DETAILED ACTION
Status of the Application
The following is a non-Final office action. In response to Examiner's communication of February 12, 2026, Applicant, on April 13, 2026, elected Group II, claims 11-21, without traverse, added claims 22-31 directed to Group II, and canceled Group I, claims 1-10, being directed to the non-elected invention. Claims 11-31 are now pending and have been rejected below. The Information Disclosure Statements (IDS) filed on May 5, 2025 and July 3, 2025 has been acknowledged.
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . 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.
Election/Restrictions
Applicant’s election without traverse of Group II, claims 11-21, in the reply filed on April 13, 2026 is acknowledged. Claims 1-10 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected invention, there being no allowable generic or linking claim.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.
Claims 11-31 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claim 11, and similarly claims 12-31, in view of the first prong of Step 2A, recites:
inputting a first natural language message received … and a first contextual prompt associated with a first … transaction workflow …;
matching the first natural language message to a first portion of the first … transaction workflow based on a first textual output generated … in response to the first natural language message and the first contextual prompt;
generating, using a tree-based model for the first … transaction workflow, a first natural language response to the first natural language message, wherein the first natural language response comprises a query for one or more data elements associated with the first … transaction workflow;
causing the first natural language response to be transmitted …;
after the first natural language response is transmitted …, inputting a second natural language message received … and a second contextual prompt associated with the first … transaction workflow …;
generating one or more mappings between one or more portions of the second natural language message and the one or more data elements based on a second textual output generated … in response to the second natural language message and the second contextual prompt; and
causing the first … transaction workflow to be performed based on the one or more mappings.
Further, claims 16-17, and similarly claims 27-29, additionally recite:
wherein the first … transaction workflow comprises a travel booking;
wherein the one or more data elements comprise at least one of a booking type, a number of stops, a travel mode, a departure location, an arrival location, a departure date, or a return date; and
wherein causing the first … transaction workflow to be performed comprises generating a recommended itinerary for the travel booking based on the one or more data elements.
Claims 11-31, in view of the claim limitations, recite the abstract idea of receiving a first natural language message and contextual prompt associated with a transaction workflow, matching the first message to a portion of the transaction workflow based on first textual output and the first message and prompt, generating a first natural language response to the first message and prompt including a query for data elements associated with the transaction workflow based on a tree-based model, transmitting the first response to the first message, receiving a second natural language message and contextual prompt associated with the transaction workflow, generating mappings between portions of the second message and the queried data elements based on second textual output and the second message and prompt, and causing the transaction workflow to be performed based on the mappings.
As a whole, in view of the claim limitations, but for the computer components and systems performing the claimed functions, the broadest reasonable interpretation of the recited claim elements of receiving a first natural language message and contextual prompt associated with a transaction workflow, matching the first message to a portion of the transaction workflow based on first textual output and the first message and prompt, generating a first natural language response to the first message and prompt including a query for data elements associated with the transaction workflow based on a tree-based model, transmitting the first response to the first message, receiving a second natural language message and contextual prompt associated with the transaction workflow, generating mappings between portions of the second message and the queried data elements based on second textual output and the second message and prompt, and causing the transaction workflow to be performed based on the mappings could all be reasonably interpreted as a human making observations regarding the first and second natural language messages and prompts associated with a workflow, a human performing evaluations and making judgements to match the portions of the first message to the workflow, to generate a response to the messages, and to map the portions of the second message to the workflow, and a human causing the workflow to be perform based on the mapping either mentally and/or using a pen and paper; therefore, the claims recite mental processes. In addition, as a whole, in view of the claim limitations, the claim limitations discussed above manage the commercial interactions and business relations of receiving messages to perform a business transaction workflow, responding to the messages, and performing the business transaction workflow, and thus, the claims recite a certain method of organizing human activity. Further, with respect to the dependent claims, aside from the additional elements beyond the recited abstract idea addressed below under the second prong of Step 2A and 2B, the limitations of dependent claims 12-20 & 23-31 recite similar further abstract limitations to those discussed above that narrow the abstract idea recited in the independent claims because, aside from the generic computer components and systems performing the claimed functions, the limitations of claims manage personal human behavior and recite mental processes that can be practically performed mentally by observing, evaluating, and judging information mentally and/or with a pen and paper. Accordingly, since the claims recite mental processes and a certain method of organizing human activity, the claims recite an abstract idea under the first prong of Step 2A.
This judicial exception is not integrated into a practical application under the second prong of Step 2A. In particular, the claims recite the additional elements beyond the recited abstract idea of “[a] computing system, comprising: one or more processors; and one or more memory resources to store a set of instructions that, when executed by the one or more processors, cause the computing system to perform operations comprising,” from and to “a computing device,” “electronic,” and into and by the “a machine learning model” in claim 11, into, by, and from “the machine learning model” in claims 12, 15, 20, 23, 26, & 31, “[a] computer-implemented method comprising,” from and to “a computing device,” “electronic,” and into and by the “a machine learning model” in claim 21, “[a] non-transitory computer-readable medium storing instructions, that when executed by one or more processors of a computer system, cause the computer system to perform operations that comprise,” from and to “a computing device,” “electronic,” and into and by the “a machine learning model” in claim 22; however, individually and when viewed as an ordered combination, and pursuant to the broadest reasonable interpretation, each of the additional elements are computing elements recited at high level of generality implementing the abstract idea on a computer (i.e. apply it), and thus, are no more than applying the abstract idea with generic computer components. In addition, these elements merely generally link the abstract idea to a field of use/technological environment, namely a generic computing environment implementing a generic machine learning model. Moreover, aside from the aforementioned additional elements, the remaining elements of dependent claims 12-20 & 23-31 do not integrate the abstract idea into a practical application because these claims merely recite further limitations that provide no more than simply narrowing the recited abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception under Step 2B. As noted above, the aforementioned additional elements beyond the recited abstract idea, as an order combination, are no more than mere instructions to implement the idea using generic computer components (i.e., apply it), and further, generally link the abstract idea to a field of use, namely a generic computing environment implementing a generic machine learning model, which is not sufficient to amount to significantly more than an abstract idea; therefore, the additional elements are not sufficient to amount to significantly more than an abstract idea. Additionally, as an ordered combination, these elements, amount to generic computer components performing repetitive calculations and receiving or transmitting data over a network, which, as held by the courts, are well-understood, routine, and conventional. See MPEP 2106.05(d); July 2015 Update, p. 7. Moreover, aside from the aforementioned additional elements, the remaining elements of dependent claims 12-20 & 23-31 do not transform the recited abstract idea into a patent eligible invention because these claims merely recite further limitations that provide no more than simply narrowing the recited abstract idea.
Looking at these limitations as an ordered combination adds nothing additional that is sufficient to amount to significantly more than the recited abstract idea because they simply provide instructions to use a generic arrangement of generic computer components and recitations of generic computer structure that perform well-understood, routine, and conventional computer functions that are used to “apply” the recited abstract idea. Thus, the elements of the claims, considered both individually and as an ordered combination, are not sufficient to ensure that the claims as a whole amount to significantly more than the abstract idea itself. Since there are no limitations in these claims that transform the exception into a patent eligible application such that these claims amount to significantly more than the exception itself, claims 11-31 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 11-18, 20-29, & 31 are rejected under 35 U.S.C. 103 as being unpatentable over Hugelmann, et al. (US 20230368103 A1), hereinafter Hugelmann, in view of Huang, et al. (US 20210141862 A1), hereinafter Huang.
Regarding claim 11, Hugelmann discloses a computing system, comprising ([0022], [0042], [0092]-[0096]):
one or more processors; and
one or more memory resources to store a set of instructions that, when executed by the one or more processors, cause the computing system to perform operations comprising ([0022], [0042], [0092]-[0096]):
inputting a first natural language message received from a computing device and a first contextual prompt associated with a first electronic transaction workflow into a machine learning model ([0065]-[0066], at 502, the conversation simulation application 110 may receive a natural language command invoking a workflow of an enterprise software application (associated with the enterprise software applications 145 hosted at the enterprise backend 140) from the client device 115 input by the user 112, which may be provided as a text input and/or a voice input, and at 504, the conversation simulation application 110 may parse the natural language by calling the natural language processing (NLP) engine 130 to apply the machine learning model 133 using a traditional machine learning model or a deep learning model or using the natural language processor (NLP) 123);
matching the first natural language message to a first portion of the first electronic transaction workflow based on a first textual output generated by the machine learning model in response to the first natural language message and the first contextual prompt ([0066], at 504, the conversation simulation application 110 may parse the natural language command to identify a first entity associated with a first value included in the natural language command, wherein the parsing of the natural language command may include inferring, based at least on a first value included in the natural language command, a first entity corresponding to the first value corresponding to an enterprise workflow, e.g., the natural language command “Assign source of supply SoS_2 to purchase requisition PR_A” may include the value “assign source of supply SoS_2,” which may correspond to the enterprise workflow “AssignSource”);
generating, using a tree-based model for the first electronic transaction workflow, a first natural language response to the first natural language message, wherein the first natural language response comprises a query for one or more data elements associated with the first electronic transaction workflow ([0067]-[0068], at 506, the conversation simulation application 110 may determine, based at least on a knowledge graph 120 representative of an ontology 125 associated with the enterprise software application, a second entity related to the first entity and the enterprise workflow, e.g., upon determining that the value “assign source of supply SoS_2” in the natural language command corresponds to the enterprise workflow “AssignSource,” the conversation simulation application 110 may call the knowledge graph service 120 to identify additional entities related to the enterprise workflow “AssignSource,” such as data object “PurchaseRequisitionItem” and operation “UpdatePurchaseRequisitionItem.,” and at 508, upon determining that a second value of the second entity is absent from the natural language command, the conversation simulation application 110 may generate a first request for the second value);
causing the first natural language response to be transmitted to the computing device ([0068], where the initial natural language command fails to provide every value required to execute the enterprise workflow invoked by the natural language command, the runtime 113 of the conversation simulation application 110 may generate requests for these values to send, to the client device 115, a request for the value, e.g., where the natural language command fails to include the value “PR_A” for the data object “PurchaseRequisitionItem,” the runtime 113 of the conversation simulation application 110 may send, to the client device 115, a request for the value);
after the first natural language response is transmitted to the computing device, inputting a second natural language message received from the computing device and a second contextual prompt associated with the first electronic transaction workflow into the [simulation] ([0063], upon receiving the values required to perform the enterprise workflow, in the initial natural language command and in responses to subsequent requests, the runtime 113 of the conversation simulation application 110 (i.e. inputting into the simulation application) may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow, [0069], at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value (i.e. inputting into the simulation application), e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource”);
generating one or more mappings between one or more portions of the second natural language message and the one or more data elements based on a second textual output generated by the [simulation] in response to the second natural language message and the second contextual prompt ([0069], at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value, e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource,” [0053], which may be sent to the enterprise backend 140 hosting the one or more enterprise software application 145); and
causing the first electronic transaction workflow to be performed based on the one or more mappings ([0053], the request may be sent to the enterprise backend 140 hosting the one or more enterprise software application 145, [0069], at 510, e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may provide, to the client device 115, the result of executing the enterprise workflow “AssignSource”).
While Hugelmann discloses all of the above, including after the first natural language response is transmitted to the computing device, inputting a second natural language message received from the computing device and a second contextual prompt associated with the first electronic transaction workflow into the [simulation];
generating one or more mappings between one or more portions of the second natural language message and the one or more data elements based on a second textual output generated by the [simulation] in response to the second natural language message and the second contextual prompt (as above), and generally discusses the simulation application applies a machine learning model ([0062]), Hugelmann does not expressly require that the simulation application in which the message receive is input necessarily uses the same disclosed machine learning model to generate the formatted command using the first and second value received from the user responses; however, the following remaining limitations are taught by further teachings in Huang.
Huang teaches after the first natural language response is transmitted to the computing device ([0052]-[0053], [0057], in fig. 7, in the flow chart of an example runtime process 700 that begins with begins block 710 wherein an input question is received from a user, at 750 the answer to the current input question is output to the user from the workspace selected at block 740, from block 750 process 700 moves to query block 755, where if it is determined if the conversation is not finished, process 700 repeats the processing in blocks 710 through 740), inputting a second natural language message received from the computing device and a second contextual prompt associated with the first electronic transaction workflow ([0053], [0056]-[0057], at block 710 an input question is received from a user and forwarded to a set of chatbots 175, as well as to an adaptive orchestrator 151, as shown in FIG. 1, at block 720 features of the user's input question are extracted, such as an intent and an entity inherent in the user's question by a feature extraction component, such as feature extractor 153, of adaptive orchestrator 151, shown in FIG. 1, and at block 740 the adaptive multi-task orchestration is performed, which includes sub-blocks 741-743, wherein at sub-block 741 new intent/entity discovery is done in each chatbot at by feature extractor 153, of adaptive orchestrator 151, for example, of FIG. 1, [0023]-[0024], fig. 1A, adaptive orchestrator 151 forwards the question to each of the chabtots in the set 175, and each chatbot then identifies at least one intent and entity in response to the question and outputs one or more corresponding answers in response, the adaptive orchestrator 151 combines the respective extracted intents and entities of the user question 160 from the set of chatbots into a feature vector, which includes each of the <intent, entity> pairs of each of the chatbots 175, and the adaptive orchestrator 151 chooses one of the chatbots to provide the answer to the user by applying a predictive model 157 to the feature, which is the input to the predictive model 157) into the machine learning model ([0028], predictive model 157 included in the adaptive orchestrator 151 is a deep learning predictive model 157 to select a single chatbot's as the best one to respond to a user's question);
generating one or more mappings between one or more portions of the second natural language message and the one or more data elements based on a second textual output generated by the machine learning model in response to the second natural language message and the second contextual prompt ([0056]-[0057], wherein the parsing of the user's input has now resulted in one or more new intent/entity pairs from each chatbot, at block 740 the adaptive multi-task orchestration is performed, which includes sub-blocks 741-743, wherein at sub-block 743 a dialogue path choice is predicted based on the updated set of intents and entities, and at block 750 the answer to the current input question is output to the user from the workspace selected at block 740, [0024]-[0025], after the adaptive orchestrator 151 combines the respective extracted intents and entities of the user question 160 from the set of chatbots into a feature vector, which includes each of the <intent, entity> pairs of each of the chatbots 175, the adaptive orchestrator 151 chooses one of the chatbots to provide the answer to the user by applying a predictive model 157 to the feature, which is, in embodiments, the input to the predictive model 157, and once adaptive orchestrator chooses a best chatbot to respond to the user question, the selected chatbot then outputs the corresponding answer to this query, sending it to user interface 150 over communications links 182).
Hugelmann and Huang are analogous fields of invention because both address the problem of identifying a particular workflow to address a series of questions and responses from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to include in the system of Hugelmann the ability to input a second natural language message received from the computing device and a second contextual prompt associated with the first electronic transaction workflow and generate mappings between portions of the second natural language message and the data elements based on a second textual output generated by the machine learning model in response to the second natural language message and the second contextual prompt as taught by Huang since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the combination would produce the predictable results of inputting a second natural language message received from the computing device and a second contextual prompt associated with the first electronic transaction workflow and generating mappings between portions of the second natural language message and the data elements based on a second textual output generated by the machine learning model in response to the second natural language message and the second contextual prompt, as claimed. Further, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Huang in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 12, the combined teachings of Hugelmann and Huang teach the computing system of claim 11 (as above). Further, Hugelmann discloses wherein the instructions further cause the computing system to perform operations comprising:
inputting a third natural language message received from the computing device and a third contextual prompt ([0038], to parse a variety of natural language commands, the conversation simulation application is required to recognize the relationships that exist between various enterprise workflows, the sequence of associated operations, and the data objects and the data values of operations (i.e., third natural language message and contextual prompt), [0043], an updated ontology 127 with changes to the enterprise workflows replaces the ontology 125 such that subsequent natural language commands may be parsed (i.e., third natural language message and contextual prompt) into the machine learning model ([0065]-[0066], at 502, the conversation simulation application 110 may receive a natural language command invoking a workflow of an enterprise software application (associated with the enterprise software applications 145 hosted at the enterprise backend 140) from the client device 115 input by the user 112, which may be provided as a text input and/or a voice input, and at 504, the conversation simulation application 110 may parse the natural language by calling the natural language processing (NLP) engine 130 to apply the machine learning model 133 using a traditional machine learning model or a deep learning model or using the natural language processor (NLP) 123);
matching the third natural language message to a portion of a second electronic transaction workflow based on a third textual output generated by the machine learning model in response to the third natural language message and the third contextual prompt ([0066], at 504, the conversation simulation application 110 may parse the natural language command to identify a first entity associated with a first value included in the natural language command, wherein the parsing of the natural language command may include inferring, based at least on a first value included in the natural language command, a first entity corresponding to the first value corresponding to an enterprise workflow, e.g., the natural language command “Assign source of supply SoS_2 to purchase requisition PR_A” may include the value “assign source of supply SoS_2,” which may correspond to the enterprise workflow “AssignSource”); and
causing the second electronic transaction workflow to be performed based on the third natural language message and the third textual output ([0069], at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value (i.e. inputting into the simulation application), e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource,” [0063], upon receiving the values required to perform the enterprise workflow, in the initial natural language command and in responses to subsequent requests, the runtime 113 of the conversation simulation application 110 (i.e. inputting into the simulation application) may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow, [0053], the request may be sent to the enterprise backend 140 hosting the one or more enterprise software application 145).
Regarding claim 13, the combined teachings of Hugelmann and Huang teach the computing system of claim 11 (as above). Further, while Hugelmann discloses wherein the instructions further cause the computing system to perform operations comprising: generating a second … response to the second natural language message based on the second textual output; and causing the second … response to be transmitted to the computing device ([0036], wherein user interactions with the enterprise software application are conducted via the conversation simulation application (e.g., a chatbot), [0069], at 510, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value (i.e. inputting into the simulation application), e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may provide, to the client device 115, the result of executing the enterprise workflow “AssignSource”), and strongly suggests the output to the client device is a natural language response because the output in the above-cited paragraphs is from the conversation simulation application ([0069]), the conversation simulation application is a chatbot ([0036]), and other output to the client from the conversation simulation application disclosed by Hugelmann are natural language responses ([0037], [0040], [0046], [0053]), Hugelmann does not expressly disclose the remaining elements of the following limitations, which however, are taught by further teachings in Huang.
Huang teaches generating a second natural language response to the second natural language message based on the second textual output; and causing the second natural language response to be transmitted to the computing device ([0056]-[0057], at sub-block 743 a dialogue path choice is predicted based on the updated set of intents and entities, and at block 750 the answer to the current input question is output to the user from the workspace selected at block 740, [0024]-[0025], after the adaptive orchestrator 151 combines the respective extracted intents and entities of the user question 160 from the set of chatbots into a feature vector, which includes each of the <intent, entity> pairs of each of the chatbots 175, the adaptive orchestrator 151 chooses one of the chatbots to provide the answer to the user by applying a predictive model 157 to the feature, which is, in embodiments, the input to the predictive model 157, and once adaptive orchestrator chooses a best chatbot to respond to the user question, the selected chatbot then outputs the corresponding answer to this query, sending it to user interface 150 over communications links 182, [0063], an example output responding to the user question includes column 913 that has the answer or response provided by each respective workspace).
PNG
media_image1.png
579
754
media_image1.png
Greyscale
Hugelmann and Huang are analogous fields of invention because both address the problem of identifying a particular workflow to address a series of questions and responses from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Huang in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 14, the combined teachings of Hugelmann and Huang teach the computing system of claim 11 (as above). Further, Hugelmann discloses wherein the instructions further cause the computing system to perform operations comprising: causing the first electronic transaction workflow to be performed based on one or more additional data elements corresponding to one or more portions of the first natural language message ([0067]-[0069], at 506, the conversation simulation application 110 may determine, based at least on a knowledge graph 120 representative of an ontology 125 associated with the enterprise software application, a second entity related to the first entity and the enterprise workflow, e.g., upon determining that the value “assign source of supply SoS_2” in the natural language command corresponds to the enterprise workflow “AssignSource,” the conversation simulation application 110 may call the knowledge graph service 120 to identify additional entities related to the enterprise workflow “AssignSource,” such as data object “PurchaseRequisitionItem” and operation “UpdatePurchaseRequisitionItem,” at 508, upon determining that a second value of the second entity is absent from the natural language command, the conversation simulation application 110 may generate a first request for the second value, at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value (i.e. inputting into the simulation application), e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource”).
Regarding claim 15, the combined teachings of Hugelmann and Huang teach the computing system of claim 11 (as above). Further, while Hugelmann discloses all of the above and wherein generating the first natural language response comprises: determining a portion of the tree-based model corresponding to the first portion of the first electronic transaction workflow ([0067]-[0068], at 506, the conversation simulation application 110 may determine, based at least on a knowledge graph 120 representative of an ontology 125 associated with the enterprise software application, a second entity related to the first entity and the enterprise workflow, e.g., upon determining that the value “assign source of supply SoS_2” in the natural language command corresponds to the enterprise workflow “AssignSource,” the conversation simulation application 110 may call the knowledge graph service 120 to identify additional entities related to the enterprise workflow “AssignSource,” such as data object “PurchaseRequisitionItem” and operation “UpdatePurchaseRequisitionItem”);
inputting the first portion of the tree-based model into the [simulation] ([0063], upon receiving the values required to perform the enterprise workflow, in the initial natural language command and in responses to subsequent requests, the runtime 113 of the conversation simulation application 110 (i.e. inputting into the simulation application) may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow, [0069], at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value (i.e. inputting into the simulation application), e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource”); and
receiving the first natural language response as a response from the [simulation] to the inputted first portion of the tree-based model ([0069], at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value, e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource,” [0053], which may be sent to the enterprise backend 140 hosting the one or more enterprise software application 145), Hugelmann does not expressly require that the simulation application in which the message receive is input necessarily uses the same disclosed machine learning model to generate the formatted command using the first and second value received from the user responses; however, the following remaining limitations are taught by further teachings in Huang.
Huang teaches determining a portion of the tree-based model corresponding to the first portion of the first electronic transaction workflow ([0040]-[0041], [0043]-[0044], fig. 2A-2B, 3, chatbot conversation path is based on parsing an intent and entity in a conversation tree, wherein each path has a different intent and entity to indicate a different answer or action, wherein a question is processed at block 320 at each individual workspace/chatbot to extract the intents and entities, and when new intent and entity values are discovered, they are used to update a master intent/entity set and the existing dialogue path at block 330, [0053], [0056]-[0057], at block 710 an input question is received from a user and forwarded to a set of chatbots 175, as well as to an adaptive orchestrator 151, as shown in FIG. 1, at block 720 features of the user's input question are extracted, such as an intent and an entity inherent in the user's question by a feature extraction component, such as feature extractor 153, of adaptive orchestrator 151, shown in FIG. 1, and at block 740 the adaptive multi-task orchestration is performed, which includes sub-blocks 741-743, wherein at sub-block 741 new intent/entity discovery is done in each chatbot at by feature extractor 153, of adaptive orchestrator 151, for example, of FIG. 1, [0023]-[0024], fig. 1A, adaptive orchestrator 151 forwards the question to each of the chabtots in the set 175, and each chatbot then identifies at least one intent and entity in response to the question and outputs one or more corresponding answers in response);
inputting the first portion of the tree-based model ([0056]-[0057], wherein the parsing of the user's input has now resulted in one or more new intent/entity pairs from each chatbot, at block 740 the adaptive multi-task orchestration is performed, which includes sub-blocks 741-743, wherein at sub-block 743 a dialogue path choice is predicted based on the updated set of intents and entities, [0023]-[0024], fig. 1A, the adaptive orchestrator 151 combines the respective extracted intents and entities of the user question 160 from the set of chatbots into a feature vector, which includes each of the <intent, entity> pairs of each of the chatbots 175, and the adaptive orchestrator 151 chooses one of the chatbots to provide the answer to the user by applying a predictive model 157 to the feature, which is the input to the predictive model 157) into the machine learning model ([0028], predictive model 157 included in the adaptive orchestrator 151 is a deep learning predictive model 157 to select a single chatbot's as the best one to respond to a user's question); and
receiving the first natural language response as a response from the machine learning model to the inputted first portion of the tree-based model ([0056]-[0057], at sub-block 743 a dialogue path choice is predicted based on the updated set of intents and entities, and at block 750 the answer to the current input question is output to the user from the workspace selected at block 740, [0024]-[0025], after the adaptive orchestrator 151 combines the respective extracted intents and entities of the user question 160 from the set of chatbots into a feature vector, which includes each of the <intent, entity> pairs of each of the chatbots 175, the adaptive orchestrator 151 chooses one of the chatbots to provide the answer to the user by applying a predictive model 157 to the feature, which is, in embodiments, the input to the predictive model 157, and once adaptive orchestrator chooses a best chatbot to respond to the user question, the selected chatbot then outputs the corresponding answer to this query, sending it to user interface 150 over communications links 182).
Hugelmann and Huang are analogous fields of invention because both address the problem of identifying a particular workflow to address a series of questions and responses from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Huang in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 16, the combined teachings of Hugelmann and Huang teach the computing system of claim 11 (as above). Further, while Hugelmann discloses wherein the first electronic transaction workflow comprises a [purchase request] ([0051], [0066]-[0067], e.g., the natural language command may be “Assign source of supply SoS_2 to purchase requisition PR_A” corresponding to the enterprise workflow “AssignSource,” with the data object “PurchaseRequisitionItem” and the operation “UpdatePurchaseRequisitionItem,” [0047]-[0048], a query template for a natural language command corresponding to a workflow may include slots for multiple entities including a first attribute (e.g., ATTRIBUTE_1), a second attribute (ATTRIBUTE_DATETIME_2) of a data object (e.g., DATA_OBJECT_1), and the attribute may be associated with a specific datatype (e.g., DATETIME)), Hugelmann does not expressly disclose the remaining elements of the following limitations, which however, are taught by further teachings in Huang.
Huang teaches wherein the first electronic transaction workflow comprises a travel booking ([0027]-[0028], an example hotel booking chatbot may receive the following user query: “what hotels are available tonight in Chicago?” The intent is “find available tonight” and the entity is “hotel room in Chicago,” a chatbot 175 may identify a <intent, entity> attribute pair for the question, deep learning predictive model 157 selects a chatbot as the best one to respond to a user's question, and then outputs the response as an answer to user 161, thus completing the query-response loop, [0038], in an example a user asks an online chatbot that appears at a travel website “how much is a hotel room in Rome, Italy in August? Using an intent/entity parser, the chatbot may extract “find a price” as the intent, and “hotel in Rome in August” as the entity, and based on the extracted intent and entity, the chatbot generates one or more possible responses).
Hugelmann and Huang are analogous fields of invention because both address the problem of identifying a particular workflow to address a series of questions and responses from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Huang in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 17, the combined teachings of Hugelmann and Huang teach the computing system of claim 16 (as above). Further, while Hugelmann discloses wherein the one or more data elements comprise at least one of a [purchase] type, …, or a … date ([0051], [0066]-[0068], e.g., the natural language command may be “Assign source of supply SoS_2 to purchase requisition PR_A” corresponding to the enterprise workflow “AssignSource,” with the data object “PurchaseRequisitionItem” and the operation “UpdatePurchaseRequisitionItem,” the conversation simulation application 110 may generate a first request for the second value when the second value is absent, e.g., the natural language command fails to include the value “PR_A” for the data object “PurchaseRequisitionItem,” the runtime 113 of the conversation simulation application 110 may send, to the client device 115, a request for the value, [0047]-[0048], a query template for a natural language command corresponding to a workflow may include slots for multiple entities including a first attribute (e.g., ATTRIBUTE_1), a second attribute (ATTRIBUTE_DATETIME_2) of a data object (e.g., DATA_OBJECT_1), and the attribute may be associated with a specific datatype (e.g., DATETIME)), Hugelmann does not expressly disclose the remaining elements of the following limitations, which however, are taught by further teachings in Huang.
Huang teaches wherein the one or more data elements comprise at least one of a booking type, a number of stops, a travel mode, a departure location, an arrival location, a departure date, or a return date ([0027]-[0028], an example hotel booking chatbot may receive the following user query: “what hotels are available tonight in Chicago?” The intent is “find available tonight” and the entity is “hotel room in Chicago,” a chatbot 175 may identify a <intent, entity> attribute pair for the question, deep learning predictive model 157 selects a chatbot as the best one to respond to a user's question, and then outputs the response as an answer to user 161, thus completing the query-response loop, [0038], in an example a user asks an online chatbot that appears at a travel website “how much is a hotel room in Rome, Italy in August? Using an intent/entity parser, the chatbot may extract “find a price” as the intent, and “hotel in Rome in August” as the entity, and based on the extracted intent and entity, the chatbot generates one or more possible responses).
Hugelmann and Huang are analogous fields of invention because both address the problem of identifying a particular workflow to address a series of questions and responses from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Huang in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 18, the combined teachings of Hugelmann and Huang teach the computing system of claim 16 (as above). Further, while Hugelmann discloses wherein causing the first electronic transaction workflow to be performed comprises generating a recommended … based on the one or more data elements ([0051], [0066]-[0070], in response to receiving the second value, e.g., the missing value of “PR_A” of the “PurchaseRequisitionItem” natural language command, and then the runtime 113 of the conversation simulation application 110 may provide, to the client device 115, the result of executing the enterprise workflow “AssignSource”), Hugelmann does not expressly disclose the remaining elements of the following limitations, which however, are taught by further teachings in Huang.
Huang teaches wherein causing the first electronic transaction workflow to be performed comprises generating a recommended itinerary for the travel booking based on the one or more data elements ([0027]-[0028], an example hotel booking chatbot may receive the following user query: “what hotels are available tonight in Chicago?,” and deep learning predictive model 157 outputs the response as an answer to user 161, [0038], in an example a user asks an online chatbot that appears at a travel website “how much is a hotel room in Rome, Italy in August?,” and the chatbot generates one or more possible responses).
Hugelmann and Huang are analogous fields of invention because both address the problem of identifying a particular workflow to address a series of questions and responses from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Huang in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 20, the combined teachings of Hugelmann and Huang teach the computing system of claim 11 (as above). Further, while Hugelmann discloses all of the above and wherein the second textual output is further generated by the [simulation] based on the first natural language message and the first contextual prompt ([0069], at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value, e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource,” [0053], which may be sent to the enterprise backend 140 hosting the one or more enterprise software application 145), Hugelmann does not expressly disclose the remaining elements of the following limitations, which however, are taught by further teachings in Huang.
Huang teaches wherein the second textual output is further generated by the machine learning model ([0028], predictive model 157 included in the adaptive orchestrator 151 is a deep learning predictive model 157 to select a single chatbot's as the best one to respond to a user's question) based on the first natural language message and the first contextual prompt ([0056]-[0057], at sub-block 743 a dialogue path choice is predicted based on the updated set of intents and entities, and at block 750 the answer to the current input question is output to the user from the workspace selected at block 740, [0024]-[0025], after the adaptive orchestrator 151 combines the respective extracted intents and entities of the user question 160 from the set of chatbots into a feature vector, which includes each of the <intent, entity> pairs of each of the chatbots 175, the adaptive orchestrator 151 chooses one of the chatbots to provide the answer to the user by applying a predictive model 157 to the feature, which is, in embodiments, the input to the predictive model 157, and once adaptive orchestrator chooses a best chatbot to respond to the user question, the selected chatbot then outputs the corresponding answer to this query, sending it to user interface 150 over communications links 182).
Hugelmann and Huang are analogous fields of invention because both address the problem of identifying a particular workflow to address a series of questions and responses from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Huang in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 21, this claim is substantially similar to claim 11, and is, therefore, rejected on the same basis as claim 11. While claim 21 is directed toward a computer implemented method, Hugelmann discloses a method as claimed. [0022], [0042], [0092]-[0096].
Regarding claims 22-29 & 31, these claims are substantially similar to claims 11-18 & 20, respectively, and are, therefore, rejected on the same basis as claims 11-18 & 20. While claims 22-29 & 31 are directed toward a non-transitory computer-readable medium storing instructions executed by processors of a computer system to perform operations, Hugelmann discloses a computer readable storage medium as claimed. [0022], [0042], [0092]-[0096].
Claims 19 & 30 are rejected under 35 U.S.C. 103 as being unpatentable over Hugelmann, et al. (US 20230368103 A1), hereinafter Hugelmann, in view of Huang, et al. (US 20210141862 A1), hereinafter Huang, in further view of Sekar, et al. (US 20210201238 A1), hereinafter Sekar.
Regarding claim 19, the combined teachings of Hugelmann and Huang teach the computing system of claim 16 (as above). Further, while Hugelmann discloses all of the above and wherein causing the first electronic transaction workflow to be performed comprises transmitting the one or more mappings to an … computing device ([0069], at 510, in response to receiving the second value, the conversation simulation application 110 may generate a second request for the enterprise software application to execute the workflow based on the first value and the second value, e.g., as shown in FIGS. 4A-B, the runtime 113 of the conversation simulation application 110 may generate a formatted request for calling an application programming interface (API) of the enterprise backend 140 to execute the enterprise workflow “AssignSource,” and the runtime 113 of the conversation simulation application 110 may provide, to the client device 115, the result of executing the enterprise workflow “AssignSource,” [0053], in the event some data values are absent from the natural language command, the runtime 113 of the conversation simulation application 110 may generate, for output at the client device 115, a natural language response that includes a request for the missing data values, upon receiving the data values required to perform the enterprise workflow “AssignSource,” the runtime 113 of the conversation simulation application 110 may generate a request (e.g., an application programming interface (API) call and/or the like), which may be sent to the enterprise backend 140 hosting the one or more enterprise software application 145 to execute the enterprise workflow “AssignSource”), Hugelmann does not expressly disclose the remaining elements of the following limitations, which however, are taught by further teachings in Sekar.
Sekar teaches wherein causing the first electronic transaction workflow to be performed comprises transmitting the one or more mappings to an additional computing device associated with a human agent ([0048], once it is determined that an inbound communication should be handled by a human agent, functionality within the routing server 218 may select an agent from those available for routing the communication thereto, once the appropriate agent is selected, the contact center 200 forms a connection between the customer device 205 and the agent device 230 that corresponds to the selected agent, including information about the customer and/or the customer's history may be provided to the selected agent via his/her agent device 230, wherein this information generally includes data that may aid the selected agent to better service the customer, [0068], the chat server 240 captures and collects customer data in a unified way, wherein such data can be stored, shared, and utilized in a subsequent conversation, whether with the same chatbot or an agent chat, the chat server 240 orchestrates the sharing of data among the various chatbots 260 as interactions are transferred or transitioned over from one chatbot to a human agent, and the data captured during interaction with a particular chatbot may be transferred along with a request to a human agent).
Hugelmann and Sekar are analogous fields of invention because both address the problem of identifying a particular action and response to address questions from users. At the time the invention was effectively filed, it would have been obvious to one of ordinary skill in the art to include in the system of Hugelmann the ability to transmit the one or more mappings to an additional computing device associated with a human agent, as taught by Sekar, since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the combination would produce the predictable results of transmitting the mappings to an additional computing device associated with a human agent, as claimed. Further, it would have been obvious to one of ordinary skill in the art to have modified the Hugelmann with the aforementioned teachings of Sekar in order to produce the added benefit of orchestrating multi-task dialogues to decide which single-task dialogue could return the best answer. [0002].
Regarding claim 30, this claim is substantially similar to claim 19, and is, therefore, rejected on the same basis as claim 19. While claim 30 is directed toward a non-transitory computer-readable medium storing instructions executed by processors of a computer system to perform operations, Hugelmann discloses a computer readable storage medium as claimed. [0022], [0042], [0092]-[0096].
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Tiwari, et al. (US 20220237567 A1) disclosing a chatbot system is disclosed that enables users to apply for opportunities via a chat interface that prompts a user to provide a missing piece of applicant information by the chatbot identifying a slot in a node of a decision tree that has not been satisfied.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLES A GUILIANO whose telephone number is (571)272-9859. The examiner can normally be reached Mon-Fri 10:00 am - 6:00 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Rutao Wu can be reached at 571-272-6045. 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.
CHARLES GUILIANO
Primary Examiner
Art Unit 3623
/CHARLES GUILIANO/Primary Examiner, Art Unit 3623
Prosecution Insights