Recommendation method and device of vehicle travel information, vehicle, equipment and medium

Abstract

In order to solve the problem, the invention provides the vehicle travel information recommendation method and device, the vehicle, the equipment and the medium, travel information is individually recommended to the user in combination with third-party ecological data, vehicle real-time data and user historical behavior data, and the user experience is improved. The vehicle travel information recommendation method comprises the steps of starting a travel recommendation model when it is recognized that a user has a travel recommendation demand; the travel recommendation model is obtained based on user historical behavior data training; and after the travel recommendation model is started, performing travel information recommendation for the user according to the travel recommendation demand of the user, the user historical behavior data, the vehicle real-time data and the third-party ecological data.

Description

Technical Field

[0001] The present application relates to the field of intelligent vehicle technology, and specifically to a method, device, vehicle, equipment and medium for recommending vehicle travel information. Background Art

[0002] As an important branch of deep learning, big models have powerful computing and data processing capabilities, and can process massive amounts of vehicle data to achieve more accurate interaction capabilities. With the popularization of Internet of Vehicles technology, the amount of data generated by vehicles has exploded, and big data processing technology has become an indispensable part of smart car assistants. Through big data technology, vehicle data can be collected, stored, analyzed and mined in real time to provide support for intelligent decision-making.

[0003] With the continuous advancement of technology and the change of social lifestyle, car owners' demand for intelligent self-driving tours is gradually increasing. This trend reflects the pursuit of convenience, safety and personalization by modern people, as well as their expectation for the new self-driving tour experience that intelligent technology can bring. In self-driving tours, car owners expect to enjoy more intelligent and personalized services to meet their growing needs.

[0004] Specifically, the intelligent demands of car owners for self-driving tours are mainly reflected in the following aspects: Intelligent route planning: Car owners hope that the intelligent system can plan the best driving route for them based on real-time traffic conditions, weather conditions and their own preferences to avoid congestion and unnecessary detours; Real-time information service: During driving, car owners need to obtain real-time road conditions, weather forecasts, scenic spot introductions, etc., so as to adjust the itinerary at any time. The intelligent self-driving tour system can provide this real-time information to ensure that the car owner's travel is smoother; Safe driving assistance: Intelligent technology can monitor in real time through vehicle sensors, cameras and other equipment.

[0005] The vehicle status and surrounding environment provide early warnings and reminders to car owners, helping them avoid potential safety hazards; Personalized recommendations: Car owners hope that the intelligent system can understand their interests and preferences, and recommend tourist attractions and restaurants that meet their needs, making self-driving tours more colorful; Social interaction experience: During self-driving tours, car owners expect to communicate and interact with other car owners and tourists, and share travel experiences and feelings. The intelligent self-driving tour system can provide social functions, allowing car owners to make new friends during the trip and increase the fun of the trip.

[0006] CN202311099966.0 proposes a method for constructing a trip planning and intelligent navigation system based on a multimodal large model. Through data acquisition, trip planning and intelligent navigation, multiple initial trips are generated for users to choose from. In addition, the trip route is optimized in combination with weather conditions, types of attractions and expected traffic. This solution uses data on the website for trip planning, which cannot understand user needs well and cannot be dynamically adjusted during the trip. CN202311616429.9 proposes an intelligent accompanying navigation system and a navigation method based on AI. Users input relevant information through a voice module, and AI processes this information to generate personalized navigation words. At the same time, it can combine the user's environmental information to infer the user's interest in topics and generate chat content. This solution can actively generate personalized recommendation content for users based on environmental information and enhance the fun of interaction, but the combined ecological resources are insufficient, and this solution has not been well applied to the vehicle-mounted system. Summary of the invention

[0007] In order to solve the above problems, the present invention proposes a method, device, vehicle, equipment and medium for recommending vehicle travel information, which combines third-party ecological data, vehicle real-time data and user historical behavior data to recommend travel information for users in a personalized way, thereby improving the user experience.

[0008] The technical solution of the present invention is:

[0009] The present application provides a method for recommending vehicle travel information, including:

[0010] When it is identified that the user has a travel recommendation demand, a travel recommendation model is started; the travel recommendation model is trained based on the user's historical behavior data;

[0011] After the travel recommendation model is started, travel information is recommended to the user based on the user's travel recommendation needs, user historical behavior data, vehicle real-time data and third-party ecological data.

[0012] Preferably, after the travel recommendation model is started, the steps of recommending travel information to the user according to the user's travel recommendation needs, the user's historical behavior data, the vehicle's real-time data and the third-party ecological data include:

[0013] Pre-process vehicle real-time data and third-party ecological data;

[0014] Identify travel destinations and plan travel routes to travel destinations based on users’ travel recommendation needs and historical user behavior data;

[0015] While the vehicle is traveling along the travel route, identifying a recommended service category currently required by the user;

[0016] According to the recommended service category currently required by the user, start the corresponding subtask model;

[0017] After the subtask model is started, service information that matches the user's habits is recommended to the user based on the user's historical behavior data, pre-processed vehicle data, and third-party ecological data;

[0018] Among them, the recommended service category currently required by the user is one of the travel route change recommendation service, charging recommendation service, refueling recommendation service, accommodation recommendation service and attraction recommendation service.

[0019] Preferably, the steps of identifying a travel destination and planning a travel route to the travel destination according to the user's travel recommendation needs and the user's historical behavior data include:

[0020] If the user's travel recommendation needs include a destination, use it as the travel destination;

[0021] If the user's travel recommendation needs do not include a destination, at least one destination that meets the user's travel habits is recommended to the user based on the historical destinations recorded in the user's historical behavior data, and the user selects a travel destination from the at least one destination.

[0022] Preferably, the method for obtaining the travel recommendation model based on user historical behavior data is as follows:

[0023] Perform full model training on the travel recommendation model or fine-tune the subtask model in the travel recommendation model based on user historical behavior data.

[0024] Preferably, the step of preprocessing the vehicle data and the third-party ecological data includes:

[0025] Clean, convert, normalize, discretize, segment and vectorize vehicle data and third-party ecological data.

[0026] Preferably, semantic recognition is performed on the voice data input by the user to identify whether the user has a need for travel recommendations.

[0027] On the other hand, the present application also provides a vehicle travel information recommendation device, comprising:

[0028] A model starting module is used to start a travel recommendation model when it is identified that the user has a travel recommendation demand; the travel recommendation model is trained based on the user's historical behavior data;

[0029] After the travel recommendation model is started, travel information is recommended to the user based on the user's travel recommendation needs, user historical behavior data, vehicle real-time data and third-party ecological data.

[0030] On the other hand, the present application also provides a vehicle, including the above-mentioned vehicle travel information recommendation device.

[0031] On the other hand, the present application also provides a control device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the vehicle travel information recommendation method as described above.

[0032] On the other hand, the present application also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the vehicle travel information recommendation method as described above are implemented.

[0033] The beneficial effects of the present invention are:

[0034] The travel recommendation model is used to provide users with route planning, food recommendations, scenic spot recommendations, hotels, charging stations, gas stations and other service recommendations during self-driving tours to meet the needs of users. It can also calculate mileage, tolls and other data for users based on real map data. In addition, it can actively remind users of risks during their trips and regenerate new self-driving tour guides based on interactions with users. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a recommended method for vehicle travel information;

[0036] Figure 2 is a flow chart for constructing a travel recommendation model in an embodiment of the present application;

[0037] Figure 3 It is a flowchart for constructing a large model of a travel recommendation model in an embodiment of the present application;

[0038] Figure 4 This is a flowchart of fine-tuning the large model of the travel recommendation model in the embodiment of the present application;

[0039] Figure 5 It is a flow chart for processing user voice data in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0041] Combination Figure 1 and Figure 2 In this embodiment, a method for recommending vehicle travel information is provided, including:

[0042] S1, when it is identified that the user has a travel recommendation demand, the travel recommendation model is started; the travel recommendation model is trained based on the user's historical behavior data;

[0043] S2, after the travel recommendation model is started, it recommends travel information to users based on their travel recommendation needs, historical behavior data, real-time vehicle data, and third-party ecological data.

[0044] Among them, the user's need for travel recommendations is determined by performing semantic recognition on the user's voice data.

[0045] Reference Figure 5 When the vehicle is started and the car system is turned on, the user directly says the preset wake-up word or wakes up the car voice processing module through physical buttons.

[0046] The vehicle voice processing module performs signal enhancement on the voice data input by the user. The signal enhancement methods include: improving the signal-to-noise ratio, improving the intelligibility of the voice, and enhancing the loudness of the voice. Specific enhancement methods may include using voice enhancement algorithms, adaptive filtering, echo cancellation, etc. The enhanced voice signal is post-processed, such as dynamic range compression and equalization, to further improve the listening experience of the voice.

[0047] After the voice data signal input by the user is enhanced, the enhanced digital voice signal is preprocessed to improve the accuracy of subsequent processing, including noise reduction (using noise reduction algorithms to remove background noise), voice segmentation (segmenting continuous voice signals into smaller segments or frames), etc. Then, the preprocessed voice data signal is converted into text.

[0048] After the text conversion is completed, semantic understanding is performed. During semantic understanding, the recognized text is preprocessed, including word segmentation, part-of-speech tagging, named entity recognition, etc. Then, natural language processing technology is used to deeply analyze the text to understand its meaning and context. Finally, based on the results of semantic analysis, the user's intention or needs are identified.

[0049] After identifying the user's needs, determine whether it is necessary to start the travel recommendation model; if the travel recommendation model does not need to be started, perform corresponding vehicle control operations, such as navigation, music playback, air conditioning adjustment, etc.; if the travel recommendation model needs to be started, start the travel recommendation model directly.

[0050] Furthermore, when the travel recommendation model does not need to be activated, the processing result is fed back to the user. At this time, the user can continue to have a dialogue, and if the user disagrees with the feedback or needs to modify the operation, the user can give feedback and make corrections through voice commands.

[0051] After the travel recommendation model is started, the step S2 of recommending travel information to the user according to the user's travel recommendation needs, the user's historical behavior data, the vehicle's real-time data and the third-party ecological data includes:

[0052] Pre-process vehicle real-time data and third-party ecological data;

[0053] Identify travel destinations and plan travel routes to travel destinations based on users’ travel recommendation needs and historical user behavior data;

[0054] While the vehicle is traveling along the travel route, identifying a recommended service category currently required by the user;

[0055] According to the recommended service category currently required by the user, start the corresponding subtask model;

[0056] After the subtask model is started, service information that matches the user's habits is recommended to the user based on the user's historical behavior data, pre-processed vehicle data, and third-party ecological data;

[0057] Among them, the recommended service category currently required by the user is one of the travel route change recommendation service, charging recommendation service, refueling recommendation service, accommodation recommendation service and attraction recommendation service.

[0058] The steps for preprocessing vehicle real-time data and third-party ecological data include:

[0059] (1) Data processing

[0060] Data cleaning mainly includes: processing missing values, processing duplicate values ​​and correcting erroneous values. Processing missing values ​​includes: deleting, interpolating (such as mean, median, mode, regression, interpolation, etc.), or using algorithms to predict missing values; processing duplicate values ​​includes: deleting completely duplicate rows or removing duplicates based on certain columns; correcting erroneous values ​​includes: such as spelling errors, format errors, outliers, etc.

[0061] Data transformation mainly involves data standardization, that is, scaling features to the same scale, such as Z-score standardization or Min-Max scaling.

[0062] (2) Data normalization: Scale the features to the range [0,1] and use the maximum and minimum value normalization algorithm. Suppose the numerical variable to be processed is X = [x1, x2…x i ], the normalized variable is Z = [z1,z2…zi ], then:

[0063]

[0064] (3) Discretization (binning): Continuous variables are divided into buckets, such as dividing the SOC at the start of charging into intervals, such as (0-5), (5-20), (20-30), etc.

[0065] (4) Data segmentation: Split unstructured data into smaller parts or segments as needed to facilitate subsequent processing and analysis. For example, split a long document into paragraphs or sentences.

[0066] (5) Text vectorization: Based on the word2vec method, text data is converted into numerical vectors, and sentences are converted into vector representations based on the words in the sentence and the corresponding word vectors. This can be achieved through a variety of methods, such as: simple averaging method: average the word vectors of all words in the sentence to obtain the vector representation of the sentence; weighted averaging method: weighted averaging the word vectors according to the importance of the words in the sentence (such as TF-IDF value) to obtain the vector representation of the sentence; recurrent neural network (RNN): use RNN to model the sequence of words in the sentence to obtain the vector representation of the sentence. This method can capture the sequential relationship between words; pre-trained models such as BERT: use pre-trained models such as BERT to encode sentences to obtain the vector representation of the sentence. This method can capture the contextual information in the sentence.

[0067] (6) Vocabulary construction: All words after word segmentation are constructed into a vocabulary, and each word has a unique index in the vocabulary. Words can be sorted according to their frequency of occurrence in the text, or customized according to business needs.

[0068] The steps of identifying the travel destination and planning the travel route to the travel destination based on the user's travel recommendation needs and the user's historical behavior data include:

[0069] If the user's travel recommendation needs include a destination, use it as the travel destination;

[0070] If the user's travel recommendation needs do not include a destination, at least one destination that meets the user's travel habits is recommended to the user based on the historical destinations recorded in the user's historical behavior data, and the user selects a travel destination from the at least one destination.

[0071] Reference Figure 3 and 4 , the travel recommendation model has the following functions:

[0072] (1) Task scheduling: Based on the voice data input by the user, the specific field that needs to be called is determined, and various tasks such as training tasks, evaluation tasks, and reasoning tasks are allocated and scheduled. In addition, the execution order of tasks is arranged based on resource availability, task priority, and dependencies.

[0073] (2) Resource management: Allocate and use computing resources (CPU, GPU, memory, storage, etc.) to ensure that resources are used efficiently and avoid resource waste and bottlenecks.

[0074] (3) Model management: store and manage various versions of the model, including model weights, configurations, metadata, and log files;

[0075] (4) Model training: Responsible for the model training process, as well as monitoring the training process, recording training logs, and performing early stopping or adjusting training parameters when necessary.

[0076] (5) Call third-party ecological data: return data on attractions, food, hotels, etc.

[0077] (6) Route planning: Use map capabilities to plan self-driving travel routes, including passing points, travel time, driving time and mileage.

[0078] The steps of identifying the travel destination and planning the travel route to the travel destination based on the user's travel recommendation needs and the user's historical behavior data include:

[0079] If the user's travel recommendation needs include a destination, use it as the travel destination;

[0080] If the user's travel recommendation needs do not include a destination, at least one destination that meets the user's travel habits is recommended to the user based on the historical destinations recorded in the user's historical behavior data, and the user selects a travel destination from the at least one destination.

[0081] In the embodiment of the present application, the basic model selected by the selected travel recommendation model is to design the architecture and parameters of the basic model according to specific needs, such as the embedding layer dimension, the number of layers, the activation function, etc. According to the task type and data characteristics, select the appropriate model type, such as the Transformer-based GPT series model. For example, for natural language processing tasks, you can choose a Transformer-based model (such as BERT, GPT, etc.); for image recognition tasks, you can choose a convolutional neural network (CNN) model. Consider the scalability and flexibility of the model so that it can be adjusted and optimized when necessary.

[0082] According to the task type, it is divided into the regular large model training process and the fine-tuning of the large model:

[0083] (1) Conventional large model training:

[0084] 1) Use the preprocessed data to train the model.

[0085] 2) Set the loss function and optimization algorithm. In this solution, the cross entropy loss function and Adam optimizer are selected.

[0086] 3) Optimize the performance of the model through iterative training until the preset stopping conditions are met (such as loss value convergence, accuracy improvement, etc.).

[0087] 4) Model evaluation and tuning: Use the validation set to evaluate the trained model and calculate indicators such as accuracy, recall, and F1 value.

[0088] 5) Fine-tune the model based on the evaluation results, such as adjusting model parameters, adding training data, etc.

[0089] 6) Deployment and maintenance: Deploy the smart travel assistant to the actual environment, regularly collect user data and usage, and continuously update and optimize the model.

[0090] (2) Large model fine-tuning training process

[0091] 1) Data preparation: First, a dataset for a specific task. This dataset contains task-related inputs and expected outputs.

[0092] 2) Select a pre-trained model / base model: Select a suitable pre-trained model based on the nature of the target task and the characteristics of the dataset.

[0093] 3) Set fine-tuning strategy: Fine-tuning is usually done using supervised learning. The model receives these specific input data and then tries to predict the output. Initially, the model's predictions may not be accurate, but as training progresses, the accuracy of the predictions will gradually improve. Depending on the task requirements and available resources, choose an appropriate fine-tuning strategy. Consider whether to perform full or partial fine-tuning, as well as the level and scope of fine-tuning.

[0094] 4) Set hyperparameters: Determine the hyperparameters in the fine-tuning process, such as learning rate, batch size, number of training rounds, etc. The choice of these hyperparameters has an important impact on the performance and convergence speed of fine-tuning.

[0095] 5) Initialize model parameters: Initialize the parameters of the fine-tuned model based on the weights of the pre-trained model. For full fine-tuning, all model parameters will be randomly initialized; for partial fine-tuning, only the parameters of the top or a few layers will be randomly initialized.

[0096] 6) Define the reinforcement learning task: Identify the reinforcement learning task to be solved, including defining the environment, state, action, and reward function.

[0097] 7) Perform fine-tuning training: Use the prepared dataset and fine-tuning strategy to train the model. During the training process, the model parameters are gradually adjusted to minimize the loss function according to the set hyperparameters and optimization algorithm.

[0098] 8) Model evaluation and tuning: During the training process, the model is regularly evaluated using the validation set, and hyperparameters or fine-tuning strategies are adjusted based on the evaluation results. This helps improve the performance and generalization ability of the model.

[0099] 9) Error feedback: The difference between the model's prediction and the true label (correct answer) is called the error. This error is used to adjust the model's internal parameters so that it is closer to the correct answer the next time it predicts. This process is achieved through the back-propagation algorithm, which calculates the gradient of the error to the model parameters and uses an optimization algorithm (such as gradient descent) to update the parameters.

[0100] 10) Iterative Optimization: Through multiple iterations of this process, the model gradually learns how to make more accurate predictions on a specific task. Each iteration uses a portion of the data to update the model parameters, which is called a training batch. The entire dataset will be traversed multiple times until the model's performance on the validation set reaches a preset standard or the maximum number of iterations is reached.

[0101] 11) Test model performance: After fine-tuning is completed, the final fine-tuned model is evaluated using the test set to obtain the final performance metrics. This helps evaluate the performance of the model in real-world applications.

[0102] 12) Model deployment and application: Deploy the fine-tuned model to actual applications and perform further optimization and adjustments to meet actual needs.

[0103] On the other hand, the present application also provides a vehicle travel information recommendation device, comprising:

[0104] A model starting module is used to start a travel recommendation model when it is identified that the user has a travel recommendation demand; the travel recommendation model is trained based on the user's historical behavior data;

[0105] After the travel recommendation model is started, travel information is recommended to the user based on the user's travel recommendation needs, user historical behavior data, vehicle real-time data and third-party ecological data.

[0106] On the other hand, the present application also provides a vehicle, including the above-mentioned vehicle travel information recommendation device.

[0107] On the other hand, the present application also provides a control device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the vehicle travel information recommendation method as described above.

[0108] On the other hand, the present application also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the vehicle travel information recommendation method as described above are implemented.

[0109] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0110] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0111] It should also be noted that, in this article, the orientation or position relationship indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, relational terms such as "first" and "second" are used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations, nor can they be understood as indicating or implying relative importance. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements does not include those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0112] The technical solution provided by the present invention is described in detail above. The principle and implementation mode of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the present invention, and the content of this specification should not be understood as limiting the present invention. At the same time, for those skilled in the art, according to the present invention, there will be different forms of changes in the specific implementation mode and application scope. It is not necessary and impossible to list all the implementation modes here, and the obvious changes or modifications derived therefrom are still within the protection scope of the present invention.

Claims

1. A method for recommending vehicle travel information, characterized in that: include: When it is identified that the user has a need for travel recommendation, the travel recommendation model is started; The travel recommendation model is trained based on user historical behavior data; After the travel recommendation model is started, travel information is recommended to the user based on the user's travel recommendation needs, user historical behavior data, vehicle real-time data and third-party ecological data.

2. The method for recommending vehicle travel information according to claim 1, characterized in that: After the travel recommendation model is started, the steps of recommending travel information to the user according to the user's travel recommendation needs, the user's historical behavior data, the vehicle's real-time data and the third-party ecological data include: Pre-process vehicle real-time data and third-party ecological data; Identify travel destinations and plan travel routes to travel destinations based on users’ travel recommendation needs and historical user behavior data; While the vehicle is traveling along the travel route, identifying a recommended service category currently required by the user; According to the recommended service category currently required by the user, start the corresponding subtask model; After the subtask model is started, service information that matches the user's habits is recommended to the user based on the user's historical behavior data, pre-processed vehicle data, and third-party ecological data; Among them, the recommended service category currently required by the user is one of the travel route change recommendation service, charging recommendation service, refueling recommendation service, accommodation recommendation service and attraction recommendation service.

3. The method for recommending vehicle travel information according to claim 2, characterized in that: The steps of identifying the travel destination and planning the travel route to the travel destination based on the user's travel recommendation needs and the user's historical behavior data include: If the user's travel recommendation needs include a destination, use it as the travel destination; If the user's travel recommendation needs do not include a destination, at least one destination that meets the user's travel habits is recommended to the user based on the historical destinations recorded in the user's historical behavior data, and the user selects a travel destination from the at least one destination.

4. The method for recommending vehicle travel information according to claim 2, characterized in that: The method of obtaining the travel recommendation model based on user historical behavior data is as follows: Perform full model training on the travel recommendation model or fine-tune the subtask model in the travel recommendation model based on user historical behavior data.

5. The method for recommending vehicle travel information according to claim 2, characterized in that: The steps for preprocessing vehicle data and third-party ecological data include: Clean, convert, normalize, discretize, segment and vectorize vehicle data and third-party ecological data.

6. The method for recommending vehicle travel information according to claim 1, characterized in that: By performing semantic recognition on the voice data input by the user, it is possible to identify whether the user has a need for travel recommendations.

7. A vehicle travel information recommendation device, characterized in that: include: A model startup module is used to start the travel recommendation model when it is identified that the user has a travel recommendation demand; The travel recommendation model is trained based on user historical behavior data; After the travel recommendation model is started, travel information is recommended to the user based on the user's travel recommendation needs, user historical behavior data, vehicle real-time data and third-party ecological data.

8. A vehicle, characterized in that: A device for recommending vehicle travel information comprising the vehicle travel information as claimed in claim 7.

9. A control device, characterized in that: It comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the vehicle travel information recommendation method as described in any one of claims 1 to 6.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by the processor, the steps of the method for recommending vehicle travel information as described in any one of claims 1 to 6 are implemented.

Images