DETAILED ACTION
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 § 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.
Claim(s) 1-16 and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Maschmeyer et al. (US Patent Application Publication 2024/0256792) in view of Duan et al. (“Query-Variant Adverstisement Text Generation with Association Knowledge) and further in view of Bendersky et al. (US Patent Application Publication 2024/0403564) .
Regarding claim 1, Maschmeyer discloses a method, comprising: receiving data indicating a first query received from a client device of a user [see para. 0007, 0009; retrieve a user record for a user associated with the request; obtain one or more user attributes based on the user record; generate a prompt to a large language model (LLM) for generating a user-specific textual description, the prompt including the one or more user attributes to include in the generated user-specific textual description and a source text; provide the prompt to the LLM and receive a generated user-specific textual description; and provide the generated user-specific textual description for display via a user device; which corresponds to the request process of generating personalized text];
obtaining an initial digital component (i) comprising a link to a first resource and (ii) depicting initial text related to the first resource [see para. 0146; providing a personalized textual description to a user device takes place during runtime on the user device, the data for a webpage (e.g., a product webpage) that is stored on the system includes the source text, when a user requests to view a webpage, the system retrieves the user record(s) and generates the personalized textual description, and provides a modified webpage including the substituted personalized textual description in real-time, in response to the request, in providing the modified webpage to the user, no permanent changes are made to the source text stored on the system; which corresponds to an advertisement or product description on a webpage with a digital component comprising a link and initial text] ;
obtaining search history data comprising a set of related past queries received from the user [see para. 0078, 0081; an optional user profiles database storing a user record(s) (e.g., user profile data) about a plurality of users or classes of users the user profiles database include, for each user or cohort, data about one or more user attributes (e.g., characteristics, preferences and/or needs associated with the user or cohort), personal information, purchase history, review history, viewing history, question history and search history, among other data. User attributes for a given user or class of users stored in a lookup table that referenced using a unique identifier (e.g., a code, an identification number, an email address or other reference identifying the user; which corresponds to user profile stated in the description of user attributes extracted from the user record the queries form search history data];
generating updated text related to the first resource by conditioning a language model with one or more contextual inputs (ii) data related to the initial digital component, or (iv) one or more tasks to be performed by the language model [see para. 0084-0089; the prompt generated by the prompt generator includes instructions to the LLM to include one or more user attributes in the generated textual description so that the generated textual description is a personalized textual description that is customized to the user. Optionally, the platform may, for example, also obtain a set of object attributes (which may be explicitly inputted by the user or may be automatically extracted from a database (e.g., the object database)) for inclusion in the prompt and obtained from a user record(s) related to past commerce events or transactions (e.g., historic purchases, past browsing history etc.) or past search events (e.g., search query, browser activity, ads clicked on etc.) over an unrestricted or extended timeframe; which corresponds to generate a prompt to a large language model that includes user attributes which can include previous search queries and the contextual inputs characterizing data related to the initial component and user history] ; generating an updated digital component that depicts the updated text [see para. 0014-0015; wherein the request is a request received from a user device to view a webpage associated with an object, and wherein the processing unit is configured to execute computer-readable instructions to further cause the system to: in response to the request, provide a modified webpage for display via the user device, the modified webpage including the user-specific textual description; wherein data for the webpage stored on the system includes the source text, and wherein the modified webpage provided to the user device has the user-specific textual description substituted in real-time in response to the request; which corresponds to create an updated digital component modified webpage or product description]; and providing, for display at the client device, the updated digital component depicting the updated text related to the first resource [see para. 0146; providing a personalized textual description to a user device takes place during runtime on the user device. The data for a webpage (e.g., a product webpage) that is stored on the system includes the source text. For example, when a user requests to view a webpage, the system retrieves the user record(s) and generates the personalized textual description, and provides a modified webpage including the substituted personalized textual description in real-time, in response to the request, in providing the modified webpage to the user, no permanent changes are made to the source text stored on the system; which corresponds to provide the generated user-specific textual description for display device and a modified webpage for display]; however, Maschmeyer fails to explicitly teach that cause the language model to generate one or more outputs comprising the updated text, the one or more contextual inputs characterizing one or more of (i) the first query.
Duan discloses that cause the language model to generate one or more outputs comprising the updated text, the one or more contextual inputs characterizing one or more of (i) the first query [see abstract, pages 412-418 and figures 4, 7; A sketch of the proposed model. Blue circles are item keywords, red circles are query words, orange circles are the associated words retrieved by the Association module from the Association Knowledge Word Graph. The Generation module is designed to generate advertisement text based on the extended sub-graph. Concrete example of advertisement text generation. Blue words represent general needs information, which is usually included in the item keywords that match the item. Red words represent diverse personalized needs contained in different user queries; which corresponds to the missing query-conditioning aspect and formulates the task of generating query-variant and the generation module conditions a transformer-based language model on the query].
Bendersky discloses (iii) the sequence of related past queries; see para. 0039-0040; the language model determines that access to a particular personal repository containing personal data of the user is required by the LLM to fulfill performance of the task specified by the textual prompt. For example, the user submit a textual prompt that requires the LLM to access a data repository or personal drive that store private documents associated with the user. In response to determining that access to the particular personal repository containing personal data of the user is required, the LLM generate a search query specifying the personal data of the user. The search query may include a special token that identifies the particular personal repository containing the personal data. Thereafter, the language model requests, using the search query generated by the LLM the particular personal repository to return the personal data specified by the search query; which corresponds to obtain and using a sequence of related past queries as a contextual input that conditions the language model].
It would have been obvious to one of an ordinary skill in the art, having the teachings of Maschmyer, Duan and Bendersky before the affective filing date of the claimed invention to modify, Maschmeyer’s personalized LLM text-generation system by incorporating the query-variant conditioned generation of Duan and the history aware local context conditioning of Bendersky.
One would have been motivated to make such a combination to recognize that feeding the current query and the sequence of related past queries into the prompt of contextual inputs and the initial digital component data and improving alignment of the generated text provided for display.
Regarding claim 2, Maschmeyer discloses wherein the one or more contextual inputs specify a format of the updated text as comprising a headline representing a title and a predefined number of bullet points providing information about the first resource [see para. 0086; user attributes may be used to inform not only the content of the personalized textual description but also the style of the personalized textual description. In examples, the style of the personalized textual description include tone of voice (e.g., serious, funny, formal, casual, enthusiastic, adventurous etc.), formatting (e.g., bullets, long-form text, use of emojis, headings, sections, font style, color and size etc.) and length, among others; which corresponds to headline representing a title and a predefined number of bullet points is a standard of output format].
Regarding claim 3, Maschmeyer discloses wherein the one or more tasks comprise a first task of generating a textual critique of the initial digital component [see para. 0088-0089; the characteristics of a user may also relate to user preferences, for example, obtained from a user record(s) related to past commerce events or transactions (e.g., historic purchases, past browsing history etc.) or past search events (e.g., search query, browser activity, ads clicked on etc.) over an unrestricted or extended timeframe. In examples, user attributes obtained from “user preference information” help to answer the question “what does the buyer like?” the characteristics of a user may also relate to user needs, for example, obtained from a user record(s) related to recent commerce events or transactions (e.g., recent purchases, recent browsing history, active cart etc.) or recent search events (e.g., search query, browser activity, ads clicked on etc.) within a more restricted and recent timeframe; which corresponds to a textual summary of user intent conditioned on the current query and the sequence of related past queries].
Regarding claim 4, Bendersky discloses wherein the one or more tasks comprise a second task of generating a textual summary of user intent; see para. 0035 and figures 1A-1C; the training process, from a plurality of sample users, a training data set of training tasks stored in a training data store and trains the prompt embedding model of the language model system on the training data set to learn to predict the soft user prompt embeddings for a given user that submits a textual prompt to the language model system, and a respective set of training user features associated with a corresponding training user that issued the training task. Here, the respective set of training user features include personal information such as emails, open documents, in addition to category user features such as age, gender, location, family status, etc; which corresponds to a textual summary of user intent conditioned on the current query and the sequence of related past queries].
Regarding claim 5, Maschmeyer discloses wherein the one or more contextual inputs specify that the textual summary of the user intent is to be generated conditioned on (i) the current query [see para. 0007, 0009; retrieve a user record for a user associated with the request; obtain one or more user attributes based on the user record; generate a prompt to a large language model (LLM) for generating a user-specific textual description, the prompt including the one or more user attributes to include in the generated user-specific textual description and a source text; provide the prompt to the LLM and receive a generated user-specific textual description; and provide the generated user-specific textual description for display via a user device].
Bendersky discloses (ii) the sequence of related past queries; see para. 0039-0040; the language model determines that access to a particular personal repository containing personal data of the user is required by the LLM to fulfill performance of the task specified by the textual prompt. For example, the user submit a textual prompt that requires the LLM to access a data repository or personal drive that store private documents associated with the user. In response to determining that access to the particular personal repository containing personal data of the user is required, the LLM generate a search query specifying the personal data of the user. The search query may include a special token that identifies the particular personal repository containing the personal data. Thereafter, the language model requests, using the search query generated by the LLM the particular personal repository to return the personal data specified by the search query; which corresponds to obtain and using a sequence of related past queries as a contextual input that conditions the language model].
One would have been motivated to make such a combination to recognize that feeding the current query and the sequence of related past queries into the prompt of contextual inputs and the initial digital component data and improving alignment of the generated text provided for display.
Regarding claim 6, Duan discloses wherein the one or more tasks comprise a third task of generating a textual summary of content of the resource [see pages 412-413 and figure 2; the query-variant advertisement text generation task, which aims to automatically generate different advertisement texts considering the needs of various queries. This task serves the query-variant search ad system and Before introducing our task formulation, we first describe the definitions of some phrases in this paper. Query and Item Keywords: Queries are the natural language search content of users in the website. Item keywords are isolated words containing the core information of the item provided by advertisement sponsors].
Regarding claim 7, Bendersky discloses wherein the one or more tasks comprise a fourth task of generating the updated text [see para. 0023 and figures 1A-1C; The user device and/or the remote system executes a language model system that a user interact with through speech, textual inputs, and/or spatial inputs such that the language model system is capable of generating personalized responses to textual prompts specifying a task for a large langue model (LLM) of the language model system to perform].
Regarding claim 8, Maschmeyer discloses wherein the one or more contextual inputs specify that the updated text is to be generated conditioned at least on the user intent predicted by performing the second task [see para. 0068-0070; GPT-3 has been trained as a generative model, meaning that it can process input text sequences to predictively generate a meaningful output text sequence. ChatGPT is built on top of a GPT-type LLM, and has been fine-tuned with training datasets based on text-based chats (e.g., chatbot conversations). ChatGPT is designed for processing natural language, receiving chat-like inputs and generating chat-like outputs].
Regarding claim 9, Maschmeyer discloses wherein the one or more contextual inputs specify that the updated text is to be generated further conditioned on content of the first resource [see para. 0064; put to a language model (whether transformer-based or otherwise) typically is in the form of natural language as may be parsed into tokensTokenization, in the context of language models and NLP, refers to the process of parsing textual input (e.g., a character, a word, a phrase, a sentence, a paragraph, etc.) into a sequence of shorter segments that are converted to numerical representations referred to as tokens (or “compute tokens”). Typically, a token may be an integer that corresponds to the index of a text segment (e.g., a word) in a vocabulary dataset. Often, the vocabulary dataset is arranged by frequency of use. Commonly occurring text, such as punctuation, may have a lower vocabulary index in the dataset and thus be represented by a token having a smaller integer value than less commonly occurring text].
Regarding claim 10, Maschmeyer discloses wherein the one or more tasks comprise a fifth task of generating a textual explanation of why the updated digital component was provided to the user in response to the component request [see para. 0088-0089; the characteristics of a user may also relate to user preferences, for example, obtained from a user record(s) related to past commerce events or transactions or past search events (e.g., search query, browser activity, ads clicked on etc.) over an unrestricted or extended timeframe. In examples, user attributes obtained from “user preference information” help to answer the question “what does the buyer like?” the characteristics of a user may also relate to user needs, for example, obtained from a user record(s) related to recent commerce events or transactions (e.g., recent purchases, recent browsing history, active cart etc.) or recent search events (e.g., search query, browser activity, ads clicked on etc.) within a more restricted and recent timeframe; which corresponds to a textual summary of user intent conditioned on the current query and the sequence of related past queries].
Regarding claim 11, Maschmeyer discloses further comprising providing the textual explanation to the client device for display [see para. 0083; a LLM to generate a personalized text, such as a personalized textual description, a computing system a server of an online platform (e.g., SaaS platform) that provide services to a user device of the user (e.g., over a wireless network) to enable the user to access LLM services for generation of a textual description. The platform obtain a source text and a set of user attributes (which may be explicitly inputted by the user or may be automatically extracted from a database (e.g., the user profiles database) and the prompt generator to generate a prompt. The prompt provided to a LLM (e.g., via an API call to a remote LLM) and the generated textual description received from the LLM. The platform may then present the generated textual description for display on the user device].
Regarding claim 12, Bendersky discloses further comprising: determining, for each respective query in a set of past queries received from the user, a similarity metric measuring a respective similarity between the respective query and the current query; and selecting the related past queries based on the respective similarity metrics of the set of past queries; see para. 0039-0040; the language model determines that access to a particular personal repository containing personal data of the user is required by the LLM to fulfill performance of the task specified by the textual prompt. For example, the user submit a textual prompt that requires the LLM to access a data repository or personal drive that store private documents associated with the user. In response to determining that access to the particular personal repository containing personal data of the user is required, the LLM generate a search query specifying the personal data of the user. The search query may include a special token that identifies the particular personal repository containing the personal data. Thereafter, the language model requests, using the search query generated by the LLM the particular personal repository to return the personal data specified by the search query; which corresponds to obtain and using a sequence of related past queries as a contextual input that conditions the language model].
Regarding claim 13, Maschmeyer discloses wherein the similarity metric comprises a salient term similarity that measures a similarity between two queries based on shared salient terms or keywords [see para. 0185; online store support a number of independently administered storefronts and process a large volume of transactional data on a daily basis for a variety of products and services. Transactional data include any customer information indicative of a customer, a customer account or transactions carried out by a customer such as for example, contact information, billing information, shipping information, returns/refund information, discount/offer information, payment information, or online store events or information such as page views, product search information (search keywords, click-through events), product reviews, abandoned carts, and/or other transactional information associated with business through the e-commerce platform].
Regarding claim 14, Maschmeyer discloses further comprising: storing outputs generated by the language model based on additional search history data of a set of users;
in response to receiving the current query and related past queries from a particular
user, searching the stored outputs to identify an output generated for a similar query history; and generating the updated digital component based on the identified output [see para. 0078; the user profiles database include, for each user or cohort, data about one or more user attributes (e.g., characteristics, preferences and/or needs associated with the user or cohort), personal information, purchase history, review history, viewing history, question history and search history, among other data. User attributes for a given user or class of users may, for example, be stored in a lookup table that can be referenced using a unique identifier (e.g., a code, an identification number, an email address or other reference identifying the user, for example, a reference to the user's account or profile) of the user or cohort. Each user attribute of a given user or cohort may be stored as a text string (which may include one or more words)].
Regarding claim 15, Duan discloses further comprising, before generating the updated text related to the first resource, training the language model using a set of examples, wherein each example specifies at least (i) a training current query, (ii) a training set of past queries and (iii) a training digital component comprising text related to a resource [see abstract, pages 412-418 and figures 4, 7; A sketch of the proposed model. Blue circles are item keywords, red circles are query words, orange circles are the associated words retrieved by the Association module from the Association Knowledge Word Graph. The Generation module is designed to generate advertisement text based on the extended sub-graph. Concrete example of advertisement text generation. Blue words represent general needs information, which is usually included in the item keywords that match the item. Red words represent diverse personalized needs contained in different user queries; which corresponds to the missing query-conditioning aspect and formulates the task of generating query-variant and the generation module conditions a transformer-based language model on the query].
Regarding claim 16, Maschmeyer discloses wherein the language model is a first language model that has been trained using outputs generated by a second language model, wherein the second language model has a larger number of parameters than the first language model [see para 0160, 0168; LLM (which a generative pre-trained transformer LLM, such as GPT-3 or ChatGPT) is prompted to generate a user-specific textual description, the generated prompt is provided to the LLM (e.g., via an API call to a remote LLM). For example, the generated prompt converted to a set of tokens (e.g., using a suitable tokenization algorithm or software), the prompt segmented into a sequence of text segments and each text segment converted to a NLP token (e.g., using a token lookup) while preserving the sequential order of the text segments. Then the set of tokens provided to the LLM (e.g., via an API call) in sequential order. A generated user-specific textual description received in response to the API call].
Regarding claim 18, Maschmeyer discloses wherein the data related to the digital component comprises one or more of text depicted by the digital component, a description of the digital component, or text of a resource linked to be the digital component [see para. 0198; Customers then pay for the content of their cart resulting in the creation of an order for the merchant, the commerce management engine configured to communicate with various payment gateways and services (e.g., online payment systems, mobile payment systems, digital wallets, credit card gateways) via a payment processing component. The actual interactions with the payment gateways provided through a card server environment. At the end of the checkout process, an order is created. An order is a contract of sale between the merchant and the customer where the merchant agrees to provide the goods and services listed on the order (e.g., order line items, shipping line items, and the like) and the customer agrees to provide payment (including taxes)].
Regarding claims 19 and 20, Maschmeyer discloses a system comprising:
one or more computers; and one or more storage devices storing instructions that when executed by the one or more computers, cause the one or more computers to perform operations comprising [see para. 0035; a computer-readable medium storing instructions that, when executed by a processor of a computing system, cause the computing system to: responsive to a request for a textual description, retrieve a user record for a user associated with the request; obtain one or more user attributes based on the user record; generate a prompt to a large language model (LLM) for generating a user-specific textual description]:
receiving data indicating a first query received from a client device of a user [see para. 0007, 0009; retrieve a user record for a user associated with the request; obtain one or more user attributes based on the user record; generate a prompt to a large language model (LLM) for generating a user-specific textual description, the prompt including the one or more user attributes to include in the generated user-specific textual description and a source text; provide the prompt to the LLM and receive a generated user-specific textual description; and provide the generated user-specific textual description for display via a user device; which corresponds to the request process of generating personalized text];
obtaining an initial digital component (i) comprising a link to a first resource and (ii) depicting initial text related to the first resource [see para. 0146; providing a personalized textual description to a user device takes place during runtime on the user device, the data for a webpage (e.g., a product webpage) that is stored on the system includes the source text, when a user requests to view a webpage, the system retrieves the user record(s) and generates the personalized textual description, and provides a modified webpage including the substituted personalized textual description in real-time, in response to the request, in providing the modified webpage to the user, no permanent changes are made to the source text stored on the system; which corresponds to an advertisement or product description on a webpage with a digital component comprising a link and initial text] ;
obtaining search history data comprising a set of related past queries received from the user [see para. 0078, 0081; an optional user profiles database storing a user record(s) (e.g., user profile data) about a plurality of users or classes of users the user profiles database include, for each user or cohort, data about one or more user attributes (e.g., characteristics, preferences and/or needs associated with the user or cohort), personal information, purchase history, review history, viewing history, question history and search history, among other data. User attributes for a given user or class of users stored in a lookup table that referenced using a unique identifier (e.g., a code, an identification number, an email address or other reference identifying the user; which corresponds to user profile stated in the description of user attributes extracted from the user record the queries form search history data];
generating updated text related to the first resource by conditioning a language model with one or more contextual inputs (ii) data related to the initial digital component, or (iv) one or more tasks to be performed by the language model [see para. 0084-0089; the prompt generated by the prompt generator includes instructions to the LLM to include one or more user attributes in the generated textual description so that the generated textual description is a personalized textual description that is customized to the user. Optionally, the platform may, for example, also obtain a set of object attributes (which may be explicitly inputted by the user or may be automatically extracted from a database (e.g., the object database)) for inclusion in the prompt and obtained from a user record(s) related to past commerce events or transactions (e.g., historic purchases, past browsing history etc.) or past search events (e.g., search query, browser activity, ads clicked on etc.) over an unrestricted or extended timeframe; which corresponds to generate a prompt to a large language model that includes user attributes which can include previous search queries and the contextual inputs characterizing data related to the initial component and user history] ; generating an updated digital component that depicts the updated text [see para. 0014-0015; wherein the request is a request received from a user device to view a webpage associated with an object, and wherein the processing unit is configured to execute computer-readable instructions to further cause the system to: in response to the request, provide a modified webpage for display via the user device, the modified webpage including the user-specific textual description; wherein data for the webpage stored on the system includes the source text, and wherein the modified webpage provided to the user device has the user-specific textual description substituted in real-time in response to the request; which corresponds to create an updated digital component modified webpage or product description]; and providing, for display at the client device, the updated digital component depicting the updated text related to the first resource [see para. 0146; providing a personalized textual description to a user device takes place during runtime on the user device. The data for a webpage (e.g., a product webpage) that is stored on the system includes the source text. For example, when a user requests to view a webpage, the system retrieves the user record(s) and generates the personalized textual description, and provides a modified webpage including the substituted personalized textual description in real-time, in response to the request, in providing the modified webpage to the user, no permanent changes are made to the source text stored on the system; which corresponds to provide the generated user-specific textual description for display device and a modified webpage for display]; however, Maschmeyer fails to explicitly teach that cause the language model to generate one or more outputs comprising the updated text, the one or more contextual inputs characterizing one or more of (i) the first query.
Duan discloses that the language model to generate one or more outputs comprising the updated text, the one or more contextual inputs characterizing one or more of (i) the first query [see abstract, pages 412-418 and figures 4, 7; A sketch of the proposed model. Blue circles are item keywords, red circles are query words, orange circles are the associated words retrieved by the Association module from the Association Knowledge Word Graph. The Generation module is designed to generate advertisement text based on the extended sub-graph. Concrete example of advertisement text generation. Blue words represent general needs information, which is usually included in the item keywords that match the item. Red words represent diverse personalized needs contained in different user queries; which corresponds to the missing query-conditioning aspect and formulates the task of generating query-variant and the generation module conditions a transformer-based language model on the query].
Bendersky discloses (iii) the sequence of related past queries; see para. 0039-0040; the language model determines that access to a particular personal repository containing personal data of the user is required by the LLM to fulfill performance of the task specified by the textual prompt. For example, the user submit a textual prompt that requires the LLM to access a data repository or personal drive that store private documents associated with the user. In response to determining that access to the particular personal repository containing personal data of the user is required, the LLM generate a search query specifying the personal data of the user. The search query may include a special token that identifies the particular personal repository containing the personal data. Thereafter, the language model requests, using the search query generated by the LLM the particular personal repository to return the personal data specified by the search query; which corresponds to obtain and using a sequence of related past queries as a contextual input that conditions the language model].
It would have been obvious to one of an ordinary skill in the art, having the teachings of Maschmyer, Duan and Bendersky before the affective filing date of the claimed invention to modify, Maschmeyer’s personalized LLM text-generation system by incorporating the query-variant conditioned generation of Duan and the history aware local context conditioning of Bendersky.
One would have been motivated to make such a combination to recognize that feeding the current query and the sequence of related past queries into the prompt of contextual inputs and the initial digital component data and improving alignment of the generated text provided for display.
Allowable Subject Matter
Claim 17 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure (See PTO-892).
Cappetta (US 2020/0387550) discloses an information handling system and method for generating a customized chat bot integration software system wherein a processor imports a chat bot template process flow into a chat bot integration process-modeling user interface which includes visual interface modeling elements corresponding to code sets, wherein the chat bot integration process-modeling user interface may include visual, drag-and-drop icons representing specific units of work for a specific chat bot integration process and modifying and customizing the visual interface modeling elements in a custom chatbot integration software system via an import wizard user-interface allowing selection of operation objects from the plurality of operation objects for each visual interface modeling element. The information handling system and method utilizes a fulfillment and response database with chat bot conversation history and association of intent and slot combinations with chat bot query responses or data locations and a natural language processing platform to determine an intent and a slot in chat bot queries to generate both simple and dynamic a chat bot query response via the customized chat bot integration software system interfacing with a plurality of data formats.
A reference to specific paragraphs, columns, pages, or figures in a cited prior art reference is not limited to preferred embodiments or any specific examples. It is well settled that a prior art reference, in its entirety, must be considered for all that it expressly teaches and fairly suggests to one having ordinary skill in the art. Stated differently, a prior art disclosure reading on a limitation of Applicant's claim cannot be ignored on the ground that other embodiments disclosed were instead cited. Therefore, the Examiner's citation to a specific portion of a single prior art reference is not intended to exclusively dictate, but rather, to demonstrate an exemplary disclosure commensurate with the specific limitations being addressed. In re Heck, 699 F.2d 1331, 1332-33,216 USPQ 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006,1009, 158 USPQ 275, 277 (CCPA 1968)). In re: Upsher-Smith Labs. v. Pamlab, LLC, 412 F.3d 1319, 1323, 75 USPQ2d 1213, 1215 (Fed. Cir. 2005); In re Fritch, 972 F.2d 1260, 1264, 23 USPQ2d 1780, 1782 (Fed. Cir. 1992); Merck & Co. v. Biocraft Labs., Inc., 874 F.2d 804, 807, 10 USPQ2d 1843, 1846 (Fed. Cir. 1989); In re Fracalossi, 681 F.2d 792,794 n.1,215 USPQ 569, 570 n.1 (CCPA 1982); In re Lamberti, 545 F.2d 747, 750, 192 USPQ 278, 280 (CCPA 1976); In re Bozek, 416 F.2d 1385, 1390, 163 USPQ 545, 549 (CCPA 1969).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CAO H NGUYEN whose telephone number is (571)272-4053. The examiner can normally be reached on Mon-Fri 9am-5pm.
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, Kieu Vu can be reached on 571-272-4057. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/CAO H NGUYEN/Primary Examiner, Art Unit 2171
Prosecution Insights