DETAILED ACTION
Claims 1-20 of the instant application are pending and have been examined.
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 04/08/2026 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 8 and 18 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 8 and 18 recite the limitation "the number of occurrences" in both of “determining/determine…” limitations. There is insufficient antecedent basis for this limitation in the claim.
Claim Rejections - 35 USC § 101
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.
Claim(s) 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. More specifically directed to the abstract idea grouping of: mental process and/or mathematical concept.
The independent claim(s) recite(s):
1. A method for generating a dialogue, comprising:
acquiring a current first question statement and historical dialogue information associated with the first question statement;
acquiring, from a knowledge base, a first knowledge item associated with the first question statement and a second knowledge item having a question-answer relationship with the first knowledge item;
obtaining a first reply statement output by a generative model by inputting the first question statement, the first knowledge item, and the historical dialogue information into the generative model;
evaluating the first reply statement based on the first question statement, the first knowledge item, and the second knowledge item; and
outputting the first reply statement in response to the first reply statement passing evaluation.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor;
wherein the at least one processor is configured to:
[perform the limitations as in claim 1, above].
20. A non-transitory computer readable storage medium, having computer instructions stored thereon, which causes a computer to perform a method for generating a dialogue, wherein the method comprises:
[perform the limitations as in claim 1, above].
This reads on a human (e.g., mentally and/or using pen and paper):
Obtaining a question along with historical information from another human;
Obtaining, from a predefined/predetermined source, an item associated with the question and a second item associated with question-answer relationship;
Obtaining a reply using a predetermined set of rules using the question, and items from above;
Evaluating, using a predetermined set of rules, the reply to the question; and
Writing down the reply in response to passing the evaluation above.
This judicial exception is not integrated into a practical application because for example: claims 1, 11, and 20 recite “a knowledge database, a generative model” while claim 11 further recites “an electronic device, processor, memory” and claim 20 recites “a non-transitory computer readable storage medium.” As an example, in ¶ [0213] of the as filed specification, it is disclosed: Various implementation modes of systems and technologies described herein may be implemented in a digital electronic circuit system, an integrated circuit system, a field programmable gate array (FPGA), a dedicated application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), a computer hardware, a firmware, a software, and/or combinations thereof. The implementations may include: implemented in one or more computer programs. The one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor. The programmable processor may be a dedicated or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and the instructions to the storage system, the at least one input device, and the at least one output device. Therefore, a general-purpose computer or computing device is described and mainly used as an application thereof. Accordingly, these additional elements do not integrate the abstract idea into a practical idea because it does not impose any meaningful limits on practicing the abstract idea.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional elements of using a computer is listed as a general computing device as noted. The claim is not patent eligible.
With respect to claims 2 and 12, the claim(s) recite:
2 and 12. The method/device according to claims 1 and 11, wherein acquiring, from the knowledge base, the first knowledge item associated with the first question statement and the second knowledge item having the question-answer relationship with the first knowledge item comprises:
determining a first similarity between a first vector corresponding to the first question statement and a second vector corresponding to each of knowledge items in the knowledge base;
determining a knowledge item with a corresponding first similarity greater than a similarity threshold as the first knowledge item; and
determining the second knowledge item having the question-answer relationship with the first knowledge item based on a third vector corresponding to the first knowledge item, wherein the third vector represents an association relationship between the first knowledge item and other knowledge items.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein obtaining, from a predefined/predetermined source, an item associated with the question and a second item associated with question-answer relationship comprises:
Determining, using a predetermined set of rules, similarity between vectors (i.e., mathematical concept);
Determining similarity is greater than a threshold;
Determining the second item based on it being associated with the first item and other items.
No additional limitations are present.
With respect to claims 3 and 13, the claim(s) recite:
3 and 13. The method/device according to claims 2 and 12, wherein obtaining the first reply statement output by the generative model by inputting the first question statement, the first knowledge item, and the historical dialogue information into the generative model comprises:
in response to a plurality of first knowledge items being present, determining a first contribution degree of each of the plurality of first knowledge items based on a similarity corresponding to each first knowledge item;
generating a first prompt information based on the first question statement, the historical dialogue information, the plurality of first knowledge items, and the first contribution degree of each first knowledge item; and
obtaining the first reply statement output by the generative model by inputting the first prompt information into the generative model.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein the obtaining a reply using a predetermined set of rules using the question, and items from above, comprises:
Determining a degree/value for each item based on similarity;
Generating or determining information based on the question, historical information, item(s) and degree; and
Obtaining a reply using predetermined set of rules.
No additional limitations are present.
With respect to claims 4 and 14, the claim(s) recite:
4 and 14. The method/device according to claims 2 and 12, wherein obtaining the first reply statement output by the generative model by inputting the first question statement, the first knowledge item, and the historical dialogue information into the generative model comprises:
in response to the first knowledge item being a predefined type item, determining a second contribution degree of each knowledge fragment in the first knowledge item respective to the second vector corresponding to the first knowledge item;
determining a target knowledge fragment from the first knowledge item based on the second contribution degree;
generating second prompt information based on the first question statement, the historical dialogue information, and the target knowledge fragment;
obtaining the first reply statement output by the generative model by inputting the second prompt information into the generative model.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein the obtaining a reply using a predetermined set of rules using the question, and items from above, comprises:
In response to the first item being a predefined type, determining a second degree/value;
Determining target fragment from the item based on the degree/value;
Generating information based on the question, historical information, and target fragment;
Obtaining a reply by using the generated information.
No additional limitations are present.
With respect to claims 5 and 15, the claim(s) recite:
5 and 15. The method/device according to claims 1 and 11, wherein evaluating the first reply statement based on the first question statement, the first knowledge item, and the second knowledge item comprises:
determining a first similarity between the first question statement and the first knowledge item, and a second similarity between the first reply statement and the second knowledge item;
determining that the first reply statement passes the evaluation in response to a difference between the first similarity and the second similarity being less than a distance threshold.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein the evaluating, using a predetermined set of rules, the reply to the question comprises:
Determining a first similarity between the first question and the first item and a second similarity between the first reply and the second item;
Determining that the first reply passes the evaluation (i.e., predetermined set of rules).
No additional limitations are present.
With respect to claims 6 and 16, the claim(s) recite:
6 and 16. The method/device according to claims 1 and 11, wherein evaluating the first reply statement based on the first question statement, the first knowledge item, and the second knowledge item comprises:
generating third prompt information based on the first knowledge item, the first question statement, the second knowledge item, and the first reply statement;
inputting the third prompt information into an evaluation model and obtaining an evaluation result output by the evaluation model.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein the evaluating, using a predetermined set of rules, the reply to the question comprises:
Writing/determining information based on item(s), question, and repl(ies)
Using the information to follow predetermined set of rules; and
Obtaining a result (predetermined set of rules or mathematical concept).
No additional limitations are present.
With respect to claims 7 and 17, the claim(s) recite:
7 and 17. The method/device according to claims 6 and 16, wherein generating the third prompt information based on the first knowledge item, the first question statement, the second knowledge item, and the first reply statement comprises:
receiving a third knowledge item associated with the first reply statement from the knowledge base;
obtaining a fused knowledge item and a weight of the fused knowledge item by fusing the third knowledge item and the second knowledge item;
generating the third prompt information based on the first knowledge item, the first question statement, the first reply statement, the fused knowledge item, and the weight of the fused knowledge item.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein writing/determining information based on item(s), question, and repl(ies) comprises:
Receiving third item associated with the reply;
Obtaining a fused/mixed/combined item and a weight (mathematical concept) of said item;
Generating information based on the first item, the question, the reply, the combined item, and weight.
No additional limitations are present.
With respect to claims 8 and 18, the claim(s) recite:
8 and 18. The method/device according to claims 7 and 17, wherein a process of determining the weight of the fused knowledge item comprises:
determining a third similarity between the fused knowledge item and the first reply statement, and the number of occurrences of the fused knowledge item in the second knowledge item and the third knowledge item;
determining the weight of the fused knowledge item based on the third similarity and/or the number of occurrences.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein determining the weight comprises:
Determining a third similarity (predetermined set of rules / mathematical concept);
Determining the weight of the combined item based on the similarity or number of occurrences.
No additional limitations are present.
With respect to claims 9 and 19, the claim(s) recite:
9 and 19. The method/device according to claims 1 and 11, wherein, after evaluating the first reply statement, the method further comprises:
in response to the first reply statement failing the evaluation, obtaining a second reply statement output by the generative model by inputting an evaluation result corresponding to the first reply statement into the generative model;
returning to perform an evaluation operation based on the second reply statement, until an reply statement that passes the evaluation is obtained and output.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein, after the evaluation, in response to the first reply failing the evaluation, obtaining a second reply (i.e., based on predetermined set of rules/steps)
Repeating the evaluation based on the second reply until the reply passes evaluation.
No additional limitations are present.
With respect to claim 10, the claim(s) recite:
10. The method according to claim 1, wherein, after outputting the first reply statement, the method further comprises:
in response to receiving the second question statement for the first reply statement, generating and outputting a third reply statement corresponding to a second question statement;
in response to receiving no third question statement for the third reply statement, generating a target reply statement corresponding to the first question statement based on the first reply statement and the third reply statement;
storing the first question statement and the target reply statement in a predefined database, wherein data in the predefined database is used to perform update training on the generative model.
This reads on a human (e.g., mentally and/or using pen and paper):
Wherein after writing the first reply, in response to receiving a second question from the other human, generating or writing a third reply corresponding to the second question;
In response to not receiving a third question, generating or writing the reply to the first question;
Writing down the first question and the reply to be used as a reference in the future.
No additional limitations are present.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 6-8, 10-11, 16-18, and 20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Shastri et al. (US 20260057254 A1).
As to independent claim 1, Shastri et al. teaches:
1. A method for generating a dialogue (see ¶ [0010]: “In another example, this disclosure describes a method …” and ¶ [0067]: “…As described above, conversation chain 300 is generated from records of past queries by a user and corresponding past responses by the machine learning model…”), comprising:
acquiring a current first question statement and historical dialogue information associated with the first question statement (see Fig. 6 (602: topic/past queries in knowledge graph and 604: query by the user) and ¶ [0096]: “System 100 receives, from user 130 via user device 132, query 110. System 100 determines, from query 110, one or more topics present within query 110 (604). System 100 determines, based at least in part on each topic present within query 110 and KG 104 corresponding to user 130, a goal query (606)…”);
acquiring, from a knowledge base, a first knowledge item associated with the first question statement and a second knowledge item having a question-answer relationship with the first knowledge item (see Fig. 6 (606: goal query based on the topic and knowledge graph) and ¶ [0021]: “…The nodes of a KG may be used to represent topics, while the edges may be used to represent relationships between the topics represented by the corresponding nodes…”, ¶ [0095]: “In accordance with the techniques of the disclosure, a conversational assistant system, such as system 100, processes, for each user of a plurality of different users, records of past queries by each user and corresponding past responses by machine learning model 114 stored by interaction database 112 to generate a KG corresponding to each user (602)… KG 104 comprises a plurality of nodes and a plurality of links. Each of the nodes represents a topic present within the past queries by user 130. Each of the links represents a co-occurrence between the topics present within the past queries by user 130…”, and ¶ [0096]: “…System 100 determines, based at least in part on each topic present within query 110 and KG 104 corresponding to user 130, a goal query (606)…”);
obtaining a first reply statement output by a generative model by inputting the first question statement, the first knowledge item, and the historical dialogue information into the generative model (see Fig. 6 (608: providing the ML model with the query, response to query, and goal topic to be included in the response) and ¶ [0097]: “System 100 provides, to machine learning model 114, query 130 to generate, by machine learning model 114, response 120 (608). System 100 constrains machine learning model 114 to include the goal topic of the goal query within response 120…”);
evaluating the first reply statement based on the first question statement, the first knowledge item, and the second knowledge item (see ¶ [0048]: “…System 100 may apply trained machine learning model 112 to the test data to evaluate the accuracy of responses produced by machine learning model 112 or an error rate of machine learning model 112. In some examples, system 100 applies trained machine learning model 112 to the test data to validate that trained machine learning model 112 accurately generates a response that is coherent and relevant to the corresponding query…”); and
outputting the first reply statement in response to the first reply statement passing evaluation (see Fig. 6 (610: output of the response to the user) and ¶ [0097]: “… System 100 outputs, for display, response 120 to query 110 by user 130 (610).”).
As to independent claim 11, Shastri et al. teaches:
11. An electronic device (see Fig. 1 (system 100) and ¶ [0005]: “…In one example of the techniques of the disclosure, a system, such as a conversational assistant system, processes, for each user of a plurality of different users, records of past queries by each user and corresponding past responses by the machine learning model to generate a knowledge graph corresponding to each user of the plurality of different users...”), comprising:
at least one processor (see ¶ [0035]: “The one or more processors and one or more storage devices of system 100 may provide an operating environment or platform for one or more modules, which may be implemented as software, but may in some examples include any combination of hardware, firmware, and software. The one or more processors may execute instructions and the one or more storage devices may store instructions and/or data of one or more modules. The combination of processors and storage devices may retrieve, store, and/or execute the instructions and/or data of one or more applications, modules, or software. The processors and/or storage devices may also be operably coupled to one or more other software and/or hardware components, including, but not limited to, one or more of the components illustrated in FIGS. 2 and 5 below.”); and
a memory communicatively coupled to the at least one processor (see ¶ [0034]: “One or more storage devices within system 100 (not depicted in FIG. 1) may store information for processing during operation of system 100…”);
wherein the at least one processor is configured (see ¶ [0035] citation as in limitation above.) to:
[perform the limitations as in claim 1, above].
As to independent claim 20, Shastri et al. teaches:
20. A non-transitory computer readable storage medium, having computer instructions stored thereon, which causes a computer to perform a method for generating a dialogue (see claim 20 (“Non-transitory, computer-readable media comprising instructions that, when executed, are configured to cause processing circuitry to…”) and ¶ [0011]: “[0011] In another example, this disclosure describes non-transitory, computer-readable media comprising instructions that, when executed, are configured to cause processing circuitry to: …”), wherein the method (see ¶ [0010]: “[0010] In another example, this disclosure describes a method …”) comprises:
[perform the limitations as in claim 1, above].
Regarding claim 6, Shastri et al. teaches the limitations as in claim 1, above.
Shastri et al. further teaches:
6. The method according to claim 1, wherein evaluating the first reply statement based on the first question statement, the first knowledge item, and the second knowledge item (see ¶ [0048] citation as in claim 1, above.) comprises:
generating third prompt information based on the first knowledge item, the first question statement, the second knowledge item, and the first reply statement (see Fig. 6 (608: providing the ML model with the query, response to query, and goal topic to be included in the response) and ¶ [0097]: “System 100 provides, to machine learning model 114, query 130 to generate, by machine learning model 114, response 120 (608). System 100 constrains machine learning model 114 to include the goal topic of the goal query within response 120…”);
inputting the third prompt information into an evaluation model and obtaining an evaluation result output by the evaluation model (see ¶ [0048]: “…System 100 may apply trained machine learning model 112 to the test data to evaluate the accuracy of responses produced by machine learning model 112 or an error rate of machine learning model 112...”).
Regarding claim 16, Shastri et al. teaches the limitations as in claim 11, above.
16. The electronic device according to claim 11, wherein the at least one processor is configured to:
[perform the limitations as in claim 6, above].
Regarding claim 7, Shastri et al. teaches the limitations as in claim 1, above.
Shastri et al. further teaches:
7. The method according to claim 6, wherein generating the third prompt information based on the first knowledge item, the first question statement, the second knowledge item, and the first reply statement (see Fig. 6 (608: providing the ML model with the query, response to query, and goal topic to be included in the response) and ¶ [0097] citation as in claim 6, above.) comprises:
receiving a third knowledge item associated with the first reply statement from the knowledge base (see Fig. 6 (608: providing the ML model with the query, response to query, and goal topic to be included in the response) and ¶ [0059]: “... In some examples, a weight of an edge denotes a probability of a co-occurrence, within a single query of the past queries by the user, of the two corresponding topics represented by two nodes of the nodes joined by the edge…” and ¶ [0097]: “System 100 provides, to machine learning model 114, query 130 to generate, by machine learning model 114, response 120 (608). System 100 constrains machine learning model 114 to include the goal topic of the goal query within response 120…”);
obtaining a fused knowledge item and a weight of the fused knowledge item by fusing the third knowledge item and the second knowledge item (see Fig. 6 and ¶ [0059 and 0097] citations as in limitation above. More specifically ¶ [0059]: “... In some examples, a weight of an edge denotes a probability of a co-occurrence, within a single query of the past queries by the user, of the two corresponding topics represented by two nodes of the nodes joined by the edge…”);
generating the third prompt information based on the first knowledge item, the first question statement, the first reply statement, the fused knowledge item, and the weight of the fused knowledge item (see Fig. 6 and ¶ [0059 and 0097] citations as in limitation above and further ¶ [0065]: “…As described in more detail in FIG. 4 below, CoT-KG builder 208 may use the user feedback scores to update a weight of an edge of a CoT-KG 204, the edge joining two nodes of the nodes representing the topic present within the preceding query and the topic present within the query.”).
Regarding claim 17, Shastri et al. teaches the limitations as in claim 11, above.
17. The electronic device according to claim 16, wherein the at least one processor is configured to:
[perform the limitations as in claim 7, above].
Regarding claim 8, Shastri et al. teaches the limitations as in claim 7, above.
Shastri et al. further teaches:
8. The method according to claim 7, wherein a process of determining the weight of the fused knowledge item (see Fig. 6 and ¶ [0059 and 0097] citations as in claims 6 and 7 above.) comprises:
determining a third similarity between the fused knowledge item and the first reply statement, and the number of occurrences of the fused knowledge item in the second knowledge item and the third knowledge item (see Fig. 6 and ¶ [0059 and 0097] citations as in claim 7 above and further ¶ [0072]: “…Each edge 404 represents a probability of a co-occurrence between two topics present within the past queries by the user (and, in some examples, a probability of this co-occurrence being accepted by user 130). Each edge 404 is further associated with a weight that represents a probability of a co-occurrence, within a single past query of the user, of two topics represented by two nodes of the nodes joined by the edge. In some examples, the weight represents a probability that a first topic is followed by a second topic in a previous conversation comprising a query-response pair between the user and system 100.”);
determining the weight of the fused knowledge item based on the third similarity and/or the number of occurrences (see ¶ [0059]: “... In some examples, a weight of an edge denotes a probability of a co-occurrence, within a single query of the past queries by the user, of the two corresponding topics represented by two nodes of the nodes joined by the edge…”).
Regarding claim 18, Shastri et al. teaches the limitations as in claim 17, above.
18. The electronic device according to claim 17, wherein the at least one processor is configured to:
[perform the limitations as in claim 8, above].
Regarding claim 10, Shastri et al. teaches the limitations as in claim 7, above.
Shastri et al. further teaches:
10. The method according to claim 1, wherein, after outputting the first reply statement (see Fig. 6 (610: output of the response to the user) and ¶ [0097] citation as in claim 1, above.), the method further comprises:
in response to receiving the second question statement for the first reply statement, generating and outputting a third reply statement corresponding to a second question statement (see ¶ [0040]: “For example, system 100 may update KG 104 based at least in part on user feedback received for response 120. System 100 receives a second query from user 130 via user device 132. System 100 determines, based at least in part on a second topic present within the second query and the updated KG 104 corresponding to user 130, a second goal query that comprises a second goal topic. System 100 provides, to ML model 114, the second query to generate, by ML model 114, a second response to the second query by user 130, wherein the second goal topic constrains ML 114 to include the second goal topic of the second goal query within the second response. System 100 outputs the second response to the second query by user 130. In this fashion, system 100 may provide a response that is based at least in part on KG 104 corresponding to user 130 and updated based at least in part on feedback to response 120 received from user 130.”);
in response to receiving no third question statement for the third reply statement, generating a target reply statement corresponding to the first question statement based on the first reply statement and the third reply statement (see Fig. 6 (608: providing the ML model with the query, response to query, and goal topic to be included in the response) and ¶ [0097]: “System 100 provides, to machine learning model 114, query 130 to generate, by machine learning model 114, response 120 (608). System 100 constrains machine learning model 114 to include the goal topic of the goal query within response 120…”);
storing the first question statement and the target reply statement in a predefined database, wherein data in the predefined database is used to perform update training on the generative model (see ¶ [0095]: “In accordance with the techniques of the disclosure, a conversational assistant system, such as system 100, processes, for each user of a plurality of different users, records of past queries by each user and corresponding past responses by machine learning model 114 stored by interaction database 112 to generate a KG corresponding to each user (602). For example, system 100 processes records of past queries by user 130 and corresponding past responses by machine learning model 114 stored by interaction database 112 to generate KG 104 corresponding to user 130…”).
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 2-5, 9, 12-15, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Shastri et al. (US 20260057254 A1) as applied to claims 1 and 11 above, and further in view of Iyengar et al. (US 20250328554 A1).
Regarding claim 2, Shastri et al. teaches the limitations as in claim 1, above.
Iyengar et al. further teaches:
2. The method according to claim 1, wherein acquiring, from the knowledge base, the first knowledge item associated with the first question statement and the second knowledge item having the question-answer relationship with the first knowledge item (see Fig. 6 (606: goal query based on the topic and knowledge graph) and ¶ [0021], ¶ [0095-0096] citations as in claim 1, above.) comprises:
determining the second knowledge item having the question-answer relationship with the first knowledge item based on a third vector corresponding to the first knowledge item (see Fig. 6 (606: goal query based on the topic and knowledge graph) and ¶ [0021]: “…The nodes of a KG may be used to represent topics, while the edges may be used to represent relationships between the topics represented by the corresponding nodes…”, ¶ [0095]: “In accordance with the techniques of the disclosure, a conversational assistant system, such as system 100, processes, for each user of a plurality of different users, records of past queries by each user and corresponding past responses by machine learning model 114 stored by interaction database 112 to generate a KG corresponding to each user (602)… KG 104 comprises a plurality of nodes and a plurality of links. Each of the nodes represents a topic present within the past queries by user 130. Each of the links represents a co-occurrence between the topics present within the past queries by user 130…”, and ¶ [0096]: “…System 100 determines, based at least in part on each topic present within query 110 and KG 104 corresponding to user 130, a goal query (606)…”),
wherein the third vector represents an association relationship between the first knowledge item and other knowledge items (see ¶ Fig. 6 and ¶ [0021 and 0095-0096] citations as in limitation above, more specifically ¶ [0021]: “…The nodes of a KG may be used to represent topics, while the edges may be used to represent relationships between the topics represented by the corresponding nodes…” and ¶ [0095]: “…Each of the nodes represents a topic present within the past queries by user 130. Each of the links represents a co-occurrence between the topics present within the past queries by user 130…”).
However, Shastri et al. does not explicitly teach, but Iyengar et al. does teach:
determining a first similarity between a first vector corresponding to the first question statement and a second vector corresponding to each of knowledge items in the knowledge base (see ¶ [0068]: “At (5), query engine 302 may then perform a search in cache knowledge database 308 for the vector v1, to identify a cached query associated with a vector v2 that is similar to vector v1, based on the selected semantic similarity threshold. One example approach for determining if there is a cached query similar to new query 415 is to compare the vector v1 to all vectors stored in cache knowledge database 308…”);
determining a knowledge item with a corresponding first similarity greater than a similarity threshold as the first knowledge item (see ¶ [0068] citation as in limitation above and further ¶ [0069]: “ During its comparison, query engine 302 may identify the most similar vector v2 stored in cache knowledge database 308. Query engine 302 then determines whether the measure of similarity between vector v1 and vector v2 exceeds the semantic similarity threshold. If the answer is yes, then query engine 302 returns the cached answer associated with the cached query that is represented as vector v2 as the answer to the new query 415, as shown at (6). The cached answer is provided to user 405 via user interface 410.”); and
Shastri et al. and Iyengar et al. are considered to be analogous to the claimed invention because they are in the same field of endeavor in question-answering / language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Shastri et al. to incorporate the teachings of Iyengar et al. of determining a first similarity between a first vector corresponding to the first question statement and a second vector corresponding to each of knowledge items in the knowledge base; determining a knowledge item with a corresponding first similarity greater than a similarity threshold as the first knowledge item which provides the benefit of improving response times to a query answering service ([0083] of Iyengar et al.).
Regarding claim 12, Shastri et al. in combination with Iyengar et al. teach the limitations as in claim 2, above.
12. The electronic device according to claim 11, wherein the at least one processor is configured to:
[perform the limitations as in claim 2 (taught by Shastri et al. in combination with Iyengar et al.), above].
Regarding claim 3, Shastri et al. in combination with Iyengar et al. teach the limitations as in claim 2, above.
Shastri et al. further teaches:
3. The method according to claim 2, wherein obtaining the first reply statement output by the generative model by inputting the first question statement, the first knowledge item, and the historical dialogue information into the generative model (see Fig. 6 (608: providing the ML model with the query, response to query, and goal topic to be included in the response) and ¶ [0097] citation as in claim 1, above.) comprises:
Iyengar et al. further teaches:
in response to a plurality of first knowledge items being present, determining a first contribution degree of each of the plurality of first knowledge items based on a similarity corresponding to each first knowledge item (see ¶ [0068] citation as in claim 2, above. More specifically: “At (5), query engine 302 may then perform a search in cache knowledge database 308 for the vector v1, to identify a cached query associated with a vector v2 that is similar to vector v1, based on the selected semantic similarity threshold. One example approach for determining if there is a cached query similar to new query 415 is to compare the vector v1 to all vectors stored in cache knowledge database 308…””);
generating a first prompt information based on the first question statement, the historical dialogue information, the plurality of first knowledge items, and the first contribution degree of each first knowledge item (see ¶ [0068] citation as in claim 2, above and further ¶ [0069]: “During its comparison, query engine 302 may identify the most similar vector v2 stored in cache knowledge database 308. Query engine 302 then determines whether the measure of similarity between vector v1 and vector v2 exceeds the semantic similarity threshold. If the answer is yes, then query engine 302 returns the cached answer associated with the cached query that is represented as vector v2 as the answer to the new query 415, as shown at (6). The cached answer is provided to user 405 via user interface 410.””); and
obtaining the first reply statement output by the generative model by inputting the first prompt information into the generative model (see ¶ [0068-0069] citations as in claim 2 and limitations above.).
Shastri et al. and Iyengar et al. are considered to be analogous to the claimed invention because they are in the same field of endeavor in question-answering / language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Shastri et al. to incorporate the teachings of Iyengar et al. of in response to a plurality of first knowledge items being present, determining a first contribution degree of each of the plurality of first knowledge items based on a similarity corresponding to each first knowledge item; generating a first prompt information based on the first question statement, the historical dialogue information, the plurality of first knowledge items, and the first contribution degree of each first knowledge item; and obtaining the first reply statement output by the generative model by inputting the first prompt information into the generative model which provides the benefit of improving response times to a query answering service ([0083] of Iyengar et al.).
Regarding claim 13, Shastri et al. in combination with Iyengar et al. teach the limitations as in claim 3, above.
13. The electronic device according to claim 12, wherein the at least one processor is configured to:
[perform the limitations as in claim 3 (taught by Shastri et al. in combination with Iyengar et al.), above].
Regarding claim 4, Shastri et al. in combination with Iyengar et al. teach the limitations as in claim 2, above.
Shastri et al. further teaches:
4. The method according to claim 2, wherein obtaining the first reply statement output by the generative model by inputting the first question statement, the first knowledge item, and the historical dialogue information into the generative model (see Fig. 6 (608: providing the ML model with the query, response to query, and goal topic to be included in the response) and ¶ [0097] citation as in claim 1, above.) comprises:
Iyengar et al. further teaches:
in response to the first knowledge item being a predefined type item, determining a second contribution degree of each knowledge fragment in the first knowledge item respective to the second vector corresponding to the first knowledge item (see ¶ [0068] citation as in claim 2, above. More specifically: “At (5), query engine 302 may then perform a search in cache knowledge database 308 for the vector v1, to identify a cached query associated with a vector v2 that is similar to vector v1, based on the selected semantic similarity threshold. One example approach for determining if there is a cached query similar to new query 415 is to compare the vector v1 to all vectors stored in cache knowledge database 308…”);
determining a target knowledge fragment from the first knowledge item based on the second contribution degree (see ¶ [0068] citation as in claim 2 and above. More specifically: “… One example approach for determining if there is a cached query similar to new query 415 is to compare the vector v1 to all vectors stored in cache knowledge database 308…”);
generating second prompt information based on the first question statement, the historical dialogue information, and the target knowledge fragment (see ¶ [0068] citation as in claim 2, above and further ¶ [0069]: “During its comparison, query engine 302 may identify the most similar vector v2 stored in cache knowledge database 308. Query engine 302 then determines whether the measure of similarity between vector v1 and vector v2 exceeds the semantic similarity threshold. If the answer is yes, then query engine 302 returns the cached answer associated with the cached query that is represented as vector v2 as the answer to the new query 415, as shown at (6). The cached answer is provided to user 405 via user interface 410.”);
obtaining the first reply statement output by the generative model by inputting the second prompt information into the generative model (see ¶ [0068-0069] citations as in claim 2 and limitations above.).
Shastri et al. and Iyengar et al. are considered to be analogous to the claimed invention because they are in the same field of endeavor in question-answering / language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Shastri et al. to incorporate the teachings of Iyengar et al. of in response to the first knowledge item being a predefined type item, determining a second contribution degree of each knowledge fragment in the first knowledge item respective to the second vector corresponding to the first knowledge item; determining a target knowledge fragment from the first knowledge item based on the second contribution degree; generating second prompt information based on the first question statement, the historical dialogue information, and the target knowledge fragment; obtaining the first reply statement output by the generative model by inputting the second prompt information into the generative model which provides the benefit of improving response times to a query answering service ([0083] of Iyengar et al.).
Regarding claim 14, Shastri et al. in combination with Iyengar et al. teach the limitations as in claim 4, above.
14. The electronic device according to claim 12, wherein the at least one processor is configured to:
[perform the limitations as in claim 4 (taught by Shastri et al. in combination with Iyengar et al.), above].
Regarding claim 5, Shastri et al. teaches the limitations as in claim 1, above.
Shastri et al. further teaches:
5. The method according to claim 1, wherein evaluating the first reply statement based on the first question statement, the first knowledge item, and the second knowledge item (see ¶ [0048] citation as in claim 1, above.) comprises:
However, Shastri et al. does not explicitly teach, but Iyengar et al. does teach:
determining a first similarity between the first question statement and the first knowledge item, and a second similarity between the first reply statement and the second knowledge item (see ¶ [0048]: “For example, a similarity threshold of 0.5 may be determined to be a good choice for similarity metrics such as a cosine similarity. The queries “What is an application-level denial of service attack?” and “What are the major types of cyber attacks?” are considerably different. However, a cosine similarity has been determined as 0.55 between these two queries using the Facebook contriever-msmarco model, exceeding the 0.5 threshold. Similarly, the cosine similarity between “What is an application-level denial of service attack?” and “How do denial of service attacks work?” is even higher at. 0.75. However, these two queries are considerably different. The former is asking about a specific type of denial of service attack while the latter is asking about denial of service attacks in general. The answers to these two queries would be expected to differ considerably, and a cached answer for the first query may not be used to satisfy the second query (or vice versa).”);
determining that the first reply statement passes the evaluation in response to a difference between the first similarity and the second similarity being less than a distance threshold (see ¶ [0048] citation as in limitation above, more specifically: “…The former is asking about a specific type of denial of service attack while the latter is asking about denial of service attacks in general. The answers to these two queries would be expected to differ considerably, and a cached answer for the first query may not be used to satisfy the second query (or vice versa)” and further ¶ [0013 and 0049-0050]: “[0013] … The device makes, using the particular similarity threshold, a determination as to whether the query matches a cached query. The device provides, based on the determination, a response associated with the cached query in lieu of inputting the query to the language model… [0049] Thus, a rigid once size fits all values for the semantic similarity threshold may not be sufficient. Therefore, the semantic similarity threshold is determined based on a number of factors and can be varied dynamically. For example, semantic threshold engine 306 provides avenues to vary the way in which the semantic similarity threshold is determined in order to better match the queries and user preferences. Some example factors that are considered to determine the semantic similarity threshold include: [0050] Type of query: some queries may tolerate low semantic similarity thresholds, while others may require higher semantic similarity thresholds…”).
Shastri et al. and Iyengar et al. are considered to be analogous to the claimed invention because they are in the same field of endeavor in question-answering / language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Shastri et al. to incorporate the teachings of Iyengar et al. of determining a first similarity between the first question statement and the first knowledge item, and a second similarity between the first reply statement and the second knowledge item; determining that the first reply statement passes the evaluation in response to a difference between the first similarity and the second similarity being less than a distance threshold which provides the benefit of improving response times to a query answering service ([0083] of Iyengar et al.).
Regarding claim 15, Shastri et al. teaches the limitations as in claim 11, above.
15. The electronic device according to claim 11, wherein the at least one processor is configured to:
[perform the limitations as in claim 5 (taught by Shastri et al. in combination with Iyengar et al.), above].
Regarding claim 9, Shastri et al. teaches the limitations as in claim 1, above.
Iyengar et al. further teaches:
9. The method according to claim 1, wherein, after evaluating the first reply statement (see ¶ [0048] citation as in claim 1, above.), the method further comprises:
in response to the first reply statement failing the evaluation, obtaining a second reply statement output by the generative model by inputting an evaluation result corresponding to the first reply statement into the generative model (see ¶ [0013 and 0048-0050] citations as in claim 5 and 15, above and further ¶ [0084-0085]: “[0084] The method may further include, in response to failing to determine the at least one query q2 stored in the cache for which the semantic similarity between the query q1 and the at least one query q2 is greater than or equal to the semantic similarity threshold, returning a response r2 obtained by sending the query q1 to the query answering service. [0085] The semantic similarity threshold is dynamically modified based on at least one of the user preference, the query type, the latency for receiving at least one response from the query answering service, the cost to make a query to the query answering service, and the level of network connectivity with the query answering service.”);
returning to perform an evaluation operation based on the second reply statement, until an reply statement that passes the evaluation is obtained and output (see ¶ [0013 and 0048-0050] citations as in claim 5 and 15, above and further ¶ [0084-0085] citations as in limitations above and further ¶ [0087]: “[0087] The method may further include, in response to determining that the at least one query q2 stored in the cache for which the semantic similarity between the query q1 and the at least one query q2 is greater than or equal to the semantic similarity threshold, returning a response r1 stored in the cache, the semantic similarity between the query q1 and the at least one query q2 stored in the cache corresponding to the response r1 being a maximum value for all cached queries compared with the query q1.”).
Shastri et al. and Iyengar et al. are considered to be analogous to the claimed invention because they are in the same field of endeavor in question-answering / language processing. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Shastri et al. to incorporate the teachings of Iyengar et al. of in response to the first reply statement failing the evaluation, obtaining a second reply statement output by the generative model by inputting an evaluation result corresponding to the first reply statement into the generative model; returning to perform an evaluation operation based on the second reply statement, until an reply statement that passes the evaluation is obtained and output which provides the benefit of improving response times to a query answering service ([0083] of Iyengar et al.).
Regarding claim 15, Shastri et al. teaches the limitations as in claim 11, above.
19. The electronic device according to claim 11, wherein the at least one processor is configured to:
[perform the limitations as in claim 9 (taught by Shastri et al. in combination with Iyengar et al.), above].
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Keisha Y Castillo-Torres whose telephone number is (571)272-3975. The examiner can normally be reached Monday - Friday, 9:00 am - 4:00 pm (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, Pierre-Louis Desir can be reached at (571)272-7799. 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.
Keisha Y. Castillo-Torres
Examiner
Art Unit 2659
/Keisha Y. Castillo-Torres/Examiner, Art Unit 2659
Prosecution Insights