ENABLING DEVICE CONTROL PLANNING CAPABILITIES OF SMALL LANGUAGE MODEL

Notice of Pre-AIA or AIA Status 1. 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 2. This action is in response to the original filing on 09/04/2024. Claims 1-20 are pending and have been considered below. Information Disclosure Statement 3. The information disclosure statement (IDS(s)) submitted on 09/04/2024, 03/18/2025, 02/03/2026 is/are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Claim Objections 4. Claim 16 is objected to because of the following informalities: Claim 16 recited “the pool of instructions” where “the pool of diverse instructions” was apparently intended. Claim Rejections - 35 USC § 112 5. The following is a quotation of 35 U.S.C. § 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. Claims 1-11 and 13-20 are rejected under 35 U.S.C. § 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention. Independent Claims 1 and 13 recite “wherein the first group of the electronic devices corresponds to all available devices in the environment … transferring the generated computer codes to the hub device.” However, independent Claims 1 and 13 do not previously introduce either an environment or a hub device before referring to “the environment” and “the hub device.” Thus, it is unclear what particular environment is encompassed by “the environment” and what particular device is encompassed by “the hub device.” Accordingly, the metes and bounds of Claims 1 and 13 are unclear. Claims 2-11 and 14-20 incorporate the deficiencies of independent Claims 1 and 13, through dependency, and are also rejected. Claims 3, 4, 15, and 16 recite “Rogue-L filter” and “Rogue-L similarity.” The meaning and scope of the terms “Rogue-L filter” and “Rogue-L similarity” are unclear. The claims do not define what constitutes a Rogue-L filter, how a Rogue-L similarity is determined, or what characteristic distinguish a Rogue-L similarity from other measure of similarity. Although the specification repeats the terminology “Rogue-L filter” and “Rogue-L similarity,” the specification merely states that filtering may correspond to measuring a Rogue-L similarity and applying a threshold. It does not provide a definition of “Rogue-L” itself. Accordingly, the disclosure does not resolve the meaning of the term sufficiently to establish the boundaries of the claimed subject matter. Claims 4 and 16 recite the opposite logical condition by requiring storage when the similarity is equal to or greater than the threshold. In particular, paragraph [0071] of the specification explains that when the Rogue-L similarity between the newly generated instruction and an existing instruction is less than threshold, the newly generated instruction is moved to and stored in the instruction pool. Conversely, when the Rogue-L similarity is equal to or greater than the threshold, the newly generated instruction is discarded. Claim 11 does not define variable N. Without defining the variable N, the metes and bounds of the claimed mathematical operation cannot be determined with reasonable certainty. Allowable Subject Matter Claim 12 is allowed. Claims 1-11 and 13-20 would be allowable if rewritten or amended to overcome the rejections under the 35 U.S.C §112(b) set forth in this Office action. The following is an examiner’s statement of reasons for allowance: The prior art of record, specifically U.S. Patent Application US 20250006196 A1 to Wang does not expressly teach or render obvious the invention as recited in independent claims 1, 12, and 13. The prior art teaches a method for enabling an improved device control capability of a language model (LM) (i.e. the system may be configured to process the ASR data using a language model (e.g., a large language model (LLM)) to determine the action responsive to the user input; para. [0016, 0054]), the method comprising: generating, by using a large language model (LLM), instructions including instructions for controlling a first group of electronic devices and instructions for controlling the first group of the electronic devices, wherein the first group of the electronic devices corresponds to available devices in the environment (i.e. where the language model 160 is an LLM, the input to the LLM may be in the form of a prompt. A prompt may be a natural language input, for example, an instruction, for the LLM to generate an output according to the prompt … the user has the following devices, bathroom light, bedroom light, kitchen light, and living room light. User: turn on the living room light; para. [0023, 0042]); generating, by using the LLM, base plans related to operations of controlling the first group of the electronic devices (i.e. The preliminary action plan generation component 140 processes the user input data 127 to generate prompt generation action plan data 145 corresponding to an instruction(s) (e.g., a request(s)) for one or more portions of data usable to generate a language model prompt for determining an action responsive to the user input. For example, if the user input data 127 represents a user input of “please turn on the kitchen lights every morning at 8 am,” then the preliminary action plan generation component 140 may determine prompt generation action plan data 145 representing instructions for one or more actions (e.g., API definitions) related to turning on the kitchens lights every morning; para. [0026, 0030, 0044]); determining, by using the LLM and a retrieval model, retrieved devices based on the base plans and the indirect instructions, wherein the retrieved devices correspond to a second group of the electronic devices and wherein a first number of the electronic devices in (i.e. The action plan execution component 180 may process the prompt generation action plan data 145 to execute the one or more instructions to retrieve/receive data corresponding to the user input and that may be used to generate the language model prompt … the device state retrieval component 240 may process the action data 185 to generate device state data 196 representing one or more states of one or more devices associated with/relevant to the user input (e.g., whether the device is powered on or off, a volume level associated with the device, etc.). For example, devices (e.g., microwave, oven, fridge, smart speaker, etc.) near the user device 110 (e.g., located in the kitchen) that received the user input may be used to determine the device state data 196. For example, the device state retrieval component 240 may be capable of comparing device profile information for a device (e.g., device ID, device group ID, a location associated with the device, etc.) to the user input to determine whether the device is relevant to the user input. In some embodiments, the device state retrieval component 240 may include the top-n identified device states in the device state data 196. The device state data 196 may be sent (at step 4) to the action plan execution component 180 as shown in FIG. 1; para. [0030-0032, 0036). However, the prior art does not teach a small language model (SLM); a pool of diverse instructions including direct instructions for controlling and indirect instructions for controlling, wherein the first group of the electronic devices corresponds to all available devices in the environment; the first group is higher than a second number of the electronic devices in the second group; generating, by using the LLM, contrastive plans based on a third group of the electronic devices, wherein a third number of the electronic devices in the third group corresponds to a number of the first number minus the second number; generating a data set by combining the base plans and the contrastive plans; performing a fine-tuning the SLM based on the data set; generating computer codes corresponding to the fine-tuned SLM; and transferring the generated computer codes to the hub device to be connected with a fourth group of the electronic devices in the environment. In addition, it is not believed to have been within the level of one of ordinary skill in the art before the effective filling date of the claimed invention to modify or integrate the system of the prior art to incorporate the features of a small language model (SLM); a pool of diverse instructions including direct instructions for controlling and indirect instructions for controlling, wherein the first group of the electronic devices corresponds to all available devices in the environment; the first group is higher than a second number of the electronic devices in the second group; generating, by using the LLM, contrastive plans based on a third group of the electronic devices, wherein a third number of the electronic devices in the third group corresponds to a number of the first number minus the second number; generating a data set by combining the base plans and the contrastive plans; performing a fine-tuning the SLM based on the data set; generating computer codes corresponding to the fine-tuned SLM; and transferring the generated computer codes to the hub device to be connected with a fourth group of the electronic devices in the environment as recited in the context of independent claims 1, 12, and 13, in combination with the other elements recited. Accordingly, claim 12 is allowable, and claims 1-11 and 13-20 contain allowable subject matter but remain rejected under 35 U.S.C §112(b) for the reasons set forth above. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. Wang et al. (Pub. No. US 20250006196 A1), the system generates a prompt including the user input, the APIs, the exemplars, the device states, and the other contextual information. A language model processes the prompt to determine an action responsive to the user input and the system causes performance of the action. Dijkman et al. (Pub. No. US 20250042024 A1), The method generally includes accessing data characterizing a physical environment in which a device is operating. A set of affordable actions is generated based on processing the data via a first set of machine learning models. A selected action to be performed in the physical environment is generated via a second set of machine learning models based on the set of affordable actions and a task. The device is then caused to execute the first selected action. Srinivasan et al. (Pub. No. US 20240135187 A1), Provided are computing systems, methods, and platforms that train query processing models, such as large language models, to perform query intent classification tasks by using retrieval augmentation and multi-stage distillation. Porter et al. (Pub. No. US 20240351218 A1), A method may include sending a query to one of a cobot or an LLM, where the query may be formed to trigger the cobot to perform a target objective, and where the LLM may be constrained to respond to requests to cause the cobot to perform a given objective with a set of human-readable discrete tasks to accomplish the given objective. It is noted that any citation to specific pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. In re Heck, 699 F.2d 1331, 1332-33, 216 U.S.P.Q. 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 U.S.P.Q. 275, 277 (C.C.P.A. 1968)). Any inquiry concerning this communication or earlier communications from the examiner should be directed to TAN TRAN whose telephone number is (303)297-4266. The examiner can normally be reached on Monday - Thursday - 8:00 am - 5:00 pm MT. 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, Matt Ell can be reached on 571-270-3264. 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. /TAN H TRAN/Primary Examiner, Art Unit 2141