WO2022218135A1 - 工作模式调整方法、装置及存储介质 - Google Patents

工作模式调整方法、装置及存储介质 Download PDF

Info

Publication number
WO2022218135A1
WO2022218135A1 PCT/CN2022/083121 CN2022083121W WO2022218135A1 WO 2022218135 A1 WO2022218135 A1 WO 2022218135A1 CN 2022083121 W CN2022083121 W CN 2022083121W WO 2022218135 A1 WO2022218135 A1 WO 2022218135A1
Authority
WO
WIPO (PCT)
Prior art keywords
communication state
time
moment
working mode
predicted value
Prior art date
Application number
PCT/CN2022/083121
Other languages
English (en)
French (fr)
Inventor
黄超
郭翱
姜建
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2022218135A1 publication Critical patent/WO2022218135A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/14—Reselecting a network or an air interface
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/0005—Control or signalling for completing the hand-off
    • H04W36/0083—Determination of parameters used for hand-off, e.g. generation or modification of neighbour cell lists
    • H04W36/0085—Hand-off measurements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/24—Reselection being triggered by specific parameters
    • H04W36/30—Reselection being triggered by specific parameters by measured or perceived connection quality data
    • H04W36/302—Reselection being triggered by specific parameters by measured or perceived connection quality data due to low signal strength

Definitions

  • the present application relates to the field of communication technologies, and in particular, to a working mode adjustment method, device and storage medium.
  • the terminal device In data services, it is usually necessary to adjust the working mode of the terminal device according to the network environment. For example, in the dual-card data service of the terminal device, sometimes the main card has a poor signal and needs to switch to the secondary card for communication.
  • the Wi-Fi signal fluctuates or the signal is poor, and it is necessary to temporarily switch to data traffic to support the current data service scenario.
  • an embodiment of the present application provides a working mode adjustment method, the method is applied to a terminal device, and the method includes: determining a coherence time window length corresponding to a current first working mode of the terminal device; A predicted value of the communication state of the terminal device is determined according to the length of the coherence time window and a plurality of historical values of the communication state of the terminal device in the first working mode, where the communication state includes signal strength, transmission at least one of delay or network bandwidth; when the predicted value satisfies a preset condition, adjust the working mode of the terminal device to a second working mode, wherein the second working mode is the same as the The channels of the first working mode are different, and the preset conditions include that the signal strength in the predicted value is less than or equal to a preset signal strength threshold, and the transmission delay in the predicted value is greater than or equal to the preset transmission delay At least one of the threshold and the network bandwidth in the predicted value is less than or equal to a preset network bandwidth threshold.
  • the coherent time window length (ie, different channel scenarios) can be considered when determining the predicted value of the communication state of the terminal device, and when the predicted value of the communication state meets the preset condition, the The working mode of the terminal device can be adjusted in advance, so that the working mode of the terminal device can be adjusted in advance in the case of poor communication status (such as weak signal, large transmission delay, small network bandwidth, etc.), reducing the communication process.
  • the stuck feeling makes users not feel the network fluctuations during the communication process, which effectively improves the user experience.
  • the multiple historical values of the communication state include the communication states at L first moments before the current moment, and the The predicted value includes the predicted value of the communication state at M second moments after the current moment, and the length of the coherent time window is N, where L, M, N are integers, L>N>1, M ⁇ 1,
  • the weighting coefficient corresponding to the first second moment is determined, and the weighting coefficient corresponding to the first second moment is determined by: weights of communication states at multiple first moments in the coherence time window indicating the first second moment; according to the weight coefficient corresponding to the first second moment, the L-N+1th From the communication state from one time to the Lth first time, the predicted value of the communication state at the first second time is determined.
  • the weight coefficients can be trained according to the coherent time window length N and the communication states of the L first moments, to obtain the weight coefficients corresponding to the first second moment, and according to the first second moment
  • the The multiple historical values of the communication state in the mode, and determining the predicted value of the communication state of the terminal device further comprising: in the case of M>1, for the jth second moment, according to the coherence time window length N , the communication state of the L first moments, the predicted value of the communication state from the first second time to the j-1th second time, and the weight coefficient corresponding to the j-1th second time, determine the The weight coefficient corresponding to the jth second moment, the weight coefficient corresponding to the jth second moment is used to indicate the communication state and the second moment in the coherence time window of the jth second moment
  • the weight of the predicted value of the communication state at the moment where 1 ⁇ j ⁇ M ⁇ N; according to the weight coefficient corresponding to the jth second moment, the coherence time window length N, and the L first moments
  • the communication state at the j+1th second time can be calculated. Iterative prediction is performed to obtain the predicted value of the communication state at the j+1th second moment, thereby realizing multi-step prediction.
  • the communication according to the coherence time window length N and the L first moments state determining the weight coefficient corresponding to the first second moment, including: according to the i-1th group of weight coefficients, the communication state from the ith first moment to the i+N-1th first moment, determining the ith +N predicted values of the communication state at the first moment, i is an integer and 0 ⁇ i ⁇ L-N, the 0th group of weight coefficients is the initial value of the weight coefficients; according to the i-1th group of weight coefficients, the i+Nth The communication state at a moment and the predicted value of the communication state at the i+Nth first moment are determined to determine the i-th group of weight coefficients; the L-N+1-th group of weight coefficients are determined to correspond to the first second moment. weight factor.
  • the weight coefficients are trained by the above-mentioned stochastic gradient descent method, and the weight coefficients corresponding to the first second moment are obtained, so that the weight coefficients can be adaptively adjusted to adapt to different channel scenarios, so that the Improve the accuracy of weight coefficients.
  • the communication according to the coherence time window length N and the L first moments state, and determining the weight coefficient corresponding to the first second time including: preprocessing the L communication states at the first time to obtain L preprocessed communication states at the first time, the preprocessing Including normalization and differential processing; according to the length of the coherent time window N and the preprocessed communication state of the L first moments, determine the differential weight coefficient corresponding to the first second moment;
  • determining the communication state of the first second time according to the weight coefficient corresponding to the first second time and the communication state from the L-N+1th first time to the L first time includes: determining the first time according to the difference weight coefficient corresponding to the first second time and the preprocessed communication state from the L-N+1 first time to the Lth first time A differential predicted value of the communication state at the second moment; post-processing the differential predicted value to obtain the first predicted value of the communication state at the second moment, and the post-processing includes inverse difference and inverse normalization processing.
  • preprocessing such as normalization and difference can be performed on the communication states of the L first moments, so as to obtain the preprocessed communication states of the L first moments, and according to the lengths of the coherent time windows N and L
  • For the preprocessed communication state at the first moment determine the differential weight coefficient corresponding to the first second moment, and then determine the differential predicted value of the first second communication state, and then perform the inverse difference on the differential predicted value and post-processing such as inverse normalization to obtain the predicted value of the communication state at the first second moment, and when the predicted value satisfies the preset condition, adjust the working mode of the terminal device to the second working mode, thereby
  • preprocessing the communication state the non-stationarity of the communication state can be reduced, and prediction is made based on the communication state after the preprocessing, which can improve the prediction accuracy of the communication state.
  • the first working mode and the first working mode is any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode.
  • the first working mode is any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode
  • the second working mode is also the main card data traffic working mode, Any one of the data traffic working mode of the secondary card and the Wi-Fi wireless communication working mode, so that the working mode of the terminal device can be between the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode. switch.
  • an embodiment of the present application provides an apparatus for adjusting a working mode, the apparatus is applied to a terminal device, and the apparatus includes: a coherence time window determination module, configured to determine the current first working mode of the terminal device The length of the coherence time window corresponding to the mode; the prediction module is configured to determine the communication state of the terminal device according to the length of the coherence time window and a plurality of historical values of the communication state of the terminal device in the first working mode The predicted value of , the communication state includes at least one of signal strength, transmission delay or network bandwidth; an adjustment module, configured to adjust the working mode of the terminal device when the predicted value satisfies a preset condition Adjusting to a second working mode, wherein the channel of the second working mode is different from that of the first working mode, and the preset condition includes that the signal strength in the predicted value is less than or equal to a preset signal strength threshold, At least one of the transmission delay in the predicted value is greater than or equal to a preset transmission delay threshold, and the
  • the coherent time window length (ie, different channel scenarios) can be considered when determining the predicted value of the communication state of the terminal device, and when the predicted value of the communication state meets the preset condition, the The working mode of the terminal device can be adjusted in advance, so that the working mode of the terminal device can be adjusted in advance in the case of poor communication status (such as weak signal, large transmission delay, small network bandwidth, etc.), reducing the communication process.
  • the stuck feeling makes users not feel the network fluctuations during the communication process, which effectively improves the user experience.
  • the multiple historical values of the communication state include the communication states at L first moments before the current moment, and the The predicted value includes the predicted value of the communication state at M second moments after the current moment, and the length of the coherent time window is N, where L, M, N are integers, L>N>1, M ⁇ 1,
  • the weight coefficients can be trained according to the coherent time window length N and the communication states of the L first moments, to obtain the weight coefficients corresponding to the first second moment, and according to the first second moment
  • the prediction module further includes: a second coefficient determination sub-module, configured to determine In the case of 1, for the jth second time, according to the coherence time window length N, the communication state of the L first time, the communication from the first second time to the j-1th second time
  • the predicted value of the state and the weight coefficient corresponding to the j-1th second moment determine the weight coefficient corresponding to the jth second moment, and the weight coefficient corresponding to the jth second moment is used to indicate the The weight of the communication state at the first time and the predicted value of the communication state at the second time in the coherence time window of the jth second time, where 1 ⁇ j ⁇ M ⁇ N;
  • the second prediction sub-module is used for according to the weight coefficient corresponding to the jth second time, the coherence time window length N, the communication state of the L first time, and the communication from the first second time to the j-1th second time
  • the communication state at the j+1th second time can be calculated. Iterative prediction is performed to obtain the predicted value of the communication state at the j+1th second moment, thereby realizing multi-step prediction.
  • the first coefficient determination sub-module is configured to: according to the i-1th group of weights coefficient, the communication state from the ith first moment to the i+N-1th first moment, determine the predicted value of the communication state at the i+Nth first moment, i is an integer and 0 ⁇ i ⁇ L-N, the The 0th group of weight coefficients is the initial value of the weight coefficient; according to the i-1th group of weight coefficients, the communication state of the i+Nth first moment, and the predicted value of the communication state of the i+Nth first moment, determine the ith Group weight coefficient; the L-N+1 group weight coefficient is determined as the weight coefficient corresponding to the first second moment.
  • the weight coefficients are trained by the above-mentioned stochastic gradient descent method, and the weight coefficients corresponding to the first second moment are obtained, so that the weight coefficients can be adaptively adjusted to adapt to different channel scenarios, so that the Improve the accuracy of weight coefficients.
  • the first coefficient determination submodule is configured to: The communication state at the time is preprocessed to obtain L preprocessed communication states at the first time. The processed communication state determines the differential weight coefficient corresponding to the first second moment;
  • the first prediction sub-module is configured to: according to the difference weight coefficient corresponding to the first second moment and the preprocessing from the L-N+1th first moment to the Lth first moment After the communication state is obtained, the difference prediction value of the communication state at the first second time is determined; the difference prediction value is post-processed to obtain the prediction value of the communication state at the first second time.
  • Post-processing includes inverse difference and inverse normalization.
  • preprocessing such as normalization and difference can be performed on the communication states of the L first moments, so as to obtain the preprocessed communication states of the L first moments, and according to the lengths of the coherent time windows N and L
  • For the preprocessed communication state at the first moment determine the differential weight coefficient corresponding to the first second moment, and then determine the differential predicted value of the first second communication state, and then perform the inverse difference on the differential predicted value and post-processing such as inverse normalization to obtain the predicted value of the communication state at the first second moment, and when the predicted value satisfies the preset condition, adjust the working mode of the terminal device to the second working mode, thereby
  • preprocessing the communication state the non-stationarity of the communication state can be reduced, and prediction is made based on the communication state after the preprocessing, which can improve the prediction accuracy of the communication state.
  • the first working mode and the first working mode is any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode.
  • the first working mode is any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode
  • the second working mode is also the main card data traffic working mode, Any one of the data traffic working mode of the secondary card and the Wi-Fi wireless communication working mode, so that the working mode of the terminal device can be between the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode. switch.
  • an embodiment of the present application provides an apparatus for adjusting a working mode, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above when executing the instructions
  • the first aspect or one or more working mode adjustment methods in multiple possible implementation manners of the first aspect.
  • the coherent time window length (ie, different channel scenarios) can be considered when determining the predicted value of the communication state of the terminal device, and when the predicted value of the communication state meets the preset condition, the The working mode of the terminal device can be adjusted in advance, so that the working mode of the terminal device can be adjusted in advance in the case of poor communication status (such as weak signal, large transmission delay, small network bandwidth, etc.), reducing the communication process.
  • the stuck feeling makes users not feel the network fluctuations during the communication process, which effectively improves the user experience.
  • embodiments of the present application provide a non-volatile computer-readable storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above-mentioned first aspect or the first aspect is implemented One or several working mode adjustment methods in a variety of possible implementation manners.
  • the coherent time window length (ie, different channel scenarios) can be considered when determining the predicted value of the communication state of the terminal device, and when the predicted value of the communication state meets the preset condition, the The working mode of the terminal device can be adjusted in advance, so that the working mode of the terminal device can be adjusted in advance in the case of poor communication status (such as weak signal, large transmission delay, small network bandwidth, etc.), reducing the communication process.
  • the stuck feeling makes users not feel the network fluctuations during the communication process, which effectively improves the user experience.
  • embodiments of the present application provide a computer program product, comprising computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer-readable codes are stored in an electronic
  • the processor in the electronic device executes the first aspect or one or more of the working mode adjustment methods in the multiple possible implementation manners of the first aspect.
  • the coherent time window length (ie, different channel scenarios) can be considered when determining the predicted value of the communication state of the terminal device, and when the predicted value of the communication state meets the preset condition, the The working mode of the terminal device can be adjusted in advance, so that the working mode of the terminal device can be adjusted in advance in the case of poor communication status (such as weak signal, large transmission delay, small network bandwidth, etc.), reducing the communication process.
  • the stuck feeling makes users not feel the network fluctuations during the communication process, which effectively improves the user experience.
  • FIG. 1 shows a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • FIG. 2 shows a schematic diagram of an application scenario of a method for adjusting a working mode according to an embodiment of the present application.
  • FIG. 3 shows a schematic diagram of an application scenario of a method for adjusting a working mode according to an embodiment of the present application.
  • FIG. 4 shows a flowchart of a method for adjusting a working mode according to an embodiment of the present application.
  • FIG. 5 shows a flowchart of a method for adjusting a working mode according to an embodiment of the present application.
  • FIG. 6 shows a block diagram of an apparatus for adjusting a working mode according to an embodiment of the present application.
  • the signal collector (such as modem processor, etc.) at the bottom of the terminal device collects the signal in real time, and reports the collected signal to the upper layer of the terminal device; the upper layer of the terminal device reads the signal reported by the bottom layer, and reads the The obtained signal is compared with a preset threshold; when the read signal is smaller than the preset threshold, the working mode of the terminal device is adjusted.
  • the acquisition cycle of the signal collector at the bottom layer of the terminal device is generally 100ms
  • the cycle of reading the signal at the upper layer of the terminal device is generally 1s, that is, the upper layer of the terminal device will filter the signal reported by the bottom layer, and then process the signal according to the filtering process. After the signal, make a decision on whether to adjust the working mode.
  • weak signal coupled with the delay of upper-layer filtering processing
  • the user has obviously felt stuck, and the timeliness is poor, which affects the user experience.
  • the signal at the next moment can be predicted based on a fixed time window length and filter coefficient, and the prediction result can be used to determine whether the working mode of the terminal device needs to be adjusted.
  • this scheme uses the prediction result to judge the adjustment of the working mode of the terminal equipment, it sets the time window length and filter coefficient to fixed values based on the experience value, which cannot adapt to the channel changes in different scenarios, and there is also the work of adjusting the terminal equipment. The user has clearly felt the problem of stuttering in the mode.
  • the terminal device reports real-time network conditions to the server, and the server distributes appropriate streams accordingly.
  • This method also has a processing delay, which is likely to cause short-term video freezes and poor user experience.
  • the working mode adjustment method of the embodiment of the present application can consider the coherent time window length (ie, different channel scenarios) when determining the predicted value of the communication state of the terminal device. , and adjust the working mode of the terminal device when the predicted value of the communication state satisfies the preset conditions, so that the communication state can be poor (such as weak signal, large transmission delay, small network bandwidth, etc.) Under the circumstance, the working mode of the terminal device is adjusted in advance to reduce the stuck feeling during the communication process, so that the user does not feel the network fluctuation during the communication process, and the user experience is effectively improved.
  • the coherent time window length ie, different channel scenarios
  • the communication state includes at least one of signal strength, transmission delay, or network bandwidth
  • the preset condition includes that the signal strength in the predicted value of the communication state is less than or equal to a preset signal strength threshold, the At least one of the transmission delay in the predicted value is greater than or equal to a preset transmission delay threshold, and the network bandwidth in the predicted value of the communication state is less than or equal to the preset network bandwidth threshold.
  • the communication state may also include other communication information, and accordingly, the preset condition may be set according to the specific content included in the communication state.
  • the specific content included in the communication state and the preset condition can set according to the actual situation, which is not limited in this application.
  • the working mode adjustment method in the embodiment of the present application can be applied to a terminal device.
  • the terminal device may be an intelligent terminal device with wireless communication function.
  • Wireless communication includes communication through wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), 2G/3G/4G/5G networks, etc. No restrictions apply.
  • WLAN wireless local area networks
  • Wi-Fi wireless fidelity
  • 2G/3G/4G/5G networks etc. No restrictions apply.
  • the terminal device of the present application may also have the function of communicating by wired connection.
  • the terminal device in this embodiment of the present application may have a touch screen, a non-touch screen, or no screen, and the touch screen can be used to click, slide, etc. on the display screen with a finger, a stylus, or the like.
  • non-touch screen terminal devices can be connected to input devices such as mouse, keyboard, touch panel, etc., and the terminal device can be controlled through the input device.
  • the terminal device without a screen can be a Bluetooth speaker without a screen.
  • FIG. 1 shows a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • the terminal device 100 may include a cell phone, a foldable electronic device, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal computer Digital assistant (personal digital assistant, PDA), augmented reality (augmented reality, AR) device, virtual reality (virtual reality, VR) device, artificial intelligence (artificial intelligence, AI) device, wearable device, vehicle-mounted device, smart home equipment, or at least one of smart city equipment.
  • PDA personal digital assistant
  • augmented reality augmented reality, AR
  • VR virtual reality
  • AI artificial intelligence
  • wearable device wearable device
  • vehicle-mounted device smart home equipment
  • smart home equipment smart home equipment
  • the terminal device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) connector 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2 , mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, sensor module 180, buttons 190, motor 191, indicator 192, camera 193, display screen 194, and Subscriber identification module (subscriber identification module, SIM) card interface 195 and so on.
  • SIM Subscriber identification module
  • the sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, and ambient light. Sensor 180L, bone conduction sensor 180M, etc.
  • the terminal device 100 may include more or less components than those shown in the drawings, or combine some components, or separate some components, or arrange different components.
  • the illustrated components may be implemented in hardware, software, or a combination of software and hardware.
  • the processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (neural-network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.
  • the processor can generate an operation control signal according to the instruction operation code and timing signal, and complete the control of fetching and executing instructions.
  • a memory may also be provided in the processor 110 for storing instructions and data.
  • the memory in the processor 110 may be a cache memory.
  • the memory may store instructions or data that are used by the processor 110 or are frequently used. If the processor 110 needs to use the instructions or data, it can be called directly from this memory. Repeated accesses are avoided and the latency of the processor 110 is reduced, thereby increasing the efficiency of the system.
  • the processor 110 may include one or more interfaces.
  • the interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous transceiver (universal asynchronous transmitter) receiver/transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and / or universal serial bus (universal serial bus, USB) interface, etc.
  • the processor 110 may be connected to modules such as a touch sensor, an audio module, a wireless communication module, a display, a camera, and the like through at least one of the above interfaces.
  • the interface connection relationship between the modules illustrated in the embodiments of the present application is only a schematic illustration, and does not constitute a structural limitation of the terminal device 100 .
  • the terminal device 100 may also adopt different interface connection manners in the foregoing embodiments, or a combination of multiple interface connection manners.
  • the wireless communication function of the terminal device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modulation and demodulation processor, the baseband processor, and the like.
  • Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals.
  • Each antenna in terminal device 100 may be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization.
  • the antenna 1 can be multiplexed as a diversity antenna of the wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.
  • the mobile communication module 150 may provide a wireless communication solution including 2G/3G/4G/5G, etc. applied on the terminal device 100 .
  • the mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA) and the like.
  • the mobile communication module 150 can receive electromagnetic waves from the antenna 1, filter and amplify the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation.
  • the mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and then turn it into an electromagnetic wave for radiation through the antenna 1 .
  • at least part of the functional modules of the mobile communication module 150 may be provided in the processor 110 .
  • at least part of the functional modules of the mobile communication module 150 may be provided in the same device as at least part of the modules of the processor 110 .
  • the modem processor may include a modulator and a demodulator.
  • the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal.
  • the demodulator is used to demodulate the received electromagnetic wave signal into a low frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing.
  • the low frequency baseband signal is processed by the baseband processor and passed to the application processor.
  • the application processor outputs sound signals through audio devices (not limited to the speaker 170A, the receiver 170B, etc.), or displays images or videos through the display screen 194 .
  • the modem processor may be a stand-alone device.
  • the modem processor may be independent of the processor 110, and may be provided in the same device as the mobile communication module 150 or other functional modules.
  • the wireless communication module 160 can provide applications on the terminal device 100 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), bluetooth low power power consumption (bluetooth low energy, BLE), ultra wide band (UWB), global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions.
  • the wireless communication module 160 may be one or more devices integrating at least one communication processing module.
  • the wireless communication module 160 receives electromagnetic waves via the antenna 2 , frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110 .
  • the wireless communication module 160 can also receive the signal to be sent from the processor 110 , perform frequency modulation on it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2 .
  • the antenna 1 of the terminal device 100 is coupled with the mobile communication module 150, and the antenna 2 is coupled with the wireless communication module 160, so that the terminal device 100 can communicate with the network and other electronic devices through wireless communication technology.
  • the wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code Division Multiple Access (WCDMA), Time Division Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), BT, GNSS, WLAN, NFC, FM, and/or IR technology, etc.
  • the GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (quasi- zenith satellite system, QZSS) and/or satellite based augmentation systems (SBAS).
  • GPS global positioning system
  • GLONASS global navigation satellite system
  • BDS Beidou navigation satellite system
  • QZSS quasi-zenith satellite system
  • SBAS satellite based augmentation systems
  • the gyro sensor 180B may be used to determine the motion attitude of the terminal device 100 .
  • the angular velocity of the end device 100 about three axes ie, the x, y and z axes
  • the gyro sensor 180B may be used to measure the angular velocity of the end device.
  • the acceleration sensor 180E can detect the magnitude of the acceleration of the terminal device 100 in various directions (generally three axes). The magnitude and direction of gravity can be detected when the terminal device 100 is stationary. It can also be used to identify the posture of electronic devices, and can be used in applications such as horizontal and vertical screen switching, pedometers, etc. In some embodiments, the acceleration sensor 180E can be used to measure the movement acceleration of the terminal device, and the acceleration sensor 180E can also be combined with the gyro sensor 180B to determine the movement speed of the terminal device.
  • the SIM card interface 195 is used to connect a SIM card.
  • the SIM card can be contacted and separated from the terminal device 100 by inserting into the SIM card interface 195 or pulling out from the SIM card interface 195 .
  • the terminal device 100 may support one or more SIM card interfaces.
  • the SIM card interface 195 can support Nano SIM card, Micro SIM card, SIM card and so on. Multiple cards can be inserted into the same SIM card interface 195 at the same time. Multiple cards can be of the same type or different.
  • the SIM card interface 195 can also be compatible with different types of SIM cards.
  • the SIM card interface 195 is also compatible with external memory cards.
  • the terminal device 100 interacts with the network through the SIM card to realize functions such as calls and data communication.
  • the terminal device 100 adopts an eSIM, that is, an embedded SIM card.
  • the eSIM card can be embedded in the terminal device 100 and cannot be separated from the terminal device 100 .
  • one SIM card interface can be set as the main card interface, and the SIM card inserted into the main card interface is the main card of the terminal device; another SIM card interface is set as the secondary card interface.
  • Card interface the SIM card inserted into the secondary card interface is the secondary card of the terminal device.
  • the terminal device can communicate with other devices through the primary card or the secondary card.
  • the gyroscope sensor 180B, the acceleration sensor 180E, the mobile communication module 150, the wireless communication module 160, the modulation and demodulation processor and other acquisition and measurement modules of the terminal device 100 may report the acquisition to the processor 110 according to a preset period. sensor data and/or measured signal parameter values.
  • the processor 110 can obtain information such as the moving speed and Doppler frequency offset of the terminal device 100 from the sensor data and/or signal parameter values reported by the acquisition and measurement module, and then according to the moving speed of the terminal device 100, Doppler frequency offset and other information. Frequency offset and other information, determine the coherent time window length corresponding to the current first working mode of the terminal device 100, and determine the terminal The predicted value of the communication state of the device 100; if the predicted value of the communication state satisfies the preset condition, adjust the working mode of the terminal device 100 to the second working mode, the second working mode is different from the channel of the first working mode.
  • the acquisition and measurement module of the terminal device may further include other modules, which are not limited in this application.
  • FIG. 2 shows a schematic diagram of an application scenario of a method for adjusting a working mode according to an embodiment of the present application.
  • the terminal device 200 includes an application processor 210 , a wireless interface layer 220 , a baseband processor 230 and a collection and measurement module 240 .
  • the application processor 210 is used for executing the processing related to the application program on the terminal device 200
  • the baseband processor 230 is used for executing the processing related to the communication (such as cellular communication, Wi-Fi communication, etc.) on the terminal device 200
  • the communication Relevant processing may include air interface state analysis, downlink bandwidth estimation, air interface state prediction, air interface state reporting, and the like.
  • the acquisition measurement module 240 may include a physical layer (PHY), a radio resource control (RRC), a media access control address (MAC address, also referred to as a physical address), a forward Error correction (forward error collection, FEC), modulation and demodulation processor (modem) and other modules.
  • PHY physical layer
  • RRC radio resource control
  • MAC address media access control address
  • FEC forward Error correction
  • modem modulation and demodulation processor
  • the acquisition and measurement module may further include sensors, such as a gyroscope sensor, an acceleration sensor, and the like.
  • the acquisition and measurement module 240 may report the acquired sensor data and/or the measured signal parameter values to the baseband processor 230 according to a preset period (eg, 100 ms).
  • the signal parameter values may include received signal strength indication (RSSI), reference signal receiving power (RSRP), block error rate (block error rate, BLER), signal-to-noise ratio (signal-to-noise ratio).
  • RSSI received signal strength indication
  • RSRP reference signal receiving power
  • BLER block error rate
  • signal-to-noise ratio signal-to-noise ratio
  • SNR Doppler frequency offset
  • the baseband processor 230 can obtain information such as the moving speed and Doppler frequency offset of the terminal device 200 from the signal parameter values and/or sensor data reported by the acquisition and measurement module 240, and, according to the moving speed of the terminal device 200, Doppler frequency offset and other information, Frequency offset and other information to determine the length of the coherent time window corresponding to the current first working mode of the terminal device 200;
  • the predicted value of the communication state of the terminal device is determined.
  • the application processor 210 reports the predicted value of the communication state to the application processor 210 through a radio interface layer (RIL) 220 .
  • the communication state may include at least one of signal strength, transmission delay, or network bandwidth, and the first working mode is any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode kind.
  • the application processor 210 may determine whether the received predicted value of the communication state satisfies the preset condition, and adjust the working mode of the terminal device to the second working mode if the predicted value of the communication state satisfies the preset condition.
  • the second working mode is any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode, and the second working mode is different from the channel of the first working mode; the preset condition It may include that the signal strength in the predicted value of the communication state is less than or equal to the preset signal strength threshold, the transmission delay in the predicted value of the communication state is greater than or equal to the preset transmission delay threshold, the network in the predicted value of the communication state
  • the bandwidth is less than or equal to at least one of preset network bandwidth thresholds.
  • the terminal device 200 has a primary card and a secondary card
  • the current first working mode is the primary card data traffic working mode
  • the signal strength in the predicted value of the communication state of the terminal device 200 is less than or equal to the preset signal strength threshold.
  • the working mode of the terminal device 200 may be adjusted to the secondary card quantity traffic working mode (ie, the second working mode). That is: when the main card has poor Internet access signal, switch to the secondary card to access the Internet.
  • FIG. 3 shows a schematic diagram of an application scenario of a method for adjusting a working mode according to an embodiment of the present application.
  • the terminal device includes a modem processor 310 , a baseband processor 320 and an application processor 330 .
  • the modulation and demodulation processor 310 can be regarded as a collection and measurement module of the terminal device, and the baseband processor 320 includes an interface adaptation layer 321 and an air interface state prediction module 322 .
  • the modulation and demodulation processor 310 may report the measured signal parameter values to the baseband processor 320 through an interface control device (ICD) in the terminal device according to a preset period.
  • ICD interface control device
  • the interface adaptation layer 321 (including the parameter adaptation interface and the control adaptation interface) of the baseband processor 320 can format the signal parameter value to obtain a formatted
  • the formatted signal parameter value is sent to the air interface state prediction module 322.
  • the air interface state prediction module 322 can obtain information such as the moving speed and Doppler frequency offset of the terminal device from the formatted signal parameter values, and determine the connection with the terminal device according to the information such as the moving speed and Doppler frequency offset of the terminal device.
  • the length of the coherent time window corresponding to the current first working mode of the device, and then according to the length of the coherent time window and the multiple historical air interface states of the terminal device in the first working mode (that is, multiple historical values of the communication state) the The air interface state is predicted to obtain the predicted value of the air interface state (ie, the predicted value of the communication state), and the predicted value is sent to the application processor 330 through the wireless interface layer (not shown in the figure).
  • the application processor 330 can determine whether the received predicted value of the communication state satisfies the preset condition, and when the predicted value satisfies the preset condition, adjust the working mode, that is, adjust the working mode of the terminal device from the first working mode to the first working mode. Two working modes.
  • FIG. 3 only takes the modulation and demodulation processor modem as an example, and exemplarily illustrates the reporting process of the signal parameter value measured by the terminal device's collection and measurement module.
  • the acquisition and measurement module may also be other modules, and the present application does not limit the specific implementation of the acquisition and measurement module.
  • FIG. 4 shows a flowchart of a method for adjusting a working mode according to an embodiment of the present application.
  • the working mode adjustment method includes:
  • Step S410 Determine the coherence time window length corresponding to the current first working mode of the terminal device.
  • the moving speed, Doppler frequency offset, etc. of the terminal device may be obtained from the sensor data and/or signal parameter values periodically reported by the acquisition and measurement module of the terminal device (ie, the bottom layer of the terminal device). information.
  • the acquisition and measurement module may include at least one of physical layer PHY, radio resource control RRC, MAC address, forward error correction FEC, modulation and demodulation processor modem, gyroscope sensor or acceleration sensor.
  • the moving speed of the terminal device may be obtained from data reported by sensors related to the motion state of the terminal device, such as a gyro sensor, an acceleration sensor, and the like.
  • the Doppler frequency offset can be obtained from the signal parameter values reported by the modem processor, etc.
  • the modem processor of the terminal device can report the signal parameter value through the interface control device ICD, and the message processing function in the interface control device ICD can apply for a buffer area, and the modem processor can be set according to the preset cycle (for example, 100ms)
  • the reported signal parameter values are stored in the buffer area; the baseband processor of the terminal device can obtain the Doppler frequency offset of the terminal device from the signal parameter values stored in the above buffer area.
  • the length of the coherence time window corresponding to the current first working mode of the terminal device may be determined according to information such as the moving speed of the terminal device and the Doppler frequency offset.
  • the first working mode may be any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode. It should be noted that the first working mode may also be other working modes of the terminal device, which is not limited in this application.
  • the coherence time window is the channel coherence time window, which is the maximum time difference range in which the channel remains constant.
  • the continuous physical signals within the channel coherence time window have good correlation and are generally considered to suffer from similar wireless fading.
  • the channel coherence time windows in different mobile scenarios are generally different. For example, in high-speed rail scenarios, due to the influence of the Doppler effect, the channel is in a fast fading mode, and the channel coherence time window will be very short; in static scenarios such as office buildings and residential areas, The channel is relatively more stable, and the channel coherence time window will be longer.
  • the length of the coherent time window corresponding to the current first working mode of the terminal device can be determined through information such as the moving speed of the terminal device, Doppler frequency offset, etc., and the terminal device can be mapped to different channel scenarios, so that the working mode of the terminal device can be mapped.
  • the mode adjustment is combined with the channel scene to improve the timeliness of working mode adjustment.
  • Step S420 Determine a predicted value of the communication state of the terminal device according to the length of the coherence time window and multiple historical values of the communication state of the terminal device in the first working mode.
  • the predicted signal value at the second moment after the current moment is related to the historical signal values of multiple first moments (that is, the historical moment) before the current moment.
  • the predicted value of the communication state of the terminal device can be determined according to the length of the coherent time window and a plurality of historical values of the communication state of the terminal device in the first working mode.
  • the communication status of the terminal device at the next moment at the current moment is related to the communication status of the five moments before the current moment
  • the communication status of the five first moments before the current moment can be calculated according to the , and determine the predicted value of the communication state at the second time after the current time by means of smoothing filtering or the like.
  • smooth filtering can be expressed by the following formula (1):
  • N represents the length of the coherent time window
  • n represents a total of n moments, where the first n-1 moments are the first moment before the current moment, and the nth moment is the second moment after the current moment
  • y n -1 , y n-2 , . ..., ⁇ N represents a weight coefficient.
  • the weighting coefficient may be a fixed coefficient corresponding to the length of the coherence time window, and the corresponding weighting coefficient may also be different when the length of the coherent time window is different.
  • the weighting coefficient may also be a coefficient that is adaptively updated according to the length of the coherent time window and a plurality of historical values of the communication state of the terminal device in the first working mode.
  • the multiple historical values of the communication state may include L communication states at the first time before the current time, and the predicted value of the communication state may include M after the current time
  • the predicted value of the communication state at the second moment, the length of the coherent time window is N, where L, M, N are integers, L>N>1, M ⁇ 1,
  • the first group of weight coefficients that is, the initial value of the weight coefficient
  • the six predicted values of the communication state at the first moment determine the first set of weighting coefficients.
  • the difference between the communication state (actual value) at the sixth first moment and the predicted value of the communication state at the sixth first moment may be determined, and the 0th group of weighting coefficients is calculated according to the difference. Update to get the first set of weight coefficients.
  • the communication states from the first first moment to the fifth first moment may also be considered.
  • the difference between the communication state (actual value) at the sixth first moment and the predicted value of the communication state at the sixth first moment can be determined, and based on the difference and the first to fifth In the communication state at the first moment, the adjustment value of each weight coefficient in the 0th group of weight coefficients is determined, and the 0th group of weight coefficients is updated according to the adjustment value of each weight coefficient to obtain the first group of weight coefficients.
  • the predicted value of the communication state at the seventh first moment can be determined according to the first group of weight coefficients and the communication status from the second first moment to the sixth first moment;
  • the group weight coefficient, the communication state at the seventh first time, and the predicted value of the communication state at the seventh first time determine the second group weight coefficient.
  • the predicted value of the communication state at the i+Nth first moment can be determined according to the i-1th group of weight coefficients and the communication state from the ith first moment to the i+N-1th first moment. , where i is an integer and 0 ⁇ i ⁇ L-N; and according to the i-1th group of weight coefficients, the communication state at the i+Nth first moment, and the predicted value of the communication state at the i+Nth first moment, Determine the i-th group of weight coefficients.
  • the difference between the communication state (actual value) at the i+Nth first moment and the predicted value of the communication state at the i+Nth first moment may be determined, and based on the difference -1 group of weight coefficients are updated to obtain the i-th group of weight coefficients.
  • the communication state from the i-th first moment to the i+N-1-th first moment may also be considered.
  • the difference between the communication state at the i+Nth first moment and the predicted value of the communication state at the i+Nth first moment can be determined, and based on the difference and the i+th first moment to the i+ N-1 communication states at the first moment, determine the adjustment value of each weight coefficient in the i-1 group of weight coefficients, and update the i-1 group of weight coefficients according to the adjustment value of each weight coefficient to obtain the i-th group of weight coefficients. weight factor.
  • the L-N+1 group of weight coefficients can be determined, and the L-N+1 group of weight coefficients can be determined as the weight coefficients corresponding to the first second moment.
  • the 16th group of weight coefficients can be determined as the corresponding first second moment.
  • weight factor may be used to indicate the weight of the communication states of multiple first moments within the coherence time window of the first second moment.
  • the weight coefficients are trained to obtain the weight coefficients corresponding to the first second moment, so that the weight coefficients can be adaptively adjusted to adapt to different channel scenarios, thereby improving the accuracy of the weight coefficients .
  • the weight coefficient corresponding to the first second moment After the weight coefficient corresponding to the first second moment is determined, it can be determined according to the weight coefficient corresponding to the first second moment and the communication status from the L-N+1 first moment to the Lth first moment.
  • the weight coefficients can be trained according to the length of the coherent time window N and the communication states of the L first moments to obtain the weight coefficients corresponding to the first second moment, and based on the first second moment
  • step S420 may further include: in the case of M>1, for the jth second moment, according to the coherence time window length N, the communication status of the L first moments , the predicted value of the communication state from the first second moment to the j-1th second moment and the weight coefficient corresponding to the j-1th second moment, determine the weight coefficient corresponding to the jth second moment, The weight coefficient corresponding to the jth second moment is used to indicate the weight of the communication state at the first moment and the predicted value of the communication state at the second moment in the coherence time window of the jth second moment, wherein , 1 ⁇ j ⁇ M ⁇ N; according to the weight coefficient corresponding to the jth second moment, the coherence time window length N, the communication state of the L first moments and the first second moment to The predicted value of the communication state at the j-1th second time is determined as the predicted value of the communication state at the jth second time.
  • the 20 communication states at the first time, the predicted values of the communication state at the first second time, and the weight coefficients corresponding to the first second time are determined to correspond to the second second time in a similar manner to the above. weight factor.
  • the weight coefficient corresponding to the second second moment is used to indicate the communication status from the 17th first moment to the 20th first moment and the first second moment in the coherence time window of the second second moment The weight of the predicted value of the communication state.
  • the above formula ( 1) determine the predicted value of the communication state at the second second moment.
  • the communication state of the 18th first time to the 20th first time the first second time to the second second time
  • the predicted value of the communication state and the weighting coefficient corresponding to the second second time are determined in a similar manner to the above to determine the weighting coefficient corresponding to the third second time.
  • the weight coefficient corresponding to the third second moment is used to indicate the communication state from the 18th first moment to the 20th first moment and the first second moment in the coherence time window of the third second moment The weight of the predicted value of the communication state up to the second second time.
  • the predicted value is determined by the above-mentioned formula (1) to determine the predicted value of the communication state at the third second time.
  • Step S430 in the case that the predicted value satisfies the preset condition, adjust the working mode of the terminal device to the second working mode.
  • the second working mode is any one of the main card data traffic working mode, the secondary card data traffic working mode, and the Wi-Fi wireless communication working mode, and the second working mode is different from the channel of the first working mode. It should be noted that, the second working mode may also be other working modes of the terminal device, which is not limited in this application.
  • the communication state may include at least one of signal strength, transmission delay, or network bandwidth.
  • the predicted value of the communication state may include at least one of signal strength, transmission delay, or network bandwidth.
  • the preset conditions may include that the signal strength in the predicted value of the communication state is less than or equal to a preset signal strength threshold, the transmission delay in the predicted value of the communication state is greater than or equal to the preset transmission delay threshold, and the predicted value of the communication state
  • the network bandwidth in is less than or equal to at least one of the preset network bandwidth thresholds.
  • the signal strength, transmission delay, and network bandwidth included in the predicted value can be judged separately, and when any one of the predicted values satisfies the preset condition, it is considered that the communication
  • the predicted value of the state satisfies the preset condition, or, when all items in the predicted value meet the preset condition, it is considered that the predicted value of the communication state satisfies the preset condition.
  • the signal strength in the predicted value of the communication state may be compared with a preset signal strength threshold.
  • the predicted value of the communication state is the predicted value of the communication state of the terminal device at the first second time
  • the predicted value of the first second time can be used as the predicted value of the communication state.
  • the signal strength in the device is compared with the signal strength threshold, and when the signal strength in the predicted value of the communication state at the first second moment is less than or equal to the signal strength threshold, it is considered that the predicted value of the terminal device satisfies the preset condition,
  • the working mode of the terminal device can be adjusted to the second working mode
  • the signal strength in the predicted value of the communication state at the last second time may be compared with a signal strength threshold. For example, when there are four predicted values of the communication state, the signal strength in the predicted value of the communication state at the fourth second time may be compared with the signal intensity threshold, and the communication at the fourth second time may be compared with the signal intensity threshold.
  • the signal strength in the state prediction is less than or equal to the signal strength threshold, it is considered that the predicted value of the terminal device satisfies the preset condition, and the working mode of the terminal device can be adjusted to the second working mode.
  • the manner of judging whether the predicted value of the communication state satisfies the preset condition is similar to the above, and the repetitive description is not repeated here.
  • the coherent time window length (ie, different channel scenarios) can be considered when determining the predicted value of the communication state of the terminal device, and when the predicted value of the communication state meets the preset condition, the The working mode of the terminal device can be adjusted in advance, so that the working mode of the terminal device can be adjusted in advance in the case of poor communication status (such as weak signal, large transmission delay, small network bandwidth, etc.), reducing the communication process.
  • the stuck feeling makes users not feel the network fluctuations during the communication process, which effectively improves the user experience.
  • FIG. 5 shows a flowchart of a method for adjusting a working mode according to an embodiment of the present application.
  • the working mode adjustment method includes step S410 , step S4201 , step S4202 , step S4203 , step S4204 and step S430 .
  • steps S4201 to S4204 are a possible more detailed implementation of step S420 in the embodiment shown in FIG. 4 .
  • Step S410 Determine the coherence time window length corresponding to the current first working mode of the terminal device.
  • step S410 in the embodiment shown in FIG. 5 is similar to step S410 in the embodiment shown in FIG. 4 , and repeated description is not repeated here.
  • Step S4201 Perform preprocessing on the communication states at the L first moments to obtain L preprocessed communication states at the first moments, where the preprocessing includes normalization and difference processing.
  • Preprocessing such as normalization and difference can be performed on the communication states at the L first moments to obtain the preprocessed communication states at the L first moments, so as to reduce the non-stationarity of the communication state.
  • the communication states of the L first moments can be normalized by the following formula (2):
  • p and q are integers, and 0 ⁇ p ⁇ L-1, 0 ⁇ q ⁇ L-1, n represents a total of n times, and the first n-1 times are the first time before the current time , the nth moment is the first second moment after the current moment.
  • y(n-L), y(n-L+1), . . . , y(n-2), and y(n-1) represent the communication states at L times before the current time.
  • y(n-L) represents the communication state at the first first moment, and also represents the communication state at the n-Lth time
  • y(n-L+1) represents the communication state at the second first moment, and also represents the n-th communication state.
  • the communication state at time L+1; ...; y(n-2) represents the communication state at the L-1th first time, and also the communication state at the n-2th time
  • y(n-1) represents the Lth communication state
  • the communication state at the first time also represents the communication state at the n-1th time.
  • y(n-L+q) is the communication state at the q+1th first moment, and also represents the communication state at the n-L+qth moment; y(n-L+p) is the p+1th first time
  • the communication state at the moment also represents the communication state at the n-L+p time; y'(n-L+p) represents the normalized communication state at the p+1 first time, and also represents the n-th communication state.
  • the following formula (3) can be used to perform differential processing on the normalized communication states of the L first moments to obtain the preprocessed communication states of the L first moments:
  • Step S4202 according to the length of the coherence time window N and the preprocessed communication states of the L first moments, determine a differential weight coefficient corresponding to the first second moment.
  • the difference weight coefficient corresponding to the first second time that is, the difference weight coefficient corresponding to the nth time.
  • the preprocessed communication state from the first first moment to the Nth first moment Determine the differential predicted value of the communication state at the N+1 th first time.
  • the preset differential weight coefficient initial value is According to the preprocessed communication state from the first first moment to the Nth first moment According to the following formula (4), the difference prediction value of the communication state at the N+1th first moment is determined
  • v is an integer and 1 ⁇ v ⁇ N
  • ⁇ v represents the vth weight coefficient
  • the 0th group of differential weight coefficients can be calculated. Adjust to obtain the first group of differential weight coefficients.
  • the first group of differential weighting coefficients (that is, the differential weighting coefficients at the n-L+Nth moment) can be determined by the following formula (5):
  • the sliding coherence time window is used to determine the second group of differential weight coefficients (that is, the differential weight coefficients at the n-L+N+1 time) and the third group of differential weight coefficients (that is, the n-L+Nth group) by the above method. +2 difference weight coefficients at time), ..., the L-N+1th group of difference weight coefficients (that is, the difference weight coefficients at the nth time).
  • the L-N+1 group of differential weight coefficients (that is, the differential weight coefficients at the nth time) is determined as the differential weight coefficients corresponding to the first second time.
  • Step S4203 according to the difference weight coefficient corresponding to the first second time and the preprocessed communication state from the L-N+1 first time to the Lth first time, determine the first time The difference prediction value of the communication state at the second time.
  • the difference weight coefficient corresponding to the first second moment is According to the difference weight coefficient and the preprocessed communication state from the L-N+1th first time to the Lth first time (that is, the preprocessed communication state from the nNth time to the n-1th time), determine the first time Differential predicted value of the communication state at the second time (ie, the nth time).
  • the following formula (6) can be used to determine the differential prediction value of the communication state at the first second moment (that is, the nth moment)
  • ⁇ ′′ v represents the vth weight coefficient, It represents the communication state after preprocessing at the L-v+1 th first time, and also represents the communication state after preprocessing at the nvth time.
  • Step S4204 Perform post-processing on the difference predicted value to obtain the first predicted value of the communication state at the second moment, where the post-processing includes inverse difference and inverse normalization processing.
  • the differential predicted value After determining the differential predicted value of the communication state at the first second time (that is, the nth time), the differential predicted value can be post-processed, and the post-processing includes inverse difference and inverse normalization, so as to obtain the first second The predicted value of the communication state at the time (ie, the nth time).
  • the following formula (7) can be used to determine the predicted value of the communication state at the first second moment (that is, the nth moment)
  • u is an integer and n-L ⁇ u ⁇ n-1.
  • the coherent time window can also be slid, and through the above method, iteratively predicts the communication state at the jth second moment to obtain the predicted value of the communication state at the jth second moment, so as to achieve Multi-step forecasting.
  • Step S430 in the case that the predicted value satisfies the preset condition, adjust the working mode of the terminal device to the second working mode.
  • the channel of the second working mode is different from that of the first working mode
  • the preset condition includes that the signal strength in the predicted value is less than or equal to a preset signal strength threshold, the transmission in the predicted value At least one of the delay is greater than or equal to a preset transmission delay threshold, and the network bandwidth in the predicted value is less than or equal to a preset network bandwidth threshold.
  • step S430 in the embodiment shown in FIG. 5 is similar to step S430 in the embodiment shown in FIG. 4 , and repeated description is not repeated here.
  • preprocessing such as normalization and difference can be performed on the communication states of the L first moments, so as to obtain the preprocessed communication states of the L first moments, and according to the lengths of the coherent time windows N and L
  • For the preprocessed communication state at the first moment determine the differential weight coefficient corresponding to the first second moment, and then determine the differential predicted value of the first second communication state, and then perform the inverse difference on the differential predicted value and post-processing such as inverse normalization to obtain the predicted value of the communication state at the first second moment, and when the predicted value satisfies the preset condition, adjust the working mode of the terminal device to the second working mode, thereby
  • preprocessing the communication state the non-stationarity of the communication state can be reduced, and prediction is made based on the communication state after the preprocessing, which can improve the prediction accuracy of the communication state.
  • the working mode of the terminal device is adjusted, so that the communication state is poor (for example, the signal is weak, the transmission delay is large, the network bandwidth is small, etc.) Under the circumstance, the working mode of the terminal device is adjusted in advance, so that the user does not feel the network fluctuation during the communication process, and the user experience is effectively improved.
  • the working mode adjustment method described in the embodiment of the present application is applied to a terminal device, and can adjust the working mode of the terminal device based on the predicted value of the communication state in different channel scenarios, so that in the case of poor communication state, the working mode of the terminal device can be adjusted. Adjust the working mode of the terminal device in advance to reduce the feeling of stuck in the communication process, so that the user can not feel the network fluctuation during the communication process, and effectively improve the user experience.
  • the video bit rate can also be adjusted in advance according to the predicted value of the communication state, which reduces the feeling of stuttering when users view the video and improves the user experience.
  • FIG. 6 shows a block diagram of an apparatus for adjusting a working mode according to an embodiment of the present application.
  • the working mode adjustment device is applied to terminal equipment.
  • the working mode adjustment device includes:
  • a coherence time window determining module 610 configured to determine the coherence time window length corresponding to the current first working mode of the terminal device
  • a prediction module 620 configured to determine a predicted value of the communication state of the terminal device according to the length of the coherence time window and a plurality of historical values of the communication state of the terminal device in the first working mode, the communication state
  • the state includes at least one of signal strength, transmission delay, or network bandwidth;
  • An adjustment module 630 configured to adjust the working mode of the terminal device to the second working mode when the predicted value satisfies a preset condition
  • the channel of the second working mode is different from that of the first working mode
  • the preset condition includes that the signal strength in the predicted value is less than or equal to a preset signal strength threshold, the transmission in the predicted value At least one of the delay is greater than or equal to a preset transmission delay threshold, and the network bandwidth in the predicted value is less than or equal to a preset network bandwidth threshold.
  • the multiple historical values of the communication status include L communication statuses at first moments before the current moment, and the predicted values of the communication status include M second communication statuses after the current moment
  • the predicted value of the communication state at the moment, the length of the coherent time window is N, where L, M, N are integers, L>N>1, M ⁇ 1,
  • the prediction module 620 further includes: a second coefficient determination sub-module for, in the case of M>1, for the jth second time instant, according to the coherence time window length N, the communication state of the L first moments, the predicted value of the communication state from the first second time to the j-1th second time, and the weight coefficient corresponding to the j-1th second time, determine The weight coefficient corresponding to the jth second moment, the weight coefficient corresponding to the jth second moment is used to indicate the communication state and the first moment in the coherence time window of the jth second moment.
  • the first coefficient determination sub-module is configured to: according to the i-1th group of weight coefficients, the i-th first moment to the i+N-1th first moment of communication state, determine the predicted value of the communication state at the i+Nth first moment, i is an integer and 0 ⁇ i ⁇ L-N, the 0th group of weight coefficients is the initial value of the weight coefficients; according to the i-1th group of weight coefficients, the first The communication state of the i+N first time and the predicted value of the communication state of the i+N first time are determined to determine the i-th group of weight coefficients; the L-N+1-th group of weight coefficients are determined to be the same as the first The weight coefficient corresponding to the second moment.
  • the first coefficient determination sub-module is configured to: preprocess the communication states of the L first moments to obtain L preprocessed communication states of the first moments , the preprocessing includes normalization and differential processing; according to the length of the coherent time window N and the preprocessed communication state of the L first moments, the differential weight coefficient corresponding to the first second moment is determined;
  • the first prediction sub-module is configured to: according to the difference weight coefficient corresponding to the first second moment and the preprocessing from the L-N+1th first moment to the Lth first moment After the communication state is obtained, the difference prediction value of the communication state at the first second time is determined; the difference prediction value is post-processed to obtain the prediction value of the communication state at the first second time.
  • Post-processing includes inverse difference and inverse normalization.
  • the first working mode and the second working mode are any one of a main card data traffic working mode, a secondary card data traffic working mode, and a Wi-Fi wireless communication working mode.
  • An embodiment of the present application provides an apparatus for adjusting a working mode, including: a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions.
  • Embodiments of the present application provide a non-volatile computer-readable storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, implement the above method.
  • Embodiments of the present application provide a computer program product, including computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer-readable codes are stored in a processor of an electronic device When running in the electronic device, the processor in the electronic device executes the above method.
  • a computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (Electrically Programmable Read-Only-Memory, EPROM or flash memory), static random access memory (Static Random-Access Memory, SRAM), portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROMs), Digital Video Discs (DVDs), memory sticks, floppy disks, mechanically encoded devices, such as punch cards or raised structures in grooves on which instructions are stored, and any suitable combination.
  • RAM random access memory
  • ROM read only memory
  • EPROM erasable programmable read-only memory
  • EPROM Errically Programmable Read-Only-Memory
  • SRAM static random access memory
  • portable compact disk read-only memory Compact Disc Read-Only Memory
  • CD-ROMs Compact Disc Read-Only Memory
  • DVDs Digital Video Discs
  • memory sticks floppy disks, mechanically encode
  • Computer readable program instructions or code described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • the computer program instructions used to perform the operations of the present application may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in one or more source or object code written in any combination of programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages.
  • the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer may be connected to the user's computer through any kind of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or, may be connected to an external computer (eg, use an internet service provider to connect via the internet).
  • electronic circuits such as programmable logic circuits, Field-Programmable Gate Arrays (FPGA), or Programmable Logic Arrays (Programmable Logic Arrays), are personalized by utilizing state information of computer-readable program instructions.
  • Logic Array, PLA the electronic circuit can execute computer readable program instructions to implement various aspects of the present application.
  • These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium on which the instructions are stored includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.
  • Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions.
  • the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented in hardware (eg, circuits or ASICs (Application) that perform the corresponding functions or actions. Specific Integrated Circuit, application-specific integrated circuit)), or can be implemented by a combination of hardware and software, such as firmware.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请涉及一种工作模式调整方法、装置及存储介质，其中，所述方法应用于终端设备，所述方法包括：确定与所述终端设备当前的第一工作模式对应的相干时窗长度；根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，所述通信状态包括信号强度、传输时延或网络带宽中的至少一种；在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式。本申请的实施例能够在不同信道场景下基于预测信号来对终端设备的工作模式进行调整，从而能够在通信状态较差的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感。

Description

工作模式调整方法、装置及存储介质
本申请要求于2021年04月16日提交中国专利局、申请号为202110411188.9、申请名称为“工作模式调整方法、装置及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种工作模式调整方法、装置及存储介质。
背景技术
在数据业务中，通常需要根据网络环境对终端设备的工作模式进行调整。例如，在终端设备的双卡数据业务中，有时会出现主卡信号不好需要切换到副卡进行通信的场景，或者，在终端设备同时连接Wi-Fi无线网络和数据流量时，有时会因为Wi-Fi信号有波动或者信号不好，需要暂时切换到数据流量来支撑当前的数据业务的场景。
在相关技术中，通常根据实时的网络波动，来判断是否需要对终端设备的工作模式进行调整。但是，该方式存在时间上的滞后，是在用户明显感觉到卡顿之后才进行工作模式调整，用户体验较差。
发明内容
有鉴于此，提出了一种工作模式调整技术方案。
第一方面，本申请的实施例提供了一种工作模式调整方法，所述方法应用于终端设备，所述方法包括：确定与所述终端设备当前的第一工作模式对应的相干时窗长度；根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，所述通信状态包括信号强度、传输时延或网络带宽中的至少一种；在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式，其中，所述第二工作模式与所述第一工作模式的信道不同，所述预设条件包括所述预测值中的信号强度小于或等于预设的信号强度阈值、所述预测值中的传输时延大于或等于预设的传输时延阈值、所述预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
根据本申请的实施例，能够在确定终端设备的通信状态的预测值时考虑相干时窗长度(即不同的信道场景)，并在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通讯过程中的网络波动，有效提升用户体验。
根据第一方面，在所述工作模式调整方法的第一种可能的实现方式中，所述通信状态的多个历史值包括当前时刻之前的L个第一时刻的通信状态，所述通信状态的预测值包括所述当前时刻之后的M个第二时刻的通信状态的预测值，所述相干时窗长度为N，其中，L，M，N为整数，L>N>1，M≥1，
所述根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历 史值，确定所述终端设备的通信状态的预测值，包括：在M＝1的情况下，根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，所述与第1个第二时刻对应的权重系数用于指示所述第1个第二时刻的相干时窗内的多个第一时刻的通信状态的权重；根据所述与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值。
在本实施例中，能够根据相干时窗长度N及L个第一时刻的通信状态，对权重系数进行训练，得到与第1个第二时刻对应的权重系数，并根据与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定终端设备在下一时刻(即第1个第二时刻)的通信状态的预测值，从而能够提高通信状态的预测值的准确性。
根据第一方面的第一种可能的实现方式，在所述工作模式调整方法的第二种可能的实现方式中，所述根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，还包括：在M>1的情况下，针对第j个第二时刻,根据所述相干时窗长度N、所述L个第一时刻的通信状态、第1个第二时刻至第j-1个第二时刻的通信状态的预测值及与第j-1个第二时刻对应的权重系数，确定与第j个第二时刻对应的权重系数，所述与第j个第二时刻对应的权重系数用于指示所述第j个第二时刻的相干时窗内的第一时刻的通信状态及第二时刻的通信状态的预测值的权重，其中，1<j≤M<N；根据所述与第j个第二时刻对应的权重系数、所述相干时窗长度N、所述L个第一时刻的通信状态及第1个第二时刻至第j-1个第二时刻的通信状态的预测值，确定所述第j个第二时刻的通信状态的预测值。
在本实施例中，能够基于L个第一时刻的通信状态及第1个第二时刻至第j个第二时刻的通信状态的预测值，对第j+1个第二时刻的通信状态进行迭代预测，得到第j+1个第二时刻的通信状态的预测值，从而实现多步预测。
根据第一方面的第一种可能的实现方式，在所述工作模式调整方法的第三种可能的实现方式中，所述根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，包括：根据第i-1组权重系数、第i个第一时刻至第i+N-1个第一时刻的通信状态，确定第i+N个第一时刻的通信状态的预测值，i为整数且0≤i≤L-N，第0组权重系数为权重系数的初始值；根据第i-1组权重系数、第i+N个第一时刻的通信状态以及第i+N个第一时刻的通信状态的预测值，确定第i组权重系数；将第L-N+1组权重系数，确定为与第1个第二时刻对应的权重系数。
在本实施例中，通过上述随机梯度下降的方式，对权重系数进行训练，得到与第1个第二时刻对应的权重系数，使得权重系数可以自适应调整，以适应不同的信道场景，从而能够提高权重系数的准确性。
根据第一方面的第一种可能的实现方式，在所述工作模式调整方法的第四种可能的实现方式中，所述根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，包括：对所述L个第一时刻的通信状态进行预处理，得到L个第一时刻的预处理后的通信状态，所述预处理包括归一化及差分处理；根据所述相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数；
其中，所述根据与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值，包括：根据所述与第1个第 二时刻对应的差分权重系数及第L-N+1个第一时刻至第L个第一时刻的预处理后的通信状态，确定所述第1个第二时刻的通信状态的差分预测值；对所述差分预测值进行后处理，得到所述第1个第二时刻的通信状态的预测值，所述后处理包括逆差分及反归一化处理。
在本实施例中，能够对L个第一时刻的通信状态进行归一化及差分等预处理，得到L个第一时刻的预处理后的通信状态，并根据相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数，进而确定第1个第二时刻的通信状态的差分预测值，然后对该差分预测值进行逆差分及反归一化等后处理，得到第1个第二时刻的通信状态的预测值，并在该预测值满足预设条件的情况下，将终端设备的工作模式调整为第二工作模式，从而能够通过对通信状态的预处理，减少通信状态的非平稳性，基于预处理后的通信状态进行预测，可提高通信状态的预测准确性。
根据第一方面或第一方面的多种可能的实现方式中的一种或几种，在所述工作模式调整方法的第五种可能的实现方式中，所述第一工作模式及所述第二工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种。
在本实施例中，第一工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种，第二工作模式也为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种，使得终端设备的工作模式可在主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式之间切换。
第二方面，本申请的实施例提供了一种工作模式调整装置，所述装置应用于终端设备，所述装置包括：相干时窗确定模块，用于确定与所述终端设备当前的第一工作模式对应的相干时窗长度；预测模块，用于根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，所述通信状态包括信号强度、传输时延或网络带宽中的至少一种；调整模块，用于在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式，其中，所述第二工作模式与所述第一工作模式的信道不同,所述预设条件包括所述预测值中的信号强度小于或等于预设的信号强度阈值、所述预测值中的传输时延大于或等于预设的传输时延阈值、所述预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
根据本申请的实施例，能够在确定终端设备的通信状态的预测值时考虑相干时窗长度(即不同的信道场景)，并在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通讯过程中的网络波动，有效提升用户体验。
根据第二方面，在所述工作模式调整装置的第一种可能的实现方式中，所述通信状态的多个历史值包括当前时刻之前的L个第一时刻的通信状态，所述通信状态的预测值包括所述当前时刻之后的M个第二时刻的通信状态的预测值，所述相干时窗长度为N，其中，L，M，N为整数，L>N>1，M≥1，
所述预测模块，包括：第一系数确定子模块，用于在M＝1的情况下，根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，所述与第1个第二时刻对应的权重系数用于指示所述第1个第二时刻的相干时窗内的多个第一时刻的通信状态的权重；第一预测子模块，用于根据所述与第1个第二时刻对应的权重系数、第L-N+1 个第一时刻至第L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值。
在本实施例中，能够根据相干时窗长度N及L个第一时刻的通信状态，对权重系数进行训练，得到与第1个第二时刻对应的权重系数，并根据与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定终端设备在下一时刻(即第1个第二时刻)的通信状态的预测值，从而能够提高通信状态的预测值的准确性。
根据第二方面的第一种可能的实现方式，在所述工作模式调整装置的第二种可能的实现方式中，所述预测模块，还包括：第二系数确定子模块，用于在M>1的情况下，针对第j个第二时刻,根据所述相干时窗长度N、所述L个第一时刻的通信状态、第1个第二时刻至第j-1个第二时刻的通信状态的预测值及与第j-1个第二时刻对应的权重系数，确定与第j个第二时刻对应的权重系数，所述与第j个第二时刻对应的权重系数用于指示所述第j个第二时刻的相干时窗内的第一时刻的通信状态及第二时刻的通信状态的预测值的权重，其中，1<j≤M<N；第二预测子模块，用于根据所述与第j个第二时刻对应的权重系数、所述相干时窗长度N、所述L个第一时刻的通信状态及第1个第二时刻至第j-1个第二时刻的通信状态的预测值，确定所述第j个第二时刻的通信状态的预测值。
在本实施例中，能够基于L个第一时刻的通信状态及第1个第二时刻至第j个第二时刻的通信状态的预测值，对第j+1个第二时刻的通信状态进行迭代预测，得到第j+1个第二时刻的通信状态的预测值，从而实现多步预测。
根据第二方面的第一种可能的实现方式，在所述工作模式调整装置的第三种可能的实现方式中，所述第一系数确定子模块，被配置为：根据第i-1组权重系数、第i个第一时刻至第i+N-1个第一时刻的通信状态，确定第i+N个第一时刻的通信状态的预测值，i为整数且0≤i≤L-N，第0组权重系数为权重系数的初始值；根据第i-1组权重系数、第i+N个第一时刻的通信状态以及第i+N个第一时刻的通信状态的预测值，确定第i组权重系数；将第L-N+1组权重系数，确定为与第1个第二时刻对应的权重系数。
在本实施例中，通过上述随机梯度下降的方式，对权重系数进行训练，得到与第1个第二时刻对应的权重系数，使得权重系数可以自适应调整，以适应不同的信道场景，从而能够提高权重系数的准确性。
根据第二方面的第一种可能的实现方式，在所述工作模式调整装置的第四种可能的实现方式中，所述第一系数确定子模块，被配置为：对所述L个第一时刻的通信状态进行预处理，得到L个第一时刻的预处理后的通信状态，所述预处理包括归一化及差分处理；根据所述相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数；
其中，所述第一预测子模块，被配置为：根据所述与第1个第二时刻对应的差分权重系数及第L-N+1个第一时刻至第L个第一时刻的预处理后的通信状态，确定所述第1个第二时刻的通信状态的差分预测值；对所述差分预测值进行后处理，得到所述第1个第二时刻的通信状态的预测值，所述后处理包括逆差分及反归一化处理。
在本实施例中，能够对L个第一时刻的通信状态进行归一化及差分等预处理，得到L个第一时刻的预处理后的通信状态，并根据相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数，进而确定第1个第二时刻的通信状态的差分预测值，然后对该差分预测值进行逆差分及反归一化等后处理，得到第1个第二时刻的 通信状态的预测值，并在该预测值满足预设条件的情况下，将终端设备的工作模式调整为第二工作模式，从而能够通过对通信状态的预处理，减少通信状态的非平稳性，基于预处理后的通信状态进行预测，可提高通信状态的预测准确性。
根据第二方面或第二方面的多种可能的实现方式中的一种或几种，在所述工作模式调整装置的第五种可能的实现方式中，所述第一工作模式及所述第二工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种。
在本实施例中，第一工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种，第二工作模式也为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种，使得终端设备的工作模式可在主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式之间切换。
第三方面，本申请的实施例提供了一种工作模式调整装置，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为执行所述指令时实现上述第一方面或者第一方面的多种可能的实现方式中的一种或几种的工作模式调整方法。
根据本申请的实施例，能够在确定终端设备的通信状态的预测值时考虑相干时窗长度(即不同的信道场景)，并在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通讯过程中的网络波动，有效提升用户体验。
第四方面，本申请的实施例提供了一种非易失性计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述第一方面或者第一方面的多种可能的实现方式中的一种或几种的工作模式调整方法。
根据本申请的实施例，能够在确定终端设备的通信状态的预测值时考虑相干时窗长度(即不同的信道场景)，并在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通讯过程中的网络波动，有效提升用户体验。
第五方面，本申请的实施例提供了一种计算机程序产品，包括计算机可读代码，或者承载有计算机可读代码的非易失性计算机可读存储介质，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行上述第一方面或者第一方面的多种可能的实现方式中的一种或几种的工作模式调整方法。
根据本申请的实施例，能够在确定终端设备的通信状态的预测值时考虑相干时窗长度(即不同的信道场景)，并在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通讯过程中的网络波动，有效提升用户体验。
本申请的这些和其他方面在以下(多个)实施例的描述中会更加简明易懂。
附图说明
包含在说明书中并且构成说明书的一部分的附图与说明书一起示出了本申请的示例性实 施例、特征和方面，并且用于解释本申请的原理。
图1示出根据本申请一实施例的终端设备的结构示意图。
图2示出根据本申请一实施例的工作模式调整方法的应用场景的示意图。
图3示出根据本申请一实施例的工作模式调整方法的应用场景的示意图。
图4示出根据本申请一实施例的工作模式调整方法的流程图。
图5示出根据本申请一实施例的工作模式调整方法的流程图。
图6示出根据本申请一实施例的工作模式调整装置的框图。
具体实施方式
以下将参考附图详细说明本申请的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。
在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。
另外，为了更好的说明本申请，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本申请同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本申请的主旨。
目前，在数据业务中，通常根据实时的网络波动来判断是否需要对终端设备的工作模式进行调整。例如，通过终端设备底层的信号采集器(例如调制解调处理器modem等)实时采集信号，并将采集的信号上报给终端设备的上层；终端设备的上层读取底层上报的信号，并将读取的信号与预设的阈值进行比较；在读取的信号小于预设的阈值的情况下，对终端设备的工作模式进行调整。
然而，终端设备底层的信号采集器的采集周期一般为100ms，而终端设备的上层读取信号的周期一般为1s，即终端设备的上层会对其底层上报的信号做滤波处理，然后根据滤波处理后的信号，对是否调整工作模式进行决策。在信号较弱的情况下，再加上上层滤波处理的时延，调整终端设备的工作模式时，用户已经明显感觉到卡顿了，时效性较差，影响用户体验。
在另一些技术方案中，能够基于固定的时间窗口长度及滤波系数对下一时刻的信号进行预测，并利用预测结果来判断是否需要对终端设备的工作模式进行调整。虽然该方案利用预测结果对终端设备工作模式的调整进行判断，但其基于经验值，将时间窗口长度及滤波系数均设置为固定值，无法适应不同场景的信道变化，也存在调整终端设备的工作模式时用户已经明显感觉到卡顿的问题。
此外，在视频应用等媒体流分发时，终端设备将实时的网络情况上报给服务器，服务器据此来分布合适的码流。这种方式同样存在处理时延，容易造成短暂的视频卡顿，用户体验较差。
为了解决上述技术问题，本申请提供了一种工作模式调整方法，本申请实施例的工作模式调整方法能够在确定终端设备的通信状态的预测值时考虑相干时窗长度(即不同的信道场景)，并在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对 终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通信过程中的网络波动，有效提升用户体验。
其中，所述通信状态包括信号强度、传输时延或网络带宽中的至少一种，所述预设条件包括通信状态的预测值中的信号强度小于或等于预设的信号强度阈值、通信状态的预测值中的传输时延大于或等于预设的传输时延阈值、通信状态的预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
需要说明的是，所述通信状态还可以包括其他通信信息，相应的，可根据通信状态包括的具体内容，对预设条件进行设置。本领域技术人员可根据实际情况对通信状态及预设条件包括的具体内容进行设置，本申请对此不作限制。
本申请实施例的工作模式调整方法可应用于终端设备。该终端设备可以是具有无线通信功能的智能终端设备。无线通信包括通过无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)、2G/3G/4G/5G网络等进行通信，本申请对无线通信的具体方式不作限制。本申请的终端设备也可以具有有线连接进行通信的功能。
本申请实施例的终端设备可以是触屏的、也可以是非触屏的、也可以是没有屏幕的，触屏的可以通过手指、触控笔等在显示屏幕上点击、滑动等方式对终端设备进行控制，非触屏的终端设备可以连接鼠标、键盘、触控面板等输入设备，通过输入设备对终端设备进行控制，没有屏幕的终端设备比如说可以是没有屏幕的蓝牙音箱等。
图1示出根据本申请一实施例的终端设备的结构示意图。
终端设备100可以包括手机、可折叠电子设备、平板电脑、桌面型计算机、膝上型计算机、手持计算机、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、蜂窝电话、个人数字助理(personal digital assistant，PDA)、增强现实(augmented reality，AR)设备、虚拟现实(virtual reality，VR)设备、人工智能(artificial intelligence,AI)设备、可穿戴式设备、车载设备、智能家居设备、或智慧城市设备中的至少一种。本申请实施例对该终端设备100的具体类型不作特殊限制。
终端设备100可以包括处理器110，外部存储器接口120，内部存储器121，通用串行总线(universal serial bus，USB)接头130，充电管理模块140，电源管理模块141，电池142，天线1，天线2，移动通信模块150，无线通信模块160，音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，传感器模块180，按键190，马达191，指示器192，摄像头193，显示屏194，以及用户标识模块(subscriber identification module，SIM)卡接口195等。其中传感器模块180可以包括压力传感器180A，陀螺仪传感器180B，气压传感器180C，磁传感器180D，加速度传感器180E，距离传感器180F，接近光传感器180G，指纹传感器180H，温度传感器180J，触摸传感器180K，环境光传感器180L，骨传导传感器180M等。
可以理解的是，本申请实施例示意的结构并不构成对终端设备100的具体限定。在本申请另一些实施例中，终端设备100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
处理器110可以包括一个或多个处理单元，例如：处理器110可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器(graphics processing unit， GPU)，图像信号处理器(image signal processor，ISP)，控制器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。处理器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器110中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器110中的存储器可以为高速缓冲存储器。该存储器可以保存处理器110用过或使用频率较高的指令或数据。如果处理器110需要使用该指令或数据，可从该存储器中直接调用。避免了重复存取，减少了处理器110的等待时间，因而提高了系统的效率。
在一些实施例中，处理器110可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuit sound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口，用户标识模块(subscriber identity module，SIM)接口，和/或通用串行总线(universal serial bus，USB)接口等。处理器110可以通过以上至少一种接口连接触摸传感器、音频模块、无线通信模块、显示器、摄像头等模块。
可以理解的是，本申请实施例示意的各模块间的接口连接关系，只是示意性说明，并不构成对终端设备100的结构限定。在本申请另一些实施例中，终端设备100也可以采用上述实施例中不同的接口连接方式，或多种接口连接方式的组合。
终端设备100的无线通信功能可以通过天线1，天线2，移动通信模块150，无线通信模块160，调制解调处理器以及基带处理器等实现。
天线1和天线2用于发射和接收电磁波信号。终端设备100中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用，以提高天线的利用率。例如：可以将天线1复用为无线局域网的分集天线。在另外一些实施例中，天线可以和调谐开关结合使用。
移动通信模块150可以提供应用在终端设备100上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块150可以包括至少一个滤波器，开关，功率放大器，低噪声放大器(low noise amplifier，LNA)等。移动通信模块150可以由天线1接收电磁波，并对接收的电磁波进行滤波，放大等处理，传送至调制解调处理器进行解调。移动通信模块150还可以对经调制解调处理器调制后的信号放大，经天线1转为电磁波辐射出去。在一些实施例中，移动通信模块150的至少部分功能模块可以被设置于处理器110中。在一些实施例中，移动通信模块150的至少部分功能模块可以与处理器110的至少部分模块被设置在同一个器件中。
调制解调处理器可以包括调制器和解调器。其中，调制器用于将待发送的低频基带信号调制成中高频信号。解调器用于将接收的电磁波信号解调为低频基带信号。随后解调器将解调得到的低频基带信号传送至基带处理器处理。低频基带信号经基带处理器处理后，被传递给应用处理器。应用处理器通过音频设备(不限于扬声器170A，受话器170B等)输出声音信号，或通过显示屏194显示图像或视频。在一些实施例中，调制解调处理器可以是独立的器件。在另一些实施例中，调制解调处理器可以独立于处理器110，与移动通信模块150或其他功能模块设置在同一个器件中。
无线通信模块160可以提供应用在终端设备100上的包括无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，蓝牙(bluetooth，BT)，蓝牙低功耗(bluetooth low energy，BLE)，超宽带(ultra wide band，UWB),全球导航卫星系统(global navigation satellite system，GNSS)，调频(frequency modulation，FM)，近距离无线通信技术(near field communication，NFC)，红外技术(infrared，IR)等无线通信的解决方案。无线通信模块160可以是集成至少一个通信处理模块的一个或多个器件。无线通信模块160经由天线2接收电磁波，将电磁波信号调频以及滤波处理，将处理后的信号发送到处理器110。无线通信模块160还可以从处理器110接收待发送的信号，对其进行调频，放大，经天线2转为电磁波辐射出去。
在一些实施例中，终端设备100的天线1和移动通信模块150耦合，天线2和无线通信模块160耦合，使得终端设备100可以通过无线通信技术与网络和其他电子设备通信。该无线通信技术可以包括全球移动通讯系统(global system for mobile communications，GSM)，通用分组无线服务(general packet radio service，GPRS)，码分多址接入(code division multiple access，CDMA)，宽带码分多址(wideband code division multiple access，WCDMA)，时分码分多址(time-division code division multiple access，TD-SCDMA)，长期演进(long term evolution，LTE)，BT，GNSS，WLAN，NFC，FM，和/或IR技术等。该GNSS可以包括全球卫星定位系统(global positioning system，GPS)，全球导航卫星系统(global navigation satellite system，GLONASS)，北斗卫星导航系统(beidou navigation satellite system，BDS)，准天顶卫星系统(quasi-zenith satellite system，QZSS)和/或星基增强系统(satellite based augmentation systems，SBAS)。
陀螺仪传感器180B可以用于确定终端设备100的运动姿态。在一些实施例中，可以通过陀螺仪传感器180B确定终端设备100围绕三个轴(即，x，y和z轴)的角速度。在一些实施例中，陀螺仪传感器180B可以用于测量终端设备的角速度。
加速度传感器180E可检测终端设备100在各个方向上(一般为三轴)加速度的大小。当终端设备100静止时可检测出重力的大小及方向。还可以用于识别电子设备姿态，应用于横竖屏切换，计步器等应用。在一些实施例中，加速度传感器180E可用于测量终端设备的移动加速度，还可将加速度传感器180E与陀螺仪传感器180B结合，用于确定终端设备的移动速度。
SIM卡接口195用于连接SIM卡。SIM卡可以通过插入SIM卡接口195，或从SIM卡接口195拔出，实现和终端设备100的接触和分离。终端设备100可以支持1个或多个SIM卡接口。SIM卡接口195可以支持Nano SIM卡，Micro SIM卡，SIM卡等。同一个SIM卡接口195可以同时插入多张卡。多张卡的类型可以相同，也可以不同。SIM卡接口195也可以兼容不同类型的SIM卡。SIM卡接口195也可以兼容外部存储卡。终端设备100通过SIM卡和网络交互，实现通话以及数据通信等功能。在一些实施例中，终端设备100采用eSIM，即：嵌入式SIM卡。eSIM卡可以嵌在终端设备100中，不能和终端设备100分离。
示例性的，在终端设备包括2个SIM卡接口时，可将一个SIM卡接口设为主卡接口，插入主卡接口的SIM卡为终端设备的主卡；将另一个SIM卡接口设为副卡接口，插入副卡接口的SIM卡为终端设备的副卡。终端设备可通过主卡或副卡与其他设备进行通信。
在一些实施例中，终端设备100的陀螺仪传感器180B、加速度传感器180E、移动通信模块150、无线通信模块160、调制解调处理器等采集测量模块，可按照预设周期向处理器110 上报采集的传感器数据和/或测量的信号参数值。
处理器110可从所述采集测量模块上报的传感器数据和/或信号参数值中，获取终端设备100的移动速度、多普勒频偏等信息，进而根据终端设备100的移动速度、多普勒频偏等信息，确定与终端设备100当前的第一工作模式对应的相干时窗长度，并根据相干时窗长度及终端设备100在第一工作模式下的通信状态的多个历史值，确定终端设备100的通信状态的预测值；在通信状态的预测值满足预设条件的情况下，将终端设备100的工作模式调整为第二工作模式，第二工作模式与第一工作模式的信道不同。在一些实施例中，终端设备的采集测量模块还可包括其他模块，本申请对此不作限制。
图2示出根据本申请一实施例的工作模式调整方法的应用场景的示意图。如图2所示，终端设备200包括应用处理器210、无线接口层220、基带处理器230及采集测量模块240。其中，应用处理器210用于执行终端设备200上与应用程序相关的处理，基带处理器230用于执行终端设备200上与通信(例如蜂窝通信、Wi-Fi通信等)相关的处理，与通信相关的处理可包括空口状态分析、下行带宽估计、空口状态预测、空口状态上报等。
采集测量模块240可包括物理层(physical layer，PHY)、无线资源控制(radio resource control，RRC)、媒体存取控制位址(media access control address，MAC地址，也称为物理地址)、前向纠错(forward error collection，FEC)、调制解调处理器(modem)等模块。可选的，采集测量模块还可包括传感器，例如陀螺仪传感器、加速度传感器等。
采集测量模块240可按照预设周期(例如100ms)向基带处理器230上报采集的传感器数据和/或测量的信号参数值。其中，信号参数值可包括接收信号强度指示(received signal strength indication、RSSI)、参考信号接收功率(reference signal receiving power，RSRP)、误块率(block error rate，BLER)、信噪比(signal-noise ratio，SNR)、多普勒频偏等中的至少一项参数的取值。
基带处理器230可从采集测量模块240上报的信号参数值和/或传感器数据中，获取终端设备200的移动速度、多普勒频偏等信息，并根据终端设备200的移动速度、多普勒频偏等信息，确定与终端设备200当前的第一工作模式对应的相干时窗长度；
然后根据相干时窗长度及终端设备200在第一工作模式下的通信状态的多个历史值(即多个历史空口状态)，确定终端设备的通信状态的预测值(即空口状态的预测值)，并将通信状态的预测值通过无线接口层(radio interface layer，RIL)220，上报给应用处理器210。其中，通信状态可包括信号强度、传输时延或网络带宽中的至少一项，第一工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种。
应用处理器210可判断接收到的通信状态的预测值是否满足预设条件，并在通信状态的预测值满足预设条件的情况下，将终端设备的工作模式调整为第二工作模式。其中，第二工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种，且第二工作模式与第一工作模式的信道不同；预设条件可包括通信状态的预测值中的信号强度小于或等于预设的信号强度阈值、通信状态的预测值中的传输时延大于或等于预设的传输时延阈值、通信状态的预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
例如，终端设备200具有主卡和副卡，当前的第一工作模式为主卡数据流量工作模式，在终端设备200的通信状态的预测值中的信号强度小于或等于预设的信号强度阈值的情况下， 可将终端设备200的工作模式调整为副卡数量流量工作模式(即第二工作模式)。即：主卡上网信号差时，切换至副卡上网。
图3示出根据本申请一实施例的工作模式调整方法的应用场景的示意图。如图3所示，终端设备包括调制解调处理器310、基带处理器320及应用处理器330。其中，调制解调处理器310可看作终端设备的采集测量模块，基带处理器320包括接口适配层321及空口状态预测模块322。
调制解调处理器310可按照预设周期，将测量的信号参数值通过终端设备中的接口控制设备(interface control device，ICD)，上报给基带处理器320。基带处理器320的接口适配层321(包括参数适配接口及控制适配接口)收到调制解调处理器310上报的信号参数值后，可对信号参数值进行格式化处理，得到格式化后的信号参数值，并将格式化后的信号参数值发送给空口状态预测模块322。
空口状态预测模块322可从格式化后的信号参数值中，获取终端设备的移动速度、多普勒频偏等信息，并根据终端设备的移动速度、多普勒频偏等信息，确定与终端设备当前的第一工作模式对应的相干时窗长度，然后根据相干时窗长度及终端设备在第一工作模式下的多个历史空口状态(即通信状态的多个历史值)，对终端设备的空口状态进行预测，得到空口状态的预测值(即通信状态的预测值)，并通过无线接口层(图中未示出)将该预测值发送给应用处理器330。
应用处理器330可判断接收的通信状态的预测值是否满足预设条件，并在预测值满足预设条件的情况下，进行工作模式调整，即将终端设备的工作模式从第一工作模式调整为第二工作模式。
需要说明的是，图3仅以调制解调处理器modem作为示例，对终端设备采集测量模块测量的信号参数值的上报过程进行了示例性地说明。在本申请的另一些实施例中，采集测量模块还可以是其他模块，本申请对采集测量模块的具体实现方式不作限制。
图4示出根据本申请一实施例的工作模式调整方法的流程图。如图4所示，所述工作模式调整方法包括：
步骤S410，确定与所述终端设备当前的第一工作模式对应的相干时窗长度。
在一种可能的实现方式中，可从终端设备的采集测量模块(即终端设备的底层)周期上报的传感器数据和/或信号参数值中，获取终端设备的移动速度、多普勒频偏等信息。其中，采集测量模块可包括物理层PHY、无线资源控制RRC、MAC地址、前向纠错FEC、调制解调处理器modem、陀螺仪传感器或加速度传感器等中的至少一种。
可选的，终端设备的移动速度可从陀螺仪传感器、加速度传感器等与终端设备的运动状态相关的传感器上报的数据中获取。多普勒频偏可从调制解调处理器等上报的信号参数值中获取。例如，终端设备的调制解调处理器可通过接口控制设备ICD上报信号参数值，接口控制设备ICD中的消息处理函数可申请一块缓存区，将调制解调处理器按照预设周期(例如100ms)上报的信号参数值存储在缓存区；终端设备的基带处理器可从上述缓存区存储的信号参数值中，获取终端设备的多普勒频偏。
可根据终端设备的移动速度、多普勒频偏等信息，确定与终端设备当前的第一工作模式对应的相干时窗长度。其中，第一工作模式可以为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种。需要说明的是，第一工作模式还可以是终端 设备的其他工作模式，本申请对此不作限制。
相干时窗即信道相干时间窗口，是信道保持恒定的最大时间差范围。在信道相干时窗内的连续物理信号具有很好的相关性，一般认为受到的无线衰落相似。而不同移动场景下的信道相干时间窗口一般都不同，例如在高铁场景下，由于多普勒效应的影响，信道处于快衰落模式，信道相干时间窗口会很短；在写字楼居民区等静态场景，信道相对更平稳，信道相干时间窗口会更长。
通过终端设备的移动速度、多普勒频偏等信息，确定与终端设备当前的第一工作模式对应的相干时窗长度，能够将终端设备映射到不同的信道场景，从而能够将终端设备的工作模式调整与信道场景相结合，提高工作模式调整的时效性。
步骤S420，根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值。
根据信号的自相关特性，在信道相干时间窗口内，当前时刻之后的第二时刻(即未来时刻)的预测信号值与当前时刻之前的多个第一时刻(即历史时刻)的历史信号值有关。基于该假设，可根据相干时窗长度及终端设备在第一工作模式下的通信状态的多个历史值，确定终端设备的通信状态的预测值。
例如，假设相干时窗长度为5，即终端设备当前时刻的下一时刻的通信状态与当前时刻之前的5个时刻的通信状态相关，则可根据当前时刻之前的5个第一时刻的通信状态，通过平滑滤波等方式，确定当前时刻之后的第二时刻的通信状态的预测值。
在一种可能的实现方式中，平滑滤波可通过下述公式(1)表示：
Figure PCTCN2022083121-appb-000001
公式(1)中，N表示相干时窗长度，n表示共有n个时刻，其中，前n-1个时刻为当前时刻之前的第一时刻，第n个时刻为当前时刻之后的第二时刻，
Figure PCTCN2022083121-appb-000002
表示第二时刻的通信状态的预测值，y n-1、y n-2、…、y n-N表示当前时刻之前的N个第一时刻的通信状态(为真实值)，α 1、α 2、…、α N表示权重系数。
在一种可能的实现方式中，权重系数可以是与相干时窗长度对应的固定系数，相干时窗长度不同，对应的权重系数也可能不同。权重系数还可以是根据相干时窗长度及终端设备在第一工作模式下的通信状态的多个历史值，自适应更新的系数。
在一种可能的实现方式中，所述通信状态的多个历史值可包括当前时刻之前的L个第一时刻的通信状态，所述通信状态的预测值可包括所述当前时刻之后的M个第二时刻的通信状态的预测值，所述相干时窗长度为N，其中，L，M，N为整数，L>N>1，M≥1，
步骤S420可包括：在M＝1的情况下，根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，所述与第1个第二时刻对应的权重系数用于指示所述第1个第二时刻的相干时窗内的多个第一时刻的通信状态的权重；根据所述与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值。
举例来说，假设相干时窗长度N＝5，第一时刻的数量L＝20，相应地，权重系数有5个，权重系数的初始值可以预先设置。
根据相干时窗长度5及20个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数时，可首先根据第0组权重系数(即权重系数的初始值)、第1个第一时刻至第5个第一时 刻的通信状态，确定第6个第一时刻的通信状态的预测值；根据第0组权重系数、第6个第一时刻的通信状态(真实值)及第6个第一时刻的通信状态的预测值，确定第1组权重系数。
可选的，可确定第6个第一时刻的通信状态(真实值)与第6个第一时刻的通信状态的预测值之间的差值，并根据该差值对第0组权重系数进行更新，得到第1组权重系数。
可选的，确定第1组权重系数时，还可考虑第1个第一时刻至第5个第一时刻的通信状态。可确定第6个第一时刻的通信状态(真实值)与第6个第一时刻的通信状态的预测值之间的差值，并根据该差值及第1个第一时刻至第5个第一时刻的通信状态，确定第0组权重系数中各个权重系数的调整值，根据各个权重系数的调整值，对第0组权重系数进行更新，得到第1组权重系数。
确定第1组权重系数后，可根据第1组权重系数、第2个第一时刻至第6个第一时刻的通信状态，确定第7个第一时刻的通信状态的预测值；根据第1组权重系数、第7个第一时刻的通信状态及第7个第一时刻的通信状态的预测值，确定第2组权重系数。
以此类推，可根据第i-1组权重系数、第i个第一时刻至第i+N-1个第一时刻的通信状态，确定第i+N个第一时刻的通信状态的预测值，其中，i为整数且0≤i≤L-N；并根据第i-1组权重系数、第i+N个第一时刻的通信状态以及第i+N个第一时刻的通信状态的预测值，确定第i组权重系数。
可选的，可确定第i+N个第一时刻的通信状态(真实值)与第i+N个第一时刻的通信状态的预测值之间的差值，并根据该差值对第i-1组权重系数进行更新，得到第i组权重系数。
可选的，确定第i组权重系数时，还可考虑第i个第一时刻至第i+N-1个第一时刻的通信状态。可确定第i+N个第一时刻的通信状态与第i+N个第一时刻的通信状态的预测值之间的差值，并根据该差值及第i个第一时刻至第i+N-1个第一时刻的通信状态，确定第i-1组权重系数中各个权重系数的调整值，根据各个权重系数的调整值，对第i-1组权重系数进行更新，得到第i组权重系数。
使用类似的方式，通过滑动相干时窗，可确定出第L-N+1组权重系数，并将第L-N+1组权重系数，确定为与第1个第二时刻对应的权重系数。例如，在相干时窗长度N＝5，第一时刻的数量L＝20的情况下，20-5+1＝16，可将第16组权重系数，确定为与第1个第二时刻对应的权重系数。其中，与第1个第二时刻对应的权重系数可用于指示所述第1个第二时刻的相干时窗内的多个第一时刻的通信状态的权重。
通过上述随机梯度下降的方式，对权重系数进行训练，得到与第1个第二时刻对应的权重系数，使得权重系数可以自适应调整，以适应不同的信道场景，从而能够提高权重系数的准确性。
确定与第1个第二时刻对应的权重系数后，可根据与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值。例如，在相干时窗长度N＝5，第一时刻的数量L＝20的情况下，可根据与第1个第二时刻对应的权重系数、第16个第一时刻至第20个第一时刻的通信状态，通过上述公式(1)，确定第1个第二时刻的通信状态的预测值。
通过这种方式，能够根据相干时窗长度N及L个第一时刻的通信状态，对权重系数进行训练，得到与第1个第二时刻对应的权重系数，并根据与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定终端设备在下一时刻(即第1个第 二时刻)的通信状态的预测值，从而能够提高通信状态的预测值的准确性。
在一种可能的实现方式中，步骤S420还可包括：在M>1的情况下，针对第j个第二时刻,根据所述相干时窗长度N、所述L个第一时刻的通信状态、第1个第二时刻至第j-1个第二时刻的通信状态的预测值及与第j-1个第二时刻对应的权重系数，确定与第j个第二时刻对应的权重系数，所述与第j个第二时刻对应的权重系数用于指示所述第j个第二时刻的相干时窗内的第一时刻的通信状态及第二时刻的通信状态的预测值的权重，其中，1<j≤M<N；根据所述与第j个第二时刻对应的权重系数、所述相干时窗长度N、所述L个第一时刻的通信状态及第1个第二时刻至第j-1个第二时刻的通信状态的预测值，确定所述第j个第二时刻的通信状态的预测值。
举例来说，假设相干时窗长度N＝5，第一时刻的数量L＝20，对于第2个第二时刻，可根据20个第一时刻的通信状态中的第17个第一时刻至第20个第一时刻的通信状态、第1个第二时刻的通信状态的预测值及与第1个第二时刻对应的权重系数，通过与上述类似的方式，确定与第2个第二时刻对应的权重系数。其中，与第2个第二时刻对应的权重系数用于指示第2个第二时刻的相干时窗内第17个第一时刻至第20个第一时刻的通信状态以及第1个第二时刻的通信状态的预测值的权重。
然后可根据与第2个第二时刻对应的权重系数、第17个第一时刻至第20个第一时刻的通信状态、以及第1个第二时刻的通信状态的预测值，通过上述公式(1)，确定第2个第二时刻的通信状态的预测值。
对于第3个第二时刻，可根据20个第一时刻的通信状态中的第18个第一时刻至第20个第一时刻的通信状态、第1个第二时刻至第2个第二时刻的通信状态的预测值及与第2个第二时刻对应的权重系数，通过与上述类似的方式，确定与第3个第二时刻对应的权重系数。其中，与第3个第二时刻对应的权重系数用于指示第3个第二时刻的相干时窗内第18个第一时刻至第20个第一时刻的通信状态以及第1个第二时刻至第2个第二时刻的通信状态的预测值的权重。
然后可根据与第3个第二时刻对应的权重系数、第18个第一时刻至第20个第一时刻的通信状态、以及第1个第二时刻至第2个第二时刻的通信状态的预测值，通过上述公式(1)，确定第3个第二时刻的通信状态的预测值。
在j取值为其他时，第j个第二时刻的通信状态的预测值的确定方式与上述类似，在此不做重复性描述。
通过这种方式，能够基于L个第一时刻的通信状态及第1个第二时刻至第j个第二时刻的通信状态的预测值，对第j+1个第二时刻的通信状态进行迭代预测，得到第j+1个第二时刻的通信状态的预测值，从而实现多步预测。
需要说明的是，本领域技术人员可根据实际情况确定上述N、L、M的具体取值，本申请对此不作限制。
步骤S430，在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式。
其中，第二工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种，且第二工作模式与第一工作模式的信道不同。需要说明的是，第二工作模式还可以是终端设备的其他工作模式，本申请对此不作限制。
通信状态可包括信号强度、传输时延或网络带宽中的至少一种，相应的，通信状态的预测值也可包括信号强度、传输时延或网络带宽中的至少一种。
预设条件可包括通信状态的预测值中的信号强度小于或等于预设的信号强度阈值、通信状态的预测值中的传输时延大于或等于预设的传输时延阈值、通信状态的预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
判断通信状态的预测值是否满足预设条件时，可对预测值中包括的信号强度、传输时延、网络带宽分别进行判断，并在预测值中的任一项满足预设条件时，认为通信状态的预测值满足预设条件，或者，在预测值中的所有项均满足预设条件时，认为通信状态的预测值满足预设条件。
例如，在通信状态的预测值包括信号强度的情况下，可将通信状态的预测值中的信号强度与预设的信号强度阈值进行比较。在通信状态的预测值为1个的情况下，即通信状态的预测值为终端设备在第1个第二时刻的通信状态的预测值，可将第1个第二时刻的通信状态的预测值中的信号强度与信号强度阈值进行比较，并在第1个第二时刻的通信状态的预测值中的信号强度小于或等于信号强度阈值的情况下，认为终端设备的预测值满足预设条件，可将终端设备的工作模式调整为第二工作模式
在通信状态的预测值为多个的情况下，可将最后一个第二时刻的通信状态的预测值中的信号强度与信号强度阈值进行比较。例如，在通信状态的预测值为4个的情况下，可将第4个第二时刻的通信状态的预测值中的信号强度与信号强度阈值进行比较，并在第4个第二时刻的通信状态的预测中的信号强度小于或等于信号强度阈值的情况下，认为终端设备的预测值满足预设条件，可将终端设备的工作模式调整为第二工作模式。
在通信状态的预测值包括传输时延或网络带宽的情况下，其判断通信状态的预测值是否满足预设条件的方式与上述类似，在此不做重复性描述。
根据本申请的实施例，能够在确定终端设备的通信状态的预测值时考虑相干时窗长度(即不同的信道场景)，并在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通讯过程中的网络波动，有效提升用户体验。
图5示出根据本申请一实施例的工作模式调整方法的流程图。如图5所示，所述工作模式调整方法包括步骤S410、步骤S4201、步骤S4202、步骤S4203、步骤S4204及步骤S430。其中，步骤S4201至步骤S4204为图4所示实施例中的步骤S420的一种可能的更为细化的实现方式。
步骤S410，确定与所述终端设备当前的第一工作模式对应的相干时窗长度。可选地，图5所示实施例中的步骤S410与图4所示实施例中的步骤S410类似，在此不做重复性描述。
步骤S4201，对所述L个第一时刻的通信状态进行预处理，得到L个第一时刻的预处理后的通信状态，所述预处理包括归一化及差分处理。
可对L个第一时刻的通信状态进行归一化及差分等预处理，得到L个第一时刻的预处理后的通信状态，以减轻通信状态的非平稳性。
在一种可能的实现方式中，可通过下述公式(2)对L个第一时刻的通信状态进行归一化处理：
Figure PCTCN2022083121-appb-000003
公式(2)中，p、q为整数，且0≤p≤L-1、0≤q≤L-1，n表示共有n个时刻，前n-1个时刻为当前时刻之前的第一时刻，第n个时刻为当前时刻之后的第1个第二时刻。y(n-L)、y(n-L+1)、…、y(n-2)、y(n-1)表示当前时刻之前的L个时刻的通信状态。
其中，y(n-L)表示第1个第一时刻的通信状态，也表示第n-L时刻的通信状态；y(n-L+1)表示第2个第一时刻的通信状态，也表示第n-L+1时刻的通信状态；…；y(n-2)表示第L-1个第一时刻的通信状态，也表示第n-2时刻的通信状态；y(n-1)表示第L个第一时刻的通信状态，也表示第n-1时刻的通信状态。
y(n-L+q)为第q+1个第一时刻的通信状态，也表示第n-L+q时刻的通信状态；y(n-L+p)为第p+1个第一时刻的通信状态，也表示第n-L+p时刻的通信状态；y′(n-L+p)表示第p+1个第一时刻的归一化处理后的通信状态，也表示第n-L+p时刻的归一化处理后的通信状态。
在一种可能的实现方式中，可通过下述公式(3)对L个第一时刻的归一化处理后的通信状态进行差分处理，得到L个第一时刻的预处理后的通信状态：
Figure PCTCN2022083121-appb-000004
公式(3)中，
Figure PCTCN2022083121-appb-000005
表示第1个第一时刻的预处理后的通信状态，也表示第n-L时刻的预处理后的通信状态；
Figure PCTCN2022083121-appb-000006
表示第p+1个第一时刻的预处理后的通信状态，也表示第n-L+p时刻的预处理后的通信状态；
Figure PCTCN2022083121-appb-000007
表示第L个第一时刻的预处理后的通信状态，也表示第n-1时刻的预处理后的通信状态。
步骤S4202，根据所述相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数。
其中，与第1个第二时刻对应的差分权重系数，也就是与第n时刻对应的差分权重系数。
在一种可能的实现方式中，可根据预设的差分权重系数初始值(即第0组差分权重系数)、第1个第一时刻至第N个第一时刻的预处理后的通信状态，确定第N+1个第一时刻的通信状态的差分预测值。
例如，预设的差分权重系数初始值为
Figure PCTCN2022083121-appb-000008
可根据第1个第一时刻至第N个第一时刻的预处理后的通信状态
Figure PCTCN2022083121-appb-000009
Figure PCTCN2022083121-appb-000010
通过下述公式(4)，确定第N+1个第一时刻的通信状态的差分预测值
Figure PCTCN2022083121-appb-000011
Figure PCTCN2022083121-appb-000012
公式(4)中，v为整数且1≤v≤N，α v表示第v个权重系数，
Figure PCTCN2022083121-appb-000013
表示第N-v+1个第一时刻的预处理后的通信状态，也表示第n-L+N-v时刻的预处理后的通信状态。
然后可根据第2个第一时刻至第N+1个第一时刻的预处理后的通信状态、第N+1个第一时刻的通信状态的差分预测值，对第0组差分权重系数进行调整，得到第1组差分权重系数。
可通过下述公式(5)，确定第1组差分权重系数(即第n-L+N时刻的差分权重系数)：
Figure PCTCN2022083121-appb-000014
公式(5)中，
Figure PCTCN2022083121-appb-000015
表示第0组差分权重系数，即更新前的差分权重系数；
Figure PCTCN2022083121-appb-000016
表示第1组差分权重系数，即更新后的差分权重系数；
Figure PCTCN2022083121-appb-000017
表示第N+1个第一时刻的预处理后的通信状态，也表示第n-L+N时刻的预处理后的通信状态；
Figure PCTCN2022083121-appb-000018
表示第N个第一时刻的预处理后的通信状态，也表示第n-L+N-1时刻的预处理后的通信状态；
Figure PCTCN2022083121-appb-000019
表示第2个第一时刻的预处理后的通信状态，也表示第n-L+1时刻的预处理后的通信状态。
可滑动相干时窗，通过与上述方式，依次确定第2组差分权重系数(即第n-L+N+1时刻的差分权重系数)、第3组差分权重系数(即第n-L+N+2时刻的差分权重系数)、…、第L-N+1组差分权重系数(即第n时刻的差分权重系数)。
然后将第L-N+1组差分权重系数(即第n时刻的差分权重系数)，确定为与第1个第二时刻对应的差分权重系数。
步骤S4203，根据所述与第1个第二时刻对应的差分权重系数及第L-N+1个第一时刻至第L个第一时刻的预处理后的通信状态，确定所述第1个第二时刻的通信状态的差分预测值。
例如，假设与第1个第二时刻对应的差分权重系数为
Figure PCTCN2022083121-appb-000020
可根据差分权重系数
Figure PCTCN2022083121-appb-000021
及第L-N+1个第一时刻至第L个第一时刻的预处理后的通信状态(即第n-N时刻至第n-1时刻的预处理后的通信状态),确定第1个第二时刻(即第n时刻)的通信状态的差分预测值。
在一种可能的实现方式中，可通过下述公式(6)，来确定第1个第二时刻(即第n时刻)的通信状态的差分预测值
Figure PCTCN2022083121-appb-000022
Figure PCTCN2022083121-appb-000023
公式(6)中，α″ v表示第v个权重系数，
Figure PCTCN2022083121-appb-000024
表示第L-v+1个第一时刻的预处理后的通信状态，也表示第n-v时刻的预处理后的通信状态。
步骤S4204，对所述差分预测值进行后处理，得到所述第1个第二时刻的通信状态的预测值，所述后处理包括逆差分及反归一化处理。
确定第1个第二时刻(即第n时刻)的通信状态的差分预测值后，可对该差分预测值进行后处理，后处理包括逆差分及反归一化，从而得到第1个第二时刻(即第n时刻)的通信状态的预测值。
在一种可能的实现方式中，可通过下述公式(7)，确定第1个第二时刻(即第n时刻)的通信状态的预测值
Figure PCTCN2022083121-appb-000025
Figure PCTCN2022083121-appb-000026
公式(7)中，u为整数且n-L≤u≤n-1。
在一种可能的实现方式中，还可滑动相干时窗，通过上述方式，对第j个第二时刻的通信状态进行迭代预测，得到第j个第二时刻的通信状态的预测值，从而实现多步预测。
步骤S430，在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式。
其中，所述第二工作模式与所述第一工作模式的信道不同,所述预设条件包括所述预测值中的信号强度小于或等于预设的信号强度阈值、所述预测值中的传输时延大于或等于预设的传输时延阈值、所述预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
可选地，图5所示实施例中的步骤S430与图4所示实施例中的步骤S430类似，在此不做重复性描述。
在本实施例中，能够对L个第一时刻的通信状态进行归一化及差分等预处理，得到L个第一时刻的预处理后的通信状态，并根据相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数，进而确定第1个第二时刻的通信状态的差分预测值，然后对该差分预测值进行逆差分及反归一化等后处理，得到第1个第二时刻的通信状态的预测值，并在该预测值满足预设条件的情况下，将终端设备的工作模式调整为第二工作模式，从而能够通过对通信状态的预处理，减少通信状态的非平稳性，基于预处理后的通信状态进行预测，可提高通信状态的预测准确性。
此外，在通信状态的预测值满足预设条件的情况下，对终端设备的工作模式进行调整，从而能够在通信状态较差(例如信号较弱、传输时延较大、网络带宽较小等)的情况下，提前对终端设备的工作模式进行调整，使得用户感觉不到通信过程中的网络波动，有效提升用户体验。
本申请实施例所述的工作模式调整方法，应用于终端设备，能够在不同信道场景下基于通信状态的预测值来对终端设备的工作模式进行调整，从而能够在通信状态较差的情况下，提前对终端设备的工作模式进行调整，减少通信过程中的卡顿感，使得用户感觉不到通讯过程中的网络波动，有效提升用户体验。
此外，在视频应用等媒体流分发时，也可根据通信状态的预测值，提前进行视频码率的调整，减少用户查看视频时的卡顿感，提升用户体验。
图6示出根据本申请一实施例的工作模式调整装置的框图。所述工作模式调整装置应用于终端设备。如图6所示，所述工作模式调整装置包括：
相干时窗确定模块610，用于确定与所述终端设备当前的第一工作模式对应的相干时窗长度；
预测模块620，用于根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，所述通信状态包括信号强度、传输时延或网络带宽中的至少一种；
调整模块630，用于在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式，
其中，所述第二工作模式与所述第一工作模式的信道不同，所述预设条件包括所述预测值中的信号强度小于或等于预设的信号强度阈值、所述预测值中的传输时延大于或等于预设的传输时延阈值、所述预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
在一种可能的实现方式中，所述通信状态的多个历史值包括当前时刻之前的L个第一时 刻的通信状态，所述通信状态的预测值包括所述当前时刻之后的M个第二时刻的通信状态的预测值，所述相干时窗长度为N，其中，L，M，N为整数，L>N>1，M≥1，
所述预测模块620，包括：第一系数确定子模块，用于在M＝1的情况下，根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，所述与第1个第二时刻对应的权重系数用于指示所述第1个第二时刻的相干时窗内的多个第一时刻的通信状态的权重；第一预测子模块，用于根据所述与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值。
在一种可能的实现方式中，所述预测模块620，还包括：第二系数确定子模块，用于在M>1的情况下，针对第j个第二时刻,根据所述相干时窗长度N、所述L个第一时刻的通信状态、第1个第二时刻至第j-1个第二时刻的通信状态的预测值及与第j-1个第二时刻对应的权重系数，确定与第j个第二时刻对应的权重系数，所述与第j个第二时刻对应的权重系数用于指示所述第j个第二时刻的相干时窗内的第一时刻的通信状态及第二时刻的通信状态的预测值的权重，其中，1<j≤M<N；第二预测子模块，用于根据所述与第j个第二时刻对应的权重系数、所述相干时窗长度N、所述L个第一时刻的通信状态及第1个第二时刻至第j-1个第二时刻的通信状态的预测值，确定所述第j个第二时刻的通信状态的预测值。
在一种可能的实现方式中，所述第一系数确定子模块，被配置为：根据第i-1组权重系数、第i个第一时刻至第i+N-1个第一时刻的通信状态，确定第i+N个第一时刻的通信状态的预测值，i为整数且0≤i≤L-N，第0组权重系数为权重系数的初始值；根据第i-1组权重系数、第i+N个第一时刻的通信状态以及第i+N个第一时刻的通信状态的预测值，确定第i组权重系数；将第L-N+1组权重系数，确定为与第1个第二时刻对应的权重系数。
在一种可能的实现方式中，所述第一系数确定子模块，被配置为：对所述L个第一时刻的通信状态进行预处理，得到L个第一时刻的预处理后的通信状态，所述预处理包括归一化及差分处理；根据所述相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数；
其中，所述第一预测子模块，被配置为：根据所述与第1个第二时刻对应的差分权重系数及第L-N+1个第一时刻至第L个第一时刻的预处理后的通信状态，确定所述第1个第二时刻的通信状态的差分预测值；对所述差分预测值进行后处理，得到所述第1个第二时刻的通信状态的预测值，所述后处理包括逆差分及反归一化处理。
在一种可能的实现方式中，所述第一工作模式及所述第二工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种。
本申请的实施例提供了一种工作模式调整装置，包括：处理器以及用于存储处理器可执行指令的存储器；其中，所述处理器被配置为执行所述指令时实现上述方法。
本申请的实施例提供了一种非易失性计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。
本申请的实施例提供了一种计算机程序产品，包括计算机可读代码，或者承载有计算机可读代码的非易失性计算机可读存储介质，当所述计算机可读代码在电子设备的处理器中运行时，所述电子设备中的处理器执行上述方法。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计 算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(Random Access Memory，RAM)、只读存储器(Read Only Memory，ROM)、可擦式可编程只读存储器(Electrical ly Programmable Read-Only-Memory，EPROM或闪存)、静态随机存取存储器(Static Random-Access Memory，SRAM)、便携式压缩盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、数字多功能盘(Digital Video Disc，DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。
这里所描述的计算机可读程序指令或代码可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本申请操作的计算机程序指令可以是汇编指令、指令集架构(Instruction Set Architecture，ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(Local Area Network，LAN)或广域网(Wide Area Network，WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或可编程逻辑阵列(Programmable Logic Array，PLA)，该电子电路可以执行计算机可读程序指令，从而实现本申请的各个方面。
这里参照根据本申请实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本申请的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机 实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本申请的多个实施例的装置、系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。
也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行相应的功能或动作的硬件(例如电路或ASIC(Application Specific Integrated Circuit，专用集成电路))来实现，或者可以用硬件和软件的组合，如固件等来实现。
尽管在此结合各实施例对本发明进行了描述，然而，在实施所要求保护的本发明过程中，本领域技术人员通过查看所述附图、公开内容、以及所附权利要求书，可理解并实现所述公开实施例的其它变化。在权利要求中，“包括”(comprising)一词不排除其他组成部分或步骤，“一”或“一个”不排除多个的情况。单个处理器或其它单元可以实现权利要求中列举的若干项功能。相互不同的从属权利要求中记载了某些措施，但这并不表示这些措施不能组合起来产生良好的效果。
以上已经描述了本申请的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术的改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (15)

  1. 一种工作模式调整方法，其特征在于，所述方法应用于终端设备，所述方法包括：
    确定与所述终端设备当前的第一工作模式对应的相干时窗长度；
    根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，所述通信状态包括信号强度、传输时延或网络带宽中的至少一种；
    在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式，
    其中，所述第二工作模式与所述第一工作模式的信道不同,所述预设条件包括所述预测值中的信号强度小于或等于预设的信号强度阈值、所述预测值中的传输时延大于或等于预设的传输时延阈值、所述预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
  2. 根据权利要求1所述的方法，其特征在于，所述通信状态的多个历史值包括当前时刻之前的L个第一时刻的通信状态，所述通信状态的预测值包括所述当前时刻之后的M个第二时刻的通信状态的预测值，所述相干时窗长度为N，其中，L，M，N为整数，L>N>1，M≥1，
    所述根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，包括：
    在M＝1的情况下，根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，所述与第1个第二时刻对应的权重系数用于指示所述第1个第二时刻的相干时窗内的多个第一时刻的通信状态的权重；
    根据所述与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，还包括：
    在M>1的情况下，针对第j个第二时刻,根据所述相干时窗长度N、所述L个第一时刻的通信状态、第1个第二时刻至第j-1个第二时刻的通信状态的预测值及与第j-1个第二时刻对应的权重系数，确定与第j个第二时刻对应的权重系数，所述与第j个第二时刻对应的权重系数用于指示所述第j个第二时刻的相干时窗内的第一时刻的通信状态及第二时刻的通信状态的预测值的权重，其中，1<j≤M<N；
    根据所述与第j个第二时刻对应的权重系数、所述相干时窗长度N、所述L个第一时刻的通信状态及第1个第二时刻至第j-1个第二时刻的通信状态的预测值，确定所述第j个第二时刻的通信状态的预测值。
  4. 根据权利要求2所述的方法，其特征在于，所述根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，包括：
    根据第i-1组权重系数、第i个第一时刻至第i+N-1个第一时刻的通信状态，确定第i+N个第一时刻的通信状态的预测值，i为整数且0≤i≤L-N，第0组权重系数为权重系数的初始值；
    根据第i-1组权重系数、第i+N个第一时刻的通信状态以及第i+N个第一时刻的通信状态的预测值，确定第i组权重系数；
    将第L-N+1组权重系数，确定为与第1个第二时刻对应的权重系数。
  5. 根据权利要求2所述的方法，其特征在于，所述根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，包括：
    对所述L个第一时刻的通信状态进行预处理，得到L个第一时刻的预处理后的通信状态，所述预处理包括归一化及差分处理；
    根据所述相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数；
    其中，所述根据与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值，包括：
    根据所述与第1个第二时刻对应的差分权重系数及第L-N+1个第一时刻至第L个第一时刻的预处理后的通信状态，确定所述第1个第二时刻的通信状态的差分预测值；
    对所述差分预测值进行后处理，得到所述第1个第二时刻的通信状态的预测值，所述后处理包括逆差分及反归一化处理。
  6. 根据权利要求1-5中任意一项所述的方法，其特征在于，所述第一工作模式及所述第二工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种。
  7. 一种工作模式调整装置，其特征在于，所述装置应用于终端设备，所述装置包括：
    相干时窗确定模块，用于确定与所述终端设备当前的第一工作模式对应的相干时窗长度；
    预测模块，用于根据所述相干时窗长度及所述终端设备在所述第一工作模式下的通信状态的多个历史值，确定所述终端设备的通信状态的预测值，所述通信状态包括信号强度、传输时延或网络带宽中的至少一种；
    调整模块，用于在所述预测值满足预设条件的情况下，将所述终端设备的工作模式调整为第二工作模式，
    其中，所述第二工作模式与所述第一工作模式的信道不同,所述预设条件包括所述预测值中的信号强度小于或等于预设的信号强度阈值、所述预测值中的传输时延大于或等于预设的传输时延阈值、所述预测值中的网络带宽小于或等于预设的网络带宽阈值中的至少一种。
  8. 根据权利要求7所述的装置，其特征在于，所述通信状态的多个历史值包括当前时刻之前的L个第一时刻的通信状态，所述通信状态的预测值包括所述当前时刻之后的M个第二时刻的通信状态的预测值，所述相干时窗长度为N，其中，L，M，N为整数，L>N>1，M≥1，
    所述预测模块，包括：
    第一系数确定子模块，用于在M＝1的情况下，根据所述相干时窗长度N及所述L个第一时刻的通信状态，确定与第1个第二时刻对应的权重系数，所述与第1个第二时刻对应的权重系数用于指示所述第1个第二时刻的相干时窗内的多个第一时刻的通信状态的权重；
    第一预测子模块，用于根据所述与第1个第二时刻对应的权重系数、第L-N+1个第一时刻至第L个第一时刻的通信状态，确定所述第1个第二时刻的通信状态的预测值。
  9. 根据权利要求8所述的装置，其特征在于，所述预测模块，还包括：
    第二系数确定子模块，用于在M>1的情况下，针对第j个第二时刻,根据所述相干时窗长度N、所述L个第一时刻的通信状态、第1个第二时刻至第j-1个第二时刻的通信状态的预测值及与第j-1个第二时刻对应的权重系数，确定与第j个第二时刻对应的权重系数，所述与第j个第二时刻对应的权重系数用于指示所述第j个第二时刻的相干时窗内的第一时刻的通信状态及第二时刻的通信状态的预测值的权重，其中，1<j≤M<N；
    第二预测子模块，用于根据所述与第j个第二时刻对应的权重系数、所述相干时窗长度N、所述L个第一时刻的通信状态及第1个第二时刻至第j-1个第二时刻的通信状态的预测值，确定所述第j个第二时刻的通信状态的预测值。
  10. 根据权利要求8所述的装置，其特征在于，所述第一系数确定子模块，被配置为：
    根据第i-1组权重系数、第i个第一时刻至第i+N-1个第一时刻的通信状态，确定第i+N个第一时刻的通信状态的预测值，i为整数且0≤i≤L-N，第0组权重系数为权重系数的初始值；
    根据第i-1组权重系数、第i+N个第一时刻的通信状态以及第i+N个第一时刻的通信状态的预测值，确定第i组权重系数；
    将第L-N+1组权重系数，确定为与第1个第二时刻对应的权重系数。
  11. 根据权利要求8所述的装置，其特征在于，所述第一系数确定子模块，被配置为：
    对所述L个第一时刻的通信状态进行预处理，得到L个第一时刻的预处理后的通信状态，所述预处理包括归一化及差分处理；
    根据所述相干时窗长度N及L个第一时刻的预处理后的通信状态，确定与第1个第二时刻对应的差分权重系数；
    其中，所述第一预测子模块，被配置为：
    根据所述与第1个第二时刻对应的差分权重系数及第L-N+1个第一时刻至第L个第一时刻的预处理后的通信状态，确定所述第1个第二时刻的通信状态的差分预测值；
    对所述差分预测值进行后处理，得到所述第1个第二时刻的通信状态的预测值，所述后处理包括逆差分及反归一化处理。
  12. 根据权利要求7-11中任意一项所述的装置，其特征在于，所述第一工作模式及所述第二工作模式为主卡数据流量工作模式、副卡数据流量工作模式、Wi-Fi无线通信工作模式中任意一种。
  13. 一种工作模式调整装置，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为执行所述指令时实现权利要求1-6中任意一项所述的方法。
  14. 一种非易失性计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1-6中任意一项所述的方法。
  15. 一种计算机程序产品，包括计算机可读代码，或者承载有计算机可读代码的非易失性计算机可读存储介质，当所述计算机可读代码在电子设备中运行时，所述电子设备中的处理器执行权利要求1-6中任意一项所述的方法。
PCT/CN2022/083121 2021-04-16 2022-03-25 工作模式调整方法、装置及存储介质 WO2022218135A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110411188.9A CN115226168A (zh) 2021-04-16 2021-04-16 工作模式调整方法、装置及存储介质
CN202110411188.9 2021-04-16

Publications (1)

Publication Number Publication Date
WO2022218135A1 true WO2022218135A1 (zh) 2022-10-20

Family

ID=83604275

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/083121 WO2022218135A1 (zh) 2021-04-16 2022-03-25 工作模式调整方法、装置及存储介质

Country Status (2)

Country Link
CN (1) CN115226168A (zh)
WO (1) WO2022218135A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103618576A (zh) * 2013-08-29 2014-03-05 上海永畅信息科技有限公司 一种基于低复杂度建模的车联网多维信道感知系统
CN105308990A (zh) * 2013-02-19 2016-02-03 班德威斯康姆公司 用于通话切换的个性化用户会话信息
CN105578550A (zh) * 2014-11-03 2016-05-11 苹果公司 Wi-Fi自适应接收器分集和Wi-Fi自适应传送天线选择
CN109792374A (zh) * 2016-09-30 2019-05-21 索尼移动通讯有限公司 用于全双工传输的天线配置切换
CN109819476A (zh) * 2017-11-21 2019-05-28 腾讯科技（深圳）有限公司 一种网络优化方法及终端、存储介质
CN112004252A (zh) * 2020-08-11 2020-11-27 北京小米移动软件有限公司 终端的通信方法及装置、终端和存储介质
CN112384960A (zh) * 2018-07-19 2021-02-19 大众汽车股份公司 用于移动收发器的装置、方法和计算机程序

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10979906B2 (en) * 2017-04-11 2021-04-13 Qualcomm Incorporated Detecting media access control (MAC) address spoofing in a wi-fi network using channel correlation
US10567108B2 (en) * 2018-02-16 2020-02-18 At&T Intellectual Property I, L.P. Adaptive configuration of modulation and coding scheme tables for new radio

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105308990A (zh) * 2013-02-19 2016-02-03 班德威斯康姆公司 用于通话切换的个性化用户会话信息
CN103618576A (zh) * 2013-08-29 2014-03-05 上海永畅信息科技有限公司 一种基于低复杂度建模的车联网多维信道感知系统
CN105578550A (zh) * 2014-11-03 2016-05-11 苹果公司 Wi-Fi自适应接收器分集和Wi-Fi自适应传送天线选择
CN109792374A (zh) * 2016-09-30 2019-05-21 索尼移动通讯有限公司 用于全双工传输的天线配置切换
CN109819476A (zh) * 2017-11-21 2019-05-28 腾讯科技（深圳）有限公司 一种网络优化方法及终端、存储介质
CN112384960A (zh) * 2018-07-19 2021-02-19 大众汽车股份公司 用于移动收发器的装置、方法和计算机程序
CN112004252A (zh) * 2020-08-11 2020-11-27 北京小米移动软件有限公司 终端的通信方法及装置、终端和存储介质

Also Published As

Publication number Publication date
CN115226168A (zh) 2022-10-21

Similar Documents

Publication Publication Date Title
CN110176226B (zh) 一种语音识别、及语音识别模型训练方法及装置
US11812304B2 (en) Method and device for data allocation, mobile terminal, and storage medium
CN108990105B (zh) 无线通信传输方法、装置、移动终端及计算机可读取存储介质
US11044678B2 (en) Electronic device, method for transmitting message, and related products
US11722251B2 (en) Data transmission method and device
CN109890022B (zh) 数据传输控制方法、移动终端及计算机可读存储介质
WO2020143579A1 (zh) 链路聚合实现方法及相关产品
CN113645345A (zh) 数据发送方法、移动终端及存储介质
CN109314930B (zh) 用户设备中的传感器数据采集
CN113421211B (zh) 光斑虚化的方法、终端设备及存储介质
CN111970738B (zh) 一种网络切换控制方法、设备及计算机可读存储介质
WO2022218135A1 (zh) 工作模式调整方法、装置及存储介质
CN110069320B (zh) 一种应用程序的分类校正方法、终端、系统及存储介质
CN113316954A (zh) 指示方法、接收方法、装置、通信设备及存储介质
CN107743204B (zh) 曝光处理方法、终端及计算机可读存储介质
WO2022143724A1 (zh) 一种信道质量评估方法以及相关装置
CN114095960B (zh) 处理方法、通信设备及存储介质
CN112667339B (zh) 屏幕刷新率的设置方法、终端以及计算机可读介质
CN111277386B (zh) 下行分配索引确定方法、终端和网络设备
CN109460988B (zh) 一种扫码支付方法、设备及计算机可读存储介质
CN113473601A (zh) 一种资源选择方法及设备
CN112134627B (zh) 一种天线调谐方法、设备及计算机可读存储介质
CN116668999B (zh) 业务传输方法、装置、计算机设备、可读存储介质及产品
CN113938256B (zh) 基于对数似然比的pdcch候选盲检方法及相关产品
CN109685496B (zh) 一种图形支付隐私处理方法、设备及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22787364

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22787364

Country of ref document: EP

Kind code of ref document: A1