a user profile record for the first user”;
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 12, because a person can mentally or using a pen and paper configure model parameters of a preliminary prediction model based on values of a user profile record for a first user, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
“determining the set of follow-up interface interaction values based on the first interface interaction value”.
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 12, because a person can mentally or using a pen and paper determine a set of follow-up interface interaction values based on a first interface interaction value, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 15 recites additional limitations, such as:
“wherein the first set of report values corresponds with a first report, the second set of report values corresponds with a second report, and wherein:
searching the data store using the set of queries comprises searching the data store to obtain a third set of report values corresponding with a third report, and
storing the second set of report values in the in-memory storage comprises storing the third set of report values in the in-memory storage”, which are steps of searching and storing data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 16 recites additional limitations, such as:
“determining an available memory amount, wherein searching the data store comprises ranking the set of queries based on an associated set of likelihood scores”;
These limitation is directed to the same abstract idea under the mental processes grouping as independent claim 12, because a person can mentally or using a pen and paper determine an available memory amount and the person can mentally or using a pen and paper rank a set of queries based on an associated set of likelihood scores for searching a data store, and because the limitations do not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claim 17 recites additional limitations, such as:
“wherein the set of queries is a first set of queries, and wherein the model input is a first model input, further comprising:
obtaining a second set of queries by providing, to the machine learning model, a second model input comprising the first interface interaction value and the first set of report values”, which are steps of providing and obtaining data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“updating the interactive interface to present a third set of report values obtained from the set of databases by using the second set of queries”, which is a step of updating and presenting data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claim 18 recites additional limitations, such as:
“wherein the set of follow-up interface interaction values comprises a first prompt for an external agent that is independent of the data store, further comprising:
obtaining an external agent-provided output by providing the first prompt to the external agent; determining an agent-provided report value based on the external agent-provided output”, which are steps of providing and obtaining data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“updating the interactive interface to present the agent-provided report value”, which is a step of updating and presenting data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data outputting, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of presenting offers and gathering statistics (MPEP 2106.05(d)(II)(iv)).
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependent claim 19 recites additional limitations, such as:
“wherein searching the data store based on the set of queries comprises:…
searching the data store based on the candidate query in response to the second result”, which are steps for searching and retrieving data.
At step 2A prong two, the step is recited at a high level of generality, and amounts to mere data gathering, which is a form of insignificant extra-solution activity.
At step 2B, the step is recognized as a well understood, routine, and conventional activity within the field of computer functions as an element of storing and retrieving information in memory (MPEP 2106.05(d)(II)(iv)).
“determining a predicted computing resource utilization for a candidate query of the set of queries;
determining a second result indicating that the predicted computing resource utilization satisfies a threshold”;
These limitations are directed to the same abstract idea under the mental processes grouping as independent claim 2, because a person can mentally or using a pen and paper determine a predicted computing resource utilization for a candidate query of a set of queries and the person can mentally or using a pen and paper determine a second result indicating that the predicted computing resource utilization satisfies a threshold, and because the limitations do not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Dependents claim 20 recites additional limitation, such as:
“wherein inferring the set of queries comprises inferring a cross-database query of the set of queries”.
This limitation is directed to the same abstract idea under the mental processes grouping as independent claim 12, because a person can mentally or using a pen and paper infer a set of queries by inferring a cross-database query of the set of queries, and because the limitation does not recite any additional elements that are sufficient to amount to significantly more.
Accordingly, the additional elements, individually or in combination, do not integrate the abstract idea into a practical application, even viewing the claims a whole, because it does not impose any meaningful limits on practicing the abstract idea.
Accordingly, dependent claims 3-11 and 13-20 are also directed to abstract idea without significantly more and are not patent eligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tawfiq (US Pub 2025/0355958, provisional application filing date 05/14/24) in view of Siebel (US Pub 2024/0202221).
With respect to claim 1, Tawfiq discloses a system for reducing network resource consumption when generating interactive audio/visual dashboard content by using a predicted language model context, comprising one or more non-transitory media storing program instructions that, when executed by one or more processors, causes the one or more processors to perform operations (Tawfiq in [0007] discloses system including one or more non-transitory computer-readable media storing instructions executed by one or more processors to perform operations; Tawfiq in [0045], [0155], and [0192] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, computing system associated with one or more web resources, computing devices obtain and/or generate one or more datasets based on data storage retrieval and download via internet from web resources; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0205] and [0212] discloses generative models include machine learned models trained to generate predictive values based on previous data associated with input data, processing input sequence using prediction layers to generate output sequence) comprising:
generating, with a server, using a preliminary prediction model, and for a large language model (LLM), a combined language model input comprising a prompt obtained from a client device and a predicted language model context comprising a set of follow-up prompts generated by the preliminary prediction model, that represent one or more anticipated…prompts…after receiving a response, to the prompt, from the LLM (Tawfiq in [0032] and [0213] discloses providing simplified explanations of responses generate by generative models, generative models include sequence processing models such as large language models (LLMs), response displayed in a user interface at the user device, sequence processing models include one or multiple machine-learned model components configured to ingest, generate, or otherwise reason over sequences of information; Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0049] and [0086] discloses generative models trained to process input data and generate a plurality of predicted words and/or other data; Tawfiq in [0053] discloses receiving a request including information identifying an output and indicating a user request for a simplified version of the output, generating a prompt based on the request that includes the user query, the output, instruction for a simplified version of the output, and other pieces of contextual information; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, generate predicted data based on generating and processing distribution data associated with input data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0212] and [0223] discloses model processing input sequence using prediction layers to generate an output sequence including one or more output elements generated based on input sequence, generating outputs based on output sequence, output sequence having various relationships to an input sequence, output sequence can translate, transform, augment, or otherwise modify input sequence);
inferring, using the LLM, a set of queries for a set of databases by providing the combined language model input to the LLM in a single pass, via a network application programming interface, to reduce the network resource consumption, the set of queries comprising a first query and a second query (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results; Tawfiq in [0045], [0155], and [0192] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, computing system associated with one or more web resources, computing devices obtain and/or generate one or more datasets based on data storage retrieval and download via internet from web resources; Tawfiq in [0053] discloses receiving a request including information identifying an output and indicating a user request for a simplified version of the output, generating a prompt based on the request that includes the user query, the output, instruction for a simplified version of the output, and other pieces of contextual information; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, generate predicted data based on generating and processing distribution data associated with input data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0212] and [0223] discloses model processing input sequence using prediction layers to generate an output sequence including one or more output elements generated based on input sequence, generating outputs based on output sequence, output sequence having various relationships to an input sequence, output sequence can translate, transform, augment, or otherwise modify input sequence);
storing, in in-memory storage, first…values and second…values by searching a data store using the set of queries to obtain the first…values for a first…based on the first query and the second…values for a second…based on the second query (Tawfiq in [0102] and [0104] discloses obtaining a query and processing the query to determine a plurality of search results based on plurality of features, plurality of search results associated with a plurality of different content items, response to a query based on content of subset of plurality of search results, displaying search results in a search results interface; Tawfiq in [0132], [0191] and [0228] discloses datasets can be stored data and/or retrieved data retrieved from web resource, datasets stored on an in-memory data storage; here Tawfiq does not explicitly disclose report values, but the Siebel reference discloses the feature, as discussed below);
updating an audio or visual…to present audio or visual content corresponding to the first…values by providing, to the client device, the first… values (Tawfiq in [0070], [0076], and [0100] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output, a second model response can be used to update user interface and the second model response can be displayed to the user, replacing a first model output with the second model output; Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; here Tawfiq does not explicitly disclose audio or visual dashboard and report values, but the Siebel reference discloses the features, as discussed below); and
in response to matching a pattern of a later-obtained text sequence to at least one sequence of the set of follow-up text sequences, updating the audio or visual…to present audio or visual content corresponding to the second…values by causing the client device to obtain the second…values stored in the in-memory storage (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0070] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output; Tawfiq in [0142] and [0143] discloses data output includes a one or more data types such as audio data, audiovisual data, natural language data etc.; here Tawfiq does not explicitly disclose audio or visual dashboard and report values, but the Siebel reference discloses the features, as discussed below).
Tawfiq discloses outputting query results including audio data or audiovisual data, however, Tawfiq does not explicitly disclose:
…report values…;
…audio or visual dashboard…;
The Siebel reference discloses report values and an audio or visual dashboard (Siebel in [0028] and [0162] discloses receiving a query and providing a response that includes summary of insights as well as a report, output includes at least one of data visualization, a report, and dashboard; Siebel in [0032] and [0047] discloses receiving a question, such as a prompt or a query, processing the query to retrieve data records and generating search results, prompting user to ask follow-up questions, user providing additional related queries, generating results as a visualization in a response graphical user interface; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
Therefore, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, having the teachings of Tawfiq and Siebel, to have combined Tawfiq and Siebel. The motivation to combine Tawfiq and Siebel would be to transform information access and content creation for enterprise systems by applying generative artificial intelligence (Siebel: [0004]).
Tawfiq discloses a set of follow-up prompts generated by a preliminary prediction model that represent one or more anticipated prompts after receiving a response to a prompt from a LLM, however, Tawfiq and Siebel do not explicitly disclose:
a set of follow-up prompts…that represent one or more anticipated future prompts that are likely to be provided after receiving a response, to the prompt, from the LLM;
The Brenna reference discloses a set of follow-up prompts that represent one or more anticipated future prompts that are likely to be provided after receiving a response to a prompt from a LLM (Brenna in [0001] and [0003] discloses a virtual assistant (VA) tool performing tasks using a large language model (LLM) to interpret a user’s natural language input, improving the predictive capabilities of the VA; Brenna in [0015], [0053], and [0066] discloses enhance predictive capabilities of virtual assistant and improving user experience by providing proactive and adaptable results more relevant to a user’s needs, analyzing user’s query log history to identify patterns in stored natural language prompts and corresponding contextual and/or semantic information, predicting based on the pattern recognition and corresponding contextual data, a future query or prompt and proactively executing the predicted prompt prior to a subsequent user interaction or event to proactively provide results to a user prior to receiving any user prompts in the subsequent interaction or event, thereby improving user interaction with the virtual assistant, determining one or more proactive prompts using one or more natural language processing models, catalog user prompt in a query log database and using pattern recognition to look for context/semantic repetitions, and trigger conditions associated with one or more prompts to predict future queries or prompts relevant to the user, generate proactive prompts and/or proactive responses for future user sessions, out and prompts provided to LLMs to generate a proactive response output, storing proactive response along with prompt and corresponding context/semantic information).
Therefore, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, having the teachings of Tawfiq, Siebel, and Brenna, to have combined Tawfiq, Siebel, and Brenna. The motivation to combine Tawfiq, Siebel, and Brenna would be to provide proactive and adaptable results more relevant to a user’s need by improving the predictive capabilities of a virtual assistant (Brenna: [0003]).
With respect to claim 2, Tawfiq discloses a method for reducing network resource consumption by using a predicted language model context (Tawfiq in [0045], [0155], and [0192] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, computing system associated with one or more web resources, computing devices obtain and/or generate one or more datasets based on data storage retrieval and download via internet from web resources; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0205] and [0212] discloses generative models include machine learned models trained to generate predictive values based on previous data associated with input data, processing input sequence using prediction layers to generate output sequence), comprising:
generating, using a preliminary prediction model and for a language model, a combined language model input comprising a first interface interaction value and a language model context comprising a set of follow-up interface interaction values generated by the preliminary prediction model, that correspond to one or more anticipated…prompts…after receiving a response, to the prompt, from the language model (Tawfiq in [0032] and [0213] discloses providing simplified explanations of responses generate by generative models, generative models include sequence processing models such as large language models (LLMs), response displayed in a user interface at the user device, sequence processing models include one or multiple machine-learned model components configured to ingest, generate, or otherwise reason over sequences of information; Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0049] and [0086] discloses generative models trained to process input data and generate a plurality of predicted words and/or other data; Tawfiq in [0053] discloses receiving a request including information identifying an output and indicating a user request for a simplified version of the output, generating a prompt based on the request that includes the user query, the output, instruction for a simplified version of the output, and other pieces of contextual information; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, generate predicted data based on generating and processing distribution data associated with input data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0212] and [0223] discloses model processing input sequence using prediction layers to generate an output sequence including one or more output elements generated based on input sequence, generating outputs based on output sequence, output sequence having various relationships to an input sequence, output sequence can translate, transform, augment, or otherwise modify input sequence);
inferring, using the language model, a set of queries for a set of databases by providing the combined language model input to the language model in a single message or in a single pass to reduce the network resource consumption, the set of queries comprising a first query associated with the first interface interaction value and a second query associated with the set of follow-up interface interaction values (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results; Tawfiq in [0045], [0155], and [0192] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, computing system associated with one or more web resources, computing devices obtain and/or generate one or more datasets based on data storage retrieval and download via internet from web resources; Tawfiq in [0053] discloses receiving a request including information identifying an output and indicating a user request for a simplified version of the output, generating a prompt based on the request that includes the user query, the output, instruction for a simplified version of the output, and other pieces of contextual information; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, generate predicted data based on generating and processing distribution data associated with input data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0212] and [0223] discloses model processing input sequence using prediction layers to generate an output sequence including one or more output elements generated based on input sequence, generating outputs based on output sequence, output sequence having various relationships to an input sequence, output sequence can translate, transform, augment, or otherwise modify input sequence);
searching a data store based on the set of queries to obtain a first set of…values based on the first query and a second set of…values based on the second query (Tawfiq in [0070], [0076], and [0100] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output, a second model response can be used to update user interface and the second model response can be displayed to the user, replacing a first model output with the second model output; Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; here Tawfiq does not explicitly disclose report values, but the Siebel reference discloses the features, as discussed below);
storing the second set of…values in a cache (Tawfiq in [0102] and [0104] discloses obtaining a query and processing the query to determine a plurality of search results based on plurality of features, plurality of search results associated with a plurality of different content items, response to a query based on content of subset of plurality of search results, displaying search results in a search results interface; Tawfiq in [0132], [0191] and [0228] discloses datasets can be stored data and/or retrieved data retrieved from web resource, datasets stored on an in-memory data storage; here Tawfiq does not explicitly disclose report values, but the Siebel reference discloses the feature, as discussed below);
updating a rendering of a…to present at least one value of the first set of…values by providing, to a client device, the first set of…values (Tawfiq in [0070], [0076], and [0100] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output, a second model response can be used to update user interface and the second model response can be displayed to the user, replacing a first model output with the second model output; Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; here Tawfiq does not explicitly disclose audio or visual dashboard and report values, but the Siebel reference discloses the features, as discussed below);
determining a result indicating that a pattern of a later-obtained interface interaction matches at least one of the set of follow-up interface interaction values (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0070] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output; Tawfiq in [0142] and [0143] discloses data output includes a one or more data types such as audio data, audiovisual data, natural language data etc.); and
in response to a determination of the result, updating the rendering of the …to present the second set of…values by causing the client device to obtain the second set of…values stored in the cache (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0070] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output; Tawfiq in [0142] and [0143] discloses data output includes a one or more data types such as audio data, audiovisual data, natural language data etc.; here Tawfiq does not explicitly disclose audio or visual dashboard and report values, but the Siebel reference discloses the features, as discussed below).
Tawfiq discloses outputting query results including audio data or audiovisual data, however, Tawfiq does not explicitly disclose:
…report values…;
…audio or visual dashboard…;
The Siebel reference discloses report values and an audio or visual dashboard (Siebel in [0028] and [0162] discloses receiving a query and providing a response that includes summary of insights as well as a report, output includes at least one of data visualization, a report, and dashboard; Siebel in [0032] and [0047] discloses receiving a question, such as a prompt or a query, processing the query to retrieve data records and generating search results, prompting user to ask follow-up questions, user providing additional related queries, generating results as a visualization in a response graphical user interface; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
Therefore, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, having the teachings of Tawfiq and Siebel, to have combined Tawfiq and Siebel. The motivation to combine Tawfiq and Siebel would be to transform information access and content creation for enterprise systems by applying generative artificial intelligence (Siebel: [0004]).
Tawfiq discloses a set of follow-up prompts generated by a preliminary prediction model that represent one or more anticipated prompts after receiving a response to a prompt from a LLM, however, Tawfiq and Siebel do not explicitly disclose:
a set of follow-up interaction values…that correspond to one or more anticipated future prompts that are likely to be provided after receiving a response, to the prompt, from the language model;
The Brenna reference discloses a set of follow-up interaction values that correspond to one or more anticipated future prompts that are likely to be provided after receiving a response to a prompt from a language model (Brenna in [0001] and [0003] discloses a virtual assistant (VA) tool performing tasks using a large language model (LLM) to interpret a user’s natural language input, improving the predictive capabilities of the VA; Brenna in [0015], [0053], and [0066] discloses enhance predictive capabilities of virtual assistant and improving user experience by providing proactive and adaptable results more relevant to a user’s needs, analyzing user’s query log history to identify patterns in stored natural language prompts and corresponding contextual and/or semantic information, predicting based on the pattern recognition and corresponding contextual data, a future query or prompt and proactively executing the predicted prompt prior to a subsequent user interaction or event to proactively provide results to a user prior to receiving any user prompts in the subsequent interaction or event, thereby improving user interaction with the virtual assistant, determining one or more proactive prompts using one or more natural language processing models, catalog user prompt in a query log database and using pattern recognition to look for context/semantic repetitions, and trigger conditions associated with one or more prompts to predict future queries or prompts relevant to the user, generate proactive prompts and/or proactive responses for future user sessions, out and prompts provided to LLMs to generate a proactive response output, storing proactive response along with prompt and corresponding context/semantic information).
Therefore, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, having the teachings of Tawfiq, Siebel, and Brenna, to have combined Tawfiq, Siebel, and Brenna. The motivation to combine Tawfiq, Siebel, and Brenna would be to provide proactive and adaptable results more relevant to a user’s need by improving the predictive capabilities of a virtual assistant (Brenna: [0003]).
With respect to claim 3, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 2, wherein the result is a first result, and wherein searching the data store based on the set of queries comprises:
searching the data store based on the first query (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results);
determining a predicted computing resource utilization for the second query (Tawfiq in [0045] and [0167] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, utilization of soft prompt can reduce computational cost for parameter tuning for object-specific content generation by reducing the parameters to be tuned; Tawfiq in [0068] and [0204] discloses evaluate each candidate output and generate a score for each candidate input, candidate outputs ranked according to the generated scores, highest ranked out provided to the output classification system, content item generation based on one or more conditions associated with a threshold amount of results; Siebel in [0081] and [0133] discloses control, regulate, or limit retrieval to ensure performance or confidence threshold, satisfying a threshold number of retrieved relevant information to answer a query);
determining a second result indicating that the predicted computing resource utilization satisfies a threshold (Tawfiq in [0045] and [0167] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, utilization of soft prompt can reduce computational cost for parameter tuning for object-specific content generation by reducing the parameters to be tuned; Tawfiq in [0068] and [0204] discloses evaluate each candidate output and generate a score for each candidate input, candidate outputs ranked according to the generated scores, highest ranked out provided to the output classification system, content item generation based on one or more conditions associated with a threshold amount of results; Siebel in [0081] and [0133] discloses control, regulate, or limit retrieval to ensure performance or confidence threshold, satisfying a threshold number of retrieved relevant information to answer a query); and
searching the data store based on the second query in response to the second result (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results).
With respect to claim 4, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 2, wherein the set of queries is a first set of queries, and wherein the combined language model input is a first combined language model input, further comprising:
obtaining a second set of queries by providing, to the language model, a second combined language model input comprising the first interface interaction value and the first set of report values (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results);
retrieving a third set of report values by searching the data store using the second set of queries (Tawfiq in [0102] and [0104] discloses obtaining a query and processing the query to determine a plurality of search results based on plurality of features, plurality of search results associated with a plurality of different content items, response to a query based on content of subset of plurality of search results, displaying search results in a search results interface; Tawfiq in [0132], [0191] and [0228] discloses datasets can be stored data and/or retrieved data retrieved from web resource, datasets stored on an in-memory data storage); and
updating the dashboard to present the third set of report values (Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
With respect to claim 5, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 4, further comprising retraining the preliminary prediction model to output at least one query of the second set of queries based on the first interface interaction value (Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context).
With respect to claim 6, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 4, wherein the result is a first result, and wherein providing the second combined language model input to the language model comprises:
retrieving a historic set of report value ranges associated with the preliminary prediction model (Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context);
determining a second result indicating that the first set of report values exceeds a set of thresholds indicated by the historic set of report value ranges (Tawfiq in [0045] and [0167] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, utilization of soft prompt can reduce computational cost for parameter tuning for object-specific content generation by reducing the parameters to be tuned; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0068] and [0204] discloses evaluate each candidate output and generate a score for each candidate input, candidate outputs ranked according to the generated scores, highest ranked out provided to the output classification system, content item generation based on one or more conditions associated with a threshold amount of results; Siebel in [0081] and [0133] discloses control, regulate, or limit retrieval to ensure performance or confidence threshold, satisfying a threshold number of retrieved relevant information to answer a query); and
providing the second combined language model input to the language model based on the second result (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context).
With respect to claim 7, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 2, wherein inferring the set of queries comprises inferring a cross-database query of the set of queries (Tawfiq in [0126] and [0231] discloses one or more databases searched based on plurality of model-generated sub-topic queries to determine a plurality of result sets; databases distributed across multiple systems; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains).
With respect to claim 8, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 2, wherein the set of follow-up interface interaction values comprises a first prompt for an external agent that is independent of the data store (Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains), further comprising:
obtaining an external agent-provided output by providing the first prompt to the external agent (Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains); and
determining an agent-provided report value based on the external agent-provided output, wherein updating the dashboard to present the first set of report values comprises updating the dashboard to present the agent-provided report value (Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
With respect to claim 9, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 8, wherein providing the first prompt to the external agent comprises providing the language model context and the first prompt to the external agent (Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains).
With respect to claim 10, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 8, wherein the external agent is a first external agent, and wherein the external agent-provided output is a first external agent-provided output, and wherein determining the agent-provided report value comprises:
obtaining a second external agent-provided output by providing the external agent-provided output to a second external agent (Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains); and
determining the agent-provided report value based on the second external agent-provided output (Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
With respect to claim 11, Tawfiq in view of Siebel and in further view of Brenna discloses the method of claim 2, wherein the set of follow-up interface interaction values comprises two different text sequences (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
With respect to claim 12, Tawfiq discloses one or more non-transitory machine-readable media storing program instructions that, when executed by one or more processors, causes the one or more processors to perform operations (Tawfiq in [0007] discloses system including one or more non-transitory computer-readable media storing instructions executed by one or more processors to perform operations; Tawfiq in [0045], [0155], and [0192] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, computing system associated with one or more web resources, computing devices obtain and/or generate one or more datasets based on data storage retrieval and download via internet from web resources; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0205] and [0212] discloses generative models include machine learned models trained to generate predictive values based on previous data associated with input data, processing input sequence using prediction layers to generate output sequence) comprising:
generating, using a preliminary prediction model and for a machine learning model, a model input comprising a representation of a first interface interaction value and a set of follow-up interface interaction values generated by the preliminary prediction model, that represent one or more anticipated... prompts…after receiving a response, to the prompt, from the machine learning model (Tawfiq in [0032] and [0213] discloses providing simplified explanations of responses generate by generative models, generative models include sequence processing models such as large language models (LLMs), response displayed in a user interface at the user device, sequence processing models include one or multiple machine-learned model components configured to ingest, generate, or otherwise reason over sequences of information; Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0049] and [0086] discloses generative models trained to process input data and generate a plurality of predicted words and/or other data; Tawfiq in [0053] discloses receiving a request including information identifying an output and indicating a user request for a simplified version of the output, generating a prompt based on the request that includes the user query, the output, instruction for a simplified version of the output, and other pieces of contextual information; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, generate predicted data based on generating and processing distribution data associated with input data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0212] and [0223] discloses model processing input sequence using prediction layers to generate an output sequence including one or more output elements generated based on input sequence, generating outputs based on output sequence, output sequence having various relationships to an input sequence, output sequence can translate, transform, augment, or otherwise modify input sequence);
obtaining, using the machine learning model, a set of queries for a set of databases by providing, to the machine learning model, the model input in a single message or in a single pass to reduce the network resource consumption, wherein the set of queries comprises a first query associated with the first interface interaction value and a second query associated with the set of follow-up interface interaction values (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results; Tawfiq in [0045], [0155], and [0192] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, computing system associated with one or more web resources, computing devices obtain and/or generate one or more datasets based on data storage retrieval and download via internet from web resources; Tawfiq in [0053] discloses receiving a request including information identifying an output and indicating a user request for a simplified version of the output, generating a prompt based on the request that includes the user query, the output, instruction for a simplified version of the output, and other pieces of contextual information; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, generate predicted data based on generating and processing distribution data associated with input data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0212] and [0223] discloses model processing input sequence using prediction layers to generate an output sequence including one or more output elements generated based on input sequence, generating outputs based on output sequence, output sequence having various relationships to an input sequence, output sequence can translate, transform, augment, or otherwise modify input sequence);
storing a second set of…values in an in-memory storage by searching a data store using the set of queries to obtain a first set of…values and the second set of…values (Tawfiq in [0102] and [0104] discloses obtaining a query and processing the query to determine a plurality of search results based on plurality of features, plurality of search results associated with a plurality of different content items, response to a query based on content of subset of plurality of search results, displaying search results in a search results interface; Tawfiq in [0132], [0191] and [0228] discloses datasets can be stored data and/or retrieved data retrieved from web resource, datasets stored on an in-memory data storage; here Tawfiq does not explicitly disclose report values, but the Siebel reference discloses the feature, as discussed below);
updating an interactive interface presented on a client device to present at least one value of the first set of…values by providing, to the client device, the first set of…values (Tawfiq in [0070], [0076], and [0100] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output, a second model response can be used to update user interface and the second model response can be displayed to the user, replacing a first model output with the second model output; Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; here Tawfiq does not explicitly disclose report values, but the Siebel reference discloses the features, as discussed below); and
in response to matching a pattern of a later-obtained interface interaction with at least one interaction of the set of follow-up interface interaction values, updating the interactive interface by causing the client device to obtain the second set of…values stored in the in-memory storage (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0070] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output; Tawfiq in [0142] and [0143] discloses data output includes a one or more data types such as audio data, audiovisual data, natural language data etc.; here Tawfiq does not explicitly disclose report values, but the Siebel reference discloses the features, as discussed below).
Tawfiq discloses outputting query results including audio data or audiovisual data, however, Tawfiq does not explicitly disclose:
…report values…;
The Siebel reference discloses report values (Siebel in [0028] and [0162] discloses receiving a query and providing a response that includes summary of insights as well as a report, output includes at least one of data visualization, a report, and dashboard; Siebel in [0032] and [0047] discloses receiving a question, such as a prompt or a query, processing the query to retrieve data records and generating search results, prompting user to ask follow-up questions, user providing additional related queries, generating results as a visualization in a response graphical user interface; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
Therefore, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, having the teachings of Tawfiq and Siebel, to have combined Tawfiq and Siebel. The motivation to combine Tawfiq and Siebel would be to transform information access and content creation for enterprise systems by applying generative artificial intelligence (Siebel: [0004]).
Tawfiq discloses a set of follow-up prompts generated by a preliminary prediction model that represent one or more anticipated prompts after receiving a response to a prompt from a LLM, however, Tawfiq and Siebel do not explicitly disclose:
a set of follow-up interaction values…that represent one or more anticipated future prompts that are likely to be provided after receiving a response, to the prompt, from the machine learning model;
The Brenna reference discloses a set of follow-up interaction values that represent one or more anticipated future prompts that are likely to be provided after receiving a response to a prompt from a machine learning model (Brenna in [0001] and [0003] discloses a virtual assistant (VA) tool performing tasks using a large language model (LLM) to interpret a user’s natural language input, improving the predictive capabilities of the VA; Brenna in [0015], [0053], and [0066] discloses enhance predictive capabilities of virtual assistant and improving user experience by providing proactive and adaptable results more relevant to a user’s needs, analyzing user’s query log history to identify patterns in stored natural language prompts and corresponding contextual and/or semantic information, predicting based on the pattern recognition and corresponding contextual data, a future query or prompt and proactively executing the predicted prompt prior to a subsequent user interaction or event to proactively provide results to a user prior to receiving any user prompts in the subsequent interaction or event, thereby improving user interaction with the virtual assistant, determining one or more proactive prompts using one or more natural language processing models, catalog user prompt in a query log database and using pattern recognition to look for context/semantic repetitions, and trigger conditions associated with one or more prompts to predict future queries or prompts relevant to the user, generate proactive prompts and/or proactive responses for future user sessions, out and prompts provided to LLMs to generate a proactive response output, storing proactive response along with prompt and corresponding context/semantic information).
Therefore, it would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, having the teachings of Tawfiq, Siebel, and Brenna, to have combined Tawfiq, Siebel, and Brenna. The motivation to combine Tawfiq, Siebel, and Brenna would be to provide proactive and adaptable results more relevant to a user’s need by improving the predictive capabilities of a virtual assistant (Brenna: [0003]).
With respect to claim 13, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, wherein each respective text sequence of the set of follow-up interface interaction values is separated from other text sequences of the set of follow-up interface interaction values by a delimiter (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0070] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output; Tawfiq in [0142] and [0143] discloses data output includes a one or more data types such as audio data, audiovisual data, natural language data etc.).
With respect to claim 14, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, the operations further comprising:
detecting that the first interface interaction value is provided by a first user (Tawfiq in [0048] and [0057] discloses a remote server system provides query response system, receiving user query, generate a prompt to a model based on the query, prompt including user query, any history of queries submitted by the user, any history of previous responses, contextual data associated with the query, instructions describing format and/or contents of responses, and any relevant user information, context retrieval system accessing previously submitted query and any response generated if an input query is associated with a previous query; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context);
configuring model parameters of a preliminary prediction model based on values of a user profile record for the first user (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0070] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output; Tawfiq in [0142] and [0143] discloses data output includes a one or more data types such as audio data, audiovisual data, natural language data etc.); and
determining the set of follow-up interface interaction values based on the first interface interaction value (Tawfiq in [0044] and [0180] discloses leveraging sub-topic determination, search result processing, query generation, follow-up queries to generate multi-part responses, complete a portion of text that follows from a portion of text represented by inputs; Tawfiq in [0085] and [0219] discloses generate predictive values based on previous behavior data, prediction layer evaluating associations between portions of input sequences and a particular output element to information a prediction of a likelihood that a particular output follows an input context; Tawfiq in [0070] discloses updating user interface to display output, enable user to switch between displaying original first model output and simplified second model output; Tawfiq in [0142] and [0143] discloses data output includes a one or more data types such as audio data, audiovisual data, natural language data etc.).
With respect to claim 15, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, wherein the first set of report values corresponds with a first report, the second set of report values corresponds with a second report, and wherein:
searching the data store using the set of queries comprises searching the data store to obtain a third set of report values corresponding with a third report (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results), and
storing the second set of report values in the in-memory storage comprises storing the third set of report values in the in-memory storage (Tawfiq in [0102] and [0104] discloses obtaining a query and processing the query to determine a plurality of search results based on plurality of features, plurality of search results associated with a plurality of different content items, response to a query based on content of subset of plurality of search results, displaying search results in a search results interface; Tawfiq in [0132], [0191] and [0228] discloses datasets can be stored data and/or retrieved data retrieved from web resource, datasets stored on an in-memory data storage).
With respect to claim 16, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, further comprising determining an available memory amount, wherein searching the data store comprises ranking the set of queries based on an associated set of likelihood scores (Tawfiq in [0045] and [0167] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, utilization of soft prompt can reduce computational cost for parameter tuning for object-specific content generation by reducing the parameters to be tuned; Tawfiq in [0068] and [0204] discloses evaluate each candidate output and generate a score for each candidate input, candidate outputs ranked according to the generated scores, highest ranked out provided to the output classification system, content item generation based on one or more conditions associated with a threshold amount of results; Siebel in [0081] and [0133] discloses control, regulate, or limit retrieval to ensure performance or confidence threshold, satisfying a threshold number of retrieved relevant information to answer a query).
With respect to claim 17, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, wherein the set of queries is a first set of queries, and wherein the model input is a first model input, further comprising:
obtaining a second set of queries by providing, to the machine learning model, a second model input comprising the first interface interaction value and the first set of report values (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results); and
updating the interactive interface to present a third set of report values obtained from the set of databases by using the second set of queries (Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
With respect to claim 18, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, wherein the set of follow-up interface interaction values comprises a first prompt for an external agent that is independent of the data store (Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains), further comprising:
obtaining an external agent-provided output by providing the first prompt to the external agent (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results); and
determining an agent-provided report value based on the external agent-provided output (Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains); and
updating the interactive interface to present the agent-provided report value (Tawfiq in [0116] discloses search results, first model-generated response, multi-part response, and/or simplified response provided for display in search results interface, which may be updated as one or more user interface elements are selected; Tawfiq in [0181] and [0182] discloses task can be question answering task, process inputs that represent a question to answer and to generate outputs that advance a goal of returning an answer to the question, output executed by an external system; Siebel in [0032] and [0083] discloses facilitating ingestion and persistence of data from external systems and external data sources; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains; Siebel in [0109] and [0140] discloses output including data visualization, report, and dynamically configured dashboard, output based on results of executed one or more query sets, output including a report or dashboards based on predictions, insights, and/or recommendations).
With respect to claim 19, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, wherein searching the data store based on the set of queries comprises:
determining a predicted computing resource utilization for a candidate query of the set of queries (Tawfiq in [0045] and [0167] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, utilization of soft prompt can reduce computational cost for parameter tuning for object-specific content generation by reducing the parameters to be tuned; Tawfiq in [0068] and [0204] discloses evaluate each candidate output and generate a score for each candidate input, candidate outputs ranked according to the generated scores, highest ranked out provided to the output classification system, content item generation based on one or more conditions associated with a threshold amount of results; Siebel in [0081] and [0133] discloses control, regulate, or limit retrieval to ensure performance or confidence threshold, satisfying a threshold number of retrieved relevant information to answer a query);
determining a second result indicating that the predicted computing resource utilization satisfies a threshold (Tawfiq in [0045] and [0167] discloses reduction of generative model processing instances can reduce computational resources utilized to provide search result interfaces with artificial intelligence options, utilization of soft prompt can reduce computational cost for parameter tuning for object-specific content generation by reducing the parameters to be tuned; Tawfiq in [0068] and [0204] discloses evaluate each candidate output and generate a score for each candidate input, candidate outputs ranked according to the generated scores, highest ranked out provided to the output classification system, content item generation based on one or more conditions associated with a threshold amount of results; Siebel in [0081] and [0133] discloses control, regulate, or limit retrieval to ensure performance or confidence threshold, satisfying a threshold number of retrieved relevant information to answer a query); and
searching the data store based on the candidate query in response to the second result (Tawfiq in [0007] discloses processing a query, generating a plurality of sub-topic queries, processing the plurality of sub-topic queries to determine search result sets, processing with generative model to generate multi-part response, providing the response to display in a search result interface; Tawfiq in [0042] and [0125] discloses query associated with a historical topic, query and/or search results processed with a query generation module, such as a large language model fine-tuned for query generation and/or conditioned based on a query generation prompt, to determine sub-topics associated with a topic of a response to the query, generate a plurality of sub-topic queries based on semantic understanding of content items of the search results).
With respect to claim 20, Tawfiq in view of Siebel and in further view of Brenna discloses the one or more non-transitory machine-readable media of claim 12, wherein inferring the set of queries comprises inferring a cross-database query of the set of queries (Tawfiq in [0126] and [0231] discloses one or more databases searched based on plurality of model-generated sub-topic queries to determine a plurality of result sets, databases distributed across multiple systems; Siebel in [0074] discloses agents processing requests relating to different domains for cross-domain queries, such as a set of queries spanning multiple domains).
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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to REZWANUL MAHMOOD whose telephone number is (571)272-5625. The examiner can normally be reached M-F 9-5:30.
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, Ann J. Lo can be reached at 571-272-9767. 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.
/R.M/Examiner, Art Unit 2159
/ANN J LO/Supervisory Patent Examiner, Art Unit 2159
Prosecution Insights