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
Regarding First Argument:
Applicant argues in substance that amended claim language overcomes previous prior art rejections.
Examiner respectfully disagrees. Applicant asserts that prior art is dealing with inference on a hand over and claim language is directed towards cellular technology selection, however the steps disclosed by the prior art reads on the claim language, as currently written, due to the broad language of the claim. One of ordinary skill in the art would know that the 5G standard contains provisions for several different RAT communications occurring simultaneously and in parallel, therefore selecting a cell for handover selecting a RAT are within the same inventive scope. Prior art references a quality of service as well as a user experience quality which reads on a minimum signal strength metric and the reinforcement learning is disclosed in [¶0377] as cited below. For at least these reasons, the rejection is proper and thus maintained.
Claim Rejections - 35 USC § 102
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Huangfu (US 20230179490 A1) hereafter Huangfu.
Regarding Claim 1:
Huangfu discloses:
A method, ([¶Abstract] This application provides a method) comprising: receiving, by a system, a service request from a user equipment; based on the service request,([¶0015] the first communication apparatus may perform the AI inference task based on a request of the second communication apparatus. In other words, in this case, the method further includes: the first communication apparatus receives a first request sent by the second communication apparatus, where the first request is used to request the inference result for the decision-making of the first task, and the first request includes an identifier of the first task.) determining, by the system, respective signal strengths of respective radio access technologies of multiple radio access technologies being used for cellular broadband communications; ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.) wherein the respective radio access technologies comprise respective cellular standards via which user equipment communications are able to occur both simultaneously and parallel; ([¶0205] The terminal device may be a device that provides voice/data connectivity for a user, for example, a handheld device that has a wireless connection function or an in-vehicle device. Currently, some examples of terminals are: a mobile phone, a tablet computer, a notebook computer, a handheld computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote surgery (remote medical surgery), a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device having a wireless communication function, a computing device or another processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5G network, a terminal device in an evolved public land mobile communication network (PLMN), or the like. This is not limited in this embodiment of this application.[¶0446] A person skilled in the art may understand that the terminal device may include a plurality of baseband processors to adapt to different network standards, and the terminal device may include a plurality of central processing units to enhance a processing capability of the terminal device) identifying, by the system, a subset of the respective radio access technologies for which a minimum signal strength criterion is satisfied; ([¶0267] In this application, the input data may be terminal device-related data, for example, include but is not limited to one or more types of the following data: [¶0268] radio resource control (RRC) signaling, a call setup success rate, a radio frequency link failure indication, an access failure rate, a handover failure rate, a call success rate, a handover success rate, a call drop rate, voice quality, a session success rate, service setup time, a session drop rate, data flow quality, a jitter, a delay, a throughput, a service rate, a service rate requirement, quality of service, user experience quality, and a random access report.) processing, by the system, a subset of the respective signal strengths corresponding to the subset of the respective radio access technologies using a machine learning model to determine a selected radio access technology of the multiple radio access technologies, ([¶0011] For example, when an inference task for network behavior (for example, mobility management) of a terminal device is performed, the initiating network element may be the terminal device, may be an access network device serving the terminal device, or may be a core network device of a network in which the terminal device is located. This is not particularly limited in this application.) wherein the machine learning model is trained to determine the selected radio access technology based on an energy efficiency metric of the system and based on resource allocation of the system, ([¶0377] the input data is a network status and network performance, and the output is a network decision. When the reinforcement learning is used to enhance the communication system, a small range of feasible configurations of the system may be explored to automatically improve system performance. The improvement of the system performance may be long-time and is enabled by a system parameter configuration dominated by reinforcement learning.[¶0261] For another example, energy efficiency information is used as the input. The output is to disable or enable a cell. The network performance is an effect obtained after the network decision is taken, and corresponds to the reward in the reinforcement learning. The reward may be set to system performance within a period of time. That is because energy efficiency of a surrounding area of the cell may be improved or reduced due to the enabling or disabling of the cell. With this feedback, the AI model may be used to explore for more network decisions that can make the system better. For example, load and energy efficiency of a specific cell and surrounding cells are input into the AI model. The AI model outputs a network decision indicating to disable the cell or reduce maximum downlink transmit power of the cell. After a period of time, statistics are collected on energy efficiency-related indicators of the cell and a few surrounding cells. The reward may be designed as follows: Reward=energy efficiency of the surrounding cells. A larger value of the reward indicates a more correct network decision. The reinforcement learning tends to increase the reward. This maximizes the energy efficiency of the few cells, and each cell may focus only on a neighboring cell, of the cell, at this location.) and wherein the machine learning model comprises a reinforcement learning model; ([¶0256] The AI model may be alternatively obtained based on deep reinforcement learning. The deep reinforcement learning is a combination of the deep neural network and the deep learning. and communicating, by the system, with the user equipment via the selected radio access technology. ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.)
Regarding Claim 2:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein at least one of the respective signal strengths comprises a reference signal received power value. ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.)
Regarding Claim 3:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein at least one of the respective signal strengths comprises a received signal strength indicator value. ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.)
Regarding Claim 4:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein, when receiving the service request from the user equipment occurs, at least some of the cellular broadband communications are being conducted with the user equipment for usage of a first application of the user equipment, wherein the service request corresponds to a second application of the user equipment, and wherein at least one of the respective signal strengths comprises a signal-to-interference and noise ratio value. ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.)
Regarding Claim 5:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the machine learning model is trained to favor decreasing the energy efficiency metric of the system while satisfying the resource allocation of the system. ([¶0261] For another example, energy efficiency information is used as the input. The output is to disable or enable a cell. The network performance is an effect obtained after the network decision is taken, and corresponds to the reward in the reinforcement learning. The reward may be set to system performance within a period of time. That is because energy efficiency of a surrounding area of the cell may be improved or reduced due to the enabling or disabling of the cell. With this feedback, the AI model may be used to explore for more network decisions that can make the system better. For example, load and energy efficiency of a specific cell and surrounding cells are input into the AI model. The AI model outputs a network decision indicating to disable the cell or reduce maximum downlink transmit power of the cell. After a period of time, statistics are collected on energy efficiency-related indicators of the cell and a few surrounding cells. The reward may be designed as follows: Reward=energy efficiency of the surrounding cells. A larger value of the reward indicates a more correct network decision. The reinforcement learning tends to increase the reward. This maximizes the energy efficiency of the few cells, and each cell may focus only on a neighboring cell, of the cell, at this location.)
Regarding Claim 6:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the machine learning model is trained to determine the selected radio access technology ([¶0264] The AI model may be pre-trained, that is, the input data may be irrelevant to the AI model, and is merely an observation on the network. Alternatively, the input data may be used in an AI model update (or training) process, that is, the input data may be alternatively related to the AI model. The AI model outputs a decision, to cause a change of the network status, and further cause a change of the input data. In this case, the input data may form a correspondence with the output of the AI model, to assist the AI model that is based on the reinforcement learning.)based on a service level agreement that corresponds to a performance metric applicable to the cellular broadband communications. ( [¶0061] the radio resource management policy may include but is not limited to power control, channel allocation, scheduling, handover, access control, load control, end-to-end quality of service QoS, adaptive code modulation, or the like.)
Regarding Claim 7:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the cellular broadband communications are first cellular broadband communications, and further comprising: updating the offline trained machine learning model according to online reinforcement learning based on feedback resulting from in-field operations of conducting second broadband cellular communications. ([¶0264] the input data may be used in an AI model update (or training) process, that is, the input data may be alternatively related to the AI model. The AI model outputs a decision, to cause a change of the network status, and further cause a change of the input data. In this case, the input data may form a correspondence with the output of the AI model, to assist the AI model that is based on the reinforcement learning.)
Regarding Claim 8:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the machine learning model is trained to determine the selected radio access technology based on satisfying at least one of a requested quality-of-service metric associated with the user equipment, a data rate associated with the user equipment, or a contract associated with the user equipment. ( [¶0061] the radio resource management policy may include but is not limited to power control, channel allocation, scheduling, handover, access control, load control, end-to-end quality of service QoS, adaptive code modulation, or the like.)
Regarding Claim 9:
A system, comprising: at least one processor; and at least one memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, ([¶0155] a processor and a memory. The processor is configured to read instructions stored in the memory) comprising: receiving a service request from a user equipment, wherein the service request corresponds to facilitating cellular broadband communications; based on the service request, ([¶0015] the first communication apparatus may perform the AI inference task based on a request of the second communication apparatus. In other words, in this case, the method further includes: the first communication apparatus receives a first request sent by the second communication apparatus, where the first request is used to request the inference result for the decision-making of the first task, and the first request includes an identifier of the first task.) determining respective signal strengths of respective radio access technologies of a group of multiple radio access technologies usable for the cellular broadband communications; ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.) wherein the respective radio access technologies comprise respective cellular standards via which user equipment communications are able to occur; ([¶0205] The terminal device may be a device that provides voice/data connectivity for a user, for example, a handheld device that has a wireless connection function or an in-vehicle device. Currently, some examples of terminals are: a mobile phone, a tablet computer, a notebook computer, a handheld computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote surgery (remote medical surgery), a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device having a wireless communication function, a computing device or another processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5G network, a terminal device in an evolved public land mobile communication network (PLMN), or the like. This is not limited in this embodiment of this application.[¶0446] A person skilled in the art may understand that the terminal device may include a plurality of baseband processors to adapt to different network standards, and the terminal device may include a plurality of central processing units to enhance a processing capability of the terminal device) identifying a subset of the respective radio access technologies for which corresponding signal strengths satisfy a minimum signal strength criterion; ([¶0267] In this application, the input data may be terminal device-related data, for example, include but is not limited to one or more types of the following data: [¶0268] radio resource control (RRC) signaling, a call setup success rate, a radio frequency link failure indication, an access failure rate, a handover failure rate, a call success rate, a handover success rate, a call drop rate, voice quality, a session success rate, service setup time, a session drop rate, data flow quality, a jitter, a delay, a throughput, a service rate, a service rate requirement, quality of service, user experience quality, and a random access report.) processing the corresponding signal strengths of the subset of the respective radio access technologies with a trained machine learning model to determine a selected radio access technology of the group of multiple radio access technologies, ([¶0011] For example, when an inference task for network behavior (for example, mobility management) of a terminal device is performed, the initiating network element may be the terminal device, may be an access network device serving the terminal device, or may be a core network device of a network in which the terminal device is located. This is not particularly limited in this application.)wherein the trained machine learning model is configured to determine the selected radio access technology based on an energy efficiency metric of the system and based on resource allocation of the system; ([¶0377] the input data is a network status and network performance, and the output is a network decision. When the reinforcement learning is used to enhance the communication system, a small range of feasible configurations of the system may be explored to automatically improve system performance. The improvement of the system performance may be long-time and is enabled by a system parameter configuration dominated by reinforcement learning.[¶0261] For another example, energy efficiency information is used as the input. The output is to disable or enable a cell. The network performance is an effect obtained after the network decision is taken, and corresponds to the reward in the reinforcement learning. The reward may be set to system performance within a period of time. That is because energy efficiency of a surrounding area of the cell may be improved or reduced due to the enabling or disabling of the cell. With this feedback, the AI model may be used to explore for more network decisions that can make the system better. For example, load and energy efficiency of a specific cell and surrounding cells are input into the AI model. The AI model outputs a network decision indicating to disable the cell or reduce maximum downlink transmit power of the cell. After a period of time, statistics are collected on energy efficiency-related indicators of the cell and a few surrounding cells. The reward may be designed as follows: Reward=energy efficiency of the surrounding cells. A larger value of the reward indicates a more correct network decision. The reinforcement learning tends to increase the reward. This maximizes the energy efficiency of the few cells, and each cell may focus only on a neighboring cell, of the cell, at this location.) and communicating with the user equipment using the selected radio access technology. ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.)
Regarding Claim 10:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the trained machine learning model is a pre-trained machine learning model, and wherein the operations further comprise: training a machine learning model to produce the pre-trained machine learning model according to a single-agent reinforcement learning process, ([¶0264] The AI model may be pre-trained, that is, the input data may be irrelevant to the AI model, and is merely an observation on the network. Alternatively, the input data may be used in an AI model update (or training) process, that is, the input data may be alternatively related to the AI model. The AI model outputs a decision, to cause a change of the network status, and further cause a change of the input data. In this case, the input data may form a correspondence with the output of the AI model, to assist the AI model that is based on the reinforcement learning.) wherein a state space of the single-agent reinforcement learning process comprises the group of multiple radio access technologies, respective power consumption values of respective multiple radio access technologies of the group of multiple radio access technologies, and respective channel resources of the respective multiple radio access technologies. ([¶0011] For example, when an inference task for network behavior (for example, mobility management) of a terminal device is performed, the initiating network element may be the terminal device, may be an access network device serving the terminal device, or may be a core network device of a network in which the terminal device is located. This is not particularly limited in this application.)wherein the trained machine learning model is configured to determine the selected radio access technology based on an energy efficiency metric of the system and based on resource allocation of the system; ([¶0377] the input data is a network status and network performance, and the output is a network decision. When the reinforcement learning is used to enhance the communication system, a small range of feasible configurations of the system may be explored to automatically improve system performance. The improvement of the system performance may be long-time and is enabled by a system parameter configuration dominated by reinforcement learning. [¶0261] For another example, energy efficiency information is used as the input. The output is to disable or enable a cell. The network performance is an effect obtained after the network decision is taken, and corresponds to the reward in the reinforcement learning. The reward may be set to system performance within a period of time. That is because energy efficiency of a surrounding area of the cell may be improved or reduced due to the enabling or disabling of the cell. With this feedback, the AI model may be used to explore for more network decisions that can make the system better. For example, load and energy efficiency of a specific cell and surrounding cells are input into the AI model. The AI model outputs a network decision indicating to disable the cell or reduce maximum downlink transmit power of the cell. After a period of time, statistics are collected on energy efficiency-related indicators of the cell and a few surrounding cells. The reward may be designed as follows: Reward=energy efficiency of the surrounding cells. A larger value of the reward indicates a more correct network decision. The reinforcement learning tends to increase the reward. This maximizes the energy efficiency of the few cells, and each cell may focus only on a neighboring cell, of the cell, at this location.)
Regarding Claim 11:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the operations further comprise: maintaining a data store that comprises respective transmission thresholds for the respective radio access technologies, and respective target spectral efficiencies of the respective radio access technologies; ([¶0022] In the communication system, a fifth communication apparatus configured to store data used for AI inference (for example, input data of the AI model) may be configured, and that the first communication apparatus obtains first data) and wherein determining the selected radio access technology of the group of multiple radio access technologies is based on determining that the selected radio access technology is configured to schedule the user equipment to use the selected radio access technology to achieve a requested throughput. ([¶0061] the radio resource management policy may include but is not limited to power control, channel allocation, scheduling, handover, access control, load control, end-to-end quality of service QoS, adaptive code modulation, or the like.)
Regarding Claim 12:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the operations further comprise: in response to an update criterion being determined to be satisfied, updating the respective transmission thresholds for the respective radio access technologies based on information received from respective link adaptation components of the respective radio access technologies. ([¶0199] The processing network element receives channel data and trains (or updates) the AI model of the processing network element. Then, the processing network element may send the updated AI model to the storage network element, that is, the storage network element may store not only the training data, but also the AI model, or even an intermediate result of the training, such as a training gradient. “Storing the AI model” may be understood as storing a related parameter of the AI model, a parameter of a neural network, a parameter of a machine learning algorithm, and the like.)
Regarding Claim 13:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the selected radio access technology is a first selected radio access technology, and wherein the operations further comprise: after determining the selected radio access technology of the group of multiple radio access technologies, determining, by the system and with the trained machine learning model, a second selected radio access technology of the group of multiple radio access technologies, wherein the second selected radio access technology corresponds to a better energy efficiency criterion with respect to the user equipment than the first selected radio access technology; and transferring the user equipment from the first selected radio access technology to the second selected radio access technology. ([¶0111] the first data may further include related information of the cell in which the terminal device is located, for example, a historical alarm log, a device configuration log, a device log, a resource utilization record, a network performance monitoring record, link availability, a call drop rate, a throughput, a network element interface-related indicator, authentication information, a crowd gathering heat map, a crowd movement trajectory, a crowd density, notification area-related signaling overheads, power consumption, cell coverage, physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency. [¶0261] For another example, energy efficiency information is used as the input. The output is to disable or enable a cell. The network performance is an effect obtained after the network decision is taken, and corresponds to the reward in the reinforcement learning. The reward may be set to system performance within a period of time. That is because energy efficiency of a surrounding area of the cell may be improved or reduced due to the enabling or disabling of the cell. With this feedback, the AI model may be used to explore for more network decisions that can make the system better. For example, load and energy efficiency of a specific cell and surrounding cells are input into the AI model. The AI model outputs a network decision indicating to disable the cell or reduce maximum downlink transmit power of the cell. After a period of time, statistics are collected on energy efficiency-related indicators of the cell and a few surrounding cells. The reward may be designed as follows: Reward=energy efficiency of the surrounding cells. A larger value of the reward indicates a more correct network decision. The reinforcement learning tends to increase the reward. This maximizes the energy efficiency of the few cells, and each cell may focus only on a neighboring cell, of the cell, at this location.)
Regarding Claim 14:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the operations further comprise: training a machine learning model to produce the trained machine learning model according to a reinforcement learning process, wherein the reinforcement learning process is configured to receive a positive reward when an energy consumption associated with a state of the reinforcement learning process is less than an average energy efficiency for a load, and wherein the reinforcement learning process is configured to receive a negative reward when the energy consumption associated with the state of the reinforcement learning process is greater than the average energy efficiency for the load. ([¶0261] For another example, energy efficiency information is used as the input. The output is to disable or enable a cell. The network performance is an effect obtained after the network decision is taken, and corresponds to the reward in the reinforcement learning. The reward may be set to system performance within a period of time. That is because energy efficiency of a surrounding area of the cell may be improved or reduced due to the enabling or disabling of the cell. With this feedback, the AI model may be used to explore for more network decisions that can make the system better. For example, load and energy efficiency of a specific cell and surrounding cells are input into the AI model. The AI model outputs a network decision indicating to disable the cell or reduce maximum downlink transmit power of the cell. After a period of time, statistics are collected on energy efficiency-related indicators of the cell and a few surrounding cells. The reward may be designed as follows: Reward=energy efficiency of the surrounding cells. A larger value of the reward indicates a more correct network decision. The reinforcement learning tends to increase the reward. This maximizes the energy efficiency of the few cells, and each cell may focus only on a neighboring cell, of the cell, at this location.)
Regarding Claim 15:
Huangfu discloses:
A non-transitory computer-readable medium comprising instructions that, in response to execution, cause a system comprising at least one processor to perform operations,([¶0162] a computer readable medium is provided. The computer readable medium stores a computer program (which may also be referred to as code or an instruction). When the computer program runs on a computer, the computer is enabled to perform the method in any one of the first aspect or the second aspect and the possible implementations thereof.) comprising: based on receiving a service request from a user equipment, ([¶0015] the first communication apparatus may perform the AI inference task based on a request of the second communication apparatus. In other words, in this case, the method further includes: the first communication apparatus receives a first request sent by the second communication apparatus, where the first request is used to request the inference result for the decision-making of the first task, and the first request includes an identifier of the first task.) wherein the respective radio access technologies comprise respective cellular standards via which user equipment communications are able to occur; ([¶0205] The terminal device may be a device that provides voice/data connectivity for a user, for example, a handheld device that has a wireless connection function or an in-vehicle device. Currently, some examples of terminals are: a mobile phone, a tablet computer, a notebook computer, a handheld computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote surgery (remote medical surgery), a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device having a wireless communication function, a computing device or another processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5G network, a terminal device in an evolved public land mobile communication network (PLMN), or the like. This is not limited in this embodiment of this application.[¶0446] A person skilled in the art may understand that the terminal device may include a plurality of baseband processors to adapt to different network standards, and the terminal device may include a plurality of central processing units to enhance a processing capability of the terminal device) determining respective signal strengths of respective radio access technologies of a group of multiple radio access technologies; ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.)identifying a subset of the respective radio access technologies for which a corresponding subset of the respective signal strengths satisfies a minimum signal strength criterion; ([¶0267] In this application, the input data may be terminal device-related data, for example, include but is not limited to one or more types of the following data: [¶0268] radio resource control (RRC) signaling, a call setup success rate, a radio frequency link failure indication, an access failure rate, a handover failure rate, a call success rate, a handover success rate, a call drop rate, voice quality, a session success rate, service setup time, a session drop rate, data flow quality, a jitter, a delay, a throughput, a service rate, a service rate requirement, quality of service, user experience quality, and a random access report.) processing the respective signal strengths of the subset of the respective radio access technologies with an artificial intelligence model to determine a selected radio access technology of the group of multiple radio access technologies, ([¶0011] For example, when an inference task for network behavior (for example, mobility management) of a terminal device is performed, the initiating network element may be the terminal device, may be an access network device serving the terminal device, or may be a core network device of a network in which the terminal device is located. This is not particularly limited in this application.)wherein the artificial intelligence model is trained to determine the selected radio access technology based on an energy efficiency metric of the system and based on resource allocation of the system; ([¶0377] the input data is a network status and network performance, and the output is a network decision. When the reinforcement learning is used to enhance the communication system, a small range of feasible configurations of the system may be explored to automatically improve system performance. The improvement of the system performance may be long-time and is enabled by a system parameter configuration dominated by reinforcement learning.[¶0261] For another example, energy efficiency information is used as the input. The output is to disable or enable a cell. The network performance is an effect obtained after the network decision is taken, and corresponds to the reward in the reinforcement learning. The reward may be set to system performance within a period of time. That is because energy efficiency of a surrounding area of the cell may be improved or reduced due to the enabling or disabling of the cell. With this feedback, the AI model may be used to explore for more network decisions that can make the system better. For example, load and energy efficiency of a specific cell and surrounding cells are input into the AI model. The AI model outputs a network decision indicating to disable the cell or reduce maximum downlink transmit power of the cell. After a period of time, statistics are collected on energy efficiency-related indicators of the cell and a few surrounding cells. The reward may be designed as follows: Reward=energy efficiency of the surrounding cells. A larger value of the reward indicates a more correct network decision. The reinforcement learning tends to increase the reward. This maximizes the energy efficiency of the few cells, and each cell may focus only on a neighboring cell, of the cell, at this location.)and communicating with the user equipment using the selected radio access technology. ([¶0035] a measurement report of a primary serving cell, a measurement report of a neighboring cell, channel power, interference power, noise power, a channel quality indicator, reference signal received power, reference signal received quality, a received signal strength indicator, a signal to interference plus noise ratio, a minimization of drive tests (MDT) report, a channel complex value, a channel value real part, a channel value imaginary part, a channel power delay spectrum, a channel angle power spectrum, a channel multipath angle of arrival, a channel multipath angle of departure, a channel multipath pitch of arrival, and a channel multipath pitch of departure.)
Regarding Claim 16:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the artificial intelligence model comprises a group of long-short term memory models, and wherein respective long-short term memory models of the group of long-short term memory models correspond to the respective radio access technologies. ([¶0269] the input data may be cell-related data, for example, include but is not limited to one or more types of the following data: [¶0270] physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency. [¶0198] The output-side configuration may include but is not limited to one or more of the following: an output softmax function, sampling manner configuration, whether storage is required, hyperparameter modification, whether output is followed by a long short-term memory (LSTM) network, parameter output of the model, and gradient output of an optimizer.)
Regarding Claim 17:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the operations further comprise: storing respective power consumption models for the respective radio access technologies, wherein the respective power consumption models comprise respective amounts of power consumed in respective low-power states. ([¶0269] the input data may be cell-related data, for example, include but is not limited to one or more types of the following data: [¶0270] physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency.)
Regarding Claim 18:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the operations further comprise: storing respective power consumption models for the respective radio access technologies, wherein at least two power consumption models of the respective power consumption models differ in terms of a number of power consumption states. ([¶0269] the input data may be cell-related data, for example, include but is not limited to one or more types of the following data: [¶0270] physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency.)
Regarding Claim 19:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the respective radio access technologies correspond to use of respective power amplifiers that have different energy consumption, and wherein the artificial intelligence model is configured to perform load balancing amongst the different radio access technologies that comprise the user equipment. ([¶0082] The first task includes mobility load balancing optimization of a cell. [¶0087] In addition, the first data may further include related information of the cell, for example, a historical alarm log, a device configuration log, a device log, a resource utilization record, a network performance monitoring record, link availability, a call drop rate, a throughput, a network element interface-related indicator, authentication information, a crowd gathering heat map, a crowd movement trajectory, a crowd density, notification area-related signaling overheads, power consumption, cell coverage, physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency.)
Regarding Claim 20:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein a first base station is configured to provide the group of multiple radio access technologies, and wherein a radio access network intelligent controller is configured to perform load balancing among respective base stations of a group of base stations that comprises the first base station based on current load conditions and a traffic prediction model. ([¶0082] The first task includes mobility load balancing optimization of a cell. [¶0087] In addition, the first data may further include related information of the cell, for example, a historical alarm log, a device configuration log, a device log, a resource utilization record, a network performance monitoring record, link availability, a call drop rate, a throughput, a network element interface-related indicator, authentication information, a crowd gathering heat map, a crowd movement trajectory, a crowd density, notification area-related signaling overheads, power consumption, cell coverage, physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency.)
Regarding Claim 21:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the energy efficient metric is based on, a first combination of, for respective channels of the respective radio access technologies, respective measures of whether the respective channels are in use, respective first amounts of power consumption of the respective radio access technologies, and respective channel resources in use, ([¶0048] In addition, the first data may further include related information of a to-be-accessed cell, for example, a historical alarm log, a device configuration log, a device log, a resource utilization record, a network performance monitoring record, link availability, a call drop rate, a throughput, a network element interface-related indicator, authentication information, a crowd gathering heat map, a crowd movement trajectory, a crowd density, notification area-related signaling overheads, power consumption, cell coverage, physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency.) and a second combination of, for the respective radio access technologies, respective measures of whether the respective radio access technologies are idle, and respective second amounts of power consumption of the respective radio access technologies while in an idle mode. ([¶0048] In addition, the first data may further include related information of a to-be-accessed cell, for example, a historical alarm log, a device configuration log, a device log, a resource utilization record, a network performance monitoring record, link availability, a call drop rate, a throughput, a network element interface-related indicator, authentication information, a crowd gathering heat map, a crowd movement trajectory, a crowd density, notification area-related signaling overheads, power consumption, cell coverage, physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency.)
Regarding Claim 22:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the respective channel resources in use comprise respective numbers of subcarriers with a given modulation coding scheme, and wherein the system satisfies an orthogonal frequency-division multiple access criterion. ([¶0054] the first data may further include related information of the first cell, for example, a historical alarm log, a device configuration log, a device log, a resource utilization record, a network performance monitoring record, link availability, a call drop rate, a throughput, a network element interface-related indicator, authentication information, a crowd gathering heat map, a crowd movement trajectory, a crowd density, notification area-related signaling overheads, power consumption, cell coverage, physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency. [¶0061] In addition, by way of example rather than limitation, the radio resource management policy may include but is not limited to power control, channel allocation, scheduling, handover, access control, load control, end-to-end quality of service QoS, adaptive code modulation, or the like.)
Regarding Claim 23:
Huangfu discloses the limitations of parent claims.
Huangfu discloses:
wherein the energy efficient metric is based on a first constraint that resources assigned to different user equipment cannot exceed a maximum amount of resources available for all user equipment, and wherein the energy efficient metric is based on a second constraint that, for respective user equipment of the different user equipment, respective key performance indicator levels are satisfied. ([¶0054] the first data may further include related information of the first cell, for example, a historical alarm log, a device configuration log, a device log, a resource utilization record, a network performance monitoring record, link availability, a call drop rate, a throughput, a network element interface-related indicator, authentication information, a crowd gathering heat map, a crowd movement trajectory, a crowd density, notification area-related signaling overheads, power consumption, cell coverage, physical resource block (PRB) utilization, a quantity of active users, a random access quantity, a cell type, a transmit power class, a quantity of available resources, cell load, a traffic type, a cell location, cell power consumption, a cell capacity, and cell energy efficiency. [¶0061] In addition, by way of example rather than limitation, the radio resource management policy may include but is not limited to power control, channel allocation, scheduling, handover, access control, load control, end-to-end quality of service QoS, adaptive code modulation, or the like.)
Conclusion
THIS ACTION IS MADE FINAL. 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 HUGH MARK ASHLEY whose telephone number is (571)272-0199. The examiner can normally be reached M-F 8-430.
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, Asad Nawaz can be reached at (571) 272-3988. 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.
/HUGH MARK ASHLEY/Examiner, Art Unit 2463
/ASAD M NAWAZ/Supervisory Patent Examiner, Art Unit 2463