Transmission power control method and apparatus, terminal device

Abstract

The application discloses a sending power regulation method and device and a terminal device. The method comprises the following steps: acquiring CSI of a plurality of subcarriers of a WiFi signal, and determining the distance between a first terminal device and a user according to the CSI; if the distance is less than a preset distance, reducing the sending power of a mobile cellular signal to a target power threshold or below, and restoring the sending power of the mobile cellular signal when the distance is greater than or equal to the preset distance; if the distance is greater than or equal to the preset distance, the sending power of the mobile cellular signal is continuously maintained. In this way, the distance between the first terminal device and the user is determined in real time according to WiFi sensing, so as to determine whether the sending power of the mobile cellular signal needs to be reduced to the target power threshold or below according to the size relationship between the distance and the preset distance, thereby realizing flexible regulation of the SAR of the terminal device while ensuring the successful transmission of the mobile cellular signal.

Description

Technical Field

[0001] This application relates to the field of wireless communication, specifically to a method and apparatus for controlling transmission power, and a terminal device. Background Technology

[0002] With the widespread use of electronic products and the rapid development of wireless communication technology, the impact of electromagnetic radiation on human health and the environment has attracted increasing attention. To ensure the safety of wireless communication and avoid adverse effects of electromagnetic radiation on users, government departments and relevant telecommunications agencies in various countries have standardized indicators of the impact of electromagnetic radiation on the human body, namely the Specific Absorption Rate (SAR). A lower SAR value indicates a smaller impact on the human body; conversely, a higher SAR value indicates a greater impact.

[0003] With the increasing emphasis and adoption of mandatory SAR standards, the requirements for SAR reduction solutions are also growing. Common solutions for balancing SAR and uplink communication include: using SAR sensors to detect the approach of a person and reducing transmission power if they are detected; improving antenna structure and layout to directly reduce the intensity of electromagnetic wave energy absorption by the human body; and using existing sensors such as earpieces to detect the approach of a person and directly reduce the transmission power of all antennas. However, these solutions usually require the use of sensors or the redesign of antenna structure and layout, resulting in certain hardware and design costs. Additionally, some solutions directly reduce the transmission power of the device to achieve SAR reduction, but reducing transmission power may also lead to signal transmission failure, causing communication failure and affecting communication reliability. Summary of the Invention

[0004] This application provides a method and apparatus for controlling transmit power, as well as a terminal device, in order to solve the problem of how to achieve flexible control of SAR while ensuring successful mobile cellular signal transmission.

[0005] In a first aspect, a transmission power regulation method according to this application is applied to a first terminal device, comprising:

[0006] The channel state information (CSI) of multiple subcarriers of the Wi-Fi signal is obtained, and the distance between the first terminal device and the user is determined based on the CSI of the multiple subcarriers.

[0007] If the distance between the first terminal device and the user is less than a preset distance, the transmission power of the mobile cellular signal will be reduced to a target power threshold or below, and the transmission power of the mobile cellular signal will be restored when the distance between the first terminal device and the user is greater than or equal to the preset distance again. The target power threshold is the minimum transmission power required to ensure successful transmission of the mobile cellular signal.

[0008] If the distance between the first terminal device and the user is greater than or equal to the preset distance, the transmission power of the mobile cellular signal will continue to be maintained.

[0009] Based on this, this application can determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers of the WiFi signal, and then determine whether it is necessary to reduce the transmission power of the mobile cellular signal to the target power threshold based on the relationship between the distance and the preset distance.

[0010] If the distance is less than the preset distance, it means that the user is very close to the first terminal device. In order to ensure the successful transmission of mobile cellular signals while avoiding the impact of electromagnetic radiation from the first terminal device on the user, this application can reduce the transmission power of mobile cellular signals to the target power threshold, thereby minimizing the SAR of the first terminal device while ensuring the reliability of mobile cellular communication.

[0011] Of course, this application can also reduce the transmission power of the mobile cellular signal to below the target power threshold. Although this may not guarantee successful mobile cellular signal transmission, it can significantly reduce the SAR of the first terminal device.

[0012] Then, when the distance is greater than or equal to the preset distance again, it indicates that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order to avoid reducing the reliability of mobile cellular communication due to insufficient transmission power, this application needs to restore the transmission power of the mobile cellular signal.

[0013] Finally, if the distance is greater than or equal to the preset distance, it means that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order not to affect the mobile cellular communication, this application needs to continue to maintain the transmission power of the mobile cellular signal without adjusting the transmission power.

[0014] Secondly, a transmission power regulation device according to this application is applied to a first terminal device, the device comprising:

[0015] The acquisition unit is used to acquire the channel state information (CSI) of multiple subcarriers of the Wi-Fi signal, and determine the distance between the first terminal device and the user based on the CSI of the multiple subcarriers.

[0016] The control unit is configured to reduce the transmission power of the mobile cellular signal to a target power threshold or below if the distance between the first terminal device and the user is less than a preset distance, and to restore the transmission power of the mobile cellular signal when the distance between the first terminal device and the user is greater than or equal to the preset distance again. The target power threshold is the minimum transmission power required to ensure successful transmission of the mobile cellular signal.

[0017] The control unit is further configured to maintain the transmission power of the mobile cellular signal if the distance between the first terminal device and the user is greater than or equal to the preset distance.

[0018] Thirdly, a terminal device according to this application includes a processor, a memory, and a computer program or instructions stored in the memory, wherein the processor executes the computer program or instructions to implement the steps of the method described in the first aspect above.

[0019] Fourthly, this application provides a computer-readable storage medium, wherein a computer program or instructions are stored on the computer-readable storage medium, and when executed by a processor, the computer program or instructions implement the steps of the method described in the first aspect above.

[0020] Fifthly, a computer program product of this application includes a computer program or instructions, wherein when the computer program or instructions are executed by a processor, they implement the steps of the method described in the first aspect above.

[0021] The beneficial effects of the technical solutions in the second to fifth aspects can be found in the technical effects of the technical solution in the first aspect, and will not be repeated here. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below.

[0023] Figure 1 This is a schematic diagram of the architecture of a transmission power regulation system according to an embodiment of this application;

[0024] Figure 2 This is a schematic flowchart of a transmission power regulation method according to an embodiment of this application;

[0025] Figure 3 This is a schematic diagram of a process for obtaining CSI of multiple subcarriers of a WiFi signal according to an embodiment of this application;

[0026] Figure 4 This is a schematic diagram of another embodiment of the present application for obtaining CSI of multiple subcarriers of WiFi signal;

[0027] Figure 5 This is a schematic diagram of another embodiment of the present application for obtaining CSI of multiple subcarriers of WiFi signal;

[0028] Figure 6 This is a schematic diagram of another embodiment of the present application for obtaining CSI of multiple subcarriers of WiFi signal;

[0029] Figure 7 This is a schematic diagram illustrating the process of obtaining CSI values ​​at different times according to an embodiment of this application;

[0030] Figure 8 This is a schematic diagram illustrating the process of obtaining a neural network model according to an embodiment of this application;

[0031] Figure 9 This is a functional unit block diagram of a transmission power regulation device according to an embodiment of this application;

[0032] Figure 10 This is a schematic diagram of the structure of a terminal device according to an embodiment of this application. Detailed Implementation

[0033] To help those skilled in the art better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the description of the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0034] It should be understood that the terms "first," "second," etc., used in the embodiments of this application are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, software, product, or device that includes a series of steps or units is not limited to the listed steps or units, but also includes steps or units not listed, or other steps or units inherent to these processes, methods, products, or devices.

[0035] The term "embodiment" as used in the embodiments of this application means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0036] In the embodiments of this application, "and / or" describes the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone; A and B exist simultaneously; B exists alone. Among them, A and B can be singular or plural.

[0037] In this embodiment, the symbol " / " can indicate that the preceding and following objects are in an "or" relationship. Alternatively, the symbol " / " can also represent a division sign, i.e., performing a division operation. For example, A / B can mean A divided by B.

[0038] In this embodiment, the symbols “*” or “·” can represent multiplication, i.e., performing a multiplication operation. For example, A*B or A·B can represent A multiplied by B.

[0039] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0040] In the embodiments of this application, "equal to" can be used with "greater than" and is applicable to technical solutions used when "greater than" is used; it can also be used with "less than" and is applicable to technical solutions used when "less than" is used. When "equal to" is used with "greater than", it is not used with "less than"; when "equal to" is used with "less than", it is not used with "greater than".

[0041] The technical solutions, beneficial effects, and related concepts involved in the embodiments of this application will be described in detail below.

[0042] I. Transmitting Power Control System

[0043] 1. Description

[0044] It should be noted that this application provides a transmission power control system. This system can determine the distance between the terminal device and the user in real time based on wireless fidelity (WiFi) sensing. In order to dynamically control the transmission power of the mobile cellular signal of the terminal device by the relationship between the distance and the preset distance, the system can flexibly control the SAR of the terminal device while ensuring mobile cellular communication, and minimize the impact of the electromagnetic radiation of the terminal device on the user.

[0045] Mobile cellular technology is a wireless communication technology that divides a geographical area into multiple small, cellular-like regions. Each cell has a network device responsible for providing wireless communication services within that cell. For example, mobile cellular signals can include 4th-Generation (4G) signals, 5G signals, and so on.

[0046] For example, such as Figure 1 As shown, the transmission power control system 10 includes a network device 110, an access point (AP) 120, a terminal device 130, and a user 140. The network device 110 and the terminal device 130 can exchange mobile cellular signals, and the access point 120 and the terminal device 130 can exchange WiFi signals.

[0047] Figure 1 This is merely an example of a network architecture for a transmit power regulation system and does not constitute a limitation on the network architecture of the transmit power regulation system in this application embodiment. For example, the transmit power regulation system 10 may also include other devices. Furthermore, the transmit power regulation system 10 may include multiple network devices, multiple terminal devices, multiple sites, etc.

[0048] The network device, access point, and terminal device of the embodiments of this application will be described in detail below.

[0049] 2. Network equipment

[0050] Network equipment can be a device with transceiver capabilities that provides terminal devices with access to General Packet Radio Service (GPRS), Long Term Evolution (LTE) systems, Advanced Long Term Evolution (LTE-A) systems, New Radio (NR) systems, evolution systems of NR systems, LTE-based Access to Unlicensed Spectrum (LTE-U) systems, NR-based Access to Unlicensed Spectrum (NR-U) systems, Non-Terrestrial Networks (NTN) systems, Universal Mobile Telecommunication System (UMTS), 6th-Generation (6G) communication systems, etc.

[0051] In some possible implementations, network devices can be responsible for radio resource management (RRM), quality of service (QoS) management, data compression and encryption, and data transmission and reception on the air interface side.

[0052] In some possible implementations, network devices may include base stations (BS) in a communication system or devices deployed in a radio access network (RAN) to provide wireless communication functions; that is, network devices may include devices in the RAN.

[0053] For example, devices in the RAN may include evolved node B (eNB or eNodeB) in the LTE communication system, next generation evolved node B (ng-eNB) in the NR communication system, next generation node B (gNB) in the NR communication system, master node (MN) in the dual connectivity architecture, and secondary node (SN) in the dual connectivity architecture, etc., without specific restrictions.

[0054] In some possible implementations, network devices may include devices in the core network (CN).

[0055] For example, devices in a CN may include access and mobility management function (AMF), user plane function (UPF), session management function (SMF), etc.

[0056] In some possible implementations, the network device can have mobility characteristics; for example, the network device can be a mobile device. Optionally, the network device can be a satellite or a balloon station. For example, the satellite can be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary Earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device can also be a base station located on land, water, or other similar locations.

[0057] In some possible implementations, network devices can provide services to a cell, and terminal devices within that cell can communicate with the network devices via transmission resources (such as spectrum resources). This cell can be a macrocell, small cell, metro cell, microcell, pico cell, or femto cell, etc.

[0058] 3. Access point

[0059] An access point can be an entity / unit / module / device that provides wireless local area network (WLAN) access to connected terminal devices via wireless media.

[0060] In some possible implementations, the access point can connect various wireless network clients to the Ethernet. It can be a network device with a WiFi chip or a device that supports various IEEE 802.11 protocol standards; there are no specific restrictions on this.

[0061] For example, the access point can be a device that supports IEEE 802.11ac, IEEE 802.11n, IEEE 802.11g, IEEE 802.11b, IEEE 802.11ax, IEEE 802.11be, and next-generation WLAN protocol standards.

[0062] For example, access points may include centralized controllers, base stations (BS), base transceiver stations (BTS), site controllers, and switches.

[0063] In some possible implementations, the access point may include a device with wireless communication capabilities (or a device with transceiver capabilities), such as a chip system, a chip, or a chip module. The chip system may include a chip, but may also include other discrete components, such as transceivers.

[0064] In some possible implementations, the access point can communicate with an Internet Protocol (IP) network, such as the Internet, a private IP network, or other data networks.

[0065] 4. Terminal equipment

[0066] 1) Description

[0067] Terminal equipment can be entities / units / modules / devices with communication functions for sending and receiving.

[0068] In some possible implementations, the terminal device can be at least one of the following: handheld device, wearable device, in-vehicle device, in-vehicle terminal, electronic device, augmented reality (AR) device, virtual reality (VR) device, Internet of Things (IoT) device, projection device, projector, user equipment (UE), terminal device, terminal, mobile terminal, smartphone, smart screen, smart TV, smartwatch, laptop, smart speaker, camera, game controller, microphone, station (STA), mobile station (MS), personal digital assistant (PDA), personal computer (PC), session initiation protocol (SIP) telephone, wireless local loop (WLL) station, etc.

[0069] In some possible implementations, this wearable device can also be called a smart wearable device, a general term for smart devices that utilize application-based wearable technology to intelligently design and develop everyday wearables. Examples include smart glasses, smart gloves, smartwatches, various smart bracelets with specific feature monitoring, and smart jewelry. Furthermore, this wearable device can be worn directly on the body or integrated into the user's clothing or accessories, making it a portable device. This wearable device can not only utilize dedicated hardware architectures but also dedicated software architectures for data interaction and cloud interaction. This wearable smart device can achieve complete or partial functionality without relying on other smart devices.

[0070] It should be noted that the embodiments of this application do not impose any particular limitation on the specific structure of the executing entity of the transmission power regulation method, as long as it can be processed by running a computer program or instructions that record the method provided in the embodiments of this application. For example, the executing entity of the method provided in the embodiments of this application can be a terminal device, or a processor / device / module / unit in the terminal device that can call and execute computer programs or instructions, etc., without specific limitations.

[0071] 2) Hardware architecture example of terminal device

[0072] In some possible implementations, the terminal device may include at least one of a processor, memory, sensing components, display components, camera components, communication components, input / output drivers, etc. Examples are given below.

[0073] ① Processor

[0074] In some possible implementations, the processor can be used to run or add an operating system, which can be any one or more computer operating systems that implement business processing through processes. Examples include Linux, Unix, Android, iOS, Windows, Zephyr, Real-Time Operating System (RTOS), DOS, Mac, ThreadX, embedded operating systems, and Nucleus Plus.

[0075] In some possible implementations, the processor can be viewed as a complete system-on-chip (SOC).

[0076] In some possible implementations, the processor may include one or more processing units. For example, a processing unit may include at least one of the following: a central processing unit (CPU), an application processor (AP), a microcontroller unit (MCU), a single-chip microcomputer (SCM), a microcontroller, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a digital signal processor (DSP), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a baseband processor, and a neural-network processing unit (NPU). The different processing units may be separate or integrated together.

[0077] In some possible implementations, a processing unit can be a single core or multiple cores.

[0078] In some possible implementations, a processing unit can run or load a multi-core subsystem. This multi-core subsystem can be an operating system with multi-core processing capabilities.

[0079] In some possible implementations, the processor may also include memory for storing computer programs or instructions.

[0080] For example, a processor can call programs stored in memory to run an operating system.

[0081] For example, the processor's memory can store or cache instructions that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from that memory, thereby avoiding repeated accesses, reducing processor wait time, and improving system efficiency.

[0082] For example, the memory in a processor can also store or cache data, and synchronize or transfer this data to other processors for execution. This memory in the processor can be a cache memory.

[0083] In some possible implementations, the processor may include one or more communication interfaces. These communication interfaces may include at least one of the following: Serial Peripheral Interface (SPI), Inter-Integrated Circuit (I2C) interface, Inter-Integrated Circuit Sound (I2S) interface, Pulse Code Modulation (PCM) interface, Universal Asynchronous Receiver / Transmitter (UART) interface, Mobile Industry Processor Interface (MIPI), General-Purpose Input / Output (GPIO) interface, Subscriber Identity Module (SIM) interface, and Universal Serial Bus (USB) interface.

[0084] ② Memory

[0085] In some possible implementations, memory can be used to store computer programs or instructions.

[0086] In some possible implementations, the memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0087] ③Sensing components

[0088] In some possible implementations, the sensing component can be a sensor.

[0089] For example, the sensing components may include at least one of the following: gravity sensor, gyroscope sensor, magnetometer sensor, accelerometer sensor, inertial sensor (such as inertial motion unit (IMU)), pressure sensor, barometric pressure sensor, distance sensor, proximity sensor, fingerprint sensor, temperature sensor, touch sensor, ambient light sensor, bone conduction sensor, ultra-wideband (UWB) sensor, near field communication (NFC) sensor, laser sensor, and / or visible light sensor.

[0090] ④ Display components

[0091] In some possible implementations, the display component can be used to display at least one of the following: user interface, user interface elements and features, user selectable controls, various displayable objects, etc.

[0092] In some possible implementations, the display component can be the physical screen of the terminal device. This physical screen can include one of a display screen, a touch screen, etc.

[0093] For example, the display component may include a display panel. The display panel may employ liquid crystal display (LCD), organic light-emitting diode (OLED), active-matrix organic light-emitting diode (AMOLED), flexible light-emitting diode (FLED), quantum dot light-emitting diodes (QLED), etc.

[0094] It should be noted that terminal devices can implement display functions through GPUs, display components, and processors. GPUs can be used to perform mathematical and geometric calculations and to perform graphics rendering. Additionally, a GPU can be a microprocessor for image processing and connects to the display component and the processor. The processor can include one or more GPUs, which execute program instructions to generate or modify display information.

[0095] ⑤ Camera components

[0096] In some possible implementations, the camera component can be a camera or camera module, which is used to capture (shoot / scan / acquire, etc.) still / moving images or videos.

[0097] In some possible implementations, the camera assembly may include a lens, a photosensitive element, etc., and the photosensitive element may be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor.

[0098] Therefore, an object can generate an optical image through the lens and project it onto the photosensitive element. The photosensitive element can convert the light signals in this optical image into electrical signals, and then pass these electrical signals to the ISP (Image Signal Processor) for conversion into digital image signals. The ISP outputs this digital image signal to the DSP (Digital Signal Processor). The DSP converts this digital image signal into image signals in standard formats such as RGB and YUV.

[0099] It should be noted that terminal devices can achieve functions such as capturing (shooting / scanning) images through ISP, DSP, camera components, video codecs, GPU, display components, and processors.

[0100] In some possible implementations, the ISP can be used to process data fed back from the camera component. For example, when taking a picture, the shutter is first opened, and then light passes through the lens of the camera component to the image sensor of the camera component, realizing the conversion of light signals into electrical signals. Finally, the image sensor transmits the electrical signals to the ISP for processing to convert them into digital images, etc.

[0101] In some possible implementations, the ISP can also perform algorithmic optimizations on image noise, brightness, and skin tone.

[0102] In some possible implementations, the ISP can also optimize parameters such as exposure and color temperature of the shooting scene.

[0103] In some possible implementations, the ISP and / or DSP can be set in the camera assembly.

[0104] ⑥ Communication components

[0105] It should be noted that communication components can be used to support wireless communication between terminal devices and network devices and access points.

[0106] In some possible implementations, the communication component can provide solutions for wireless communication applications, including 2G / 3G / 4G / 5G, on terminal devices.

[0107] In some possible implementations, the communication component can provide solutions for wireless communication applications on terminal devices, including Bluetooth (BT), WLAN, WiFi networks, near field communication (NFC), ultra-wideband (UWB), and infrared (IR) technologies.

[0108] In some possible implementations, the communication component can receive electromagnetic waves via an antenna, and then process the received electromagnetic waves by filtering, amplification, etc., before transmitting them to a modem processor for demodulation. The communication component can also amplify the signal modulated by the modem processor and then radiate it as electromagnetic waves via the antenna.

[0109] In some possible implementations, the communication components may include at least one filter, switch, power amplifier, and low noise amplifier (LNA), etc.

[0110] In some possible implementations, at least some functional modules of the communication component may be located in the processor; or, at least some functional modules of the communication component may be located in the same device as some modules of the processor.

[0111] ⑦ Input / output drivers

[0112] In some possible implementations, input / output drivers can be used to handle various inputs / outputs from user-operated devices.

[0113] For example, when the display is a touchscreen, the input / output driver can operate to detect and process various click or touch events. A click or touch event on the touchscreen simultaneously indicates the area of ​​interest and initiates scanning of an object. The object can be displayed on the touchscreen as a preview of the image to be scanned, and a touch event at a specific location on the touchscreen indicates the image that should be scanned.

[0114] II. A method for controlling transmission power

[0115] 1. Description

[0116] With the improvement and promotion of SAR mandatory standards, there are more and more requirements for SAR reduction solutions. There are many common solutions to achieve a balance between SAR and uplink communication. However, some solutions usually require the use of sensors or redesign of antenna structure layout, which brings certain hardware and design costs.

[0117] In addition, some solutions directly reduce the transmission power of the equipment to reduce SAR. However, reducing the transmission power may also lead to signal transmission failure, causing communication failure and affecting communication reliability.

[0118] To address this, this application proposes a transmission power control method. This method can determine the distance between the first terminal device and the user in real time based on WiFi sensing. By comparing the distance with a preset distance, it can determine whether the transmission power of the mobile cellular signal needs to be reduced to a target power threshold or below. This not only helps to ensure the reliability of mobile cellular communication as much as possible, but also facilitates flexible control of the SAR of the terminal device to avoid the impact of the terminal device's electromagnetic radiation on the user. Furthermore, it saves hardware and design costs by eliminating the need to use sensors and redesign the antenna structure layout.

[0119] like Figure 2 As shown, Figure 2 This is a flowchart illustrating a transmission power regulation method according to an embodiment of this application, applied to a first terminal device. The method may include the following steps:

[0120] S210. Obtain the channel state information (CSI) of multiple subcarriers of the Wi-Fi signal, and determine the distance between the first terminal device and the user based on the CSI of the multiple subcarriers.

[0121] S220. If the distance between the first terminal device and the user is less than a preset distance, the transmission power of the mobile cellular signal is reduced to a target power threshold or below, and the transmission power of the mobile cellular signal is restored when the distance between the first terminal device and the user is greater than or equal to the preset distance again. The target power threshold is the minimum transmission power required to ensure successful transmission of the mobile cellular signal.

[0122] S230. If the distance between the first terminal device and the user is greater than or equal to the preset distance, the transmission power of the mobile cellular signal shall continue to be maintained.

[0123] Based on this, this application can determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers of the WiFi signal, and then determine whether it is necessary to reduce the transmission power of the mobile cellular signal to the target power threshold based on the relationship between the distance and the preset distance.

[0124] If the distance is less than the preset distance, it means that the user is very close to the first terminal device. In order to ensure the successful transmission of mobile cellular signals while avoiding the impact of electromagnetic radiation from the first terminal device on the user, this application can reduce the transmission power of mobile cellular signals to the target power threshold, thereby minimizing the SAR of the first terminal device while ensuring the reliability of mobile cellular communication.

[0125] Of course, this application can also reduce the transmission power of the mobile cellular signal to below the target power threshold. Although this may not guarantee successful mobile cellular signal transmission, it can significantly reduce the SAR of the first terminal device.

[0126] Then, when the distance is greater than or equal to the preset distance again, it indicates that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order to avoid reducing the reliability of mobile cellular communication due to insufficient transmission power, this application needs to restore the transmission power of the mobile cellular signal.

[0127] Finally, if the distance is greater than or equal to the preset distance, it means that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order not to affect the mobile cellular communication, this application needs to continue to maintain the transmission power of the mobile cellular signal without adjusting the transmission power.

[0128] 2. Detailed Implementation Instructions

[0129] The following is a summary of the above. Figure 2 The implementation methods involved will be explained in detail. It should be noted that the contents of the following sections can be combined and related to each other in order to realize the complete technical solution of this application.

[0130] 1) First terminal equipment and second terminal equipment

[0131] It should be noted that, for ease of distinction and description, this application introduces the concepts of a first terminal device and a second terminal device. Both the first terminal device and the second terminal device refer to the terminal devices mentioned in "I. Transmission Power Control System" above.

[0132] To determine the distance between a first terminal device and a user based on WiFi sensing, this application allows both the first and second terminal devices to participate in establishing WiFi sensing. Thus, the second terminal device can be a terminal device that collaborates with the first terminal device in performing WiFi sensing.

[0133] 2) Channel State Information (CSI) of multiple subcarriers of the WiFi signal

[0134] A key technology in WiFi is Multiple-Input Multiple-Output (MIMO), which provides high throughput to meet the ever-increasing demand for wireless data traffic. MIMO, along with Orthogonal Frequency Division Multiplexing (OFDM), provides CSI for each transmit and receive antenna pair at each carrier frequency.

[0135] Compared to Received Signal Strength Indication (RSSI), CSI, as physical layer information and a channel characteristic, reflects the performance of the WiFi wireless channel, representing the amplitude and phase information of each OFDM subcarrier, and possesses a certain multipath resolution capability. For example, the expression for CSI is:

[0136]

[0137] Among them, H k (t) represents the CSI of the k-th subcarrier at time t, ||H k (t)|| represents the amplitude of the k-th subcarrier at time t, ∠H k (t) represents the phase of the k-th subcarrier at time t.

[0138] For WiFi systems with MIMO-OFDM, this application can obtain a three-dimensional complex matrix (the dimension is determined by the number of transmitting antennas, receiving antennas, and subcarriers), and by collecting the CSI of multiple subcarriers of the WiFi signal, it can effectively analyze how the WiFi signal passes through surrounding objects in the time domain, frequency domain, and spatial domain, thus making it applicable to various wireless sensing applications.

[0139] 3) How to obtain the CSI of multiple subcarriers of a WiFi signal

[0140] It should be noted that this application can employ various methods to obtain the CSI of multiple subcarriers of a WiFi signal. In this way, by using multiple methods, this application adapts to various scenario requirements, improving the flexibility and diversity of CSI acquisition.

[0141] Method 1:

[0142] a. Description

[0143] In "Method 1", this application can use the first channel measurement result and / or the second channel measurement result as the CSI of multiple subcarriers of the WiFi signal. In this way, this application only needs to obtain the first channel measurement result and / or the second channel measurement result to obtain the CSI of multiple subcarriers of the WiFi signal.

[0144] b. First channel measurement results

[0145] The first channel measurement result can represent the measurement result of the WiFi channel status between the access point and the second terminal device.

[0146] It should be noted that, since this application introduces a second terminal device to participate in establishing WiFi sensing together with the first terminal device, this application needs to measure the WiFi channel status between the access point and the second terminal device by exchanging WiFi measurement signals between the access point and the second terminal device, and then use the measurement result obtained as the "first channel measurement result".

[0147] Then, in “Method 1”, in order to ensure that the first terminal device can obtain the “first channel measurement result”, the access point needs to send the first channel measurement result to the first terminal device; correspondingly, the first terminal device receives the first channel measurement result.

[0148] c. Second channel measurement results

[0149] To measure the WiFi channel state between the first terminal device and the access point, in "Method 1", the access point of this application can send a first WiFi measurement signal to the first terminal device. Thus, the first terminal device can measure the WiFi channel state between itself and the access point based on the first WiFi measurement signal. For ease of distinction and description, this measurement result is referred to as the "second channel measurement result".

[0150] In other words, the first WiFi measurement signal is used by the first terminal device to measure the WiFi channel status between the first terminal device and the access point to obtain the second channel measurement result, that is, the second channel measurement result is obtained by the first terminal device based on the first WiFi measurement signal.

[0151] d. Exemplary Description

[0152] The following example illustrates "Method 1" using the interaction between the first terminal device, the access point, and the second terminal device as an example. Figure 3 As shown, Figure 3 This is a schematic diagram of a process for obtaining the CSI of multiple subcarriers of a WiFi signal according to an embodiment of this application. The method may include the following steps:

[0153] S310: The access point interacts with the second terminal device to exchange WiFi measurement signals to obtain the first channel measurement result.

[0154] S320: The access point sends a first WiFi measurement signal and / or a first channel measurement result to the first terminal device.

[0155] Correspondingly, the first terminal device receives the first WiFi measurement signal and / or the first channel measurement result.

[0156] S330, the first terminal device measures the second channel measurement result based on the first WiFi measurement signal.

[0157] S340, The first terminal device uses the first channel measurement result and / or the second channel measurement result as the CSI of multiple subcarriers of the WiFi signal.

[0158] Thus, this application only needs to obtain the first channel measurement results and / or the second channel measurement results to obtain the CSI of multiple subcarriers of the WiFi signal.

[0159] Method 2:

[0160] a. Description

[0161] In "Method 2", this application can use the first channel measurement results and / or the third channel measurement results as the CSI of multiple subcarriers of the WiFi signal. In this way, this application only needs to obtain the first channel measurement results and / or the third channel measurement results to obtain the CSI of multiple subcarriers of the WiFi signal.

[0162] b. First channel measurement results

[0163] The measurement results for the first channel are consistent with the description in "Method 1" above, and will not be repeated here.

[0164] c. Third-channel measurement results

[0165] To measure the WiFi channel state between the first terminal device and the access point, in "Method 2", the first terminal device of this application can send a second WiFi measurement signal to the access point. In this way, the access point can measure the WiFi channel state between the first terminal device and the access point based on the second WiFi measurement signal. For ease of distinction and description, this measurement result is referred to as the "third channel measurement result".

[0166] In other words, the second WiFi measurement signal is used by the access point to measure the WiFi channel status between the first terminal device and the access point in order to obtain the third channel measurement result. That is, the third channel measurement result is obtained by the access point based on the second WiFi measurement signal.

[0167] d. Exemplary Description

[0168] The following example illustrates "Method 2" using the interaction between the first terminal device, the access point, and the second terminal device as an example. Figure 4 As shown, Figure 4 This is a schematic diagram of another embodiment of the present application for obtaining CSI of multiple subcarriers of a WiFi signal. The method may include the following steps:

[0169] S410: The access point interacts with the second terminal device to exchange WiFi measurement signals to obtain the first channel measurement result.

[0170] S420: The first terminal device sends a second WiFi measurement signal to the access point.

[0171] Correspondingly, the access point receives the second WiFi measurement signal.

[0172] Of course, this application may execute S420 first and then S410, without making any specific restrictions on this.

[0173] S430, the access point measures the third channel measurement result based on the second WiFi measurement signal.

[0174] S440: The access point sends the first channel measurement result and / or the third channel measurement result to the first terminal device.

[0175] Correspondingly, the first terminal device receives the measurement results of the first channel and / or the measurement results of the third channel.

[0176] S450, the first terminal device uses the first channel measurement result and / or the third channel measurement result as the CSI of multiple subcarriers of the WiFi signal.

[0177] Thus, this application only needs to obtain the first channel measurement results and / or the third channel measurement results to obtain the CSI of multiple subcarriers of the WiFi signal.

[0178] Method 3:

[0179] a. Description

[0180] In "Method 3", this application can use the first channel measurement results and / or the fourth channel measurement results as the CSI of multiple subcarriers of the WiFi signal. In this way, this application only needs to obtain the first channel measurement results and / or the fourth channel measurement results to obtain the CSI of multiple subcarriers of the WiFi signal.

[0181] b. First channel measurement results

[0182] The first channel measurement result can represent the measurement result of the WiFi channel status between the access point and the second terminal device.

[0183] It should be noted that, since this application introduces a second terminal device to participate in establishing WiFi sensing together with the first terminal device, this application needs to measure the WiFi channel status between the access point and the second terminal device by exchanging WiFi measurement signals between the access point and the second terminal device, and then use the measurement result obtained as the "first channel measurement result".

[0184] Then, in “Method 3”, in order to ensure that the first terminal device can obtain the “first channel measurement result”, the second terminal device needs to send the first channel measurement result to the first terminal device; correspondingly, the first terminal device receives the first channel measurement result.

[0185] c. Fourth channel measurement results

[0186] To measure the WiFi channel state between the first terminal device and the second terminal device, in "Method 3", the second terminal device can send a third WiFi measurement signal to the first terminal device. In this way, the first terminal device can measure the WiFi channel state between itself and the second terminal device based on the third WiFi measurement signal. For ease of distinction and description, this measurement result is referred to as the "fourth channel measurement result".

[0187] In other words, the third WiFi measurement signal is used by the first terminal device to measure the WiFi channel status between the first terminal device and the second terminal device to obtain the fourth channel measurement result. That is, the fourth channel measurement result is obtained by the first terminal device based on the third WiFi measurement signal.

[0188] d. Exemplary Description

[0189] The following example illustrates "Method 3" using the interaction between the first terminal device, the access point, and the second terminal device as an example. Figure 5 As shown, Figure 5This is a schematic diagram of another embodiment of the present application for obtaining CSI of multiple subcarriers of a WiFi signal. The method may include the following steps:

[0190] S510: The access point interacts with the second terminal device to exchange WiFi measurement signals to obtain the first channel measurement result.

[0191] S520, the second terminal device sends a third WiFi measurement signal and / or a first channel measurement result to the first terminal device.

[0192] Correspondingly, the first terminal device receives the third WiFi measurement signal and / or the first channel measurement result.

[0193] S530, the first terminal device measures the fourth channel measurement result based on the third WiFi measurement signal.

[0194] S540, the first terminal device uses the first channel measurement result and / or the fourth channel measurement result as the CSI of multiple subcarriers of the WiFi signal.

[0195] Thus, this application only needs to obtain the first channel measurement results and / or the fourth channel measurement results to obtain the CSI of multiple subcarriers of the WiFi signal.

[0196] Method 4:

[0197] a. Description

[0198] In "Method 4", this application can use the first channel measurement result and / or the fifth channel measurement result as the CSI of multiple subcarriers of the WiFi signal. In this way, this application only needs to obtain the first channel measurement result and / or the fifth channel measurement result to obtain the CSI of multiple subcarriers of the WiFi signal.

[0199] b. First channel measurement results

[0200] The measurement results for the first channel are consistent with the description in "Method 3" above, and will not be repeated here.

[0201] c. Fifth channel measurement results

[0202] To measure the WiFi channel state between the first terminal device and the second terminal device, in "Method 4", the first terminal device of this application can send a fourth WiFi measurement signal to the second terminal device. Thus, the second terminal device can measure the WiFi channel state between the first terminal device and the second terminal device based on the fourth WiFi measurement signal. For ease of distinction and description, this measurement result is referred to as the "fifth channel measurement result".

[0203] In other words, the fourth WiFi measurement signal is used by the second terminal device to measure the WiFi channel status between the first terminal device and the second terminal device to obtain the fifth channel measurement result. That is, the fifth channel measurement result is obtained by the second terminal device based on the fourth WiFi measurement signal.

[0204] d. Exemplary Description

[0205] The following example illustrates "Method 2" using the interaction between the first terminal device, the access point, and the second terminal device as an example. Figure 6 As shown, Figure 6 This is a schematic diagram of another embodiment of the present application for obtaining CSI of multiple subcarriers of a WiFi signal. The method may include the following steps:

[0206] S610: The access point interacts with the second terminal device to exchange WiFi measurement signals to obtain the first channel measurement result.

[0207] S620, the first terminal device sends a fourth WiFi measurement signal to the second terminal device.

[0208] Correspondingly, the second terminal device receives the WiFi measurement signal from the third party.

[0209] Of course, this application may execute S620 first and then S610, without making any specific restrictions on this.

[0210] S630, the second terminal device measures the fifth channel measurement result based on the fourth WiFi measurement signal.

[0211] S640, the second terminal device sends the first channel measurement result and / or the fifth channel measurement result to the first terminal device.

[0212] Correspondingly, the first terminal device receives the measurement results of the first channel and / or the measurement results of the fifth channel.

[0213] S650, the first terminal device uses the first channel measurement result and / or the fifth channel measurement result as the CSI of multiple subcarriers of the WiFi signal.

[0214] Thus, this application only needs to obtain the first channel measurement results and / or the fifth channel measurement results to obtain the CSI of multiple subcarriers of the WiFi signal.

[0215] 4) How to establish WiFi awareness

[0216] It should be noted that, in order to achieve CSI (Communication Sequence Information) for acquiring multiple subcarriers of the WiFi signal, this application needs to establish WiFi sensing between the first terminal device and the access point, determine the second terminal device that will participate in establishing WiFi sensing together with the first terminal device, and establish WiFi sensing between the first terminal device and the second terminal device, etc. These will be explained separately below.

[0217] a. Establish WiFi sensing between the first terminal device and the access point

[0218] It should be noted that, in order to establish WiFi sensing between the first terminal device and the access point, this application introduces first request information and first response information. The first request information can be used to request the establishment of WiFi sensing with the access point; the first response information can be a response to the first request information and can be used to indicate that the WiFi sensing between the first terminal device and the access point has been established.

[0219] As can be seen, the first terminal device can send a first request message to the access point, and the access point receives the first request message; then, the access point sends a first response message to the first terminal device, and the first terminal device receives the first response message, thereby establishing WiFi awareness between the first terminal device and the access point through the first request message and the first response message.

[0220] In this way, after the WiFi sensing between the first terminal device and the access point is established, the first terminal device and the access point can then exchange WiFi measurement signals to measure the WiFi channel status between the first terminal device and the access point in order to obtain the second channel measurement result or the second channel measurement result.

[0221] b. A second terminal device that participates in establishing WiFi sensing along with the first terminal device.

[0222] It should be noted that, in order to improve the accuracy of the distance between the first terminal device and the user determined based on WiFi sensing, the first terminal device of this application can request the access point to determine the second terminal device, so that the second terminal device can participate in the establishment of WiFi sensing together with the first terminal device, thereby improving the accuracy of determining the distance.

[0223] Therefore, this application introduces second request information and second response information. The second request information can be used to request an access point to determine a second terminal device, and the second response information can be a response to the second request information and can be used to indicate the device identifier of the second terminal device.

[0224] As can be seen, the first terminal device can send a second request message to the access point, and the access point receives the second request message; then, the access point sends a second response message to the first terminal device, and the first terminal device receives the second response message, thereby identifying the second terminal device through the second request message and the second response message.

[0225] In some possible implementations, the first request information and the second request information can be carried by the same signaling. In this way, this application can send only one signaling message to both request the establishment of WiFi awareness with the access point and request the access point to identify the second terminal device.

[0226] In some possible implementations, the first request information and the second request information can be carried by different signaling messages. Thus, this application can send one signaling message to request the establishment of WiFi sensing with the access point, and send another signaling message to request the access point to identify the second terminal device. Furthermore, this application does not impose specific restrictions on the order in which these two signaling messages are sent.

[0227] c. Establish WiFi sensing between the first terminal device and the second terminal device.

[0228] It should be noted that after receiving the second response information, the first terminal device learns the device identifier of the second terminal device. In this way, the first terminal device can locate the second terminal device based on its device identifier in order to request the establishment of WiFi sensing with the second terminal device.

[0229] Therefore, this application introduces third request information and third response information. The third request information can be used to request the establishment of WiFi sensing with a third terminal device, and the third response information can be used to indicate that the WiFi sensing between the first terminal device and the second terminal device has been established.

[0230] As can be seen, the first terminal device can send a third request message to the second terminal device, and the second terminal device receives the third request message; then, the second terminal device sends a third response message to the first terminal device, and the first terminal device receives the third response message, thereby establishing WiFi sensing between the first terminal device and the second terminal device through the third request message and the third response message.

[0231] In this way, after establishing WiFi sensing between the first terminal device and the second terminal device, the first terminal device and the second terminal device can then exchange WiFi measurement signals to measure the WiFi channel status between the first terminal device and the second terminal device in order to obtain the fifth channel measurement result.

[0232] 5) How to determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers?

[0233] a. Description

[0234] It should be noted that WiFi sensing methods are mainly divided into model-based methods and learning-based methods.

[0235] Model-based methods model human activity based on physical signal models, among which the Fresnel zone theory is well-known. It models the long ellipsoidal space region between and around the transmitter and receiver.

[0236] Learning-based methods, driven by machine learning or deep learning, require sophisticated equipment and ideal environments to effectively model complex human activities. To address the recognition of these activities, machine learning or deep learning can collect vast amounts of data and then train neural network models for identification.

[0237] Based on this, this application adopts a learning-based method to determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers, so as to improve the accuracy of the determined distance through the learning-based method.

[0238] In specific implementation, determining the distance between the first terminal device and the user based on the CSI of multiple subcarriers can include:

[0239] Feature extraction is performed on the CSI of multiple subcarriers to obtain feature information, which is used to reflect the user's motion state and position state;

[0240] The feature information is input into the trained neural network model to output the distance between the first terminal device and the user.

[0241] As can be seen, in order to adopt a learning-based method, this application needs to first extract features from the CSI of multiple subcarriers in order to extract feature information that can reflect the user's motion state and position state, and remove interference information that is irrelevant to the human body. Then, the feature information is input into the trained neural network model to obtain the distance between the first terminal device and the user.

[0242] b. Feature information

[0243] ① Description

[0244] In some possible implementations, feature extraction of the CSI of multiple subcarriers to obtain feature information may include:

[0245] The CSI of each subcarrier in the CSI of multiple subcarriers is sequentially denoised, linear time-domain interpolated, and wavelet transformed.

[0246] Calculate the variance of the CSI amplitude of each subcarrier within a preset sliding time window to obtain the characteristic variance of each subcarrier;

[0247] Calculate the feature variance matrix of each subcarrier within a preset time period to obtain feature information.

[0248] As can be seen, to improve the accuracy of CSI, this application can denoise the CSI of multiple subcarriers. Then, to achieve time-frequency domain analysis of the CSI and more clearly analyze the changes in user motion or position reflected by the CSI, this application can perform linear time-domain interpolation and wavelet transform on the CSI of multiple subcarriers. Finally, in the feature extraction section, this application extracts the feature variance matrix of the CSI of all subcarriers as characteristic information, so as to more reasonably and effectively reflect the user's motion and position state through the feature variance matrix. These will be explained in detail below.

[0249] ② Reduce restlessness

[0250] It should be noted that noise reduction mainly targets the amplitude and phase noise in CSI, in order to improve the accuracy of CSI by eliminating this noise.

[0251] Regarding phase noise, in practical WiFi systems, due to hardware imperfections and other reasons, CSI may include phase offsets, such as sampling time offset and sampling frequency offset. Sampling time offset is usually caused by the asynchronous sampling clocks of the receiver and transmitter, while sampling frequency offset is related to each carrier frequency. This application can employ various methods to eliminate phase offset.

[0252] For example, this application can use multiple linear regression to eliminate phase shift, thereby obtaining a more accurate absolute phase value.

[0253] For amplitude noise, this application can use a moving average filter or a median filter to eliminate amplitude noise.

[0254] ③ Linear time-domain interpolation

[0255] It should be noted that the CSI of each subcarrier can be a discrete sequence at different times in the time domain. For example, the CSI of the k-th subcarrier at a preset time T (T = t) M The discrete sequences at different times within -t0) are:

[0256] H k ={H k (t0),...,H k (t i ),...,H k (t M )}, i = 0, 1, ..., M;

[0257] Among them, H k (t i ) indicates that the k-th subcarrier at time t i CSI.

[0258] Since the CSI of each subcarrier is a discrete sequence in the time domain, it is impossible to obtain the CSI of each subcarrier at all times, resulting in missing CSI at certain times. These missing CSI values ​​are detrimental to reflecting the user's overall motion and location status. To address this, this application performs linear time-domain interpolation on the CSI of each subcarrier, enabling CSI analysis from the time domain to more accurately reflect the user's motion and location status.

[0259] For example, with the above H k For example, this application can obtain the time at time t through linear time-domain interpolation. i and time t i+1 The time t between Δ The CSI is H Δ :

[0260] H Δ =H k (t i )+α(H k (t i+1 )-H k (t i ));

[0261] α=(t Δ -t i ) / (t i+1 -t i ).

[0262] ④ Wavelet Transform

[0263] It should be noted that CSI not only contains fine-grained time-domain information but also rich frequency-domain information. Wavelet transform can perform time-frequency analysis and processing on signals. Its feature is to highlight the local features of signals through transformation, adapt to the requirements of time-frequency signal analysis, and can play a filtering role to a certain extent. Thus, it more clearly shows the local features of the subcarrier changes corresponding to each action.

[0264] In this way, the present application can perform wavelet transform on the CSI of each subcarrier, thereby more clearly reflecting the local features of the changes of the user's motion state and position state on the subcarriers.

[0265] ⑤ Extract the feature variance matrix

[0266] Since the change trends of the amplitudes of the CSI of different subcarriers are generally the same, but the amplitudes of the CSI of different subcarriers have different values at different times, as Figure 7 shown, the present application can calculate the variance of the amplitude of the CSI of each subcarrier within a preset sliding time window in the time domain to obtain the feature variance, and then calculate the feature variance matrix of the feature variances of each subcarrier within a preset time, so as to more accurately reflect the user's motion state and position state through the feature variance matrix.

[0267] For example, taking the above H k as an example, the present application calculates the feature variance D(H k (1)) of the k-th subcarrier starting from time t0 within the first preset sliding time window L (L < T) as:

[0268]

[0269] Then, calculate the feature variance matrix D(H k ) of the feature variance of the k-th subcarrier within the preset time T as:

[0270] D(H k ) = {D(H k (1)), D(H k (2)),..., D(H k (n))};

[0271] where n = T / L, and D(H k (n)) represents the feature variance of the k-th subcarrier within the n-th preset sliding time window L.

[0272] c. Neural network model

[0273] ① Description

[0274] It should be noted that the neural network model of this application can be used to determine the distance between the first terminal device and the user, and can have any network structure. This neural network model can be obtained from Neural Architecture Search (NAS). These will be explained in detail below.

[0275] ②NAS

[0276] a. Description

[0277] Neural Network Architecture (NAS) has become a very popular research topic in the field of artificial intelligence in recent years. The core elements of a NAS algorithm include the search space, search strategy, and performance evaluation strategy. The search space defines the set of searchable neural network structures, i.e., the solution space. The search strategy defines how to find the optimal neural network structure within the search space. The performance evaluation strategy defines how to evaluate the network performance of the searched neural network structure, and the network performance can be measured by metrics such as accuracy and computational power (or computing power).

[0278] The principle of the NAS algorithm can be summarized as follows: Define a search space; in each iteration of the search process, a neural network structure called a "sub-network" is obtained from the search space through a search strategy; train the sub-network on the training sample set, and evaluate the performance of the sub-network on the validation set through a performance evaluation strategy, so as to gradually optimize the network structure until the sub-network with the best performance is found.

[0279] b. Search space

[0280] The search space defines the types and set of neural network structures that the NAS algorithm can search, i.e., the solution space, and also defines how the neural network structure should be described.

[0281] The computations performed by neural networks can be abstracted as a directed acyclic graph (DAG) without isolated nodes. In this DAG, the nodes represent the layers of the neural network or the feature maps in a convolutional network; the edges of the DAG represent the flow of data or operations (OPs), which can also be called operators, such as convolution and pooling.

[0282] Each node in a Directed Acyclic Graph (DAG) receives data from its predecessor (with incoming edges), performs computation, and then outputs the data to subsequent nodes (with outgoing edges). Theoretically, any DAG without isolated nodes is a valid neural network structure. Depending on the scale, the structural definition of a neural network includes the following levels of information:

[0283] ◆Network topology

[0284] The topology of a network describes the number of layers in a neural network and the connections between them. The simplest neural network is a linear chain structure, which corresponds to at most one predecessor node and one successor node in its graph, similar to a linked list in data structures. When describing the topology of a network, the predecessor node is typically used for definition; that is, the predecessor node of each node is defined. Once this information is determined, the network topology is determined.

[0285] ◆Type of each layer

[0286] In a neural network architecture, the first layer is the input layer, the last layer is the output layer, and the types of the intermediate layers are optional; they represent various operations (operators), i.e., the layer types. Typical examples include fully connected layers, convolutional layers, deconvolutional layers, separable convolutional layers, dilated convolutional layers, pooling layers, and activation functions.

[0287] ◆ Hyperparameters within each layer

[0288] The hyperparameters of a convolutional layer include the kernel size, the number of kernels, the number of channels in the kernel, height, width, horizontal stride, and vertical stride.

[0289] The hyperparameters of the pooling layer include the pooling kernel height, pooling kernel width, horizontal step size, and vertical step size.

[0290] The hyperparameters of a fully connected layer include the number of neurons.

[0291] The hyperparameters of the activation function layer include the type of the activation function and the parameters of the activation function.

[0292] To improve search efficiency, the search space is sometimes limited or simplified. For example, the network can be divided into basic units, and more complex networks can be formed by stacking these cells. A cell consists of multiple nodes and edges that appear repeatedly throughout the network but have different weight parameters.

[0293] c. Search strategy

[0294] Search strategies define how to find the optimal neural network structure in the search space. For example, search strategies include reinforcement learning-based search strategies, genetic algorithm-based search strategies, gradient descent-based search strategies, and so on.

[0295] d. Performance evaluation strategy

[0296] The performance evaluation strategy defines how to evaluate the performance of the searched neural network architecture, and the performance of the neural network architecture can be measured by metrics such as accuracy and computing power.

[0297] ③ How to obtain a neural network model

[0298] a. Description

[0299] It should be noted that the neural network model in this application can be obtained from the supernet of the target neural network architecture search after training; wherein, the supernet of the target neural network architecture search can be obtained by adjusting the hyperparameters of the target subnetwork in the supernet of the preset neural network architecture search.

[0300] As can be seen, this application achieves the construction of a supernet for target neural network architecture search by adjusting the hyperparameters of the target subnetwork in the supernet of the preset neural network architecture search, so that the supernet of the target neural network architecture search and the target subnetwork can have the same performance.

[0301] Thus, given that the target subnetwork has optimal network performance, it is possible that the supernet searched for the target neural network architecture can also have optimal network performance. Then, a neural network model is searched from the trained supernet of the target neural network architecture search, ensuring that the neural network model meets the requirements for both computational power and accuracy, thus realizing the possibility of finding a neural network model with excellent computational power and accuracy.

[0302] b. Preset Neural Network Architecture Search

[0303] The search for the predefined neural network architecture can be a NAS based on a gradient descent search strategy, a NAS with a continuously relaxed search space, or a NAS with a continuously relaxed search space and a gradient descent search strategy.

[0304] For example, a predefined neural network architecture search may include Differentiable Architecture Search (DARTS).

[0305] c. Target Neural Network Architecture Search

[0306] Target neural network architecture search can be a NAS that decouples the training and search processes.

[0307] For example, the search for a target neural network architecture could include training a network and specializing it for efficient deployment (TrainOne Network and Specialize it for Efficient Deployment, Once-For-All).

[0308] d. Process of obtaining neural network models

[0309] like Figure 8 As shown, Figure 8 This is an overall flowchart of obtaining a neural network model according to an embodiment of this application. The specific steps are as follows:

[0310] Step 1: Obtain the search space for the preset neural network architecture search

[0311] It should be noted that the search space for the preset neural network architecture search can include a list of operators. Operator types can include convolution, pooling, identity, etc.

[0312] Step 2: Construct a supernet for the search based on the search space and DAG using a pre-defined neural network architecture.

[0313] It should be noted that the supernet searched by the pre-defined neural network architecture can be viewed as a stack of cells. Here, a cell represents a directed acyclic graph (DAG). Each node in the DAG represents a feature map, and all nodes are connected by at least one edge, with each edge representing an operator (operation). Each edge corresponds to a weight parameter (such as the weights of a convolutional kernel).

[0314] Step 3: Obtain preset training data

[0315] Step 4: Train the supernet for searching the preset neural network architecture

[0316] It should be noted that, in this embodiment of the application, the preset training data obtained in step 3 can be used to train the supernet of the preset neural network architecture search.

[0317] Step 5: Search to obtain the target subnetwork

[0318] It should be noted that the embodiments of this application can search for the target subnetwork from the supernet searched by the trained preset neural network architecture. The search strategy employed is a gradient descent-based search strategy.

[0319] Furthermore, the target subnetwork can be a subnetwork whose accuracy meets the preset requirements, where the architecture parameters of the edges (operators / operations) connecting each pair of nodes are maximized. In other words, the target subnetwork is the subnetwork with the best accuracy among the supernets searched using the preset neural network architecture.

[0320] To ensure the performance of the target subnetwork, embodiments of this application may retrain the target subnetwork. For example, the target subnetwork may be retrained to ensure that the accuracy meets the requirements.

[0321] Step 6: Adjust the hyperparameters of the target sub-network to obtain the hypernet for the target neural network architecture search.

[0322] It should be noted that the target subnetwork has hyperparameters.

[0323] For example, the hyperparameter includes at least one of the following: network width (i.e., the number of channels in each layer of the target sub-network), network depth (i.e., the number of layers in the target sub-network), kernel size (i.e., the kernel size in the target sub-network), number of kernels (i.e., the number of kernels in the target sub-network), and feature map resolution (i.e., the feature map resolution in each layer of the target sub-network).

[0324] As can be seen, the embodiments of this application can adjust at least one of the following: network width, network depth, convolution kernel size, number of convolution kernels, feature map resolution, etc., of the target sub-network to obtain the supernet for target neural network architecture search, thereby realizing the construction of the supernet for target neural network architecture search based on the target sub-network, so that the supernet for target neural network architecture search and the target sub-network can have the same performance.

[0325] In this way, the supernet searched by the target neural network architecture can also have the best accuracy when the target subnetwork has the best accuracy.

[0326] In addition, this adjustment can include increasing, decreasing, or keeping it unchanged. For example, increasing the network width, decreasing the network depth, increasing the kernel size, keeping the number of kernels constant, and increasing the feature map resolution.

[0327] For example, increase the kernel size from 3×3 to 5×5.

[0328] Step 7: Train the supernet for the target neural network architecture search.

[0329] It should be noted that, in this embodiment of the application, knowledge distillation can be used to train the supernet of the target neural network architecture search as a teacher network, thereby enabling the trained supernet of the target neural network architecture search to achieve better network performance.

[0330] In practice, training the supernet for the target neural network architecture search can include the following steps:

[0331] ◆Using the hypernet of the preset neural network architecture search as the target neural network architecture search in the teacher network of knowledge distillation

[0332] It should be noted that, in the embodiments of this application, the supernet searched by the preset neural network architecture can be used as the teacher network in knowledge distillation, thereby realizing the construction of the teacher network.

[0333] ◆ Input the preset training data into the hypernet of the teacher network and the target neural network architecture search, and obtain the first loss value of the loss function between the teacher network and the target neural network architecture search hypernet.

[0334] It should be noted that the preset training data can be any kind of preset data, such as images, data, feature points, etc. In this application embodiment, the preset training data can be input into the supernet of the teacher network and the target neural network architecture search to obtain their respective output results.

[0335] Then, in the process of inputting the preset training data into the supernet of the teacher network and the target neural network architecture search, this embodiment of the application needs to calculate the value of the loss function according to the output results between layers to obtain the first loss value.

[0336] ◆ Input the preset training data into the ground truth and the hypernet of the target neural network architecture search, and obtain the second loss value of the loss function between the ground truth and the hypernet of the target neural network architecture search.

[0337] It should be noted that, in the embodiments of this application, preset training data can be input into the supernet of the Ground Truth and the target neural network architecture search to obtain their respective output results.

[0338] Then, in the process of inputting the preset training data into the supernet of the Ground Truth and the target neural network architecture search, this embodiment of the application needs to calculate the value of the loss function according to the output results between layers to obtain the second loss value.

[0339] ◆Calculate the regularization coefficient of the loss function for knowledge distillation between the teacher network and the hypernet of the target neural network architecture search.

[0340] It should be noted that, since knowledge distillation is used, this embodiment of the application also needs to calculate the regularization of the loss function of knowledge distillation between the teacher network and the supernet of the target neural network architecture search, and calculate the product between the first value and the regularization term coefficient to obtain the value of the regularized loss function.

[0341] The regularization coefficients can be determined by the first value, the second value, and the weight parameters of the supernet (such as the weights of the convolutional layers) of the target neural network architecture search.

[0342] For example, the value of the regularized loss function is a*R, where a represents the coefficient of the regularization term. Here, a is:

[0343] a = cos(dR / dw, dL / dw);

[0344] Where dR represents the gradient of the first value; dL represents the gradient of the second value; w represents the weight parameters of the supernet in the target neural network architecture search; and cos() represents the cosine calculation.

[0345] Thus, this application can measure the vector difference between two gradient optimization vectors (i.e., dR / dw, dL / dw) through cosine calculation, thereby improving the accuracy and precision of network optimization.

[0346] ◆Calculate the product of the first value and the regularization coefficient, and then add the second value to obtain the target value. Train the supernet for the target neural network architecture search with the goal of minimizing the target value.

[0347] It should be noted that, based on the above, the target value is a*R+L.

[0348] Thus, this application completes the training of the supernet for target neural network architecture search by training the supernet for target neural network architecture search with the goal of minimizing the target value.

[0349] Step 8: Search for neural network models

[0350] It should be noted that, in the embodiments of this application, the neural network model can be obtained from the supernet of the trained target neural network architecture search.

[0351] Understandably, a neural network model can be a subnetwork within a supernet that can be searched for the target neural network architecture.

[0352] In some possible implementations, obtaining the neural network model from the supernet of the trained target neural network architecture search can include the following steps:

[0353] ◆Collect training data

[0354] It should be noted that the embodiments of this application can collect training data to train the accuracy predictor. The accuracy predictor can be viewed as a predictive model used to calculate the accuracy of a sub-network, such as a multi-layer perceptron machine (MLP).

[0355] In some possible implementations, embodiments of this application can collect subnetworks from the supernet searched by the target neural network architecture, encode the subnetworks, and calculate the corresponding precision of the subnetworks to form data pairs in the training data. That is, the data pair can be represented as [the encoding of the subnetwork, the precision of the subnetwork]. Typically, embodiments of this application can collect 5000 data pairs to form the training data to ensure training quality.

[0356] ◆Training accuracy predictor

[0357] ◆Search for subnetworks that meet preset computing power constraints

[0358] It should be noted that, in this embodiment of the application, subnetworks can be searched from the supernet of the trained target neural network architecture to meet preset computing power constraints, thereby obtaining at least one candidate subnetwork. Therefore, each candidate subnetwork meets the preset computing power requirements.

[0359] In some possible implementations, the preset computing power constraints may include the number of floating-point operations per second (FLOPs) or the number of parameters (#Params).

[0360] ◆Search within at least one candidate subnetwork based on the trained accuracy predictor.

[0361] It should be noted that, in the embodiments of this application, the accuracy of at least one candidate sub-network can be calculated based on the accuracy predictor after training, and the search can be performed based on the accuracy of the candidate sub-networks.

[0362] ◆Search to obtain neural network models

[0363] It should be noted that the embodiments of this application can search for and obtain the neural network model according to the constraint of satisfying the maximum accuracy.

[0364] In other words, the candidate subnetwork corresponding to the maximum accuracy of at least one candidate subnetwork is taken as the neural network model.

[0365] In this way, the neural network model satisfies the performance constraints of computing power and accuracy, enabling the search to obtain sub-networks with both excellent computing power and accuracy, thus making the distance between the first terminal device and the user output from the neural network model more accurate.

[0366] III. Exemplary Description of a Transmission Power Regulation Device

[0367] 1. Description

[0368] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the terminal device includes the corresponding hardware structure and / or software modules for executing each function. Those skilled in the art should recognize that the methods, functions, modules, units, or steps described in conjunction with the embodiments provided herein can be implemented in hardware or a combination of hardware and computer software. Whether a method, function, module, unit, or step is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described methods, functions, modules, units, or steps for each specific application, but such implementation should not be considered beyond the scope of this application.

[0369] This application embodiment can divide the terminal device into functional units / modules according to the above method example. For example, each function can be divided into a separate functional unit / module, or two or more functions can be integrated into one functional unit / module. The integrated functional unit / module can be implemented in hardware or software. It should be noted that the division of functional units / modules in this application embodiment is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods.

[0370] When using integrated units, Figure 9 This is a functional unit block diagram of a transmission power regulation device according to an embodiment of this application. The transmission power regulation device 900 specifically includes: an acquisition unit 910 and a regulation unit 920.

[0371] It should be noted that the acquisition unit 910 can be a module unit used for acquiring information, etc., and there are no specific restrictions on it.

[0372] The control unit 920 can be a module unit used for processing or controlling the transmission power, etc., and there are no specific limitations on it.

[0373] In some possible implementations, the acquisition unit 910 and the control unit 920 can be integrated into one unit or integrated into different units.

[0374] For example, the acquisition unit 910 and the control unit 920 can be integrated into the processing unit.

[0375] For example, the acquisition unit 910 can be integrated into the communication unit, and the control unit 920 can be integrated into the processing unit.

[0376] It should be noted that the processing unit can be a processor or controller, such as a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processing unit can also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0377] In some possible implementations, the transmit power regulation device 900 may also include a storage unit for storing computer programs or instructions executed by the transmit power regulation device 900.

[0378] For example, the storage unit could be a memory.

[0379] In some possible implementations, the transmit power regulation device 900 can be a chip / chip module / processor / hardware, etc.

[0380] In specific implementation, the transmit power regulation device 900 is used to perform the steps described in the above method embodiments. A detailed explanation follows.

[0381] The acquisition unit 910 is used to acquire the channel state information (CSI) of multiple subcarriers of the Wi-Fi signal and determine the distance between the first terminal device and the user based on the CSI of the multiple subcarriers.

[0382] The control unit 920 is used to reduce the transmission power of the mobile cellular signal to a target power threshold or below if the distance between the first terminal device and the user is less than a preset distance, and to restore the transmission power of the mobile cellular signal when the distance between the first terminal device and the user is greater than or equal to the preset distance again. The target power threshold is the minimum transmission power required to ensure successful transmission of the mobile cellular signal.

[0383] The control unit 920 is also used to maintain the transmission power of the mobile cellular signal if the distance between the first terminal device and the user is greater than or equal to a preset distance.

[0384] Based on this, this application can determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers of the WiFi signal, and then determine whether it is necessary to reduce the transmission power of the mobile cellular signal to the target power threshold based on the relationship between the distance and the preset distance.

[0385] If the distance is less than the preset distance, it means that the user is very close to the first terminal device. In order to ensure the successful transmission of mobile cellular signals while avoiding the impact of electromagnetic radiation from the first terminal device on the user, this application can reduce the transmission power of mobile cellular signals to the target power threshold, thereby minimizing the SAR of the first terminal device while ensuring the reliability of mobile cellular communication.

[0386] Of course, this application can also reduce the transmission power of the mobile cellular signal to below the target power threshold. Although this may not guarantee successful mobile cellular signal transmission, it can significantly reduce the SAR of the first terminal device.

[0387] Then, when the distance is greater than or equal to the preset distance again, it indicates that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order to avoid reducing the reliability of mobile cellular communication due to insufficient transmission power, this application needs to restore the transmission power of the mobile cellular signal.

[0388] Finally, if the distance is greater than or equal to the preset distance, it means that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order not to affect the mobile cellular communication, this application needs to continue to maintain the transmission power of the mobile cellular signal without adjusting the transmission power.

[0389] It should be noted that the specific implementation of each operation performed by the power control device 900 can be found in the corresponding description of the method embodiment shown above, and will not be repeated here.

[0390] 2. Other implementation methods

[0391] The following section will explain some of the implementation methods involved. For other content not covered, please refer to the above description for details, which will not be repeated here.

[0392] In some possible implementations, the acquisition unit 910 is used to: determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers.

[0393] Feature extraction is performed on the CSI of multiple subcarriers to obtain feature information, which is used to reflect the user's motion state and position state;

[0394] The feature information is input into the trained neural network model to output the distance between the first terminal device and the user.

[0395] It should be noted that, based on the content of "5) How to determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers" above, there are no specific restrictions on this.

[0396] In some possible implementations, the acquisition unit 910 is used for: extracting features from the CSI of multiple subcarriers to obtain feature information.

[0397] The CSI of each subcarrier in the CSI of multiple subcarriers is sequentially denoised, linear time-domain interpolated, and wavelet transformed.

[0398] Calculate the variance of the CSI amplitude of each subcarrier within a preset sliding time window to obtain the characteristic variance of each subcarrier;

[0399] Calculate the feature variance matrix of each subcarrier within a preset time period to obtain feature information.

[0400] It should be noted that, based on the content in "b. Feature Information" above, there are no specific restrictions on this.

[0401] In some possible implementations, the neural network model is obtained through the following steps:

[0402] Obtain the search space for the preset neural network architecture;

[0403] A supernet for search is constructed based on a pre-defined neural network architecture using the search space and the directed acyclic graph.

[0404] Search for the target subnetwork from the supernet of the pre-trained neural network architecture;

[0405] Adjust the hyperparameters of the target subnetwork to obtain the supernet for the target neural network architecture search;

[0406] The neural network model is obtained by searching the supernet of the trained target neural network architecture.

[0407] It should be noted that, based on the content in "d. the process of obtaining the neural network model" above, there are no specific restrictions on this.

[0408] In some possible implementations, the acquisition unit 910 is used for: acquiring the CSI of multiple subcarriers of the WiFi signal.

[0409] Receive a first WiFi measurement signal and / or a first channel measurement result from an access point. The first WiFi measurement signal is used by the first terminal device to measure the WiFi channel state between the first terminal device and the access point to obtain a second channel measurement result. The first channel measurement result represents the measurement result of the WiFi channel state between the access point and the second terminal device. Use the first channel measurement result and / or the second channel measurement result as the CSI of multiple subcarriers of the WiFi signal; or,

[0410] Send a second WiFi measurement signal to the access point, the second WiFi measurement signal being used by the access point to measure the WiFi channel state between the first terminal device and the access point to obtain a third channel measurement result; receive the first channel measurement result and / or the third channel measurement result from the access point; use the first channel measurement result and / or the third channel measurement result as the CSI of multiple subcarriers of the WiFi signal; or,

[0411] Receive a third WiFi measurement signal and / or a first channel measurement result from a second terminal device, wherein the third WiFi measurement signal is used by the first terminal device to measure the WiFi channel state between the first terminal device and the second terminal device to obtain a fourth channel measurement result; use the first channel measurement result and / or the fourth channel measurement result as the CSI of multiple subcarriers of the WiFi signal; or,

[0412] Send a fourth WiFi measurement signal to the second terminal device. The fourth WiFi measurement signal is used by the second terminal device to measure the WiFi channel status between the first terminal device and the second terminal device to obtain a fifth channel measurement result; receive the first channel measurement result and / or the fifth channel measurement result from the second terminal device; and use the first channel measurement result and / or the fifth channel measurement result as the CSI of multiple subcarriers of the WiFi signal.

[0413] It should be noted that, based on the content of "3) How to obtain the CSI of multiple subcarriers of the WiFi signal" above, there are no specific restrictions on this.

[0414] In some possible implementations, prior to acquiring the CSI of multiple subcarriers of the WiFi signal, the acquisition unit 910 is also used for:

[0415] Send a first request message to the access point, the first request message being used to request the establishment of WiFi sensing with the access point; receive a first response message from the access point, the first response message being used to indicate that the WiFi sensing establishment between the first terminal device and the access point is complete; and / or

[0416] Send a second request message to the access point, the second request message being used to request the access point to identify the second terminal device that will participate in establishing WiFi awareness together with the first terminal device; receive a second response message from the access point, the second response message being used to indicate the device identifier of the second terminal device.

[0417] It should be noted that, based on the above content regarding "b. the second terminal device that participates in establishing WiFi awareness together with the first terminal device," there are no specific restrictions on this.

[0418] In some possible implementations, after receiving the second response information from the access point, the acquisition unit 910 is further configured to:

[0419] A third request message is sent to the second terminal device based on the device identifier of the second terminal device. The third request message is used to request the establishment of WiFi sensing with the third terminal device.

[0420] Receive a third response message from the second terminal device, the third response message being used to indicate that the WiFi sensing between the first terminal device and the second terminal device has been established.

[0421] It should be noted that, based on the content of "c. Establishing WiFi sensing between the first terminal device and the second terminal device" above, there are no specific restrictions on this.

[0422] IV. Exemplary Description of a Terminal Device

[0423] The following is a schematic diagram of the structure of a terminal device according to an embodiment of this application, such as... Figure 10 As shown. Among them, terminal device 1000 is a first terminal device, including processor 1010, memory 1020 and at least one communication bus for connecting processor 1010 and memory 1020.

[0424] In some possible implementations, processor 1010 may be one or more central processing units (CPUs). If processor 1010 is a CPU, the CPU may be a single-core CPU or a multi-core CPU. Memory 1020 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), and memory 1020 is used to store computer programs or instructions.

[0425] In some possible implementations, the terminal device 1000 also includes a communication interface for receiving and sending data.

[0426] In some possible implementations, the processor 1010 in the terminal device 1000 is used to execute a computer program or instruction 1021 stored in the memory 1020 to perform the following steps:

[0427] The channel state information (CSI) of multiple subcarriers of the Wi-Fi signal is obtained, and the distance between the first terminal device and the user is determined based on the CSI of the multiple subcarriers.

[0428] If the distance between the first terminal device and the user is less than the preset distance, the transmission power of the mobile cellular signal will be reduced to the target power threshold or below, and the transmission power of the mobile cellular signal will be restored when the distance between the first terminal device and the user is greater than or equal to the preset distance again. The target power threshold is the minimum transmission power required to ensure successful transmission of the mobile cellular signal.

[0429] If the distance between the first terminal device and the user is greater than or equal to the preset distance, the transmission power of the mobile cellular signal will continue to be maintained.

[0430] Based on this, this application can determine the distance between the first terminal device and the user based on the CSI of multiple subcarriers of the WiFi signal, and then determine whether it is necessary to reduce the transmission power of the mobile cellular signal to the target power threshold based on the relationship between the distance and the preset distance.

[0431] If the distance is less than the preset distance, it means that the user is very close to the first terminal device. In order to ensure the successful transmission of mobile cellular signals while avoiding the impact of electromagnetic radiation from the first terminal device on the user, this application can reduce the transmission power of mobile cellular signals to the target power threshold, thereby minimizing the SAR of the first terminal device while ensuring the reliability of mobile cellular communication.

[0432] Of course, this application can also reduce the transmission power of the mobile cellular signal to below the target power threshold. Although this may not guarantee successful mobile cellular signal transmission, it can significantly reduce the SAR of the first terminal device.

[0433] Then, when the distance is greater than or equal to the preset distance again, it indicates that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order to avoid reducing the reliability of mobile cellular communication due to insufficient transmission power, this application needs to restore the transmission power of the mobile cellular signal.

[0434] Finally, if the distance is greater than or equal to the preset distance, it means that the user is far away from the first terminal device. At this time, the electromagnetic radiation of the first terminal device has little impact on the user. In order not to affect the mobile cellular communication, this application needs to continue to maintain the transmission power of the mobile cellular signal without adjusting the transmission power.

[0435] It should be noted that the specific implementation of each operation performed by the terminal device 1000 can be found in the corresponding description of the method embodiment shown above, and will not be repeated here.

[0436] V. Other Exemplary Descriptions

[0437] This application also provides a computer-readable storage medium storing a computer program or instructions that, when executed by a processor, implement the steps described in the above embodiments.

[0438] This application also provides a computer program product, including a computer program or instructions, wherein the computer program or instructions, when executed by a processor, implement the steps described in the above embodiments. For example, the computer program product may be a software installation package.

[0439] In addition, computer program products should be understood as software products that primarily implement the technical solutions of this application through computer programs or instructions.

[0440] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0441] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0442] Those skilled in the art should understand that the functions of the methods, steps, or related modules / units described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product, or by a processor executing computer program instructions. The computer program product includes at least one computer program instruction, which can be composed of corresponding software modules. These software modules can be stored in RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, portable hard disk, read-only optical disc (CD-ROM), or any other form of storage medium well known in the art. The computer program instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media, or semiconductor media (e.g., SSDs).

[0443] The modules / units included in the various devices or products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of software modules / units and hardware modules / units. For example, for devices or products where the application is applied to or integrated into a chip, all of their modules / units can be implemented using hardware methods such as circuits; or, some of their modules / units can be implemented using software programs that run on a processor integrated within the chip, while other (if any) modules / units can be implemented using hardware methods such as circuits. The same principle applies to devices or products where the application is applied to or integrated into a chip module, or devices or products where the application is applied to or integrated into a terminal.

[0444] The above detailed embodiments further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above are merely specific implementations of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made based on the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A method for controlling transmission power, characterized in that, Applied to the first terminal device, including: The method involves acquiring Channel State Information (CSI) of multiple subcarriers of a Wi-Fi signal and determining the distance between the first terminal device and the user based on the CSI of the multiple subcarriers. Acquiring the CSI of the multiple subcarriers of the Wi-Fi signal includes: receiving a first Wi-Fi measurement signal and a first channel measurement result from an access point; the first Wi-Fi measurement signal is used by the first terminal device to measure the Wi-Fi channel state between the first terminal device and the access point to obtain a second channel measurement result; the first channel measurement result represents the measurement result of the Wi-Fi channel state between the access point and the second terminal device; and using the first channel measurement result and the second channel measurement result as... The second terminal device is a terminal device that works in conjunction with the first terminal device to perform WiFi sensing, based on the CSI of multiple subcarriers of the WiFi signal. The CSI of each subcarrier is sequentially denoised, linearly interpolated in the time domain, and subjected to wavelet transform. The variance of the amplitude of the CSI of each subcarrier within a preset sliding time window is calculated to obtain the characteristic variance of each subcarrier. The characteristic variance matrix of the characteristic variance of each subcarrier within a preset time period is calculated to obtain feature information, which reflects the user's motion and position. The feature information is input into a trained neural network model to output the distance between the first terminal device and the user. If the distance between the first terminal device and the user is less than a preset distance, the transmission power of the mobile cellular signal will be reduced to a target power threshold or below, and the transmission power of the mobile cellular signal will be restored when the distance between the first terminal device and the user is greater than or equal to the preset distance again. The target power threshold is the minimum transmission power required to ensure successful transmission of the mobile cellular signal. If the distance between the first terminal device and the user is greater than or equal to the preset distance, the transmission power of the mobile cellular signal will continue to be maintained.

2. The method according to claim 1, characterized in that, The neural network model was obtained according to the following steps: Obtain the search space for the preset neural network architecture; Construct the supernet for the preset neural network architecture search based on the search space and the directed acyclic graph; Search for the target subnetwork from the supernet trained using the preset neural network architecture; The hyperparameters of the target sub-network are adjusted to obtain the supernet for the target neural network architecture search; The neural network model is obtained by searching the supernet of the target neural network architecture after training.

3. The method according to claim 1, characterized in that, The CSI for acquiring multiple subcarriers of the WiFi signal also includes: Send a second WiFi measurement signal to the access point, the second WiFi measurement signal being used by the access point to measure the WiFi channel state between the first terminal device and the access point to obtain a third channel measurement result; receive the first channel measurement result and / or the third channel measurement result from the access point; use the first channel measurement result and / or the third channel measurement result as the CSI of multiple subcarriers of the WiFi signal; or... Receive a third WiFi measurement signal and / or the first channel measurement result from the second terminal device, wherein the third WiFi measurement signal is used by the first terminal device to measure the WiFi channel state between the first terminal device and the second terminal device to obtain a fourth channel measurement result; use the first channel measurement result and / or the fourth channel measurement result as the CSI of multiple subcarriers of the WiFi signal; or... Send a fourth WiFi measurement signal to the second terminal device, the fourth WiFi measurement signal being used by the second terminal device to measure the WiFi channel state between the first terminal device and the second terminal device to obtain a fifth channel measurement result; receive the first channel measurement result and / or the fifth channel measurement result from the second terminal device; and use the first channel measurement result and / or the fifth channel measurement result as the CSI of multiple subcarriers of the WiFi signal.

4. The method according to claim 3, characterized in that, Prior to acquiring the CSI of multiple subcarriers of the WiFi signal, the method further includes: Send a first request message to the access point, the first request message being used to request the establishment of WiFi sensing with the access point; receive a first response message from the access point, the first response message being used to indicate that the WiFi sensing between the first terminal device and the access point has been established; and / or Send a second request message to the access point, the second request message being used to request the access point to identify the second terminal device that participates in establishing WiFi sensing together with the first terminal device; receive a second response message from the access point, the second response message being used to indicate the device identifier of the second terminal device.

5. The method according to claim 4, characterized in that, After receiving the second response information from the access point, the method further includes: A third request message is sent to the second terminal device according to the device identifier of the second terminal device. The third request message is used to request the establishment of WiFi sensing with the third terminal device. The system receives a third response message from the second terminal device, the third response message indicating that the WiFi sensing between the first terminal device and the second terminal device has been established.

6. A power transmission regulation device, characterized in that, Applied to a first terminal device, the device includes: An acquisition unit is configured to acquire Channel State Information (CSI) of multiple subcarriers of a Wi-Fi signal, and determine the distance between the first terminal device and the user based on the CSI of the multiple subcarriers. Acquiring the CSI of the multiple subcarriers of the Wi-Fi signal includes: receiving a first Wi-Fi measurement signal and / or a first channel measurement result from an access point; the first Wi-Fi measurement signal is used by the first terminal device to measure the Wi-Fi channel state between the first terminal device and the access point to obtain a second channel measurement result; the first channel measurement result represents the measurement result of the Wi-Fi channel state between the access point and the second terminal device; and converting the first channel measurement result and / or the second channel measurement result into a data transfer value. The measurement results are used as the CSI of multiple subcarriers of the WiFi signal. The second terminal device is a terminal device that works in conjunction with the first terminal device to perform WiFi sensing. Specifically, the CSI of each subcarrier is sequentially denoised, linearly interpolated in the time domain, and subjected to wavelet transform. The variance of the amplitude of the CSI of each subcarrier within a preset sliding time window is calculated to obtain the characteristic variance of each subcarrier. The characteristic variance matrix of the characteristic variance of each subcarrier within a preset time period is calculated to obtain feature information, which reflects the user's motion and position. The feature information is input into a trained neural network model to output the distance between the first terminal device and the user. The control unit is configured to reduce the transmission power of the mobile cellular signal to a target power threshold or below if the distance between the first terminal device and the user is less than a preset distance, and to restore the transmission power of the mobile cellular signal when the distance between the first terminal device and the user is greater than or equal to the preset distance again. The target power threshold is the minimum transmission power required to ensure successful transmission of the mobile cellular signal. The control unit is further configured to maintain the transmission power of the mobile cellular signal if the distance between the first terminal device and the user is greater than or equal to the preset distance.

7. A terminal device, characterized in that, The terminal device is a first terminal device, including a processor, a memory, and a computer program or instructions stored in the memory. The processor executes the computer program or instructions to implement the steps of the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores a computer program or instructions that, when executed, implement the steps of the method described in any one of claims 1-5.

Images