DETAILED ACTION
This office action is in response to the above identified application filed on December 31, 2025. The application contains claims 1-23.
Claims 2, 12, 17, and 20 were previously cancelled
Claims 1, 11, 16, and 21-23 are amended
Claims 1, 3-11, 13-16, 18, 19, and 21-23 are pending
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on December 31, 2025 has been entered.
Information Disclosure Statement
The information disclosure statement (IDS) was submitted on December 31, 2025. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
Applicant's arguments and amendments filed on December 31, 2025 have been fully considered and the objections and rejections are updated accordingly.
Claim Rejections - 35 USC § 112
The amendments raise new issues. The claim objections and rejections as set forth below reflect remaining issues after entry of the amendments. Please refer to below for details.
Claim Rejections - 35 USC § 103
Applicant’s arguments with respect to the new limitations introduced with the amendments are addressed with new prior art and rationale.
Please refer to the updated 35 U.S.C. 103 rejections as set forth below for details.
Claim Objections
Claims 1, 11, and 16 are objected to because of the following informalities:
The limitation “fulling” in the following places appears to be a typo or an error:
Claim 1, line 8
Claim 11, line 10
Claim 16, line 12
The limitation “the backend components” in the following places should read “the first set of backend components” for clarity:
Claim 1, line 11
Claim 11, line 13
Claim 16, line 15
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph 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.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
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 of carrying out his invention.
Claims 1, 3-11, 13-16, 18, 19, and 21-23 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains 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 or a joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claims 1, 11, and 16 each recite the limitation “parsing the first user input to obtain one or more prestored keywords that are related to an intention of the user and a result desired by the user” in lines 3-4, 5-6, and 7-8, respectively. The specification discloses parsing the user input to obtain a user intent and a user request in paragraph [0046] but never the underlined part “a result desired by the user” anywhere. Therefore, claims 1, 11, and 16 are rejected under 35 U.S.C. 112(a).
Dependent claims 3-10 & 21-23, 13-15, and 18 & 19 are also rejected for inheriting the deficiency from their corresponding independent claims 1, 11, and 16, respectively.
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 1, 3-11, 13-16, 18, 19, and 21-23 are 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 pre-AIA the applicant regards as the invention.
Claims 1, 11, and 16 each recite the limitation “parsing the first user input to obtain one or more prestored keywords that are related to an intention of the user and a result desired by the user” in lines 3-4, 5-6, and 7-8, respectively. Not only is the underlined part not supported by the specification as discussed above, but also it is unclear what “a result desired by the user” means. Therefore, claims 1, 11, and 16 are indefinite and rejected under 35 U.S.C. 112(b).
Claims 1, 11, and 16 each recite the limitation “a first set of the backend components” in lines 14-15, 16-17, and 19, respectively. It is unclear what “the backend components” refer to and whether or not “a first set of the backend components” refers to the “a first set of backend components” recited in lines 7-8, 9-10, and 12, respectively or a different set of backend components. Therefore, claims 1, 11, and 16 are indefinite and rejected under 35 U.S.C. 112(b).
Claim 1 recites the limitation “the first set of the backend components” in lines 15-16, 18-19, 23, 25, 26-27, and 30-31, respectively. Due to the indefiniteness of the antecedent basis of this limitation as discussed above, these occurrences are indefinite too. Therefore, claim 1 is indefinite and rejected under 35 U.S.C. 112(b).
Claim 11 recites the limitation “the first set of the backend components” in lines 17-18, 20-21, 25, 27, 28-29, and 32-33, respectively. Due to the indefiniteness of the antecedent basis of this limitation as discussed above, these occurrences are indefinite too. Therefore, claim 11 is indefinite and rejected under 35 U.S.C. 112(b).
Claim 16 recites the limitation “the first set of the backend components” in lines 19-20, 23, 28-29, 31, 32-33, and 37, respectively. Due to the indefiniteness of the antecedent basis of this limitation as discussed above, these occurrences are indefinite too. Therefore, claim 16 is indefinite and rejected under 35 U.S.C. 112(b).
Claims 21, 22, and 23 each recite the limitation “the first set of the backend components” in lines 1, 2-3 & 5, and 1, respectively. Due to the indefiniteness of the antecedent basis of this limitation in their respective parent claim 1 as discussed above, these occurrences are indefinite too. Therefore, claims 21, 22, and 23 are indefinite and rejected under 35 U.S.C. 112(b).
Dependent claims 3-10 & 21-23, 13-15, and 18 & 19 are also rejected for inheriting the deficiency from their corresponding independent claims 1, 11, and 16, respectively.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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, 3-8, 11, 13-16, 18, 19, and 21-23 are rejected under 35 U.S.C. 103 as being unpatentable over Liang et al. (US 20210144107 A1), in view of Fong et al. (US 20210241152 A1), and in further view of Mei et al. (US 20210227351 A1).
With respect to claim 1,
Liang teaches
a method for managing backend components (Abstract: orchestrate chat services by managing a plurality of backend chatbots registered with a centralized chat service, wherein registered chatbots correspond to backend components), the method comprising:
obtaining a first user input comprising a first request from a user (Fig. 8a; [0109]: receive user input in step 805 and analyze user input to identify one or more intents in step 807, wherein the identified intents correspond to a first request from a user);
parsing the first user input to obtain one or more prestored keywords that are related to an intention of the user and a result desired by the user, the one or more prestored keywords being stored in and obtained from a backend component evaluation data repository (Fig. 2b; [0070]: the natural language processor 261 within the analytics module 205 may parse and analyze passages of the user input to identify one or more terms, including one or more intents evidenced by the user input. [0107]; [0082]: one or more intents associated with registration information for the chatbot 241 may be stored by the data repository 227 as chatbot registration 231, wherein the data repository 227 corresponds to “a backend component evaluation data repository”, intents in the form of terms are stored in it, and the intents indicate “a result desired by the user”);
selecting, based on data stored in the backend component evaluation data repository, a first set of backend components for fulling the first request by:
using, one or more mapping tables stored in the backend component evaluation data repository, to map the one or more prestored keywords to ones of the first set of backend components, the backend components and the one or more prestored keywords being stored in the one or more mapping tables as mapped data (Fig. 2a; [0088]: in response to a user question “can I check the balance on my credit card”, the analysis module 205 may detect important intents, such as “check”, “balance”, “credit card” associated with the user input, and the classification module 213 and the mapping module 215 use the detected intents to classify and identify the appropriate chatbots 241 for responding to the user input, wherein the mapping module 215 indicates “the one or more mapping tables as mapped data”);
invoking a first set of the backend components to fulfill the first request (Fig. 8a; [0110]-[0111]; Fig. 8b; [0112]: identify matching chatbots based on data maintained by data repository 227 and invoke the selected chatbot in step 823), wherein the first set of the backend components comprise components that are not originally designed to be interoperable with one another and are invoked to follow a unified interface and protocol defined by an entity of which the user is a member such that all of the first set of the backend components become interoperable with one another (Fig. 2a; [0090]; [0095]; [0112]: the orchestrator service 217 may comprise a format exchanger 221 that transforms the format of the user input and intents etc. into a format of the API that is used by the chatbot 241 selected to receive the user input and the resulting response received from the chatbot 241 into a format usable by the chat services 225, wherein the chatbots, which are not originally designed to be interoperable with each other, now follow a unified interface and protocol provided by the orchestrator service 217 to work together); and
reporting a first result of the fulfillment of the first request to the user (Fig. 8b; [0113]: display the response received from the chatbot on the user system 235),
Liang does not teach
wherein the first result comprises, as information making up the first result and displayed together as a whole to the user:
each of the backend components making up the first set of the backend components,
a resolution to the first request generated by each of the backend components making up the first set of the backend components, and
for each of the backend components making up the first set of the backend components, invocation statistics associated with an obtaining of the resolution, the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components.
Fong teaches
wherein the first result comprises, as information making up the first result and displayed together as a whole to the user (Fig. 2; [0039]; [0042]-[0043]; [0051]: obtain a request for a ML pipeline selection in step 200, identify a set of ML pipelines based on the domain specified in the request in step 202, train each ML pipeline in the set using a standard dataset to generate the runtime statistics in step 204, and present the ordering, the runtime statistics, and an explanation of the ordering of the ML pipelines to the client using a graphical user interface (GUI) in step 208):
each of the backend components making up the first set of the backend components (Fig. 2; [0051]; Fig. 3A-3C: the identified ML pipelines A-F as shown in Fig. 3A-3C correspond to “the first set of the backend components”),
a resolution to the first request generated by each of the backend components making up the first set of the backend components (Fig. 2; [0043]-[0044]; Fig. 3A; [0066]-[0067]: accuracy as shown in Fig. 3A is generated by each ML pipeline as a resolution to the user’s request for a ML pipeline selection thus corresponds to “a resolution to the first request”), and
for each of the backend components making up the first set of the backend components, invocation statistics associated with an obtaining of the resolution (Fig. 2; [0051]; Fig. 3B, 3C; [0068]: present the ordering, the runtime statistics, and an explanation of the ordering of the ML pipelines to the client using a graphical user interface (GUI) in step 208, which is also discussed in [0068] and shown in Fig. 3B and 3C).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Liang to incorporate the teachings of Fong to display as information making up the first result and together as a whole to the user: each of the backend components making up the first set of the backend components, a resolution to the first request generated by each of the backend components making up the first set of the backend components, and for each of the backend components making up the first set of the backend components, invocation statistics is associated with an obtaining of the resolution. Doing so would meet the desire of a user that prompts computing devices to execute computing instructions to personalize the computing instructions based on the accuracy of the results, the infrastructure in which the computing devices are executing, and the cost to execute such computing instructions as taught by Fong ([0001]).
Liang and Fong do not teach
the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components.
Mei teaches
the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components (Abstract; Fig. 10; [0166]: user interface 1000 shows various navigation paths in 1002 along with statistics regarding application versions 1004, device types 1006, connection types 1008, carrier types 1010, and regions of end users 1012).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Liang and Fong to incorporate the teachings of Mei to the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components. Doing so would overcome the challenge of conventional end user monitoring platforms that typically gather and monitor data isolated to particular devices, nodes, processes, etc., and do not provide a complete picture of an end user's interaction with a website and/or mobile application as taught by Mei ([0003]).
With respect to claim 3,
As discussed regarding claim 1, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 1, wherein the data stored in the backend component evaluation data repository comprises an accuracy of each of the backend components and invocation performance of each of the backend components ([0089]: a 95% or 50% probability that the chatbot 241 will accurately and correctly respond to the user request, wherein the probability corresponds to an accuracy of each of the backend components in response to a user request).
With respect to claim 4,
As discussed regarding claim 3, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 3, wherein the data stored in the backend component evaluation data repository further comprises a user preference of the user ([0080]: the session manager 207 may load and store user profiles describing user behavior, preferences and interests of the user in a centralized database (such as data repository 227) and use historical data stored in the data repository 227 to further influence chatbot 241 selections made by the chatbot orchestration system 201 in the future (for either the same user or users having a similar user profile)).
With respect to claim 5,
As discussed regarding claim 3, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 3, wherein the accuracy of each of the backend components is based on feedback received from the user and other users that submitted other ones of the first user input ([0080]: for example, where positive feedback has been received for an identified conversation topic, the chatbot orchestration system 201 may be influenced to use the same chatbot 241 for responding to the same user (or similar users having a similar user profile) on the same or similar topic. Likewise, where a chatbot 241 was not satisfactory to a user, avoiding the use of the same chatbot 241 for the same or similar topic and instead defer the questions posed by the user's input to a different chatbot 241).
With respect to claim 6,
As discussed regarding claim 1, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 1, further comprising:
obtaining, after reporting the first result and from the user, user feedback with regard to the first result; and updating the data stored in the backend component evaluation data repository using the user feedback to obtain an updated backend component evaluation data repository (Fig. 2a; [0068]; [0080]; [0083]: collect user ratings, feedback and log overall satisfaction of the user, log user satisfaction and preferences to a centralized database (such as data repository 227), and use historical data stored in the data repository 227 to further influence chatbot selections in the future (for either the same user or users having a similar user profile)).
With respect to claim 7,
As discussed regarding claim 6, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 6, further comprising:
obtaining a second user input comprising a second request from the user, the second request being identical to the first request; invoking, based on data stored in the updated backend component evaluation data repository, a second set of the backend components to fulfill the second request (Fig. 2a; [0068]; [0080]; [0083]: use historical data stored in the data repository 227 to further influence chatbot selections in the future (for either the same user or users having a similar user profile). Likewise, where a chatbot 241 was not satisfactory to a user, avoiding the use of the same chatbot 241 for the same or similar topic and instead defer the questions posed by the user's input to a different chatbot 241); and
reporting a second result of the fulfillment of the second request to the user (Fig. 8b; [0113]: display the response received from the chatbot on the user system 235).
With respect to claim 8,
As discussed regarding claim 7, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 7, wherein the second set of the backend components is different from the first set of the backend components (Fig. 2a; [0068]; [0080]; [0083]: use historical data stored in the data repository 227 to further influence chatbot selections in the future (for either the same user or users having a similar user profile). Likewise, where a chatbot 241 was not satisfactory to a user, avoiding the use of the same chatbot 241 for the same or similar topic and instead defer the questions posed by the user's input to a different chatbot 241).
With respect to claim 11,
Liang teaches
a non-transitory machine-readable medium having instructions stored therein, which when executed by a processor (Fig. 1: processor(s) 103), cause the processor to perform operations for managing backend components (Abstract: orchestrate chat services by managing a plurality of backend chatbots registered with a centralized chat service, wherein registered chatbots correspond to backend components), the operations comprising:
obtaining a first user input comprising a first request from a user (Fig. 8a; [0109]: receive user input in step 805 and analyze user input to identify one or more intents in step 807, wherein the identified intents correspond to a first request from a user);
parsing the first user input to obtain one or more prestored keywords that are related to an intention of the user and a result desired by the user, the one or more prestored keywords being stored in and obtained from a backend component evaluation data repository (Fig. 2b; [0070]: the natural language processor 261 within the analytics module 205 may parse and analyze passages of the user input to identify one or more terms, including one or more intents evidenced by the user input. [0107]; [0082]: one or more intents associated with registration information for the chatbot 241 may be stored by the data repository 227 as chatbot registration 231, wherein the data repository 227 corresponds to “a backend component evaluation data repository”, intents in the form of terms are stored in it, and the intents indicate “a result desired by the user”);
selecting, based on data stored in the backend component evaluation data repository, a first set of backend components for fulling the first request by:
using, one or more mapping tables stored in the backend component evaluation data repository, to map the one or more prestored keywords to ones of the first set of backend components, the backend components and the one or more prestored keywords being stored in the one or more mapping tables as mapped data (Fig. 2a; [0088]: in response to a user question “can I check the balance on my credit card”, the analysis module 205 may detect important intents, such as “check”, “balance”, “credit card” associated with the user input, and the classification module 213 and the mapping module 215 use the detected intents to classify and identify the appropriate chatbots 241 for responding to the user input, wherein the mapping module 215 indicates “the one or more mapping tables as mapped data”);
invoking a first set of the backend components to fulfill the first request (Fig. 8a; [0110]-[0111]; Fig. 8b; [0112]: identify matching chatbots based on data maintained by data repository 227 and invoke the selected chatbot in step 823), wherein the first set of the backend components comprise components that are not originally designed to be interoperable with one another and are invoked to follow a unified interface and protocol defined by an entity of which the user is a member such that all of the first set of the backend components become interoperable with one another (Fig. 2a; [0090]; [0095]; [0112]: the orchestrator service 217 may comprise a format exchanger 221 that transforms the format of the user input and intents etc. into a format of the API that is used by the chatbot 241 selected to receive the user input and the resulting response received from the chatbot 241 into a format usable by the chat services 225, wherein the chatbots, which are not originally designed to be interoperable with each other, now follow a unified interface and protocol provided by the orchestrator service 217 to work together); and
reporting a first result of the fulfillment of the first request to the user (Fig. 8b; [0113]: display the response received from the chatbot on the user system 235),
Liang does not teach
wherein the first result comprises, as information making up the first result and displayed together as a whole to the user:
each of the backend components making up the first set of the backend components,
a resolution to the first request generated by each of the backend components making up the first set of the backend components, and
for each of the backend components making up the first set of the backend components, invocation statistics associated with an obtaining of the resolution, the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components.
Fong teaches
wherein the first result comprises, as information making up the first result and displayed together as a whole to the user (Fig. 2; [0039]; [0042]-[0043]; [0051]: obtain a request for a ML pipeline selection in step 200, identify a set of ML pipelines based on the domain specified in the request in step 202, train each ML pipeline in the set using a standard dataset to generate the runtime statistics in step 204, and present the ordering, the runtime statistics, and an explanation of the ordering of the ML pipelines to the client using a graphical user interface (GUI) in step 208):
each of the backend components making up the first set of the backend components (Fig. 2; [0051]; Fig. 3A-3C: the identified ML pipelines A-F as shown in Fig. 3A-3C correspond to “the first set of the backend components”),
a resolution to the first request generated by each of the backend components making up the first set of the backend components (Fig. 2; [0043]-[0044]; Fig. 3A; [0066]-[0067]: accuracy as shown in Fig. 3A is generated by each ML pipeline as a resolution to the user’s request for a ML pipeline selection thus corresponds to “a resolution to the first request”), and
for each of the backend components making up the first set of the backend components, invocation statistics associated with an obtaining of the resolution (Fig. 2; [0051]; Fig. 3B, 3C; [0068]: present the ordering, the runtime statistics, and an explanation of the ordering of the ML pipelines to the client using a graphical user interface (GUI) in step 208, which is also discussed in [0068] and shown in Fig. 3B and 3C).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Liang to incorporate the teachings of Fong to display as information making up the first result and together as a whole to the user: each of the backend components making up the first set of the backend components, a resolution to the first request generated by each of the backend components making up the first set of the backend components, and for each of the backend components making up the first set of the backend components, invocation statistics is associated with an obtaining of the resolution. Doing so would meet the desire of a user that prompts computing devices to execute computing instructions to personalize the computing instructions based on the accuracy of the results, the infrastructure in which the computing devices are executing, and the cost to execute such computing instructions as taught by Fong ([0001]).
Liang and Fong do not teach
the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components.
Mei teaches
the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components (Abstract; Fig. 10; [0166]: user interface 1000 shows various navigation paths in 1002 along with statistics regarding application versions 1004, device types 1006, connection types 1008, carrier types 1010, and regions of end users 1012).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Liang and Fong to incorporate the teachings of Mei to the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components. Doing so would overcome the challenge of conventional end user monitoring platforms that typically gather and monitor data isolated to particular devices, nodes, processes, etc., and do not provide a complete picture of an end user's interaction with a website and/or mobile application as taught by Mei ([0003]).
With respect to claim 13,
As discussed regarding claim 11, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the non-transitory machine-readable medium of claim 11, wherein the data stored in the backend component evaluation data repository comprises an accuracy of each of the backend components and invocation performance of each of the backend components ([0089]: a 95% or 50% probability that the chatbot 241 will accurately and correctly respond to the user request, wherein the probability corresponds to an accuracy of each of the backend components in response to a user request).
With respect to claim 14,
As discussed regarding claim 13, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the non-transitory machine-readable medium of claim 13, wherein the data stored in the backend component evaluation data repository further comprises a user preference of the user ([0080]: the session manager 207 may load and store user profiles describing user behavior, preferences and interests of the user in a centralized database (such as data repository 227) and use historical data stored in the data repository 227 to further influence chatbot 241 selections made by the chatbot orchestration system 201 in the future (for either the same user or users having a similar user profile)).
With respect to claim 15,
As discussed regarding claim 13, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the non-transitory machine-readable medium of claim 13, wherein the accuracy of each of the backend components is based on feedback received from the user and other users that submitted other ones of the first user input ([0080]: for example, where positive feedback has been received for an identified conversation topic, the chatbot orchestration system 201 may be influenced to use the same chatbot 241 for responding to the same user (or similar users having a similar user profile) on the same or similar topic. Likewise, where a chatbot 241 was not satisfactory to a user, avoiding the use of the same chatbot 241 for the same or similar topic and instead defer the questions posed by the user's input to a different chatbot 241).
With respect to claim 16,
Liang teaches
a backend component orchestrator (Fig. 2a), comprising:
a processor (Fig. 1: processor(s) 103); and a memory (Fig. 1: memory 105) coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations for managing backend components (Abstract: orchestrate chat services by managing a plurality of backend chatbots registered with a centralized chat service, wherein registered chatbots correspond to backend components), the operations comprising:
obtaining a first user input comprising a first request from a user (Fig. 8a; [0109]: receive user input in step 805 and analyze user input to identify one or more intents in step 807, wherein the identified intents correspond to a first request from a user);
parsing the first user input to obtain one or more prestored keywords that are related to an intention of the user and a result desired by the user, the one or more prestored keywords being stored in and obtained from a backend component evaluation data repository (Fig. 2b; [0070]: the natural language processor 261 within the analytics module 205 may parse and analyze passages of the user input to identify one or more terms, including one or more intents evidenced by the user input. [0107]; [0082]: one or more intents associated with registration information for the chatbot 241 may be stored by the data repository 227 as chatbot registration 231, wherein the data repository 227 corresponds to “a backend component evaluation data repository”, intents in the form of terms are stored in it, and the intents indicate “a result desired by the user”);
selecting, based on data stored in the backend component evaluation data repository, a first set of backend components for fulling the first request by:
using, one or more mapping tables stored in the backend component evaluation data repository, to map the one or more prestored keywords to ones of the first set of backend components, the backend components and the one or more prestored keywords being stored in the one or more mapping tables as mapped data (Fig. 2a; [0088]: in response to a user question “can I check the balance on my credit card”, the analysis module 205 may detect important intents, such as “check”, “balance”, “credit card” associated with the user input, and the classification module 213 and the mapping module 215 use the detected intents to classify and identify the appropriate chatbots 241 for responding to the user input, wherein the mapping module 215 indicates “the one or more mapping tables as mapped data”);
invoking a first set of the backend components to fulfill the first request (Fig. 8a; [0110]-[0111]; Fig. 8b; [0112]: identify matching chatbots based on data maintained by data repository 227 and invoke the selected chatbot in step 823), wherein the first set of the backend components comprise components that are not originally designed to be interoperable with one another and are invoked to follow a unified interface and protocol defined by an entity of which the user is a member such that all of the first set of the backend components become interoperable with one another (Fig. 2a; [0090]; [0095]; [0112]: the orchestrator service 217 may comprise a format exchanger 221 that transforms the format of the user input and intents etc. into a format of the API that is used by the chatbot 241 selected to receive the user input and the resulting response received from the chatbot 241 into a format usable by the chat services 225, wherein the chatbots, which are not originally designed to be interoperable with each other, now follow a unified interface and protocol provided by the orchestrator service 217 to work together); and
reporting a first result of the fulfillment of the first request to the user (Fig. 8b; [0113]: display the response received from the chatbot on the user system 235),
Liang does not teach
wherein the first result comprises, as information making up the first result and displayed together as a whole to the user:
each of the backend components making up the first set of the backend components,
a resolution to the first request generated by each of the backend components making up the first set of the backend components, and
for each of the backend components making up the first set of the backend components, invocation statistics associated with an obtaining of the resolution, the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components.
Fong teaches
wherein the first result comprises, as information making up the first result and displayed together as a whole to the user (Fig. 2; [0039]; [0042]-[0043]; [0051]: obtain a request for a ML pipeline selection in step 200, identify a set of ML pipelines based on the domain specified in the request in step 202, train each ML pipeline in the set using a standard dataset to generate the runtime statistics in step 204, and present the ordering, the runtime statistics, and an explanation of the ordering of the ML pipelines to the client using a graphical user interface (GUI) in step 208):
each of the backend components making up the first set of the backend components (Fig. 2; [0051]; Fig. 3A-3C: the identified ML pipelines A-F as shown in Fig. 3A-3C correspond to “the first set of the backend components”),
a resolution to the first request generated by each of the backend components making up the first set of the backend components (Fig. 2; [0043]-[0044]; Fig. 3A; [0066]-[0067]: accuracy as shown in Fig. 3A is generated by each ML pipeline as a resolution to the user’s request for a ML pipeline selection thus corresponds to “a resolution to the first request”), and
for each of the backend components making up the first set of the backend components, invocation statistics associated with an obtaining of the resolution (Fig. 2; [0051]; Fig. 3B, 3C; [0068]: present the ordering, the runtime statistics, and an explanation of the ordering of the ML pipelines to the client using a graphical user interface (GUI) in step 208, which is also discussed in [0068] and shown in Fig. 3B and 3C).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Liang to incorporate the teachings of Fong to display as information making up the first result and together as a whole to the user: each of the backend components making up the first set of the backend components, a resolution to the first request generated by each of the backend components making up the first set of the backend components, and for each of the backend components making up the first set of the backend components, invocation statistics is associated with an obtaining of the resolution. Doing so would meet the desire of a user that prompts computing devices to execute computing instructions to personalize the computing instructions based on the accuracy of the results, the infrastructure in which the computing devices are executing, and the cost to execute such computing instructions as taught by Fong ([0001]).
Liang and Fong do not teach
the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components.
Mei teaches
the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components (Abstract; Fig. 10; [0166]: user interface 1000 shows various navigation paths in 1002 along with statistics regarding application versions 1004, device types 1006, connection types 1008, carrier types 1010, and regions of end users 1012).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Liang and Fong to incorporate the teachings of Mei to the invocation statistics comprising at least a type of network connection required to invoke each of the backend components making up the first set of the backend components. Doing so would overcome the challenge of conventional end user monitoring platforms that typically gather and monitor data isolated to particular devices, nodes, processes, etc., and do not provide a complete picture of an end user's interaction with a website and/or mobile application as taught by Mei ([0003]).
With respect to claim 18,
As discussed regarding claim 16, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the backend component orchestrator of claim 16, wherein the data stored in the backend component evaluation data repository comprises an accuracy of each of the backend components and invocation performance of each of the backend components ([0089]: a 95% or 50% probability that the chatbot 241 will accurately and correctly respond to the user request, wherein the probability corresponds to an accuracy of each of the backend components in response to a user request).
With respect to claim 19,
As discussed regarding claim 18, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the backend component orchestrator of claim 18, wherein the data stored in the backend component evaluation data repository further comprises a user preference of the user ([0080]: the session manager 207 may load and store user profiles describing user behavior, preferences and interests of the user in a centralized database (such as data repository 227) and use historical data stored in the data repository 227 to further influence chatbot 241 selections made by the chatbot orchestration system 201 in the future (for either the same user or users having a similar user profile)).
With respect to claim 21,
As discussed regarding claim 1, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 1, wherein the first set of the backend components is selected from a group of backend components associated with the entity of which the user is a member through being part of a first internal team of the entity, and at least one backend component within the group of backend components is managed by a second internal team of the entity that is different from the first internal team ([0018]; Fig. 7; [0082]: chatbots registered with the orchestrated chat service are owned by different owners. When an owner of a registered chatbot uses the orchestrated chat service, the chatbots selected by the service as suitable may be owned by a different owner).
With respect to claim 22,
As discussed regarding claim 1, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 1, wherein the user is part of a first internal team of the entity and at least one of the backend components of the first set of the backend components is managed by a second internal team of the entity that is different from the first internal team, the user having no direct access to information associated with the at least one of the backend components of the first set of the backend components that is generated and managed by the second internal team without communicating with the second internal team or without being provided with the first result ([0018]; Fig. 7; [0082]: chatbots registered with the orchestrated chat service are owned by different owners. For a chatbot registered by other owners, the only information available to users about the chatbot is limited to what is provided by the owner using the form shown in Fig. 7, i.e., “the user having no direct access to information” associated with backend components generated and managed by other owners).
With respect to claim 23,
As discussed regarding claim 1, Liang and Fong and Mei teach all the limitations therein.
Liang further teaches
the method of claim 1, wherein the first set of the backend components are selected from a group of backend components accessible to the entity of which the user is a member, the group of backend components comprises internal backend components that are owned by the entity and external backend components that are not owned by the entity ([0018]; Fig. 7; [0082]: chatbots registered with the orchestrated chat service are owned by different owners. In reference to the owner of some registered chatbots, all other chatbots registered by other owners are “external backend components”).
Claims 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Liang et al. (US 20210144107 A1), in view of Fong et al. (US 20210241152 A1) and Mei et al. (US 20210227351 A1), and in further view of Jain et al. (US 12111747 B1).
With respect to claim 9,
As discussed regarding claim 1, Liang and Fong and Mei teach all the limitations therein.
Liang and Fong and Mei do not teach
the method of claim 1, wherein reporting the first result of the fulfillment of the first request to the user comprises:
generating one or more prompts for conveying the information making up the first result; generating, using a large language model (LLM), a summary comprising a summarization of the one or more prompts and the information making up the first result; and providing the summary to the user as the first result.
Jain teaches
the method of claim 1, wherein reporting the first result of the fulfillment of the first request to the user comprises:
generating one or more prompts for conveying the information making up the first result; generating, using a large language model (LLM), a summary comprising a summarization of the one or more prompts and the information making up the first result; and providing the summary to the user as the first result (Fig. 11; Col. 32, lines 57-67; Col. 33, lines 1-6: use LLMs to generate software-related code samples based on a desired output indicated in a prompt, for example, a text-based instruction. Col. 37, lines 7-19; Col. 38, lines 48-56: generate the output for display on a device associated with the user).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Liang and Fong and Mei to incorporate the teachings of Jain to generate one or more prompts for conveying the information making up the first result, generate, using a large language model (LLM), a summary comprising a summarization of the one or more prompts and the information making up the first result, and provide the summary to the user as the first result. Doing so would enable generation of outputs (e.g., natural language outputs) using models specified by the user when system resources are available to process associated prompts as taught by Jain (Col. 37, lines 16-19).
With respect to claim 10,
As discussed regarding claim 9, Liang and Fong and Mei and Jain teach all the limitations therein.
Jain further teaches
the method of claim 9, wherein the one or more prompts are dynamically generated based on a prompt preference of the user (Fig. 11; Col. 32, lines 57-67; Col. 33, lines 1-6: use LLMs to generate software-related code samples based on a desired output indicated in a prompt, for example, a text-based instruction).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIAOQIN HU whose telephone number is (571)272-1792. The examiner can normally be reached on Monday-Friday 7:00am-3:30pm.
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 on (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 an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/XIAOQIN HU/Examiner, Art Unit 2168
/CHARLES RONES/Supervisory Patent Examiner, Art Unit 2168