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 § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-5, 7-12 and 14-19 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Yang et al. (CN115203366 A).
As to claim 1, Yang teaches a method of question answering, the method comprising:
receiving, a text document (preconstructed knowledge base, Fig.7) and an input question (PG.9, S101: obtaining question information.)
generating, using a hybrid parser model (reasoning module, Fig.7) including a first
neural network model (BERT module), a representation of the input question, wherein
the representation includes primitives (sub-questions/sub-problems/events) and operations
(target operations including result updating) representing relationships among the primitives
(relationship between events may be a sequence relationship, a causal relationship, a conditional relationship, or the like)
(S102: a first splitting module 802, configured to split the question: the problem topological graph comprises a plurality of problem nodes, and each problem node represents each target sub- problem obtained by splitting the question information; ….
Fig.7. the reasoning module is used for acquiring the complex problem to be solved and splitting the complex problem to obtain a plurality of subproblems. Then, based on the plurality of sub-problems, a problem topology is constructed. The question topological graph comprises a plurality of question nodes, each question node represents each subproblem obtained by splitting the question, and the initial state of each question node is unanswered. The reasoning module determines the sub-problem to be processed currently (namely, the current node to be processed) according to the state of the problem node corresponding to the sub-problem. Then, the searcher searches the answer result corresponding to the sub-question in the knowledge base by adopting sparse query, dense query, graph query and other query modes, and
checks the answer result based on the knowledge graph. After the verification is passed, the state of the question node corresponding to the subproblem is updated to be answered, and the answer result of the subproblem is used as evidence to update the next subproblem of the subproblem.
generating, using a hybrid executor model (to execute the pre-constructed knowledge base to obtain the target result/answer, 803-805), to the input question by executing the representation based on the text-document/knowledge-based, (S104-S105):
wherein the hybrid executor model includes: an execution neural network model for executing the primitives of the representation and an execution programming model (Figs.7-8) for executing the operations of the representation (Abstract; Figs.1-8; Pgs.9-16; Claims 1-6)
PNG
media_image1.png
180
204
media_image1.png
Greyscale
PNG
media_image2.png
264
426
media_image2.png
Greyscale
As to claim 2, Yang teaches wherein the input question is a complex question, and wherein the primitives include single-hop (one problem node) (Fig.2; Pgs.10-14).
As to claim 3, Yang teaches wherein the hybrid executor model includes: an interpreter for generating a tree structure (topological graph) based on the representation; wherein the hybrid executor model executes the representation by traversing the tree structure (Abstract; Pgs.2, 10-13)
As to claim 4, Yang teaches wherein the tree structure includes: a plurality of leaf nodes corresponding to the primitives (Fig.2, problem nodes 1-3); and one or more non-leaf nodes (operation problem nodes 2, 4, 6) corresponding to the operations (problem type, updating, comparing, multiplying, dividing, summing) (Fig.2, Pgs. 10-13)
As to claim 5, Yang teaches wherein the execution neural network model is used to execute the leaf nodes, and wherein the execution programming model is used to execute the non-leaf nodes (Figs.2-8).
As to claim 7, Yang teaches wherein the execution neural network model includes a knowledge based neural network model, and wherein the hybrid executor model generates the answer to the input question by executing the representation based on a knowledge base (Figs.7-8).
Regarding claims 8-12 and 14-19, the corresponding system and instruction comprising the steps similar to the claims addressed above, are analogous therefore rejected as being anticipated by Yang et al. for the foregoing reasons.
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.
Claim(s) 6, 13 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yang et al. (CN115203366 A) as applied above, and in view of Ravishankar et al. (US 2023/0060589).
As to claims 6, 13 and 20, Yang et al. doesn’t explicitly teaches wherein the execution programming model (answer generating and updating module, Figs.7-8) includes deterministic symbolic rules. However, Ravishankar similar to Yang teaches a neuro-symbolic question answering system for processing complex natural language question, where the question is semantically parsed and converted into plurality of candidate logical queries, wherein the system facilitates a pipeline-based structure that integrates multiple modules trained specifically for their individual tasks that include semantic parser, entity and relationship linkers, and neuro-symbolic reasoner logic/model (Figs.1-3; Pars.25-26, 38-41, 46, 81, 91).
The combination of the analogous arts would be obvious to one of ordinary skill in the art before the time of applicant’s invention for the purpose of efficiently generating the answers for the complex problems.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL DEMELASH ABEBE whose telephone number is (571)272-7615. The examiner can normally be reached monday-friday 7-4.
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, Daniel Washburn can be reached at 571-272-5551. 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.
/DANIEL ABEBE/Primary Examiner, Art Unit 2657
Prosecution Insights