Wireless communication data processing method for vehicle-mounted refrigerator in complex environment

Abstract

The invention discloses a wireless communication data processing method for a vehicle-mounted refrigerator in a complex environment, and relates to the field of communication data process.The method comprises the steps that instruction complexity is obtained; acquiring a plurality of communication influence parameters of the vehicle-mounted communication environment in real time, performing fitness evaluation analysis based on the plurality of communication influence parameters and the instruction complexity, and calculating the current communication fitness; obtaining a preset fitness threshold, and determining a communication interference coefficient based on the preset fitness threshold and the current communication fitness; acquiring a basic transmission power and a basic transmission rate based on the plurality of communication influence parameters, and correcting the basic transmission power and the basic transmission rate according to the communication interference coefficient to obtain a corrected transmission power and a corrected transmission rate; and performing wireless communication control on the vehicle-mounted refrigerator according to the corrected transmission power and the corrected transmission rate. The problems that in the prior art, the command transmission failure rate of vehicle-mounted refrigerator communication transmission is high, response is delayed, and the reliability of vehicle-mounted refrigerator communication transmission control is not high are solved.

Description

Technical Field

[0001] This invention relates to the field of communication data processing, and more specifically to a wireless communication data processing method for a vehicle-mounted refrigerator in a complex environment. Background Technology

[0002] In everyday driving scenarios, the vehicle's infotainment system needs to generate control commands in real time, such as pre-cooling start, temperature adjustment, and operating mode switching for the refrigerator, based on information such as external ambient temperature, driving plan, and user preferences.

[0003] Because electric vehicles contain multiple interference sources such as motor controllers, high-voltage battery systems, and on-board electrical equipment, traditional fixed-parameter wireless communication methods are difficult to adapt to dynamic changes in interference, leading to problems such as command transmission failure and response delay. This seriously affects the reliability of communication transmission and control of the on-board refrigerator and the intelligent control effect of the refrigerator. Summary of the Invention

[0004] This application provides a wireless communication data processing method for vehicle-mounted refrigerators in complex environments, addressing the problems of high command transmission failure rate, response delay, and low reliability of communication transmission control in vehicle-mounted refrigerators in the prior art.

[0005] In view of the above problems, this application provides a wireless communication data processing method for a vehicle-mounted refrigerator in a complex environment, the method comprising: Receive vehicle refrigerator control commands generated by the vehicle intelligent system, perform command feature analysis on the vehicle refrigerator control commands, and obtain command complexity; Multiple communication impact parameters of the vehicle communication environment are collected in real time. Based on the multiple communication impact parameters and the instruction complexity, a fitness evaluation analysis is performed to calculate the current communication fitness. Obtain a preset fitness threshold, and determine a communication interference coefficient based on the preset fitness threshold and the current communication fitness; The basic transmission power and basic transmission rate are obtained based on the multiple communication influence parameters, and the basic transmission power and basic transmission rate are corrected according to the communication interference coefficient to obtain the corrected transmission power and corrected transmission rate. The vehicle-mounted refrigerator is wirelessly controlled according to the corrected transmission power and corrected transmission rate.

[0006] Optionally, the control commands for the vehicle-mounted refrigerator are subjected to command feature analysis to obtain command complexity, including: Retrieve a pre-trained instruction analyzer, which includes a real-time analysis branch, a reliability analysis branch, and a data volume analysis branch; The vehicle refrigerator control command is input into the command analyzer, and the real-time demand coefficient is obtained through the real-time analysis branch, the reliability demand coefficient is obtained through the reliability analysis branch, and the data volume load coefficient is obtained through the data volume analysis branch. The instruction complexity of the vehicle refrigerator control command is obtained by weighting the real-time requirement coefficient, the reliability requirement coefficient, and the data load coefficient.

[0007] Optionally, the construction steps of the instruction analyzer include: Collect historical vehicle refrigerator control command records, which include multiple historical vehicle refrigerator control commands, and construct a sample vehicle refrigerator control command set; Real-time requirement annotation and reliability requirement annotation are performed on each sample vehicle refrigerator control command in the sample vehicle refrigerator control command set to construct a sample real-time requirement coefficient set and a sample reliability requirement coefficient set. Construct a real-time analysis branch architecture and a reliability analysis branch architecture; The real-time analysis branch architecture is trained using the sample vehicle refrigerator control instruction set and the sample real-time demand coefficient set to obtain the real-time analysis branch; The reliability analysis branch architecture is trained using the sample vehicle refrigerator control instruction set and the sample reliability requirement coefficient set to obtain the reliability analysis branch; A data volume analysis branch is constructed, which obtains the data volume load coefficient by directly calculating the data length of the vehicle refrigerator control command. The real-time analysis branch, the reliability analysis branch, and the data volume analysis branch are integrated to construct the instruction analyzer.

[0008] Optionally, multiple communication impact parameters of the vehicle communication environment are collected in real time, and a fitness evaluation analysis is performed based on the multiple communication impact parameters and the instruction complexity to calculate the current communication fitness, including: Multiple communication impact parameters of the vehicle communication environment are collected in real time, including motor interference intensity, vehicle electrical interference power, and frequency band occupancy rate. The multiple communication impact parameters are vectorized to construct a communication impact parameter vector; The communication impact parameter vector is input into a pre-trained communication bearer estimator to obtain the communication bearer degree; Based on the communication capacity and instruction complexity, a fitness evaluation analysis is performed to calculate the current communication fitness.

[0009] Optionally, the construction steps of the communication bearer evaluator include: Under the conditions of basic transmission power and basic transmission rate, multiple historical communication impact parameters of different historical vehicle communication environments are collected, a vector of historical communication impact parameters is constructed, and a sample communication impact parameter vector set is formed. For each sample communication influence parameter vector in the sample communication influence parameter vector set, corresponding to the historical environmental conditions, the highest instruction complexity successfully transmitted under the historical environmental conditions is statistically analyzed, and the highest instruction complexity is used as the communication carrying capacity label value. Construct a sample communication carrying capacity set based on the aforementioned communication carrying capacity label values; The communication carrying capacity evaluator is trained and generated using the sample communication influence parameter vector set as the input vector and the sample communication carrying capacity set as the label.

[0010] Optionally, a fitness evaluation analysis is performed based on the communication capacity and the instruction complexity to calculate the current communication fitness, including: Compare the communication capacity with the instruction complexity; When the communication capacity is greater than or equal to the instruction complexity, the current communication fitness is set to 1; When the communication capacity is less than the instruction complexity, the ratio of the communication capacity to the instruction complexity is calculated, and the ratio is used as the current communication fitness.

[0011] Optionally, obtaining a preset fitness threshold and determining a communication interference coefficient based on the preset fitness threshold and the current communication fitness includes: Obtain a preset fitness threshold, wherein the preset fitness threshold is 1; Calculate the difference between the preset fitness threshold and the current communication fitness, and use the difference as the communication interference coefficient.

[0012] Optionally, the basic transmission power and basic transmission rate are obtained based on the plurality of communication impact parameters, and the basic transmission power and basic transmission rate are corrected according to the communication interference coefficient to obtain the corrected transmission power and corrected transmission rate, including: Obtain the preset base transmission power and base transmission rate; Calculate the sum of 1 and the communication interference coefficient to obtain the correction coefficient; Multiply the base transmission power by the correction factor to obtain the corrected transmission power; Divide the base transmission rate by the correction factor to obtain the corrected transmission rate.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application first obtains the command complexity by receiving and analyzing the control commands of the vehicle-mounted refrigerator, thus acquiring data on the inherent communication requirements of the commands. Second, it performs fitness assessment by real-time collection of multiple communication impact parameters and combining them with command complexity, achieving real-time, multi-dimensional measurement of environmental interference. It then matches the environmental carrying capacity with specific command requirements, calculating the current communication fitness, which reflects the reliability of the current communication link. Third, it determines the communication interference coefficient based on a preset ideal fitness threshold and the calculated current communication fitness, converting the difference into a communication interference coefficient. This quantifies the burden on specific command transmission caused by the current environment relative to the ideal state, providing a mathematical basis for subsequent parameter adjustments. Simultaneously, it obtains the basic transmission power and basic transmission rate based on the communication impact parameters and uses the communication interference coefficient to collaboratively correct the basic transmission power and basic transmission rate, increasing the transmission power to overcome attenuation and interference, achieving an optimal balance between communication transmission reliability, real-time performance, and energy consumption. Finally, it executes wireless communication control according to the corrected parameters, applying the aforementioned steps to the corresponding modules to ensure that the transmitted control commands are executed under optimized communication parameters, guaranteeing the continuity and reliability of the vehicle-mounted refrigerator's communication data control. Attached Figure Description

[0014] Figure 1 This is a flowchart illustrating a wireless communication data processing method for a vehicle-mounted refrigerator in a complex environment, as described in this application.

[0015] Figure 2 This is a flowchart illustrating the calculation of corrected transmission power and corrected transmission rate in a wireless communication data processing method for a vehicle-mounted refrigerator in a complex environment, as described in this application. Detailed Implementation

[0016] This application provides a wireless communication data processing method for vehicle-mounted refrigerators in complex environments, specifically addressing the problems of high command transmission failure rate, response delay, and low reliability of communication transmission control in vehicle-mounted refrigerators in the prior art.

[0017] The present invention will now be described in detail with reference to the accompanying drawings.

[0018] In the embodiments, such as Figure 1 As shown, this application provides a wireless communication data processing method for a vehicle-mounted refrigerator in a complex environment, the method including: S10: Receives vehicle refrigerator control commands generated by the vehicle intelligent system, performs command feature analysis on the vehicle refrigerator control commands, and obtains command complexity; In this embodiment, the in-vehicle intelligent system is the central control system of the vehicle, usually referring to the vehicle infotainment system or domain controller; the in-vehicle refrigerator control command is a digital command issued by the in-vehicle intelligent system to change the operating state or parameters of the in-vehicle refrigerator; command feature analysis is the process of parsing and evaluating the received control command data packets; command complexity is used to characterize the level of wireless communication link quality required to execute the control command.

[0019] Specifically, an instruction analyzer is first constructed to perform multi-dimensional feature analysis on the control instructions of the vehicle refrigerator. The real-time requirements, reliability requirements and data transmission load of the instructions are evaluated through real-time analysis branches, reliability analysis branches and data volume analysis branches, respectively. The instruction complexity is obtained by weighted fusion calculation, which quantifies the specific requirements of different control instructions on communication quality.

[0020] Step S10 in the method provided in this application embodiment includes: Retrieve the pre-trained instruction analyzer, which includes a real-time analysis branch, a reliability analysis branch, and a data volume analysis branch; The vehicle refrigerator control command is input into the command analyzer. The real-time requirement coefficient is obtained through the real-time analysis branch, the reliability requirement coefficient is obtained through the reliability analysis branch, and the data volume load coefficient is obtained through the data volume analysis branch. The instruction complexity of the vehicle refrigerator control command is obtained by weighting the real-time requirement coefficient, reliability requirement coefficient, and data load coefficient.

[0021] In this embodiment, a pre-trained instruction analyzer is first invoked. The instruction analyzer includes a real-time analysis branch, a reliability analysis branch, and a data volume analysis branch. The instruction analysis branch is an integrated software algorithm module or a lightweight neural network model, acting as an instruction requirement decoder. It automatically parses the input vehicle refrigerator control instructions and outputs various coefficients quantifying their communication requirements. The real-time analysis branch is specifically responsible for evaluating the instruction's sensitivity or tolerance to transmission and execution time delays; the reliability analysis branch is specifically responsible for evaluating the instruction's requirements for transmission success rate and data accuracy; and the data volume analysis branch is specifically responsible for evaluating the scale of information carried by the instruction itself.

[0022] Specifically, the pre-trained instruction analyzer evaluates the real-time requirements, reliability requirements, and data transmission load of instructions. The three branches within the instruction analyzer work together to evaluate these requirements: the real-time analysis branch determines the urgency of the instruction; the reliability analysis branch determines the criticality of the instruction; and the data volume analysis branch calculates the physical volume of the instruction. The instruction analyzer produces structured analytical data, ensuring the comprehensiveness and professionalism of the requirements analysis and providing quality assurance for subsequent coefficient extraction.

[0023] Secondly, the vehicle refrigerator control commands are input into the command analyzer. The real-time requirement coefficient is obtained through the real-time analysis branch, the reliability requirement coefficient through the reliability analysis branch, and the data volume load coefficient through the data volume analysis branch. The real-time requirement coefficient represents the command's sensitivity to transmission delay. The reliability requirement coefficient represents the degree to which the command requires successful transmission and data accuracy. The data volume load coefficient is calculated based on the actual length of the command data packet.

[0024] Specifically, the vehicle refrigerator control commands are first input into a pre-trained command analyzer. The real-time analysis branch parses the command content and outputs a real-time demand coefficient. A higher real-time demand coefficient indicates that the command requires more immediate transmission and execution, and tolerates shorter latency. The reliability analysis branch parses the command's opcode and outputs a reliability coefficient. A higher reliability coefficient indicates that the command is less susceptible to packet loss, retransmission, or data errors, and is more critical. The data volume analysis branch calculates the command's data length and outputs a data volume load coefficient. A higher data volume load coefficient indicates a larger amount of data to be transmitted, longer channel occupancy time, and indirectly increased requirements for communication continuity.

[0025] Finally, the real-time requirement coefficient, reliability requirement coefficient, and data load coefficient are weighted to obtain the instruction complexity of the vehicle refrigerator control command. Specifically, based on the degree of influence of real-time performance, reliability, and data load on the vehicle refrigerator control command, corresponding weight coefficients are set for the real-time requirement coefficient, reliability requirement coefficient, and data load coefficient, where the sum of the weights of the three is 1. Then, based on the weight coefficients, the real-time requirement coefficient, reliability requirement coefficient, and data load coefficient are weighted and fused to obtain the instruction complexity of the control command, where the instruction complexity of the control command = real-time requirement coefficient × real-time requirement coefficient weight coefficient + reliability requirement coefficient × real-time requirement coefficient weight coefficient + data load coefficient × real-time requirement coefficient weight coefficient.

[0026] For example, if the calculated real-time requirement coefficient, reliability requirement coefficient, and data load coefficient are 0.4, 0.6, and 0.19 respectively, and the weight coefficients of the real-time requirement coefficient, reliability requirement coefficient, and data load coefficient after analyzing the three dimensions of real-time performance, reliability, and data load are 0.35, 0.5, and 0.15 respectively, then the instruction complexity of the vehicle refrigerator control command is approximately (0.4 × 0.35 + 0.6 × 0.5 + 0.19 × 0.15) ≈ 0.47.

[0027] In step S10 of the method provided in this application embodiment, the instruction analyzer construction step includes: Collect historical vehicle refrigerator control command records, which include multiple historical vehicle refrigerator control commands, and construct a sample vehicle refrigerator control command set; Real-time requirement annotation and reliability requirement annotation are performed on each sample vehicle refrigerator control command in the sample vehicle refrigerator control command set to construct a sample real-time requirement coefficient set and a sample reliability requirement coefficient set. Construct a real-time analysis branch architecture and a reliability analysis branch architecture; The real-time analysis branch architecture is trained using the sample vehicle-mounted refrigerator control instruction set and the sample real-time demand coefficient set to obtain the real-time analysis branch. The reliability analysis branch architecture is trained using the sample vehicle-mounted refrigerator control instruction set and the sample reliability requirement coefficient set to obtain the reliability analysis branch. A data volume analysis branch is constructed, which obtains the data volume load coefficient by directly calculating the data length of the vehicle refrigerator control command. The real-time analysis branch, reliability analysis branch, and data volume analysis branch are integrated to build an instruction analyzer.

[0028] In this embodiment, historical vehicle refrigerator control command records are first collected. These records include multiple historical vehicle refrigerator control commands, forming a sample vehicle refrigerator control command set. Specifically, the historical vehicle refrigerator control command records are log data of all control commands actually generated and issued by the vehicle's intelligent system during past vehicle operation; the historical vehicle refrigerator control commands are records of each historical control command instance; and the sample set is a dataset formed by formatting and organizing the large number of collected historical command records.

[0029] Specifically, the process begins by collecting historical vehicle refrigerator control command records from the cloud or local storage over a given period of time. These records are then read to obtain multiple historical vehicle refrigerator control commands. The raw data is then processed to remove invalid or erroneous records and unify the data of different formats into a standard structure. This standard structure is used as sample data to construct a sample vehicle refrigerator control command set for subsequent model training.

[0030] Furthermore, real-time requirement annotation and reliability requirement annotation are performed on each sample vehicle-mounted refrigerator control command in the sample vehicle-mounted refrigerator control command set, constructing a sample real-time requirement coefficient set and a sample reliability requirement coefficient set. Annotation refers to the process by which technicians or annotation tools add labels to each sample in the dataset based on annotation rules; these labels are the target values ​​that the model needs to learn and predict. Real-time requirement annotation assigns a numerical value to each historical command, indicating the urgency of the required transmission and execution at that time. Reliability requirement annotation assigns a numerical value to each historical command, indicating its criticality to successful transmission and data accuracy.

[0031] Specifically, the first step was to annotate the control commands of each vehicle refrigerator in the sample vehicle refrigerator control command set. During the annotation process, professional technicians manually annotated the commands based on the actual control requirements and application scenarios of the vehicle refrigerators. Based on their in-depth understanding of the functional characteristics and usage needs of the vehicle refrigerators, the professional technicians precisely quantified the different types of control commands.

[0032] For example, for a temperature anomaly alarm command that immediately activates when the refrigerator compartment temperature exceeds 10°C, due to food safety concerns and the need for immediate response, the real-time requirement is rated as 0.95 and the reliability requirement as 0.90 by professional technicians; for a normal temperature adjustment command that sets the refrigerator compartment temperature to 5°C, considering that users can accept a few minutes of execution delay and that occasional failures can be retried, the real-time requirement is rated as 0.60 and the reliability requirement as 0.75; for a mode switching command that switches to energy-saving mode, since the time requirement is not high and the impact of failure is small, its real-time requirement is rated as 0.40 and the reliability requirement as 0.55; for a query command that queries the current freezer compartment temperature status, considering that query failure has the least impact on user experience, its real-time requirement is rated as 0.25 and the reliability requirement as 0.30.

[0033] Furthermore, real-time analysis and reliability analysis branch architectures are constructed. Specifically, these branch architectures are built using fully connected neural networks. A fully connected neural network is a feedforward neural network structure, typically composed of multiple stacked neuron layers. In a fully connected neural network, each neuron in one layer is connected to all neurons in the previous layer, meaning they have a complete interconnected structure.

[0034] For example, a fully connected neural network can be used to simultaneously construct a real-time analysis branch architecture and a reliability analysis branch architecture. Both branches consist of an input layer, hidden layers, and an output layer. The input layer directly receives the input data. The hidden layer is the core of the fully connected neural network, capable of performing complex nonlinear transformations on the data to extract deep features. Each neuron in the hidden layer receives input from the neurons in the previous layer, and through weighted summation, bias term correction, and activation functions, obtains the input for the next layer. The output layer is used to generate the final prediction result.

[0035] Furthermore, the real-time analysis branch architecture is trained using the sample vehicle-mounted refrigerator control command set and the sample real-time demand coefficient set to obtain the real-time analysis branch. Specifically, the labeled sample vehicle-mounted refrigerator control command set and sample real-time demand coefficient set are input into the initial model architecture, and the internal weight parameters of the model are adjusted repeatedly through optimization algorithms to make the model's predicted output as close as possible to the true value.

[0036] For example, a fully connected neural network is used to train the real-time analysis branch architecture and the reliability analysis branch architecture. The sample vehicle refrigerator control command set and the sample real-time demand coefficient set are used as inputs to the model, and the training, validation, and test sets are divided in a 7:2:1 ratio. Training parameters are set with a learning rate of 0.001, and the Adam optimizer is used for training. Through forward propagation, the input data is weighted and summed using weights and biases, and then nonlinearly transformed using an activation function. Through multiple nonlinear transformations, the complex relationship between the input data and the target output is learned. Subsequently, backpropagation is used to calculate the gradient information of the output error, and the weights and biases in the network are updated using gradient descent. Through optimization, the model's prediction error is continuously reduced. After training, the model's performance on the reserved validation set is evaluated. If the average absolute error between the predicted real-time coefficients and the expert-annotated values ​​decreases to within 0.05, the requirement is met, and the real-time analysis branch architecture is obtained.

[0037] Furthermore, the reliability analysis branch architecture is trained using the sample vehicle-mounted refrigerator control command set and the sample reliability requirement coefficient set, resulting in the reliability analysis branch. Similarly, following the fully connected neural network-based reliability analysis branch, the sample vehicle-mounted refrigerator control command set and the sample reliability requirement coefficient set are used as the model's input data. The training, validation, and test sets are divided in a 7:2:1 ratio using the same training method described above. Training parameters are set with a learning rate of 0.001, and the Adam optimizer is used for training. Through forward propagation, the input data undergoes a weighted summation of weights and biases, followed by a nonlinear transformation using an activation function. Through multiple nonlinear transformations, the complex relationship between the input data and the target output is learned. Subsequently, the gradient information of the output error is calculated through backpropagation, and the weights and biases in the network are updated using gradient descent. Through optimization, the model's prediction error is continuously reduced. After training, the model's performance on the reserved validation set is evaluated. Assuming that the mean absolute error (MAE) of its predicted real-time coefficients relative to the expert-annotated values ​​is reduced to within 0.05, the requirement is met, and the reliability analysis branch architecture is obtained.

[0038] Furthermore, a data volume analysis branch is constructed. This branch obtains the data volume load factor by directly calculating the data length of the vehicle refrigerator control commands. Specifically, it first calculates the data length of the vehicle refrigerator control commands based on the sample vehicle refrigerator control command set and the sample reliability requirement coefficient set to obtain the data volume load factor. Then, based on the calculated data volume load factor, a mapping relationship between data length and data volume load factor is constructed, resulting in a mapping table between data length and data volume load factor. Finally, the corresponding data volume load factor is obtained through the mapping table.

[0039] Finally, the real-time analysis branch, reliability analysis branch, and data volume analysis branch are integrated to construct the instruction analyzer. Specifically, the real-time analysis branch for predicting real-time coefficients, the reliability analysis branch for predicting reliability coefficients, and the data volume analysis branch for calculating data volume load coefficients are integrated into a unified interface. When the instruction analyzer is invoked, it first receives the input instruction; then sends the instruction to all three branches simultaneously; and collects the output real-time requirement coefficient, reliability requirement coefficient, and data volume load coefficient as a set of data outputs.

[0040] In this embodiment, an instruction analyzer is constructed to deconstruct and evaluate instructions from three dimensions: real-time performance, reliability, and data volume, providing a precise basis for subsequent resource allocation. Subsequently, based on historical data, the analysis branch is trained by collecting historical instructions and labeling their requirements, learning real communication behavior patterns, improving the model's generalization and adaptability, and obtaining the decision-making basis for the inherent communication requirements of dynamic control instructions.

[0041] S20: Collect multiple communication impact parameters of the vehicle communication environment in real time, perform fitness evaluation and analysis based on multiple communication impact parameters and instruction complexity, and calculate the current communication fitness; In this embodiment, the vehicle communication environment is the sum of physical and electromagnetic conditions inside and outside the vehicle that affect wireless signal transmission, and is the supply-side condition for communication; the communication impact parameter is measurable data that can directly or indirectly reflect the strength of the current environment's interference with wireless communication; the fitness evaluation analysis is the process of calculating the matching degree between instruction complexity and environmental supply capacity; the current communication fitness is the expected ease of successfully transmitting and executing the current specific instruction under the current environmental interference level.

[0042] Specifically, a communication bearer evaluator is established to monitor the interference status of the vehicle environment in real time. By collecting key environmental parameters such as motor interference intensity, vehicle electrical interference power, and frequency band occupancy, multiple communication impact parameters and instruction complexity are evaluated and analyzed for fitness. The communication bearer capacity under the current environment is assessed, and the communication fitness under the current environment is calculated accordingly.

[0043] Step S20 in the method provided in this application embodiment includes: Multiple communication impact parameters of the vehicle communication environment are collected in real time, including motor interference intensity, vehicle electrical interference power, and frequency band occupancy rate. Multiple communication impact parameters are vectorized to construct a communication impact parameter vector. Input the communication impact parameter vector into a pre-trained communication bearer estimator to obtain the communication bearer level; Fitness evaluation analysis is performed based on communication capacity and instruction complexity to calculate the current communication fitness.

[0044] In this embodiment, multiple communication impact parameters of the vehicle communication environment are first collected in real time. These parameters include motor interference intensity, vehicle electrical interference power, and frequency band occupancy. Motor interference intensity refers to the PWM interference generated by the motor controller during the operation of the electric vehicle's drive motor, which can be quantified by detecting the motor's operating frequency. Vehicle electrical interference power refers to the real-time power consumption of devices such as air conditioners, audio systems, and chargers; higher power consumption results in stronger electromagnetic interference. Frequency band occupancy refers to the usage of the same frequency band by in-vehicle Wi-Fi and Bluetooth devices, which directly affects the channel quality of the StarFlash communication.

[0045] Specifically, when preparing to send a control command for the vehicle refrigerator, synchronous data acquisition equipment collects data on motor interference intensity, vehicle electrical interference power, and frequency band occupancy. Motor interference intensity is obtained by connecting to the vehicle controller's local area network or directly from the motor controller, estimating the current interference intensity generated by the motor. Vehicle electrical interference power is obtained by querying the vehicle's electrical management module, obtaining the real-time power consumption of devices such as the air conditioner, audio system, and charger. Frequency band occupancy is determined by monitoring specific channels within a certain frequency band and statistically analyzing the percentage of time the signal strength exceeds a threshold.

[0046] For example, by collecting data, a snapshot of the environment at the current moment is obtained: [motor interference intensity = 0.65, vehicle electrical interference power = 0.40, frequency band occupancy rate = 0.75].

[0047] Secondly, multiple communication impact parameters are vectorized to construct a communication impact parameter vector. Vectorization involves arranging multiple independent scalar values ​​in a fixed order and combining them into a mathematical vector. The communication impact parameter vector, after vectorization, becomes a feature vector representing the current environmental state. Specifically, the dispersed parameters are first vectorized, then arranged and combined in a fixed order into a one-dimensional array, which serves as the communication impact parameter vector. This communication impact parameter vector then represents the feature vector of the current environmental state.

[0048] Next, the communication impact parameter vector is input into a pre-trained communication bearer estimator to obtain the communication bearer capacity. The communication bearer capacity is the highest instruction complexity value that the wireless communication link is expected to stably transmit under the current environmental conditions of the communication impact parameter vector. Specifically, the communication impact parameter vector is input into the pre-trained communication bearer estimator, which searches for similar historical patterns in its internal feature space and comprehensively judges the stability of the communication link under the current interference combination, i.e., the communication bearer capacity. This process accurately assesses the supply-side capability of the communication environment. A higher bearer capacity indicates a higher level of instruction complexity that can be processed, more complex instructions that can be carried, and higher communication stability.

[0049] Finally, a fitness assessment analysis is performed based on communication capacity and instruction complexity to calculate the current communication fitness. The fitness assessment analysis evaluates the degree of matching between environmental supply capacity and instruction requirements. Specifically, the fitness is calculated based on the ratio of communication capacity to instruction complexity to obtain the current communication fitness.

[0050] In step S20 of the method provided in this application embodiment, the construction step of the communication bearer evaluator includes: Under the conditions of basic transmission power and basic transmission rate, multiple historical communication impact parameters of different historical vehicle communication environments are collected, a vector of historical communication impact parameters is constructed, and a sample communication impact parameter vector set is formed. For each sample communication influence parameter vector in the sample communication influence parameter vector set, corresponding to the historical environmental conditions, the highest instruction complexity successfully transmitted under the historical environmental conditions is statistically analyzed, and the highest instruction complexity is used as the communication carrying capacity label value. Construct a sample communication carrying capacity set based on the communication carrying capacity label values; Using the sample communication influence parameter vector set as the input vector and the sample communication carrying capacity set as the label, a communication carrying capacity evaluator is trained and generated.

[0051] In this embodiment, firstly, under basic transmission power and basic transmission rate conditions, multiple historical communication influence parameters for different historical vehicle communication environments are collected to construct a historical communication influence parameter vector, forming a sample communication influence parameter vector set. The basic transmission rate condition involves fixing the transmit power and physical layer coding rate of the wireless communication module to a set of preset values ​​during the data acquisition phase of constructing the evaluator. The historical vehicle communication environment refers to the various communication environment states experienced by the vehicle during past operation; the historical communication influence parameters are the parameter values ​​actually measured and recorded by sensors and monitoring modules under various historical environmental conditions.

[0052] Specifically, under the conditions of basic transmission power and basic transmission rate, the hardware transmission parameters of the wireless communication module are kept constant while data is collected to obtain multiple historical communication impact parameters for different historical vehicle communication environments. The collected parameter values ​​are then converted into vectors to construct a historical communication impact parameter vector. This process is repeated several times to obtain hundreds of thousands of such historical vectors, which are finally aggregated to form a sample communication impact parameter vector set. Under the conditions of basic transmission power and basic transmission rate, the hardware transmission parameters of the wireless communication module remain constant. This ensures that any observed differences in communication performance can be attributed to changes in environmental parameters, rather than changes in transmission parameters, thus eliminating confounding variables.

[0053] Secondly, for each sample communication influence parameter vector in the sample communication influence parameter vector set, corresponding to the historical environmental conditions, the highest successfully transmitted instruction complexity under the historical environmental conditions is statistically analyzed, and this highest instruction complexity is used as the communication capacity label value. Specifically, the highest instruction complexity is the maximum instruction complexity among all successfully transmitted instructions found under a specific historical environmental condition by analyzing historical communication logs; the communication capacity label value is the communication capacity value under the environmental condition corresponding to the highest instruction complexity. In detail, if an instruction with a complexity of N (relatively large) can be successfully transmitted, transmitting instructions with a complexity lower than N is easier; conversely, if an instruction with a complexity of M (relatively small) fails to be transmitted, the actual capacity of the corresponding environment is definitely lower than M. Therefore, the highest successfully transmitted instruction complexity can be used as an indicator reflecting the limit of environmental capacity.

[0054] Next, a sample communication capacity set is constructed based on the communication capacity label values. Based on historical environmental data, the communication capacity is quantitatively integrated. By statistically analyzing the highest successfully transmitted instruction complexity under various historical environmental conditions, the obtained complexity values ​​are used as the communication capacity label values ​​for the corresponding environmental conditions, thus forming the sample communication capacity set.

[0055] During the construction process, it is necessary to determine the communication carrying capacity under various environmental conditions in advance through historical data analysis. Specifically, for each sample vector in the pre-established sample communication influence parameter vector set, the historical environmental condition parameters represented by the vector are extracted, and the highest command complexity that was actually successfully transmitted under this set of parameter conditions is statistically analyzed. This highest complexity value is used as the communication carrying capacity label value under that specific environmental condition.

[0056] For example, a certain historical environmental condition parameter includes: motor interference intensity of 40 units, vehicle electrical interference power of 80W, and frequency band occupancy rate of 50%. If the highest instruction complexity actually successfully transmitted under these parameter conditions is 0.7, then the communication carrying capacity label value corresponding to this environment is determined to be 0.7.

[0057] By performing the above annotation operation on all vectors in the sample communication influence parameter vector set, a communication carrying capacity value corresponding to each environmental parameter vector is obtained. These labeled values ​​are systematically organized and stored in the same order as the parameter vectors, thus constructing a complete sample communication carrying capacity set. Each element in the set is a specific value, representing the maximum instruction transmission complexity that the communication system can support under the corresponding environmental conditions, i.e., the upper limit of communication carrying capacity, providing accurate supervised learning labels for subsequent model training.

[0058] Finally, using the sample communication influence parameter vector set as the input vector and the sample communication carrying capacity set as the label, a communication carrying capacity estimator is trained. A backpropagation (BP) neural network can be used to construct the preprocessing predictor, predicting the direction of output parameter adjustment. The BP neural network model is a feedforward neural network trained through error backpropagation and is commonly used to predict continuous values. Specifically, to construct the communication carrying capacity estimator, a specific neural network is selected. First, the dataset is divided into training, validation, and test sets. The training set is input into the preprocessing predictor model. The preprocessing predictor predicts each vector and calculates the mean squared error between the predicted value and the true label. The network weights are adjusted using the backpropagation algorithm to reduce error, iterating several times. Then, the model performance is evaluated using the validation set to prevent overfitting. Training stops when the validation set loss no longer decreases. Finally, the optimal network weights at this point are saved, resulting in the communication carrying capacity estimator.

[0059] For example, the steps to construct a communication bearer estimator based on a BP neural network are as follows: First, using the sample communication influence parameter vector set as the input vector and the sample communication carrying capacity set as the label, the sample data is divided into training set, validation set, and test set in a ratio of 7:2:1.

[0060] Secondly, the communication bearer evaluator mainly consists of an input layer, a hidden layer, and an output layer. The input layer is used to receive the sample saline feature set and the sample preprocessed saline feature set; the hidden layer performs nonlinear transformation through an activation function; and the output layer outputs the prediction result through an activation function.

[0061] Finally, using the sample communication influence parameter vector set as input and the sample communication carrying capacity set as labels, an initial learning rate and weights are set and weights are assigned. The mean squared error function is used to calculate the error between the predicted and actual results, and the weights are adjusted and calculated iteratively until the error is minimized. The input data is processed by weighted summation and activation function through forward propagation and passed layer by layer to the output layer. The gradient of the loss function is calculated through backpropagation, and the parameters are updated. The performance is evaluated using a validation set after each training epoch to avoid overfitting. When the MSE loss of the training set decreases by less than 1e-5 for 5 consecutive epochs and the MSE loss of the validation set stabilizes below 0.01, the model is considered to have converged, and the communication carrying capacity estimator is obtained.

[0062] Assuming the collected scalar values ​​are 0.65, 0.40, and 0.75, arranged in a fixed order, an environmental feature vector of [0.65, 0.40, 0.75] is constructed. Inputting this into the communication bearer evaluator yields a communication bearer score of 0.5, indicating that under the current environment, it can reliably and stably transmit instructions with a complexity ≤ 0.5.

[0063] In step S20 of the method provided in this application embodiment, a fitness evaluation analysis is performed based on communication bearer capacity and instruction complexity to calculate the current communication fitness, including: Compare communication capacity with instruction complexity; When the communication capacity is greater than or equal to the instruction complexity, the current communication fitness is set to 1; When the communication capacity is less than the instruction complexity, the ratio of the communication capacity to the instruction complexity is calculated, and the ratio is used as the current communication fitness.

[0064] In this embodiment, the communication capacity and instruction complexity are compared first. Specifically, the communication capacity and instruction complexity are numerically compared, and the comparison result is used as the direction for subsequent adjustment calculations.

[0065] Furthermore, when the communication capacity is greater than or equal to the instruction complexity, the current communication fitness is set to 1. Specifically, if the communication capacity is greater than or equal to the instruction complexity, it indicates that environmental resources are sufficient and the instruction transmission requirements can be fully met. Therefore, the current communication fitness is set to 1.

[0066] Furthermore, when the communication capacity is less than the instruction complexity, the ratio of communication capacity to instruction complexity is calculated, and this ratio is used as the current communication fitness. Specifically, if the communication capacity is less than the instruction complexity, it indicates that under the current environmental conditions, the inherent capability of the communication link cannot meet the instruction transmission requirements, and there is a capability gap. Therefore, the ratio of communication capacity to instruction complexity is used as the current communication fitness.

[0067] For example, the communication load capacity is 0.5 and the instruction complexity is 0.47. Since the communication load capacity is greater than the instruction complexity, the environment's communication load capacity is higher than or equal to the instruction requirements, so the current communication fitness is 1.

[0068] In this embodiment, multi-source interference parameters are collected in real time and a pre-trained communication bearer evaluator is used for comprehensive judgment. Environmental information is fused into a communication bearer level that directly reflects the current channel reliability, avoiding the one-sidedness of single-parameter evaluation. Under baseline communication parameters, the highest command complexity that can be stably transmitted in a large number of historical environments is statistically analyzed and used as a label for training, thus constructing the communication bearer evaluator. This evaluator predicts the upper limit of the command complexity that can be tolerated based on the current environment. Subsequently, the communication bearer level is compared with the command complexity, and adjustments are calculated hierarchically based on the comparison results, providing direct decision input for subsequent parameter correction.

[0069] S30: Obtain a preset fitness threshold, and determine the communication interference coefficient based on the preset fitness threshold and the current communication fitness; In this embodiment, the preset fitness threshold is a pre-set fitness benchmark value, representing the ideal state in which the instruction requirements and the environmental carrying capacity are perfectly matched; the communication interference coefficient is the value of the degree to which the current communication conditions deviate from the ideal state, which can directly reflect the intensity of the adjustment of communication parameters required to overcome environmental interference and meet the instruction transmission requirements.

[0070] Specifically, based on the fitness assessment analysis results obtained under the current environment, a preset fitness threshold is set. Then, based on the preset fitness threshold and the fitness assessment analysis results, a communication interference coefficient is further calculated. This interference coefficient can be used to correct the basic transmission parameters, providing the foundational data for correction. A higher interference coefficient indicates a more severe environment, requiring greater parameter correction.

[0071] Step S30 in the method provided in this application embodiment includes: Obtain the preset fitness threshold, which is 1; Calculate the difference between the preset fitness threshold and the current communication fitness, and use the difference as the communication interference coefficient.

[0072] In this embodiment, a preset fitness threshold is obtained, which is set to 1. The fitness threshold is a critical value used to measure whether the current communication fitness has reached an ideal state. Specifically, the preset fitness threshold is first obtained, and a preset fitness threshold of 1 represents an ideal, fully adapted state, indicating that the environment's carrying capacity fully covers or even exceeds the instruction requirements. Subsequently, the deviation of the current communication environment from the ideal communication environment can be assessed based on the similarity between the current communication fitness and the preset fitness threshold of 1.

[0073] Secondly, the difference between the preset fitness threshold and the current communication fitness is calculated, and this difference is used as the communication interference coefficient. Specifically, the communication interference coefficient is determined by calculating the difference between the preset fitness threshold and the current communication fitness, and the difference directly reflects the degree of deviation between the current communication environment and the ideal state. If the current communication fitness is 1 and the difference is 0, it indicates that the environment fully meets the communication requirements, and no parameter adjustment is needed; if the current communication fitness is 0.7 and the difference is 0.3, it indicates that the environment has a 30% deficiency, and compensation needs to be made through parameter adjustment.

[0074] In this embodiment, a preset fitness threshold of 1 is set, and the difference between the current fitness and the current fitness is calculated. When the current fitness is 1, the difference is 0, indicating that no correction is needed; when the fitness is less than 1, the difference is a positive number between 0 and 1, and the lower the fitness, the greater the communication interference coefficient. The communication interference coefficient represents the proportion of interference from the current environment to the transmission of the specific instruction, ensuring the accuracy of the correction.

[0075] S40: Obtain the basic transmission power and basic transmission rate based on multiple communication influence parameters, and correct the basic transmission power and basic transmission rate according to the communication interference coefficient to obtain the corrected transmission power and corrected transmission rate. In this embodiment, the basic transmission power and basic transmission rate are preset wireless transmission power and data transmission rate under normal or default vehicle communication configuration to balance energy consumption, speed and general interference; correction refers to dynamically and directionally adjusting the basic transmission parameters according to the calculated communication interference coefficient; the corrected transmission power and corrected transmission rate are the actual transmission power and actual data transmission rate finally used for this command transmission after intelligent adjustment.

[0076] Specifically, multiple basic transmission powers and basic transmission rates are corrected based on the communication interference coefficient. Through correction, the actual transmission power and actual data transmission rate used for this command transmission can be obtained, which facilitates direct control and execution of the obtained command transmission parameters for actual operation control.

[0077] Step S40 in the method provided in this application embodiment includes: Obtain the preset base transmission power and base transmission rate; Calculate the sum of 1 and the communication interference coefficient to obtain the correction coefficient; Multiply the base transmission power by the correction factor to obtain the corrected transmission power; Divide the base transmission rate by the correction factor to obtain the corrected transmission rate.

[0078] like Figure 2 As shown in the embodiments of this application, a preset base transmission power and base transmission rate are first obtained, where the preset base transmission power and base transmission rate represent reference values ​​determined under standard environmental conditions. For example, for the communication module of a certain model of vehicle-mounted refrigerator, the parameters read for a smooth driving scenario are: base transmission power = 12dBm, base transmission rate = 5Mbps.

[0079] Next, the sum of 1 and the communication interference coefficient is calculated to obtain the correction coefficient. The correction coefficient indicates the degree to which the basic parameters need adjustment. Specifically, when the communication interference coefficient is 0, i.e., the current communication fitness = 1, and the environment perfectly carries the command, the correction coefficient = 1 + 0 = 1, indicating that no enhancement adjustments to the basic parameters are needed. When the communication interference coefficient is greater than 0, i.e., the current communication fitness < 1, the correction coefficient = 1 + the current communication fitness, and its value is greater than 1, indicating the degree to which the basic parameters need adjustment.

[0080] For example, if the communication interference factor is 0.3, then the correction factor is 1.3, which means that the parameters need to be adjusted with 1.3 times the strength to overcome the interference.

[0081] Next, multiply the base transmission power by the correction factor to obtain the corrected transmission power. The corrected transmission power is the adjusted actual signal transmission strength used for this wireless communication. Specifically, when the communication environment deteriorates or the command requirements increase, the signal transmission power is increased linearly. Multiplying the base transmission power by the correction factor yields the corrected transmission power: Corrected transmission power = Base transmission power × Correction factor.

[0082] For example, if the base transmission power is 12dBm and the correction factor is 1.3, the corrected transmission power = 12dBm × 1.3 = 13.14dBm.

[0083] Finally, the base transmission rate is divided by the correction factor to obtain the corrected transmission rate. The corrected transmission rate is the actual data transmission speed used for this wireless communication after adjustment. Specifically, when the communication environment deteriorates or the command requirements become more stringent (i.e., the correction factor > 1), the data transmission rate needs to be linearly reduced to correct the transmission rate, where the corrected transmission rate = base transmission rate / correction factor. By reducing the transmission rate, the duration of data bits is increased, the occupied spectrum is narrowed, and energy is more concentrated. At the same signal-to-noise ratio, the receiver has more time to identify the data, thus significantly reducing the bit error rate and improving the reliability of data transmission.

[0084] For example, with a base transmission rate of 5 Mbps and a correction factor of 1.3, the corrected transmission rate = 5 / 1.3 ≈ 3.85 Mbps.

[0085] In this embodiment, a preset base transmission power and base transmission rate are first obtained. Then, a correction coefficient is obtained by calculating the sum of I and the communication interference coefficient. The correction coefficient is used to adjust both the transmission power and transmission rate simultaneously. The base transmission power is then multiplied by the correction coefficient to obtain the corrected transmission power, thereby increasing the power and enhancing signal strength and anti-interference capability. Simultaneously, the base transmission rate is divided by the correction coefficient to obtain the corrected transmission rate, thereby appropriately reducing the rate and improving data transmission reliability. This ensures stable and reliable wireless communication quality even in complex in-vehicle environments, effectively solving the adverse effects of environmental interference on the transmission of control commands for in-vehicle refrigerators.

[0086] S50: Perform wireless communication control on the vehicle refrigerator according to the corrected transmission power and corrected transmission rate.

[0087] In this embodiment, wireless communication control is performed on the vehicle-mounted refrigerator according to the corrected transmission power and corrected transmission rate. This wireless communication control involves using a wireless communication module configured with specific power and rate to transmit data packets containing control commands to the vehicle-mounted refrigerator's communication receiving unit via a wireless channel. Specifically, after the corrected transmission power and corrected transmission rate are determined, the main control system immediately sends the parameters to the corresponding responsible module via a hardware interface. The communication module then modulates and radiates the encapsulated command data packets at the specified transmission power and encoding rate. The receiver at the vehicle-mounted refrigerator demodulates and decodes the data at the corresponding rate, thus completing the command transmission. This optimized communication strategy is accurately implemented at the physical layer, thereby maximizing communication success rate and efficiency in complex environments.

[0088] For example, the final system uses a power of 13.14dBm and a rate of 3.85Mbps to send temperature control commands, ensuring a high transmission success rate under the current interference environment.

[0089] In this embodiment, after the corrected transmission power and corrected transmission rate are determined, the main control system immediately sends the parameters to the corresponding responsible module through the hardware interface. The communication module then modulates and radiates the encapsulated instruction data packet at the specified transmission power and encoding rate. The receiver at the vehicle-mounted refrigerator demodulates and decodes the instruction at the corresponding rate, thereby completing the transmission of the instruction. The optimized communication strategy is accurately implemented at the physical layer. This improves the link budget and error resilience, enabling the refrigerator to successfully receive the instruction and immediately execute safety protection actions, avoiding potential risks.

[0090] The embodiments of this application, through the above specific implementation methods, achieve the following technical effects: In this embodiment, an instruction analyzer is first constructed to deconstruct and evaluate instructions from three dimensions: real-time performance, reliability, and data volume, providing a precise basis for subsequent resource allocation. Then, based on historical data, the analysis branch is trained by collecting historical instructions and labeling their requirements, learning real communication behavior patterns, improving the model's generalization and adaptability, and obtaining the decision-making basis for the inherent communication needs of dynamic control instructions.

[0091] Secondly, by collecting multi-source interference parameters in real time and using a pre-trained communication bearer estimator for comprehensive judgment, environmental information is integrated into a communication bearer level that directly reflects the current channel reliability, avoiding the one-sidedness of single-parameter evaluation. Under baseline communication parameters, the highest command complexity that can be stably transmitted in a large number of historical environments is statistically analyzed and used as a label for training to construct the communication bearer estimator, which predicts the upper limit of the command complexity that can be tolerated based on the current environment. Subsequently, the communication bearer level is compared with the command complexity, and based on the comparison results, hierarchical adjustment calculations are performed, providing direct decision input for subsequent parameter correction.

[0092] Next, a preset fitness threshold of 1 is set, and the difference between this threshold and the current communication fitness is calculated. When the current fitness is 1, the difference is 0, indicating that no correction is needed; when the fitness is less than 1, the difference is a positive number between 0 and 1, and the lower the fitness, the greater the communication interference coefficient. The communication interference coefficient represents the proportion of interference from the current environment to the transmission of this specific command, ensuring the accuracy of the correction.

[0093] Meanwhile, in this embodiment, a preset base transmission power and base transmission rate are first obtained. Then, a correction coefficient is obtained by calculating the sum of I and the communication interference coefficient. This correction coefficient is used to adjust both the transmission power and transmission rate simultaneously. The base transmission power is then multiplied by the correction coefficient to obtain the corrected transmission power, thereby increasing power to enhance signal strength and anti-interference capabilities. Simultaneously, the base transmission rate is divided by the correction coefficient to obtain the corrected transmission rate, thereby appropriately reducing the rate to improve data transmission reliability. This ensures stable and reliable wireless communication quality even in complex in-vehicle environments, effectively solving the adverse effects of environmental interference on the transmission of control commands for in-vehicle refrigerators.

[0094] Finally, after determining the corrected transmission power and rate, the main control system immediately sends the parameters to the corresponding responsible module via the hardware interface. The communication module then modulates and radiates the encapsulated instruction data packet at the specified transmit power and encoding rate. The receiver at the vehicle-mounted refrigerator demodulates and decodes the instruction at the corresponding rate, thus completing the transmission. The optimized communication strategy is accurately implemented at the physical layer. This improves the link budget and error resilience, enabling the refrigerator to successfully receive the instruction and immediately execute safety protection actions, avoiding potential risks.

Claims

1. A wireless communication data processing method for a vehicle-mounted refrigerator in a complex environment, characterized in that, The method includes: Receive vehicle refrigerator control commands generated by the vehicle intelligent system, perform command feature analysis on the vehicle refrigerator control commands, and obtain command complexity; Multiple communication impact parameters of the vehicle communication environment are collected in real time. Based on the multiple communication impact parameters and the instruction complexity, a fitness evaluation analysis is performed to calculate the current communication fitness. Obtain a preset fitness threshold, and determine a communication interference coefficient based on the preset fitness threshold and the current communication fitness; The basic transmission power and basic transmission rate are obtained based on the multiple communication influence parameters, and the basic transmission power and basic transmission rate are corrected according to the communication interference coefficient to obtain the corrected transmission power and corrected transmission rate. The vehicle-mounted refrigerator is wirelessly controlled according to the corrected transmission power and corrected transmission rate.

2. The method according to claim 1, characterized in that, The control commands for the vehicle-mounted refrigerator are analyzed for command characteristics to obtain command complexity, including: Retrieve a pre-trained instruction analyzer, which includes a real-time analysis branch, a reliability analysis branch, and a data volume analysis branch; The vehicle refrigerator control command is input into the command analyzer, and the real-time demand coefficient is obtained through the real-time analysis branch, the reliability demand coefficient is obtained through the reliability analysis branch, and the data volume load coefficient is obtained through the data volume analysis branch. The instruction complexity of the vehicle refrigerator control command is obtained by weighting the real-time requirement coefficient, the reliability requirement coefficient, and the data load coefficient.

3. The method according to claim 2, characterized in that, The steps for constructing the instruction analyzer include: Collect historical vehicle refrigerator control command records, which include multiple historical vehicle refrigerator control commands, and construct a sample vehicle refrigerator control command set; Real-time requirement annotation and reliability requirement annotation are performed on each sample vehicle refrigerator control command in the sample vehicle refrigerator control command set to construct a sample real-time requirement coefficient set and a sample reliability requirement coefficient set. Construct a real-time analysis branch architecture and a reliability analysis branch architecture; The real-time analysis branch architecture is trained using the sample vehicle refrigerator control instruction set and the sample real-time demand coefficient set to obtain the real-time analysis branch; The reliability analysis branch architecture is trained using the sample vehicle refrigerator control instruction set and the sample reliability requirement coefficient set to obtain the reliability analysis branch; A data volume analysis branch is constructed, which obtains the data volume load coefficient by directly calculating the data length of the vehicle refrigerator control command. The real-time analysis branch, the reliability analysis branch, and the data volume analysis branch are integrated to construct the instruction analyzer.

4. The method according to claim 1, characterized in that, Multiple communication impact parameters of the vehicle communication environment are collected in real time. Based on these multiple communication impact parameters and the instruction complexity, a fitness evaluation analysis is performed to calculate the current communication fitness, including: Multiple communication impact parameters of the vehicle communication environment are collected in real time, including motor interference intensity, vehicle electrical interference power, and frequency band occupancy rate. The multiple communication impact parameters are vectorized to construct a communication impact parameter vector; The communication impact parameter vector is input into a pre-trained communication bearer estimator to obtain the communication bearer degree; Based on the communication capacity and instruction complexity, a fitness evaluation analysis is performed to calculate the current communication fitness.

5. The method according to claim 4, characterized in that, The construction steps of the communication bearer evaluator include: Under the conditions of basic transmission power and basic transmission rate, multiple historical communication impact parameters of different historical vehicle communication environments are collected, a vector of historical communication impact parameters is constructed, and a sample communication impact parameter vector set is formed. For each sample communication influence parameter vector in the sample communication influence parameter vector set, corresponding to the historical environmental conditions, the highest instruction complexity successfully transmitted under the historical environmental conditions is statistically analyzed, and the highest instruction complexity is used as the communication carrying capacity label value. Construct a sample communication carrying capacity set based on the aforementioned communication carrying capacity label values; The communication carrying capacity evaluator is trained and generated using the sample communication influence parameter vector set as the input vector and the sample communication carrying capacity set as the label.

6. The method according to claim 4, characterized in that, Based on the communication capacity and instruction complexity, a fitness evaluation analysis is performed to calculate the current communication fitness, including: Compare the communication capacity with the instruction complexity; When the communication capacity is greater than or equal to the instruction complexity, the current communication fitness is set to 1; When the communication capacity is less than the instruction complexity, the ratio of the communication capacity to the instruction complexity is calculated, and the ratio is used as the current communication fitness.

7. The method according to claim 1, characterized in that, Obtain a preset fitness threshold, and determine a communication interference coefficient based on the preset fitness threshold and the current communication fitness, including: Obtain a preset fitness threshold, wherein the preset fitness threshold is 1; Calculate the difference between the preset fitness threshold and the current communication fitness, and use the difference as the communication interference coefficient.

8. The method according to claim 1, characterized in that, Based on the aforementioned multiple communication impact parameters, a base transmission power and a base transmission rate are obtained. Then, the base transmission power and base transmission rate are corrected according to the communication interference coefficient to obtain corrected transmission power and corrected transmission rate, including: Obtain the preset base transmission power and base transmission rate; Calculate the sum of 1 and the communication interference coefficient to obtain the correction coefficient; Multiply the base transmission power by the correction factor to obtain the corrected transmission power; Divide the base transmission rate by the correction factor to obtain the corrected transmission rate.

Images