DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This Office Action is in response to the claim amendment filed on June 1, 2026 and wherein claims 1, 17, 20 amended.
In virtue of this communication, claims 1-20 are currently pending in this Office Action.
The Office appreciates the explanation of the amendment and analyses of the prior arts, and however, although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993) and MPEP 2145.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a), as failing to comply with the written description requirement. The claims contain subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor(s) or joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 amended by adding “generating, a model-generated machine readable query based at least in part on the natural language user query, the one or more prompts and …” which is not supported by the original disclosure. For example, claim 9 recites “embedding the natural language user query within the one or more prompts wherein a first prompt, of the one or more prompts causes the machine learning model to generate the model-generated machine-readable query to query …” and similar to para 31, 152, 222, etc. in USPGPub 20250110976 A1, i.e., “generating, a model-generated machine readable query” is based on “the one or more prompts” that has been embedded with NL “user query”, and there is no disclosure for both NL “user query” and the “one or more prompts” to be used for generating “a model-generated machine readable query”. Claims 2-16 are rejected due to the dependencies to claim 1.
Claims 17, 20 are rejected for the at least similar reasons described in claim 1 above because claims 17, 20 recited similar deficient features as recited in claim 1. Claims 18-19 are rejected due to the dependencies to claim 17.
Claim 5 depends on claim 1 and further recites “pre-processing the natural language user query” and parent claim 1 recites “preprocessing the natural language user query by determining an intent …”. Because claim 5 incorporated all limitations of its parent claim 1 under 35 U.S.C. 112(d), there is no disclosure that “the natural language user query” is processed by both “preprocessing … by determining an intent …” as recited in parent claim 1 and “pre-processing …” as recited in claim 5. Claims 7-9 are rejected due to the dependencies to claim 5.
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.
Claim 9 is rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which applicant regards as the invention.
Claim 9 recited “the one or more prompts” in lines 6-7 of claim 9, which is confusing because it is unclear whether this term is referred back to selected “one or more prompts” as recited in claim 9 or to selected “one or more prompts” as recited in parent claim 1 and thus, renders claim indefinite.
Claim Rejections - 35 USC § 112(d)
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 5 is rejected under 35 U.S.C. 112(d), as being of improper dependent form for failing to further limit the subject matter of the claim upon which they depend, or for failing to include all the limitations of the claim upon which they depend.
Claim 5 depends on claim 1 and recites “prior to generating the model-generated machine-readable query, pre-processing the natural language user query, wherein generating the model-generated machine-readable query comprises generating, based at least in part on the pre-processed natural language user query and using the machine learning model, the model-generated machine-readable query” which is not considered to be a further limitation to parent claim 1 because claim 1 recites “generating, a model-generated machine-readable query based at least on … the one or more prompts” and “the one or more prompts” selected based on “intent” generated by the “preprocessing”, i.e., claim 5 recited a broader limitation, e.g., “pre-processed natural language user query”, than the narrow limitation, e.g., “preprocessing … by determining an intent”, etc., as recited in parent claim 1. Claims 6-9 are rejected due to the dependencies to claim 5. It is recommended to cancel claims 5-9.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5, 9-10, 13-20 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 11726994 B1, hereinafter Wang) and in view of reference Aalipour Hafshejani et al. (US 20220245134 A1, hereinafter Aalipour).
Claim 1: Wang teaches a method of an identity management system (title and abstract, ln 1-10, a system in fig. 1, a business intelligence service in fig. 2 and implementing natural language query processing system 110 in fig. 1), comprising:
receiving, from a client device (client 270 in fig. 2, comprising web browser, or plug-in module, col7, ln 23-40) associated with a client organization (receiving metadata with the client request is about “weekly revenue for X products”, col 10, ln 46-67, i.e., associated with an organization inherently), a natural language user query (natural language query 140 received by natural language query processing system 110 in fig. 1 and at step 810 in fig. 8), wherein the natural language user query comprises a request for information (e.g., requesting a retrieve of information about “Weekly Revenue for X products” above) related to configuration data or a system event occurring in the identity management system (related to WoW change in revenue associated with ads, col 20, ln3-4) and associated with the client organization (e.g., requesting for materialized view management platform 210 such as creating a materialized view from different data sources of the other provider network services and identify one or more as a target data source, etc., col 7, ln 25-29 and from the client 270 through the web browser, etc. and further example, requesting “Show me monthly sales per product for the last 3 months”, col 18, ln 16-24);
preprocessing the natural language user query for one or more prompts (via the lightweight data set selection 401 and/or cell value search 405 to generate possible cell values references in the natural language query 306 in fig. 4, col 17, ln 35-40);
generating, a model-generated machine-readable query (entity recognition labels outputted from an output layer of the entity recognition model 410, or query input bundle 408 outputted from entity linkage candidate index search 420 and in fig. 4, col 18, ln 60-67, col 19, ln 1-29 or linkages with selected data sets 506 through data set selection model 520, col 20, ln 62-67) based at least in part on the natural language user query (through light weight data set selection 401 in fig. 4) one or mor prompts (selected lightweight data set selected through element 401 and search cell value 409 in fig. 4) and using a machine learning model (entity recognition model 410 as machine learning model trained to identify all entities within the query 306 in figs. 3-4, col 17, ln 41-49 and e.g., deep learning model by using a neural network trained, col 18, ln 38-43), , wherein the model-generated machine-readable query is generated in a machine-readable language (e.g., type of labels, column names, column name index, cell values, tokenized column or cell values, etc., as machine-readable language, and discussed above, col 18, ln 60-67, col 19, ln 1-29 or generated by deep learning model implemented by data set selection model 520, col 20, ln 62-67) associated with the identity management system (associated with a business intelligence service provided by the system, col 18, ln 60-67, col 19, ln 1-29 and discussed above);
retrieving, based at least in part on executing the model-generated machine-readable query (including entity recognition model 410 as machine learning model trained to identify all entities within the query 306 in figs. 3-4, col 17, ln 41-49 and e.g., deep learning model by using a neural network trained, col 18, ln 38-43 or through generating intermediate representation via the intermediate representation generation model 530 in fig. 5), information responsive to the natural language user query (desired result for the natural language query is obtained or retrieved from stored fixed schema data sets 122 through generated intermediate representation 508 of the natural language query and representation execution formatting 308 to business intelligence service 210, etc., through a transformation of the representation into a business intelligence service 210, and to obtain the result as the information at step 620 in fig. 6, col 22, ln 61-67, col 23, ln 1-3, retrieve data from database, col 5, ln 56-67, col 6, ln 1-9 or query restatement by the query restatement generation 610 based on intermediate representation 508 in fig. 6); and
outputting the information responsive to the natural language user query (the business intelligence service 210 includes analysis and visualization execution 214, the element 214 is to outputting the results in a text form and/or displayable form such as charts, graphs, etc., that answers the natural language query as result 150, col 3, 44-48, e.g., the result is displayed 730 in fig. 7).
However, Wang does not explicitly teaching wherein pre-processing the natural language user query comprises: determining an intent associated with the natural language user query; and selecting one or more prompts based at least in part on the determined intent associated with the natural language user query.
Aalipour teaches an analogous field of endeavor by disclosing a method (title and abstract, ln 1-11 and method steps in figs.4-5) and wherein pre-processing the natural language user query is disclosed (user’s question 401 is processed by natural language processing 410, and as input to a question answering computing device 102, intent classifier entity tagger 413, etc., in fig. 4) comprising determining an intent associated with the natural language user query (an intent is determined as product_info_nutrient for the request “Does great value milk contain Vitamin D3”, para 40); selecting one or more prompts based at least in part on the determined intent associated with the natural language user query (performing “SELECT X FROM KB WHERE root=Y and SELECT brand From DB WHERE root=Milk” as a pseudo-SQL query to the knowledge database 116, etc., and “great value” and “horizon organic” as results selected from the knowledge database 116 and as prompts to the dialog manager 430 in fig. 4) for benefits of maximizing usage of data sources (independently relied on user’s request by cypher the request for accurate answer return, para 3 and regardless database type user’s query may be related to, para 4).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied the pre-processing of the natural language user query and wherein the pre-processing of the natural language user query comprises: determining the intent associated with the natural language user query; selecting one or more prompts based at least in part on the determined intent associated with the natural language user query, one or more prompts; as taught by Aalipour, to the pre-processing of the natural language user query in the method, as taught by Wang, for the benefits discussed above.
Claim 17 has been analyzed and rejected according to claim 1 above and the combination of Wang and Aalipour further teaches, an device associated with an identity management system (Wang, a computer system in fig. 10 and Aalipour, computing or question answering device suited for implementing the disclosed method, para 6-7), comprising: one or more memories storing processor-executable code (Wang, computer-readable storage medium coupled to the processors and storing processors executing program instructions in fig. 10, col 25, ln 47-62 and Aalipour, non-transitory computer readable medium having instructions stored thereon, para 9); and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the device to perform the method of claim 1 (Wang, discussed in claim 1 above and at least one processor for implemented the stored instructions, para 9).
Claim 20 has been analyzed and rejected according to claims 1, 17 above.
Claim 2: the combination of Wang and Aalipour further teaches, according to claim 1 above, wherein the model-generated machine-readable query is generated in a first machine-readable language (Wang, the generated entities can be read and recognized by entity linking 510 or intermediate representation generation model 530 in fig. 5 above, and discussed in claim 1 above and Aalipour, the selected contents can be read and recognized by dialog manager 430 in fig. 4), wherein the method further comprises:
outputting the model-generated machine-readable query in the first machine-readable language (Wang, outputted from entity recognition model 410 or outputted from entity linkage candidate index search 420 as query input bundle 408 in fig. 4, including the original natural language query 306 or 402, user-specified entity linkages 404, linkage candidates per entity for recognized entities, col 19, ln 25-29 or outputting an intermediate representation 508 generated based on query input bundle 408 in fig. 5 and in a language to be recognized by the following processing such as entity linking 510, data set selection model 520, intermediate representation generation model 530, etc., in fig. 5 or recognized by representation execution formatting 620 in fig. 6 and Aalipour, outputting the output from the dialog manager 430 to revise results 435 in fig. 4);
receiving an indication of a modification to the model-generated machine-readable query (Wang, prompting the user with multiple candidates linking options when comparing the evaluating confidence scores of dataset match to a minimum confidence threshold in order to update intermediate representation 508 based on the user’s selection and the query input bundle 408 in fig. 4, col 4, ln 12-23, col 20, ln 26-42 and detailed update in fig. 9 and Aalipour, received as revised result to form a final response 440 in fig. 4); and
translating the modified model-generated machine-readable query from the first machine-readable language to a second machine-readable language (Wang, via representation execution formatting 620 to format the updated intermediate representation to be executable by the analysis and visualization execution 214 of the business intelligence service 210 in fig. 2, col 5, ln 56-67, col 6, ln 1-15),
wherein retrieving the information responsive to the natural language user query comprises retrieving, based at least in part on executing the modified model-generated machine-readable query in the second machine-readable language (Wang, the updated intermediate representation is formatted for execution 308 via element 620 and to be recognized by analysis and visualization execution 214 of the business intelligence service 210 for generating the result and visualizing the result, col 5, ln 56-67, col 6, ln 1-9), the information responsive to the natural language user query (Wang, the result is obtained through the analyses and accessing the database and displayed on screen 730 corresponding to the user’s natural language query 720 in fig. 7).
Claim 3: Wang teaches, according to claim 2 above, wherein translating the modified model-generated machine-readable query (discussed in claim 2 above), except comprises compiling the modified model-generated machine-readable query in the first machine-readable language to generate the modified model-generated machine-readable query in the second machine-readable language.
Aalipour teaches an analogous field of endeavor by disclosing a method (title and abstract, ln 1-11 and method steps in figs.4-5) and wherein compiling (the query is cyphered to database query language, para 7-9, 49) is disclosed to compile the modified model-generated machine-readable query in the first machine-readable language (the intermediate representation from element 415 in fig. 4) to generate the modified model-generated machine-readable query in the second machine-readable language is disclosed (cyphered query to the knowledge base database 116 in fig. 4) for the benefits discussed in claim 1 above.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied the compiling of the modified model-generated machine-readable query in the first machine-readable language to generate the modified model-generated machine-readable query in the second machine-readable language, as taught by Aalipour, to the translating of the modified model-generated machine-readable query, as taught by Wang, for the benefits discussed above.
Claim 4: the combination of Wang and Aalipour further teaches, according to claim 1 above, wherein the retrieved information comprises the information related to the configuration data or the system event occurring in the identity management system (information (Wang, e.g., “Weekly Revenue for X products” above) related to configuration data or a system event occurring in the identity management system (Wang, related to WoW change in revenue associated with ads, col 20, ln3-4, entity “weekly”, “revenue”, etc., as configuration data about time and fund inherently) and associated with the client organization (Wang, e.g., requesting for materialized view management platform 210 such as creating a materialized view from different data sources of the other provider network services and identify one or more as a target data source, etc., col 7, ln 25-29 and from the client 270 through the web browser, etc. and further example, requesting “Show me monthly sales per product for the last 3 months”, col 18, ln 16-24, and discussed in claim 1 above).
Claim 5: the combination of Wang and Aalipour further teaches, according to claim 1 above, the method further comprising: prior to generating the model-generated machine-readable query, pre-processing the natural language user query (Wang, the intermediate representation or updated intermediate representation as the model-generated machine-readable query discussed in claim 1 above, and llightweight data set selection 401 by accessing the available dataset index 403, entity recognition model 410, etc., based on the natural language query 306 in figs. 4-5 as pre-processing and Aalipour, the discussion in claim 1 above), wherein generating the model-generated machine-readable query comprises generating, based at least in part on the pre-processed natural language user query and using the machine learning model, the model-generated machine-readable query (Wang, via the intermediate representation generation model 530 with data set selection model 520, etc., in fig. 5 and discussed in claim 1 above and Aalipour, the discussion in claim 1 above).
Claim 9: Wang teaches, according to claim 5 above, the pre-processing of the natural language user query, except explicitly teaching wherein pre-processing the natural language user query comprises: determining an intent associated with the natural language user query; selecting, based at least in part on the determined intent associated with the natural language user query, one or more prompts; and embedding the natural language user query within the one or more prompts wherein a first prompt, of the one or more prompts, causes the machine learning model to generate the model-generated machine-readable query to query one or more: system logs, security logs, configuration logs, analytics logs, threat logs, management logs, machine access logs, browser activity logs, extended detection and response XDR logs, error logs, mobile device management MDM logs, database tables, or files.
Aalipour teaches an analogous field of endeavor by disclosing a method (title and abstract, ln 1-11 and method steps in figs.4-5) and wherein pre-processing the natural language user query is disclosed (user’s question 401 is processed by natural language processing 410, and as input to a question answering computing device 102, intent classifier entity tagger 413, etc., in fig. 4) comprising determining an intent associated with the natural language user query (an intent is determined as product_info_nutrient for the request “Does great value milk contain Vitamin D3”, para 40); selecting, based at least in part on the determined intent associated with the natural language user query, one or more prompts (the knowledge based results 420 via cypher 417, etc., and prompt to the dialog manager 430 in fig. 4); and embedding the natural language user query (through NLU 410 to the KB results 420 combined with the extracted data from the knowledge base database 116) within the one or more prompts (the prompts to the dialog manager 430 in fig. 4) wherein a first prompt, of the one or more prompts, causes the machine learning model to generate the model-generated machine-readable query to query one or more (triggering the revise results 435 in fig. 4): system logs, security logs, configuration logs, analytics logs, threat logs, management logs, machine access logs, browser activity logs, extended detection and response XDR logs, error logs, mobile device management MDM logs, database tables, or files (Markush limitations, MPEP 2117, information in knowledge database 116, including products and their attributes, i.e., database tables having relationship between the product and their attributes, as files, para 40-46, etc.) for benefits of improving the performance of the query-answer system (by accurately providing answers by effective query generations, para 3, and allowing efficient retrieval of the requested entities, para 35).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied the pre-processing of the natural language user query and wherein the pre-processing of the natural language user query comprises: determining the intent associated with the natural language user query; selecting, based at least in part on the determined intent associated with the natural language user query, one or more prompts; and embedding the natural language user query within the one or more prompts wherein the first prompt, of the one or more prompts, causes the machine learning model to generate the model-generated machine-readable query to query one or more: system logs, security logs, configuration logs, analytics logs, threat logs, management logs, machine access logs, browser activity logs, extended detection and response XDR logs, error logs, mobile device management MDM logs, database tables, or files, as taught by Aalipour, to the pre-processing of the natural language user query in the method, as taught by Wang, for the benefits discussed above.
Claim 10: the combination of Wang and Aalipour further teaches, according to claim 1 above, the method further comprising: prior to executing the model-generated machine-readable query, post-processing the model-generated machine-readable query, wherein executing the model-generated machine-readable query comprises executing the post-processed model-generated machine-readable query (Wang, the intermediate representation 508 as the model-generated machine-readable query, representation execution formatting 620 being the post-processing before the execution of the intermediate representation 508 in fig. 6 and discussed in claim 1 above; while query input bundle 408 as the model-generated machine readable query in fig. 4, processing in fig. 5, including ambiguity handler 514, entity linkage model 512, etc., as the post-processing and discussed in claim 1 above and Aalipour, by revise results 435 in fig. 4).
Claim 13: the combination of Wang and Aalipour further teaches, according to claim 1 above, wherein the information responsive to the natural language user query (Wang, e.g., the query restatement via the query restatement generation 610 in fig. 6, as the information responsive to the natural language user query) comprises one or more portions (Wang, word or portion of restatement 740 in fig. 7), wherein outputting the information comprises outputting the one or more portions (Wang, 740, 730, “Showing sales by month and product name last 3 months” and displayed annotation 750 with related and displayed metadata information 760 in fig. 7 and based on user’s input through an interactive user interface, col 23, ln 57-67, col 24, ln 1-6), and wherein the method further comprises: receiving a user selection of at least one portion of the one or more portions (Wang, the interactive user interface for the user to edit metadata 760, col 24, ln 1-6); generating, based at least in part on the selected at least one portion and using the machine learning model, a natural language explanation of the selected at least one portion (Wang, the modified metadata triggering a re-execution of the natural language query in fig. 9, col 24, ln 1-6); and outputting the natural language explanation of the selected at least one portion (Wang, through the template or the annotation in fig. 7, col 23, ln 57-67, col 24, ln 1-6).
Claim 14: the combination of Wang and Aalipour further teaches, according to claim The method of claim 13, wherein the natural language explanation comprises a summarization of information associated with the at least one portion and retrieved from a plurality of data sources (Wang, retrieved from database storing column, aggregation, etc., in fig. 7, and user selected features including columns, cell values, etc., prompted by auto-complete or query assistance features through entity recognition model 410 by using the metadata snapshot 406 in fig. 4, col 17, ln 41-53 and metadata snapshot contains column features and values, col 10, ln 48-67, col 11, 13, 15).
Claim 15: the combination of Wang and Aalipour further teaches, according to claim 1, wherein the information responsive to the natural language user query comprises information associated with identity management data associated with the client organization, information associated with resources of the client organization, information associated with users of the client organization, information associated with groups associated with the client organization, information associated with access events associated with the client organization, information associated with authorization events associated with the client organization, information associated with a system configuration associated with the client organization, or any combination thereof (Wang, Markush, see MPEP 2117, the discussion in claim 1 above, e.g., “show me monthly sales per product for the last 3 months” 720 as user’s query for search service in fig. 7, e.g., identity “per product” of the organization, limitation to “3 months”, etc.,).
Claim 16: the combination of Wang and Aalipour further teaches, according to claim 1 above, the method further comprising: training the machine learning model to translate a natural language query into a machine-readable query (Wang, training the machine learning model included in intermediate representation generation model 530 in fig. 5, col 25, ln 23-35 and the trained model is used to convert or translate the query input bundle 408 to the intermediate representation to be recognized by the query restatement generation 610 and/or representation execution formatting 620 in fig. 6).
Claim 18 has been analyzed and rejected according to claims 17, 2 above.
Claim 19 has been analyzed and rejected according to claims 18, 3 above.
Claims 6-7 are rejected under 35 U.S.C. 103 as being unpatentable over Wang (above) and in view of references Aalipour (above) and Nachenberg et al. (US 7444331 B1, hereinafter Nachenberg).
Claim 6: the combination Wang and Aalipour further teaches, according to claim 5 above, wherein pre-processing the natural language user query (Wang and Aalipour, discussed in claim 5 above), except wherein the natural language user query comprises: parsing the natural language user query to determine whether the natural language user query comprises:
language that is potentially malicious, or
language that violates a constraint configured by the identity management system.
Nachenberg teaches an analogous field of endeavor by disclosing a method (title and abstract, ln 1-14 and fig. 4) and wherein receiving, from a client device associated with a client organization, a natural language user query is disclosed (receiving incoming query 410 in fig. 4, col 3, ln 61-67, col 4, ln 1-5) and wherein parsing the natural language user query (converting the query to canonical form at 412 in fig. 4) to determine whether the natural language user query (through the template query application at steps 414, 422 in fig. 4) comprises:
language that is potentially malicious, or
language that violates a constraint configured by the identity management system is disclosed (query anomalous 426 or query malicious 424 at step 422 and report the result 420) for benefits of improving the operation performance of the system (by providing safeguard to the system and avoid external attacking, col 2, ln 13-19).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied the parsing of the natural language user query to determine whether the natural language user query comprises: language that is potentially malicious, or language that violates a constraint configured by the identity management system, as taught by Nachenberg, to the pre-processing in the method, as taught by the combination of Wang and Aalipour, for the benefits discussed above.
Claim 7: the combination of Wang, Aalipour, and Nachenberg further teaches, according to claim 6 above, the method further comprising: removing the determined language; or rejecting the natural language user query (Nachenberg, reporting the detect result without executing query at step 424, 426 and 420 in fig. 4).
Claims 8, 11 are rejected under 35 U.S.C. 103 as being unpatentable over Wang (above) and in view of references Aalipour (above) and Weston et al. (US 20170277667 A1, hereinafter Weston).
Claim 8: the combination of Wang and Aalipour teaches, according to claim 5 above, the pre-processing of the natural language user query (the discussion in claim 5 above), except explicitly teaching wherein pre-processing the natural language user query comprises:
parsing the natural language user query to identify personally-identifiable information;
replacing the personally-identifiable information with a placeholder value; and caching the personally-identifiable information.
Weston teaches an analogous field of endeavor by disclosing a method (title and abstract, ln 1-18 and fig. 6) and wherein pre-processing a natural language user query is disclosed (user interaction exchanges of the data set is pre-processed, para 73) to comprise:
parsing the natural language user query to identify personally-identifiable information (identified that the request-specific information comprising one or more of name information, contact information, financial information, price information and the identification is performed based on patterns of responding to user service request, para 73-74);
replacing the personally-identifiable information with a placeholder value (the specific information is removed and replaced or anonymized with placeholder text, para 73); and caching the personally-identifiable information (the user-specific information is reused later in post-processing, para 75, i.e., stored temporarily for later usage inherently) for benefits of improving the affordability and scalability of the service system (para 21 and by providing privacy protection in accessing the public resources, 38).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied the pre-processing of the natural language user query and wherein the pre-processing of the natural language user query comprises: parsing the natural language user query to identify personally-identifiable information; and replacing the personally-identifiable information with the placeholder value; and caching the personally-identifiable information, as taught by Weston, to the pre-processing of the natural language user query in the method, as taught by Wang, for the benefits discussed above.
Claim 11 has been analyzed and rejected according to claim 10, 8 above (Weston, Weston’s placeholder text as placeholder value and discussed in claim 8 above).
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Wang (above) and in view of references Aalipour (above) and Khillar et al. (US 20210026898 A1, hereinafter Khillar).
Claim 12: the combination of Wang and Aalipour teaches, according to claim 10 above, the post-processing of the model-generated machine-readable query (discussed in claim 10 above), except explicitly teaching wherein post-processing the model-generated machine-readable query comprises:
validating, based at least in part on a syntax associated with the machine-readable language and a schema associated with a database associated with the identity management system, the model-generated machine-readable query.
Khillar teaches an analogous field of endeavor by disclosing a method (title and abstract, ln 1-15 and fig. 7) and wherein post-processing a model-generated machine-readable query is disclosed (through generate query 706 based on the received natural language input 701 in fig. 1 and validate query 707 and 708 as post-processing) and wherein the post-processing the model-generated machine-readable query comprises: validating, based at least in part on a syntax associated with the machine-readable language (rules defined by the database schema 303, para 77) and a schema associated with a database associated with the identity management system (by using database schema 303, para 76), the model-generated machine-readable query (validating through 707-708 in fig. 7) for benefits of improving the performance of query system (by formatting the queries to comply with syntax structure requirement defined by the database to be accessed, para 19, by guiding the user query input, para 49, by accurately segmenting the queries based on analysis of the user’s queries, para 70).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied the post-processing of the model-generated machine-readable query and the post-processing comprising validating, based at least in part on a syntax associated with the machine-readable language and a schema associated with a database associated with the identity management system, the model-generated machine-readable query, as taught by Khillar, to the post-processing in the method, as taught by the combination of Wang and Aalipour, for the benefits discussed above.
Response to Arguments
Applicant's arguments filed on June 1, 2026 have been fully considered and but are moot in view of the new ground(s) of rejection necessitated by the applicant amendment. Although a new ground of rejection has been used to address additional limitations that have been added to claims 1, 17, 20, a response is considered necessary for several of applicant’s arguments since references Wang and Aalipour will continue to be used to meet several claimed limitations.
With respect to amendment independent claim 1, similar to amendment claims 17, 20 applicant challenged Office’s interpretation to claimed “selecting one or more prompts based at least in part on the determined intent associated with …” and argued that Aalipour’s “map the intents and entities into the predicate representations” (Aalipour, [0037]) and “a deterministic mapping of the user’s question to an intermediate representation [0036]”, not claimed “selecting the one or more prompts …” because Aalipour disclosed “generating a cypher query [0036]), see paragraphs 3-4 of page 9, paragraphs 1-3 of page 10, and paragraph 1 of page 11 in Remarks filed on June 1, 2026.
In response to the argument above, the Office respectfully disagrees because (1) claims broadly recited “selecting one or more prompts based at least in part on … determined intent …” with no recitation of how “selecting” is performed and what “one or more prompts” is, and thus, a BRI would be applied as to claimed “selecting …” above, e.g., “take”, “pick”, etc., and (2) as discussed in the office action above, Aalipour disclosed “selects one or more prompts” (by generated query “SELECT X FROM KB WHERE root=Y”, and wherein “X” such as “great value” and “horizon organic” are selected from the knowledge database KB, as “one or more prompts” to the Aalipour’s “dialog manager” by performing “cypher query” or pseudo-SQL query to the Aalipour’s knowledge database (Aalipour, [0038]), but applicant is in silence about mapping “select” to Aalipour’s “SELECT X FROM …” as discussed in the office action above. Applicant appears to improperly interpret Aalipou’s “cypher query” to claimed “select”. Clearly, Aalipour’s accomplishment of “SELECT …” by performing “cypher query” to the database would be narrower limitation and anticipate broadly claimed “select …” above.
In the response to this office action, the Office respectfully requests that support be shown for language added to any original claims on amendment and any new claims. That is, indicate support for newly added claim language by specifically pointing to page(s) and line numbers in the specification and/or drawing figure(s). This will assist the Office in prosecuting this application.
The prior art (US 20170277667 A1 by Weston et al., US 20250094506 A1 by Sachindran et al., US 20250005288 A1 byAmatriain-Rubio et al.) made of record and not relied upon is considered pertinent to applicant's disclosure because prior art above disclosed processing of user query to form prompts and selecting prompts from the generated prompts to generate return to the user’s query, etc., which is part of the disclosures disclosed by the applicant.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LESHUI ZHANG whose telephone number is (571)270-5589. The examiner can normally be reached Monday-Friday 6:30amp-4:00pm EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vivian Chin can be reached at 571-272-7848. 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.
/LESHUI ZHANG/
Primary Examiner,
Art Unit 2695
Prosecution Insights