DETAILED ACTION
Claims 2-21 are pending in the Instant Application.
Claims 2-21 are rejected (Final Rejection).
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 2-5 and 8-12 and 15-19 are rejected under 35 U.S.C. 103 as being unpatentable over Tater et al. (“Tater”), United States Patent Application Publication No. 2023/0131495, in view of Hagger et al. (“Hagger”), Untied States Patent Application Publication No. 2014/0365502.
As per claim 2, Tater discloses a computer-implemented method comprising:
receiving an input ([0052]-[[0053] wherein a task or query is received as input);
inferring that a first category of data is needed ([0027] wherein it can be inferred a first category of data is needed based on user input, where each agent is good at serving a certain category of data (recognized as a skill or service in the prior art));
retrieving information, using a first retrieval model, data based on the input and the first category of data ([0028] wherein each of the agents may retrieve information based on the first category of data);
generating a prompt comprising one or more passages based on the retrieved information ([0022] and [0025] wherein a prompt is generated from the retrieve information);
determining whether the one or more passages contain sufficient information to satisfy criteria based on the input ([0055] wherein determining a confidence score that the agent’s generated passage (response in the prior art) has sufficient information to satisfy criteria based on the input);
inferring that a different category of data is needed if it is determined that there is not enough information to satisfy the criteria ([0055] wherein there is no agent with 100% inventory, then another agent/category must be used); retrieving, based on the different category of data and using a different retrieval model, additional information via an iterative process if it is determined that there is not enough information to satisfy the criteria [0055] wherein a different agent/category retrieves a response. If it is determined that there is not enough information to satisfy a criteria); generating an output result based on the one or more passages ([0054] wherein an output is generated based on the agent/model with the highest confidence based on the passages); and displaying the output result ([0054] wherein the output is displayed to the user in a chat), but does not disclose where the data is from one or more enterprise data sources. However, Hagger teaches where the data is from one or more enterprise data sources ([0016] wherein Watson™ describes querying enterprise data).
Both Tater and Hagger describe machine learning models to answer natural language questions. One could support the documents being part of an enterprise system as in Hagger with the multiple models trained on different categories as in Tater to teach the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the method of using multiple learning models to answer questions as in Tater with the questions being on enterprise data as in Hagger in order to allow for massive data gathering from different domains as required in today’s business environments.
As per claim 3, note the rejection of claim 2 where Tater and Hagger are combined. The combination teaches the method of claim 2. Tater further discloses wherein the step of retrieving additional information via the iterative process further comprises: generating a new query ([0055] wherein a new query can be generated for an agent with a better knowledge of the word “plot”); retrieving additional information from one or more enterprise data sources based on the new query ([0055] wherein that agent can come up with a response); and generating a new prompt comprising one or more additional passages based on the additional retrieved information ([0054] wherein an output is generated based on the agent/model with the highest confidence based on the passages).
As per claim 4, note the rejection of claim 2 where Tater and Hagger are combined. The combination teaches the method of claim 2. Tater further discloses generating a rationale based on the one or more passages ([0035] wherein the rationale is generated that the word “plot” is not understood); and wherein the step of retrieving additional information via the iterative process further comprises: generating a new query; retrieving additional information from one or more enterprise data sources based on the new query ([0035] wherein another agent understands the word and can be used to query to retrieve additional information); and generating a new prompt comprising one or more additional passages based on the additional retrieved information and the rationale ([0035] wherein another agent’s response is provided as a result).
As per claim 5, note the rejection of claim 2 where Tater and Hagger are combined. The combination teaches the method of claim 2. Tater further discloses wherein the step of determining whether the one or more passages contain sufficient information to satisfy the criteria comprises: determining whether a number of passages containing relevant information exceeds a threshold ([0033] wherein a score of 100% confidence means the number of passages has exceeded the confidence threshold).
As per claim 8, note the rejection of claim 2 where Tater and Hagger are combined. The combination teaches the method of claim 2. Tater further discloses receiving feedback from a user ([0048] wherein a user can provide feedback using icons); and improving an accuracy of the output result based on the user feedback ([0048] wherein learning and updating is improving the accuracy).
As per claim 9, claim 9 is the product that performs the method of claim 2 and is rejected for the same rationale and reasoning.
As per claim 10, claim 10 is the product that performs the method of claim 3 and is rejected for the same rationale and reasoning.
As per claim 11, claim 11 is the product that performs the method of claim 4 and is rejected for the same rationale and reasoning.
As per claim 12, claim 12 is the product that performs the method of claim 5 and is rejected for the same rationale and reasoning.
As per claim 15, claim 15 is the product that performs the method of claim 8 and is rejected for the same rationale and reasoning.
As per claim 16, Tater discloses a system comprising: one or more memory devices storing instructions and one or more processing devices communicatively coupled to the one or more memory devices ([0067]), wherein the one or more processing devices execute the instructions to perform the method of claim 2. Therefore, the claim is rejected for the same rationale and reasoning as claim 2.
As per claim 17, claim 17 is the system that performs the method of claim 3 and is rejected for the same rationale and reasoning.
As per claim 18, claim 18 is the system that performs the method of claim 4 and is rejected for the same rationale and reasoning.
As per claim 19, claim 19 is the system that performs the method of claim 5 and is rejected for the same rationale and reasoning.
Claims 6, 7, 13, 14, 20 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Tater in further view of Hagger in view of RODRIQUEZ et al. (“Rodriguez”), United States Patent Application Publication No. 2022/0246144.
As per claim 6 note the rejection of claim 2 where Tater and Hagger are combined. The combination teaches the method of claim 2, but does not disclose stopping the iterative process after a number of iterations has reached a limit. However, Rodriquez teaches stopping the iterative process after a number of iterations has reached a limit ([0032] wherein the number of iterations is limited).
Both Tater and Rodriguez disambiguate an inquiry of a user. One could use the limited number of iterations from Rodriguez with the iterations performed in Hagger to teach the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the method of iteratively determining if a satisfactory output by confidence score as determined for a user input in Tater with the limiting of the number of iterations in Rodriquez in order to be ablet to stop providing ineffective options and changing focus of the inquiry.
As per claim 7, note the rejection of claim 6 where Tater, Hagger and Rodriquez are combined. The combination teaches the method of claim 6. Hagger further discloses wherein the output result comprises: an indication that an answer to the input could not be determined ([0082] wherein no answer can be found is output.)
As per claim 13, claim 13 is the product that performs the method of claim 6 and is rejected for the same rationale and reasoning.
As per claim 14, claim 14 is the product that performs the method of claim 7 and is rejected for the same rationale and reasoning.
As per claim 20, claim 20 is the system that performs the method of claim 6 and is rejected for the same rationale and reasoning.
As per claim 21, claim 21 is the system that performs the method of claim 7 and is rejected for the same rationale and reasoning.
Response to Arguments
Applicant’s arguments with respect to claims 2-21 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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 KANNAN SHANMUGASUNDARAM whose telephone number is (571)270-7763. The examiner can normally be reached M-F 9:00 AM -6:00 PM.
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, Charles Rones can be reached at (571) 272-4085. 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.
/KANNAN SHANMUGASUNDARAM/Primary Examiner, Art Unit 2168
Prosecution Insights