Real-time vehicle speed recommendation method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of vehicles and discloses a real-time vehicle speed recommendation method and device, electronic equipment and a storage medium. The method comprises the following steps: constructing a current parameter vector according to current vehicle related parameters, and constructing a historical time sequence vector corresponding to a current moment according to historical parameters corresponding to a corresponding historical moment in a historical period; inputting the current parameter vector into a target first model to obtain a first vehicle speed combination, and inputting the historical time sequence vector into a target second model to obtain a second vehicle speed combination; wherein the number of structure layers of the target first model is less than that of the target second model; and determining a current recommended vehicle speed interval according to the first vehicle speed combination and the second vehicle speed combination. The application can provide an accurate recommended vehicle speed interval for a driver, so as to optimize the driving behavior of the driver and reduce the energy consumption of vehicle driving.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicles, in particular to a real-time vehicle speed recommendation method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Vehicle endurance has always been a hot topic in the field of electric and electric hybrid vehicles. Generally, the endurance of the vehicle is improved by reasonably adjusting the energy consumption of each component of the running vehicle to ensure the endurance of the vehicle. In related technologies, an intelligent speed adaptation (ISA) system is mentioned, which provides a recommended speed for the driver to save energy consumption, so as to optimize the driving behavior of the driver and improve the energy efficiency of the vehicle.

[0003] However, the intelligent speed adaptation system is affected by factors such as vehicle conditions, resulting in low accuracy of the recommended speed provided by the system, which cannot provide accurate recommended speed for the driver, thereby failing to effectively reduce the energy consumption of the vehicle. SUMMARY

[0004] In view of the above problems, the present application provides a real-time vehicle speed recommendation method, device, electronic equipment and computer readable storage medium, which is used to provide an accurate recommended speed range in real time, so as to optimize the driving behavior of the driver and reduce the energy consumption of the vehicle.

[0005] According to one aspect of the present application, a real-time vehicle speed recommendation method is provided, which comprises: constructing a current parameter vector according to current vehicle related parameters, and constructing a historical time sequence vector corresponding to the current time according to historical parameters corresponding to the historical time in the historical period; inputting the current parameter vector into a target first model to obtain a first speed combination, and inputting the historical time sequence vector into a target second model to obtain a second speed combination; wherein the number of layers of the structure of the target first model is less than the number of layers of the structure of the target second model; determining a current recommended speed range according to the first speed combination and the second speed combination.

[0006] In an optional manner, the current vehicle related parameters include current road parameters, and the current road parameters include vehicle detection road parameters; a preset laser point is arranged around the vehicle; the current parameter vector is further constructed according to the current vehicle related parameters, which comprises: sending a detection laser to the surrounding area through the preset laser point to receive reflected light of the detection laser; determining three-dimensional coordinate parameters of objects in the surrounding area according to the reflected light, and determining a current parameter vector corresponding to the vehicle detection road parameter according to the three-dimensional coordinate parameters.

[0007] In an optional mode, the determining the current parameter vector corresponding to the vehicle road detection parameter according to the three-dimensional coordinate parameter further comprises: multiplying each dimension parameter in the three-dimensional coordinate parameter by a respective preset scaling factor, and performing summation operation on the calculated products to obtain a normalized value; and constructing the current parameter vector corresponding to the vehicle road detection parameter according to the normalized value and the number of preset laser point positions.

[0008] In an optional mode, the recommendation method further comprises: matching the current user identity information with the preset user identity information, and taking the preset first model and the preset second model corresponding to the matched preset user identity information as the target first model and the target second model, respectively; wherein the structure layer of the preset first model comprises a convolutional neural network layer and a fully connected neural network layer, and the structure layer of the preset second model comprises a recurrent neural network layer and a long short-term memory neural network layer.

[0009] In an optional mode, the constructing the historical time sequence vector corresponding to the current time according to the historical parameters corresponding to the respective historical time in the historical period further comprises: determining the historical parameter vector corresponding to each respective historical time according to the historical parameters corresponding to the respective historical time in the historical period; and inputting each historical parameter vector into a blank vector matrix in time sequence to obtain the historical time sequence vector corresponding to the current time; wherein the number of vectors in the blank vector matrix is the same as the number of historical parameter vectors.

[0010] In an optional mode, the first vehicle speed combination comprises a first highest vehicle speed and a first lowest vehicle speed, and the second vehicle speed combination comprises a second highest vehicle speed and a second lowest vehicle speed; and the determining the current recommended vehicle speed interval according to the first vehicle speed combination and the second vehicle speed combination further comprises: multiplying the first highest vehicle speed and the second highest vehicle speed by respective preset weight coefficients, respectively, and performing summation operation on the calculated products to obtain a recommended highest vehicle speed; multiplying the first lowest vehicle speed and the second lowest vehicle speed by respective preset weight coefficients, respectively, and performing summation operation on the calculated products to obtain a recommended lowest vehicle speed; and determining the current recommended vehicle speed interval according to the recommended highest vehicle speed and the recommended lowest vehicle speed.

[0011] In an optional mode, the current vehicle-related parameters represent a set of multiple different types of parameters; and the constructing the current parameter vector according to the current vehicle-related parameters further includes: performing numerical processing on each type of parameter respectively to obtain a vector element corresponding to each type of parameter; and constructing a parameter vector corresponding to each type of parameter according to the vector element corresponding to each type of parameter to obtain a current parameter vector corresponding to the current vehicle-related parameters; wherein the current parameter vector includes a current battery parameter vector, a current motor parameter vector, a current driving parameter vector, and a current road parameter vector.

[0012] According to another aspect of the present application, a real-time vehicle speed recommendation device is provided, which includes: a construction module configured to construct a current parameter vector according to current vehicle-related parameters and to construct a historical time sequence vector corresponding to a current time according to historical parameters corresponding to a corresponding historical time in a historical period; a vehicle speed combination module configured to input the current parameter vector into a target first model to obtain a first vehicle speed combination and to input the historical time sequence vector into a target second model to obtain a second vehicle speed combination; wherein the target first model has a smaller number of structure layers than the target second model; and a recommendation module configured to determine a current recommended vehicle speed range according to the first vehicle speed combination and the second vehicle speed combination.

[0013] According to an aspect of the present application, an electronic device is provided, which includes: a controller; and a memory configured to store one or more programs, which, when executed by the controller, perform the above-described recommendation method.

[0014] According to an aspect of the present application, a computer-readable storage medium is also provided, which stores computer-readable instructions, which, when executed by a processor of a computer, cause the computer to perform the above-described recommendation method.

[0015] According to an aspect of the present application, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the above-described recommendation method.

[0016] This application constructs a current parameter vector (i.e., a point value vector at real time) based on vehicle-related parameters in real time, and constructs a historical time-series vector (i.e., a segment value vector for a historical time period) based on historical parameters. The current parameter vector and the historical time-series vector are then input into models with different structural layers to obtain two vehicle speed combinations. Based on these two speed combinations, a recommended vehicle speed range for the current time is determined, providing drivers with accurate recommended speed ranges to optimize driving behavior and reduce vehicle energy consumption. The historical time-series vector is a time-series segment value vector composed of point value vectors corresponding to multiple historical times. Inputting it into a model with a higher structural layer allows for better feature extraction from the sequence data, resulting in more accurate vehicle speed combinations.

[0017] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0019] Figure 1 This is a flowchart illustrating an exemplary embodiment of the present application of a method for recommending real-time vehicle speed.

[0020] Figure 2 Based on Figure 1 The exemplary embodiment shown illustrates a flowchart of another method for recommending real-time vehicle speed.

[0021] Figure 3 Based on Figure 1 The exemplary embodiment shown illustrates a flowchart of another method for recommending real-time vehicle speed.

[0022] Figure 4 This is a schematic diagram illustrating an application scenario for the recommended method for real-time vehicle speed in this application.

[0023] Figure 5 This is a schematic diagram of the structure of a real-time vehicle speed recommendation device illustrated in an exemplary embodiment of this application.

[0024] Figure 6 This is a schematic diagram of the structure of a computer system for an electronic device, as illustrated in an exemplary embodiment of this application. Detailed Implementation

[0025] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0026] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0027] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0028] In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0029] Intelligent speed recommendation systems in related technologies can provide drivers with recommended speeds to save energy consumption, thereby improving vehicle energy efficiency by optimizing driver behavior.

[0030] However, intelligent speed recommendation systems are affected by factors such as vehicle condition, resulting in low accuracy of the recommended speeds they provide. This makes it impossible to provide drivers with accurate speed recommendations and thus fail to effectively reduce vehicle energy consumption.

[0031] Therefore, one aspect of this application provides a method for recommending real-time vehicle speed. Please refer to [link / reference] for details. Figure 1 , Figure 1 This is a flowchart illustrating an exemplary embodiment of a method for recommending real-time vehicle speeds. The method includes at least steps S110 to S130, which are detailed below:

[0032] S110: Construct a current parameter vector according to the current vehicle-related parameters, and construct a historical time sequence vector corresponding to the current time according to the historical parameters corresponding to the historical time in the historical period.

[0033] The current vehicle-related parameters are parameters related to the vehicle during driving, including but not limited to state parameters of various components of the vehicle, traffic flow parameters of the road on which the vehicle is driving, and surrounding environment parameters of the vehicle.

[0034] The current parameter vector is a one-dimensional vector composed of different vehicle-related parameters during driving at the current time, which is a point value vector representing a time point, and specifically includes various vehicle-related parameters at the current time.

[0035] The historical period is a relative period determined with the current time as the time scale, and the historical period is the preceding period immediately before the current time. For example, if the current time is 10:00, the period before 10:00 is determined as the historical period.

[0036] The historical time sequence vector is a vector matrix constructed by historical vectors of multiple historical times, that is, each element in the historical time sequence vector is a historical vector of a historical time. The elements in the historical time sequence vector are arranged according to the time sequence, which can represent a set of historical vectors of multiple historical times, similar to a segment value vector. The number of vector elements in the historical time sequence vector is related to the number of historical times in the historical period.

[0037] Historical time sequence vector construction example: determine the historical parameter vector corresponding to each corresponding historical time according to the historical parameters corresponding to the corresponding historical time in the historical period; input each historical parameter vector into a blank vector matrix according to the time sequence to obtain a historical time sequence vector corresponding to the current time; wherein the number of vectors in the blank vector matrix is the same as the number of historical parameter vectors.

[0038] The historical parameter vector corresponding to the historical time farthest from the current time in the historical period is input as the first vector in the blank vector matrix, and each historical parameter vector is input in turn according to the time sequence to obtain the historical time sequence vector.

[0039] In some embodiments, the current vehicle-related parameters represent a set of multiple different types of parameters, and different types of parameters need to be processed to unify different parameter units, for example: each type of parameter is subjected to numerical value processing to obtain a vector element corresponding to each type of parameter; according to the vector elements corresponding to each type of parameter, a parameter vector corresponding to each type of parameter is constructed to obtain a current parameter vector corresponding to the current vehicle-related parameters; wherein the current parameter vector includes a current battery parameter vector, a current motor parameter vector, a current driving parameter vector, and a current road parameter vector.

[0040] For example, the current battery parameters include battery power, battery voltage, battery temperature, battery pack balancing parameters, which are numerically processed to obtain respective corresponding vector elements a1, a2, a3, a4, to construct the current battery parameter vector A n =(a1, a2, a3, a4), the corresponding historical time battery parameter vector in the historical period is also constructed in this way, and the historical battery parameter time sequence vector B corresponding to the current time is constructed n =(A n-4 , A n-3 , A n-2 , A n-1 ); wherein the number of vector elements in the historical battery parameter time sequence vector is related to the corresponding historical time in the historical period, and the number of historical times here is 4.

[0041] For another example, the current motor parameter vector includes motor temperature, engine speed, engine torque, which are numerically processed to obtain respective corresponding vector elements c1, c2, c3, to construct the current battery parameter vector C n =(c1, c2, c3), the corresponding historical time battery parameter vector in the historical period is also constructed in this way, and the historical motor parameter time sequence vector D corresponding to the current time is constructed n =(C n-3 , C n-2 , C n-1 ). The number of historical times here is 3, the number of vector elements in a uniform value vector and a segment value vector, in order to balance the characteristic elements of the two kinds of vectors, and facilitate subsequent fair calculation of vehicle speed.

[0042] For another example, the current driving parameters include vehicle speed, wind resistance, tire pressure, weather, which are numerically processed to obtain respective corresponding vector elements e1, e2, e3, e4, to construct the current driving parameter vector E n =(e1, e2, e3, e4), the corresponding historical time driving parameter vector in the historical period is also constructed in this way, and the historical driving parameter time sequence vector F corresponding to the current time is constructed n =(E n-4 , E n-3 , E n-2 , E n-1 ).

[0043] Another exemplary, the current road parameters include vehicle detection road parameters, satellite positioning road parameters, traffic flow parameters, road conditions parameters, which are numerically processed to obtain the respective corresponding vector elements g1, g2, g3, g4. g1 is a two-dimensional parameter of the vehicle laser detection of the surrounding object; g2=(whether congested, congested road distance, total length of the road section, time to destination), representing the road conditions determined by satellite positioning, g3=(vehicle flow per minute through the intersection, people flow per minute through the intersection, the speed of the remaining vehicles through the front), representing the road traffic flow; g4=(whether there is construction in front of the vehicle, vehicle congestion road condition duration, vehicle congestion road distance), representing the road repair situation. According to g1, g2, g3, g4, the current road parameter vector G is constructed n =(g1, g2, g3, g4), the road parameter vector of the corresponding historical time in the historical period is also constructed in this way, and the historical road parameter time sequence vector H corresponding to the current time is constructed n n-4 , G n-3 , G n-2 , G n-1 .

[0044] S120: input the current parameter vector into the target first model to obtain the first speed combination, and input the historical time sequence vector into the target second model to obtain the second speed combination; wherein the structure layer number of the target first model is less than the structure layer number of the target second model.

[0045] The target first model and the target second model are speed recommendation models adapted to the current user (i.e. the current driver).

[0046] The more the structure layer number of the model, the more in-depth the feature extraction. For the point-like structure data of the current parameter vector, there is no need for deep feature extraction, and the corresponding features can be quickly extracted by using the first model with a relatively small structure layer number, so that the first model quickly outputs the first speed combination. For the time series data of the historical time sequence vector, deep feature extraction is needed to accurately extract the corresponding features, so that the second model outputs the second speed combination more accurately.

[0047] In some embodiments, the current parameter vector and the historical time sequence vector need to be data cleaned to remove invalid or error records, and the cleaned data is standardized or normalized to make the parameter values between [0, 1], which is beneficial to the learning of the corresponding model. If there are missing parameter values, interpolation or deletion can be used to complete the data processing. The processed current parameter vector and historical time sequence vector can be better applied to the corresponding model to make the corresponding model output accurate speed combination.

[0048] ​S130: determining the current recommended speed interval according to the first speed combination and the second speed combination.

[0049] Exemplarily, the lowest speed and the highest speed in the first speed combination and the second speed combination are respectively taken as the lowest speed and the highest speed of the current recommended speed interval, so as to obtain the recommended speed interval.

[0050] Another exemplarily, the first speed combination comprises a first highest speed and a first lowest speed, and the second speed combination comprises a second highest speed and a second lowest speed. The first highest speed and the second highest speed are respectively multiplied by the respective corresponding preset weight coefficients, and the calculated products are summed to obtain a recommended highest speed; the first lowest speed and the second lowest speed are respectively multiplied by the respective corresponding preset weight coefficients, and the calculated products are summed to obtain a recommended lowest speed; the current recommended speed interval is determined according to the recommended highest speed and the recommended lowest speed. The corresponding calculation formula is as follows:

[0051] final_min_speed = weight_structured * V1 + weight_sequence * V3;

[0052] final_max_speed = weight_structured * V2 + weight_sequence * V4;

[0053] Wherein, final_min_speed represents the lowest speed of the recommended speed interval, final_max_speed represents the highest speed of the recommended speed interval, weight_structured represents the first preset weight coefficient corresponding to each speed in the first speed combination, weight_sequence represents the second preset weight coefficient corresponding to each speed in the second speed combination, V1 represents the lowest speed (i.e. the first lowest speed) in the first speed combination, V2 represents the lowest speed (i.e. the second lowest speed) in the second speed combination, V3 represents the highest speed (i.e. the first highest speed) in the first speed combination, and V4 represents the highest speed (i.e. the second highest speed) in the second speed combination. The first preset weight coefficient + the second preset weight coefficient = 1, and the application does not limit the preset weight coefficients corresponding to the two speed combinations, which can be the same or different.

[0054] The embodiment constructs a current parameter vector in real time according to vehicle related parameters, that is, a point value vector at a real time moment, and constructs a historical time sequence vector corresponding to the current moment, that is, a segment value vector of a historical period, according to historical parameters. The current parameter vector and the historical time sequence vector are respectively input into models with different numbers of structures to obtain two vehicle speed combinations, and a recommended vehicle speed interval corresponding to the current moment is determined according to the two vehicle speed combinations, so as to provide an accurate recommended vehicle speed interval for a driver, optimize the driving behavior of the driver, and thus reduce the energy consumption of the vehicle. The historical period vector is a segment value vector with time sequence composed of multiple point value vectors corresponding to historical moments. The historical period vector is input into a model with a higher number of structures, so as to better extract features of sequence data and make the obtained vehicle speed combination more accurate.

[0055] The determination process of the related recommended vehicle speed only considers the vehicle condition of the driving vehicle, does not consider other parameters affecting the driving of the vehicle, and thus the determined recommended vehicle speed is not applicable to the current driving vehicle. The driver adjusts the speed according to the recommended vehicle speed with low accuracy, and thus cannot optimize the energy consumption of the vehicle.

[0056] Therefore, in another example embodiment of the present application, how to construct a current parameter vector according to current vehicle related parameters is introduced in detail by introducing a road parameter. For details, please refer to Figure 2 , Figure 2 is another flowchart of a real-time vehicle speed recommendation method shown in the example embodiment shown in Figure 1 . The recommendation method further includes S210 to S220 in S110 shown in Figure 1 . The vehicle is provided with a preset laser point around the vehicle, which is introduced in detail as follows:

[0057] S210: Send a detection laser to the surrounding area through the preset laser point to receive reflected light of the detection laser.

[0058] The number and position of the preset laser point can be adjusted according to different vehicles, and there is no fixed number and position limitation. For example, a vehicle is provided with 192 laser points, and the pulse frequency is 10HZ, that is, theoretically the vehicle can send out at most 1920 detection laser points per second, and 1920 three-dimensional coordinates are obtained according to the reflected light of the received detection laser.

[0059] S220: Determine the three-dimensional coordinate parameters of the object in the surrounding area according to the reflected light, and determine a current parameter vector corresponding to the vehicle detection road parameter according to the three-dimensional coordinate parameters.

[0060] For example, the dimension parameters in a certain three-dimensional coordinate parameter are summed, and the sum is taken as a vector element, and in this way, a current parameter vector corresponding to the vehicle detection road parameter is constructed according to multiple vector elements.

[0061] In another example, each dimension parameter in the three-dimensional coordinate parameters is multiplied by its corresponding preset scaling factor, and the calculated product is summed to obtain a normalized value; based on the normalized value and the number of preset laser points, the current parameter vector corresponding to the vehicle detection road parameters is constructed.

[0062] For example, the three-dimensional coordinate parameters (2.00, 0.00, 0.50) indicate that the object is 2 meters directly in front of the corresponding preset laser point, with a horizontal offset of 0 meters and a height offset of 0.5 meters. Each coordinate value is normalized to the interval [0, 1] to obtain (x1, x2, x3), and then the three values ​​are combined into one by multiplying by an appropriate scaling factor.

[0063] Y = (a1*x1) + (a2*x2) + (a3*x3) rounded down;

[0064] Where a1, a2, and a3 are preset scaling factors corresponding to different dimensional parameters. In order to convert the normalized values ​​to integers, a1 = a2 = a3 = 10 5 At this point, a two-dimensional vector [1920, Y] is obtained. Flattening the data yields the current parameter vector corresponding to the vehicle's road detection parameters.

[0065] In related technologies, the first and second models are relatively fixed, and their learning data comes from parameters generated during vehicle operation. In scenarios using the first and second models, the lack of personalized adjustments for drivers will affect the model's output and daily training.

[0066] Therefore, in another exemplary embodiment of this application, the model is linked to preset user identity information to adapt a personalized model for different drivers. See details below. Figure 3 , Figure 3 Based on Figure 1 The exemplary embodiment shown illustrates a flowchart of another real-time vehicle speed recommendation method. This recommendation method, in the example described... Figure 1 Based on S110 to S130 shown, at least S310 is also included, which is described in detail below:

[0067] S310: Match the current user identity information with the preset user identity information, and use the preset first model and preset second model corresponding to the successfully matched preset user identity information as the target first model and target second model, respectively; wherein, the structure layer of the preset first model includes a convolutional neural network layer and a fully connected neural network layer, and the structure layer of the preset second model includes a recurrent neural network layer and a long short-term memory neural network layer.

[0068] Exemplarily, the current user identity information is matched with the preset user identity information in Table 1 to quickly determine the target first model and the target second model suitable for the current user.

[0069] Table 1: Relationship table of preset user identity information and corresponding preset model

[0070]

[0071]

[0072] The establishment of the preset first model is exemplarily described below, and the relevant code example is as follows:

[0073] model = models.Sequential()

[0074] # One-dimensional convolution layer, 64 filters, kernel size 6, no activation function model.add(layers.Conv1D(64, 6, activation=None, input_shape=input_shape))

[0075] # Add BatchNormalization layer

[0076] model.add(BatchNormalization())

[0077] # Add activation function

[0078] model.add(ReLU())

[0079] # Pooling layer

[0080] model.add(layers.MaxPooling1D(3))

[0081] # Second one-dimensional convolution layer, 128 filters

[0082] model.add(layers.Conv1D(128, 3, activation='relu'))

[0083] # Add BatchNormalization layer

[0084] model.add(BatchNormalization())

[0085] # Add activation function

[0086] model.add(ReLU())

[0087] Pooling layer

[0088] model.add(layers.MaxPooling1D(3))

[0089] Flattening layer

[0090] model.add(layers.Flatten())

[0091] Fully connected layer with 64 neurons

[0092] model.add(layers.Dense(64, activation='relu'))

[0093] Add a Dropout layer with a dropout rate of 0.2, meaning approximately twenty percent of the neurons will be randomly dropped

[0094] model.add(Dropout(0.2))

[0095] Add a hidden layer with 128 neurons

[0096] model.add(layers.Dense(128, activation='relu'))

[0097] Add a Dropout layer with a dropout rate of 0.5, meaning approximately fifty percent of the neurons will be randomly dropped

[0098] model.add(Dropout(0.5))

[0099] Second hidden layer with 64 neurons

[0100] model.add(layers.Dense(64, activation='relu'))

[0101] Add a Dropout layer with a dropout rate of 0.2, meaning approximately twenty percent of the neurons will be randomly dropped

[0102] model.add(Dropout(0.2))

[0103] Third hidden layer with 32 neurons

[0104] model.add(layers.Dense(32, activation='relu'))

[0105] # Add a Dropout layer with 0.1 dropout rate, meaning that approximately ten percent of the neurons will be randomly dropped

[0106] model.add(Dropout(0.1))

[0107] # Branch 1: Predict the minimum speed value (i.e., the lowest car speed preset as the first model output)

[0108] min_speed_branch = layers.Dense(1, name='min_speed_output')(inputs)

[0109] # Branch 2: Predict the maximum speed value (i.e., the highest car speed preset as the first model output)

[0110] max_speed_branch = layers.Dense(num_classes, activation='softmax', name='max_speed_output')(inputs)

[0111] # Merge the two branches into one model

[0112] model = Model(inputs=inputs, outputs=[min_speed_branch, max_speed_branch])

[0113] # Compile the model

[0114] # Use mean squared error as the loss function for both outputs

[0115] model.compile(optimizer='adam', loss=['mean_squared_error','mean_squared_error'])

[0116] Here, layers.Conv1D() is mainly used to extract features from the input vector values, learning more local features. By stacking multiple convolutional layers, the network can learn different scale feature representations, while reducing the computational complexity and memory usage compared to fully connected layers.

[0117] layers.MaxPooling1D() is mainly used to reduce the dimensionality of one-dimensional data, retaining the most important features in the sequence and ignoring insignificant changes, reducing the computational complexity of subsequent layers and improving the speed of model training and inference.

[0118] The purpose of layers.Flatten() is to better input data to the next layer.

[0119] layers.Dense() can integrate features from the previous layer and extract more global features based on the previous local features. In this design, three Dense() layers are used for feature extraction.

[0120] Dropout layer: Proper regularization techniques help the model better generalize to unseen data (e.g., more parameters representing road conditions, reducing parameter quantity through this method) while also preventing network overfitting and improving generalization ability.

[0121] Batch normalization before the activation function can help stabilize and speed up the training process, as it normalizes the output of the convolutional layer, allowing the activation function to work more effectively.

[0122] Max pooling after the activation function can reduce the spatial size of the data while preserving important features processed by the activation function.

[0123] Activation function (ReLU): Apply a nonlinear activation function after batch normalization to introduce nonlinear characteristics.

[0124] This model combines 2 layers of layers.Conv1D() and 4 layers of layers.Dense(), which can obtain more local features, reduce model parameters, and extract more global features based on the previous local features. Two layers of layers.Conv1D() will not cause the model parameter quantity to be large, and the corresponding Dropout() added in the middle of the four layers of layers.Dense() can effectively reduce the parameter quantity and prevent overfitting. The dropout rates of 0.2, 0.5, 0.2, and 0.1 correspond to the 64, 128, 64, and 2 layers of layers.Dense(), which can effectively reduce the requirement for computing power

[0125] The following is an example of the establishment of the second preset model, and the relevant code example is as follows:

[0126] # Assuming the input data is time series data with time_steps time steps, and the feature dimension of each time step is features

[0127] time_steps = 100

[0128] features = 16

[0129] # Create a sequential model

[0130] model = Sequential()

[0131] # Add an RNN layer

[0132] model.add(SimpleRNN(32, return_sequences=True, input_shape=(time_steps, features)))

[0133] # Add an LSTM layer, more RNN or LSTM layers can be stacked

[0134] model.add(LSTM(64, return_sequences=True))

[0135] model.add(SimpleRNN(64, return_sequences=True))

[0136] model.add(LSTM(128, return_sequences=True))

[0137] # Add a fully connected layer, TimeDistributed layer can apply Dense layer on each time step's output

[0138] model.add(TimeDistributed(Dense(32, activation='relu')))

[0139] # Add additional fully connected layers to extract features

[0140] model.add(Dense(64, activation='relu'))

[0141] # Branch 1: Predict the minimum speed value (i.e., the lowest car speed that the second model outputs)

[0142] min_speed_branch = Dense(1, name='min_speed_output')(inputs)

[0143] # Branch 2: Predict the maximum speed value (i.e., the highest car speed that the second model outputs)

[0144] max_speed_branch = Dense(num_classes, activation='softmax', name='max_speed_output')(inputs)

[0145] # Combine the two branches into one model

[0146] model = Model(inputs=inputs, outputs=[min_speed_branch, max_speed_branch])

[0147] # Compile the model

[0148] # Since there are two outputs, we need to define two loss functions

[0149] model.compile(optimizer='adam', loss={'min_speed_output':'mean_squared_error','max_speed_output': 'categorical_crossentropy'})

[0150] Among them, the RNN layer is particularly suitable for processing sequence data because it can capture dynamic features in time series. Time series data mainly refers to historical records such as vehicle speed, acceleration, and battery charging status.

[0151] The LSTM layer is a special type of RNN that can learn long-term dependencies and is very suitable for processing and predicting time series data. Mainly for capturing dynamic features and long-term dependencies in time series. Utilize the fast processing power of the RNN layer and the long-term dependency learning ability of the LSTM layer.

[0152] Use the RNN layer to better capture dynamic features in time series, and use the LSTM layer to learn long-term dependencies, where an RNN layer will be added in two LSTM layers to capture dynamic features again after learning long-term dependencies, and analyze features in a deeper level. The number of layers of 32, 64, 64, and 128 is also set to fit the size of the data. At the same time, additional fully connected layers are added to extract features again, which is better to fuse and correlate dynamic features, dependencies, and global and local relationships for subsequent output calculations.

[0153] The application scenarios of the above-mentioned multiple recommendation methods are exemplarily illustrated in another exemplary embodiment of the present application. For details, please refer to Figure 4 , Figure 4 is a schematic diagram of the application scenario of the real-time vehicle speed recommendation method of the present application. Among them, it includes a vehicle 100, a server 200 and a display screen 300, which can be connected through wireless communication between the three ends, and the present application does not limit the connection mode between them.

[0154] The display screen 300 is a component placed in the vehicle 100, which can display the recommended speed interval determined by the server 200. The server 200 can be likeFigure 4 The vehicle 100 is shown to be placed in the vehicle 100, and can be independent of the vehicle 100, which is the execution subject of the recommendation method shown in any of the above exemplary embodiments, to execute any of the above recommendation methods, which are exemplarily illustrated as follows:

[0155] The server 200 constructs a current parameter vector according to current vehicle 100 related parameters, and constructs a historical time sequence vector corresponding to the current time according to historical parameters corresponding to the corresponding historical time in the historical period; the server 200 inputs the current parameter vector into a target first model to obtain a first vehicle speed combination, and inputs the historical time sequence vector into a target second model to obtain a second vehicle speed combination; wherein the structure layer number of the target first model is less than the structure layer number of the target second model; the server 200 determines a current recommended vehicle speed interval according to the first vehicle speed combination and the second vehicle speed combination.

[0156] If the server 300 is independent of the vehicle 100, it can be a server cluster composed of multiple physical servers or a distributed system, wherein multiple servers can form a block chain, and the server is a node on the block chain. The server 300 can also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, etc. Basic cloud computing services, which are not limited herein.

[0157] Another aspect of the present application also provides a real-time vehicle speed recommendation device, as shown in Figure 5 Figure 5 is a structural schematic diagram of the real-time vehicle speed recommendation device according to an exemplary embodiment of the present application. The recommendation device 500 comprises:

[0158] The construction module 510 constructs a current parameter vector according to current vehicle related parameters, and constructs a historical time sequence vector corresponding to the current time according to historical parameters corresponding to the corresponding historical time in the historical period.

[0159] The vehicle speed combination module 530 inputs the current parameter vector into a target first model to obtain a first vehicle speed combination, and inputs the historical time sequence vector into a target second model to obtain a second vehicle speed combination; wherein the structure layer number of the target first model is less than the structure layer number of the target second model.

[0160] The recommendation module 550 determines a current recommended vehicle speed interval according to the first vehicle speed combination and the second vehicle speed combination.

[0161] ​In another example embodiment, the current vehicle-related parameter includes a current road parameter, the current road parameter includes a vehicle-probed road parameter; the vehicle-surrounding environment is provided with a preset laser point; the construction module 510 further includes:

[0162] The detection unit sends a detection laser to the surrounding area through the preset laser point to receive reflected light of the detection laser.

[0163] The determination unit determines a three-dimensional coordinate parameter of an object in the surrounding area according to the reflected light, and determines a current parameter vector corresponding to the vehicle-probed road parameter according to the three-dimensional coordinate parameter.

[0164] In another example embodiment, the determination unit further includes:

[0165] The normalization block multiplies each dimension parameter in the three-dimensional coordinate parameter by a respective corresponding preset scaling factor, and performs summation operation on the calculated product to obtain a normalized value.

[0166] The construction block constructs a current parameter vector corresponding to the vehicle-probed road parameter according to the normalized value and the number of preset laser points.

[0167] In another example embodiment, the recommendation device 500 further includes:

[0168] The identity matching module matches the current user identity information with the preset user identity information, and takes the preset first model and the preset second model corresponding to the matched preset user identity information as the target first model and the target second model, respectively; wherein, the structure layer of the preset first model includes a convolutional neural network layer and a fully connected neural network layer, and the structure layer of the preset second model includes a recurrent neural network layer and a long short-term memory neural network layer.

[0169] In another example embodiment, the construction module 510 further includes:

[0170] The historical parameter vector determination unit determines a historical parameter vector corresponding to each corresponding historical moment according to a historical parameter corresponding to the corresponding historical moment in the historical period.

[0171] The historical time sequence vector unit inputs each historical parameter vector into a blank vector matrix in time sequence to obtain a historical time sequence vector corresponding to the current moment; wherein, the number of vectors in the blank vector matrix is the same as the number of historical parameter vectors.

[0172] In another example embodiment, the first vehicle speed combination includes a first highest vehicle speed and a first lowest vehicle speed, and the second vehicle speed combination includes a second highest vehicle speed and a second lowest vehicle speed; the recommendation module 550 further includes:

[0173] The first calculation unit multiplies the first highest vehicle speed and the second highest vehicle speed by respective preset weight coefficients, and performs summation operation on the calculated products to obtain a recommended highest vehicle speed.

[0174] The second calculation unit multiplies the first lowest vehicle speed and the second lowest vehicle speed by respective preset weight coefficients, and performs summation operation on the calculated products to obtain a recommended lowest vehicle speed.

[0175] The vehicle speed recommendation unit determines a current recommended vehicle speed range according to the recommended highest vehicle speed and the recommended lowest vehicle speed.

[0176] In another exemplary embodiment, the current vehicle-related parameters represent a set of multiple different types of parameters; the construction module 510 further includes:

[0177] The numerical processing unit performs numerical processing on each type of parameter to obtain a vector element corresponding to each type of parameter.

[0178] The current parameter vector construction unit constructs a parameter vector corresponding to each type of parameter according to the vector element corresponding to each type of parameter to obtain a current parameter vector corresponding to the current vehicle-related parameters; wherein the current parameter vector includes a current battery parameter vector, a current motor parameter vector, a current driving parameter vector, and a current road parameter vector.

[0179] The recommendation device of the present application constructs a current parameter vector in real time according to vehicle-related parameters, i.e., a point value vector at a real-time moment, and constructs a historical time sequence vector corresponding to the current moment according to historical parameters, i.e., a segment value vector of a historical period; the current parameter vector and the historical time sequence vector are respectively input into models with different numbers of structures to obtain two vehicle speed combinations, and a recommended vehicle speed range corresponding to the current moment is determined according to the two vehicle speed combinations, which can provide an accurate recommended vehicle speed range for the driver to optimize the driving behavior of the driver and thus reduce the energy consumption of the vehicle. Wherein the historical period vector is a segment value vector with time sequence composed of multiple point value vectors corresponding to historical moments, which is input into a model with a higher number of structures to better extract features from sequence data, so that the obtained vehicle speed combination is more accurate.

[0180] It should be noted that the recommendation device provided in the above embodiments and the recommendation method provided in the foregoing embodiments belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiments, which will not be described here.

[0181] Another aspect of the present application also provides an electronic device, including: a controller; a memory for storing one or more programs, when the one or more programs are executed by the controller, to perform the above-mentioned recommendation method.

[0182] Referring to Figure 6 , Figure 6 is a structural diagram of a computer system of an electronic device according to an example embodiment of the present application, which shows a structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application.

[0183] It should be noted that Figure 6 The computer system 600 of the electronic device shown is only an example and should not impose any limitation on the functions and usage range of the embodiments of the present application.

[0184] As Figure 6 shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or programs loaded from a storage portion 608 into a random access memory (RAM) 603, such as performing the methods in the above-described embodiments. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0185] The following components are connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker, and the like; a storage portion 608 including a hard disk, and the like; and a communication portion 609 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as necessary. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 610 as necessary, so that a computer program read therefrom is installed in the storage portion 608 as necessary.

[0186] In particular, the processes described above with reference to the flow charts can be implemented as a computer software program in accordance with the embodiments of the present application. For example, embodiments of the present application include a computer program product which includes a computer program tangibly embodied on a computer readable medium, the computer program containing instructions for executing the methods illustrated by the flow charts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 609 and / or installed from the removable media 611. When the computer program is executed by the central processing unit (CPU) 601, various functions defined in the system of the present application are executed.

[0187] It should be noted that the computer readable medium shown in the embodiments of the present application can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as part of a carrier wave, in which the computer readable computer program is carried. Such a propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium that can send, propagate or transfer a program for use by or in connection with an instruction execution system, apparatus or device. The computer program contained in the computer readable medium can be transmitted in any suitable medium, including but not limited to wireless, wired, optical, or any suitable combination of the above.

[0188] The flowcharts and block diagrams in the attached drawings illustrate the possible architectural, functional and operational scenarios of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowcharts or block diagrams can represent a module, a segment, or a portion of code which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks noted in succession can in fact be executed substantially concurrently, or they can be executed in reverse order, depending on the functionality involved. It should also be noted that each block in the flowcharts or block diagrams and combinations of blocks in the flowcharts or block diagrams can be implemented by dedicated hardware-based systems which perform the specified functions or operations, or they can be implemented by a combination of dedicated hardware and computer instructions.

[0189] The units described in the embodiments of the present application can be implemented by software, or by hardware, or by a combination of software and hardware. The units described can also be located in a single processor. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0190] Another aspect of the present application provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the recommendation method as described above. The computer readable storage medium can be included in the electronic device as described in the embodiments above, or it can exist separately from the electronic device.

[0191] Another aspect of the present application provides a computer program product or computer program, which includes computer instructions. The computer instructions are stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device performs the recommendation method provided in the embodiments above.

[0192] According to an aspect of an embodiment of the present application, a computer system is also provided, which includes a central processing unit (CPU) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage section into a random access memory (RAM), such as performing the method in the above-described embodiments. In the RAM, various programs and data required for system operation are also stored. The CPU, the ROM, and the RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0193] Connected to the I / O interface are an input section including a keyboard, a mouse, etc.; an output section including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section including a hard disk, etc.; and a communication section including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as necessary. A removable recording medium, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is attached to the drive as necessary, so that a computer program read out therefrom is installed into the storage section as necessary.

[0194] The above-described content is merely a preferred exemplary embodiment of the present application, and is not intended to limit the implementation of the present application. Those skilled in the art can easily make corresponding modifications or variations according to the main idea and spirit of the present application, and the protection scope of the present application should be subject to the protection scope required by the claims.

Claims

1. A method of recommending a real-time vehicle speed, characterized by, The recommendation method includes: A current parameter vector is constructed based on the current vehicle-related parameters, and a historical time-series vector corresponding to the current moment is constructed based on the historical parameters corresponding to the corresponding historical moments in the historical period. This includes: determining the historical parameter vectors corresponding to each corresponding historical moment based on the historical parameters corresponding to the corresponding historical moments in the historical period; inputting each historical parameter vector into a blank vector matrix according to the time sequence to obtain the historical time-series vector corresponding to the current moment; wherein, the number of vectors in the blank vector matrix is ​​the same as the number of historical parameter vectors. The current parameter vector is input into the first target model to obtain the first vehicle speed combination, and the historical time series vector is input into the second target model to obtain the second vehicle speed combination; wherein, the number of structural layers of the first target model is less than the number of structural layers of the second target model; Based on the first speed combination and the second speed combination, the current recommended speed range is determined; The method further includes: matching the current user identity information with preset user identity information, and using the preset first model and preset second model corresponding to the successfully matched preset user identity information as the target first model and target second model, respectively; wherein, the structure layer of the preset first model includes a convolutional neural network layer and a fully connected neural network layer, and the structure layer of the preset second model includes a recurrent neural network layer and a long short-term memory neural network layer.

2. The recommendation method according to claim 1, characterized in that, The current vehicle-related parameters include current road parameters, which in turn include vehicle-detected road parameters; Pre-set laser points are placed around the vehicle; The step of constructing the current parameter vector based on the current vehicle-related parameters further includes: The detection laser is sent to the surrounding area through the preset laser point, and the reflected light of the detection laser is received. The three-dimensional coordinate parameters of the object in the surrounding area are determined based on the reflected light, and the current parameter vector corresponding to the vehicle's road detection parameters is determined based on the three-dimensional coordinate parameters.

3. The recommendation method of claim 2, wherein, The step of determining the current parameter vector corresponding to the vehicle-detected road parameters based on the three-dimensional coordinate parameters further includes: Multiply each dimension parameter in the three-dimensional coordinate parameters by its corresponding preset scaling factor, and sum the calculated products to obtain a normalized value. Based on the normalized values ​​and the number of preset laser points, a current parameter vector corresponding to the vehicle's road detection parameters is constructed.

4. The recommended method according to any one of claims 1 to 3, characterized in that, The first speed combination includes a first maximum speed and a first minimum speed, and the second speed combination includes a second maximum speed and a second minimum speed. The step of determining the current recommended speed range based on the first speed combination and the second speed combination further includes: The first maximum speed and the second maximum speed are multiplied by their respective preset weight coefficients, and the calculated products are summed to obtain the recommended maximum speed. The first minimum vehicle speed and the second minimum vehicle speed are multiplied by their respective preset weight coefficients, and the calculated products are summed to obtain the recommended minimum vehicle speed. The current recommended speed range is determined based on the recommended maximum speed and the recommended minimum speed.

5. The recommended method according to any one of claims 1 to 3, characterized in that, The current vehicle-related parameters represent a set of multiple different types of parameters; The step of constructing the current parameter vector based on the current vehicle-related parameters further includes: Each type of parameter is numerically processed to obtain the vector elements corresponding to each type of parameter; Based on the vector elements corresponding to each type of parameter, a parameter vector corresponding to each type of parameter is constructed to obtain the current parameter vector corresponding to the current vehicle-related parameters; wherein, the current parameter vector includes the current battery parameter vector, the current motor parameter vector, the current driving parameter vector, and the current road parameter vector.

6. A real-time vehicle speed recommendation device, characterized in that, The recommendation device includes: The construction module constructs a current parameter vector based on the current vehicle-related parameters, and constructs a historical time-series vector corresponding to the current moment based on the historical parameters corresponding to the corresponding historical moments in the historical period. This includes: determining the historical parameter vectors corresponding to each corresponding historical moment based on the historical parameters corresponding to the corresponding historical moments in the historical period; inputting each historical parameter vector into a blank vector matrix according to the time sequence to obtain the historical time-series vector corresponding to the current moment; wherein the number of vectors in the blank vector matrix is ​​the same as the number of historical parameter vectors. The vehicle speed combination module inputs the current parameter vector into the target first model to obtain the first vehicle speed combination, and inputs the historical time series vector into the target second model to obtain the second vehicle speed combination; wherein, the number of structural layers of the target first model is less than the number of structural layers of the target second model; The recommendation module determines the current recommended speed range based on the first speed combination and the second speed combination. The identity matching module matches the current user's identity information with preset user identity information, and uses the preset first model and preset second model corresponding to the successfully matched preset user identity information as the target first model and target second model, respectively; wherein, the structure layer of the preset first model includes a convolutional neural network layer and a fully connected neural network layer, and the structure layer of the preset second model includes a recurrent neural network layer and a long short-term memory neural network layer.

7. An electronic device, characterized in that, include: Controller; A memory for storing one or more programs that, when executed by a controller, cause the controller to implement the recommended method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that, when executed by the computer's processor, cause the computer to perform the recommended method as described in any one of claims 1 to 5.

Images