DETAILED ACTION
Status of the Application
Claims 1-21 have been examined in this application. This communication is the first action on the merits. The information disclosure statement (IDS) submitted on 01/01/2026; was filed with this application. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner
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 .
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
This action is a Non-Final Action on the merits in response to the application filed on 02/27/2024.
Claims 1-21 remain pending in this application.
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 1-10 are directed towards a system, and claims 11-21 are directed towards a method all of which are among the statutory categories of invention.
Step 1: This part of the eligibility analysis evaluates whether the claim falls within any statutory category. See MPEP 2106.03. The claim recites at least one step or act, the claim is to a process, which is one of the statutory categories of invention. (Step 1: YES).
Step 2A, Prong One: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
With respect to claims 1-21, the independent claims (claims 1, 11, and 21) are directed to managing of questions and answers, In independent claim 1, the bolded limitations emphasized below correspond to the abstract ideas of the claimed invention:
Claim 1, A system for generating dynamic questions and answers for a customer of an ecommerce store, the system comprising:
at least one source database storing context information regarding one or more products listed on the ecommerce store;
at least one user interface element supported by the ecommerce store, the user interface element displayable on a graphical user interface on a user device and configured to receive at least one user query and further configured to populate at least one answer to the user query and at least one predicted follow-up question;
at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection;
at least one large language model communicatively coupled to the at least one source database and the at least one server, the at least one large language model being trained using data stored in the at least one source database, the at least one large language model being configured to:
generate an initial set of at least one product-related question using the context information for each of the one or more products listed on the ecommerce store;
receive the at least one user query from the user device, the user query comprising a query for information regarding the product listed on the ecommerce store;
prepare a contextual response to the user query using a pre-configured prompt, the at least one user query, and the information regarding the product stored in the at least one source database;
generate and display the contextual response and the at least one predicted follow-up question.
these steps fall within and recite an abstract ideas because they are directed to a method of organizing human activity which includes commercial interaction includes business relations; managing personal behavior such as social activities and following rules or instructions (See MPEP 2106.04(a)(2), subsection II).
Regarding steps of:
A system for generating dynamic questions and answers for a customer of an ecommerce store, the system comprising:
at least one source database storing context information regarding one or more products listed on the ecommerce store;
at least one user interface element supported by the ecommerce store, the user interface element displayable on a graphical user interface on a user device and configured to receive at least one user query and further configured to populate at least one answer to the user query and at least one predicted follow-up question;
at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection;
at least one large language model communicatively coupled to the at least one source database and the at least one server, the at least one large language model being trained using data stored in the at least one source database, the at least one large language model being configured to:
generate an initial set of at least one product-related question using the context information for each of the one or more products listed on the ecommerce store;
receive the at least one user query from the user device, the user query comprising a query for information regarding the product listed on the ecommerce store;
prepare a contextual response to the user query using a pre-configured prompt, the at least one user query, and the information regarding the product stored in the at least one source database;
generate and display the contextual response and the at least one predicted follow-up question.
If a claim limitation, under its broadest reasonable interpretation, covers commercial interaction and managing personal behavior, then it falls within the “method of organizing human activity” grouping of abstract ideas. Therefore, If the identified limitation(s) falls within any of the groupings of abstract ideas enumerated in the 2019 PEG, the analysis should proceed to Prong Two. (Step 2A, Prong One: YES).
Step 2A, Prong Two: This part of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception into a practical application of the exception or whether the claim is “directed to” the judicial exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. See MPEP 2106.04(d). The claim recites the additional elements of database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network. The claims recite the steps are performed by the database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network.
The limitations of
A system for generating dynamic questions and answers for a customer of an ecommerce store, the system comprising:
at least one source database storing context information regarding one or more products listed on the ecommerce store;
at least one user interface element supported by the ecommerce store, the user interface element displayable on a graphical user interface on a user device and configured to receive at least one user query and further configured to populate at least one answer to the user query and at least one predicted follow-up question;
at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection;
at least one large language model communicatively coupled to the at least one source database and the at least one server, the at least one large language model being trained using data stored in the at least one source database, the at least one large language model being configured to:
generate an initial set of at least one product-related question using the context information for each of the one or more products listed on the ecommerce store;
receive the at least one user query from the user device, the user query comprising a query for information regarding the product listed on the ecommerce store;
prepare a contextual response to the user query using a pre-configured prompt, the at least one user query, and the information regarding the product stored in the at least one source database;
generate and display the contextual response and the at least one predicted follow-up question.
are mere data gathering and output recited at a high level of generality, and thus are insignificant extra-solution activity. See MPEP 2106.05(g) (“whether the limitation is significant”). In addition, all uses of the recited judicial exceptions require such data gathering and output, and, as such, these limitations do not impose any meaningful limits on the claim. These limitations amount to necessary data gathering and outputting. See MPEP 2106.05.
Further, the limitations are recited as being performed by database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network. The database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network are recited at a high level of generality. In limitation (a), the neural network; large language model is used as a tool to perform the generic computer function of receiving data. See MPEP 2106.05(f). the neural network; large language model are used to perform an abstract idea, as discussed above in Step 2A, Prong One, such that it amounts to no more than mere instructions to apply the exception using a generic computer. See MPEP 2106.05(f). Additionally, claim 1 recites the neural network; large language model. The general use of a machine learning technique does not provide a meaningful limitation to transform the abstract idea into a practical application.
Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application (Step 2A, Prong Two: NO), and the claim is directed to the judicial exception. (Step 2A: YES).
Step 2B: This part of the eligibility analysis evaluates whether the claim as a whole amounts to significantly more than the recited exception i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05. As explained with respect to Step 2A, Prong Two, the additional elements are the database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network. The additional elements were found to be insignificant extra-solution activity in Step 2A, Prong Two, because they were determined to be insignificant limitations as necessary data gathering and outputting. Then, the machine learning techniques recited in the claim are disclosed at a high-level of generality (see at least Specification [0034 “the system uses machine learning methods featuring one or more neural networks trained and tuned for precision using information related to contextual information regarding a product.”]) and does not amount to significantly more than the abstract idea.
However, a conclusion that an additional element is insignificant extra solution activity in Step 2A, Prong Two should be re-evaluated in Step 2B. See MPEP 2106.05, subsection I.A. At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well understood, routine, and conventional in the field. See MPEP 2106.05(g). As discussed in Step 2A, Prong Two above, the recitations of
A system for generating dynamic questions and answers for a customer of an ecommerce store, the system comprising:
at least one source database storing context information regarding one or more products listed on the ecommerce store;
at least one user interface element supported by the ecommerce store, the user interface element displayable on a graphical user interface on a user device and configured to receive at least one user query and further configured to populate at least one answer to the user query and at least one predicted follow-up question;
at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection;
at least one large language model communicatively coupled to the at least one source database and the at least one server, the at least one large language model being trained using data stored in the at least one source database, the at least one large language model being configured to:
generate an initial set of at least one product-related question using the context information for each of the one or more products listed on the ecommerce store;
receive the at least one user query from the user device, the user query comprising a query for information regarding the product listed on the ecommerce store;
prepare a contextual response to the user query using a pre-configured prompt, the at least one user query, and the information regarding the product stored in the at least one source database;
generate and display the contextual response and the at least one predicted follow-up question.
are recited at a high level of generality. These elements amount to transmitting data and are well understood, routine, conventional activity. See MPEP 2106.05(d), subsection II. 10 As discussed in Step 2A, Prong Two above, the recitation of a database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network to perform limitations amounts to no more than mere instructions to apply the exception using a generic computer component. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept. (Step 2B: NO).
Dependent claims 2-10, 12-20 do not contain any new additional elements. Rather, these claims offer further descriptive limitations of elements found in the independent claims. In this case, the claims are rejected for the same reasons at step 2a, prong one; step 2a, prong 2; and step 2b. Thus, the claim is not patent eligible.
Regarding the dependent claims, dependent claims 3, 13 recite conversation agent to record customer’s behavior; claims 4, 14 recite large language model to generate responses; claim 5, 15 recite server and retrieval unit to cache and fetch frequently asked questions; claims 6 , 16 recite large language model to collect trained data; claims 8, 18 recite large language model to generate frequently asked questions; claim 10, 20 recite a neural network to receive and process data.. The dependent claims 2-10, 12-20 recite limitations that are not technological in nature and merely limits the abstract idea to a particular environment. Claims 2-10, 12-20 recites database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network which are considered an insignificant extra-solution activities of collecting and analyzing data; see MPEP 2106.05(g). Claims 2-7, 9-14, 16-20 recites database, interface, device, processor, memory, network, model, conservation agent, server, unit, neural network, which merely recites an instruction to apply the abstract idea using a generic computer component; MPEP 2106.05(f). Additionally, claims 2-10, 12-20 recite steps that further narrow the abstract idea. No additional elements are disclosed in the dependent claims that were not considered in independent claims 1, 11, and 21. Therefore claims 2-10, 12-20 do not provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to significantly more than the abstract idea itself.
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 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-21 are rejected under 35 U.S.C. 103 as being unpatentable over United States Patent Publication US 20230106590, Fabbrizio, et al. to hereinafter Fabbrizio in view of United States Patent Publication US 20240354321, Kundel, et al.
Referring to Claim 1, Fabbrizio teaches a system for generating dynamic questions and answers for a customer of an ecommerce store, the system comprising:
at least one source database storing context information regarding one or more products listed on the ecommerce store (
Fabbrizio: Sec. 0006, The query information can be received from a user in an electronic commerce platform. The item catalog can include a listing of the plurality of items, a listing of one or more attributes associated with each item of the plurality of items, and a listing of one or more attribute values associated with each of the one or more attributes. The attribute can include at least one of an item size, an item dimension, an item shape, an item configuration, an item feature, an item availability, an item component, an item ranking, an item capacity, an item usage, and/or an item price.
Fabbrizio: Sec. 0021, The question-answer expansion system can provide query responses for products which may be newly listed in an item catalog or for which a full mapping of attributes and attribute values has not yet been established. Thus, some implementations of the question-answer expansion approach described herein can enable rapid start up and bootstrapping of item attribute data in an e-commerce platform or an item catalog interface.
Fabbrizio: Sec. 0049, The QA processing platform 120 can include a variety of end-user connectors 328 configured to interface the QA processing platform 120 to one or more databases or data sources identifying end-users. );
at least one user interface element supported by the ecommerce store (
Fabbrizio: Sec. 0006, The query information can be received from a user in an electronic commerce platform.
Fabbrizio: Sec. 0022, the applications 106 can include a web browser configured to display a web site that can include a product catalog, a list of items for sale, or a similar electronic commerce platform accessible via the internet.
Fabbrizio: Sec. 0025, A user can interact with the input device 114 to provide query data, such as a question, via a web-site or electronic commerce platform at which the user is enquiring about one or more items or products. For example, the user can provide a query asking “What kind of ice cubes does the Acme SLX2 refrigerator make?”.
Fabbrizio: Sec. 0028, A processing platform 120 can include a first subsystem 130A which can be associated with a first tenant 130A, such as an appliance manufacturer, and a second subsystem 130B which can be associated with a second tenant 130B, such as an ecommerce marketplace hosting a large variety of products from different manufacturers.
Fabbrizio: Sec. 0051, The interface 330 can enable access to the tenant's catalog data which can be accessed via one or more catalog or e-commerce connectors 332.),
the user interface element displayable on a graphical user interface on a user device and configured to receive at least one user query (
Fabbrizio: Sec. 0038, In some embodiments, the applications 106 can implement client APIs on different client devices 102 and web browsers in order to provide responsive multi-modal interactive graphical user interfaces (GUI) that are customized for the entity or tenant. The GUI and applications 106 can be provided based on a profile associated with the tenant or entity. In this way, the QA expansion system 100 can provide customizable branded assets defining the look and feel of a user interface, different product or item catalogs, as well as query responses for products or items which are specific to the tenant or entity associated with the product or item.
Fabbrizio: Sec. 0050, The orchestrator 316 can also provide an interface 330 to tenant catalog data sources. The catalog data sources can include a product catalog or an item catalog including a plurality of products or items for which a user may provide a query in regard to.
Fabbrizio: Sec. 0093, The question-answer expansion system also provides improved interfaces for tenants to customize query dialog interfaces and provide more accurate query dialog responses based on integrated e-commerce data sources such as user account, billing, and customer order data.)
at least one server comprising at least one processor and memory for storing instructions executable on the processor, the at least one server communicatively coupled to the user device over a network connection (
Fabbrizio: Sec. 0026, In certain aspects, the QA processing platform 120 can be configured as one or more servers, which can be located on-premises of an entity deploying the QA expansion system 100, or can be located remotely from the entity. In some implementations, the QA processing platform 120 can be implemented as a distributed architecture or a cloud computing architecture. In some implementations, one or more of the components or functionality included in the QA processing platform 120 can be configured in a microservices architecture. In some implementations, one or more components of the QA processing platform 120 can be provided via a cloud computing server of an infrastructure-as-a-service (IaaS) and be able to support a platform-as-a-service (PaaS) and software-as-a-service (SaaS) services.
Fabbrizio: Sec. 0100, The subject matter described herein can be implemented in a computing system that includes a back-end component (e.g., a data server), a middleware component (e.g., an application server), or a front-end component (e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the subject matter described herein), or any combination of such back-end, middleware, and front-end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), e.g., the Internet.);
generate an initial set of at least one product-related question using the context information for each of the one or more products listed on the ecommerce store (
Fabbrizio: Sec. 0021, user query responses can be generated accurately and more quickly than existing systems, which can require extensive manual configuration of the attribute and attribute value mappings needed to generate query responses in regard to a particular item or product
Fabbrizio: Sec. 0026, The QA processing platform 120 operates to receive query data, such as questions provided to the client device 102 in regard to a particular item or product, and to process the query data to generate responses to the user in regard to the particular item or product that the user was inquiring about.
Fabbrizio: Sec. 0041, The QA processing platform 120 includes run-time components that are responsible for processing incoming speech or text inputs, determining the meaning in the context of a query and a product or item, and generate query responses to the user which are provided as speech and/or text.);
receive the at least one user query from the user device, the user query comprising a query for information regarding the product listed on the ecommerce store (
Fabbrizio: Sec. 0041, The QA processing platform 120 includes run-time components that are responsible for processing incoming speech or text inputs, determining the meaning in the context of a query and a product or item, and generate query responses to the user which are provided as speech and/or text. Additionally, the QA processing platform 120 provides a multi-tenant portal where both administrators and tenants can customize, manage, and monitor platform resources, and can generate run-time reports and analytic data. The QA processing platform 120 interfaces with a number of real-time resources such as ASR engines 140, TTS synthesis engines 155, and telephony platforms described in relation to FIG. 1 . The QA processing platform 120 also provides consistent authentication and access APIs to commercial e-commerce platforms to which it may be coupled via network 118.
Fabbrizio: Sec. 0052, The maestro 334 can dynamically scale these resources as query-response traffic increases. The maestro 334 can deploy new resources without interrupting the processing being performed by existing resources. The maestro 334 can also manage updates to the CTD modules 160 with respect to updates to the tenants e-commerce data, such as updated to item or product catalogs.
Fabbrizio: Sec. 0054, Products or items in an e-commerce catalogs can be typically organized in a multi-level taxonomy, which can group the products into specific categories. The categories can be broader at higher levels (e.g., there are more products) and narrower (e.g., there are less products) at lower levels of the product taxonomy. For example, a product taxonomy associated with clothing can be represented as Clothing>Sweaters>Cardigans & Jackets. The category “Clothing” is quite general, while “Cardigans & Jackets” are a very specific type of clothing. A user's queries can refer to a category (e.g., dresses, pants, skirts, etc.) identified by a taxonomy label or to a specific product item (e.g., item #30018, Boyfriend Cardigan, etc.). In a web-based search or query session, a query could either start from a generic category and narrow down to a specific product or vice versa. CTD module 160 can extract category labels from the catalog taxonomy, product attributes, attribute types, and attribute values, as well as product titles and descriptions.
Fabbrizio: Sec. 0067, Data characterizing user queries is often provided to e-commerce platforms or web sites where a variety of products or items can be described or provided for sale.
Fabbrizio: Sec. 0049, Although subjective and opinion query types are useful to better understand how a product is perceived and used in the marketplace,);
prepare a contextual response to the user query using a pre-configured prompt, the at least one user query, and the information regarding the product stored in the at least one source database (
Fabbrizio: Sec. 0027, The QA processing platform 120 also includes at least one processor 124 configured to execute instructions, which when executed cause the processor 124 to perform expansion of QA data for a plurality of items or products identified in an item catalog and to generate contextually specific query responses to user queries.
Fabbrizio: Sec. 0039, In some implementations, the telephony application 225 can be configured to generate short conversational prompts or dialog sequences without reference to the content of the screen.
Fabbrizio: Sec. 0056, The CTD module 160 utilizes the extracted data to train classification algorithms to automatically categorize catalog data and product attributes included in a natural language query provided by a user. The extracted data can also be used to train a full search engine based on the extracted catalog information. The full search engine can thus include indexes for each product category and attribute. The extracted data can also be used to automatically define a dialog frame structure that will be used by a dialog manger module, described later, to maintain a contextual state of the query response dialog with the user.
Fabbrizio: Sec. 0057, In some implementations, the NLA ensembles 145 can include pre-built automations, which when executed at run-time, implement query response policies for a particular context of a query response dialog with a user. For example, the pre-built automations can include policies associated with searching, frequently-asked-questions (FAQ), customer care or support, order tracking, and small talk or commonly occurring query response dialog sequences which may or may not be contextually relevant to the user's query. );
Fabbrizio does not explicitly teach and further configured to populate at least one answer to the user query and at least one predicted follow-up question; at least one large language model communicatively coupled to the at least one source database and the at least one server, the at least one large language model being trained using data stored in the at least one source database, the at least one large language model being configured to; generate and display the contextual response and the at least one predicted follow-up question.
However, Kundel teaches these limitation.
and further configured to populate at least one answer to the user query and at least one predicted follow-up question (
Kundel: Sec. 0013, to ask one or more follow-up questions aimed to identify the relevant contextual information. This consumes additional computing resources, increases the time needed to obtain a meaningful response, requires the user to expend additional effort to answer such follow-up questions, and may decrease the overall user satisfaction.
Kundel: Sec. 0014, all user data with the query or relying on the user to respond to follow-up questions from the model, a query tool (QT) may obtain contextual information that is pertinent to the query. The query tool may be able to accomplish this without requesting direct user's involvement. In one example embodiment, the QT may receive a user query (e.g., “recommend a restaurant”) and may first generate a first (intermediate) query to the generative model asking for any additional data that the model may need to process the query (e.g., “what information will you need to recommend a restaurant to User?”). The model may process the intermediate query and generate a response to the QT (e.g., “location of User and history of User's restaurant visits”));
Kundel describes the populating of answers and predicting follow-up questions to a query by generating responses.
at least one large language model communicatively coupled to the at least one source database and the at least one server, the at least one large language model being trained using data stored in the at least one source database, the at least one large language model being configured to (
Kundel: Sec. 0021, In some embodiments, data store 110 (database, data warehouse, etc.) may store any suitable raw and/or processed data, e.g., user data 112, and/or metadata associated with one or more users of user machine 140 and/or any other users.
Kundel: Sec. 0036, In some embodiments, the intermediate query is processed by a lightweight GM 215, which may be an NL model, an LLM model, and/or the like. In some embodiments, lightweight GM 215 may be trained using various user queries as training inputs and responses of GM 120 to those queries as ground truth. After lightweight GM 215 has generated a response to the intermediate query, workflow 300 may continue similarly to workflow 200, e.g., QT 101 (or user query analyzer 103) may parse the received response and generate one or more context requests to DM 160 (operation 222).):
generate and display the contextual response and the at least one predicted follow-up question (
Kundel: Sec. 0013, to ask one or more follow-up questions aimed to identify the relevant contextual information. This consumes additional computing resources, increases the time needed to obtain a meaningful response, requires the user to expend additional effort to answer such follow-up questions, and may decrease the overall user satisfaction.
Kundel: Sec. 0014, all user data with the query or relying on the user to respond to follow-up questions from the model, a query tool (QT) may obtain contextual information that is pertinent to the query. The query tool may be able to accomplish this without requesting direct user's involvement. In one example embodiment, the QT may receive a user query (e.g., “recommend a restaurant”) and may first generate a first (intermediate) query to the generative model asking for any additional data that the model may need to process the query (e.g., “what information will you need to recommend a restaurant to User?”). The model may process the intermediate query and generate a response to the QT (e.g., “location of User and history of User's restaurant visits”));
Fabbrizio and Kundel are both directed to the analysis of ecommerce data (See Fabbrizio at 0021, 0022, 0024, 0028; Kundel at 0003). Fabbrizio discloses that additional elements, such as the predictive modeling can be considered (See Fabbrizio at 0005). It would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Fabbrizio, which teaches detecting and repairing information technology problems in view of Kundel, to efficiently apply analysis of ecommerce data to enhancing the capability to modify and train the large language model. (See Kundel at 5 and 6).
Referring to Claim 2, Fabbrizio teaches the system of claim 1, the at least one user query being submitted as any one of:
a clickable link having the text of the at least one product-related question, and a plain text query generated by the user (
Fabbrizio: Sec. 0039, the dynamic content can include clickable and multimodal interactive components and data.
Fabbrizio: Sec. 0053, The QA processing platform 120 further includes a CTD module 160. The CTD module 160 can implement methods to collect e-commerce data from item or product catalogs, product reviews, user account and order data, and user clickstream data collected at the tenants web site to generate a data structure that can be used to learn specific domain knowledge and to onboard or bootstrap a newly configured QA expansion system 100).
Referring to Claim 3, Fabbrizio teaches the system of claim 1, Fabbrizio does not explicitly teach further comprising a conversation agent configured to record a customer’s browse behavior on an ecommerce store and an identifier of the customer.
However, Kundel teaches these further comprising a conversation agent configured to record a customer’s browse behavior on an ecommerce store (See Fabbrizio) and an identifier of the customer (
Kundel: Sec. 0021, user data 112 may include (for a particular user) a user identification, a user profile (e.g., address, preferences, settings, traits, etc.), history of user queries, browsing history, and/or any other information associated with the user.
Kundel: Sec. 0022, the DM-supported software may be a code snippet integrated into user's browsers/apps and/or websites visited by the user. Generating, tracking, and transmitting data may be facilitated by one or more libraries of DM 160.
Kundel: Sec. 0031, the context data request(s) may include a request for the school that user 210 is currently attending, dates and destinations of user's trips over the last two years, costs of those trips, browsing history of user 210, travel destinations researched by user 210 over the last 6 months, and/or the like.).
Fabbrizio and Kundel are both directed to the analysis of ecommerce data (See Fabbrizio at 0021, 0022, 0024, 0028; Kundel at 0003). Fabbrizio discloses that additional elements, such as the predictive modeling can be considered (See Fabbrizio at 0005). It would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Fabbrizio, which teaches detecting and repairing information technology problems in view of Kundel, to efficiently apply analysis of ecommerce data to enhancing the capability to modify and train the large language model. (See Kundel at 5 and 6).
Referring to Claim 4, Fabbrizio teaches the system of claim 3, Fabbrizio does not explicitly teach the large language model further configured to generate the contextual response to the at least one user query and the follow-up question based on the customer’s browse behavior and the identifier as recorded by the conversation agent.
However, Kundel teaches these the large language model further configured to generate the contextual response to the at least one user query and the follow-up question based on the customer’s browse behavior and the identifier as recorded by the conversation agent (
Kundel: Sec. 0013, to ask one or more follow-up questions aimed to identify the relevant contextual information. This consumes additional computing resources, increases the time needed to obtain a meaningful response, requires the user to expend additional effort to answer such follow-up questions, and may decrease the overall user satisfaction.
Kundel: Sec. 0014, all user data with the query or relying on the user to respond to follow-up questions from the model, a query tool (QT) may obtain contextual information that is pertinent to the query. The query tool may be able to accomplish this without requesting direct user's involvement. In one example embodiment, the QT may receive a user query (e.g., “recommend a restaurant”) and may first generate a first (intermediate) query to the generative model asking for any additional data that the model may need to process the query (e.g., “what information will you need to recommend a restaurant to User?”). The model may process the intermediate query and generate a response to the QT (e.g., “location of User and history of User's restaurant visits”));
Kundel: Sec. 0021, user data 112 may include (for a particular user) a user identification, a user profile (e.g., address, preferences, settings, traits, etc.), history of user queries, browsing history, and/or any other information associated with the user.
Kundel: Sec. 0022, the DM-supported software may be a code snippet integrated into user's browsers/apps and/or websites visited by the user. Generating, tracking, and transmitting data may be facilitated by one or more libraries of DM 160.
Kundel: Sec. 0031, the context data request(s) may include a request for the school that user 210 is currently attending, dates and destinations of user's trips over the last two years, costs of those trips, browsing history of user 210, travel destinations researched by user 210 over the last 6 months, and/or the like.).
Fabbrizio and Kundel are both directed to the analysis of ecommerce data (See Fabbrizio at 0021, 0022, 0024, 0028; Kundel at 0003). Fabbrizio discloses that additional elements, such as the predictive modeling can be considered (See Fabbrizio at 0005). It would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Fabbrizio, which teaches detecting and repairing information technology problems in view of Kundel, to efficiently apply analysis of ecommerce data to enhancing the capability to modify and train the large language model. (See Kundel at 5 and 6).
Referring to Claim 5, Fabbrizio teaches the system of claim 1, further comprising:
a caching means communicatively coupled to the server, the caching means configured to cache frequently asked questions and question-answer pairs (
Fabbrizio: Sec. 0002, The determining can be performed using a predictive model trained using question-answer pair data associated with a portion of the plurality of items.
Fabbrizio: Sec. 0057, implement query response policies for a particular context of a query response dialog with a user. For example, the pre-built automations can include policies associated with searching, frequently-asked-questions (FAQ), customer care or support, order tracking, and small talk or commonly occurring query response dialog sequences which may or may not be contextually relevant to the user's query.
Fabbrizio: Sec. 0060, The NLU module 336 can include competing models which can predict the same labels but using different algorithms and domain models where each model produces different labels (customer care inquires, search queries, FAQ, etc.).);
a retrieval unit configured to fetch cached (See Kundel) answers for the frequently asked questions and the question-answer pairs and display them without invoking the large language model (
Fabbrizio: Sec. 0003, The query type can be determined based on at least one of a clustering similarity metric, a text classification similarity metric, or retrieved information.
Fabbrizio: Sec. 0057, implement query response policies for a particular context of a query response dialog with a user. For example, the pre-built automations can include policies associated with searching, frequently-asked-questions (FAQ), customer care or support, order tracking, and small talk or commonly occurring query response dialog sequences which may or may not be contextually relevant to the user's query.
Fabbrizio: Sec. 0060, The NLU module 336 can include competing models which can predict the same labels but using different algorithms and domain models where each model produces different labels (customer care inquires, search queries, FAQ, etc.).
Fabbrizio: Sec. 0074, The query type can be determined based on a clustering similarity metric, a text classification similarity metric, or comparison with stored or retrieved information. The stored or retrieved information can include product specific information and attribute data which may be included in product marketing or sales data, a product specification data sheet, or a comparison document comparing the product to one or more similar products in the same product category or the like.
Fabbrizio: Sec. 0080, the attribute value can be determined based on retrieved or stored information corresponding to the attribute. The stored or retrieved information can include product specific information and attribute data which may be included in product marketing or sales data, a product specification data sheet, or a comparison document comparing the product to one or more similar products in the same product category or the like.).
Fabbrizio does not explicitly teach a caching means communicatively coupled to the server, the caching means configured to cache.
However, Kundel teaches these a caching means communicatively coupled to the server, the caching means configured to cache. (
Kundel: Sec. 0054, While the computer-readable storage medium 624 is shown in the illustrative examples to be a single medium, the term “computer-readable storage medium” should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more sets of instructions. )
Fabbrizio and Kundel are both directed to the analysis of ecommerce data (See Fabbrizio at 0021, 0022, 0024, 0028; Kundel at 0003). Fabbrizio discloses that additional elements, such as the predictive modeling can be considered (See Fabbrizio at 0005). It would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Fabbrizio, which teaches detecting and repairing information technology problems in view of Kundel, to efficiently apply analysis of ecommerce data to enhancing the capability to modify and train the large language model. (See Kundel at 5 and 6).
Referring to Claim 6, Fabbrizio teaches the system of claim 1, the configuring of the large language model including training the large language model, at least in part, by:
collecting training data comprising one or more of:
product details posted on a page on the ecommerce store, including but not limited to the product page itself (
Fabbrizio: Sec. 0005, Training the predictive model can include clustering the question-answer pair data associated with the plurality of items in the item catalog. The question-answer pair data can include a first data element characterizing a query by a user for information associated with an item and a second data element characterizing a natural language answer to the query.
Fabbrizio: Sec. 0086, When a full entity tagger is trained in this manner, it can recognize and tag entities for instances in which the entity has not been observed before in the training data. The product catalog 620 can be used to train the predictive model.);
articles, blogs, and content available online regarding the product; purchasing guides with information regarding specifications, such as sizing, dimensions, and customization options (
Fabbrizio: Sec. 0006, The attribute can include at least one of an item size, an item dimension, an item shape, an item configuration, an item feature, an item availability, an item component, an item ranking, an item capacity, an item usage, and/or an item price.
Fabbrizio: Sec. 0050, An attribute of a product or item can be a feature, a component, a product or item size, a product or item dimension, a product or item shape, a product or item configuration, a product or item feature, a product or item availability, a product or item ranking, a product or item capacity, a product or item usage, and/or a product or item price. An attribute value can identify the attribute. );
product image information (
Fabbrizio: Sec. 0051, data from one or more sources of catalog data can be ingested into the CTD modules 160 to populate the modules with product or item names, descriptions, brands, images, colors, swatches, as well as structured and free-form item or product attributes and corresponding attribute values.);
customer reviews and feedback, including written reviews and ratings (
Fabbrizio: Sec. 0053, The QA processing platform 120 further includes a CTD module 160. The CTD module 160 can implement methods to collect e-commerce data from item or product catalogs, product reviews, user account and order data, and user clickstream data collected at the tenants web site to generate a data structure that can be used to learn specific domain knowledge and to onboard or bootstrap a newly configured QA expansion system 100.
Fabbrizio: Sec. 0065, the data characterizing the query may be received in regard to a product review or a user inquiring about one or more aspects of a particular product available in the product catalog and/or via a product web site.);
customer-posted questions and answers to the customer-posted questions from other customers or from online sellers (
Fabbrizio: Sec. 0067, Data characterizing user queries is often provided to e-commerce platforms or web sites where a variety of products or items can be described or provided for sale. E-commerce websites are typically capable of capturing query data in the form of product questions, such as community or product question answering (PQA) data, that can be posted on the specific product description page and answered by product experts, e-commerce brand ambassadors, or other customers with experience with the actual product usage.);
processing the training data to create training prompts simulating real-world scenarios where a hypothetical customer seeks product-related information based on the hypothetical customer’s history and context (
Fabbrizio: Sec. 0077, In some embodiments, a subjective query type can include a question that may include reference to a hypothetical situation or a personal usage of the product or item. );
training the large language model using the training prompts to predict most likely questions the hypothetical customer might have about a product (
Fabbrizio: Sec. 0059, The NLU module 336 can combine different classification algorithms and can select the classification algorithm most likely to provide the best semantic interpretation for a particular user query by determining context of the query response dialog and integrating past query response dialog histories.
Fabbrizio: Sec. 0005, Training the predictive model can also include determining at least one centroid question based on the clustering and categorizing the question-answer pair data base don the clustering. Training the predictive model can further include removing at least one outlier from the categorized question-answer pair data. Training the predictive model can also include associating an attribute with each question-answer pair included in the question-answer pair data.
Fabbrizio: Sec. 0020, A predictive model can be trained using question-answer pair data associated with items in an item catalog to determine the topic of the query and to generate a query response. The query response can be provided to a user in a natural language format.);
refining the large language model’s (See Kundel) predictions using feedback received from actual customer interactions on the ecommerce store (
Fabbrizio: Sec. 0020, A predictive model can be trained using question-answer pair data associated with items in an item catalog to determine the topic of the query and to generate a query response. The query response can be provided to a user in a natural language format.
Fabbrizio: Sec. 0053, The QA processing platform 120 further includes a CTD module 160. The CTD module 160 can implement methods to collect e-commerce data from item or product catalogs, product reviews, user account and order data, and user clickstream data collected at the tenants web site to generate a data structure that can be used to learn specific domain knowledge and to onboard or bootstrap a newly configured QA expansion system 100.
Fabbrizio: Sec. 0098, feedback provided to the user can be any form of sensory feedback, (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user can be received in any form, including acoustic, speech, or tactile input.).
Fabbrizio does not explicitly teach large language model’s.
However, Kundel teaches these large language model’s (
Kundel: Sec. 0043, if the first NL generative model is lightweight GM 215, the second NL generative model may be GM 120 (or vice versa). In some embodiments, the first NL generative model and/or the second NL generative model may be or include a large language model (LLM).)
Fabbrizio and Kundel are both directed to the analysis of ecommerce data (See Fabbrizio at 0021, 0022, 0024, 0028; Kundel at 0003). Fabbrizio discloses that additional elements, such as the predictive modeling can be considered (See Fabbrizio at 0005). It would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Fabbrizio, which teaches detecting and repairing information technology problems in view of Kundel, to efficiently apply analysis of ecommerce data to enhancing the capability to modify and train the large language model. (See Kundel at 5 and 6).
Referring to Claim 7, Fabbrizio teaches the system of claim 6, the training data further comprising Fabbrizio does not explicitly teach customer browse behavior, customer context information, and customer queries related to one or more of the products.
However, Kundel teaches these customer browse behavior, customer context information, and customer queries related to one or more of the products (
Kundel: Sec. 0021, user data 112 may include (for a particular user) a user identification, a user profile (e.g., address, preferences, settings, traits, etc.), history of user queries, browsing history, and/or any other information associated with the user.
Kundel: Sec. 0022, the DM-supported software may be a code snippet integrated into user's browsers/apps and/or websites visited by the user. Generating, tracking, and transmitting data may be facilitated by one or more libraries of DM 160.
Kundel: Sec. 0031, the context data request(s) may include a request for the school that user 210 is currently attending, dates and destinations of user's trips over the last two years, costs of those trips, browsing history of user 210, travel destinations researched by user 210 over the last 6 months, and/or the like.).
Fabbrizio and Kundel are both directed to the analysis of ecommerce data (See Fabbrizio at 0021, 0022, 0024, 0028; Kundel at 0003). Fabbrizio discloses that additional elements, such as the predictive modeling can be considered (See Fabbrizio at 0005). It would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Fabbrizio, which teaches detecting and repairing information technology problems in view of Kundel, to efficiently apply analysis of ecommerce data to enhancing the capability to modify and train the large language model. (See Kundel at 5 and 6).
Referring to Claim 8, Fabbrizio teaches the system of claim 1, the large language model further configured to generate a plurality of frequently asked questions and a subset within the plurality of the frequently asked questions, the subset to be displayed within the user interface element (
Fabbrizio: Sec. 0057, implement query response policies for a particular context of a query response dialog with a user. For example, the pre-built automations can include policies associated with searching, frequently-asked-questions (FAQ), customer care or support, order tracking, and small talk or commonly occurring query response dialog sequences which may or may not be contextually relevant to the user's query.
Fabbrizio: Sec. 0060, The NLU module 336 can include competing models which can predict the same labels but using different algorithms and domain models where each model produces different labels (customer care inquires, search queries, FAQ, etc.).).
Referring to Claim 9, Fabbrizio teaches the system of claim 8, further comprising a scoring means for determining an optimal set of questions to feature as the subset within the plurality of frequently asked questions, the determination being based at least in part on input comprising at least one of:
sales trends, browse rate, click rate, browse-to-purchase ratio, and click-to-purchase ratio (
Fabbrizio: Sec. 0046, The tenant portal 320 can allow customers or tenants of the QA expansion system 100 to configure reporting and analytic data, such as account management, customized reports and graphical data analysis, trend aggregation and analysis, as well as drill-down data associated product or item queries provided by a user.
Fabbrizio: Sec. 0074, The stored or retrieved information can include product specific information and attribute data which may be included in product marketing or sales data, a product specification data sheet, or a comparison document comparing the product to one or more similar products in the same product category or the like.).
Referring to Claim 10, Fabbrizio teaches the system of claim 9, the scoring means comprising a deep neural network configured to receive the input at a first input layer (
Fabbrizio: Sec. 0036, The machine learning platform 165 can include a number of components configured to generate one or more trained prediction models suitable for use in the QA expansion system 100 described in relation to FIG. 1 . For example, during a machine learning process, a feature selector can provide a selected subset of features to a model trainer as inputs to a machine learning algorithm to generate one or more training models. A wide variety of machine learning algorithms can be selected for use including algorithms such as support vector regression, ordinary least squares regression (OLSR), linear regression, logistic regression, stepwise regression, multivariate adaptive regression splines (MARS), locally estimated scatterplot smoothing (LOESS), ordinal regression, Poisson regression, fast forest quantile regression, Bayesian linear regression, neural network regression, decision forest regression, boosted decision tree regression, artificial neural networks (ANN), deep neural networks (DNN));
process the input by one or more hidden layers; generate a first output; transmit the first output to an output layer (
Fabbrizio: Sec. 0088, The BERT model can pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications.);
generate a first outcome comprising the determining of the optimal set of questions (
Fabbrizio: Sec. 0062, The DM module 338 can receive semantic interpretations generated by the NLU module 336 and can generate a query response dialog response action using context interpreter, a dialog state tracker, a database of dialog history, and an ensemble of dialog action policies. The ensemble of dialog action policies can be refined and optimized using rules, frames and one or more machine learning techniques.
Fabbrizio: Sec. 0085, In some embodiments, the QA pair data can be cleaned after classifying to remove spam questions, or unrelated questions from the original set of QA pair data).
Referring to Claim 11, Fabbrizio teaches a method for generating dynamic questions and answers for a customer of an ecommerce store, the method comprising:
training a large language model (See Kundel) using context information stored in at least one source database, the information pertaining to one or more products listed by the ecommerce store (
Fabbrizio: Sec. 0006, The query information can be received from a user in an electronic commerce platform. The item catalog can include a listing of the plurality of items, a listing of one or more attributes associated with each item of the plurality of items, and a listing of one or more attribute values associated with each of the one or more attributes. The attribute can include at least one of an item size, an item dimension, an item shape, an item configuration, an item feature, an item availability, an item component, an item ranking, an item capacity, an item usage, and/or an item price.
Fabbrizio: Sec. 0021, The question-answer expansion system can provide query responses for products which may be newly listed in an item catalog or for which a full mapping of attributes and attribute values has not yet been established. Thus, some implementations of the question-answer expansion approach described herein can enable rapid start up and bootstrapping of item attribute data in an e-commerce platform or an item catalog interface.
Fabbrizio: Sec. 0022, the applications 106 can include a web browser configured to display a web site that can include a product catalog, a list of items for sale, or a similar electronic commerce platform accessible via the internet.
Fabbrizio: Sec. 0025, A user can interact with the input device 114 to provide query data, such as a question, via a web-site or electronic commerce platform at which the user is enquiring about one or more items or products. For example, the user can provide a query asking “What kind of ice cubes does the Acme SLX2 refrigerator make?”.
Fabbrizio: Sec. 0049, The QA processing platform 120 can include a variety of end-user connectors 328 configured to interface the QA processing platform 120 to one or more databases or data sources identifying end-users. );
preparing a pre-configured prompt for a context-appropriate response to at least one user query by the large language model (See Kundel) (
Fabbrizio: Sec. 0027, The QA processing platform 120 also includes at least one processor 124 configured to execute instructions, which when executed cause the processor 124 to perform expansion of QA data for a plurality of items or products identified in an item catalog and to generate contextually specific query responses to user queries.
Fabbrizio: Sec. 0039, In some implementations, the telephony application 225 can be configured to generate short conversational prompts or dialog sequences without reference to the content of the screen.
Fabbrizio: Sec. 0056, The CTD module 160 utilizes the extracted data to train classification algorithms to automatically categorize catalog data and product attributes included in a natural language query provided by a user. The extracted data can also be used to train a full search engine based on the extracted catalog information. The full search engine can thus include indexes for each product category and attribute. The extracted data can also be used to automatically define a dialog frame structure that will be used by a dialog manger module, described later, to maintain a contextual state of the query response dialog with the user.
Fabbrizio: Sec. 0057, In some implementations, the NLA ensembles 145 can include pre-built automations, which when executed at run-time, implement query response policies for a particular context of a query response dialog with a user. For example, the pre-built automations can include policies associated with searching, frequently-asked-questions (FAQ), customer care or support, order tracking, and small talk or commonly occurring query response dialog sequences which may or may not be contextually relevant to the user's query. );
generating an initial set of at least one product-related question using the context information for each of the one or more products listed on the ecommerce store (
Fabbrizio: Sec. 0021, user query responses can be generated accurately and more quickly than existing systems, which can require extensive manual configuration of the attribute and attribute value mappings needed to generate query responses in regard to a particular item or product
Fabbrizio: Sec. 0026, The QA processing platform 120 operates to receive query data, such as questions provided to the client device 102 in regard to a particular item or product, and to process the query data to generate responses to the user in regard to the particular item or product that the user was inquiring about.
Fabbrizio: Sec. 0041, The QA processing platform 120 includes run-time components that are responsible for processing incoming speech or text inputs, determining the meaning in the context of a query and a product or item, and generate query responses to the user which are provided as speech and/or text.);
receiving at least one user query regarding at least one of the one or more products, the at least one query being submitted by a user interface element supported by the ecommerce store (
Fabbrizio: Sec. 0041, The QA processing platform 120 includes run-time components that are responsible for processing incoming speech or text inputs, determining the meaning in the context of a query and a product or item, and generate query responses to the user which are provided as speech and/or text. Additionally, the QA processing platform 120 provides a multi-tenant portal where both administrators and tenants can customize, manage, and monitor platform resources, and can generate run-time reports and analytic data. The QA processing platform 120 interfaces with a number of real-time resources such as ASR engines 140, TTS synthesis engines 155, and telephony platforms described in relation to FIG. 1 . The QA processing platform 120 also provides consistent authentication and access APIs to commercial e-commerce platforms to which it may be coupled via network 118.
Fabbrizio: Sec. 0052, The maestro 334 can dynamically scale these resources as query-response traffic increases. The maestro 334 can deploy new resources without interrupting the processing being performed by existing resources. The maestro 334 can also manage updates to the CTD modules 160 with respect to updates to the tenants e-commerce data, such as updated to item or product catalogs.
Fabbrizio: Sec. 0054, Products or items in an e-commerce catalogs can be typically organized in a multi-level taxonomy, which can group the products into specific categories. The categories can be broader at higher levels (e.g., there are more products) and narrower (e.g., there are less products) at lower levels of the product taxonomy. For example, a product taxonomy associated with clothing can be represented as Clothing>Sweaters>Cardigans & Jackets. The category “Clothing” is quite general, while “Cardigans & Jackets” are a very specific type of clothing. A user's queries can refer to a category (e.g., dresses, pants, skirts, etc.) identified by a taxonomy label or to a specific product item (e.g., item #30018, Boyfriend Cardigan, etc.). In a web-based search or query session, a query could either start from a generic category and narrow down to a specific product or vice versa. CTD module 160 can extract category labels from the catalog taxonomy, product attributes, attribute types, and attribute values, as well as product titles and descriptions.
Fabbrizio: Sec. 0067, Data characterizing user queries is often provided to e-commerce platforms or web sites where a variety of products or items can be described or provided for sale.
Fabbrizio: Sec. 0049, Although subjective and opinion query types are useful to better understand how a product is perceived and used in the marketplace,),
the user interface element displayed on a user device communicatively coupled with the large language model (See Kundel) by way of at least one server (
Fabbrizio: Sec. 0038, In some embodiments, the applications 106 can implement client APIs on different client devices 102 and web browsers in order to provide responsive multi-modal interactive graphical user interfaces (GUI) that are customized for the entity or tenant. The GUI and applications 106 can be provided based on a profile associated with the tenant or entity. In this way, the QA expansion system 100 can provide customizable branded assets defining the look and feel of a user interface, different product or item catalogs, as well as query responses for products or items which are specific to the tenant or entity associated with the product or item.
Fabbrizio: Sec. 0050, The orchestrator 316 can also provide an interface 330 to tenant catalog data sources. The catalog data sources can include a product catalog or an item catalog including a plurality of products or items for which a user may provide a query in regard to.
Fabbrizio: Sec. 0093, The question-answer expansion system also provides improved interfaces for tenants to customize query dialog interfaces and provide more accurate query dialog responses based on integrated e-commerce data sources such as user account, billing, and customer order data.);
preparing, by the large language model (See Kundel), a contextual response to the at least one user query using the pre-configured prompt and the information regarding the product stored in the at least one source database (
Fabbrizio: Sec. 0027, The QA processing platform 120 also includes at least one processor 124 configured to execute instructions, which when executed cause the processor 124 to perform expansion of QA data for a plurality of items or products identified in an item catalog and to generate contextually specific query responses to user queries.
Fabbrizio: Sec. 0039, In some implementations, the telephony application 225 can be configured to generate short conversational prompts or dialog sequences without reference to the content of the screen.
Fabbrizio: Sec. 0056, The CTD module 160 utilizes the extracted data to train classification algorithms to automatically categorize catalog data and product attributes included in a natural language query provided by a user. The extracted data can also be used to train a full search engine based on the extracted catalog information. The full search engine can thus include indexes for each product category and attribute. The extracted data can also be used to automatically define a dialog frame structure that will be used by a dialog manger module, described later, to maintain a contextual state of the query response dialog with the user.
Fabbrizio: Sec. 0057, In some implementations, the NLA ensembles 145 can include pre-built automations, which when executed at run-time, implement query response policies for a particular context of a query response dialog with a user. For example, the pre-built automations can include policies associated with searching, frequently-asked-questions (FAQ), customer care or support, order tracking, and small talk or commonly occurring query response dialog sequences which may or may not be contextually relevant to the user's query. );
Fabbrizio does not explicitly teach the user interface element configured to receive the at least one user query and to populate an answer to the at least one user query and at least one follow-up question; training a large language model; generating, by the large language model, the answer to the user query and the at least one follow-up question.
However, Kundel teaches these limitations
the user interface element configured to receive the at least one user query and to populate an answer to the at least one user query and at least one follow-up question (
Kundel: Sec. 0013, to ask one or more follow-up questions aimed to identify the relevant contextual information. This consumes additional computing resources, increases the time needed to obtain a meaningful response, requires the user to expend additional effort to answer such follow-up questions, and may decrease the overall user satisfaction.
Kundel: Sec. 0014, all user data with the query or relying on the user to respond to follow-up questions from the model, a query tool (QT) may obtain contextual information that is pertinent to the query. The query tool may be able to accomplish this without requesting direct user's involvement. In one example embodiment, the QT may receive a user query (e.g., “recommend a restaurant”) and may first generate a first (intermediate) query to the generative model asking for any additional data that the model may need to process the query (e.g., “what information will you need to recommend a restaurant to User?”). The model may process the intermediate query and generate a response to the QT (e.g., “location of User and history of User's restaurant visits”)),
Kundel describes the populating of answers and predicting follow-up questions to a query by generating responses.
training a large language model (
Kundel: Sec. 0036, the intermediate query is processed by a lightweight GM 215, which may be an NL model, an LLM model, and/or the like. In some embodiments, lightweight GM 215 may be trained using various user queries as training inputs and responses of GM 120 to those queries as ground truth.
Kundel: Sec. 0043, if the first NL generative model is lightweight GM 215, the second NL generative model may be GM 120 (or vice versa). In some embodiments, the first NL generative model and/or the second NL generative model may be or include a large language model (LLM).)
generating, by the large language model (See Kundel), the answer to the user query and the at least one follow-up question (
Kundel: Sec. 0013, to ask one or more follow-up questions aimed to identify the relevant contextual information. This consumes additional computing resources, increases the time needed to obtain a meaningful response, requires the user to expend additional effort to answer such follow-up questions, and may decrease the overall user satisfaction.
Kundel: Sec. 0014, all user data with the query or relying on the user to respond to follow-up questions from the model, a query tool (QT) may obtain contextual information that is pertinent to the query. The query tool may be able to accomplish this without requesting direct user's involvement. In one example embodiment, the QT may receive a user query (e.g., “recommend a restaurant”) and may first generate a first (intermediate) query to the generative model asking for any additional data that the model may need to process the query (e.g., “what information will you need to recommend a restaurant to User?”). The model may process the intermediate query and generate a response to the QT (e.g., “location of User and history of User's restaurant visits”)).
Fabbrizio and Kundel are both directed to the analysis of ecommerce data (See Fabbrizio at 0021, 0022, 0024, 0028; Kundel at 0003). Fabbrizio discloses that additional elements, such as the predictive modeling can be considered (See Fabbrizio at 0005). It would have been obvious for one having ordinary skill in the art before the effective filing date of the claimed invention to have modified Fabbrizio, which teaches detecting and repairing information technology problems in view of Kundel, to efficiently apply analysis of ecommerce data to enhancing the capability to modify and train the large language model. (See Kundel at 5 and 6).
Claims 12-21 recite limitations that stand rejected via the art citations and rationale applied to claims 2-11. Regarding displaying dynamic questions and answers (
Fabbrizio: Fig. 1,
Fabbrizio: Sec. 0032, The NLG module can process the action response determined by the dialog manager and can convert the action response into a corresponding textual response to be provided to the user as a query response. The NLG module provides multimodal support for generating textual responses to user queries for a variety of different output device modalities, such as voice outputs or visually displayed (e.g., textual) outputs. In some implementations, the ensemble can include a set of models that are included in the NLU and optimized jointly to select the right response.
Fabbrizio: Sec. 0034, the QA processing platform 120 can process the users query to determine a response regarding the type of ice cubes made by the Acme SLX2 refrigerator. As a result of the processing initially described above and to be described in more detail in relation to FIG. 3 , the QA processing platform 120 can generate a response to the user's query. The query response can be transmitted to the client device 102 and provided as speech output via output device 116 and/or provided as text displayed via display 112.):
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Bowman-Amuah., U.S. Patent. 6697824, (discussing the personalizing a website to include an e-commerce ).
Gruber et al., J.P. Pub. JP7498402B2, (discussing the engagement of users in a ecommerce environment.).
Mekkawi., The implications of AI in E-commerce, https://ijlso.ccdsara.ro/international-journal-of-legal-a/article/download/201/164, Int'l J. Legal & Soc. Ord., 2024 (discussing the integration of artificial intelligence with e-commerce).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to UCHE BYRD whose telephone number is (571)272-3113. The examiner can normally be reached Mon.-Fri..
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, Patricia Munson can be reached at (571) 270-5396. 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.
UCHE BYRD
Examiner
Art Unit 3624
/UCHE BYRD/Examiner, Art Unit 3624