DETAILED ACTION
1. Claims 1-20 are pending in this application.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
In the event the determination of the status of the application as subject to AIA 35 U.S.C. §102 and §103 (or as subject to pre-AIA 35 U.S.C. §102 and §103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Information Disclosure Statement
3. The information disclosure statement filed 06/27/2025 is in compliance with the provisions of 37 CFR 1.97, 1.98 and MPEP § 609. It has been placed in the application file and the information referred to therein has been considered as to the merits.
Claim Rejections - 35 USC § 101
4. 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 (Mental Process) without significantly more. The claims similarly describe steps to enhancing AI chatbots through retrieval and search augmentation.
The following is an analysis based on 2019 Revised Patent Subject Matter Eligibility Guidance (2019 PEG).
Step 1, Statutory Category?
Claims 1-10 are directed to a method.
Claims 11-15 are directed to a computing device.
Claims 16-20 are directed to a non-transitory computer-readable media.
Therefore, claims 1-20 fall into at least one of the four statutory categories.
Step 2A, Prong I: Judicial Exception Recited?
The examiner submits that the foregoing claim limitations constitute a “Mental Process”, as the claims cover performance of the limitations in the human mind, given the broadest reasonable interpretation.
As per independent claims 1, 11 and 16, the claims similarly recite the limitations of:
“in response to receiving the user prompt, searching, by the one or more computers, for data objects and values that are relevant to the user prompt, including using the search index to search for data objects and values of one or more data sets that the chatbot is configured to access;” A human can review a data sheet to identify keywords that can be referenced later to locate specific information. There is nothing so complex in the limitation that could not be doing in the human mind.
“using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt,
including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model;” A human can mentally observe data and visualize the answers to any questions that arise from that same data. There is nothing so complex in the limitation that could not be doing in the human mind.
As per dependent claims 5, 15 and 20, the claims similarly recite the limitation of:
“wherein the searching comprises identifying elements that are likely to identify or disambiguate references to attributes, metrics, and other data objects referenced in the user prompt.” A human can observe data and mentally identify elements that can be used as references. There is nothing so complex in the limitation that could not be doing in the human mind.
As per dependent claim 6, the claim recites the limitations of:
“wherein the one or more results are provided to the AI/ML model such that the one or more results are used by the AI/ML model to determine data objects corresponding to terms or concepts in the user prompt.” A human can mentally observe data and determine if parts of the data correspond to a criterion such as a specific word. There is nothing so complex in the limitation that could not be doing in the human mind.
As per dependent claim 8, the claim recites the limitation of:
“wherein the searching comprises searching for similarity using a vector database, including by comparing the distance of embeddings for terms or concepts of the user prompt with stored embeddings.” A human can mentally observe and review data to determine similarities between the observed datasets. The data observed can even be as simple as a two-dimensional vector. There is nothing so complex in the limitation that could not be doing in the human mind.
As per dependent claim 9, the claim recites the limitation of:
“comprising using the search index to identify which data set or data sets, from among multiple data sets, should be used to generate an answer to the user prompt.” A human can mentally observe data and identify the information needed to answer a question. There is nothing so complex in the limitation that could not be doing in the human mind.
Accordingly, claims 1-20 recite at least one abstract idea.
Step 2A, Prong II: Integrated into a Practical Application?
The claims recite the following additional limitations/elements:
As per independent claims 1, 11 and 16, the claims similarly recite the limitations of:
The additional limitation of “storing, by the one or more computers, a search index for data sets, wherein the search index describes data objects of the data sets and values for the data objects in the data sets;” is recognized by the courts as well-understood, routine, conventional activity when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. see MPEP 2106.05(d)(II)(iv).
The additional element of “in response to receiving the user prompt, searching, by the one or more computers, for data objects and values that are relevant to the user prompt, including using the search index to search for data objects and values of one or more data sets that the chatbot is configured to access;” is recognized by the courts as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. See MPEP 2106.05(d)(II)(i).
The additional elements of “in response to receiving the user prompt, searching, by the one or more computers, for data objects and values that are relevant to the user prompt, including using the search index to search for data objects and values of one or more data sets that the chatbot is configured to access;” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
The additional limitation of “receiving, by the one or more computers, a user prompt to a chatbot;” is recognized by the courts as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. See MPEP 2106.05(d)(II)(i).
The additional element of “using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model;” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
The additional element of “using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model;” is recognized by the courts as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. See MPEP 2106.05(d)(II)(i).
The additional element of “using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model;” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
The additional limitation of “providing, by the one or more computers, the chatbot response as a response to the user prompt.” is recognized by the courts as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. See MPEP 2106.05(d)(II)(i). It is simple transmitting information.
As per dependent claims 2, 12 and 17, the claims similarly recite the limitations of:
The additional limitation of “wherein the one or more results obtained using the search index comprise data objects corresponding to terms of the user prompt.” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
As per dependent claims 3, 13 and 18, the claims similarly recite the limitations of:
The additional limitation of “wherein the one or more results obtained using the search index comprise values corresponding to terms of the user prompt.” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
As per dependent claims 4, 14 and 19, the claims similarly recite the limitations of:
The additional limitation of “wherein the search index includes information determined based on structure and metadata of a data set, including at least one of data table names, data table labels, data table descriptions, column names, column labels, or column descriptions.” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
As per dependent claim 6, the claim recites the limitations of:
The additional element of “wherein the one or more results are provided to the AI/ML model such that the one or more results are used by the AI/ML model to determine data objects corresponding to terms or concepts in the user prompt.” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
As per dependent claim 7, the claim recites the limitations of:
The additional element of “wherein the one or more results comprise information that specifies relationships between terms of the user prompt and data objects, such as data indicating the data objects identified as being most closely related to particular words or phrases of the user prompt.” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
As per dependent claim 10, the claim recites the limitations of:
The additional element of “wherein the one or more results include at least one of semantic graph content or knowledge base content.” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
As per independent claim 11, the claim recites the limitations of:
The additional element of “one or more computers, and one or more computer-readable media.” is mere instructions to apply an exception. A recitation of the words "apply it" (or an equivalent) are mere instructions to implement an abstract idea or other exception on a computer. (See MPEP 2106.05(f)).
Therefore, claims 1-20 do not integrate the recited abstract ideas into a practical application.
Step 2B: Claim provides an Inventive Concept?
With respect to the limitations identified as insignificant extra-solution activity above the conclusions are carried over, and both the “storing …; receiving …; providing …; obtaining ….” is well-understood, routine, and conventional operations.
For support as being well-understood, routine, and conventional for “storing …; receiving …; providing …; obtaining ….” as noted by the courts is well understood routine and conventional, see MPEP 2106.05(d)(ii) “i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);” and/or MPEP 2106.05(d)(ii) “iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93;”, and/or MPEP 2106.05(d)(II) “iii. Ultramercial, 772 F.3d at 716, 112 USPQ2d at 1755 (updating an activity log);”.
Looking at the limitations in combination and the claim as a whole does not change this conclusion and the claim is ineligible.
Therefore, the claims 1-20 are not patent eligible.
Claim Rejections - 35 USC § 103
5. In the event the determination of the status of the application as subject to AIA 35 U.S.C. § 102 and § 103 (or as subject to pre-AIA 35 U.S.C. § 102 and § 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. § 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section § 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under pre-AIA 35 U.S.C. § 103(a) are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
6. Claims 1-7 and 11-20 are rejected under 35 U.S.C. § 103 as being unpatentable over Willems et al. (US 20180150514 A1) in view of Kolluri Venkata Sesha et al. (US 20200073982 A1) in further view of Wang et al. (US 20230041181 A1).
As per claim 1, Willems teaches a method performed by one or more computers (i.e. “the method 700 can be performed by a computing apparatus 600”; para. [0077], wherein the method comprises:
storing, by the one or more computers, a search index for data sets (i.e. “storing the first data portion in a predetermined memory location … the first data portion can comprise a data table having one or more rows and one or more columns.”; para. [0004]; Examiner note: using a BRI the search index for data sets is interpreted as the data table),
wherein the search index describes data objects of the data sets and values for the data objects in the data sets (i.e. “the data table 590 can include M columns and/or N rows of data. In some aspects, N can refer to a document identifier associated with a particular entry, as opposed to an identifier for a row (e.g., plain indices to identify a physical row). The data can take any form (e.g., alphanumeric values) and/or the form of the data in the columns/rows can be dependent upon the type of table 590 (e.g., column store, row store, hash table, dictionary, and/or the like).”; para. [0055]; Examiner note: using a BRI the data objects are interpreted as the particular entry. Using a BRI the values for the data objects are interpreted as the e.g., alphanumeric values);
in response to receiving the user prompt (i.e. “in response to receipt of a query instantiated by a user”; para. [0076]),
searching, by the one or more computers, for data objects and values that are relevant to the user prompt (i.e. “the pump operator 510 can pull data from a database table 590 based upon one or more functions (also referred to herein as “predicates”). For example, rows/entries from the table can be retrieved based upon whether “(X>14) AND (Y<100)” is satisfied. In an example implementation, “(X>14)” can refer to whether a value stored in the column indexed ‘X’ is greater than a value of ‘14’, and/or “(Y<100)” can refer to whether a value stored in the column indexed ‘Y’ is less than a value of ‘100’.”; para. [0056]; Examiner note: using a BRI the data objects are X and Y. using a BRI The value is 14 and 100),
including using the search index to search for data objects and values of one or more data sets that the chatbot is configured to access (i.e. “Based upon these predicates, rows (or some portion thereof) which match both (“AND”) conditions can be pulled/retrieved from the table 590 and/or loaded in memory (e.g., in a cache, heap, main memory, etc.).”; para. [0056]. Further, i.e. “dictionaries can be maintained, which can contain entries for each unique value within a column, along with corresponding document identifiers which contain the value. Thus, columns can be condensed in this manner and/or can be searched faster.”; para. [0061]. Examiner note: it is note that the prior art of Kolluri Venkata Sesha et al. (US 20200073982 A1) also teach a chatbot);
However, it is noted that the prior art of Willems does not explicitly teach “receiving, by the one or more computers, a user prompt to a chatbot; using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model; and providing, by the one or more computers, the chatbot response as a response to the user prompt.”
On the other hand, in the same field of endeavor, Kolluri Venkata Sesha teaches receiving, by the one or more computers, a user prompt to a chatbot (i.e. “chatbot 130 receives a query from a user.”; fig.2, para. [0028]; Examiner note: using a BRI the user prompt is interpreted as the query from a user);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Kolluri Venkata Sesha that teaches automated natural language agents into Willems that teaches query execution and planning with pipelining and pump operators. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to using modular chatbots to improve the functionality of computing devices via increased reliability, reducing processing resources, and improved customizability is provided by processing a natural language query (Kolluri Venkata Sesha, para. [0002]).
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model; and providing, by the one or more computers, the chatbot response as a response to the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt (i.e. “database chatbot assistants that dynamically respond to user inquiries, adjusting results provided and query-generating models employed, in response to result assessment feedback 2096.”; para. [0105]; Examiner note: using a BRI the generate a chatbot response to the user prompt is interpreted as the respond to user inquiries, adjusting results),
including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model (i.e. “The server computer 102, at block 216 makes query generation ML model adjustments based on the accepted data results 119 and revises the model with updated training data. In particular, the server computer 102 via Model Adjustment Module “MAM” 126 generates training data based, at least in part, on a selected secondary (e.g., revised primary query) and associated user inquiry. In an embodiment, the MAM retrains the ML model with the training data to generate an adjusted ML model that reflects, at least partially, the primary query after user-desired content adjustments 512, 522 are identified and processed.”; fig. 1, para. [0042], [0051], [0060]-[0061]; Examiner note: using BRI the results is transmit to the Module “MAM” which made adjustments to the ML model based on the results); and
providing, by the one or more computers, the chatbot response as a response to the user prompt (i.e. “if the server computer 102 determines that the feedback is relevant only for selected users, then the server computer assigns, at block 304, the adjusted ML model (e.g., the ML model generated with the user-specific feedback and resultant training data) to the relevant user or groups of users, and processing flow returns to block 216.”; para. [0061]; Examiner note: using a BRI the chatbot response as a response to the user prompt is interpreted as the resultant training data).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 2, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the one or more results obtained using the search index comprise data objects corresponding to terms of the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the one or more results obtained using the search index comprise data objects corresponding to terms of the user prompt (i.e. “the server computer 102 applies a primary DB query (e.g., a query based on ML-based interpretation of a user inquiry 108) to retrieve data that matches attributes 412 and filter values 414 identified by the DGQM 114 from within the database 110.”; fig. 4b, para. [0052]. Further, i.e. “The server computer 102, identifies in block 210, user desired adjustments for the results provided.”; fig. 5d, para. [0055]; Examiner note: using a BRI the data objects are interpreted as the attributes 412. Using a BRI the user desired adjustments is interpreted as the terms of the user prompt).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 3, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the one or more results obtained using the search index comprise values corresponding to terms of the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the one or more results obtained using the search index comprise values corresponding to terms of the user prompt (i.e. “the server computer 102 applies a primary DB query (e.g., a query based on ML-based interpretation of a user inquiry 108) to retrieve data that matches attributes 412 and filter values 414 identified by the DGQM 114 from within the database 110.”; fig. 4c, para. [0052]. Further, i.e. “The server computer 102, identifies in block 210, user desired adjustments for the results provided.”; fig. 5d, para. [0055]; Examiner note: using a BRI the values are interpreted as the filter values 414. Using a BRI the user desired adjustments is interpreted as the terms of the user prompt).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 4, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
Additionally, Willems teaches wherein the search index includes information determined based on structure and metadata of a data set, including at least one of data table names, data table labels, data table descriptions, column names, column labels, or column descriptions (i.e. “The computing apparatus 600 can be configured to access a database that includes at least one table, which can in turn include at least one column. The database table can store any kind of data, potentially including but not limited to definitions of scenarios, processes, and one or more configurations as well as transactional data, metadata,”; para. [0075]).
As per claim 5, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the searching comprises identifying elements that are likely to identify or disambiguate references to attributes, metrics, and other data objects referenced in the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the searching comprises identifying elements that are likely to identify or disambiguate references to attributes, metrics, and other data objects referenced in the user prompt (i.e. “the server computer 102 uses DB queries that represent target data attributes (e.g., such as the model-identified data attributes 412,422 identified within an associated user inquiry 108 and shown schematically in table 402 of FIG. 4B and table 420 of FIG. 4C, respectively) and attributes 510,522 identified within user feedback 116 (e.g., as shown schematically in table 520 of FIG. 5C and table 530 of FIG. 5D, respectively) to retrieve data items matching an associated user inquiry 108 from the database 110”; para. [0052]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 6, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the one or more results are provided to the AI/ML model such that the one or more results are used by the AI/ML model to determine data objects corresponding to terms or concepts in the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the one or more results are provided to the AI/ML model such that the one or more results are used by the AI/ML model to determine data objects corresponding to terms or concepts in the user prompt (i.e. “In an embodiment, the MAM retrains the ML model with the training data to generate an adjusted ML model that reflects, at least partially, the primary query after user-desired content adjustments 512, 522 are identified and processed.”; para. [0060]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 7, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
Additionally, Willems teaches wherein the one or more results comprise information that specifies relationships between terms of the user prompt and data objects, such as data indicating the data objects identified as being most closely related to particular words or phrases of the user prompt (i.e. “the chunks 516, 518 are illustrated as containing matching values for columns X and Y, in some implementations, the chunks 516, 518 may only contain document identifiers. Including the matching values for columns X and/or Y”; para. [0060]).
As per claim 11, Willems teaches a system comprising: one or more computers (i.e. “the system 100 may include one or more user equipment 102A-N, such as a computer,”; para. [0023]); and
one or more computer-readable media storing instructions that are operable, when executed by the one or more computers, to cause the system to perform operations (i.e. “computing apparatus 600 may include one or more processors such as processor 610 to execute instructions that may implement operations”; para. [0070]) comprising:
storing, by the one or more computers, a search index for data sets (i.e. “storing the first data portion in a predetermined memory location …..the first data portion can comprise a data table having one or more rows and one or more columns.”; para. [0004]; Examiner note: using a BRI the search index for data sets is interpreted as the data table),
wherein the search index describes data objects of the data sets and values for the data objects in the data sets (i.e. “the data table 590 can include M columns and/or N rows of data. In some aspects, N can refer to a document identifier associated with a particular entry, as opposed to an identifier for a row (e.g., plain indices to identify a physical row). The data can take any form (e.g., alphanumeric values) and/or the form of the data in the columns/rows can be dependent upon the type of table 590 (e.g., column store, row store, hash table, dictionary, and/or the like).”; para. [0055]; Examiner note: using a BRI the data objects are interpreted as the particular entry. Using a BRI the values for the data objects are interpreted as the e.g., alphanumeric values);
in response to receiving the user prompt (i.e. “in response to receipt of a query instantiated by a user”; para. [0076]),
searching, by the one or more computers, for data objects and values that are relevant to the user prompt (i.e. “the pump operator 510 can pull data from a database table 590 based upon one or more functions (also referred to herein as “predicates”). For example, rows/entries from the table can be retrieved based upon whether “(X>14) AND (Y<100)” is satisfied. In an example implementation, “(X>14)” can refer to whether a value stored in the column indexed ‘X’ is greater than a value of ‘14’, and/or “(Y<100)” can refer to whether a value stored in the column indexed ‘Y’ is less than a value of ‘100’.”; para. [0056]; Examiner note: using a BRI the data objects are X and Y. using a BRI The value is 14 and 100),
including using the search index to search for data objects and values of one or more data sets that the chatbot is configured to access (i.e. “Based upon these predicates, rows (or some portion thereof) which match both (“AND”) conditions can be pulled/retrieved from the table 590 and/or loaded in memory (e.g., in a cache, heap, main memory, etc.).”; para. [0056]. Further, i.e. “dictionaries can be maintained, which can contain entries for each unique value within a column, along with corresponding document identifiers which contain the value. Thus, columns can be condensed in this manner and/or can be searched faster.”; para. [0061]. Examiner note: it is note that the prior art of Kolluri Venkata Sesha et al. (US 20200073982 A1) also teach a chatbot);
However, it is noted that the prior art of Willems does not explicitly teach “receiving, by the one or more computers, a user prompt to a chatbot; using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model; and providing, by the one or more computers, the chatbot response as a response to the user prompt.”
On the other hand, in the same field of endeavor, Kolluri Venkata Sesha teaches receiving, by the one or more computers, a user prompt to a chatbot (i.e. “chatbot 130 receives a query from a user.”; fig.2, para. [0028]; Examiner note: using a BRI the user prompt is interpreted as the query from a user);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Kolluri Venkata Sesha that teaches automated natural language agents into Willems that teaches query execution and planning with pipelining and pump operators. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to using modular chatbots to improve the functionality of computing devices via increased reliability, reducing processing resources, and improved customizability is provided by processing a natural language query (Kolluri Venkata Sesha, para. [0002]).
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model; and providing, by the one or more computers, the chatbot response as a response to the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt (i.e. “database chatbot assistants that dynamically respond to user inquiries, adjusting results provided and query-generating models employed, in response to result assessment feedback 2096.”; para. [0105]; Examiner note: using a BRI the generate a chatbot response to the user prompt is interpreted as the respond to user inquiries, adjusting results),
including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model (i.e. “The server computer 102, at block 216 makes query generation ML model adjustments based on the accepted data results 119 and revises the model with updated training data. In particular, the server computer 102 via Model Adjustment Module “MAM” 126 generates training data based, at least in part, on a selected secondary (e.g., revised primary query) and associated user inquiry. In an embodiment, the MAM retrains the ML model with the training data to generate an adjusted ML model that reflects, at least partially, the primary query after user-desired content adjustments 512, 522 are identified and processed.”; fig. 1, para. [0042], [0051], [0060]-[0061]; Examiner note: using BRI the results is transmit to the Module “MAM” which made adjustments to the ML model based on the results); and
providing, by the one or more computers, the chatbot response as a response to the user prompt (i.e. “if the server computer 102 determines that the feedback is relevant only for selected users, then the server computer assigns, at block 304, the adjusted ML model (e.g., the ML model generated with the user-specific feedback and resultant training data) to the relevant user or groups of users, and processing flow returns to block 216.”; para. [0061]; Examiner note: using a BRI the chatbot response as a response to the user prompt is interpreted as the resultant training data).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 12, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 11 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the one or more results obtained using the search index comprise data objects corresponding to terms of the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the one or more results obtained using the search index comprise data objects corresponding to terms of the user prompt (i.e. “the server computer 102 applies a primary DB query (e.g., a query based on ML-based interpretation of a user inquiry 108) to retrieve data that matches attributes 412 and filter values 414 identified by the DGQM 114 from within the database 110.”; para. [0052]. Further, i.e. “The server computer 102, identifies in block 210, user desired adjustments for the results provided.”; fig. 5d, para. [0055]; Examiner note: using a BRI the data objects are interpreted as the attributes 412. Using a BRI the user desired adjustments is interpreted as the terms of the user prompt).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 13, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 11 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the one or more results obtained using the search index comprise values corresponding to terms of the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the one or more results obtained using the search index comprise values corresponding to terms of the user prompt (i.e. “the server computer 102 applies a primary DB query (e.g., a query based on ML-based interpretation of a user inquiry 108) to retrieve data that matches attributes 412 and filter values 414 identified by the DGQM 114 from within the database 110.”; para. [0052]. Further, i.e. “The server computer 102, identifies in block 210, user desired adjustments for the results provided.”; fig. 5d, para. [0055]; Examiner note: using a BRI the values are interpreted as the filter values 414. Using a BRI the user desired adjustments is interpreted as the terms of the user prompt).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 14, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 11 above.
Additionally, Willems teaches wherein the search index includes information determined based on structure and metadata of a data set, including at least one of data table names, data table labels, data table descriptions, column names, column labels, or column descriptions (i.e. “The computing apparatus 600 can be configured to access a database that includes at least one table, which can in turn include at least one column. The database table can store any kind of data, potentially including but not limited to definitions of scenarios, processes, and one or more configurations as well as transactional data, metadata,”; para. [0075]).
As per claim 15, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 11 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the searching comprises identifying elements that are likely to identify or disambiguate references to attributes, metrics, and other data objects referenced in the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the searching comprises identifying elements that are likely to identify or disambiguate references to attributes, metrics, and other data objects referenced in the user prompt (i.e. “the server computer 102 uses DB queries that represent target data attributes (e.g., such as the model-identified data attributes 412,422 identified within an associated user inquiry 108 and shown schematically in table 402 of FIG. 4B and table 420 of FIG. 4C, respectively) and attributes 510,522 identified within user feedback 116 (e.g., as shown schematically in table 520 of FIG. 5C and table 530 of FIG. 5D, respectively) to retrieve data items matching an associated user inquiry 108 from the database 110”; para. [0052]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 16, Willems teaches one or more non-transitory computer-readable media storing instructions that are operable, when executed by one or more computers, to cause the one or more computers to perform operations (i.e. “A memory, which can include a computer-readable storage medium, may include, encode, store, or the like one or more programs that cause one or more processors to perform one or more of the operations”; para. [0007]) comprising
storing, by the one or more computers, a search index for data sets (i.e. “storing the first data portion in a predetermined memory location …..the first data portion can comprise a data table having one or more rows and one or more columns.”; para. [0004]; Examiner note: using a BRI the search index for data sets is interpreted as the data table),
wherein the search index describes data objects of the data sets and values for the data objects in the data sets (i.e. “the data table 590 can include M columns and/or N rows of data. In some aspects, N can refer to a document identifier associated with a particular entry, as opposed to an identifier for a row (e.g., plain indices to identify a physical row). The data can take any form (e.g., alphanumeric values) and/or the form of the data in the columns/rows can be dependent upon the type of table 590 (e.g., column store, row store, hash table, dictionary, and/or the like).”; para. [0055]; Examiner note: using a BRI the data objects are interpreted as the particular entry. Using a BRI the values for the data objects are interpreted as the e.g., alphanumeric values);
in response to receiving the user prompt (i.e. “in response to receipt of a query instantiated by a user”; para. [0076]),
searching, by the one or more computers, for data objects and values that are relevant to the user prompt (i.e. “the pump operator 510 can pull data from a database table 590 based upon one or more functions (also referred to herein as “predicates”). For example, rows/entries from the table can be retrieved based upon whether “(X>14) AND (Y<100)” is satisfied. In an example implementation, “(X>14)” can refer to whether a value stored in the column indexed ‘X’ is greater than a value of ‘14’, and/or “(Y<100)” can refer to whether a value stored in the column indexed ‘Y’ is less than a value of ‘100’.”; para. [0056]; Examiner note: using a BRI the data objects are X and Y. using a BRI The value is 14 and 100),
including using the search index to search for data objects and values of one or more data sets that the chatbot is configured to access (i.e. “Based upon these predicates, rows (or some portion thereof) which match both (“AND”) conditions can be pulled/retrieved from the table 590 and/or loaded in memory (e.g., in a cache, heap, main memory, etc.).”; para. [0056]. Further, i.e. “dictionaries can be maintained, which can contain entries for each unique value within a column, along with corresponding document identifiers which contain the value. Thus, columns can be condensed in this manner and/or can be searched faster.”; para. [0061]. Examiner note: it is note that the prior art of Kolluri Venkata Sesha et al. (US 20200073982 A1) also teach a chatbot);
However, it is noted that the prior art of Willems does not explicitly teach “receiving, by the one or more computers, a user prompt to a chatbot;”
On the other hand, in the same field of endeavor, Kolluri Venkata Sesha teaches receiving, by the one or more computers, a user prompt to a chatbot (i.e. “chatbot 130 receives a query from a user.”; fig.2, para. [0028]; Examiner note: using a BRI the user prompt is interpreted as the query from a user);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Kolluri Venkata Sesha that teaches automated natural language agents into Willems that teaches query execution and planning with pipelining and pump operators. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to using modular chatbots to improve the functionality of computing devices via increased reliability, reducing processing resources, and improved customizability is provided by processing a natural language query (Kolluri Venkata Sesha, para. [0002]).
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt, including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model; and providing, by the one or more computers, the chatbot response as a response to the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches using, by the one or more computers, one or more results obtained using the search index to generate a chatbot response to the user prompt (i.e. “database chatbot assistants that dynamically respond to user inquiries, adjusting results provided and query-generating models employed, in response to result assessment feedback 2096.”; para. [0105]; Examiner note: using a BRI the generate a chatbot response to the user prompt is interpreted as the respond to user inquiries, adjusting results),
including providing the one or more results to an artificial intelligence and/or machine learning (AI/ML) model (i.e. “The server computer 102, at block 216 makes query generation ML model adjustments based on the accepted data results 119 and revises the model with updated training data. In particular, the server computer 102 via Model Adjustment Module “MAM” 126 generates training data based, at least in part, on a selected secondary (e.g., revised primary query) and associated user inquiry. In an embodiment, the MAM retrains the ML model with the training data to generate an adjusted ML model that reflects, at least partially, the primary query after user-desired content adjustments 512, 522 are identified and processed.”; fig. 1, para. [0042], [0051], [0060]-[0061]; Examiner note: using BRI the results is transmit to the Module “MAM” which made adjustments to the ML model based on the results); and
providing, by the one or more computers, the chatbot response as a response to the user prompt (i.e. “if the server computer 102 determines that the feedback is relevant only for selected users, then the server computer assigns, at block 304, the adjusted ML model (e.g., the ML model generated with the user-specific feedback and resultant training data) to the relevant user or groups of users, and processing flow returns to block 216.”; para. [0061]; Examiner note: using a BRI the chatbot response as a response to the user prompt is interpreted as the resultant training data).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 17, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 16 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the one or more results obtained using the search index comprise data objects corresponding to terms of the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the one or more results obtained using the search index comprise data objects corresponding to terms of the user prompt (i.e. “the server computer 102 applies a primary DB query (e.g., a query based on ML-based interpretation of a user inquiry 108) to retrieve data that matches attributes 412 and filter values 414 identified by the DGQM 114 from within the database 110.”; para. [0052]. Further, i.e. “The server computer 102, identifies in block 210, user desired adjustments for the results provided.”; fig. 5d, para. [0055]; Examiner note: using a BRI the data objects are interpreted as the attributes 412. Using a BRI the user desired adjustments is interpreted as the terms of the user prompt).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 18, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 16 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the one or more results obtained using the search index comprise values corresponding to terms of the user prompt.”
On the other hand, in the same field of endeavor, Wang teaches wherein the one or more results obtained using the search index comprise values corresponding to terms of the user prompt (i.e. “the server computer 102 applies a primary DB query (e.g., a query based on ML-based interpretation of a user inquiry 108) to retrieve data that matches attributes 412 and filter values 414 identified by the DGQM 114 from within the database 110.”; para. [0052]. Further, i.e. “The server computer 102, identifies in block 210, user desired adjustments for the results provided.”; fig. 5d, para. [0055]; Examiner note: using a BRI the values are interpreted as the filter values 414. Using a BRI the user desired adjustments is interpreted as the terms of the user prompt).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
As per claim 19, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 11 above.
Additionally, Willems teaches wherein the search index includes information determined based on structure and metadata of a data set, including at least one of data table names, data table labels, data table descriptions, column names, column labels, or column descriptions (i.e. “The computing apparatus 600 can be configured to access a database that includes at least one table, which can in turn include at least one column. The database table can store any kind of data, potentially including but not limited to definitions of scenarios, processes, and one or more configurations as well as transactional data, metadata,”; para. [0075]).
As per claim 20, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 16 above.
However, it is noted that the combination of prior arts of Willems and Kolluri Venkata Sesha do not explicitly teach “wherein the searching comprises identifying elements that are likely to identify or disambiguate references to attributes, metrics, and other data objects referenced in the user prompt”
On the other hand, in the same field of endeavor, Wang teaches wherein the searching comprises identifying elements that are likely to identify or disambiguate references to attributes, metrics, and other data objects referenced in the user prompt (i.e. “the server computer 102 uses DB queries that represent target data attributes (e.g., such as the model-identified data attributes 412,422 identified within an associated user inquiry 108 and shown schematically in table 402 of FIG. 4B and table 420 of FIG. 4C, respectively) and attributes 510,522 identified within user feedback 116 (e.g., as shown schematically in table 520 of FIG. 5C and table 530 of FIG. 5D, respectively) to retrieve data items matching an associated user inquiry 108 from the database 110”; para. [0052]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Wang that teaches chatbot agents that respond to requests for information into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, and Kolluri Venkata Sesha that teaches automated natural language agents. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow AI models to recognize terms with specialized meanings within the associated domain, as this improves accuracy and other aspects of model performance for all users (Wang, para. [0002], [0050]).
7. Claims 8 and 10 are rejected under 35 U.S.C. § 103 as being unpatentable over Willems et al. (US 20180150514 A1) in view of Kolluri Venkata Sesha et al. (US 20200073982 A1) in further view of Wang et al. (US 20230041181 A1) still in further view of Marin et al. (US 20190034780 A1).
As per claim 8, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
However, it is noted that the combination of prior arts of Willems, Kolluri Venkata Sesha and Wang do not explicitly teach “wherein the searching comprises searching for similarity using a vector database, including by comparing the distance of embeddings for terms or concepts of the user prompt with stored embeddings.”
On the other hand, in the same field of endeavor, Marin teaches wherein the searching comprises searching for similarity using a vector database, including by comparing the distance of embeddings for terms or concepts of the user prompt with stored embeddings (i.e. “executing the knowledge graph search action against a knowledge graph comprising stored recipes and semantic representations of real world information;”; para. [0171]. Further, i.e. “the top N acts that best match the user input (e.g., have the highest confidence scores) are selected to execute.”; para. [0125]; Examiner note: using a BRI the concepts of the user prompt is interpreted as the semantic representations of real world information. Using a BRI the stored embeddings is interpreted as the stored recipes).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Marin that teaches implementing digital assistants and conversational search systems into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, Kolluri Venkata Sesha that teaches automated natural language agents, and Wang that teaches chatbot agents that respond to requests for information. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow search engines to receive queries in the form of text phrases and/or keywords, as this enables them to return relevant search results (Marin, para. [0003]).
As per claim 10, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
However, it is noted that the combination of prior arts of Willems, Kolluri Venkata Sesha and Wang do not explicitly teach “wherein the one or more results include at least one of semantic graph content or knowledge base content.”
On the other hand, in the same field of endeavor, Marin teaches wherein the one or more results include at least one of semantic graph content or knowledge base content (i.e. “the policy engine selects the search_KG recipe to run. The policy engine outputs the selected action and the search_KG is executed with the semantic input and/or context as input. The output entity includes a knowledge entity that describes what sunrise is, a language understanding recipe, a chatbot recipe,”; para. [0100]; Examiner note: using a BRI the semantic graph content or knowledge base content is interpreted as the what sunrise is, a language understanding recipe, a chatbot recipe).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Marin that teaches implementing digital assistants and conversational search systems into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, Kolluri Venkata Sesha that teaches automated natural language agents, and Wang that teaches chatbot agents that respond to requests for information. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to allow search engines to receive queries in the form of text phrases and/or keywords, as this enables them to return relevant search results (Marin, para. [0003]).
8. Claim 9 is rejected under 35 U.S.C. § 103 as being unpatentable over Willems et al. (US 20180150514 A1) in view of Kolluri Venkata Sesha et al. (US 20200073982 A1) in further view of Wang et al. (US 20230041181 A1) still in further view of Dispensa et al. (US 20170329827 A1).
As per claim 9, Willems, Kolluri Venkata Sesha and Wang teach all the limitations as discussed in claim 1 above.
However, it is noted that the combination of prior arts of Willems, Kolluri Venkata Sesha and Wang do not explicitly teach “comprising using the search index to identify which data set or data sets, from among multiple data sets, should be used to generate an answer to the user prompt.”
On the other hand, in the same field of endeavor, Dispensa teaches comprising using the search index to identify which data set or data sets, from among multiple data sets, should be used to generate an answer to the user prompt (i.e. “a structured result may be retrieved based on its location in a dataset (e.g., the result being located in a field in which the result was identified as residing), whereas structured results may be retrieved based on the result itself matching the query.”; para. [0071]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teachings of Dispensa that teaches searching multiple data sets into the combination of the prior arts of Willems that teaches query execution and planning with pipelining and pump operators, Kolluri Venkata Sesha that teaches automated natural language agents, and Wang that teaches chatbot agents that respond to requests for information. Additionally, this can handle responses to queries very quickly in order to satisfy systems requirements with respect to transaction time.
The motivation for doing so would be to selectively expanding certain search results and providing alternative queries in response to a search because it can more relevant results to queries (Dispensa, para. [0006]).
Prior Art of Record
9. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kuppur et al. (US 20260162009 A1), teaches a process for enhancing generative model robustness.
Mishra et al. (US 12619668 B1), teaches techniques for utilizing machine learning to generate a question and answer pair for a conversational agent.
Luo et al. (US 20260072908 A1), teaches enabling search and query functions.
Angeles (US 20260037863 A1), teaches gamifying physical assets, digital assets, and virtual assets through advertising and e-commerce, and system and method for personalized digital twin LLM chatbot gamification in e-commerce and emotional intelligence development.
Kumaresan et al. (US 20250335715 A1), teaches a chatbot system for answering natural language questions with answers from non-tabular and/or tabular data sources.
Shimshock et al. (US 12332878 B1), teaches generating a response to a natural-language query from an entity associated with an organization.
Coursey (US 12210849 B1), teaches an AI language virtual agent having self-improvement features and which uses language modeling and tree search techniques.
Conclusion
10. Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANTONIO CAIA DO whose telephone number is (469)295-9251. The examiner can normally be reached on Monday - Friday / 06:30 to 16:30.
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, Ng, Amy can be reached on (571) 270-1698. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ANTONIO J CAIA DO/
Examiner, Art Unit 2164
Prosecution Insights