DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 4-5, 7-9, 11-12, 14-16, 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (U.S Pub # 20220121656) in view of Singh (U.S Pub # 20150019216).
With regards to claim 1, Zheng discloses a method comprising:
receiving, via a natural language query conversion framework, a natural language query ([0015] natural language query);
converting, via the natural language query conversion framework, the natural language query into a database query using a language model (LM) ([0015] convert natural language queries and generate database queries).
Zheng does not disclose however Singh discloses:
executing, via the natural language query conversion framework, the database query against an oil and gas (O&G) database ([0097] query for oil, gas and mining data in a table).
It would have been obvious for one of ordinary skill in the art before the date the current invention was effectively filed to have modified the system of Zheng by Singh to query a database including oil and gas data.
One of ordinary skill in the art would have been motivated to make this modification in order to filter for tables with useful content (Singh [0047]).
Claims 8 and 15 correspond to claim 1 and are rejected accordingly.
With regards to claim 2, Zheng further discloses:
appending, via the natural language query conversion framework, the natural language query with one or more database schema attributes prior to converting, via the natural language query conversion framework, the natural language query into the database query using the LM ([0033] tokenize the natural language query and label the tokens with primitive concepts prior to converting. A primitive concept may include a number (e.g., 1, 100, 12.59), a numerical operator (e.g., equals, less than, greater than, between), an aggregation (e.g., a sum, an average, a minimum, a maximum, a mode, a median), a measure field (e.g., a numerical field, an amount field, a propensity to close field), a dimension field (e.g., a string field, a region field, an account field, an owner field), a field value (e.g., Canada, emea, closed, won), a date part (e.g., day, week, quarter, today, yesterday), a date modifier (e.g., this, last, next), a sort field (e.g., top, best, ascending), or the like).
Claims 9 and 16 correspond to claim 2 and are rejected accordingly.
With regards to claim 4, Zheng does not disclose however Singh discloses:
wherein converting, via the natural language query conversion framework, the natural language query into the database query using the LM comprises using target entity detection of the natural language query ([0064] natural language may be disambiguated to identity entities).
It would have been obvious for one of ordinary skill in the art before the date the current invention was effectively filed to have modified the system of Zheng by Singh to query a database including oil and gas data.
One of ordinary skill in the art would have been motivated to make this modification in order to filter for tables with useful content (Singh [0047]).
Claims 11 and 18 correspond to claim 4 and are rejected accordingly.
With regards to claim 5, Zheng does not disclose however Singh discloses:
wherein converting, via the natural language query conversion framework, the natural language query into the database query using the LM comprises using O&G discipline classification of the natural language query ([0097] oil and gas companies).
It would have been obvious for one of ordinary skill in the art before the date the current invention was effectively filed to have modified the system of Zheng by Singh to query a database including oil and gas data.
One of ordinary skill in the art would have been motivated to make this modification in order to filter for tables with useful content (Singh [0047]).
Claims 12 and 19 correspond to claim 5 and are rejected accordingly.
With regards to claim 7, Zheng further discloses:
wherein values of the database query are in a natural language different than the natural language query ([0034] converting to a common language using utf-8 encoding may support language agnostic processing of the natural language queries 215, such that the token labeling system described herein may apply to various different languages).
Claims 14 and 20 correspond to claim 7 and are rejected accordingly.
Claims 3, 10, 17 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (U.S Pub # 20220121656) in view of Singh (U.S Pub # 20150019216) and in further view of Surepeddi (U.S Pub # 20210149886).
With regards to claim 3, Zheng does not disclose however Surepeddi discloses:
upon determining that no records were found upon execution of the database query, comparing, via the natural language query conversion framework, a predicted value with all values corresponding to a predicted attribute in the O&G database; and
replacing, via the natural language query conversion framework, the predicted value with a corrected value based on a similar value found in the O&G database ([0045, 0059] a user querying for data may receive an error if the user does not use terms which are known by the querying system, meaning that any terms or language which is unique to the user's associated organization may result in querying errors. Further iterations may correctly identify word groupings despite spelling errors. At a later iteration, the query parser may group “forcast categ ory” as a single field, having robustness against spelling errors or accidental character inserts (e.g., the misspelling of “forecast” and the extra space dividing the word “category”). The parser of the superpod 305 may use simple heuristics such as field type and proximity to disambiguate the natural language query).
It would have been obvious for one of ordinary skill in the art before the date the current invention was effectively filed to have modified the system of Zheng and Singh by Surepeddi to correct a user’s data query.
One of ordinary skill in the art would have been motivated to make this modification in order to interpret a natural language query from a user and provide an appropriate data query the user (Surepeddi [0019]).
Claims 10 and 17 correspond to claim 4 and are rejected accordingly.
Claims 6 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Zheng (U.S Pub # 20220121656) in view of Singh (U.S Pub # 20150019216) and in further view of Saxe (U.S Pub # 20230315722).
With regards to claim 6, Zheng does not disclose however Saxe discloses:
wherein the LM is a transformer-based LM ([0103] language model can be a generative pre-trained transformer).
It would have been obvious for one of ordinary skill in the art before the date the current invention was effectively filed to have modified the system of Zheng and Singh by Saxe to use a deep learning language model to translate a natural language query.
One of ordinary skill in the art would have been motivated to make this modification in order to use a ML model to infer a template query based on natural language data (Saxe [0004]).
Claim 13 corresponds to claim 6 and is rejected accordingly.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TONY WU whose telephone number is (571)272-2033. The examiner can normally be reached Monday-Friday (9-5).
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, Sanjiv Shah can be reached at (571) 272-4098. 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.
/TONY WU/ Primary Examiner, Art Unit 2166
Prosecution Insights