Response to Amendment
This office action in response to a communication received on January 30, 2026.
Claims 1-20 are pending in this application.
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 .
Response to Arguments
Applicant’s comment (see remarks Pg. 11) with respect to the claim interpretation of claim 1 under 35 U.S.C. §112(f) have been fully considered and claim interpretation is maintained.
Applicant’s arguments (see remarks Pg. 12-13) with respect to the rejection(s) of claim(s) 1-20 under 35 U.S.C. §103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn.
However, upon further consideration, a new ground(s) of rejection is made as necessitated by the claim amendments.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
“a testing component, configured to: obtain, …, one or more output parameters…”, “perform, …, one or more test operations”, “determine, …, one or more performance parameters…, and”, “perform, …, one or more action.” in claim 1.
Sufficient structure for the functions were found in the specification in at least pages 33-34 and 41-43.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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, 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 non-obviousness.
Claim(s) 1-4, 8-9 and 15, are rejected under 35 U.S.C. 103 as being unpatentable over CHAI et al., US 20240211810 A1, (hereinafter CHAI) in view of ZHAO, US 20200349471 A1, (hereinafter ZHAO) and in further view of SUN et al., US 20250021861 A1, (hereinafter SUN).
Regarding claim 1, and 8, CHAI teaches a testing system, comprising:
a testing component, configured to: obtain, from a wireless communication device, one or more output parameters associated with a second embedded AI/ML model indicating information associated with one or more functions performed by the second embedded AI/ML model (see Fig. 7, e.g., element Base station, Terminal, 703; ¶ [0120], a terminal reports a first test result to a base station. The first test result indicates an output of the AI model, a performance indicator determined based on an output of the AI model, or the like. The base station determines, based on the first test result, whether the AI models participating in the test meets the performance goal, and the like. For details, refer to a procedure shown in FIG. 7.),
based on a network scenario, of the plurality of different network scenarios, in which the wireless communication device is operating (see ¶ [0063], e.g., the terminal is widely used in communication in various scenarios, for example, including but not limited to at least one of the following scenarios: a device-to-device (device-to-device, D2D) scenario, a vehicle-to-everything (vehicle-to-everything, V2X) scenario; see ¶ [0065], e.g., The base station and the terminal are fixed or movable. The base station and/or the terminal is deployed on the land, including an indoor device, an outdoor device, a handheld device, or a vehicle-mounted device, is deployed on the water, … The base station and the terminal is deployed in a same scenario or different scenarios. For example, the base station and the terminal are both deployed on the land.),
wherein the second embedded AI/ML model is embedded at the wireless communication device (see ¶ [0003], e.g., Embodiments described herein provide a model test method and an apparatus. A network device tests an AI model deployed in a terminal, so that the network device evaluates, manages, and controls the AI model deployed in the terminal.), and
wherein the one or more functions are associated with an air interface over which the wireless communication device is configured to communicate; (see Fig. 3a, 3b, e.g., Air interface; ¶ [0100], e.g., the first information includes a downlink data signal sent on a predefined downlink channel. For example, the base station configures a downlink channel for the terminal, where the downlink channel is predefined or known to the terminal. The base station notifies the terminal that the downlink channel is used to obtain a test set online.),
perform, one or more test operations using the one or more output parameters (see ¶ [0128], e.g., In response to receiving the second information sent by the terminal, the base station determines, based on the first test result indicated by the second information, whether each AI models participating in the test meets a performance goal; In a design, in response to the first test result fed back by the terminal indicating the output that is of the AI model and that is obtained based on the test set, in a case of supervised learning, the base station compares the output of the AI model with the corresponding label (namely, an accurate output) to determine an error between the output of the AI model and the corresponding label, and determines, based on the error between the output of the AI model and the corresponding label, whether the AI models participating in the test meets the performance goal.);
determine, based on the one or more test operations, one or more performance parameters indicating a performance level of the second embedded AI/ML model (see ¶ [0129], e.g., In another design, in response to the first test result fed back by the terminal indicating the performance indicator that is of the AI model obtained by testing the AI model based on the at least one test set, the base station determines, based on the performance indicator of the AI model, whether the AI model meets the performance goal. For example, the performance indicator fed back by the terminal is an NMSE. In this case, in response to the NMSE being less than a threshold, the base station considers that the AI models participating in the test meets the performance goal. In response to the NMSE not being less than a threshold, the base station considers that the AI models participating in the test does not meet the performance goal.); and
perform, based on the one or more performance parameters, one or more actions (Fig. 7, e.g., element Base station, Terminal, 704; ¶ [0131], Step 704: The base station sends first indication information to the terminal. There are one or more pieces of first indication information. This is not limited. For example, in response to the first indication information indicating that the AI models participating in the test meets or does not meet the performance goal, whether each of the AI models participating in the test meets the performance goal is indicated by using one piece of indication information, for example, by using the following bitmap.),
however, it does not explicitly teach a test model that includes a first embedded artificial intelligence or machine learning (AI/ML) model that is trained to evaluate performance of other embedded AI/ML models in connection with one or more network events under a plurality of different network scenarios and wherein the first embedded AI/ML model is a reference model for the one or more test operations and using the test model to perform the one or more test operations using the one or more output parameters.
ZHAO teaches, a test model that includes a first embedded artificial intelligence or machine learning (AI/ML) model that is trained to evaluate performance of other embedded AI/ML models in connection with one or more network events (see ¶ [0068], e.g., the trained reference model may be a neural network model that has a large number of layers, a large number of nodes, a large number of parameters, or the like, or any combination thereof. The trained reference model may be well trained to predict an accurate result. For example, the trained reference model may be trained on a computing platform with a strong computational power with a large amount of sample data from big-data database. The trained reference model may be trained and tested until the trained reference model meets a predetermined condition) and
wherein the first embedded AI/ML model is a reference model for the one or more test operations and using the test model to perform the one or more test operations using the one or more output parameters (see ¶ [0064], e.g., The model testing module 430 may be configured to test a plurality of trained learner models to obtain a final trained learner model. For example, for each of the plurality of trained learner models, the model testing module 430 may determine an output difference between the trained learner model and the trained reference model using a test data set as inputs of the trained learner model and the trained reference model. The model testing module 430 may determine a final trained learner model from the plurality of trained learner models based on the plurality of output differences; ¶ [0059], when a server 110 processes a task, such as use a trained reference model to train a learner model, the server 110 may operate logic circuits in its processor to process such task. When the server 110 completes training the learner model, the processor of the server 110 may generate electrical signals encoding the trained learner model. The processor of the server 110 may then send the electrical signals to at least one information exchange port of a target system associated with the server 110.).
SUN teaches, a test model that is trained under a plurality of different network scenarios (see ¶ [0064] the system can be used to train and test the ML model either offline via ML training module/host 204 or online via ML model module 222 within the real physical network. Also see ¶ [0065], wherein the ML model is trained in all possible scenarios generated from digital replica of a physical RAN as if it is real through advanced simulation and ¶ [0068], wherein it is trained on real network data).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified label (namely, an accurate output) of CHAI to incorporate the teachings of ZHAO to include a test model that includes a first embedded artificial intelligence or machine learning (AI/ML) model that is trained to evaluate performance of other embedded AI/ML models and using the test model to perform the one or more test operations using the one or more output parameters, and incorporate the teachings of SUN to include a test model that is trained under a plurality of different network scenarios. Doing so would facilitate in achieving simpler learner model to mimic behaviors of a structurally more complicated reference model as suggested by ZHAO (see ¶ [0013], e.g., an artificial intelligent method for using a structurally simpler learner model to mimic behaviors of a structurally more complicated reference model), and would facilitate in achieving training under various scenarios and supporting both offline and online training of AI/ML models as suggested by SUN (see ¶ [0005], e.g., the digital twin, implemented through digital simulation and modelling, can represent a digital replica of a physical O-RAN network connected with the RIC. The AI/ML model before deployment in the rAppls/xApps can be trained with a training data set generated from the digital twin which can complement the limitation of real data captured from the physical network.).
Regarding claim 2, and 9, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 1.
CHAI further teaches, wherein the first embedded AI/ML model is trained to facilitate the one or more functions associated with the air interface by one or more network events (see ¶ [0084], e.g., Perform model training by using the training set, to obtain an AI model, where this process is referred to as model training. ¶ [0085], e.g., Model training is an important part of machine learning. The essence of machine learning is to learn some features of the training sample from the training sample, so that a difference between an output of the AI model and an ideal target value is minimized through training of the training set. Usually, even in response to a same network structure being used, weights and/or outputs of AI models trained by using different training sets are different. Therefore, to some extent, performance of the AI model is determined by composition and selection of the training set.),
however, it does not explicitly teach simulating or recreating the one or more network events under a plurality of different network scenarios.
SUN teaches, simulating or recreating the one or more network events (see ¶ [0072], e.g., referring to FIG. 7, in one exemplary method of operation, RAN scenario generator module 310 (which can be powered with AI/ML technology) can configure the parameters of the digital twin model, or the simulated O-RAN network, in order to automatically generate one or a plurality of test scenarios or network events (data sets) to challenge the RIC AI/ML model module 324 under training and testing),
under a plurality of different network scenarios (see ¶ [0064] the system can be used to train and test the ML model either offline via ML training module/host 204 or online via ML model module 222 within the real physical network. Also see ¶ [0065], wherein the ML model is trained in all possible scenarios generated from digital replica of a physical RAN as if it is real through advanced simulation and ¶ [0068], wherein it is trained on real network data).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified network events of CHAI to incorporate the teachings of SUN to include simulating the one or more network events. Doing so would facilitate in achieving accurate replica of the network for any future or unseen states for generating and constructing training scenarios and supporting both offline and online training of AI/ML models as suggested by SUN (see ¶ [0005], e.g., the digital twin, implemented through digital simulation and modelling, can represent a digital replica of a physical O-RAN network connected with the RIC. The AI/ML model before deployment in the rAppls/xApps can be trained with a training data set generated from the digital twin which can complement the limitation of real data captured from the physical network. The digital twin module can be calibrated with the physical network data in order to create an accurate replica of the network for not only the historical state when the physical network data was captured but also any future or unseen states for generating and constructing training scenarios. According to one or more example embodiments, the digital twin module can be deployed in Near-RT RIC, rApp, xApps, or external to RIC supporting both offline and online training of AI/ML models.).
Regarding claim 3, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 1.
CHAI further teaches, wherein the testing component, to perform the one or more test operations, is configured to:
generate, using the one or more output parameters, evaluation data for one or more active testing scenarios;
and obtain, one or more reference parameters indicating an expected behavior in the one or more active testing scenarios,
wherein the one or more performance parameters are based on a comparison of the one or more reference parameters to the one or more output parameters (see ¶ [0128], e.g., In response to receiving the second information sent by the terminal, the base station determines, based on the first test result indicated by the second information, whether each AI models participating in the test meets a performance goal. In a design, in response to the first test result fed back by the terminal indicating the output that is of the AI model and that is obtained based on the test set, in a case of supervised learning, the base station compares the output of the AI model with the corresponding label (namely, an accurate output) to determine an error between the output of the AI model and the corresponding label, and determines, based on the error between the output of the AI model and the corresponding label, whether the AI models participating in the test meets the performance goal. For example, in response to the error between the output of the AI model and the corresponding label being less than a specific threshold, the AI models participating in the test meets the performance goal. In response to the error between the output of the AI model and the corresponding label not being less than a specific threshold, the AI models participating in the test do not meet the performance goal.),
however, it does not explicitly teach, provide, as an input to the test model, the evaluation data; and obtain, via an output of the test model, one or more reference parameters.
ZHAO teaches, provide, as an input to the test model, the evaluation data; and obtain, via an output of the test model, one or more reference parameters (see ¶ [0064], e.g., The model testing module 430 may be configured to test a plurality of trained learner models to obtain a final trained learner model. For example, for each of the plurality of trained learner models, the model testing module 430 may determine an output difference between the trained learner model and the trained reference model using a test data set as inputs of the trained learner model and the trained reference model. The model testing module 430 may determine a final trained learner model from the plurality of trained learner models based on the plurality of output differences; ¶ [0059], when a server 110 processes a task, such as use a trained reference model to train a learner model, the server 110 may operate logic circuits in its processor to process such task. When the server 110 completes training the learner model, the processor of the server 110 may generate electrical signals encoding the trained learner model. The processor of the server 110 may then send the electrical signals to at least one information exchange port of a target system associated with the server 110.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified label (namely, an accurate output) of CHAI to incorporate the teachings of ZHAO to include a test model that includes a first embedded artificial intelligence or machine learning (AI/ML) model that is trained to evaluate performance of other embedded AI/ML models. Doing so would facilitate in achieving simpler learner model to mimic behaviors of a structurally more complicated reference model as suggested by ZHAO (see ¶ [0013], e.g., an artificial intelligent method for using a structurally simpler learner model to mimic behaviors of a structurally more complicated reference model).
Regarding claim 4, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 1.
CHAI further teaches, wherein the testing component is further configured to: transmit, to the wireless communication device, test data for one or more active testing scenarios,
wherein the testing component, to obtain the one or more output parameters, is configured to:
obtain the one or more output parameters based on transmitting the test data (see Fig. 7, e.g., element Base station, Terminal, 701, 702; ¶ [0124], e.g., Step 701: The base station sends the first information to the terminal, where the first information is used to determine at least one test set. ¶ [0125], e.g., Step 702: The terminal tests the AI model based on the at least one test set, to obtain a first test result).
Regarding claim 15, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 8.
CHAI further teaches, wherein performing the one or more actions comprises:
transmitting, to a network operator device, an indication of the one or more performance parameters (see ¶ [0112], e.g., In an implementation, the AI model is tested by another device other than the base station. The Another device includes a core network device, OAM, remote intelligent communication, a wireless intelligent controller, an AI node, or the like. The base station specifically forwards information. For example, a core network device tests an AI model deployed in a terminal.).
Claim(s) 5-6, 10-12, 14, and 16-20, are rejected under 35 U.S.C. 103 as being unpatentable over CHAI in view of ZHAO and SUN and in further view of FEVOLD et al., US 20250053872 A1, (hereinafter FEVOLD).
Regarding claim 5, and 20, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 1 and CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 16.
CHAI as improved by ZHAO and SUN does not teach but FEVOLD teaches, wherein the testing component, to perform the one or more actions, is configured to:
cause the wireless communication device to switch from the second embedded AI/ML model to a third embedded AI/ML model that is trained to perform the one or more functions (see Fig. 4, e.g., element Model Monitoring, Steps 4-9; ¶ [0106], Another augmentation, as indicated by block 410, is the indication (step 4b-2, though this might also involve one or both of steps 4c and 5) of poor performance for a particular model, if indicated by multiple UEs 10, may cause the network 1 to decide to change the model (e.g., minimization of resource utilization, performing retuning when multiple/many UEs need retuning, such as via a threshold). For instance, if 10 UEs are using the model, and three UEs report poor performance, this might cause the network 1 to determine to change the model (and perform steps 6 and 7 to effect the change). A threshold number or percentage of UEs that have implemented the model could be used for this step. Note that the multiple UE aspect is one example, as if there is a single UE (e.g., as in FIG. 3) with the model and that UE has indicated poor performance, the network 1 may decide to change that model; ¶ [0011], wherein the retuning creates a second artificial intelligence or machine learning model that is a retuned version of the first artificial intelligence or machine learning model, wherein the first and second artificial intelligence or machine learning models are from a same lineage of artificial intelligence or machine learning models; and switching by the user equipment from the first artificial intelligence or machine learning model to the second artificial intelligence or machine learning model).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI to incorporate the teachings of FEVOLD to include switching to a new AI/ML model. Doing so would facilitate in achieving quickly and efficiently resolving degradation in UE performance as suggested by FEVOLD (see ¶ [0037], e.g., [0037] As a result of AI/ML models being created from large, aggregate datasets, AI/ML models may experience performance fluctuations when deployed in different geographic locations, channel conditions, scenarios, or for all time, e.g., the model's performance could decrease over time. To resolve degradation in UE performance, there are three options: fallback to a legacy non-AI/ML mechanism; obtain or switch to a new model; or retune an existing model to perform well under conditions more specific than could be addressed by the more general base model. Additionally, the degradation should be resolved quickly and efficiently, and ideally before the AI/ML model's performance drops below that of legacy techniques.).
Regarding claim 6, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 1.
CHAI as improved by ZHAO and SUN does not teach but FEVOLD teaches, wherein the testing component, to perform the one or more actions, is configured to:
cause the wireless communication device to modify one or more parameters of the second embedded AI/ML model (see ¶ [0214], e.g., Example 4. The method according to example 3, wherein: the method further comprises receiving, by the network element, multiple indications indicating poor performance from multiple user equipment; the method further comprises deciding, by the network element, to change the first artificial intelligence or machine learning model based on reception of the multiple indications; and the sending configuration for model retuning to trigger the user equipment to perform operations to aid in retuning of the first artificial intelligence or machine learning model is performed in response to deciding to change the first artificial intelligence or machine learning model).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI to incorporate the teachings of FEVOLD to include switching to a new AI/ML model. Doing so would facilitate in achieving, quickly and efficiently resolving degradation in UE performance as suggested by FEVOLD (see ¶ [0037], e.g., As a result of AI/ML models being created from large, aggregate datasets, AI/ML models may experience performance fluctuations when deployed in different geographic locations, channel conditions, scenarios, or for all time, e.g., the model's performance could decrease over time. To resolve degradation in UE performance, there are three options: fallback to a legacy non-AI/ML mechanism; obtain or switch to a new model; or retune an existing model to perform well under conditions more specific than could be addressed by the more general base model. Additionally, the degradation should be resolved quickly and efficiently, and ideally before the AI/ML model's performance drops below that of legacy techniques.).
Regarding claim 10, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 8.
CHAI as improved by ZHAO and SUN does not teach but FEVOLD teaches, wherein the one or more output parameters are associated with a plurality of operation modes of the embedded AI/ML model, and wherein performing the one or more actions comprises:
selecting an active operation mode from the plurality of operation modes using the one or more performance parameters indicating that the active operation mode is associated with a highest performance level; and
transmitting, to the wireless communication device, an indication to use the active operation mode (see ¶ [0105], e.g., The network could, in some implementations, choose more than one UE to retune to mitigate the risk that a UE leaves the coverage area without completing the AI/ML retuning procedure and in the second monitoring phase, described in FIG. 8, FIG. 9, FIG. 10, and FIG. 11, choose the best of the retuned AI/ML models. Steps 8 and 9 provide configuration to the UE B to aid in the model retuning that is performed later; ¶ [0163], e.g., An AI/ML model memory phase is now described. Now that the original AI/ML model has been retuned, made available to the UE, selected by the UE, monitored, determined to be well-performing, and its binary transferred/delivered to the network (FIG. 8, FIG. 9, FIG. 11) or to the OTT server (FIG. 9) or its ID and metadata transferred to the network (FIG. 9, FIG. 11), the network can store, alongside the AI/ML model binary, model ID, and/or model metadata, information related to the conditions (e.g., channel conditions, network loading, time of day, and the like) under which the model is to be used and would perform well. These conditions can be used to help UEs not part of the AI/ML model retuning procedures described herein to acquire and execute the retuned AI/ML model for the best performance.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI to incorporate the teachings of FEVOLD to include switching to a best available AI/ML model. Doing so would facilitate in achieving, quickly and efficiently resolving degradation in UE performance as suggested by FEVOLD (see ¶ [0037], e.g., As a result of AI/ML models being created from large, aggregate datasets, AI/ML models may experience performance fluctuations when deployed in different geographic locations, channel conditions, scenarios, or for all time, e.g., the model's performance could decrease over time. To resolve degradation in UE performance, there are three options: fallback to a legacy non-AI/ML mechanism; obtain or switch to a new model; or retune an existing model to perform well under conditions more specific than could be addressed by the more general base model. Additionally, the degradation should be resolved quickly and efficiently, and ideally before the AI/ML model's performance drops below that of legacy techniques.).
Regarding claim 11, CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 10.
CHAI as improved by ZHAO and SUN does not teach but FEVOLD teaches, wherein obtaining the one or more output parameters comprises:
obtaining at least one output parameter, of the one or more output parameters, associated with an operation mode, of the plurality of operation modes, based on the air interface being associated with one or more radio conditions that are indicative of an operational scenario that is associated with the operation mode (see ¶ [0163], e.g., An AI/ML model memory phase is now described. Now that the original AI/ML model has been retuned, made available to the UE, selected by the UE, monitored, determined to be well-performing, and its binary transferred/delivered to the network (FIG. 8, FIG. 9, FIG. 11) or to the OTT server (FIG. 9) or its ID and metadata transferred to the network (FIG. 9, FIG. 11), the network can store, alongside the AI/ML model binary, model ID, and/or model metadata, information related to the conditions (e.g., channel conditions, network loading, time of day, and the like) under which the model is to be used and would perform well.).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI to incorporate the teachings of FEVOLD to include switching to available AI/ML model. Doing so would facilitate in achieving, quickly and efficiently resolving degradation in UE performance as suggested by FEVOLD (see ¶ [0037], e.g., As a result of AI/ML models being created from large, aggregate datasets, AI/ML models may experience performance fluctuations when deployed in different geographic locations, channel conditions, scenarios, or for all time, e.g., the model's performance could decrease over time. To resolve degradation in UE performance, there are three options: fallback to a legacy non-AI/ML mechanism; obtain or switch to a new model; or retune an existing model to perform well under conditions more specific than could be addressed by the more general base model. Additionally, the degradation should be resolved quickly and efficiently, and ideally before the AI/ML model's performance drops below that of legacy techniques.).
Regarding claim 12, CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 10.
CHAI as improved by ZHAO and SUN does not teach but FEVOLD teaches, wherein the plurality of operation modes include a main operation mode and one or more alternate operation modes (see Fig. 2, e.g., element 3. Model Selection (A.1), 5. Evaluate Performance, 6. Search Retuned Model Memory; ¶ [0070], e.g., 3a. The evaluation of performance (e.g., in step 5) can use many evaluation tools and/or algorithms, such as determining values for one or more KPIs. [0071] 3b. After the performance is evaluated, a search can be performed of a retuned model memory 200, which has multiple retuned models),
wherein the performance level is associated with the main operation mode, and wherein performing the one or more actions comprises (see ¶ [0064], e.g., Steps 15 and 16 represent a new UE (B) running a model (A.1) experiencing poor performance. With respect to step 15, one may consider the procedures related to UE A to be complete, so while monitoring would continue even for UE A, that is not relevant to the rest of the signaling diagram. For UE B, Model A.I would be monitored since that model what UE B has):
causing the wireless communication device to switch between the main operation mode and an alternate operation mode of the one or more alternate operation modes using the one or more performance parameters indicating that the performance level does not meet one or more criteria (see ¶ [0065], e.g., In step 17, the NW 1 again searches a retuned model memory 220. In step 18, the entities perform a model transfer of the retuned model A.3, Model A.3 230-3 (e.g., performed by the OTT server 210, the UE A 10-A, or the NW 1). In step 19, a model switch is performed, e.g., to use the retuned model A.3 by the UE B 10-B. Steps 17-19 can be considered to find a retuned model, transfer, and switch. In the example of FIG. 1, step 18 refers to a model transfer, assuming that Model A.3 230-3 would be transferred to the to the UE B 10-1. However, UE B might actually have A.3 and the NW 1 can have the UE B to just switch to Model A.3 in step 18 instead of using a “transfer”).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI to incorporate the teachings of FEVOLD to include switching to alternate AI/ML model. Doing so would facilitate in achieving, quickly and efficiently resolving degradation in UE performance as suggested by FEVOLD (see ¶ [0037], e.g., As a result of AI/ML models being created from large, aggregate datasets, AI/ML models may experience performance fluctuations when deployed in different geographic locations, channel conditions, scenarios, or for all time, e.g., the model's performance could decrease over time. To resolve degradation in UE performance, there are three options: fallback to a legacy non-AI/ML mechanism; obtain or switch to a new model; or retune an existing model to perform well under conditions more specific than could be addressed by the more general base model. Additionally, the degradation should be resolved quickly and efficiently, and ideally before the AI/ML model's performance drops below that of legacy techniques.).
Regarding claim 14, CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 12.
CHAI as improved by ZHAO and SUN does not teach but FEVOLD teaches, wherein determining the one or more performance parameters comprises:
determining performance differences between the main operation mode and respective alternate operation modes of the one or more alternate operation modes (see ¶ [0138], e.g., Next, the final performance monitoring phase is described. The final monitoring phase determines whether the retuned AI/ML model performs well compared to the performance of the original model and/or the legacy method. As in the initial monitoring phase, the AI/ML model's performance is evaluated against a standardized or network-configured KPI value; ¶ [0129], The OTT server delivers the retuned AI/ML model, A.3, to the UE. The OTT server optionally transfers/delivers, to the UE A, one of the following, which could be in a binary format: (1) its retuned model; (2) the delta between the original and retuned model; or (3) information required to reconstruct the retuned model, metadata; and a unique ID associated with its retuned model).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI to incorporate the teachings of FEVOLD to include determining performance differences between the main operation mode and respective alternate operation modes of the one or more alternate operation modes. Doing so would facilitate in achieving, quickly and efficiently resolving degradation in UE performance as suggested by FEVOLD (see ¶ [0037], e.g., As a result of AI/ML models being created from large, aggregate datasets, AI/ML models may experience performance fluctuations when deployed in different geographic locations, channel conditions, scenarios, or for all time, e.g., the model's performance could decrease over time. To resolve degradation in UE performance, there are three options: fallback to a legacy non-AI/ML mechanism; obtain or switch to a new model; or retune an existing model to perform well under conditions more specific than could be addressed by the more general base model. Additionally, the degradation should be resolved quickly and efficiently, and ideally before the AI/ML model's performance drops below that of legacy techniques.).
Regarding claim 16, the claim recites a testing device, comprising: one or more processors of the testing system of claim 1, and is similarly analyzed. The distinguishing feature with respect to claim1 can be identified as, the test model is ground truth model instead of a reference model.
CHAI as improved by ZHAO does not teach but FEVOLD teaches, the test model is ground truth model instead of a reference model (see ¶ [0110] The following steps take place as part of the UE-side retuning procedure in FIG. 5. [0111] 9. Data collection configuration (for retuning)—The UE is configured to collect measurements, including labels (i.e., ground truth), on signals transmitted by the network and/or sensor data available to the UE and is optionally provided assistance data for use in retuning).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI to incorporate the teachings of FEVOLD to include ground truth model instead of a reference model. Doing so would facilitate in achieving, quickly and efficiently resolving degradation in UE performance as suggested by FEVOLD (see ¶ [0037], e.g., As a result of AI/ML models being created from large, aggregate datasets, AI/ML models may experience performance fluctuations when deployed in different geographic locations, channel conditions, scenarios, or for all time, e.g., the model's performance could decrease over time. To resolve degradation in UE performance, there are three options: fallback to a legacy non-AI/ML mechanism; obtain or switch to a new model; or retune an existing model to perform well under conditions more specific than could be addressed by the more general base model. Additionally, the degradation should be resolved quickly and efficiently, and ideally before the AI/ML model's performance drops below that of legacy techniques.).
Regarding claim 17, CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 16.
CHAI further teaches, wherein the one or more processors, to perform the one or more actions, are configured to:
perform the one or more actions via a network management plane interface (see Fig, 3a, e.g., element AI model in OAM; ¶ [0099], e.g., In a design, the first information includes indication information of the at least one test set. For example, the base station sends the at least one test set to the terminal. The test set is generated by the base station, or is from another device. For example, the test set is from a core network device, OAM, remote intelligent communication, a wireless intelligent controller, an AI node, another device, or the like. Alternatively, the base station sends the indication information of the at least one test set to the terminal. The indication information indicates the terminal to select at least one test set from a plurality of predefined test sets to perform a test. The plurality of predefined test sets is stored in the terminal (for example, as specified in a protocol), or stored in a third-party node, where the third-party node is referred to as a test data management node).
Regarding claim 18, CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 16.
CHAI further teaches, wherein the testing component, to perform the one or more test operations, is configured to:
generate, using the one or more output parameters, evaluation data for one or more active testing scenarios;
provide, as an input to the test model, the evaluation data; and
obtain, via an output of the test model, one or more reference parameters indicating an expected behavior in the one or more active testing scenarios,
wherein the one or more performance parameters are based on a comparison of the one or more reference parameters to the one or more output parameters (see ¶ [0128], e.g., In response to receiving the second information sent by the terminal, the base station determines, based on the first test result indicated by the second information, whether each AI models participating in the test meets a performance goal. In a design, in response to the first test result fed back by the terminal indicating the output that is of the AI model and that is obtained based on the test set, in a case of supervised learning, the base station compares the output of the AI model with the corresponding label (namely, an accurate output) to determine an error between the output of the AI model and the corresponding label, and determines, based on the error between the output of the AI model and the corresponding label, whether the AI models participating in the test meets the performance goal. For example, in response to the error between the output of the AI model and the corresponding label being less than a specific threshold, the AI models participating in the test meets the performance goal. In response to the error between the output of the AI model and the corresponding label not being less than a specific threshold, the AI models participating in the test do not meet the performance goal.).
Regarding claim 19, CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 16.
CHAI further teaches, wherein the testing component is further configured to: transmit, to the wireless communication device, test data for one or more active testing scenarios,
wherein the testing component, to obtain the one or more output parameters, is configured to:
obtain the one or more output parameters based on transmitting the test data (see Fig. 7, e.g., element Base station, Terminal, 701, 702; ¶ [0124], e.g., Step 701: The base station sends the first information to the terminal, where the first information is used to determine at least one test set. ¶ [0125], e.g., Step 702: The terminal tests the AI model based on the at least one test set, to obtain a first test result).
Claim(s) 7, is rejected under 35 U.S.C. 103 as being unpatentable over CHAI in view of ZHAO and SUN and in further view of KHALILI et al., WO 2025031574 A1, (hereinafter KHALILI).
Regarding claim 7, CHAI as combined with ZHAO and SUN teaches the limitations of Claim 1.
CHAI as improved by ZHAO and SUN does not teach but KHALILI teaches, wherein the second embedded AI/ML model is a channel state information (CSI) compression model that is trained to compress CSI, and wherein the testing component, to perform the one or more actions, is configured to (see Fig. 4, e.g., element 130, 110a, 2. Notification of compression level; Pg. 14, lines 5-11, e.g., an autoencoder model with only one agent entity is assumed to be trained and deployed at the base station 120, 130 and the UE 110a. The compression configuration of the autoencoder may be based on the network conditions at the base station 120, such as the channel quality to all users connected to the base station 120 or the load at the base station 120. Hence the base station 120 may determine and share the compression level with the UE 110a. The base station may be further configured to share the mapping, between communication and computation resources available, and execution policy index):
transmit, to the wireless communication device, an indication to modify a compression level of the CSI compression model (see Pg. 14, lines 13-19, e.g., Upon receiving the compression level from the base station 120, the UE 110a based on its computational capability (e.g., depending on battery status) and the shared table determines the complexity level (of compression/decompression process), and hence the execution policy from the shared execution policy table, for instance, the table shown in figure 2. The CSI feedback at the UE 110a may be compressed based on this decision. The UE 110a may share the compressed output and the associated execution policy to enable decompression at the base station as part of a CSI report (see step 6 of figure 4)).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified AI/ML model of CHAI to incorporate the teachings of KHALILI to include AI/ML model as a channel state information (CSI) compression model that is trained to compress CSI. Doing so would facilitate in achieving, allowing adapting to the learning procedure at runtime to the current communication and computation resources/capabilities as suggested by KHALILI (see Pg. 10, lines 15-21, e.g., Thus, according to embodiments disclosed herein the agent entities 1 lOa-c and the controller entity 130 may adapt the level of computation by dynamically adapting the complexity of the ML models 11 la-c during run-time. In further embodiments, the agent entities 1 lOa-c may adjust for different levels of communication resources (i.e. communication capabilities) by dynamically adapting the compression of the output of each ML model 11 la-c of each agent entity 1 lOa-c. In other words, embodiments disclosed herein allow adapting the learning procedure at runtime to the current communication and computation resources/capabilities.).
Claim(s) 13, is rejected under 35 U.S.C. 103 as being unpatentable over CHAI in view of ZHAO, SUN, FEVOLD and in further view of GUAN et al., WO 2024098398 A1, (hereinafter GUAN).
Regarding claim 13, CHAI as combined with ZHAO, SUN and FEVOLD teaches the limitations of Claim 12.
CHAI as improved by ZHAO, SUN and FEVOLD does not teach but GUAN teaches, further comprising: maintaining a counter indicating a quantity of instances of the wireless communication device switching between the main operation mode and the one or more alternate operation modes, wherein the quantity of instances is included in the one or more performance parameters (see Pg. 19, ¶ [0085], per each AI/ML model or per group of AI/ML models, at least one of the followings may be configured: configuration of the model monitoring method, condition, threshold, timer, counter, start/suspend/end/control signaling for model monitoring, periodicity/duty cycle/time duration/time offset configuration for model monitoring, capability signaling to indicate whether the entity 320 is able to perform the model monitoring method. In some embodiments, at least one of the following capability may also be indicated: the supported number of AI/ML models can be monitored, whether the entity 320 can monitor more than one AI/ML model, or whether to support a default AI/ML model).
It would have been obvious to one of ordinary skill in the art before the effective
filing date of the claimed invention to have modified teachings of CHAI and FEVOLD to incorporate the teachings of GUAN to include counter indicating a quantity of instances of the wireless communication device switching between the main operation mode and the one or more alternate operation modes. Doing so would facilitate in achieving, counting number of AI/ML model failure instances before declaring the AI/ML model failure as suggested by GUAN (see ¶ [0081], e.g., Alternatively, the second configuration may include a counter. For example, the counter may be used to count the number of AI/ML model failure instances. The counter may be configured to count the number of AI/ML model failure instances before declaring the AI/MLmodel failure. Alternatively, the counter may count the consecutive number of AI/ML model failure instance before declaring AI/ML model failure. In some other embodiments, the counter may count the ratio of AI model failure instances to the AI/ML model success instances. For example, if the failure instance of the first AI/ML model occurs, the counter may start or restarted. A value of the counter may be increased by 1 for a following AI/ML model failure instance. If the value of the counter exceeds a maximum value, the AI/ML model failure can be declared, and the corresponding action may be requested.).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to POONAM SHARMA whose telephone number is (571)272-6579. The examiner can normally be reached Monday thru 8:30-5:30 pm, ET.
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, Kevin Bates can be reached at (571) 272-3980. 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.
/POONAM SHARMA/Examiner, Art Unit 2472
/KEVIN T BATES/Supervisory Patent Examiner, Art Unit 2472
Prosecution Insights