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 .
DETAILED ACTION
The instant application having Application No. 18/455,595 filed on 8/24/2023 is presented for examination.
Examiner Notes
Examiner cites particular columns and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
Drawings
The applicant’s drawings submitted are acceptable for examination purposes.
Authorization for Internet Communications
The examiner encourages Applicant to submit an authorization to communicate with the examiner via the Internet by making the following statement (from MPEP 502.03):
“Recognizing that Internet communications are not secure, I hereby authorize the USPTO to communicate with the undersigned and practitioners in accordance with 37 CFR 1.33 and 37 CFR 1.34 concerning any subject matter of this application by video conferencing, instant messaging, or electronic mail. I understand that a copy of these communications will be made of record in the application file.”
Please note that the above statement can only be submitted via Central Fax, Regular postal mail, or EFS Web.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Mohajer (US 10,418,032).
As per claim 1, Mohajer discloses a method comprising:
generating, by at least one processor, an instruction configured to cause at least one large language model (LLM) to request data from a user while preventing the at least one LLM from performing calculations using the data (Column 3, lines 42-62 “The present invention is directed to systems and methods to extract, store, and retrieve dialog context information relevant to creating intelligent dialog in a conversational assistant. Particular embodiments of the present invention are portable across domains, and do not require natural language application developers to acquire a deep training in linguistics or an extensive background in artificial intelligence. Virtual assistants according to embodiments of the invention give users a better experience by supporting natural communication during a dialog with a user. A conversational assistant according with the invention remembers relevant information from recent dialog exchanges, accesses it, and uses it appropriately. Some embodiments of the present invention provide natural language application developers with a framework for handling conversation context. Such a framework has a data structure (called the dialog history) that keeps track of relevant context information and updates it as the dialog progresses. Conversational virtual assistants access a dialog history selectively to retrieve context information from recent queries.”);
presenting, by the at least one processor, a user interface (UI) including output of the at least one LLM to the user, wherein the request for data by the at least one LLM is made through the UI (Column 9, lines 18-28 “The present invention is directed to a virtual personal assistant that is capable of engaging with a user, conversationally, in a natural, human-like way. Such engagement requires the assistant to show an awareness of the conversation context. This involves gathering, storing, and retrieving dialog context information and using it to understand requests. Embodiments of the invention create this functionality by storing and retrieving information from recent dialog. Access to the dialog context depends on the system's ability to recognize, store, and retrieve context data entities of interest, and to use them when processing queries.”);
receiving, through the UI, a user-generated response to the request for data, the user-generated response including at least a portion of the data (Column 4, lines 31-34 “In other words, the context created by one or more previous queries can usefully affect a subsequent query, even if the various queries are not in the same domain.”);
translating the user-generated response into a machine-readable response in a format configured for processing by a calculation engine executed by the at least one processor (Column 5, lines 51-59 “The terms semantic grammar and semantic parser are used herein broadly, as follows. In addition to the specific embodiment using augmented grammars and syntax-based semantics, they will also cover alternative embodiments of similar scope and purpose. In the generalized form, a semantic grammar comprises a collection of syntactic rules (or patterns) and associated semantic rules (interpretation patterns), which, when used in combination, control and enable the functionality of a semantic parser.”);
processing, by the calculation engine executed by the at least one processor, the machine-readable response, thereby generating a calculation engine output (Column 6, 33-51 “The terms semantic grammar and semantic parser are used herein broadly, as follows. In addition to the specific embodiment using augmented grammars and syntax-based semantics, they will also cover alternative embodiments of similar scope and purpose. In the generalized form, a semantic grammar comprises a collection of syntactic rules (or patterns) and associated semantic rules (interpretation patterns), which, when used in combination, control and enable the functionality of a semantic parser.”); and
modifying, by the at least one processor, the UI to include an indication of the calculation engine output (Column 6, 33-51).
As per claim 2, Mohajer further discloses wherein in response to receiving the at least the portion of the data comprising less than all of the data, the at least one LLM makes at least one additional request for at least a portion of remaining data (Column 7, lines 20-33 “As another example, the isolated query ‘and with $200,000 down’ is meaningless. However, this query is issued right after the dialog of FIG. 1, the dialog context allows the assistant to respond as if the user had uttered the complete query, ‘What is the mortgage on a one million dollar house with two hundred thousand dollars down at four percent interest over thirty years?’ This query has a definite answer. A virtual assistant that imitates people's handling of context should be able to answer, too. Following up with a query like ‘and at three point seven five percent?’ is similarly interpreted as ‘What is the mortgage on a one million dollar house with two hundred thousand dollars down at three point seven five percent interest over thirty years?’ and answered accordingly.”).
As per claim 3, Mohajer further discloses further comprising:
determining, by the at least one processor, that the at least the portion of the data that has been received comprises less than all of the data (Column 7, lines 20-33); and
in response to the determining, generating, by the at least one processor, a second instruction configured to cause the at least one LLM to request remaining data from the user while preventing the at least one LLM from performing calculations using the remaining data, wherein the request for the remaining data by the at least one LLM is made through the UI (Column 7, lines 20-33).
As per claim 4, Mohajer further discloses further comprising:
receiving, through the UI, a second user-generated response to the request for remaining data, the second user-generated response including at least a second portion of the data (Column 7, lines 20-33);
translating the second user-generated response into a second machine-readable response in the format configured for processing by the calculation engine executed by the processor (Column 7, lines 20-33);
processing, by the calculation engine executed by the at least one processor, the second machine-readable response, thereby generating a second calculation engine output (Column 7, lines 20-33); and
modifying, by the at least one processor, the UI to include an indication of the second calculation engine output (Column 7, lines 20-33).
As per claim 5, Mohajer further discloses wherein:
the data comprises multiple parts (Column 7, lines 20-33); and
the instruction is further configured to cause the at least one LLM to attempt to obtain a plurality of the multiple parts in a single user-generated response (Column 7, lines 20-33).
As per claim 6, Mohajer further discloses wherein the translating comprises:
generating, by the at least one processor, a translation instruction configured to cause the at least one LLM to convert the a user-generated response into the machine-readable response (Column 11, 27-41 “Instances of a dialog layer data structure hold values for the slot variables. In an embodiment that supports types, slot values must match their slot type. Values may be simple and self-contained (such as the value of a HOW MANY slot which is an integer); they may also be objects a.k.a. entities (or internal pointers to entities) that act as entry points into arbitrarily complex networks of inter-related data, such as data structures and databases; or finally they may be expressions—data structures that, if/when evaluated, yield a value of one of the previous types. The latter are unevaluated expressions. For example, we can have an ADDRESS slot whose type is <an Address> and assign to it an expression that is the internal representation of ‘Uncle Robert's country home’ and that (once given access to the user's address book, for example) will properly evaluate to an Address.”); and
receiving, by the at least one processor, the machine-readable response from the at least one LLM (Column 11, 27-41).
As per claim 7, Mohajer further discloses wherein the translating comprises applying, by the at least one processor, a data extraction model to the user-generated response, thereby generating the machine-readable response (Column 7, line 38 – Column 8, line 6 “(35) Recall that a semantic parser parses and interprets a query, according to a given semantic grammar. The semantic parser serves the function of a ‘plain’ (non-semantic) parser, which is to check the syntactic structure of the query: the word sequence must be valid according to a ‘plain’ (un-augmented) grammar. A second function is to extract the meaning (or interpretation) of the query. The terms meaning and interpretation are technically equivalent in this disclosure. They both refer to an internal data structure that a semantic parser creates as the encoding of a user's query as an internal form suitable for further processing. Parsing uses both syntactic and semantic constraints to decide if a query is recognized as valid. A query fails to be recognized if the sequence of words is rejected by the syntax. For example, ‘what is the weather in Chicago’ is recognized by some embodiments of the invention, but the parser will (or should) reject ‘weather what is Chicago’ due to syntax. Syntactically correct queries can fail on semantic grounds. For example, ‘what time is my first appointment on February 29’ is syntactically correct, but not semantically correct—except on leap years; the date expression ‘February 29’ has to be syntactically correct, since this is a valid word sequence for a date on a leap year; yet, it is incorrect in a non-leap year. In a typical embodiment, calendar knowledge about leap years is part of calendar semantics, not date syntax. According to an embodiment, a query that fails during semantic parsing has no interpretation. In another embodiment, the absence of a valid interpretation may be handled, data structure-wise, by the use of a special value, such as a NULL pointer, or another convention. In yet another embodiment, a syntactically valid but semantically invalid query may have a special error interpretation whose purpose is to give the user an error message, or more interestingly, to ask for a clarification, e.g., ‘There is no February 29 this year, do you mean March 1?’”).
As per claims 8-13, they are method claims having similar limitations as cited in claims 1-7 and are rejected under the same rationale.
As per claims 14-20, they are method claims having similar limitations as cited in claims 1-7 and are rejected under the same rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Gruber (US 2015/0348551) discloses handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription process. The text string can be parsed into multiple candidate substrings based on domain keywords, imperative verbs, predetermined substring lengths, or the like. For each candidate substring, a probability can be determined indicating whether the candidate substring corresponds to an actionable command. Such probabilities can be determined based on semantic coherence, similarity to user request templates, querying services to determine manageability, or the like. If the probabilities exceed a threshold, the user intent of each substring can be determined, processes associated with the user intents can be executed, and an acknowledgment can be provided to the user.
London (US 2015/0142704) discloses an adaptive virtual intelligent agent ("AVIA") service are disclosed. It may include the functions of a human administrative assistant for an enterprise including customer support, customer relationship management, and fielding incoming caller inquiries. It also has multi-modal applications for the home through interaction with AVIA implemented in the home. It may engage in free-form natural language dialogs. During a dialog, embodiments maintain the context and meaning of the ongoing dialog and provides information and services as needed by the domain of the application. Over time, the service automatically extends its knowledge of the domain (as represented in the Knowledge Tree Graphs) through interaction with external resources. Embodiments can intelligently understand and converse with users using free-form speech without pre-programmed deterministic sequences of questions and answers, can dynamically determine what it needs to know to converse meaningfully with users, and knows how to obtain information it needs.
Mirkovic (US 2006/0271364) discloses representation-neutral dialogue systems and methods ("RNDS") are described that include multi-application, multi-device spoken-language dialogue systems based on the information-state update approach. The RNDS includes representation-neutral core components of a dialogue system that provide scripted domain-specific extensions to routines such as dialogue move modeling and reference resolution, easy substitution of specific semantic representations and associated routines, and clean interfaces to external components for language-understanding (i.e., speech-recognition and parsing) and language-generation, and to domain-specific knowledge sources. The RNDS also resolves multi-device dialogue by evaluating and selecting among candidate dialogue moves based on features at multiple levels. Multiple sources of information are combined, multiple speech recognition and parsing hypotheses tested, and multiple device and moves considered to choose the highest scoring hypothesis overall. Confirmation and clarification behaviour can be governed by the overall score.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TIMOTHY A MUDRICK whose telephone number is (571)270-3374. The examiner can normally be reached 9am-5pm Central Time.
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, Pierre Vital can be reached at (571)272-4215. 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.
/TIMOTHY A MUDRICK/Primary Examiner, Art Unit 2198 12/30/2025