Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
Claims 1-3, 5, 7, 10-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter without significantly more. The claims as whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea.
Independent claims 1, 19 and 20 recite generate an indexed database based on a plurality of documentation from disparate data sources; provide a self-service function that includes a user interface as a search function and a chatbot, each configured to receive user queries regarding at least one of data or data analytics and return answers or results in response to the user queries based on the indexed database; and based on an inability to return an answer or result in response to a user query, route the user query to an agent selected from a plurality of agents for one of asynchronous or synchronous support for the user query. The limitations of generate, provide and route as drafted cover a mental process where a human catalogs technical articles and provides an index for important concepts for each of the multiple documents, and based on a person asking a question, looks up in the database and if unable to find an answer, writes the questions on paper and holds it in front of two other people to see if they know the answer.
This judicial exception is not integrated into a practical application. In particular claim 1 recites additional element of processor, which is a form of generic computer equipment. In the as-filed Specifications recite ¶[0059] Although computing system 300 of FIG. 3 is illustrated as a stand-alone device, in other examples computing system 300 may be implemented in any of a wide variety of ways, and may be implemented using multiple devices and/or systems. In some examples, computing system 300 may be, or may be part of, any component, device, or system that includes a processor or other suitable computing environment for processing information or executing software instructions and that operates in accordance with one or more aspects of the present disclosure. In some examples, computing system 300 may be fully implemented as hardware in one or more devices or logic elements. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional element of using a computer is noted as a general computer. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
Claims 2 recites wherein the user query identifies a data product associated with the at least one of data or data analytics, and wherein the processing circuitry is configured to: based on an indication from the selected agent, generate a product enhancement ticket to modify at least a portion of the data product based on the user query; and send control signals to one or more computing devices instructing the one or more computing devices to include the product enhancement ticket in a queue. This amounts to the 1st person saying he cannot answer, adds in a notebook under “tickets for improvement” the question that was not answered. No additional limitations are present.
Claims 3 recites periodically batch load the plurality of documentation from the disparate data sources; process content of the plurality of documentation, including format normalization, de-duplication, vectorization, and indexing of the content; and store the processed content in the indexed database for search and retrieval. This amounts to the human collecting a batch of new documents, indexing it again, assigning a numerical value to each new concept and writes it in the notebook. No additional limitations are present.
Claims 5recites wherein to provide the user interface as the search function, the processing circuitry is configured to provide the search function in an application. This amounts to the human allowing the person to write his question on a whiteboard. No additional limitations are present.
Claim 7 recites wherein the processing circuitry is configured to determine that the search function is unable to return the result in response to the user query based on confidence scores associated with one or more potential results from the search of the indexed database failing to satisfy a threshold. This amounts to the human not finding an answer to the question based on his search as all searches are below his threshold of 0.5. No additional limitations are present.
Claim 10 recites wherein the processing circuitry is configured to determine that the chatbot is unable to return the answer in response to the user query based on one of: an inability to understand the intent of the user query; confidence scores associated with the one or more results from the search of the indexed database failing to satisfy a threshold; or a determination of the intent to be a request for an agent. This amounts to the human not finding an answer to the question based on his search as all searches are below his threshold of 0.5. No additional limitations are present.
Claim 11 recites wherein the processing circuitry is configured to, based on an inability of the chatbot to return the answer in response to the user query, use the search function to perform a search of the indexed database based on the user query. This amounts to the human process where a human catalogs technical articles and provides an index for important concepts for each of the multiple documents, and based on a person asking a question, looks up in the database and if unable to find an answer, writes the questions on paper and holds it in front of two other people to see if they know the answer. No additional limitations are present.
Claim 12 recites wherein to route the user query to the selected agent, the processing circuity is configured to: determine a data product identified in the user query; determine a set of candidate agents associated with the data product; determine an activity status of each agent in the set of candidate agents based on an active directory; and select the agent from the set of candidate agents for the one of asynchronous or synchronous support for the user query based on the activity status of the agent. This amounts to the human where a human determining the question is about enhancing the motorcycle features, and forwards it to one of two people who are not busy. No additional limitations are present.
Claim 13 recites wherein to route the user query to the selected agent for synchronous support, the processing circuity is configured to: select the agent from the set of candidate agents based on the activity status of the agent indicating that the agent is currently available; and establish a synchronous live agent session in a chat portal between the first agent and a user from which the user query was received. This amounts to the human where a human determining the question is about enhancing the motorcycle features, and forwards it to one of two people who are not busy and the person communicates with the questioner. No additional limitations are present.
Claim 14 recites wherein based on no agent of the set of candidate agents being currently available, automatically generate a support ticket for the user query in an asynchronous ticketing system.. This amounts to the human on determining that none of the two people who answer questions is available, writing the question in the “tickets” section of his notebook. No additional limitations are present.
Claim 15 recites wherein to route the user query to the selected agent for asynchronous support, the processing circuity is configured to: route a user from which the user query was received to an asynchronous ticketing system for the user to generate a support ticket for the user query; select the agent from the set of candidate agents based on the activity status of the agent indicating that the agent was active during one or more previous days; and route the support ticket for the user query to the selected agent via the asynchronous ticketing system. This amounts to the human noting that the person whose question was ticketed and forwards the question to the third person who was helping that questioner yesterday. No additional limitations are present.
Claim 16 recites wherein to route the user query to the selected agent for asynchronous support, the processing circuity is configured to: automatically generate a support ticket for the user query in an asynchronous ticketing system; select the agent from the set of candidate agents based on the activity status of the agent indicating that the agent was active during one or more previous days; and route the support ticket for the user query to the selected agent via the asynchronous ticketing system. This amounts to the human noting that the person whose question was ticketed and forwards the question to the third person who was helping that questioner yesterday. No additional limitations are present.
Claim 17 recites wherein the processing circuitry is configured to, based on an indication from the selected agent, escalate the user query from the selected agent to a higher knowledge level agent from the set of candidate agents associated with the data product for the one of asynchronous or synchronous support for the user query. This amounts to the selected person who answered the question deciding his skill level is inadequate and lets the fourth higher knowledge person answer the question. No additional limitations are present.
Claim 18 recites wherein to select the agent from the set of candidate agents, the processing circuitry is configured to: identify a first agent from the set of candidate agents based on a first knowledge level of the first agent; based on the activity status of the first agent indicating that the first agent is not available, selecting a second agent from the set of candidate agents based on a second knowledge level of the second agent and the activity status of the second agent indicating that the second agent is available, wherein the second knowledge level is higher than the first knowledge level. This amounts to the human asking person 1 to answer and realizing that he is not there, asks person to who is more knowledgeable to instead answer. No additional limitations are present.
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 (i.e., changing from AIA to pre-AIA ) 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor et al. (US 20250061491 A1 )(herein " Ahmad-Taylor "), and in further view of Zhang et al. (US 20180054464 A1 )(herein "Zhang") and Bonageri et al. (US 20200410614 A1 )(herein " Bonageri")
With respect to claims 1, 19 and 20, Ahmad Taylor teaches (claim 1. )A computing system comprising: memory (Ahmad-Taylor ¶[0192] The machine 900 may include processors 904, memory 906, and input/output I/O components 908, which may be configured to communicate with each other via a bus 910.); (claim 19. ) A method comprising: (claim 20. ) 20. Non-transitory computer readable media comprising instructions that, when executed, cause one or more programmable processors to: ([0317] “Non-transitory machine-readable storage medium” refers to a tangible medium that is capable of storing, encoding, or carrying the instructions for execution by a machine.)
and processing circuitry in communication with the memory and configured to (Ahmad-Taylor ¶[0192] The machine 900 may include processors 904, memory 906, and input/output I/O components 908, which may be configured to communicate with each other via a bus 910.):
[[generate an indexed database based on a plurality of documentation from disparate data sources]]; provide a self-service function that includes a user interface as a search function and a chatbot, each configured to receive user queries regarding at least one of data or data analytics and return answers or results in response to the user queries based on the indexed database (Ahmad-Taylor ¶[0020] In some examples, a chatbot [chatbot] system using a dynamic advertisement system allows businesses to directly engage with customers [self-help]through a chat interface, freeing businesses to focus on more meaningful customer conversations. For instance, by handling common product queries, pricing questions, and transactional processes automatically, the chatbot system reduces the repetitive day-to-day customer service burden on vendor agents, ¶[0029] In some examples, the chatbot system stores the aggregated catalog data from all vendors in an inventory database. When a user submits a query [queries] through the chat interface regarding a product, the chatbot system accesses the inventory database [database] to identify vendors with the product and determine availability across catalogs. The chatbot system generates a natural language response to the user query using this data, allowing it to engage in a conversational dialogue.);
Ahmad-Taylor does not explicitly disclose however Zhang teaches based on an inability to return an answer or result in response to a user query, route the user query to an agent selected from a plurality of agents for one of asynchronous or synchronous support for the user (Zhang ¶[0057] The human agent may also assess from time to time during the dialog, at 168, whether there is a need to route the chat user to a different [plurality of agents] agent, either virtual or human. If no, the conversation continues at 166. If there is a need to route the chat user to other agent, the process proceeds to 154, where it is determined whether to route to a (different) human agent or a virtual agent. Once the new conversation is initiated with a different agent, the process proceeds to 150, ¶[0076] In a different situation, the agent re-router 260 may re-route the user to the human agent [synchronous]150, when, e.g., the conversation with the user indicates a situation that requires human agent involvement [inability to return an answer]. Such a situation may be pre-defined or dynamically detected. )
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor to include routing of Zhang in order to preserve context and optimize support for user issues.
None of Ahmad-Taylor and Zhang explicitly disclose however Bonageri teaches generate an indexed database based on a plurality of documentation from disparate data sources (Bonageri ¶[0040] For example, the server 110 can invoke a single database query to access relevant medical record data stored within a row and/or column of an aggregate data structure instead of necessitating multiple database queries to access the same type of data from multiple data structures. This can be accomplished by generating an indexed database record that enables the server 110 to filter, search, and/or parallel process processed data obtained from multiple disparate data sources , ¶[0057] In this manner, the aggregated data 104 represents clinical trial data obtained from multiple disparate data sources that has been filtered, sorted, and segmented with respect to various types of hierarchical levels (e.g., individual investigators, individual clinical trial sites, individual drug trials conducted at multiple clinical trial sites, etc.).)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang to include indexed database of Bonageri in order to maintain data consistency and unified search and retrieval.
Claim (s) 2 is(are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang and Bonageri in further view of Srivastava (US 20090043882 A1).
With respect to claim 2, none of Ahmad-Taylor, Zhang and Bonageri explicitly disclose however Srivastava teaches wherein the user query identifies a data product associated with the at least one of data or data analytics, and wherein the processing circuitry is configured to: based on an indication from the selected agent, generate a product enhancement ticket to modify at least a portion of the data product based on the user query ([0005] It is an objective of the present invention to provide a method and a system for AI-driven & AI-optimized decisions, actions, & workflows in process operations. In an embodiment, the present invention enables users to go from transactional to analytical to predictive to action to transactional scenarios. The present invention aims to automate the following workflows: [0006] 1. Customer Transaction Occurs [0007] 2. Employees determine if they can act on the transaction [0008] 3. Employees enable the transaction [0009] 4. If they cannot enable, they create tickets [0010] 5. Tickets are worked on by other employees [0011] 6. Other employees analyze and generate insights [0012] 7. Other employees research the transactions and generate an understanding of what needs to be improved or developed [0013] 8. These employees research and generate ideas, discussions and strategies to address these problems [0014] 9. These employees generate & research documents and content to support their hypothesis and plans; and send control signals to one or more computing devices instructing the one or more computing devices to include the product enhancement ticket in a (¶[0015]The system of the present invention can analyze the content of the ticket and assign the ticket automatically to the appropriate ticket queue that is owned by a user or team. The one or more tickets are automatically created by observing individual events as they occur in real-time or by observing groups of events that are related or based on the output of AI processing of incoming events and transactions or documents )
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include ticket generation of Srivastava in order to improve data products adapt to users’ needs and reduce product backlog
Claim (s) 3 and 4 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri in further view of Baker (US 20090043882 A1).
With respect to claim 3, Bonageri further teaches store the processed content in the indexed database for search and retrieval (Bonageri ¶[0040] For example, the server 110 can invoke a single database query to access relevant medical record data stored within a row and/or column of an aggregate data structure instead of necessitating multiple database queries to access the same type of data from multiple data structures. This can be accomplished by generating an indexed database record that enables the server 110 to filter, search, and/or parallel process processed data obtained from multiple disparate data sources , ¶[0057] T In this manner, the aggregated data 104 represents clinical trial data obtained from multiple disparate data sources that has been filtered, sorted, and segmented with respect to various types of hierarchical levels (e.g., individual investigators, individual clinical trial sites, individual drug trials conducted at multiple clinical trial sites, etc.).)
None of Ahmad-Taylor, Zhang and Bonageri explicitly disclose however Baker teaches wherein to generate the indexed database, the processing circuitry is configured to: periodically batch load the plurality of documentation from the disparate data sources (Baker ¶[0023] The RSS feeds [data sources] may be a precompiled list of RSS feeds that are published and constantly updated [batch load] by content provider 104...Parser module 204 may parse the RSS feeds using a third-party open source Python module called Feedparser, for example.);
process content of the plurality of documentation, including format normalization, de-duplication, vectorization, and indexing of the content; [[and store the processed content in the indexed database for search and retrieval ]](Baker ¶[0036] Preprocessing module 212 may implement the one or more preprocessing steps on the title of each article using the same steps described previously: (1) tokenization; (2) lowercasing; (3) stopwords removal; and (4) stemming. Once preprocessing module 212 has preprocessed the titles in the set of articles, deduplication [de-duplication] module 210 may vectorize the titles using a bag-of-words vectorization [vectorization] approach and the vectors are weighted using the algorithm known as TF-IDF. Finally vectors are reduced in dimensionality using the Latent Semantic Indexing [indexing] (LSI) algorithm, ¶[0074] Summarization system 110 may then retrieve the textual content embedded [format normalization] in the HTML code of the article from the URL.)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include batch loading of Baker in order to improve network efficiency and resource optimization.
With respect to claim 4, Baker further teaches wherein to periodically batch load the plurality of documentation, the processing circuitry is configured to: periodically batch load documentation from one or more internal document repositories associated with one or more enterprise services via one or more service-specific connectors or application programming interfaces (APIs) (Baker ¶[0023] Parsing module 204 is configured to parse one or more Rich Site Summary (RSS) feeds. The RSS feeds may be provided by content provider 104. The RSS feed may include one or more entries identifying an article published by content provider 104. The RSS feeds may be monitored by interface module 202 and/or parsing module 204. The RSS feeds may be a precompiled list of RSS feeds that are published and constantly updated by content provider 104. Parser module 204 stores a precompiled list of RSS feeds in data storage 120 and retrieves them at regular intervals. Parser module 204 may parse the RSS feeds using a third-party open source Python module called Feedparser, [enterprise services] for example.)); and
periodically batch load documentation form one or more external document repositories associated with one or more websites via one or more web scrapers (Baker ¶[0024] Parser module 204 is configured to parse the RSS feeds to retrieve one or more URLs [websites]. Each URL corresponds to a specific article. For each URL retrieved, Parser module 204 also extracts a title and a publication date for that article).
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include batch loading of Baker in order to improve network efficiency and resource optimization.
Claim (s) 5 and 6 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri in further view of Mendes (US 20240054285 A1).
With respect to claim 5 None of Ahmad-Taylor, Zhang and Bonageri explicitly disclose however Mendes teaches wherein to provide the user interface as the search function, the processing circuitry is configured to provide the search function in an application(Mendes ¶[0036] The one or more search attributes can include text content that can be compared to the text of the user's question and/or problem statement.,¶[0076] At 1208, the computer-implemented method 1200 can comprise searching (e.g., via API [search function in an application] 206), by the system 100, the indexed attributes of the prepared knowledge database 120 for one or more articles responsive to a user's inquiry with the virtual assistant 116. In one or more embodiments, the query interface to the knowledge database 120 can be decoupled from the graphical user interface (e.g., of the one or more input device 106), which allows its use both by the virtual assistant 116 itself and by other applications.)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include search function of Mendes in order to improve seamless integration in the user workflow and increase accessibility.
With respect to claim 6 none of Ahmad-Taylor, Zhang and Bonageri explicitly disclose however Mendes teaches wherein to provide the user interface as the search function, the processing circuitry is configured to: receive the user query via the user interface (Mendes ¶[0076] At 1208, the computer-implemented method 1200 can comprise searching (e.g., via API 206), by the system 100, the indexed attributes of the prepared knowledge database 120 for one or more articles responsive to a user's inquiry with the virtual assistant 116. In one or more embodiments, the query interface to the knowledge database 120 can be decoupled from the graphical user interface (e.g., of the one or more input device 106), which allows its use both by the virtual assistant 116 itself and by other applications);
perform a search of the indexed database via a runtime application programming interface (API) call based on a vectorized version of the user query (Mendes ¶[0036] The one or more search attributes can include text content that can be compared [digital representation=vectorization required for this computation] to the text of the user's question and/or problem statement.,[0076] At 1208, the computer-implemented method 1200 can comprise searching (e.g., via API [API] 206), by the system 100, the indexed attributes of the prepared knowledge database 120 for one or more articles responsive to a user's inquiry [query] with the virtual assistant 116. In one or more embodiments, the query interface to the knowledge database 120 can be decoupled from the graphical user interface (e.g., of the one or more input device 106), which allows its use both by the virtual assistant 116 itself and by other applications.); and
based on identifying at least one result from the search of the indexed database, return the at least one result for display via the user interface (Mendes ¶[0099]Also, in one or more embodiments the one or more input devices 106 can be employed to display [display] one or more outputs from the one or more computing devices 102 and/or query one or more system 100 users. For example, the one or more input devices 106 can send, receive, and/or otherwise share data (e.g., inputs and/or outputs) with the computing device 102 (e.g., via a direct electrical connection and/or the one or more networks 104)).
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include search function of Mendes in order to improve seamless integration in the user workflow and increase accessibility.
Claim (s) 7 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri and Mendes in further view of Legrand (US 20150227631 A1).
With respect to claim 7 none of Ahmad-Taylor, Zhang, Bonageri and Mendes explicitly disclose however Legrand teaches wherein the processing circuitry is configured to determine that the search function is unable to return the result in response to the user query based on confidence scores associated with one or more potential results from the search of the indexed database failing to satisfy a threshold (Legrand ¶[0038] In other embodiments, the client 4 may initially also be provided with pre-collected search results below (i.e., less than) the confidence threshold, while the search platform performs a validation of these pre-collected search results below the threshold [threshold] and updates the tentatively returned pre-collected search results below the threshold with the corresponding validated search results. These mechanisms have the effect that pre-collected search results at the search platform 2 that have a higher likelihood of being invalid [unable to return results] are either not returned at all to the client or updated with search results having a higher likelihood of being valid).
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of search function of Mendes to include inability to return result of Legrand in order to reduce noise and clutter and improving user experience.
Claim (s) 8 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri in further view of Kozhaya (US 20210058455 A1).
With respect to claim 8 None of Ahmad-Taylor, Zhang, Bonageri explicitly disclose, however Kozhaya teaches wherein to provide the user interface as the chatbot, the processing circuitry is configured provide the chatbot as an application programming interface (API) microservice in at least one of an application or a website (Kozhaya ¶[0046] Further, by parsing the code of the microservice, [microservice] illustrative embodiments may identify another resource, such as, for example, a particular type of assistant [chatbot] service API, [API] utilized by the microservice).
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include microservice of Kozhaya in order to improve scalability and simplify maintenance.
Claim (s) 9 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri in further view of Kok (US 20210058455 A1).
With respect to claim 9 Ahmad-Taylor teaches return the answer for display via the user interface (Ahmad-Taylor [0150] In operation 410, the chatbot system 300 provides the natural language product query message 360 to the user during the conversation 338. For example, after formulating the natural language product query message 360 comprising relevant vendor, product, and inventory information, the chatbot system 300 provides this information to the user 320 through a conversational chat interface via the client system 306 during the conversation 338.)
None of Ahmad-Taylor, Zhang, Bonageri explicitly disclose, however Kok teaches wherein to provide the user interface as the chatbot, the processing circuitry is configured to: receive the user query via the user interface (Kok ¶ [0062] In further aspects, a booking application may be configured to receive an input (e.g., text, voice, speech, audio, gesture, visual cue, or the like) from a user. The user input may include a query, a description);
determine an intent of the user query (Kok ¶ [0062] In further aspects, a booking application may be configured to receive an input (e.g., text, voice, speech, audio, gesture, visual cue, or the like) from a user. The user input may include a query, a description, ¶[0087] In some embodiments, retrieval augmented generation (RAG) [RAG] may be utilized to retrieve contextually relevant data (e.g., up-to-date, proprietary, private, or dynamic data) from a database associated with a system (e.g., a system performing process 400). The contextually relevant data may be provided to an LLM to improve the accuracy and performance of the LLM. System-specific data or proprietary data may be converted into vectors by providing the data as input into an embedding model, which may be a type of ML model that converts data into vectors, arrays, or groups of numbers. Vector representation of the data may enable the search for semantically similar items based on the numerical representation of the data... By means of non-limiting example, when a user inputs a query [query] in natural language, natural language search terms of the input may be translated into embeddings. The embeddings may be sent to a vector database, where a semantic search may be performed to determine vectors that most closely resemble a user intent. The results of the search (e.g., the retrieved contexts) may be included in a prompt composed for an LLM. The LLM may produce a more satisfactory (e.g., accurate or relevant) output because the LLM has access to the most contextually relevant data from the vector database, ¶[0089] In some embodiments, operation 434 may include initiating a function call. An LLM may enable access to external application programming interfaces (APIs) [API] by determining when and how a function should be called based on the context of an LLM prompt, and by structuring outputs based on a function specified in the LLM prompt.);
based on determining the intent to be a search request, perform retrieval-augmented generation (RAG) that includes a search of the indexed database via a runtime application programming interface (API) call based on the intent of the user query and generation of a natural language answer to the search request based on one or more results from the search of the indexed database input to a large language model (LLM) (Kok ¶ [0062] In further aspects, a booking application may be configured to receive an input (e.g., text, voice, speech, audio, gesture, visual cue, or the like) from a user. The user input may include a query, a description, ¶[0087] In some embodiments, retrieval augmented generation (RAG) [RAG] may be utilized to retrieve contextually relevant data (e.g., up-to-date, proprietary, private, or dynamic data) from a database associated with a system (e.g., a system performing process 400). The contextually relevant data may be provided to an LLM to improve the accuracy and performance of the LLM. System-specific data or proprietary data may be converted into vectors by providing the data as input into an embedding model, which may be a type of ML model that converts data into vectors, arrays, or groups of numbers. Vector representation of the data may enable the search for semantically similar items based on the numerical representation of the data... By means of non-limiting example, when a user inputs a query [query] in natural language, natural language search terms of the input may be translated into embeddings. The embeddings may be sent to a vector database, where a semantic search may be performed to determine vectors that most closely resemble a user intent. The results of the search (e.g., the retrieved contexts) may be included in a prompt composed for an LLM. The LLM may produce a more satisfactory (e.g., accurate or relevant) output because the LLM has access to the most contextually relevant data from the vector database, ¶[0089] In some embodiments, operation 434 may include initiating a function call. An LLM may enable access to external application programming interfaces (APIs) [API] by determining when and how a function should be called based on the context of an LLM prompt, and by structuring outputs based on a function specified in the LLM prompt.);
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include API/LLM of Kok in order to enhance contextual relevance using real-time data with API calls.
Claim (s) 10 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri, Kok in further view of Legrand.
With respect to claim 10 none of Ahmad-Taylor, Zhang, Bonageri and Kok explicitly disclose, however Legrand teaches wherein the processing circuitry is configured to determine that the chatbot is unable to return the answer in response to the user query based on one of: an inability to understand the intent of the user query; confidence scores associated with the one or more results from the search of the indexed database failing to satisfy a threshold (Legrand ¶[0038] In other embodiments, the client 4 may initially also be provided with pre-collected search results below (i.e., less than) the confidence threshold, while the search platform performs a validation of these pre-collected search results below the threshold [threshold] and updates the tentatively returned pre-collected search results below the threshold with the corresponding validated search results. These mechanisms have the effect that pre-collected search results at the search platform 2 that have a higher likelihood of being invalid [unable to return results] are either not returned at all to the client or updated with search results having a higher likelihood of being valid); or a determination of the intent to be a request for an agent.
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of API/LLM of Kok to include inability to answer of Legrand in order to reduce noise and clutter and improving user experience.
Claim (s) 11 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri in further view of Legrand.
With respect to claim 10 none of Ahmad-Taylor, Zhang, Bonageri explicitly disclose, however Legrand teaches wherein the processing circuitry is configured to, based on an inability of the chatbot to return the answer in response to the user query, use the search function to perform a search of the indexed database based on the user query (Legrand ¶[0038] In other embodiments, the client 4 may initially also be provided with pre-collected search results below (i.e., less than) the confidence threshold, while the search platform performs a validation of these pre-collected search results below the threshold [threshold] and updates the tentatively returned pre-collected search results below the threshold with the corresponding validated search results. These mechanisms have the effect that pre-collected search results at the search platform 2 that have a higher likelihood of being invalid [unable to return results] are either not returned at all to the client or updated with search results having a higher likelihood of being valid).
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include inability to answer of Legrand in order to reduce noise and clutter and improving user experience.
Claim (s) 12, 13 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri in further view of Jaiswal (US 20080144803 A1).
With respect to claim 12 none of Ahmad-Taylor, Zhang, Bonageri explicitly disclose however Jaiswal teaches wherein to route the user query to the selected agent, the processing circuity is configured to: determine a data product identified in the user query (Jaiswal ¶[0017] When an incoming call is received, the incoming call may be identified by call director 108 based on the type [data product] of call (e.g., a call for technical assistance, a call for billing questions, etc.), the type of caller placing the call (e.g., a premier caller may be provided level-3 support rather than level-1 support), and the like. Once the type of call or the caller is known, the call routing software determines which of call support agents 110-118 [candidate agents] has the necessary skill set to handle the incoming call. For example, if the incoming call is from a non-premier caller who has a basic technical question (i.e., level-1 question), the call routing software identifies that this call may be handled by an agent with a basic skill set, and therefore assigns the first available [activity status] call support agent in the level-1 group, such as call support agent 110, to the incoming call. It should be noted that while the present invention is described in terms of tiers of support, e.g., level-1 and level-2 support, the present invention is not limited to such. Rather, these designations are only provided for illustration in order to differentiate between human operators rather than to imply any particular limitations of the present invention);
determine a set of candidate agents associated with the data product (Jaiswal ¶[0017] When an incoming call is received, the incoming call may be identified by call director 108 based on the type [data product] of call (e.g., a call for technical assistance, a call for billing questions, etc.), the type of caller placing the call (e.g., a premier caller may be provided level-3 support rather than level-1 support), and the like. Once the type of call or the caller is known, the call routing software determines which of call support agents 110-118 [candidate agents] has the necessary skill set to handle the incoming call. For example, if the incoming call is from a non-premier caller who has a basic technical question (i.e., level-1 question), the call routing software identifies that this call may be handled by an agent with a basic skill set, and therefore assigns the first available [activity status] call support agent in the level-1 group, such as call support agent 110, to the incoming call. It should be noted that while the present invention is described in terms of tiers of support, e.g., level-1 and level-2 support, the present invention is not limited to such. Rather, these designations are only provided for illustration in order to differentiate between human operators rather than to imply any particular limitations of the present invention);
determine an activity status of each agent in the set of candidate agents based on an active directory (Jaiswal ¶[0017] When an incoming call is received, the incoming call may be identified by call director 108 based on the type [data product] of call (e.g., a call for technical assistance, a call for billing questions, etc.), the type of caller placing the call (e.g., a premier caller may be provided level-3 support rather than level-1 support), and the like. Once the type of call or the caller is known, the call routing software determines which of call support agents 110-118 [candidate agents] has the necessary skill set to handle the incoming call. For example, if the incoming call is from a non-premier caller who has a basic technical question (i.e., level-1 question), the call routing software identifies that this call may be handled by an agent with a basic skill set, and therefore assigns the first available [activity status] call support agent in the level-1 group, such as call support agent 110, to the incoming call. It should be noted that while the present invention is described in terms of tiers of support, e.g., level-1 and level-2 support, the present invention is not limited to such. Rather, these designations are only provided for illustration in order to differentiate between human operators rather than to imply any particular limitations of the present invention); and
select the agent from the set of candidate agents for the one of asynchronous or synchronous support for the user query based on the activity status of the agent (Jaiswal ¶[0017] When an incoming call is received, the incoming call may be identified by call director 108 based on the type [data product] of call (e.g., a call for technical assistance, a call for billing questions, etc.), the type of caller placing the call (e.g., a premier caller may be provided level-3 support rather than level-1 support), and the like. Once the type of call or the caller is known, the call routing software determines which of call support agents 110-118 [candidate agents] has the necessary skill set to handle the incoming call. For example, if the incoming call is from a non-premier caller who has a basic technical question (i.e., level-1 question), the call routing software identifies that this call may be handled by an agent with a basic skill set, and therefore assigns [selects] the first available [activity status] call support agent in the level-1 group, such as call support agent 110, to the incoming call. It should be noted that while the present invention is described in terms of tiers of support, e.g., level-1 and level-2 support, the present invention is not limited to such. Rather, these designations are only provided for illustration in order to differentiate between human operators rather than to imply any particular limitations of the present invention)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri to include agent selection of Jaiswal in order to intelligently match capabilities.
With respect to claim 13 Jaiswal further teaches wherein to route the user query to the selected agent for synchronous support, the processing circuity is configured to: select the agent from the set of candidate agents based on the activity status of the agent indicating that the agent is currently available (Jaiswal ¶[0017] When an incoming call is received, the incoming call may be identified by call director 108 based on the type [data product] of call (e.g., a call for technical assistance, a call for billing questions, etc.), the type of caller placing the call (e.g., a premier caller may be provided level-3 support rather than level-1 support), and the like. Once the type of call or the caller is known, the call routing software determines which of call support agents 110-118 [candidate agents] has the necessary skill set to handle the incoming call. For example, if the incoming call is from a non-premier caller who has a basic technical question (i.e., level-1 question), the call routing software identifies that this call may be handled by an agent with a basic skill set, and therefore assigns [selects] the first available [activity status] call support agent in the level-1 group, such as call support agent 110, to the incoming call. It should be noted that while the present invention is described in terms of tiers of support, e.g., level-1 and level-2 support, the present invention is not limited to such. Rather, these designations are only provided for illustration in order to differentiate between human operators rather than to imply any particular limitations of the present invention); and
establish a synchronous live agent session in a chat portal between the first agent and a user from which the user query was received (Jaiswal ¶[0017] When an incoming call is received, the incoming call may be identified by call director 108 based on the type [data product] of call (e.g., a call for technical assistance, a call for billing questions, etc.), the type of caller placing the call (e.g., a premier caller may be provided level-3 support rather than level-1 support), and the like. Once the type of call or the caller is known, the call routing software determines which of call support agents 110-118 [candidate agents] has the necessary skill set to handle the incoming call. For example, if the incoming call is from a non-premier caller who has a basic technical question (i.e., level-1 question), the call routing software identifies that this call may be handled by an agent with a basic skill set, and therefore assigns [selects] the first available [activity status] call support agent in the level-1 group, such as call support agent 110, to the incoming call [establishes a synchronous connection]. It should be noted that while the present invention is described in terms of tiers of support, e.g., level-1 and level-2 support, the present invention is not limited to such. Rather, these designations are only provided for illustration in order to differentiate between human operators rather than to imply any particular limitations of the present invention).
Claim (s) 14 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri, Jaiswal in further view of Dojwa (US 20240354816 A1).
With respect to claim 14 none of Ahmad-Taylor, Zhang, Bonageri and Jaiswal explicitly disclose however Dojwa teaches wherein based on no agent of the set of candidate agents being currently available, automatically generate a support ticket for the user query in an asynchronous ticketing system (Dojwa ¶Claims 1. determining whether another agent is available within a time period and if the another agent is available assigning the chat conversation to a queue; routing to the another agent if the agents are not available; creating a ticket [ticket] if neither the agents nor the another agent is unavailable; [not available] and wherein the definition of incoming chat may be either new for newlycreated conversation or returning for the end users that opens the chat widget to continue the conversation; wherein the step of checking availability further comprises the steps of determining whether at least one of the agents and the another agent are online have a queue of chats below predefined limit and are able to accept incoming chats based on predefined working hours and average efficiency of response.)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of agent selection of Jaiswal to include support ticket of Dojwa in order to track and automate queries and prioritize resolution.
Claim (s) 15 and 16 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri, Jaiswal in further view of Dojwa and Girishankar (US 20180225607 A1).
With respect to claim 15 none of Ahmad-Taylor, Zhang, Bonageri and Jaiswal explicitly disclose however Dojwa teaches the processing circuity is configured to: route a user from which the user query was received to an asynchronous ticketing system for the user to generate a support ticket for the user query (Dojwa ¶[0038]Once the agent from a group or particular agent becomes available (307) the chat is assigned (103). In the case where there is no available agent or a group of agents that the chat conversation may be queued to (304), the embodiment of the invention enables the creation of a ticket [generate a ticket] option (105) that is further assigned to the agent (103) to respond [route to the agent] in an asynchronous manner.);
route the support ticket for the user query to the selected agent via the asynchronous ticketing system (Dojwa ¶[0038]Once the agent from a group or particular agent becomes available (307) the chat is assigned (103). In the case where there is no available agent or a group of agents that the chat conversation may be queued to (304), the embodiment of the invention enables the creation of a ticket [generate a ticket] option (105) that is further assigned to the agent (103) to respond [route to the agent] in an asynchronous manner.)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of agent selection of Jaiswal to include support ticket of Dojwa in order to track and automate queries and prioritize resolution.
None of Ahmad-Taylor, Zhang, Bonageri, Jaiswal and Dojwa explicitly disclose however Girishankar teaches select the agent from the set of candidate agents based on the activity status of the agent indicating that the agent was active during one or more previous days (Girishankar ¶Claim 14. are further configured to select a previously assigned active agent within the agent group for assignment of the incoming message, when the incoming message is identified as an active conversation and is received within a predefined period of time);
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of agent selection of Jaiswal in view of support ticket of Dojwa to include agent selection based on activity of Girishankar in order to maintain context retention for issue resolution.
With respect to claim 16 none of Ahmad-Taylor, Zhang, Bonageri and Jaiswal explicitly disclose however Dojwa teaches the processing circuity is configured to: automatically generate a support ticket for the user query in an asynchronous ticketing system (Dojwa ¶[0038]Once the agent from a group or particular agent becomes available (307) the chat is assigned (103). In the case where there is no available agent or a group of agents that the chat conversation may be queued to (304), the embodiment of the invention enables the creation of a ticket [generate a ticket] option (105) that is further assigned to the agent (103) to respond [route to the agent] in an asynchronous manner.);
route the support ticket for the user query to the selected agent via the asynchronous ticketing system (Dojwa ¶[0038]Once the agent from a group or particular agent becomes available (307) the chat is assigned (103). In the case where there is no available agent or a group of agents that the chat conversation may be queued to (304), the embodiment of the invention enables the creation of a ticket [generate a ticket] option (105) that is further assigned to the agent (103) to respond [route to the agent] in an asynchronous manner.);
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of agent selection of Jaiswal to include support ticket of Dojwa in order to track and automate queries and prioritize resolution.
None of Ahmad-Taylor, Zhang, Bonageri, Jaiswal and Dojwa explicitly disclose however Girishankar teaches select the agent from the set of candidate agents based on the activity status of the agent indicating that the agent was active during one or more previous days (Girishankar ¶Claim 14. are further configured to select a previously assigned active agent within the agent group for assignment of the incoming message, when the incoming message is identified as an active conversation and is received within a predefined period of time);
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of agent selection of Jaiswal in view of support ticket of Dojwa to include agent selection based on activity of Girishankar in order to maintain context retention for issue resolution
Claim (s) 17 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri, Jaiswal in further view of Czachor (US 20170078485 A1).
With respect to claim 17 none of Ahmad-Taylor, Zhang, Bonageri and Jaiswal explicitly disclose however Czachor teaches wherein the processing circuitry is configured to, based on an indication from the selected agent, escalate the user query from the selected agent to a higher knowledge level agent from the set of candidate agents associated with the data product for the one of asynchronous or synchronous support for the user query (Czachor ¶[0003]Correspondingly, the bank would prefer that a more complicated [higher knowledge] matter or a more profitable matter, such as an inquiry for a loan, be handled by a higher-level service representative that is trained to handle such a more complicated matter, and also that is likely trained to effectuate the loan, ¶[0047] In various embodiments of the present innovation, the lower-level agent 54 during the course of the call with the client 50 may decide on his or her own and independently of any trigger point in the script 68 that the call should be escalated to a higher-level agent 58, and based thereon may actuate the escalation [escalate] of the call in an appropriate manner as at 409, such as for example by entering an appropriate command [indication] or selecting an ‘escalate’ button or the like shown on the display 62.)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of agent selection of Jaiswal to include knowledge-based agent selection of Czachor in order for intelligent workload distribution based on skills.
Claim(s) 18 is (are) rejected under 35 U.S.C. 103 as being unpatentable over Ahmad-Taylor, Zhang, Bonageri, Jaiswal in further view of Yamanaka (US 20070206770 A1).
With respect to claim 18 none of Ahmad-Taylor, Zhang, Bonageri and Jaiswal explicitly disclose however, Yamanaka teaches identify a first agent from the set of candidate agents based on a first knowledge level of the first agent (Yamanaka ¶[0007] Supposing that there are three lines, front, middle, and back, then agents having lower skills [first knowledge level] are assigned to the front line, agents having intermediate skills are assigned to the middle line, and agents having higher skills are assigned to the back line. If a task is too difficult for an agent in a lower-level [first agent] line such as the front line or the middle line, that task is transferred to a higher-level line such as the middle line or the back line.¶[0036] Upon receiving a call from a customer, the PBX 20 inquires the ACD 30 to which agent the call is to be sent. The ACD 30 selects an agent in the lower-level line 11 who can answer the call at the soonest timing. If no such agent is available in the lower-level line 11, the ACD 30 selects an agent from the mid-level [second agent] line 12.)
based on the activity status of the first agent indicating that the first agent is not available, selecting a second agent from the set of candidate agents based on a second knowledge level of the second agent and the activity status of the second agent indicating that the second agent is available, wherein the second knowledge level is higher than the first knowledge level(Yamanaka ¶[0007] Supposing that there are three lines, front, middle, and back, then agents having lower skills [first knowledge level] are assigned to the front line, agents having intermediate skills are assigned to the middle line [higher knowledge level], and agents having higher skills are assigned to the back line. If a task is too difficult for an agent in a lower-level [first agent] line such as the front line or the middle line, that task is transferred to a higher-level line such as the middle line or the back line.¶[0036] Upon receiving a call from a customer, the PBX 20 inquires the ACD 30 to which agent the call is to be sent. The ACD 30 selects an agent in the lower-level line 11 who can answer the call at the soonest timing. If no such agent is available in the lower-level line 11, the ACD 30 selects an agent from the mid-level [second agent] line 12.)
It would have been obvious to one of ordinary skill in the art prior to the effective filing date of the invention to modify chatbot of Ahmad-Taylor in view of routing of Zhang in view of indexed database of Bonageri in view of agent selection of Jaiswal to include knowledge-based agent selection of Yamanaka in order for intelligent workload distribution based on skills.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ATHAR N PASHA whose telephone number is (408)918-7675. The examiner can normally be reached Monday-Thursday Alternate Fridays, 7:30-4:30 PT.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Daniel Washburn can be reached on (571)272-5551. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ATHAR N PASHA/Primary Examiner, Art Unit 2657
Prosecution Insights