Intelligent cabin system monitoring method and device, terminal and storage medium

Abstract

The invention provides an intelligent cabin system monitoring method and device, a terminal and a storage medium. The method comprises the following steps: acquiring an intelligent cabin system data sample; inputting the sample into a to-be-trained classifier model, iteratively performing target feature selection on the sample through quantum gate operation, classifying the selected target features through a random forest algorithm, and adjusting parameters of a quantum gate according to a classification result to obtain adjusted parameters of the quantum gate until a preset iteration stop condition is reached, obtaining a target classifier model; collecting target intelligent cabin system data; and classifying the target intelligent cabin system data through the target classifier model to obtain an intelligent cabin system state monitoring result. Through fusion of the quantum coding technology and the random forest algorithm, the target feature selection efficiency and classification accuracy of the classifier model are improved, and real-time monitoring and predictive maintenance of the state of the intelligent cabin system are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent cockpit system monitoring, and in particular to an intelligent cockpit system monitoring method, device, terminal and storage medium. Background Art

[0002] With the rapid development of automobile intelligence, the performance and reliability of the smart cockpit system, as an important part of vehicle intelligence, directly affect the driving experience and driving safety. Smart cockpit systems usually integrate a variety of sensors and electronic devices to provide functions such as infotainment and driver assistance. However, these systems may encounter various faults and performance degradation problems during operation. Traditional maintenance methods often rely on regular inspections and post-repairs, which is not only inefficient but also unable to effectively prevent the occurrence of faults. In addition, the existing technologies in the monitoring and maintenance of smart cockpit systems include limitations in data collection, low data processing efficiency, inaccurate feature selection, limited model generalization, reactive maintenance rather than predictive maintenance, insufficient technology integration, and lack of real-time monitoring and prediction capabilities. These limitations make it impossible for the system to fully capture the operating status inside the cockpit, making it difficult to quickly and accurately predict and respond to faults, increasing downtime and maintenance costs, while limiting the adaptability and scalability of the system in different application scenarios. Summary of the invention

[0003] The main purpose of the present invention is to provide a smart cockpit system monitoring method, device, terminal and storage medium, aiming to solve the technical problems that the existing smart cockpit system monitoring and maintenance cannot fully capture the operating status inside the cockpit, it is difficult to quickly and accurately predict and respond to faults, which increases downtime and maintenance costs, and at the same time limits the adaptability and scalability of the system in different application scenarios.

[0004] In a first aspect, the present invention provides a smart cockpit system monitoring method, comprising:

[0005] Acquire a smart cockpit system data sample, where the smart cockpit system data sample identifies an operating state type of the smart cockpit system;

[0006] Inputting the smart cockpit system data sample into the classifier model to be trained, so as to iteratively select target features of the smart cockpit system data sample through quantum gate operation, classifying the selected target features through a random forest algorithm, and adjusting the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate, until a preset iteration stop condition is reached, and a target classifier model is obtained;

[0007] Collect target intelligent cockpit system data;

[0008] The target intelligent cockpit system data is classified by the target classifier model to obtain the intelligent cockpit system status monitoring result.

[0009] In a specific embodiment, the target feature selection of the smart cockpit system data sample by quantum gate operation, classification of the selected target features by random forest algorithm, and adjustment of the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate include:

[0010] Initializing a quantum register; wherein each qubit of the quantum register corresponds to a feature in the data sample feature set of the smart cockpit system;

[0011] Superposition and manipulation of each of the quantum bits are performed through the quantum gate operation;

[0012] Measuring the quantum register after the operation, selecting a target feature according to the collapsed state of the quantum bit, and generating a plurality of different target feature subsets;

[0013] Constructing a decision tree in a random forest according to the selected target feature subset; wherein a different target feature subset is selected in each iteration;

[0014] Integrate the outputs of all the decision trees and determine the final classification result through a voting mechanism;

[0015] The parameter settings of the quantum gate are adjusted according to the classification result to obtain the adjusted parameters of the quantum gate.

[0016] In a specific embodiment, the initialization of the quantum register is expressed as:

[0017]

[0018] In the formula, is the quantum register in the initialized state, n is the number of features, and |0>i indicates that the i-th quantum bit is in the ground state.

[0019] In a specific embodiment, the superposition and manipulation of each of the qubits through the quantum gate operation includes:

[0020] Placing each of the quantum bits in a superposition state by a first quantum gate operation, so that each of the quantum bits simultaneously represents a state where the feature is selected and a state where the feature is not selected;

[0021] The state of each of the qubits is dynamically adjusted through a second quantum gate operation.

[0022] In a specific embodiment, the step of placing each of the quantum positions in a superposition state by operating a first quantum gate comprises:

[0023] The first quantum gate operation places each of the quantum positions in a superposition state by the following formula:

[0024]

[0025] In the formula, represents a quantum gate acting on all said qubits to create a superposition state, is the quantum register state after the operation of the first quantum gate, is the quantum register in the initialized state.

[0026] In a specific embodiment, dynamically adjusting the state of each of the qubits through a second quantum gate operation includes:

[0027] The second quantum gate operation dynamically adjusts the state of each of the quantum bits through the following formula;

[0028]

[0029] Where U(θ,φ) represents the parameterized second quantum gate operation, is the state of the quantum register after the operation of the second quantum gate;

[0030] The calculation method of the second quantum gate operation is expressed as:

[0031]

[0032] In the formula, X and Z represent the Pauli X gate and Pauli Z gate in quantum computing, respectively, and θ and φ are the population and phase of the second quantum gate that can be dynamically adjusted according to the data samples of the smart cockpit system.

[0033] In a specific embodiment, constructing a decision tree in a random forest according to the selected target feature subset includes:

[0034] A decision tree in a random forest is constructed according to the selected target feature subset using the following formula;

[0035] Treeu=BuildTree(D,F(Mu))

[0036] In the formula, Treeu represents a decision tree, D is a data set of data samples of the intelligent cockpit system, and F(Mu) represents a target feature subset selected according to the quantum measurement results;

[0037] Wherein, the quantum measurement result Mu is expressed as:

[0038]

[0039] In the formula, is the state of the quantum register after the second quantum gate operation.

[0040] In a specific embodiment, the calculation method of the target feature subset F(Mu) selected according to the quantum measurement result is expressed as:

[0041]

[0042] In the formula, is the value of the ith bit in the quantum measurement result, when , it means that the i-th feature is selected.

[0043] In a specific embodiment, the parameters of the quantum gate include population and phase, and adjusting the parameter settings of the quantum gate according to the classification result includes:

[0044] Adjust the parameter settings of the quantum gate according to the following formula and the classification result;

[0045] θnew,φnew=Adjust(θ,φ,Feedback(Resultu))

[0046] Wherein, θnew and φnew are the population and phase of the second quantum gate after adjustment, respectively; Resultu represents the final classification result;

[0047] Wherein, the classification result Resultu is expressed as:

[0048]

[0049] Where K represents the number of decision trees. Represents the output of the kth decision tree.

[0050] In a specific embodiment, the parameter adjustment formula of the second quantum gate is expressed as:

[0051]

[0052] In the formula, α is the learning rate, L is the loss function calculated based on the actual classification results, and are the gradients of the loss function with respect to the population θ and the phase φ, respectively.

[0053] In a second aspect, the present invention provides an intelligent cockpit system monitoring device, comprising:

[0054] A data sample acquisition module, used to acquire a smart cockpit system data sample, wherein the smart cockpit system data sample identifies an operating state type of the smart cockpit system;

[0055] A classifier model training module is used to input the smart cockpit system data sample into the classifier model to be trained, so as to iteratively select target features for the smart cockpit system data sample through quantum gate operation, classify the selected target features through a random forest algorithm, and adjust the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate, until a preset iteration stop condition is reached, and a target classifier model is obtained;

[0056] Target data acquisition module, used to collect target intelligent cockpit system data;

[0057] The monitoring result generating module is used to classify the target smart cockpit system data through the target classifier model to obtain the smart cockpit system status monitoring result.

[0058] In a third aspect, the present invention provides a terminal comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the intelligent cockpit system monitoring method as described in the first aspect is implemented.

[0059] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the intelligent cockpit system monitoring method as described in the first aspect.

[0060] Compared with the prior art, the beneficial effect of the present invention is that: the target feature selection of the data sample of the intelligent cockpit system is performed through quantum gate operation, the selected target feature is classified through the random forest algorithm, and the parameters of the quantum gate are adjusted according to the classification results to obtain the adjusted parameters of the quantum gate, until the preset iteration stop condition is reached, the target classifier model is obtained, and the target intelligent cockpit system data is classified through the target classifier model to obtain the intelligent cockpit system status monitoring result. The present invention combines quantum coding technology with the random forest algorithm, takes the random forest algorithm as the basis, adopts the target feature subset selection mechanism represented by quantum bits, utilizes the superposition and entanglement characteristics of quantum bits, and optimizes the target feature selection through quantum gate operation, thereby improving the target feature selection efficiency and classification accuracy of the classifier model, realizing real-time monitoring and predictive maintenance of the status of the intelligent cockpit system, being able to predict faults more accurately, reducing unexpected downtime, and improving the reliability and safety of the system. In addition, the present invention is also highly scalable and can be applied to a variety of scenarios requiring predictive maintenance to optimize the driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a flow chart of a smart cockpit system monitoring method provided by one embodiment of the present invention;

[0062] Figure 2 It is a schematic diagram of the training process of the classifier model provided by one embodiment of the present invention;

[0063] Figure 3 is a structural schematic diagram of an intelligent cockpit system monitoring device provided by one embodiment of the present invention;

[0064] Figure 4 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention.

[0065] in:

[0066] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0067] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0068] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0069] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0070] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0071] See also Figure 1 , Figure 1 It is a flow chart of a smart cockpit system monitoring method provided by one embodiment of the present invention.

[0072] A smart cockpit system monitoring method according to an embodiment of the present invention comprises the following steps:

[0073] S100: Acquire a smart cockpit system data sample, where the smart cockpit system data sample identifies an operating status type of the smart cockpit system.

[0074] The data samples of the smart cockpit system in the embodiment of the present invention are derived from various sensors in the smart cockpit system, such as temperature sensors, humidity sensors, vibration sensors, etc., which are used to monitor the operating status inside the cockpit in real time. All collected data are stored in a structured database and recorded in JSON format.

[0075] In one embodiment, the attributes of the data include:

[0076] Temperature Ta: indicates the temperature inside the cabin, in degrees Celsius (℃);

[0077] Humidity Ha: indicates the relative humidity inside the cabin, in percentage (%);

[0078] Vibration Va: Indicates the vibration intensity inside the cabin, in meters per second (m / s 2 );

[0079] Operation status Oa: indicates the operation status of the cockpit, such as start, run, and stop;

[0080] Maintenance record Ma: means recording cockpit maintenance activities, such as replacement of parts, cleaning, etc.;

[0081] Fault code Fa: indicates the error code when a cockpit system fails;

[0082] Energy consumption Ea: represents the energy consumption of the cabin during operation, in kilowatt-hours (kWh);

[0083] Usage frequency Ua: indicates the frequency at which the cockpit is activated or operated;

[0084] Response time Ra: indicates the time it takes for the system to respond to an operation, in seconds (s);

[0085] Log entry La: represents the detailed entry of the system operation log, recording the time and type of the operation.

[0086] It should be noted that this embodiment is only for illustrating the data format and types of the present invention. In actual applications, the attributes of data are usually more than 10 attributes, and the number of attributes of data may reach dozens or even hundreds.

[0087] Furthermore, the collected data is annotated, and the annotation method of the present invention is manual annotation.

[0088] In one embodiment, the marked categories include: normal state, fault state, unknown state, a total of 3 categories, and the operating state types of the smart cockpit system also include: normal state, fault state, unknown state.

[0089] This embodiment ensures the quality of data and the accuracy of the classifier model through real-time data collection and manual labeling.

[0090] S200, inputting the smart cockpit system data sample into the classifier model to be trained, so as to iteratively select target features of the smart cockpit system data sample through quantum gate operation, classify the selected target features through a random forest algorithm, and adjust the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate, until a preset iteration stop condition is reached, and a target classifier model is obtained.

[0091] The collected data samples of the smart cockpit system are input into the classifier to train the classifier model. The classifier model of the embodiment of the present invention adopts the random forest algorithm as the basis, combined with quantum coding technology to enhance the target feature selection and classification efficiency of the classifier model. Among them, the random forest is an integrated learning model that improves the overall classification accuracy and robustness by constructing multiple decision trees and voting. On this basis, the present invention adopts a target feature subset selection mechanism represented by quantum bits, utilizes the superposition and entanglement characteristics of quantum states, and explores the feature space through quantum gate operations to achieve more efficient target feature subset selection.

[0092] Specifically, the training process of the classifier model based on the quantum coded random forest algorithm is described by the following steps.

[0093] See also Figure 2 , Figure 2 It is a schematic diagram of the training process of the classifier model provided by one embodiment of the present invention.

[0094] In step S200, target features are selected for the smart cockpit system data samples through quantum gate operation, the selected target features are classified through a random forest algorithm, and the parameters of the quantum gate are adjusted according to the classification results to obtain the adjusted parameters of the quantum gate, including the following steps S210 to S260:

[0095] S210, initializing a quantum register; wherein each qubit of the quantum register corresponds to a feature in the data sample feature set of the smart cockpit system.

[0096] In a specific embodiment, the initialization of the quantum register is expressed as:

[0097]

[0098] In the formula, is the quantum register in the initialized state, n is the number of features, and |0>i indicates that the i-th quantum bit is in the ground state.

[0099] S220, superimposing and manipulating each of the quantum bits through the quantum gate operation.

[0100] In this embodiment, the generation of target feature subsets depends on the superposition and manipulation of quantum states. A target feature subset selection mechanism represented by quantum bits is adopted. The superposition and entanglement characteristics of quantum states are utilized to optimize the target feature selection through quantum gate operations to explore the feature space and achieve more efficient target feature subset selection.

[0101] In a specific embodiment, the step S220 performs superposition and manipulation on each of the qubits through the quantum gate operation, including the following steps S221-S222:

[0102] S221. Place each of the quantum bits in a superposition state through a first quantum gate operation, so that each of the quantum bits simultaneously represents a state where the feature is selected and a state where the feature is not selected.

[0103] In this embodiment, a quantum gate is used to put each quantum bit into a superposition state, so that each quantum bit simultaneously represents two states: the feature is selected and the feature is not selected.

[0104] In quantum computing, logic gates are the basic units for implementing quantum computing operations. The quantum gates of this embodiment include but are not limited to Hadamard gates (also known as Hadamard gates).

[0105] In a specific embodiment, the first quantum gate operation places each of the quantum positions in a superposition state by the following formula:

[0106]

[0107] In the formula, represents a quantum gate acting on all said qubits to create a superposition state, is the quantum register state after the operation of the first quantum gate, is the quantum register in the initialized state.

[0108] S222. Dynamically adjust the state of each quantum bit through a second quantum gate operation.

[0109] In this embodiment, the second quantum gate operation includes a parameterized second quantum gate operation.

[0110] Through the parameterized second quantum gate operation, dynamic adjustment of the quantum bit state is achieved, making the target feature selection process more flexible and efficient.

[0111] In a specific embodiment, the second quantum gate operation dynamically adjusts the state of each of the quantum bits by the following formula:

[0112]

[0113] Where U(θ,φ) represents the parameterized second quantum gate operation, is the state of the quantum register after the second quantum gate operation.

[0114] The calculation method of the second quantum gate operation is expressed as:

[0115]

[0116] Wherein, X and Z represent the Pauli-X gate and Pauli-Z gate in quantum computing, respectively, and θ and φ are the population and phase of the second quantum gate that can be dynamically adjusted according to the data sample of the smart cockpit system.

[0117] In this embodiment, the parameterized second quantum gate operation U(θ, φ) depends on the training data of the intelligent cockpit system data sample to adjust the parameters to optimize the target feature selection. Specifically, the parameters of the second quantum gate (population number θ and phase φ) are parameters that are dynamically adjusted according to the intelligent cockpit system data sample to control the process of target feature selection.

[0118] Correspondingly, the second quantum gate operation process is expressed as:

[0119]

[0120] In this way, through the application of a series of control gates and revolving doors, the state of the qubit is dynamically adjusted according to the training data of the intelligent cockpit system data sample, optimizing the process of target feature selection.

[0121] S230, measuring the quantum register after the operation, selecting a target feature according to the collapsed state of the quantum bit, and generating a plurality of different target feature subsets.

[0122] Among them, the quantum measurement result Mu is expressed as:

[0123]

[0124] In the formula, is the state of the quantum register after the second quantum gate operation.

[0125] In this embodiment, the quantum register after the operation is measured, and the quantum measurement result determines the selected target feature subset. Specifically, which target features are selected is determined according to the collapse state of the quantum bit, and multiple different target feature subsets are generated.

[0126] In this way, using quantum measurement results to determine the selection of target feature subsets increases the diversity of the classifier model and helps improve the robustness and generalization ability of the classifier model.

[0127] S240, constructing a decision tree in a random forest according to the selected target feature subset; wherein a different target feature subset is selected in each iteration.

[0128] In this embodiment, the decision tree in the random forest is constructed using the selected target feature subset, and a different target feature subset is selected in each iteration to further increase the diversity of the classifier model.

[0129] In a specific embodiment, the step S240 constructs a decision tree in a random forest according to the selected target feature subset, comprising the following steps:

[0130] A decision tree in a random forest is constructed according to the selected target feature subset using the following formula;

[0131] Treeu=BuildTree(D,F(Mu))

[0132] Wherein, Treeu represents a decision tree, D is a data set of data samples of the intelligent cockpit system, and F(Mu) represents a target feature subset selected according to the quantum measurement results.

[0133] In a specific embodiment, the calculation method of the target feature subset F(Mu) selected according to the quantum measurement result is expressed as:

[0134]

[0135] In the formula, is the value of the ith bit in the quantum measurement result, when , it means that the i-th feature is selected.

[0136] S250, integrating the outputs of all the decision trees and determining the final classification result through a voting mechanism.

[0137] In this embodiment, the classification result Resultu is expressed as:

[0138]

[0139] Where K represents the number of decision trees. Represents the output of the kth decision tree.

[0140] S260, adjusting the parameter settings of the quantum gate according to the classification result to obtain the adjusted parameters of the quantum gate.

[0141] In this embodiment, the parameter settings of the quantum gate are adjusted according to the classification result feedback to further optimize the target feature selection process.

[0142] In a specific embodiment, the parameters of the quantum gate include population and phase, and the step S260 of adjusting the parameter settings of the quantum gate according to the classification result includes the following steps:

[0143] Adjust the parameter settings of the quantum gate according to the following formula and the classification result;

[0144] θnew,φnew=Adjust(θ,φ,Feedback(Resultu))

[0145] Wherein, θnew and φnew are the population number and phase of the second quantum gate after adjustment, respectively; Resultu represents the final classification result.

[0146] In this embodiment, the population number θnew and the phase φnew depend on the feedback of the classification result Resultu.

[0147] In a specific embodiment, the parameter adjustment formula of the second quantum gate is expressed as:

[0148]

[0149] In the formula, α is the learning rate, L is the loss function calculated based on the actual classification results, and are the gradients of the loss function with respect to the population θ and the phase φ, respectively.

[0150] Therefore, the adjusted parameters of the quantum gate are the population number θnew and the phase φnew, which are used to further optimize the process of target feature selection.

[0151] The above steps S210 to S260 are iterated repeatedly until the preset stop iteration condition is met, which means that the classifier model training is completed and the optimal model parameters are obtained, thereby obtaining the target classifier model.

[0152] In a specific embodiment, the preset condition for stopping iteration is that a preset maximum number of iterations is reached or the performance of the classifier model meets the requirements.

[0153] S300. Collect target intelligent cockpit system data.

[0154] The target smart cockpit system data in the embodiment of the present invention is derived from a variety of sensors in the smart cockpit system, such as temperature sensors, humidity sensors, vibration sensors, etc., which are used to monitor the operating status inside the cockpit in real time. It can be understood that the attributes of the smart cockpit system data sample can cover the newly collected target smart cockpit system data, for example, the target smart cockpit system data includes the temperature value inside the cabin, the relative humidity inside the cabin, the vibration intensity inside the cabin, the operating status of the cabin, the maintenance activity record of the cabin, the error code when the cockpit system fails, the arrival time of the data packet, the frequency of the cockpit being activated or operated, the time for the system to respond to the operation, and one or more of the detailed entries of the system operation log.

[0155] S400: classify the target smart cockpit system data by using the target classifier model to obtain a smart cockpit system status monitoring result.

[0156] Use the trained classifier model to process the target smart cockpit system data and obtain the smart cockpit system status monitoring results.

[0157] In one embodiment, the collected raw data is input into the target classifier model for classification, and then the classification results are obtained. The classification categories include: normal state, fault state, unknown state, a total of 3 categories. The intelligent cockpit system status monitoring results include normal state, fault state or unknown state. In this way, real-time monitoring and predictive maintenance of the intelligent cockpit system status are realized, and the reliability and safety of the system are improved.

[0158] In summary, an embodiment of the present invention provides a method for monitoring a smart cockpit system, which selects target features of the smart cockpit system data sample through quantum gate operation, classifies the selected target features through the random forest algorithm, and adjusts the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate until the preset iteration stop condition is reached, and obtains the target classifier model, and classifies the target smart cockpit system data through the target classifier model to obtain the smart cockpit system status monitoring result. The present invention combines quantum coding technology with the random forest algorithm, takes the random forest algorithm as the basis, adopts the target feature subset selection mechanism represented by quantum bits, utilizes the superposition and entanglement characteristics of quantum bits, and optimizes the target feature selection through quantum gate operations, thereby improving the target feature selection efficiency and classification accuracy of the classifier model, realizing real-time monitoring and predictive maintenance of the smart cockpit system status, being able to more accurately predict faults, reduce unexpected downtime, and improve the reliability and safety of the system. In addition, the present invention is also highly scalable and can be applied to a variety of scenarios requiring predictive maintenance to optimize the driving experience.

[0159] See also Figure 3 , Figure 3 It is a structural schematic diagram of an intelligent cockpit system monitoring device provided by one embodiment of the present invention.

[0160] An intelligent cockpit system monitoring device according to an embodiment of the present invention includes:

[0161] A data sample acquisition module, used to acquire a smart cockpit system data sample, wherein the smart cockpit system data sample identifies an operating state type of the smart cockpit system;

[0162] A classifier model training module is used to input the smart cockpit system data sample into the classifier model to be trained, so as to iteratively select target features for the smart cockpit system data sample through quantum gate operation, classify the selected target features through a random forest algorithm, and adjust the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate, until a preset iteration stop condition is reached, and a target classifier model is obtained;

[0163] Target data acquisition module, used to collect target intelligent cockpit system data;

[0164] The monitoring result generating module is used to classify the target smart cockpit system data through the target classifier model to obtain the smart cockpit system status monitoring result.

[0165] In a specific embodiment, the classifier model training module is also used to:

[0166] Initializing a quantum register; wherein each qubit of the quantum register corresponds to a feature in the data sample feature set of the smart cockpit system;

[0167] Superposition and manipulation of each of the quantum bits are performed through the quantum gate operation;

[0168] Measuring the quantum register after the operation, selecting a target feature according to the collapsed state of the quantum bit, and generating a plurality of different target feature subsets;

[0169] Constructing a decision tree in a random forest according to the selected target feature subset; wherein a different target feature subset is selected in each iteration;

[0170] Integrate the outputs of all the decision trees and determine the final classification result through a voting mechanism;

[0171] The parameter settings of the quantum gate are adjusted according to the classification result to obtain the adjusted parameters of the quantum gate.

[0172] An intelligent cockpit system monitoring device provided in an embodiment of the present invention can execute all steps and functions of an intelligent cockpit system monitoring method provided in any of the above embodiments, and the specific functions of the device are not described in detail herein.

[0173] See also Figure 4 , Figure 4 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention.

[0174] The terminal includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned smart cockpit system monitoring method embodiment are implemented, for example: Figure 1 Alternatively, the processor implements the functions of each module in the above-mentioned device embodiments when executing the computer program.

[0175] Exemplarily, the computer program may be divided into one or more modules, and the one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal. For example, the computer program may be divided into several modules, and the specific functions of each module have been described in detail in a smart cockpit system monitoring method provided in any of the above embodiments, and the specific functions of the device will not be repeated here.

[0176] The terminal may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal and does not constitute a limitation on a terminal. The terminal may include more or fewer components than shown in the figure, or may combine certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0177] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal, and uses various interfaces and lines to connect various parts of the entire terminal.

[0178] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the intelligent cockpit system monitoring method by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0179] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned intelligent cockpit system monitoring method is implemented.

[0180] If the terminal integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0181] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for monitoring an intelligent cockpit system, characterized in that: include: Acquire a smart cockpit system data sample, where the smart cockpit system data sample identifies an operating state type of the smart cockpit system; Inputting the smart cockpit system data sample into the classifier model to be trained, so as to iteratively select target features of the smart cockpit system data sample through quantum gate operation, classifying the selected target features through a random forest algorithm, and adjusting the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate, until a preset iteration stop condition is reached, and a target classifier model is obtained; Collect target intelligent cockpit system data; The target intelligent cockpit system data is classified by the target classifier model to obtain the intelligent cockpit system status monitoring result.

2. The intelligent cockpit system monitoring method according to claim 1, characterized in that: The step of selecting target features of the smart cockpit system data sample by quantum gate operation, classifying the selected target features by random forest algorithm, and adjusting the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate includes: Initializing a quantum register; wherein each qubit of the quantum register corresponds to a feature in the data sample feature set of the smart cockpit system; Superposition and manipulation of each of the quantum bits are performed through the quantum gate operation; Measuring the quantum register after the operation, selecting a target feature according to the collapsed state of the quantum bit, and generating a plurality of different target feature subsets; Constructing a decision tree in a random forest according to the selected target feature subset; wherein a different target feature subset is selected in each iteration; Integrate the outputs of all the decision trees and determine the final classification result through a voting mechanism; The parameter settings of the quantum gate are adjusted according to the classification result to obtain the adjusted parameters of the quantum gate.

3. The intelligent cockpit system monitoring method according to claim 2, characterized in that: The initialization of the quantum register is expressed as: In the formula, is the quantum register in the initialized state, n is the number of features, and |0>i indicates that the i-th quantum bit is in the ground state.

4. The intelligent cockpit system monitoring method according to claim 2, characterized in that: The superposition and manipulation of each of the quantum bits through the quantum gate operation includes: Placing each of the quantum bits in a superposition state by a first quantum gate operation, so that each of the quantum bits simultaneously represents a state where the feature is selected and a state where the feature is not selected; The state of each of the qubits is dynamically adjusted through a second quantum gate operation.

5. The intelligent cockpit system monitoring method according to claim 4, characterized in that: The step of placing each of the quantum positions in a superposition state by operating a first quantum gate comprises: The first quantum gate operation places each of the quantum positions in a superposition state by the following formula: In the formula, represents a quantum gate acting on all said qubits to create a superposition state, is the quantum register state after the operation of the first quantum gate, is the quantum register in the initialized state.

6. The intelligent cockpit system monitoring method according to claim 5, characterized in that: The dynamically adjusting the state of each of the quantum bits by operating a second quantum gate comprises: The second quantum gate operation dynamically adjusts the state of each of the quantum bits through the following formula; Where U(θ,φ) represents the parameterized second quantum gate operation, is the state of the quantum register after the operation of the second quantum gate; The calculation method of the second quantum gate operation is expressed as: U(θ,φ)=ei ( θX+φZ) In the formula, X and Z represent the Pauli X gate and Pauli Z gate in quantum computing, respectively, and θ and φ are the population and phase of the second quantum gate that can be dynamically adjusted according to the data samples of the smart cockpit system.

7. The intelligent cockpit system monitoring method according to claim 6, characterized in that: The step of constructing a decision tree in a random forest according to the selected target feature subset includes: A decision tree in a random forest is constructed according to the selected target feature subset using the following formula; Treeu=BuildTree(D,F(Mu)) In the formula, Treeu represents a decision tree, D is a data set of data samples of the intelligent cockpit system, and F(Mu) represents a target feature subset selected according to the quantum measurement results; Wherein, the quantum measurement result Mu is expressed as: In the formula, is the state of the quantum register after the second quantum gate operation.

8. The intelligent cockpit system monitoring method according to claim 7, characterized in that: The calculation method of the target feature subset F(Mu) selected according to the quantum measurement result is expressed as: In the formula, is the value of the ith bit in the quantum measurement result, when , it means that the i-th feature is selected.

9. The intelligent cockpit system monitoring method according to claim 7, characterized in that: The parameters of the quantum gate include population number and phase, and the step of adjusting the parameter setting of the quantum gate according to the classification result includes: Adjust the parameter settings of the quantum gate according to the following formula and the classification result; θnew,φnew=Adjust(θ,φ,Feedback(Resultu)) Wherein, θnew and φnew are the population and phase of the second quantum gate after adjustment, respectively; Resultu represents the final classification result; Wherein, the classification result Resultu is expressed as: Where K represents the number of decision trees. Represents the output of the kth decision tree.

10. The intelligent cockpit system monitoring method according to claim 9, characterized in that: The parameter adjustment formula of the second quantum gate is expressed as: In the formula, α is the learning rate, L is the loss function calculated based on the actual classification results, and are the gradients of the loss function with respect to the population θ and the phase φ, respectively.

11. An intelligent cockpit system monitoring device, characterized in that: include: A data sample acquisition module, used to acquire a smart cockpit system data sample, wherein the smart cockpit system data sample identifies an operating state type of the smart cockpit system; A classifier model training module is used to input the smart cockpit system data sample into the classifier model to be trained, so as to iteratively select target features for the smart cockpit system data sample through quantum gate operation, classify the selected target features through a random forest algorithm, and adjust the parameters of the quantum gate according to the classification results to obtain the adjusted parameters of the quantum gate, until a preset iteration stop condition is reached, and a target classifier model is obtained; Target data acquisition module, used to collect target intelligent cockpit system data; The monitoring result generating module is used to classify the target smart cockpit system data through the target classifier model to obtain the smart cockpit system status monitoring result.

12. The intelligent cockpit system monitoring device according to claim 11, characterized in that: The classifier model training module is used to: Initializing a quantum register; wherein each qubit of the quantum register corresponds to a feature in the data sample feature set of the smart cockpit system; Superposition and manipulation of each of the quantum bits are performed through the quantum gate operation; Measuring the quantum register after the operation, selecting a target feature according to the collapsed state of the quantum bit, and generating a plurality of different target feature subsets; Constructing a decision tree in a random forest according to the selected target feature subset; wherein a different target feature subset is selected in each iteration; Integrate the outputs of all the decision trees and determine the final classification result through a voting mechanism; The parameter settings of the quantum gate are adjusted according to the classification result to obtain the adjusted parameters of the quantum gate.

13. The intelligent cockpit system monitoring device according to claim 12, characterized in that: The initialization of the quantum register is expressed as: In the formula, is the quantum register in the initialized state, n is the number of features, and |0>i indicates that the i-th qubit is in the ground state.

14. A terminal, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the intelligent cockpit system monitoring method as described in any one of claims 1 to 10 when executing the computer program.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the intelligent cockpit system monitoring method according to any one of claims 1 to 10.

Images