Dynamic adaptive communication optimization method and system, electronic equipment and product

Abstract

The invention belongs to the technical field of communication, and aims to provide a dynamic adaptive communication optimization method and system, electronic equipment and a product. The method comprises the following steps: initializing a protocol layer particle swarm and a physical layer particle swarm; collecting multi-source environment data in real time, and performing dynamic fitness evaluation on protocol layer particles in the protocol layer particle swarm and physical layer particles in the physical layer particle swarm based on the multi-source environment data to obtain a communication performance fitness value; performing joint optimization on the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value to obtain an optimal protocol layer particle and an optimal physical layer particle; and updating communication protocol layer parameters according to the optimal protocol layer particles, and adjusting communication physical layer parameters according to the optimal physical layer particles. According to the invention, joint adaptive adjustment of the communication parameters of the protocol layer and the physical layer in the active implantable medical device can be realized, the communication stability can be improved, and the energy consumption can be reduced.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of communication, and particularly relates to a dynamic adaptive communication optimization method, system, electronic device and product. BACKGROUND

[0002] With the wide application of active implantable medical devices (such as cardiac pacemakers, neurostimulators, orthopedic implants, etc.), the wireless communication capability plays a key role in postoperative monitoring, remote diagnosis and treatment, and precise intervention. However, in the process of using the prior art, the inventors found that at least the following problems exist in the prior art: Most of the existing implantable medical devices use fixed communication protocol parameters and physical layer radio frequency configurations, which are difficult to adapt to dynamic factors such as patient posture changes, tissue impedance changes, and electromagnetic environment interference, resulting in poor communication stability, high bit error rate, high power consumption, and even the risk of communication interruption. This static configuration method seriously limits the long-term stable operation of the implanted device and affects the real-time and integrity of the diagnosis and treatment data.

[0003] In the prior art, a Chinese patent with publication number CN114448112A discloses an implantable medical device wireless charging optimal power self-finding system, which finds the optimal transmission path through optimal power, and a power adaptive processing unit dynamically calculates the index parameters during charging, adaptively adjusts the duty cycle of the wireless charging drive signal, and adjusts the transmission power to ensure the charging efficiency while reducing the eddy current heat temperature rise. However, this prior art is limited to single-layer optimization (only adjusting the transmission power), and fails to realize the coordinated linkage between the protocol layer and the physical layer, lacking a global communication performance optimization strategy in a dynamic environment. SUMMARY

[0004] The present application aims to at least partially solve the above technical problems, and provides a dynamic adaptive communication optimization method, system, electronic device and product.

[0005] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides a dynamic adaptive communication optimization method applied to an active implantable medical device, the method comprising: initializing a protocol layer particle swarm and a physical layer particle swarm; wherein the protocol layer particle swarm comprises a plurality of protocol layer particles, and the physical layer particle swarm comprises a plurality of physical layer particles; real-time collection of multi-source environment data, and dynamic fitness evaluation of the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm based on the multi-source environment data, to obtain a communication performance fitness value; jointly optimizing the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value, to obtain an optimal protocol layer particle and an optimal physical layer particle; updating a communication protocol layer parameter according to the optimal protocol layer particle, and adjusting a communication physical layer parameter according to the optimal physical layer particle, to realize adaptive optimization of the communication performance of the active implantable medical device.

[0006] In one possible design, the protocol layer particle in the protocol layer particle swarm is encoded to include [master-slave switching period, channel mask], and is dynamically loaded by a lookup table method; and the physical layer particle in the physical layer particle swarm is encoded to include [transmit power value, antenna phase angle], where the transmit power value is between -20 dBm and +10 dBm, with a step size of 0.5 dBm, and the antenna phase angle is a discrete angle between 0° and 360°, with a step size of 5°.

[0007] In one possible design, after real-time collection of multi-source environment data, the method further includes: sequentially performing filtering processing, timestamp alignment processing, and normalization processing on the multi-source environment data, to obtain preprocessed multi-source environment data, so as to perform dynamic fitness evaluation on the protocol layer particle in the protocol layer particle swarm and the physical layer particle in the physical layer particle swarm based on the preprocessed multi-source environment data, to obtain a communication performance fitness value.

[0008] In one possible design, the multi-source environment data includes gyroscope data, temperature data, battery power, and bit error rate; and correspondingly, the dynamic fitness evaluation on the protocol layer particle in the protocol layer particle swarm and the physical layer particle in the physical layer particle swarm based on the multi-source environment data, to obtain a communication performance fitness value, includes: inputting the multi-source environment data into a preset communication index fitness function, to obtain a communication performance fitness value; where the communication index fitness function is: Fitness=Throughput / (1+BER)-λ*(P+Δθ)+μ*e -Tsurface ; where Fitness represents the communication performance fitness value; Throughput represents a data throughput when the multi-source environment data is collected; BER represents the bit error rate; P represents a physical layer radio frequency front-end power consumption calculated according to the battery power; Δθ represents a deviation of an actual antenna direction from an optimal angle calculated by using the gyroscope data; T surface represents the temperature data; e represents a natural constant; λ represents a power dynamic penalty factor corresponding to the battery power; and μ represents a temperature change dynamic penalty factor corresponding to the temperature data.

[0009] In one possible design, in the communication performance fitness function, both the power dynamic penalty factor and the temperature change dynamic penalty factor employ a dynamic weight factor; wherein the power dynamic penalty factor is automatically adjusted based on the battery power, and when the battery power is higher than 20%, the power dynamic penalty factor is: λ = λ max (1 - B / B max ); wherein λ max represents a preset maximum power penalty factor, B represents the battery power, and B max represents a preset maximum remaining battery power. When the battery power is lower than 20%, the power dynamic penalty factor is λ = 0.8. The temperature change dynamic penalty factor is automatically adjusted based on the temperature data, and the temperature change dynamic penalty factor is: μ = μ' * (T surface / T threshold ); wherein μ' represents a preset temperature penalty factor, T surface represents the temperature data, and T threshold represents a preset device threshold temperature.

[0010] In one possible design, the protocol layer particle swarm and the physical layer particle swarm are jointly optimized based on the communication performance fitness value to obtain an optimal protocol layer particle and an optimal physical layer particle, including: The protocol layer particles in the protocol layer particle swarm and the protocol layer particles in the physical layer particle swarm are iteratively updated, and then the communication performance fitness values corresponding to the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm are recalculated; When a preset iteration termination condition is reached, the protocol layer particle and the physical layer particle with the maximum communication performance fitness value are taken as the optimal protocol layer particle and the optimal physical layer particle.

[0011] In one possible design, after the communication protocol layer parameters are updated according to the optimal protocol layer particle, the method further includes: obtaining a data throughput, an error code rate, and a connection stability during data communication, and performing communication quality evaluation according to the data throughput, the error code rate, and the connection stability to obtain a communication quality evaluation result; wherein the communication quality evaluation result is: Q = α × Throughput' - β × BER' × 100 - γ × Disconnect_Count In the formula, Throughput' represents the data throughput during data communication, BER' represents the bit error rate during data communication, Disconnect_Count represents the connection stability during data communication, and alpha, beta and gamma are weight coefficients of the data throughput, the bit error rate and the connection stability, respectively.

[0012] In a second aspect, the present application provides a dynamic adaptive communication optimization system for implementing the dynamic adaptive communication optimization method according to any one of the preceding aspects; the dynamic adaptive communication optimization system comprises: a population initialization module configured to initialize a protocol layer particle swarm and a physical layer particle swarm; wherein the protocol layer particle swarm comprises a plurality of protocol layer particles, and the physical layer particle swarm comprises a plurality of physical layer particles; an adaptability evaluation module in communication connection with the population initialization module and configured to collect multi-source environment data in real time, and perform dynamic adaptability evaluation on the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm based on the multi-source environment data, to obtain a communication performance adaptability value; a population optimization module in communication connection with the adaptability evaluation module and configured to perform joint optimization on the protocol layer particle swarm and the physical layer particle swarm based on the communication performance adaptability value, to obtain an optimal protocol layer particle and an optimal physical layer particle; a communication optimization module in communication connection with the population optimization module and configured to update a communication protocol layer parameter according to the optimal protocol layer particle, and adjust a communication physical layer parameter according to the optimal physical layer particle, to realize adaptive optimization of the communication performance of the active implantable medical device.

[0013] In a third aspect, the present application provides an electronic device comprising: a memory configured to store computer program instructions; and a processor configured to execute the computer program instructions to complete the operations of the dynamic adaptive communication optimization method according to any one of the preceding aspects.

[0014] In a fourth aspect, the present application provides a computer program product comprising computer programs or instructions, which, when executed by a computer, implement the dynamic adaptive communication optimization method according to any one of the preceding aspects.

[0015] The present application has the following beneficial effects: The application discloses a dynamic adaptive communication optimization method and system, an electronic device and a product, can realize joint adaptive adjustment of protocol layer and physical layer communication parameters in active implantable medical devices, can improve communication stability, and can reduce energy consumption. Specifically, the application introduces a protocol layer particle swarm and a physical layer particle swarm modeling method, combines multi-source environmental data collected by a multi-source sensor in real time, obtains a communication performance fitness value of a particle combination composed of protocol layer particles and physical layer particles, and performs cross-layer joint iterative optimization on the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value, can dynamically adjust Bluetooth communication protocol parameters and radio frequency hardware configuration according to an actual communication environment, realizes adaptive optimization control of active implantable medical device communication, can significantly improve communication robustness, reduce bit error rate and power consumption, and is suitable for active implantable medical devices.

[0016] Other benefits of the application will be further described in the specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a flowchart of a dynamic adaptive communication optimization method in an embodiment; Figure 2 is a module block diagram of a dynamic adaptive communication optimization system in an embodiment; Figure 3 is a module block diagram of an electronic device in an embodiment. DETAILED DESCRIPTION

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the present application will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the drawings is only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor. It should be noted that the description of these embodiments is used to help understand the present application, but does not constitute a limitation on the present application.

[0019] Embodiment 1: This embodiment discloses a dynamic adaptive communication optimization method, which can be executed by a computer device or a virtual machine with certain computing resources, such as an electronic device such as a personal computer, a smart phone, a personal digital assistant or a wearable device, or a virtual machine.

[0020] As shown in Figure 1 A dynamic adaptive communication optimization method applied to active implantable medical devices, the method can include but is not limited to the following steps: S1. initializing a protocol layer particle swarm and a physical layer particle swarm; wherein the protocol layer particle swarm comprises a plurality of protocol layer particles, and the physical layer particle swarm comprises a plurality of physical layer particles.

[0021] In step S1, the protocol layer particle swarm and the physical layer particle swarm are initialized, including: constructing a plurality of protocol layer particles in the form of encoding vectors for the protocol layer, each of which represents a group of testable communication protocol configuration schemes for optimizing Bluetooth communication protocol parameters, such as master-slave switching period and channel mask selection; and constructing a plurality of physical layer particles in the form of encoding vectors for the physical layer, each of which represents a group of testable radio frequency hardware configuration schemes for optimizing physical layer parameters such as transmission power value and antenna phase angle.

[0022] In this embodiment, the protocol layer particle encoding in the protocol layer particle swarm includes: [master-slave switching period, channel mask], and is dynamically loaded by table lookup method. Specifically, the table lookup method is dynamically selected by a built-in data table, and different use scenarios are used, such as in a medical scenario, the switching period can be optimized and shortened to 50 ms to meet real-time requirements; the physical layer particle encoding in the physical layer particle swarm includes: [transmission power value, antenna phase angle], wherein: the transmission power value is between -20 dBm and +10 dBm, with a step of 0.5 dBm, and the antenna phase angle is a discrete angle between 0° and 360°, with a step of 5°.

[0023] Specifically, in this embodiment, the protocol layer particles in the protocol layer particle swarm are set as the following two-dimensional vectors: P1=[role_switch_interval, channel_mask]; Wherein, role_switch_interval represents the master-slave switching period, and channel_mask represents the channel mask. As an example, a certain protocol layer particle is: [150, 0b101], which represents that the master-slave switching period is 150 seconds, and the shielded channel 38 (the channel mask 0b101 corresponds to the available channels 37 / 39).

[0024] The physical layer particles in the physical layer particle swarm are set as the following two-dimensional vectors: P2=[tx_power, phase_angle]; Wherein, tx_power represents the transmission power value, and phase_angle represents the antenna phase angle.

[0025] As an example, a certain physical layer particle is: [8.5, 225], which represents that the transmission power value is 8.5 dBm, and the antenna phase angle is 225°.

[0026] S2. Real-time acquisition of multi-source environment data, and dynamic fitness evaluation of the protocol layer particles in the protocol layer particle group and the physical layer particles in the physical layer particle group based on the multi-source environment data, to obtain a communication performance fitness value.

[0027] In step S2, after real-time acquisition of multi-source environment data, the method further comprises: The multi-source environment data is sequentially subjected to filtering processing, timestamp alignment processing and normalization processing to obtain preprocessed multi-source environment data, so as to perform dynamic fitness evaluation of the protocol layer particles in the protocol layer particle group and the physical layer particles in the physical layer particle group based on the preprocessed multi-source environment data, to obtain a communication performance fitness value. Specifically, in this embodiment, the multi-source environment data is sequentially subjected to filtering processing, timestamp alignment processing and normalization processing, and then preprocessed multi-source environment data is obtained; when the data is subjected to timestamp alignment processing, the temperature data corresponding to the temperature rise data is taken as a reference to interpolate and compensate other sensor data, so that the time deviation of each sensor data is <1ms, and the normalization processing is used to map each data to the [0-1] interval, facilitating subsequent fitness calculation.

[0028] In this embodiment, DMA (Direct Memory Access) transmission is used to avoid CPU (Central Processing Unit) blocking in the data acquisition process, aiming at the CPU blocking problem that is prone to occur in the multi-sensor transmission in the multi-source environment data transmission process.

[0029] It should be understood that, in a communication environment corresponding to a particle combination composed of protocol layer particles and physical layer particles, the communication performance fitness value of the particle combination can be calculated by acquiring multi-source environment data. Based on this, in this embodiment, the individuals in the protocol layer particle group and the physical layer particle group can be iteratively updated to obtain the communication performance fitness values of multiple particle combinations, and finally the optimal protocol layer particle and the optimal physical layer particle that satisfy the maximum communication performance fitness value condition are obtained.

[0030] In step S2, the multi-source environmental data includes gyroscope data, temperature data, battery power, and bit error rate. Specifically, in this embodiment, the gyroscope data is obtained by acquiring three-dimensional angular velocity at a frequency of 1kHz using an MPU-6050 six-axis sensor, and the antenna pointing deviation angle Δθ (accuracy ±0.5°) is calculated using Kalman filtering. The temperature data can be obtained based on an NTC thermistor, for example, by detecting the voltage data on both sides of the resistor every 100ms, and indirectly detecting the surface temperature rise T of the device (resolution ±0.1℃) through the correspondence between the reference voltage and temperature. The battery power is detected using the battery internal resistance measurement method, that is, during the operation of the device, the battery internal resistance is calculated by using a short-circuit small current; if the internal resistance increases, the battery power decreases. The bit error rate data is obtained by statistically analyzing the BER (Bit Error Ratio) of each frame of data based on CRC (Cyclic Redundancy Check) verification, with a sampling window of 10ms.

[0031] Correspondingly, in step S2, dynamic fitness evaluation is performed on the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm based on the multi-source environmental data to obtain communication performance fitness values, including: The multi-source environmental data is input into a preset communication index fitness function to obtain a communication performance fitness value; wherein, the communication index fitness function is: Fitness=Throughput / (1+BER)-λ*(P+Δθ)+μ*e -Tsurface ; In the formula, Fitness represents the communication performance fitness value; Throughput represents the data throughput when collecting data from multiple sources, that is, the amount of effective data successfully transmitted per unit time (unit: bps), used to reflect the transmission efficiency of the protocol layer; BER represents the bit error rate, which is the ratio of the number of erroneous bits at the receiving end to the total number of transmitted bits, used to measure the signal quality of the physical layer; P represents the power consumption of the physical layer RF front end calculated based on the battery power (unit: mW), this parameter directly affects the device's battery life. Specifically, in this embodiment, after obtaining the battery power, power consumption is estimated by looking up the built-in data relationship table (this method is more dependent on the battery model and requires calibration of the data table based on the battery model); Δθ represents the deviation between the actual antenna direction and the optimal angle calculated from the gyroscope data (unit: degrees), this parameter is used to reflect hardware calibration error; T surfacerepresents the temperature data, which is the surface temperature of the implanted medical device monitored by the infrared sensor; e represents a natural constant; λ represents a battery power dynamic penalty factor corresponding to the battery power; μ represents a temperature change dynamic penalty factor corresponding to the temperature data.

[0032] In the communication performance fitness function, the battery power dynamic penalty factor and the temperature change dynamic penalty factor both adopt a dynamic weight factor and are adjusted by a dynamic weight factor adjustment strategy; wherein the battery power dynamic penalty factor is automatically adjusted based on the battery power, and when the battery power is higher than 20%, the battery power dynamic penalty factor is: λ=λ max (1-B / B max ); In the formula, λ max represents a preset battery power maximum penalty factor, B represents the battery power, that is, the battery remaining power, and B max represents a preset maximum battery remaining power; When the battery power is lower than 20%, the battery power dynamic penalty factor is λ=0.8; based on this, the algorithm can be forced to prioritize energy saving when the battery power is lower than 20%.

[0033] The temperature change dynamic penalty factor is automatically adjusted based on the temperature data, and the temperature change dynamic penalty factor is: μ=μ’*(T surface / T threshold ); μ’ represents a preset temperature penalty factor, T surface represents the temperature data, and T threshold represents a preset device threshold temperature.

[0034] S3. Based on the communication performance fitness value, the protocol layer particle swarm and the physical layer particle swarm are jointly optimized to obtain the optimal protocol layer particle and the optimal physical layer particle.

[0035] In step S3, based on the communication performance fitness value, the protocol layer particle swarm and the physical layer particle swarm are jointly optimized to obtain the optimal protocol layer particle and the optimal physical layer particle, including: S301. The protocol layer particles in the protocol layer particle swarm and the protocol layer particles in the physical layer particle swarm are iteratively updated, and then the communication performance fitness values corresponding to the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm are recalculated; S302. When a preset iteration termination condition is reached, the protocol layer particle and the physical layer particle with the maximum communication performance fitness value are taken as the optimal protocol layer particle and the optimal physical layer particle.

[0036] Specifically, when there is a communication performance fitness value corresponding to a particle combination of a protocol layer particle and a physical layer particle is greater than a preset threshold or the number of iterations reaches a maximum number of iterations, the protocol layer particle and the physical layer particle with the maximum communication performance fitness value are taken as the optimal protocol layer particle and the optimal physical layer particle.

[0037] In this embodiment, the protocol layer particle group is updated by a general particle group updating algorithm, which is not limited here.

[0038] For the physical layer particle group, the embodiment introduces a hybrid updating rule: for continuous parameters (transmit power values), a standard particle swarm algorithm is used for updating; and for discrete parameters (antenna phase angles), a probability mapping updating is used.

[0039] S4. updating the communication protocol layer parameters according to the optimal protocol layer particle to drive the dynamic adjustment of the communication protocol layer, and adjusting the communication physical layer parameters according to the optimal physical layer particle to realize the adaptive optimization of the communication performance of the active implantable medical device.

[0040] It should be noted that the optimal protocol layer particle provides a reliable wireless communication adaptive framework for the implantable device, and the optimal physical layer particle realizes dynamic radio frequency tuning in the mode of "power-phase hybrid coding" and "hardware delay compensation", which provides a reliable physical layer adaptive framework for the implantable medical device, and finally realizes the adjustment in both the protocol layer and the physical layer. Specifically, for the Bluetooth protocol stack interface, the optimized master-slave cycle and channel mask configuration information can be obtained, and the HCI (Host Controller Interface) instruction is used to dynamically modify the connection interval (example instruction: hci_le_set_connection_interval (cycle value)); the frequency hopping sequence is updated, and the Bluetooth controller register is written to shield the interference channel (example instruction: ll_set_channel_map (mask value)); for antenna communication, the optimized transmit power and antenna phase angle optimal solution can be obtained, and the phase weight tuning and power level adjustment are performed (the phase angle is controlled through SPI; the radio frequency power is output through digital-to-analog conversion), which strictly controls the device surface heating and electromagnetic radiation caused by device operation while ensuring the function, and ensures the long-term safety of the active implantable medical device.

[0041] After updating the communication protocol layer parameters according to the optimal protocol layer particle, the method further comprises: S5. obtaining data throughput, bit error rate and connection stability during data communication, and performing communication quality evaluation according to the data throughput, the bit error rate and the connection stability to obtain a communication quality evaluation result; wherein the communication quality evaluation result is: Q = a x Throughput' - b x BER' x 100 - g x Disconnect_Count In the formula, Throughput' represents the data throughput during data communication, BER' represents the bit error rate during data communication, Disconnect_Count represents the connection stability during data communication, in the embodiment, the connection stability is measured by the number of connection interruptions per unit time, a, b and g are weight coefficients of the data throughput, the bit error rate and the connection stability, specifically, in the embodiment, a = 60%, b = 30%, g = 10%.

[0042] The embodiment can realize joint adaptive adjustment of protocol layer and physical layer communication parameters in active implantable medical devices, improve communication stability, and reduce energy consumption. Specifically, the embodiment introduces a protocol layer particle swarm and a physical layer particle swarm modeling method, combines multi-source environmental data collected by multi-source sensors in real time, obtains a communication performance fitness value of a particle combination composed of protocol layer particles and physical layer particles, and performs cross-layer joint iterative optimization on the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value, which can dynamically adjust Bluetooth communication protocol parameters and radio frequency hardware configuration according to the actual communication environment, realize adaptive optimization control of active implantable medical device communication, significantly improve communication robustness, reduce bit error rate and power consumption, and be suitable for active implantable medical devices.

[0043] Embodiment 2: The embodiment discloses a dynamic adaptive communication optimization system for realizing the dynamic adaptive communication optimization method in embodiment 1; as shown in Figure 2 The dynamic adaptive communication optimization system comprises: A population initialization module is configured to initialize a protocol layer particle swarm and a physical layer particle swarm; wherein the protocol layer particle swarm comprises a plurality of protocol layer particles, and the physical layer particle swarm comprises a plurality of physical layer particles; An adaptability evaluation module is in communication connection with the population initialization module and is configured to collect multi-source environmental data in real time, and perform dynamic adaptability evaluation on protocol layer particles in the protocol layer particle swarm and physical layer particles in the physical layer particle swarm based on the multi-source environmental data to obtain a communication performance fitness value; The population optimization module is connected in communication with the fitness evaluation module, and is configured to jointly optimize the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value, to obtain an optimal protocol layer particle and an optimal physical layer particle. The communication optimization module is connected in communication with the population optimization module, and is configured to update a communication protocol layer parameter according to the optimal protocol layer particle, and adjust a communication physical layer parameter according to the optimal physical layer particle, to realize adaptive optimization of the communication performance of the active implantable medical instrument.

[0044] It should be noted that the working process, working details and technical effects of the dynamic adaptive communication optimization system provided in Embodiment 2 can be referred to Embodiment 1, and will not be repeated here.

[0045] Embodiment 3 On the basis of Embodiment 1 or 2, the present embodiment discloses an electronic device, which can be a smartphone, a tablet computer, a notebook computer or a desktop computer, etc. The electronic device can be referred to as a user terminal, a portable terminal, a desktop terminal, etc., as shown in Figure 3 The electronic device includes: a memory configured to store computer program instructions; and a processor configured to execute the computer program instructions to complete the operations of the dynamic adaptive communication optimization method according to any one of Embodiments 1.

[0046] Specifically, the processor 301 can include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), a FPGA (Field-Programmable Gate Array), a PLA (Programmable Logic Array). The processor 301 can also include a main processor and a coprocessor, the main processor is a processor for processing data in the wake-up state, also known as CPU (Central Processing Unit), the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 can be integrated with a GPU (Graphics Processing Unit) for rendering and drawing the content required to be displayed by the display screen.

[0047] The memory 302 can include one or more computer-readable storage media. The computer-readable storage media can be non-transitory. The memory 302 can also include high-speed random access memory and nonvolatile, computer-readable storage media such as one or more magnetic disk storage devices, optical storage devices, flash memory devices, solid-state storage devices, or other computer-readable storage media including non-transitory computer-readable storage media. In some embodiments, the non-transitory computer-readable storage media of the memory 302 is used to store at least one instruction for execution by the processor 301 to implement the dynamic adaptive communication optimization method provided in Embodiment 1.

[0048] In some embodiments, the terminal can further optionally include a communication interface 303 and at least one peripheral device. The processor 301, the memory 302, and the communication interface 303 can be connected through a bus or a signal line. Each peripheral device can be connected to the communication interface 303 through a bus, a signal line, or a circuit board. Specifically, the peripheral device includes at least one of a radio frequency circuit 304, a display screen 305, and a power supply 306.

[0049] The communication interface 303 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 can be implemented on a separate chip or circuit board, and the present embodiment does not limit this.

[0050] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with a communication network and other communication devices through electromagnetic signals.

[0051] The display screen 305 is used to display a UI (User Interface). The UI can include any combination of graphics, text, icons, and video.

[0052] The power supply 306 is used to supply power to various components in the electronic device.

[0053] Embodiment 4 On the basis of any one of Embodiments 1 to 3, the present embodiment discloses a computer program product including a computer program or instructions, which, when executed by a computer, implement a dynamic adaptive communication optimization method as described in any one of Embodiment 1. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0054] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be realized by universal computing devices, which can be centralized on a single computing device or distributed on a network composed of multiple computing devices, and optionally, they can be realized by program codes executable by the computing devices, so that they can be stored in storage devices and executed by the computing devices, or they can be respectively manufactured into individual integrated circuit modules, or multiple modules or steps among them can be manufactured into a single integrated circuit module to realize. Thus, the present application is not limited to any specific combination of hardware and software.

[0055] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features therein can be replaced by equivalents. Such modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of dynamic adaptive communication optimization, the method comprising: The method is applied to an active implantable medical device, and the method comprises: initializing a protocol layer particle swarm and a physical layer particle swarm; wherein the protocol layer particle swarm comprises a plurality of protocol layer particles, and the physical layer particle swarm comprises a plurality of physical layer particles; collecting multi-source environment data in real time, and performing dynamic fitness evaluation on the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm based on the multi-source environment data to obtain a communication performance fitness value; jointly optimizing the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value to obtain optimal protocol layer particles and optimal physical layer particles; updating a communication protocol layer parameter according to the optimal protocol layer particles, and adjusting a communication physical layer parameter according to the optimal physical layer particles, so as to realize adaptive optimization of the communication performance of the active implantable medical device.

2. The method of claim 1, wherein, The protocol layer particle swarm comprises protocol layer particles encoded as [master-slave switching period, channel mask], which are dynamically loaded by a lookup table method; the physical layer particle swarm comprises physical layer particles encoded as [transmit power value, antenna phase angle], wherein the transmit power value is between -20 dBm and +10 dBm with a step size of 0.5 dBm, and the antenna phase angle is a discrete angle between 0° and 360° with a step size of 5°.

3. The method of claim 1, wherein, After collecting the multi-source environment data in real time, the method further comprises: sequentially performing filtering processing, timestamp alignment processing and normalization processing on the multi-source environment data to obtain preprocessed multi-source environment data, so as to perform dynamic fitness evaluation on the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm based on the preprocessed multi-source environment data to obtain a communication performance fitness value.

4. The method of claim 1, wherein, The multi-source environment data comprises gyroscope data, temperature data, battery power and bit error rate; correspondingly, performing dynamic fitness evaluation on the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm based on the multi-source environment data to obtain a communication performance fitness value comprises: inputting the multi-source environment data into a preset communication index fitness function to obtain a communication performance fitness value; wherein the communication index fitness function is: Fitness = Throughput / (1 + BER) - λ * (P + Δθ) + μ * e -Tsurface ; In the formula, Fitness represents the communication performance fitness value; Throughput represents the data throughput when multi-source environment data collection is performed; BER represents the bit error rate; P represents the physical layer radio frequency front end power consumption calculated according to the battery power; Δθ represents the deviation of the actual antenna direction from the optimal angle calculated through the gyroscope data; T surface represents the temperature data; e represents a natural constant; λ represents a power dynamic penalty factor corresponding to the battery power; and μ represents a temperature change dynamic penalty factor corresponding to the temperature data.

5. The method of claim 4, wherein, In the communication index fitness function, the power dynamic penalty factor and the temperature change dynamic penalty factor both adopt a dynamic weight factor; wherein the power dynamic penalty factor is automatically adjusted based on the battery power to obtain a value, when the battery power is higher than 20%, the power dynamic penalty factor is: λ = λ max (1 - B / B max ); In the formula, λ max represents a preset maximum penalty factor of the electric quantity, B represents the battery electric quantity, B max represents a preset maximum remaining electric quantity of the battery; when the battery power is lower than 20%, the power dynamic penalty factor is λ=0.8; the temperature change dynamic penalty factor is automatically adjusted based on the temperature data to obtain a value, and the temperature change dynamic penalty factor is: μ = μ' * (T surface / T threshold ); μ' denotes a preset temperature penalty factor, T surface denotes the temperature data, T threshold denotes a preset device threshold temperature.

6. The method of claim 4 or 5, wherein, jointly optimizing the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value to obtain optimal protocol layer particles and optimal physical layer particles comprises: updating the protocol layer particles in the protocol layer particle swarm and the protocol layer particles in the physical layer particle swarm iteratively, and then recalculating the communication performance fitness values corresponding to the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm; when a preset iteration termination condition is reached, taking the protocol layer particle and the physical layer particle with the maximum communication performance fitness value as the optimal protocol layer particle and the optimal physical layer particle.

7. The method of claim 1, wherein, After updating the communication protocol layer parameters according to the optimal protocol layer particle, the method further comprises: obtaining the data throughput, the error code rate and the connection stability during data communication, and performing communication quality evaluation according to the data throughput, the error code rate and the connection stability to obtain a communication quality evaluation result; wherein the communication quality evaluation result is: Q = α × Throughput' - β × BER' × 100 - γ × Disconnect_Count In the formula, Throughput' represents the data throughput during data communication, BER' represents the error code rate during data communication, Disconnect_Count represents the connection stability during data communication, and α, β and γ are weight coefficients of the data throughput, the error code rate and the connection stability, respectively.

8. A dynamic adaptive communication optimization system, characterized by, The dynamic adaptive communication optimization system comprises: a population initialization module for initializing a protocol layer particle swarm and a physical layer particle swarm; wherein the protocol layer particle swarm comprises a plurality of protocol layer particles, and the physical layer particle swarm comprises a plurality of physical layer particles; a fitness evaluation module in communication connection with the population initialization module, for collecting multi-source environmental data in real time, and performing dynamic fitness evaluation on the protocol layer particles in the protocol layer particle swarm and the physical layer particles in the physical layer particle swarm based on the multi-source environmental data to obtain a communication performance fitness value; a population optimization module in communication connection with the fitness evaluation module, for jointly optimizing the protocol layer particle swarm and the physical layer particle swarm based on the communication performance fitness value to obtain an optimal protocol layer particle and an optimal physical layer particle; a communication optimization module in communication connection with the population optimization module, for updating communication protocol layer parameters according to the optimal protocol layer particle, and adjusting communication physical layer parameters according to the optimal physical layer particle, so as to realize adaptive optimization of the communication performance of the active implantable medical device.

9. An electronic device, comprising: comprise: a memory for storing computer program instructions; and a processor for executing the computer program instructions to complete the operations of the dynamic adaptive communication optimization method according to any one of claims 1 to 7.

10. A computer program product comprising computer programs or instructions, characterized in that, The computer program or the instructions realize the dynamic adaptive communication optimization method according to any one of claims 1 to 7 when executed by a computer. The computer program or the instructions realize the dynamic adaptive communication optimization method according to any one of claims 1 to 7 when executed by a computer.

Images