Vehicle energy supply strategy processing method and device, equipment and storage medium

Abstract

The invention provides an energy supply strategy processing method and device of a vehicle, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring sensor data of a vehicle driven by a target object, wherein the sensor data comprises vehicle voice data; classifying the energy source of the vehicle based on the vehicle voice to obtain an energy source classification result of the vehicle; and obtaining an energy supply strategy matched with the energy source classification result, and executing a recommendation operation for the energy supply strategy to the target object. Through the method and the device, the energy source type of the vehicle driven by the target object can be automatically identified, and the corresponding energy supply strategy is recommended for the target object, so that the man-machine interaction efficiency is improved.

Description

Technical Field

[0001] The present application relates to computer technology, and in particular to a vehicle energy replenishment strategy processing method, device, equipment and storage medium. Background Art

[0002] For various map applications, recommending geographic coordinate points (Position of Interest, POI) that users may be interested in is not only an important function that can create practical value for users, but also an important source of advertising and other revenue for such applications. Among them, POIs that can meet the energy replenishment needs of motor vehicles are the key development direction of map applications.

[0003] Usually, energy refueling station recommendations such as gas stations and charging stations in map applications are in fixed positions, such as below the search bar, the first or last position in the search bar's more menu, etc., and regardless of whether the energy source of the user's vehicle is fuel, electricity, or a hybrid, the actual location of the fuel station will be displayed in the navigation route display map, and it is impossible to match the recommended strategy of energy refueling stations for users in a targeted manner. Summary of the invention

[0004] The embodiments of the present application provide a vehicle energy replenishment strategy processing method, device, electronic device, computer-readable storage medium and computer program product, which can recommend a corresponding energy replenishment strategy for a target object based on the type of energy source of the vehicle driven by the target object, thereby improving the efficiency of human-computer interaction.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] The present application provides a method for processing a vehicle energy replenishment strategy, the method comprising:

[0007] Acquiring sensor data of a vehicle driven by a target object, wherein the sensor data includes vehicle voice data;

[0008] Classify the energy source of the vehicle based on the vehicle voice data to obtain a classification result of the energy source of the vehicle;

[0009] An energy replenishment strategy matching the energy source classification result is obtained, and a recommended operation for the energy replenishment strategy is performed on the target object.

[0010] The embodiment of the present application provides a vehicle energy replenishment strategy processing device, including:

[0011] An acquisition module, used to acquire sensor data of a vehicle driven by a target object, wherein the sensor data includes vehicle voice data;

[0012] A classification module, used for classifying the energy source of the vehicle based on the vehicle voice data to obtain a classification result of the energy source of the vehicle;

[0013] The recommendation module is used to obtain an energy replenishment strategy that matches the energy source classification result, and perform a recommendation operation for the energy replenishment strategy on the target object.

[0014] An embodiment of the present application provides an electronic device, the electronic device comprising:

[0015] A memory for storing computer executable instructions or computer programs;

[0016] The processor is used to implement the vehicle energy replenishment strategy processing method provided in the embodiment of the present application when executing the computer executable instructions or computer programs stored in the memory.

[0017] An embodiment of the present application provides a computer-readable storage medium storing a computer program or computer-executable instructions. When the computer program or computer-executable instructions are executed by a processor, the vehicle energy replenishment strategy processing method provided in the embodiment of the present application is implemented.

[0018] An embodiment of the present application provides a computer program product, including a computer program or computer executable instructions. When the computer program or computer executable instructions are executed by a processor, the vehicle energy replenishment strategy processing method provided in the embodiment of the present application is implemented.

[0019] The embodiments of the present application have the following beneficial effects:

[0020] By obtaining sensor data of the vehicle driven by the target object, the energy source of the vehicle is classified and processed to determine the energy source of the vehicle driven by the user, and then an energy replenishment strategy corresponding to the energy source is recommended to the user, so that the target object can obtain a suitable energy replenishment plan for the vehicle driven by the target object more quickly, thereby improving the efficiency of the target object in obtaining the energy replenishment strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic diagram of the architecture of the energy replenishment strategy processing system for a vehicle provided in an embodiment of the present application;

[0022] Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0023] Figures 3A-3C It is a flowchart of a method for processing a vehicle energy replenishment strategy provided by an embodiment of the present application;

[0024] Figure 4A-4Eis a schematic diagram of a map application point of interest recommendation provided in an embodiment of the present application;

[0025] Figure 5 It is a flow chart of the vehicle energy replenishment strategy processing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0027] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0028] In the following description, the terms "first\second" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0029] Unless otherwise defined, all technical and scientific terms used in the embodiments of the present application have the same meanings as those commonly understood by those skilled in the art. The terms used in the embodiments of the present application are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0030] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0031] 1) Speech classification task: Speech classification is a basic link in the field of speech processing. In essence, it is to extract features from audio and then determine which category of sound the feature belongs to, such as human voice or animal call.

[0032] 2) Global Navigation Satellite System (GNSS): It is a technology that uses satellites for positioning, navigation and timing. It consists of multiple satellites and can determine the position, speed and time of the receiver by receiving signals from satellites. GNSS systems include the Global Positioning System (GPS), Russia's GLONASS, Europe's Galileo and China's BeiDou. GNSS technology has been widely used in vehicle navigation, ship and aviation navigation, surveying and mapping, agriculture and resource exploration.

[0033] 3) Inertial Measurement Unit (IMU): It is a device that integrates multiple sensors such as accelerometers, gyroscopes and magnetometers. It can determine the motion state of an object in space by measuring information such as the object's linear acceleration, angular velocity and direction angle. IMU is commonly used in aerospace, navigation, motion control and other fields, as well as consumer electronics such as virtual reality, games, and fitness tracking.

[0034] 4) Point of Interest (POI): It is a concept in the field of geographic information system, which refers to geographical objects that can be abstracted as points, especially some geographical entities closely related to people's lives, such as schools, banks, restaurants, gas stations, hospitals, supermarkets, bus stops, etc.

[0035] 5) Wind noise: This refers to the noise generated when the pressure of the oncoming wind exceeds the sealing resistance of the car door when the car is driving at high speed, causing the wind to enter the car. The faster the driving speed, the greater the wind noise.

[0036] 6) Tire noise: refers to the noise generated by the friction between the tires and the road when the vehicle is traveling at high speed. The amount of tire noise is usually related to the road conditions and tire performance. The worse the road conditions, the greater the tire noise.

[0037] Usually, the recommendations for energy refueling stations such as gas stations and charging stations in map applications are in preset fixed positions, such as below the search bar, the first or last position in the search bar's more menu, etc., and no matter whether the energy source of the user's vehicle is fuel, electricity, or a hybrid, the actual locations of all energy refueling stations will be displayed in the navigation route display map, and it is impossible to match the recommendation strategy for the user in a targeted manner. Therefore, when the vehicle driven by the user needs to replenish energy, it must spend more time to find a gas station or charging station that meets the energy replenishment needs, resulting in low energy replenishment efficiency.

[0038] The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium, and computer program product for processing an energy replenishment strategy for a vehicle, which can recommend a corresponding energy replenishment strategy for a target object according to the type of energy source of the vehicle driven by the target object. The exemplary application of the electronic device provided by the embodiments of the present application is described below. The electronic device provided by the embodiments of the present application can be implemented as various types of user terminals such as laptop computers, tablet computers, desktop computers, set-top boxes, mobile devices (e.g., mobile phones, portable music players, personal digital assistants, dedicated messaging devices, portable gaming devices), smart phones, smart speakers, smart watches, smart TVs, and vehicle-mounted terminals, and can also be implemented as servers. Below, exemplary applications when the electronic device is implemented as a terminal or a server will be described.

[0039] See also Figure 1 , Figure 1 It is a schematic diagram of the architecture of the vehicle energy replenishment strategy processing system provided in an embodiment of the present application. To implement an energy replenishment strategy processing application that supports a vehicle, the terminal 500 is connected to the server 200 via the network 300. The network 300 can be a wide area network or a local area network, or a combination of the two.

[0040] Terminal 500 is used to obtain sensor data of the vehicle driven by the target object. Terminal 500 is deployed on the vehicle driven by the target object. Terminal 500 can obtain sensor data collected by sensors on the vehicle through short-range communication. The microphone deployed on the terminal itself can also be used as a sensor to collect voice data. The sensor is then sent to server 200 through network 300, so that server 200 classifies the energy source of the vehicle based on the sensor data, obtains the energy source classification result of the vehicle, and obtains an energy replenishment strategy that matches the energy source classification result. Then server 200 sends recommended information of the energy replenishment strategy to terminal 500 through network 300, so that terminal 500 displays the recommended information of the energy replenishment strategy on display interface 510.

[0041] In some embodiments, the server 200 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. The terminal 500 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a car terminal, etc., but is not limited thereto. The terminal and the server may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0042] See also Figure 2 , Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, Figure 2 The electronic device 400 shown includes: at least one processor 410, a memory 450, at least one network interface 420 and a user interface 430. The various components in the electronic device 400 are coupled together via a bus system 440. It is understood that the bus system 440 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 440 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 440 is not described in detail. Figure 2 Various buses are labeled as bus system 440 .

[0043] The processor 410 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0044] The user interface 430 includes one or more output devices 431 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0045] The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard disk drives, optical disk drives, etc. The memory 450 may optionally include one or more storage devices that are physically remote from the processor 410.

[0046] The memory 450 includes a volatile memory or a non-volatile memory, and may also include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.

[0047] In some embodiments, memory 450 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplarily described below.

[0048] Operating system 451, including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0049] A network communication module 452, used to reach other electronic devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 include: Bluetooth, Wireless Compatibility Certification (WiFi), and Universal Serial Bus (USB), etc.;

[0050] a presentation module 453 for enabling presentation of information via one or more output devices 431 (e.g., display screen, speaker, etc.) associated with the user interface 430 (e.g., a user interface for operating peripherals and displaying content and information);

[0051] The input processing module 454 is used to detect one or more user inputs or interactions from one of the one or more input devices 432 and translate the detected inputs or interactions.

[0052] In some embodiments, the device provided in the embodiments of the present application can be implemented in software. Figure 2 The energy replenishment strategy processing device 455 of the vehicle stored in the memory 450 is shown, which can be software in the form of a program and a plug-in, etc., including the following software modules: an acquisition module 4551, a classification module 4552, and a recommendation module 4553. These modules are logical, so they can be arbitrarily combined or further split according to the functions implemented. The functions of each module will be explained below.

[0053] In other embodiments, the device provided in the embodiments of the present application can be implemented in hardware. As an example, the device provided in the embodiments of the present application can be a processor in the form of a hardware decoding processor, which is programmed to execute the vehicle energy replenishment strategy processing method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor can adopt one or more application specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (Digital Signal Processor, DSP), programmable logic devices (Programmable Logic Device, PLD), complex programmable logic devices (Complex Programmable Logic Device, CPLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other electronic components.

[0054] The energy replenishment strategy processing method for a vehicle provided in an embodiment of the present application will be described in conjunction with an exemplary application and implementation of an electronic device provided in an embodiment of the present application.

[0055] The following describes the vehicle energy replenishment strategy processing method provided by the embodiment of the present application. As mentioned above, the electronic device that implements the vehicle energy replenishment strategy processing method of the embodiment of the present application can be a terminal, a server, or a combination of the two. Therefore, the execution subject of each step will not be repeated below.

[0056] See also Figure 3A , Figure 3A is a flow chart of a method for processing a vehicle energy replenishment strategy provided by an embodiment of the present application, which will be combined with Figure 3A The steps shown are explained.

[0057] In step 101, sensor data of a vehicle driven by a target object is obtained.

[0058] In some embodiments, the sensor data includes vehicle voice data, which can be collected by all sensors that can collect sound data, such as microphones, such as capacitive sensors for low-frequency signal collection, piezoresistive sensors for environmental noise detection, pyroelectric sensors that use the effect of sound waves on heat to generate electrical signals, etc. The sensor data also includes at least one of vehicle speed data, vehicle amplitude data, and vehicle air pressure change amplitude data. The vehicle speed data can be obtained directly through a speed sensor or through GNSS, and then the vehicle speed data is sent to the terminal; the vehicle amplitude data is obtained through a vibration sensor; and the vehicle air pressure change amplitude data is obtained through a pressure sensor. In addition, the sensor data can also include data obtained by magnetic, gravity, optical and other sensors.

[0059] It should be noted that the above-mentioned sensors can be installed in terminal devices such as mobile phones and vehicle-mounted terminals, and can also be installed in other parts of the vehicle driven by the target object.

[0060] In some embodiments, the vehicles driven by the target object include motor vehicles that use fuel such as gasoline and diesel as energy sources, motor vehicles that use electricity as energy sources, and motor vehicles that use fuel and electricity as mixed energy sources; motor vehicles include motorcycles, cars, trailers, etc.

[0061] In an embodiment of the present application, the energy source of the vehicle driven by the target object is classified based on the sensor data obtained by one or more sensors mentioned above, which can make the classification result more accurate.

[0062] In step 102, the energy source of the vehicle is classified based on the vehicle voice data to obtain a classification result of the energy source of the vehicle.

[0063] In some embodiments, see Figure 3B , Figure 3B is a flow chart of a method for processing a vehicle energy replenishment strategy provided in an embodiment of the present application, Figure 3A Step 102 shown in FIG. 1 can be performed by Figure 3B Steps 1021 to 1022 in are implemented, and are described in detail below.

[0064] In step 1021, a speech classification model is called to classify the vehicle speech data to obtain a first probability that the vehicle speech data includes vehicle engine noise.

[0065] In some embodiments, the speech classification model includes a convolutional neural network and a time series neural network, the convolutional neural network includes a convolutional layer, a pooling layer and a hidden layer, and the speech classification model is called to perform classification processing on the vehicle voice data to obtain a first probability that the vehicle voice data includes vehicle engine noise. This can be specifically achieved in the following way: obtaining a speech feature signal corresponding to the vehicle voice data, wherein the vehicle voice data includes N frames of voice data, the speech feature signal includes N signal features, each signal feature corresponds to one frame of voice data, and N is an integer greater than or equal to 1; calling the convolutional neural network to perform convolution processing on the speech feature signal to obtain a target feature vector; calling the time series neural network to perform probability mapping processing on the target feature vector to obtain a first probability that the vehicle voice data includes vehicle engine noise.

[0066] Specifically, the speech classification model includes two parts: a convolutional neural network and a time series neural network. The convolutional neural network is a feedforward neural network. The convolutional neural network includes a convolutional layer, a pooling layer, and a hidden layer. The convolutional layer can be used to extract features, the pooling layer can be used to select features, and the hidden layer can be used to output feature vectors. The convolutional neural network includes at least one convolutional network, each of which includes a convolutional layer and a pooling layer. After obtaining N signal features, a central frame is taken out, that is, the signal feature at the tth moment. Considering the content relevance, it is necessary to expand L frames to the left and R frames to the right. Then the input feature sequence is [X t -L,X t ,X t+R], that is, each input is a number of signal features among N signal features, and finally, a target feature vector is output through the hidden layer. Then, the target feature vector is input into the time series neural network in chronological order, and then the output of the feature vector corresponding to each frame of speech data is used as the input of the next frame. Finally, the feature vector corresponding to the last frame of speech data is output as the input of the fully connected layer, and after softmax, a first probability in the range of [-1,1] is output.

[0067] It can be understood that the larger the first probability is, the greater the possibility that the vehicle voice data includes the vehicle engine noise. When the first probability is 1, it can be considered that the vehicle voice data must include the vehicle engine noise. When the first probability is 0, it can be considered that the vehicle voice data must not include the vehicle engine noise.

[0068] It should be noted that in addition to the network structure that combines CNN and LSTM, the speech classification model can also use only CNN network structure or LSTM network structure, or use support vector machine (SVM), decision tree, hidden Markov, Gaussian mixture, perceptron, RNN, Transformer and other neural network models, without limitation here.

[0069] In the embodiments of the present application, any one of the multiple neural network models is used as a speech classification model for classification processing, which can make the application scope of the present application wider and the usage method more convenient.

[0070] In step 1022, the energy source of the vehicle is classified based on the first probability to obtain a classification result of the energy source of the vehicle.

[0071] As an example, when the first probability is not less than the second probability threshold, the energy source classification result of the vehicle is determined to be fuel; when the first probability is not greater than the first probability threshold, the energy source classification result of the vehicle is determined to be electricity; when the first probability is less than the second probability threshold and greater than the first probability threshold, the energy source classification result of the vehicle is determined to be a hybrid of oil and electricity; wherein the second probability threshold is greater than the first probability threshold.

[0072] In an embodiment of the present application, the energy source of the vehicle is classified and processed only through the vehicle voice data obtained by the sensor to obtain the energy source classification result of the vehicle. This can effectively reduce the difficulty of obtaining data and reduce the amount of calculation during data processing, so as to more efficiently obtain the energy source classification result of the vehicle.

[0073] In some embodiments, see Figure 3C , Figure 3Cis a flow chart of a method for processing a vehicle energy replenishment strategy provided in an embodiment of the present application, Figure 3B Step 1022 shown in FIG. 1 may be performed by Figure 3C Steps 10221 to 10222 in are implemented, and are described in detail below.

[0074] In step 10221, a first mapping process is performed on the vehicle motion data to obtain the environmental noise of the vehicle.

[0075] In some embodiments, the sensor data also includes vehicle motion data, and the vehicle motion data includes at least one of the vehicle driving speed, the vehicle amplitude, and the vehicle air pressure change amplitude. When the vehicle motion data includes the vehicle driving speed, the first wind noise positively correlated with the vehicle driving speed is obtained; when the vehicle motion data includes the vehicle amplitude, the tire noise positively correlated with the vehicle amplitude is obtained; when the vehicle motion data includes the vehicle air pressure change amplitude, the second wind noise positively correlated with the vehicle air pressure change amplitude is obtained; and at least one of the first wind noise, the second wind noise, and the tire noise is used as the environmental noise of the vehicle.

[0076] It is understandable that the greater the vehicle's driving speed, the greater the vehicle's wind resistance, and the greater the first wind noise generated. The vehicle amplitude refers to the overall vibration amplitude of the vehicle body, or the shaking amplitude of the vehicle body, such as the body amplitude generated by the steady and regular shaking of the engine of a fuel vehicle when running, or the body amplitude generated when the vehicle is driving on an uneven and undulating road surface, etc. Since the vehicle will generate a large tire noise when driving on such a road surface, it can be considered that the vehicle amplitude is positively correlated with the tire noise of the vehicle. The vehicle air pressure change amplitude refers to the change amplitude of the air pressure in the vehicle's cab. When the vehicle's windows are in the open state, the change amplitude of the air pressure in the vehicle's cab is large, and the greater the change amplitude of the air pressure in the vehicle's cab, the greater the wind noise generated in the cab, so the air pressure change amplitude in the vehicle's cab is positively correlated with the second wind noise.

[0077] Specifically, the relationship between the vehicle speed and the first wind noise, the vehicle amplitude and the tire noise, and the air pressure change amplitude and the second wind noise can be represented by a positive correlation function or a pre-trained neural network model, which is not specifically limited here. The vehicle's environmental noise can include at least one of the first wind noise, the second wind noise and the tire noise, and can also include noise related to the vehicle driven by the target object obtained by other sensors.

[0078] In the embodiment of the present application, the wind noise is determined by the vehicle's driving speed and the amplitude of the vehicle's air pressure change, and the tire noise is determined by the vehicle's amplitude to obtain the vehicle's environmental noise. This can make the range of the vehicle's environmental noise sources wider, thereby minimizing the interference of environmental noise on engine noise during subsequent noise reduction.

[0079] In step 10222, the first probability is corrected based on the environmental noise of the vehicle to obtain an energy source classification result of the vehicle.

[0080] In some embodiments, step 10222 can be implemented in the following manner: adjust the first probability based on the ambient noise of the vehicle to obtain a second probability that the vehicle voice data includes the vehicle engine noise; when the second probability is not less than the second probability threshold, determine that the energy source classification result of the vehicle is fuel; when the second probability is not greater than the first probability threshold, determine that the energy source classification result of the vehicle is electricity; when the second probability is less than the second probability threshold and greater than the first probability threshold, determine that the energy source classification result of the vehicle is a hybrid of oil and electricity; wherein the second probability threshold is greater than the first probability threshold.

[0081] In an embodiment of the present application, the second probability obtained by adjusting the first probability is compared with the first probability threshold and the second probability threshold to determine the energy source classification result of the vehicle, which can make the classification result more accurate.

[0082] Specifically, adjusting the first probability based on the ambient noise of the vehicle to obtain a second probability that the vehicle voice data includes the vehicle engine noise can be achieved in the following manner: extracting environmental features from the ambient noise, and extracting engine features from the first probability; fusing the environmental features and the engine features to obtain fused features; and fully connecting the fused features to obtain the second probability that the vehicle voice data includes the vehicle engine noise.

[0083] As an example, the above-mentioned process of obtaining the second probability is implemented through a neural network, and the training method of the neural network model includes: obtaining a training sample set, the training sample set including multiple sample first probabilities and sample environmental noises, inputting the sample first probabilities and the sample environmental noises into a pre-trained neural network model, and obtaining a model prediction result of the second probability, determining a loss function value based on the label data in the training sample set and the model prediction result, performing backpropagation in the model based on the loss function value to update the model parameters of the pre-trained neural network model, and performing the next round of iterative updates based on the updated model to train and obtain the final neural network model, wherein the neural network includes a convolutional layer for extracting features, a pooling layer for feature fusion, and a fully connected layer for probability mapping.

[0084] Under normal circumstances, since pure fuel vehicles and hybrid vehicles are fully or partially powered by the engine during normal driving, even if there are many ways to reduce the noise generated by the engine when the car is manufactured, the engine noise cannot be completely shielded, so there will be engine noise when the vehicle is started or running normally; while pure electric vehicles are fully powered by batteries, and there is no engine inside the vehicle, so there is no engine noise at all when the vehicle is started or running; in addition, since the engine in the hybrid vehicle only provides partial power, the engine noise generated during operation is less than that of pure fuel vehicles. Therefore, when the second probability that the vehicle voice data includes the vehicle engine noise is greater than or equal to the second probability threshold, it means that the vehicle voice data is very likely to contain engine noise, and the energy source classification result of the vehicle is fuel; when the second probability is less than or equal to the first probability threshold, it means that the vehicle voice data is very likely not to contain engine noise, and the energy source classification result of the vehicle is electric energy. When the second probability is greater than the first probability threshold and less than the second probability threshold, the energy source classification result of the vehicle is hybrid.

[0085] For example, when the first probability threshold is 0.2 and the second probability threshold is 0.8, when the second probability that the vehicle voice data includes vehicle engine noise is greater than or equal to 0.8, the vehicle's energy source classification result is considered to be fuel; when the second probability is less than or equal to 0.2, the vehicle's energy source classification result is considered to be electrical energy; when the second probability is greater than 0.2 and less than 0.8, the vehicle's energy source classification result is considered to be a hybrid.

[0086] In some embodiments, adjusting the first probability based on the vehicle's environmental noise is to perform noise reduction processing on the vehicle voice data, that is, to remove the influence of tire noise, first wind noise and second wind noise contained in the vehicle voice data. Therefore, in addition to the above-mentioned adjustment method, the pre-processed sensor data can also be directly subjected to noise reduction processing by noise reduction methods such as linear filters, spectral subtraction, and subspace algorithms, and then the noise-reduced vehicle voice data is processed based on the voice classification model to obtain the first probability, thereby directly comparing the first probability with the first probability threshold and the second probability threshold to determine the vehicle energy source classification result, without modifying the first probability to obtain the second probability.

[0087] In some embodiments, the energy source of the vehicle is classified based on the vehicle voice data to obtain the energy source classification result of the vehicle, which can be achieved in the following way: the vehicle motion data is sequentially subjected to timestamp alignment, segmentation, normalization and filtering to obtain preprocessed vehicle motion data; the energy source of the vehicle is classified based on the preprocessed vehicle motion data and the vehicle voice data to obtain the energy source classification result of the vehicle. The process of classifying the energy source of the vehicle based on the preprocessed vehicle motion data and the vehicle voice data here can refer to the specific implementation of step 1022, the only difference being that the vehicle motion data used in the embodiment of the present application is obtained after preprocessing.

[0088] It should be noted that when there are multiple sensors for acquiring sensor data, each sensor has its own internal clock. However, due to the different clock drift of each internal clock, there is a time difference between the internal clocks. Therefore, it is necessary to unify the time source of each sensor. Here, the clock source can be unified through hardware, for example, a pulse generator is set between multiple sensors, and all sensors are triggered by this pulse. Each trigger corrects its own clock once, thereby eliminating the cumulative error of the clock source. Then the sensor data is segmented, that is, the sensor data is converted into discrete data, for example, the sensor data is segmented into the smallest unit data that can be analyzed and processed in units of 0.1s or 0.01s. Finally, the sensor data is normalized and filtered. Normalization is to map the sensor data to the range of 0-1, so that the machine learning model can converge faster when processing data; data filtering is data smoothing processing, for example, an arithmetic average algorithm can be used to reduce the influence of interference signals contained in the sensor data.

[0089] In an embodiment of the present application, the energy source of the vehicle is classified based on the pre-processed vehicle motion data and vehicle voice data, which can effectively reduce the interference of noise such as wind noise and tire noise on engine noise, thereby making the classification result of the vehicle's energy source more accurate.

[0090] Continue to see Figure 3A In step 103, an energy replenishment strategy matching the energy source classification result is obtained, and a recommended operation for the energy replenishment strategy is performed on the target object.

[0091] In some embodiments, obtaining an energy replenishment strategy that matches the energy source classification result can be achieved in the following ways: when the energy source classification result of the vehicle is electric energy, an energy replenishment strategy is generated based on electric energy supply stations within a preset range of the target object; when the energy source classification result of the vehicle is fuel, an energy replenishment strategy is generated based on gas stations within a preset range of the target object; when the energy source classification result of the vehicle is a hybrid, electric energy supply stations and gas stations within the preset range of the target object are obtained as the energy replenishment strategy.

[0092] In the embodiment of the present application, by using an electric energy recharge station or a gas station within a preset range of the target object as an energy recharge strategy, the recharge strategy can be made to better meet the energy recharge needs of the target object.

[0093] Specifically, generating an energy replenishment strategy based on electric energy supply stations within a preset range of a target object can be achieved in the following manner: obtaining a first confidence level that the energy source classification result is electric energy, and determining a first target number of gas stations within a preset range based on the first confidence level, wherein the first target number is negatively correlated with the first confidence level; and using the electric energy supply stations within the preset range of the target object and the first target number of gas stations as the energy supply strategy.

[0094] When the energy source classification result of the vehicle is determined to be electric energy by comparing the above second probability with the first probability threshold and the second probability threshold, there will be certain errors in the energy source classification result due to differences in configuration of vehicles driven by different target objects, differences in driving habits, etc. Therefore, it is necessary to obtain the first confidence that the energy source classification result is electric energy. The higher the first confidence, the fewer gas stations recommended for the target object. The first confidence is negatively correlated with the first probability, and the first confidence is also negatively correlated with the second probability. The preset range refers to a circular range with the vehicle driven by the target object as the center and a preset length as the radius, or refers to the range displayed by the map application on the terminal display interface. Electric energy supply stations include charging piles, charging stations, and battery swap stations.

[0095] For example, when the first confidence level is 0.8, and there are 5 gas stations and 10 electric energy supply stations within the preset range, the first target number is 1, and the 10 electric energy supply stations and 1 gas station within the preset range are recommended to the terminal device of the target object as the energy supply strategy. The first target number of gas stations can be selected arbitrarily from the gas stations within the preset range, or the distances between the gas stations within the preset range and the target object's driving vehicle can be sorted in ascending order, and the first target number of gas stations can be selected from the head of the sorting result, that is, the first target number of gas stations closest to the target object's driving vehicle are selected.

[0096] In the embodiment of the present application, the number of first trusted gas stations can make the energy replenishment strategy determined based on the energy source classification result of the vehicle more reasonable and humane, so as to avoid the impact on the energy replenishment strategy when the classification result is wrong in a few cases.

[0097] In some embodiments, see Figure 4D , Figure 4D This is a schematic diagram of the map application point of interest recommendation provided in an embodiment of the present application. The electric energy supply stations within a preset range of the target object and the first target number of gas stations are used as energy supply strategies, and after being recommended to the map application of the target object, they will be displayed in the map application of the target object. For example, the electric energy supply stations within the preset range include charging station A and charging station B, and the gas stations include gas station C.

[0098] In some embodiments, generating an energy replenishment strategy based on gas stations within a preset range of a target object can be achieved in the following manner: obtaining a second confidence level that the energy source classification result is fuel, and determining a second target number of electric energy supply stations within the preset range based on the second confidence level, wherein the second target number is negatively correlated with the second confidence level; and using the gas stations within the preset range of the target object and the second target number of electric energy supply stations as the energy replenishment strategy.

[0099] After determining that the energy source classification result of the vehicle is fuel by comparing the above-mentioned second probability with the first probability threshold and the second probability threshold, it is necessary to obtain the second confidence that the energy source classification result is fuel. The higher the second confidence, the fewer the number of electric energy supply stations recommended for the target object. The second confidence is positively correlated with the first probability, and the second confidence is also positively correlated with the second probability.

[0100] For example, when the second confidence level is 0.8, and there are 10 gas stations and 5 electric energy recharge stations within the preset range, the second target number is 1, and the 10 gas stations and 1 electric energy recharge station within the preset range are recommended to the terminal device of the target object as the energy recharge strategy. The second target number of electric energy recharge stations can be selected arbitrarily from the electric energy recharge stations within the preset range, or the distances between the electric energy recharge stations within the preset range and the target object's driving vehicle can be sorted in ascending order, and the second target number of electric energy recharge stations are selected from the head of the sorting result, that is, the second target number of electric energy recharge stations closest to the target object's driving vehicle are selected.

[0101] In an embodiment of the present application, by determining the number of electric energy replenishment stations through the second confidence level, the energy replenishment strategy determined based on the energy source classification result of the vehicle can be more reasonable and humane, so as to avoid the impact on the energy replenishment strategy when the classification result is wrong in a few cases.

[0102] It should be noted that, in addition to recommending gas stations or electric energy supply stations within a preset range to the target object, the energy supply strategy can also recommend different map application display strategies to the target object's terminal. Figure 4A , Figure 4A is a schematic diagram of a map application point of interest recommendation provided in an embodiment of the present application, such as Figure 4A As shown, usually, after clicking the search box of the map application, different points of interest will be recommended below the search box, such as food, hotels, attraction tickets, gas stations, etc. When you click the More button, the map application will display more categories of points of interest, such as Figure 4B As shown, Figure 4B is a schematic diagram of a map application POI recommendation provided in an embodiment of the present application, for example, the travel category includes gas stations, bus stations, train stations, etc., the play category includes cinemas, swimming pools, etc., or Figure 4C As shown, Figure 4C It is a schematic diagram of the recommended points of interest of the map application provided in an embodiment of the present application. When the target object clicks the search box of the map application, multiple points of interest such as refueling, charging, food, and hotels will be displayed below the search box.

[0103] In the embodiment of the present application, when the energy source classification result is fuel, the energy replenishment strategy includes displaying the point of interest "gas station" in the map application at the front position of all points of interest, for example, Figure 4A The location of "food" in the display "gas station" point of interest, or in Figure 4B The first location under the travel category shows the point of interest for "gas station", or Figure 4C The first position below the search box shows the point of interest for "gas station".

[0104] See also Figure 4E , is a schematic diagram of the recommended points of interest in the map application provided in an embodiment of the present application. When the target object clicks the point of interest "gas station" or searches for "gas station" in the search box, the map application will display the multiple gas stations included in the above energy replenishment strategy in the display interface according to certain sorting rules. The sorting rules here include sorting from near to far according to the distance to the target object, and sorting from low to high according to the oil price, etc.

[0105] Similarly, when the energy source classification result is electric energy, the energy replenishment strategy includes displaying the point of interest "charging station" in the map application at the front position of all points of interest, for example, Figure 4A Display the "charging station" point of interest at the "food" location in the Figure 4B The first location under the travel category of the display "Charging station" point of interest, or Figure 4C The first position below the search box shows the point of interest for "charging station".

[0106] When the energy source classification result is oil-electric hybrid, the energy supply strategy includes displaying the "charging station" and "gas station" points of interest in the map application at the front position of all points of interest, such as Figure 4A , and then display the points of interest of "charging station" and "gas station" in the "food" and "hotel" locations respectively, or in Figure 4B The first and second locations under the travel category of the display the points of interest of "charging station" and "gas station" respectively, or Figure 4C The first and second positions below the search box show the points of interest of “charging station” and “gas station” respectively.

[0107] By displaying points of interest related to energy replenishment strategies at the front of the map application, the target object can obtain the target energy replenishment location more quickly when using the map application to search for energy replenishment strategies.

[0108] The following is an explanation of an exemplary application of the embodiments of the present application in a practical application scenario.

[0109] For various map applications, recommending geographic coordinate points that users may be interested in is not only an important function that can create practical value for users, but also an important source of advertising and other revenue for such applications. Among them, POIs that can meet the energy replenishment needs of motor vehicles are the focus of map applications.

[0110] Usually, the gas station and charging station recommendations in map applications are in preset fixed positions, such as below the search bar, the first or last position in the search bar's more menu, etc., and regardless of whether the energy source of the user's vehicle is fuel or electricity, the actual locations of all gas stations and charging stations will be displayed in the navigation route display map, and it is impossible to match the recommendation strategy for the user in a targeted manner. Therefore, when the vehicle driven by the user needs to replenish energy, it must spend more time to find a gas station or charging station that meets the energy replenishment needs.

[0111] In response to the above problems, an embodiment of the present application provides a vehicle energy replenishment strategy processing method, which collects data such as noise generated during the operation of the vehicle through sensors in devices such as mobile phones or vehicle-mounted terminals, and then identifies and classifies the collected data based on preset judgment rules or neural network models, thereby realizing the judgment of the vehicle's energy source type through limited information, such as fuel, pure electric energy, hybrid, etc., and recommends suitable energy replenishment solutions to users through user-accessible components such as the screen or speaker of the mobile phone or vehicle-mounted terminal. For example, for users of fuel vehicles, only gas stations are recommended to them, and for users of pure electric vehicles, only charging stations are recommended to them, etc., so that users can find suitable energy replenishment locations more quickly through map applications.

[0112] See also Figure 5 , Figure 5 It is a flow chart of the energy replenishment strategy processing method for a vehicle provided in an embodiment of the present application. The motion data in the figure is the motion data of the vehicle, which mainly includes the vehicle speed obtained by GNSS and the vehicle vibration obtained by IMU. The main reason for collecting the vehicle's motion data is that the quality of the data received by the microphone may be different under different vehicle motion states. For example, when the vehicle speed is high, the wind noise may be too large. When the vehicle vibration amplitude is large, it may indicate that the vehicle is passing through a gravel road or a road with poor road conditions. At this time, there will be serious tire noise. Therefore, it is necessary to collect the vehicle's driving speed and vehicle vibration conditions for motion state analysis, so as to calculate the wind noise and tire noise of the vehicle.

[0113] The main function of the air pressure sensor is to analyze the airtight condition, that is, to determine whether the vehicle window is open. When the vehicle window is open, the air pressure in the vehicle cab often changes dramatically, and the air pressure increases with the increase of vehicle speed. When the window is open, there is often a lot of noise in the car, which will also affect the quality of the data received by the microphone.

[0114] The main function of the speech classification model is to identify whether the digital speech signal collected by the microphone contains engine noise. Generally speaking, the characteristics of engine noise are often more obvious, and humans can distinguish them with certain driving experience. This is also the factual basis for identifying vehicle engine noise through algorithms. In addition, due to cost and technology constraints, the engine noise of the vehicle is often difficult to be completely shielded, and it has long been one of the main sources of noise in the cockpit, so there is basically no problem that the engine noise cannot be collected in the cockpit or recorded by the on-board terminal. There is no restriction on the specific type of speech classification model here. Statistical models (such as SVM, decision tree, hidden Markov, Gaussian mixture, etc.) or neural network-based weight models (perceptron, RNN, Transformer, etc.) can achieve this purpose, so I will not go into details here.

[0115] The data obtained by each sensor here needs to be timestamped first to solve the delay time difference problem of different sensors or the problem of different time formats; since the sensor obtains continuous data, the data needs to be segmented into the smallest unit that can be analyzed, so the data needs to be segmented again to obtain discrete data, such as data within 0.01s or 0.1s; then the data is normalized and filtered to filter out high-frequency or low-frequency data in the data wave, or filter out human voice data, so as to improve the effectiveness and generalization ability of the model based on consistent and clean data.

[0116] It should be noted that the data from different sensors can be processed uniformly or separately. Usually, tight coupling will process the data uniformly, while loose coupling will process the data separately.

[0117] In addition, the motion state analysis module and the airtightness analysis module can generate outputs according to preset rules. For example, when the acceleration is greater than a preset value or the gyroscope inclination angle is greater than a preset value, the vehicle is judged to be in an accelerating state; when the air pressure in the vehicle is greater than a preset value, the vehicle is judged to be in a window-closed state; or a label or a feature representation can be output through a machine learning model.

[0118] Then, the speed information output by the motion state analysis module, the air pressure change value or air pressure value output by the closed condition analysis module, the engine noise value or the probability of noise existence output by the speech classification model and other information are summarized into the state judgment rule module. The state judgment rule module combines a single or a group of previous analysis results and gives a label according to preset rules (for example, the recognition result of the speech classification model when the window is closed and the state is stationary has a higher weight among multiple analysis results) or the state judgment algorithm. The content of this label is the vehicle energy information, that is, the energy source of the vehicle is gasoline, pure electric or hybrid, etc.

[0119] Finally, based on the vehicle energy information, a suitable energy replenishment plan is recommended to the car owner. For example, when it is determined that the vehicle's energy source is fuel, the click entrance of the gas station is displayed at the front of the menu bar in the map application, and the click entrance of the charging station is set at the back of the menu. Or, when the car owner uses the map application for navigation, only the POI of the gas station is displayed during the navigation, and the charging station is not displayed, so that users can more conveniently perform the operations they want to complete.

[0120] In addition, since users generally do not frequently change the vehicles they drive, nor do they frequently change terminal devices such as mobile phones, it can be considered that the terminal and the vehicle have an almost fixed correspondence for a considerable period of time. Therefore, the judgment results of the vehicle's energy source and the software strategy can also be persistently stored locally on the terminal and continued to be used when the subsequent software is enabled. Through local storage and quick call at the next startup, the correct recommendation information can be given before the user starts the vehicle. At the same time, it can also reduce the operating frequency of the services involved in the system, thereby saving the performance consumption of the terminal itself or the server.

[0121] The method provided in the embodiment of the present application classifies the energy source of the vehicle through the acquired sensor data to determine the energy source of the vehicle driven by the user, and then recommends a corresponding energy replenishment strategy to the user, so that the user can find a suitable energy replenishment plan more quickly through the map application, thereby improving the efficiency of the user in obtaining energy replenishment strategies when using the map application.

[0122] It is understandable that in the embodiments of the present application, related data such as user information is involved. When the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0123] The following is a description of an exemplary structure of the vehicle energy replenishment strategy processing device 455 provided in the embodiment of the present application implemented as a software module. In some embodiments, Figure 2 As shown, the software modules stored in the vehicle energy replenishment strategy processing device 455 of the memory 440 may include:

[0124] An acquisition module 4551 is used to acquire sensor data of a vehicle driven by a target object, wherein the sensor data includes vehicle voice data; a classification module 4552 is used to classify an energy source of the vehicle based on the vehicle voice data to obtain a classification result of the energy source of the vehicle; a recommendation module 4553 is used to acquire an energy replenishment strategy that matches the energy source classification result, and execute a recommendation operation on the energy replenishment strategy to the target object.

[0125] In some embodiments, the classification module 4552 is also used to call the voice classification model to classify the vehicle voice data to obtain a first probability that the vehicle voice data includes vehicle engine noise; and classify the energy source of the vehicle based on the first probability to obtain a classification result of the energy source of the vehicle.

[0126] In some embodiments, the classification module 4552 is also used to obtain a voice feature signal corresponding to the vehicle voice data, wherein the vehicle voice data includes N frames of voice data, and the voice feature signal includes N signal features, each signal feature corresponds to one frame of voice data, and N is an integer greater than or equal to 1; calling the convolutional neural network to perform convolution processing on the voice feature signal to obtain a target feature vector; calling the time series neural network to perform probability mapping processing on the target feature vector to obtain a first probability that the vehicle voice data includes vehicle engine noise.

[0127] In some embodiments, the classification module 4552 is also used to perform a first mapping process on the vehicle motion data to obtain the environmental noise of the vehicle; and to correct the first probability based on the environmental noise of the vehicle to obtain a classification result of the energy source of the vehicle.

[0128] In some embodiments, the classification module 4552 is further used to obtain a first wind noise that is positively correlated with the vehicle speed when the vehicle motion data includes the vehicle speed; to obtain a tire noise that is positively correlated with the vehicle amplitude when the vehicle motion data includes the vehicle amplitude; to obtain a second wind noise that is positively correlated with the vehicle pressure change amplitude when the vehicle motion data includes the vehicle air pressure change amplitude; and to use at least one of the first wind noise, the second wind noise and the tire noise as the environmental noise of the vehicle.

[0129] In some embodiments, the classification module 4552 is also used to determine that the energy source classification result of the vehicle is fuel when the second probability is not less than a second probability threshold; when the second probability is not greater than the first probability threshold, determine that the energy source classification result of the vehicle is electricity; when the second probability is less than the second probability threshold and greater than the first probability threshold, determine that the energy source classification result of the vehicle is a hybrid of oil and electricity; wherein the second probability threshold is greater than the first probability threshold.

[0130] In some embodiments, the classification module 4552 is also used to extract environmental features from the environmental noise and extract engine features from the first probability; fuse the environmental features and the engine features to obtain fused features; and fully connect the fused features to obtain a second probability that the vehicle voice data includes the vehicle engine noise.

[0131] In some embodiments, the classification module 4552 is also used to perform timestamp alignment processing, segmentation processing, normalization and filtering processing on the vehicle motion data in sequence to obtain preprocessed vehicle motion data; based on the preprocessed vehicle motion data and the vehicle voice data, the energy source of the vehicle is classified to obtain the energy source classification result of the vehicle.

[0132] In some embodiments, the recommendation module 4553 is also used to generate the energy supply strategy based on the electric energy supply stations within a preset range of the target object when the energy source classification result of the vehicle is electric energy; to generate the energy supply strategy based on the gas stations within a preset range of the target object when the energy source classification result of the vehicle is fuel; and to obtain the electric energy supply stations and gas stations within the preset range of the target object as the energy supply strategy when the energy source classification result of the vehicle is oil-electric hybrid.

[0133] In some embodiments, the recommendation module 4553 is also used to obtain a first confidence level that the energy source classification result is electric energy, and determine a first target number of gas stations within the preset range based on the first confidence level, wherein the first target number is negatively correlated with the first confidence level; and use the electric energy supply stations within the preset range of the target object and the first target number of gas stations as the energy supply strategy.

[0134] In some embodiments, the recommendation module 4553 is also used to obtain a second confidence level that the energy source classification result is fuel, and determine a second target number of electric energy supply stations within the preset range based on the second confidence level, wherein the second target number is negatively correlated with the second confidence level; and use the gas stations within the preset range of the target object and the second target number of electric energy supply stations as the energy supply strategy.

[0135] It is understandable that in the embodiments of the present application, related data such as user information is involved. When the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0136] The embodiment of the present application provides a computer program product, which includes a computer program or a computer executable instruction, and the computer program or the computer executable instruction is stored in a computer-readable storage medium. The processor of the electronic device reads the computer executable instruction from the computer-readable storage medium, and the processor executes the computer executable instruction, so that the electronic device executes the vehicle energy replenishment strategy processing method described in the embodiment of the present application.

[0137] The embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions or computer programs are stored. When the computer-executable instructions or computer programs are executed by a processor, the processor will execute the vehicle energy replenishment strategy processing method provided by the embodiment of the present application, for example, Figure 3A A method for handling the energy replenishment strategy of a vehicle is shown.

[0138] In some embodiments, the computer-readable storage medium may be a memory such as RAM, ROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.

[0139] In some embodiments, computer executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0140] As an example, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0141] As an example, computer executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed at multiple sites and interconnected by a communication network.

[0142] To sum up, the method provided in the embodiment of the present application classifies the energy source of the vehicle through the acquired sensor data to determine the energy source of the vehicle driven by the user, and then recommends the corresponding energy replenishment strategy to the user, so that the user can find the appropriate energy replenishment plan more quickly through the map application, thereby improving the efficiency of the user in obtaining energy replenishment strategies when using the map application.

[0143] The above is only an embodiment of the present application and is not intended to limit the protection scope of the present application. Any modifications, equivalent substitutions and improvements made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims

1. A method for processing a vehicle energy replenishment strategy, characterized in that: The method comprises: Acquiring sensor data of a vehicle driven by a target object, wherein the sensor data includes vehicle voice data; Classify the energy source of the vehicle based on the vehicle voice data to obtain a classification result of the energy source of the vehicle; An energy replenishment strategy matching the energy source classification result is obtained, and a recommended operation for the energy replenishment strategy is performed on the target object.

2. The method according to claim 1, characterized in that The classifying the energy source of the vehicle based on the vehicle voice data to obtain the energy source classification result of the vehicle includes: Calling a speech classification model to classify the vehicle speech data to obtain a first probability that the vehicle speech data includes vehicle engine noise; The energy source of the vehicle is classified based on the first probability to obtain a classification result of the energy source of the vehicle.

3. The method according to claim 2, characterized in that The speech classification model includes a convolutional neural network and a temporal neural network; The calling of the voice classification model to classify the vehicle voice data to obtain a first probability that the vehicle voice data includes vehicle engine noise includes: Acquire a voice feature signal corresponding to the vehicle voice data, wherein the vehicle voice data includes N frames of voice data, the voice feature signal includes N signal features, each signal feature corresponds to one frame of voice data, and N is an integer greater than or equal to 1; Calling the convolutional neural network to perform convolution processing on the speech feature signal to obtain a target feature vector; The temporal neural network is called to perform probability mapping processing on the target feature vector to obtain a first probability that the vehicle voice data includes vehicle engine noise.

4. The method according to claim 2, characterized in that: The sensor data also includes vehicle motion data; The classifying the energy source of the vehicle based on the first probability to obtain the energy source classification result of the vehicle includes: Performing a first mapping process on the vehicle motion data to obtain the environmental noise of the vehicle; The first probability is corrected based on the environmental noise of the vehicle to obtain an energy source classification result of the vehicle.

5. The method according to claim 4, characterized in that The vehicle motion data includes at least one of the following: vehicle speed, vehicle amplitude, and vehicle air pressure change amplitude; The performing a first mapping process on the vehicle motion data to obtain the environmental noise of the vehicle includes: When the vehicle motion data includes the vehicle driving speed, obtaining a first wind noise that is positively correlated with the vehicle driving speed; When the vehicle motion data includes the vehicle amplitude, obtaining tire noise that is positively correlated with the vehicle amplitude; When the vehicle motion data includes the vehicle air pressure change amplitude, obtaining a second wind noise that is positively correlated with the vehicle air pressure change amplitude; At least one of the first wind noise, the second wind noise, and the tire noise is used as the environmental noise of the vehicle.

6. The method according to claim 4, characterized in that The correcting the first probability based on the environmental noise of the vehicle to obtain the energy source classification result of the vehicle includes: Adjusting the first probability based on the environmental noise of the vehicle to obtain a second probability that the vehicle voice data includes the vehicle engine noise; When the second probability is not less than a second probability threshold, determining that the energy source classification result of the vehicle is fuel; When the second probability is not greater than the first probability threshold, determining that the energy source classification result of the vehicle is electric energy; When the second probability is less than the second probability threshold and greater than the first probability threshold, determining that the energy source result of the vehicle is a hybrid vehicle; The second probability threshold is greater than the first probability threshold.

7. The method according to claim 6, characterized in that The adjusting the first probability based on the environmental noise of the vehicle to obtain a second probability that the vehicle voice data includes the vehicle engine noise includes: extracting environmental features from the environmental noise, and extracting engine features from the first probability; fusing the environmental features and the engine features to obtain fused features; The fused features are fully connected to obtain a second probability that the vehicle voice data includes the vehicle engine noise.

8. The method according to claim 1, characterized in that The sensor data also includes vehicle motion data, and the energy source of the vehicle is classified based on the vehicle voice data to obtain the energy source classification result of the vehicle, including: The vehicle motion data is sequentially subjected to timestamp alignment processing, segmentation processing, normalization and filtering processing to obtain pre-processed vehicle motion data; The energy source of the vehicle is classified based on the pre-processed vehicle motion data and the vehicle voice data to obtain a classification result of the energy source of the vehicle.

9. The method according to claim 1, characterized in that: The obtaining of an energy replenishment strategy that matches the energy source classification result includes: When the energy source classification result of the vehicle is electric energy, generating the energy recharge strategy based on electric energy recharge stations within a preset range of the target object; When the energy source classification result of the vehicle is fuel, generating the energy replenishment strategy based on gas stations within a preset range of the target object; When the energy source classification result of the vehicle is oil-electric hybrid, electric energy refueling stations and gas stations within a preset range of the target object are obtained as the energy refueling strategy.

10. The method according to claim 9, characterized in that The generating the energy replenishment strategy based on the electric energy replenishment station within the preset range of the target object includes: Obtaining a first confidence level that the energy source classification result is electric energy, and determining a first target number of gas stations within the preset range based on the first confidence level, wherein the first target number is negatively correlated with the first confidence level; The electric energy refueling stations within a preset range of the target object and the first target number of gas stations are used as the energy refueling strategy.

11. The method according to claim 9, characterized in that The generating the energy replenishment strategy based on the gas stations within the preset range of the target object includes: Obtaining a second confidence level that the energy source classification result is fuel, and determining a second target number of electric energy supply stations within the preset range based on the second confidence level, wherein the second target number is negatively correlated with the second confidence level; The gas stations within a preset range of the target object and the second target number of electric energy replenishment stations are used as the energy replenishment strategy.

12. A vehicle energy replenishment strategy processing device, characterized in that: The device comprises: An acquisition module, used to acquire sensor data of a vehicle driven by a target object, wherein the sensor data includes vehicle voice data; A classification module, used for classifying the energy source of the vehicle based on the vehicle voice data to obtain a classification result of the energy source of the vehicle; The recommendation module is used to obtain an energy replenishment strategy that matches the energy source classification result, and perform a recommendation operation for the energy replenishment strategy on the target object.

13. An electronic device, characterized in that: The electronic device comprises: A memory for storing computer executable instructions or computer programs; A processor is used to implement the vehicle energy replenishment strategy processing method as described in any one of claims 1 to 11 when executing the computer executable instructions or computer programs stored in the memory.

14. A computer-readable storage medium storing computer-executable instructions or a computer program, characterized in that: When the computer executable instructions or computer program are executed by a processor, the vehicle energy replenishment strategy processing method according to any one of claims 1 to 11 is implemented.

15. A computer program product comprising computer executable instructions or a computer program, characterized in that When the computer executable instructions or computer program are executed by a processor, the vehicle energy replenishment strategy processing method according to any one of claims 1 to 11 is implemented.

Images