Travel note generation method and device, equipment, storage medium and vehicle

Abstract

The invention discloses a travel note generation method and device, equipment, a storage medium and a vehicle, and the method comprises the steps: generating travel note elements corresponding to user operation information according to the user operation information collected by the vehicle in a target path, and generating a travel note corresponding to the target path based on the travel note elements. According to the embodiment of the invention, the related travel note elements are automatically generated in real time in the vehicle driving process according to the operation information of the user on the vehicle, the travel note is automatically generated based on the travel note elements, the travel note does not need to be written manually, the time consumed by the user to write the travel note can be reduced, and the user experience is improved due to the fact that the travel note elements are generated in real time in the vehicle driving process. Therefore, compared with the mode that the user arranges the travel notes after playing, the mode of generating the travel notes in real time is more in line with the actual touring experience, and the readability is higher.

Description

Technical Field

[0001] This application belongs to the field of vehicle information technology, and particularly relates to a travel note generation method, device, equipment, storage medium, and vehicle. Background Art

[0002] A travel note is a style of writing that records what one sees and hears during a trip. When users travel, they usually record the process of their trips by writing travel notes.

[0003] As the popularity of cars increases, more and more people choose self-driving tours when traveling. Usually, during a self-driving tour, multiple scenic spots will be passed by. If users manually write travel notes for each scenic spot, it will take a long time. Moreover, when arriving at a scenic spot, users are often busy with on-site sightseeing, and the organization and writing of travel notes usually occur after the visit or even after a period of time. In this way, for users, the memories of the trip are usually only stored in the mobile phone album or the album of a digital camera, and they may have forgotten the names of the scenic spots corresponding to the pictures. Therefore, when users organize their travel notes after the trip, it is not only inconvenient, but also due to the lack of experience in writing travel notes, the readability of the organized travel notes is not high. Summary of the Invention

[0004] Embodiments of this application provide a travel note generation method, device, equipment, storage medium, and vehicle, which can automatically generate travel notes during driving, reduce the time consumed by users in writing travel notes, and improve the readability of travel notes.

[0005] In a first aspect, embodiments of this application provide a travel note generation method, including:

[0006] Obtain user operation information collected when the vehicle travels on a target path;

[0007] Generate travel note elements corresponding to the user operation information, where the travel note elements include relevant information for generating travel notes;

[0008] Generate a travel note corresponding to the target path based on the travel note elements.

[0009] In a second aspect, embodiments of this application provide a travel note generation device, including:

[0010] An obtaining module, configured to obtain user operation information collected when the vehicle travels on a target path;

[0011] An element generation module, configured to generate travel note elements corresponding to the user operation information, where the travel note elements include relevant information for generating travel notes;

[0012] A travel note generation module, configured to generate a travel note corresponding to the target path based on the travel note elements.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, which includes: a processor and a memory storing computer program instructions;

[0014] When the processor executes the computer program instructions, the steps of the travel note generation method as in the first aspect are implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the steps of the travel note generation method as in the first aspect are implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a vehicle, including the travel note generation device as in the second aspect.

[0017] For the travel note generation method, device, equipment, storage medium and vehicle in the embodiments of the present application, according to the user operation information collected by the vehicle in the target path, travel note elements corresponding to the user operation information are generated, and a travel note corresponding to the target path is generated based on the travel note elements. According to the embodiments of the present application, relevant travel note elements are automatically generated in real time during the vehicle driving process according to the user operation information of the vehicle, and a travel note is automatically generated based on the travel note elements, without the need for manual writing of the travel note, which can reduce the time consumed by the user in writing the travel note. Moreover, since the travel note elements are generated in real time during the vehicle driving process, they are directly related to the vehicle driving path. Thus, compared with the user sorting out the travel note after the tour, this real-time generation of the travel note is more in line with the actual tour experience and has higher readability. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of the travel note generation method provided by an embodiment of the present application;

[0020] Figure 2 is a logical diagram of travel note generation provided by an embodiment of the present application;

[0021] Figure 3 is a structural diagram of the travel note generation device provided by an embodiment of the present application;

[0022] Figure 4 is a structural diagram of the electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] To better understand the above objects, features, and advantages of the present disclosure, the solutions of the present disclosure will be further described below. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments may be combined with each other.

[0024] In the following description, many specific details are set forth to facilitate a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0025] It should be noted that, in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the said element.

[0026] See Figure 1 , which is a schematic flowchart of a travel note generation method provided by an embodiment of the present application. The execution subject of this method may be a vehicle controller, such as Figure 1 shown, and this method may include the following steps S11 - S13.

[0027] S11. Obtain user operation information when the vehicle is traveling on a target path.

[0028] Here, the user operation information refers to information related to the operations of the user, that is, the driver, during the vehicle's travel, including but not limited to vehicle control information, path point of interest information, user voice information, etc.

[0029] In some embodiments of the present application, when the user is driving the vehicle, the navigation system is usually turned on, and the starting point and the ending point are set in the navigation system. The navigation system can generate a corresponding path based on the starting point and the ending point set by the user. Based on this, the target path in S11 may be the path planned in the vehicle's navigation system.

[0030] In some embodiments of the present application, when the distance between the starting point and the ending point is relatively long, the user can also set a rest stop point in addition to the starting point and the ending point in the navigation system. Thus, the navigation system can generate a route based on the starting point, the ending point, and the rest stop point set by the user. The generated route can be divided into multiple sub-routes with the rest stop point as the dividing point. Based on this, the target route in S11 can also be any sub-route.

[0031] When the user uses the vehicle, corresponding vehicle control information, route points of interest, etc. can be set for the target route according to actual needs. Among them, the vehicle control information can include the driving mode of the vehicle, the music being played, etc. The route point of interest refers to the Point of Interest (POI) in the route, which can be a house, a store, a hospital, a bus stop, a service area, a scenic spot, etc. In addition, during the vehicle driving process, the voice collection device in the vehicle can be turned on to collect the user's voice information. Based on this, during the vehicle driving on the target route, vehicle user operation information, route point of interest information, user voice information, etc. can be obtained. Among them, the route point of interest information can include the attribute information and characteristics of the points of interest on the road. The attribute information of the point of interest can include, but is not limited to, the name of the point of interest, the type of the point of interest, longitude, latitude information, etc. The type of the point of interest can include, but is not limited to: scenic spots, hospitals, service areas, bus stops, buildings, etc. The characteristics of the point of interest can include, but is not limited to: natural scenery, historical relics, empty roads, etc.

[0032] In some embodiments of the present application, an API (Application Programming Interface) for [travel note mode service] can be pre-set in the vehicle. When the user needs to generate a travel note, the user can obtain the vehicle user operation information through this API.

[0033] S12. Generate travel note elements corresponding to the user operation information. The travel note elements include relevant information for generating a travel note.

[0034] Here, the travel note elements refer to the elements required to generate a travel note, including but not limited to background music, pictures, videos, titles, copywriting, etc.

[0035] In some embodiments of the present application, after obtaining the vehicle user operation information on the target route, travel note elements corresponding to the user operation information and conforming to the user's habits can be generated based on the user operation information.

[0036] As a possible implementation, when the user operation information includes vehicle control information, the vehicle control information includes the driving mode and the played music, and the travel note elements include background music, generating travel note elements corresponding to the user operation information may include:

[0037] Input the driving mode and the played music into a music prediction model to obtain the target music features corresponding to the driving mode and the played music output by the music prediction model. The music prediction model is trained based on the historical vehicle control information of the vehicle, the music features of the historical vehicle control information, and the user's background music satisfaction. The background music satisfaction is used to indicate the degree of satisfaction of the user with the background music determined based on the music features of the historical vehicle control information;

[0038] Search for the target music that matches the target music features from a preset music library. The music library stores music with music features;

[0039] Use the target music as the background music corresponding to the vehicle control information in the travel note elements.

[0040] Among them, the degree of satisfaction can be divided into satisfied, dissatisfied, average, etc.

[0041] In some embodiments of the present application, the music prediction model can be pre-trained based on the historical vehicle control information of the vehicle, the music features of the historical vehicle control information, and the user's background music satisfaction. After obtaining the music prediction model, the music prediction model can be stored in a specified location, such as stored in a travel note server, where the travel note server is a server related to the travel note mode service. In this way, when it is necessary to generate the background music corresponding to the vehicle control information, the music prediction model can be directly called from the specified location, and then the music features corresponding to the vehicle control information can be predicted based on the music prediction model, so as to obtain the background music that matches the predicted music features from the music library.

[0042] Obtaining the background music based on the music prediction model has high efficiency, good accuracy, and makes the obtained background music more in line with the user's music preferences.

[0043] Among them, the driving modes include but are not limited to: sports mode, energy-saving mode, snow mode, off-road mode, normal mode, etc. Generally, users can use different driving modes in different scenarios, and the music styles that users like are usually different in different scenarios. Therefore, there is a certain correlation between the driving modes used by users and the music they like. For example, when the user is on an off-road road, the off-road mode can be used. When off-roading, the user may like some dynamic music. So it can be considered that the user likes dynamic music in the off-road mode; when the user is driving on snow, the snow mode can be used. When driving on snow, the road conditions are poor, so the user's spirit will be relatively tense. Therefore, some soothing music can be listened to at this time to relieve the tension. Therefore, it can be considered that the user likes soothing music in the snow mode; when the user is driving on urban roads, the normal mode can be used. When driving on urban roads, the user can listen to some lively music to adjust the mood. Therefore, it can be considered that the user likes lively music in the normal mode.

[0044] In this embodiment, the music features may include but are not limited to: music type, singer, language, etc. Among them, the music types include but are not limited to soothing, lively, dynamic, etc.

[0045] In some embodiments of the present application, when training the music prediction model, the following steps may be included:

[0046] Determine the initial model. The initial model can be a machine learning model, including but not limited to a neural network model;

[0047] Obtain multiple historical vehicle control information of the vehicle, the music features of each historical vehicle control information, and the user's background music satisfaction. The background music satisfaction is used to indicate the degree of satisfaction of the user with the background music found from the preset music library based on the music features of the historical vehicle control information;

[0048] Construct multiple sets of training data based on the obtained multiple historical vehicle control information, the music features of each historical vehicle control information, and the user's background music satisfaction. Each set of training data includes a historical vehicle control information, the music features corresponding to the historical vehicle control information, and the user's background music satisfaction; train the initial model based on the multiple sets of training data. During the training process, input the historical vehicle control information in the training data into the initial model to obtain the music features output by the initial model. Based on the music features and background music satisfaction in the training data, determine whether the satisfaction of the user with the background music determined based on the music features output by the initial model meets the preset satisfaction requirements. If not, adjust the parameters of the initial model and then continue to train the initial model using the training data until the satisfaction of the user with the background music determined based on the music features output by the initial model meets the preset satisfaction requirements, and then stop the training;

[0049] Use the initial model obtained after stopping the training as the music prediction model.

[0050] In some embodiments of the present application, based on the music features in the training data and the satisfaction with the background music, determining whether the satisfaction of the user with the background music determined based on the music features output by the initial model meets the preset satisfaction requirement may include:

[0051] Calculate the similarity between the music features output by the initial model and the music features in the training data;

[0052] When the similarity is greater than the preset similarity threshold and the satisfaction with the background music in the training data meets the preset satisfaction requirement, determine that the satisfaction of the user with the background music determined based on the music features output by the initial model also meets the preset satisfaction requirement;

[0053] When the similarity is not greater than the preset similarity threshold and the satisfaction with the background music in the training data meets the preset satisfaction requirement, determine that the satisfaction of the user with the background music determined based on the music features output by the initial model does not meet the preset satisfaction requirement;

[0054] When the similarity is greater than the preset similarity threshold and the satisfaction with the background music in the training data does not meet the preset satisfaction requirement, determine that the satisfaction of the user with the background music determined based on the music features output by the initial model also does not meet the preset satisfaction requirement;

[0055] When the similarity is not greater than the preset similarity threshold and the satisfaction with the background music in the training data does not meet the preset satisfaction requirement, it can be determined that the satisfaction of the user with the background music determined based on the music features output by the initial model meets the preset satisfaction requirement.

[0056] In this way, the music prediction model can predict the corresponding music features based on the vehicle control information, and the background music obtained based on the music features meets the user's music preferences.

[0057] As a possible implementation, when the user operation information includes path point-of-interest information, the path point-of-interest information includes the attribute information of the points of interest in the path and the characteristics of the points of interest, and the travel note elements include a title, generating travel note elements corresponding to the user operation information may include:

[0058] Input the point of interest information into the title prediction model to obtain the target point of interest features corresponding to the path point of interest information output by the title prediction model. The title prediction model is trained based on the historical path point of interest information of the vehicle, the point of interest features of the historical path point of interest information, and the user's title satisfaction. The title satisfaction is used to indicate the degree of satisfaction of the user with the title determined based on the point of interest features of the historical path point of interest information.

[0059] Search for a title that matches the target point of interest features in a preset title library. The title library stores titles with point of interest features.

[0060] Use the title that matches the target point of interest features as the title corresponding to the path point of interest information in the travel notes elements.

[0061] In this embodiment, the point of interest feature is a feature that can characterize the characteristics of the point of interest.

[0062] In some embodiments of the present application, the title prediction model can be pre-trained based on the historical path point of interest information of the vehicle, the point of interest features of the historical path point of interest information, and the user's title satisfaction. After obtaining the title prediction model, the title prediction model can be stored at a specified location, such as stored in a travel notes server. In this way, when a title corresponding to the path point of interest information needs to be generated, the title prediction model can be directly called from the specified location, and then the point of interest features corresponding to the path point of interest information can be predicted based on the title prediction model, so as to obtain a title that matches the predicted point of interest features from the title library.

[0063] Obtaining a title based on the title prediction model is efficient, accurate, and makes the obtained title more in line with the user's title preference.

[0064] In some embodiments of the present application, when training the title prediction model, the following steps may be included:

[0065] Determine an initial model. The initial model can be a machine learning model, including but not limited to a neural network model.

[0066] Obtain multiple historical path point of interest information of the vehicle, the point of interest features of each historical path point of interest information, and the user's title satisfaction. The title satisfaction is used to indicate the degree of satisfaction of the user with the title found from the preset title library based on the point of interest features of the historical vehicle control information.

[0067] Construct multiple sets of training data based on the obtained multiple historical path point of interest information, the point of interest features of each historical path point of interest information, and the user's title satisfaction. Each set of training data includes a historical path point of interest information, the point of interest features corresponding to the historical path point of interest information, and the user's title satisfaction.

[0068] The initial model is trained based on multiple sets of training data. During the training process, the historical path point of interest information in the training data is input into the initial model to obtain the point of interest features output by the initial model. Based on the point of interest features in the training data and the title satisfaction degree, it is determined whether the satisfaction degree of the user with respect to the title determined based on the point of interest features output by the initial model meets the preset satisfaction requirement. If not, after adjusting the parameters of the initial model, the initial model is continuously trained using the training data until the satisfaction degree of the user with respect to the title determined based on the point of interest features output by the initial model meets the preset satisfaction requirement, and then the training is stopped;

[0069] The initial model obtained after the training stops is used as the title prediction model.

[0070] Among them, the manner of determining whether the satisfaction degree of the user with respect to the title determined based on the point of interest features output by the initial model meets the preset satisfaction requirement based on the point of interest features in the training data and the title satisfaction degree is similar to the manner of determining whether the satisfaction degree of the user with respect to the background music determined based on the music features output by the initial model meets the preset satisfaction requirement based on the music features in the training data and the background music satisfaction degree. To avoid repetition, it will not be elaborated here.

[0071] In this way, the title prediction model can predict the corresponding point of interest features based on the path point of interest information, and the title obtained based on the point of interest features meets the user's title preference.

[0072] As a possible implementation manner, considering that the user may be accustomed to taking pictures at certain specific points of interest, so in the case where the user operation information includes path point of interest information and the travel note elements include pictures and / or videos, generating travel note elements corresponding to the user operation information may include the following steps:

[0073] Input the path point of interest information into the shooting prediction model to obtain the first shooting features corresponding to the path point of interest information output by the shooting prediction model. The first shooting features include shooting parameters and / or video recording parameters. The shooting prediction model is trained based on the historical path point of interest information in the vehicle, the shooting features of the historical path point of interest information, and the user's first shooting result satisfaction degree. The first shooting result satisfaction degree is used to indicate the satisfaction degree of the user with respect to the pictures and / or videos taken based on the shooting features of the historical path point of interest information;

[0074] Control the image acquisition device in the vehicle to perform image acquisition based on the first shooting features to obtain the first pictures and / or the first videos;

[0075] Use the first pictures and / or the first videos as the pictures / or videos corresponding to the path point of interest information in the travel note elements.

[0076] In this embodiment, the photographing parameters may include a photographing instruction and photographing parameters such as a photographing start position and a photographing interval time point; the video recording parameters may include a video recording instruction and video recording parameters such as a video recording time point and a recording duration.

[0077] In some embodiments of the present application, the shooting prediction model may be pre-trained based on historical path interest point information in the vehicle, shooting features of the historical path interest point information, and the user's first shooting result satisfaction. After obtaining the shooting prediction model, the shooting prediction model may be stored at a specified location, such as stored in a travel note server. Thus, when it is necessary to generate pictures and / or videos corresponding to the path interest point information, the shooting prediction model may be directly called from the specified location, and then the first shooting features corresponding to the path interest point information may be predicted based on the shooting prediction model, so as to control an image acquisition device in the vehicle to perform image acquisition based on the first shooting features, thereby obtaining the first pictures and / or the first videos.

[0078] Obtaining pictures and / or videos based on the shooting prediction model is efficient, accurate, and makes the obtained pictures and / or videos more in line with the user's picture and / or video preferences.

[0079] In some embodiments of the present application, when training the shooting prediction model, the following steps may be included:

[0080] Determine an initial model, and the initial model may be a machine learning model, including but not limited to a neural network model;

[0081] Obtain a plurality of historical path interest point information of the vehicle, shooting features of each historical path interest point information, and the user's first shooting result satisfaction, where the first shooting result satisfaction is used to indicate the degree of satisfaction of the user with the pictures and / or videos taken based on the shooting features of the historical vehicle control information;

[0082] Construct multiple groups of training data based on the obtained plurality of historical path interest point information, shooting features of each historical path interest point information, and the user's first shooting result satisfaction, and each group of training data includes a historical path interest point information, the shooting features corresponding to the historical path interest point information, and the user's first shooting result satisfaction;

[0083] Train the initial model based on multiple sets of training data. During the training process, input the historical path POI information in the training data into the initial model to obtain the shooting features output by the initial model. Determine whether the pictures and / or videos taken based on the shooting features output by the initial model meet the preset satisfaction requirements based on the shooting features in the training data and the first shooting result satisfaction. If not, adjust the parameters of the initial model and then continue to train the initial model using the training data until the satisfaction of the user with the title determined based on the shooting features output by the initial model meets the preset satisfaction requirements, and then stop the training;

[0084] Use the initial model obtained after the training stops as the shooting prediction model.

[0085] Similarly, the method for determining whether the pictures and / or videos taken based on the shooting features output by the initial model meet the preset satisfaction requirements based on the shooting features in the training data and the first shooting result satisfaction is similar to the method for determining whether the satisfaction of the user with the background music determined based on the music features output by the initial model meets the preset satisfaction requirements based on the music features in the training data and the background music satisfaction. To avoid repetition, the storage will not be elaborated here.

[0086] In this way, the shooting prediction model can predict the corresponding shooting features based on the path POI information, and the pictures and / or videos taken based on the shooting features meet the user's shooting preferences.

[0087] As a possible implementation, considering that the user may send voice information for instructing the vehicle to take pictures or voice information with a shooting intention during the vehicle driving, such as voice information like "Take a picture" or "It would be great if I could take a picture", when the user operation information includes the user voice information and the travel notes elements include pictures and / or videos, generating the travel notes elements corresponding to the user operation information may include the following steps:

[0088] Input the user voice information into the first voice intention prediction model to obtain the second shooting features corresponding to the user voice information output by the first voice intention prediction model. The second shooting features include photo-taking parameters and / or video-recording parameters. The first voice intention prediction model is trained based on the historical user voice information in the vehicle, the shooting features of the historical user voice information, and the user's second shooting result satisfaction. The second shooting result satisfaction is used to indicate the satisfaction degree of the user with the pictures and / or videos taken based on the shooting features of the historical user voice information;

[0089] Control the image acquisition device in the vehicle to perform image acquisition based on the second shooting features to obtain the second pictures and / or second videos;

[0090] Use the second picture and / or the second video as the picture / video corresponding to the user voice information in the travel notes elements.

[0091] In this embodiment, the second shooting feature may also include shooting parameters and / or video recording parameters. Similar to the first shooting feature, the shooting parameters may include a shooting instruction, a shooting start position, a shooting interval time point, and other shooting parameters; the video recording parameters may include a video recording instruction, a video recording time point, a recording duration, and other video recording parameters.

[0092] In some embodiments of the present application, the first voice intention prediction model may be pre-trained based on the historical user voice information of the vehicle, the shooting features of the historical user voice information, and the user's shooting result satisfaction. After obtaining the first voice intention prediction model, the first voice intention prediction model may be stored at a specified location, such as stored in a travel notes server. Thus, when it is necessary to generate a picture and / or a video corresponding to the user voice information, the first voice intention prediction model may be directly called from the specified location, and then the shooting features corresponding to the user voice information may be predicted based on the first voice intention prediction model, so as to control the image acquisition device in the vehicle to perform image acquisition based on the shooting features and obtain the corresponding picture and / or video.

[0093] Obtaining pictures and / or videos based on the first voice intention prediction model is efficient, accurate, and makes the obtained pictures and / or videos more in line with the user's picture and / or video preferences.

[0094] In some embodiments of the present application, when training the first voice intention prediction model, the following steps may be included:

[0095] Determine an initial model, and the initial model may be a machine learning model, including but not limited to a neural network model;

[0096] Obtain multiple historical user voice information of the vehicle, the shooting features of each historical user voice information, and the user's shooting result satisfaction, where the shooting result satisfaction is used to indicate the degree of satisfaction of the user with the picture and / or video obtained by shooting based on the shooting features of the historical vehicle control information;

[0097] Construct multiple groups of training data based on the obtained multiple historical user voice information, the shooting features of each historical user voice information, and the user's shooting result satisfaction. Each group of training data includes a historical user voice information, the shooting features corresponding to the historical user voice information, and the user's shooting result satisfaction;

[0098] Train the initial model based on multiple sets of training data. During the training process, input the historical user voice information in the training data into the initial model to obtain the shooting features output by the initial model. Determine whether the satisfaction of the user with the pictures and / or videos taken based on the shooting features output by the initial model meets the preset satisfaction requirements based on the shooting features in the training data and the satisfaction of the shooting results. If not, adjust the parameters of the initial model and then continue to train the initial model using the training data until the satisfaction of the user with the pictures and / or videos taken based on the shooting features output by the initial model meets the preset satisfaction requirements, and then stop the training;

[0099] Take the initial model obtained after the training stops as the first voice intent prediction model.

[0100] Similarly, the method for determining whether the satisfaction of the user with the pictures and / or videos taken based on the shooting features output by the initial model meets the preset satisfaction requirements based on the shooting features in the training data and the satisfaction of the shooting results is similar to the method for determining whether the satisfaction of the user with the background music determined based on the music features output by the initial model meets the preset satisfaction requirements based on the music features in the training data and the satisfaction of the background music. To avoid repetition, the storage will not be elaborated here.

[0101] In this way, the first voice intent prediction model can predict the corresponding shooting features based on the user voice information, and the pictures and / or videos taken based on the shooting features meet the user's pictures and / or video preferences.

[0102] As a possible implementation, when the user operation information includes path interest point information and / or user voice information and the travel notes elements also include copywriting, generating the travel notes elements corresponding to the user operation information may further include the following steps:

[0103] After obtaining the pictures and / or videos corresponding to the user operation information, use a preset image recognition model to extract the image features of the pictures and / or videos to obtain the target image features, where the target image features include at least one of the following: the style of the pictures and / or videos, the objects included in the pictures and / or videos;

[0104] Search for the first copywriting that matches the target image features in a preset copywriting library, where the copywriting library stores copywriting with image features;

[0105] Take the first copywriting as the copywriting corresponding to the user operation information in the travel notes elements.

[0106] Among them, the image recognition model may include an AI (Artificial Intelligence) model, such as a GPT (Generative Pre-trained Transformer) model, etc.

[0107] Through the above method, it is possible to realize writing a description based on pictures, generating a text corresponding to the captured picture and / or video, making the travelogue content more abundant.

[0108] As a possible implementation, considering that during the vehicle driving process, the user may also send some voice messages for expressing emotions with emotional colors, such as voice messages like "I'm in a great mood today" and "Had a great time", when the user operation information includes the user voice information and the travelogue element includes the text, generating the travelogue element corresponding to the user operation information may include the following steps:

[0109] Input the user voice information into the second voice intention prediction model to obtain the target expression intention feature corresponding to the user voice information output by the second voice intention prediction model. The second voice intention prediction model is trained based on the historical user voice information in the vehicle, the expression intention feature of the historical user voice information, and the user's copywriting satisfaction. The copywriting satisfaction is used to indicate the degree of satisfaction of the user with the text determined based on the expression intention feature of the historical user voice information;

[0110] Search for a second text in the preset text library that matches the target expression intention feature. The text library stores texts with expression intention features;

[0111] Use the second text as the text corresponding to the user's voice information in the travelogue element.

[0112] Among them, the expression intention feature may include features that can characterize the intention the user wants to express, including but not limited to: the user's emotion, control instructions, etc.

[0113] In some embodiments of the present application, the second voice intention prediction model can be pre-trained based on the historical user voice information in the vehicle, the expression intention feature of the historical user voice information, and the user's copywriting satisfaction. After obtaining the second voice intention prediction model, the second voice intention prediction model can be stored at a specified location, such as stored in the travelogue server. In this way, when it is necessary to generate a text corresponding to the user voice information, the second voice intention prediction model can be directly called from the specified location, and then the expression intention feature corresponding to the user voice information is predicted based on the second voice intention prediction model, so as to obtain the corresponding text from the text library based on the expression intention feature.

[0114] Obtaining a copywriting based on the second voice intent prediction model is efficient, accurate, and makes the obtained copywriting more in line with the user's expression intent and copywriting preference.

[0115] In some embodiments of the present application, when training the second voice intent prediction model, the following steps may be included:

[0116] Determine an initial model, which may be a machine learning model, including but not limited to a neural network model;

[0117] Obtain multiple historical user voice information of the vehicle, the expression intent features of each historical user voice information, and the user's copywriting satisfaction, where the copywriting satisfaction is used to indicate the degree of satisfaction of the user with the copywriting obtained from the copywriting library based on the expression intent features of the historical vehicle control information;

[0118] Construct multiple sets of training data based on the obtained multiple historical user voice information, the expression intent features of each historical user voice information, and the user's copywriting satisfaction. Each set of training data includes a historical user voice information and the corresponding expression intent feature and the user's copywriting satisfaction of this historical user voice information;

[0119] Train the initial model based on multiple sets of training data. During the training process, input the historical user voice information in the training data into the initial model to obtain the expression intent features output by the initial model. Based on the expression intent features and copywriting satisfaction in this training data, determine whether the satisfaction of the user with the copywriting obtained based on the expression intent features output by the initial model meets the preset satisfaction requirement. If not, after adjusting the parameters of the initial model, continue to train the initial model using the training data until the satisfaction of the user with the copywriting captured based on the expression intent features output by the initial model meets the preset satisfaction requirement, and then stop the training;

[0120] Use the initial model obtained after the training stops as the second voice intent prediction model.

[0121] Similarly, the method for determining whether the satisfaction of the user with the copywriting obtained based on the expression intent features output by the initial model meets the preset satisfaction requirement based on the expression intent features and copywriting satisfaction in this training data is similar to the method for determining whether the satisfaction of the user with the background music determined based on the music features output by the initial model meets the preset satisfaction requirement based on the music features and background music satisfaction in the training data. To avoid repetition, it will not be elaborated here.

[0122] In this way, the second voice intent prediction model can predict the corresponding expression intent features based on the user voice information, and the copywriting captured based on the expression intent features meets the user's copywriting preference.

[0123] S13. Generate a travelogue corresponding to the target path based on travelogue elements.

[0124] In this embodiment, after obtaining the required travelogue elements, a travelogue corresponding to the target path can be generated using the travelogue elements based on the predicted travelogue generation rules.

[0125] In some embodiments of the present application, a travelogue template can be set in advance according to actual needs. The travelogue template includes filling positions corresponding to each travelogue element. After obtaining the travelogue elements, a travelogue corresponding to the target path and conforming to the travelogue template is generated by adding the travelogue elements to the corresponding filling positions in the travelogue template.

[0126] The travelogue generation method provided in this embodiment generates travelogue elements corresponding to the user operation information according to the user operation information of the vehicle in the target path. The travelogue corresponding to the target path can be obtained by combining the travelogue elements. According to the embodiments of the present application, relevant travelogue elements are automatically generated in real time during the vehicle driving process according to the user operation information of the vehicle, and the travelogue is automatically generated based on the travelogue elements without manual writing of the travelogue, which can reduce the time consumed by the user in writing the travelogue. Moreover, since the travelogue elements are generated in real time during the vehicle driving process, they are directly related to the vehicle driving path. Thus, compared with the user sorting out the travelogue after the trip, this real-time generation of the travelogue is more in line with the actual tour experience and has higher readability.

[0127] As a possible implementation manner, after obtaining the travelogue corresponding to the target path, the following steps can also be performed:

[0128] Upload the travelogue and the obtained user operation information of the vehicle to the travelogue server so that the travelogue client can obtain the travelogue from the travelogue server.

[0129] In some embodiments of the present application, after the travelogue is generated, the travelogue can be bound to the user operation information of the vehicle and then uploaded to the travelogue server, which can be a cloud server. Thus, the user can pull the travelogue from the travelogue server through the travelogue client on the mobile phone or in-vehicle computer to perform operations such as browsing, editing, and publishing to the community.

[0130] Further, after the user edits the travelogue, the edited travelogue can be used to replace the travelogue before editing and stored in the travelogue server so that the edited travelogue can be obtained subsequently.

[0131] In addition, when browsing travelogues, users can rate their satisfaction with each travelogue element in the travelogue, so as to obtain the user satisfaction with each travelogue element. The satisfaction of each travelogue element is uploaded to the travelogue server, and the travelogue server can correspondingly store the user satisfaction with the travelogue element, the user operation information for generating the travelogue element, and the features related to the travelogue element extracted from the user operation information. In this way, after a preset time interval, the relevant models used in the travelogue generation process can be retrained based on the relevant content stored in the travelogue server to improve the accuracy of the models.

[0132] See Figure 2 , which is a schematic diagram of the travelogue generation logic in a certain application scenario. Taking the user operation information of a vehicle including vehicle control information, path interest point information, and user voice information, and the travelogue elements including background music, pictures, videos, titles, and copywriting as examples.

[0133] Such as Figure 2As shown, the acquired data includes driving mode, played music, path point-of-interest information, and user voice information. The driving mode and played music of the vehicle are input into the music prediction model to obtain music features, and the music matching the music features is searched from the music library as the background music in the travelogue elements. The path point-of-interest information is input into the title prediction model and the shooting prediction model respectively, and the point-of-interest features output by the title prediction model and the first shooting features output by the shooting prediction model are obtained. The title matching the point-of-interest features is searched from the title library as the title in the travelogue elements, and based on the first shooting features, the image acquisition device of the vehicle is controlled to take pictures and / or videos as the pictures and / or videos in the travelogue elements. The voice information is input into the first voice intention prediction model and the second voice intention prediction model respectively, and the second shooting features output by the first voice intention prediction model and the expression intention features output by the second voice intention prediction model are obtained. Based on the second shooting features, the image acquisition device of the vehicle is controlled to take pictures and / or videos as the pictures and / or videos in the travelogue elements, and the copywriting matching the expression intention features is searched from the copywriting library as the copywriting in the travelogue elements. Further, the taken pictures and / or videos are output to the image recognition model, and the image features output by the image recognition model are obtained. The copywriting matching the image features is searched from the copywriting library as the copywriting in the travelogue elements. After obtaining all the required travelogue elements, the travelogue elements are combined based on the preset travelogue generation rules to obtain a travelogue, and the travelogue is uploaded to the travelogue server. In this way, the user can pull the travelogue from the travelogue server through the travelogue client to perform operations such as browsing, editing, and publishing the travelogue. In addition, the user can also score the satisfaction of the travelogue elements in the travelogue through the travelogue client to obtain the user's satisfaction with each travelogue element, and the user's satisfaction with each travelogue element is transmitted back to the travelogue server. In this way, the travelogue server can train each model used based on the user operation information corresponding to the travelogue and the user's satisfaction with each travelogue element to improve the accuracy of the model.

[0134] Based on the travelogue generation method provided in the above embodiment, correspondingly, the present application also provides a specific implementation manner of the travelogue generation device. Please refer to the following embodiments.

[0135] See Figure 3 , the travelogue generation device provided in the embodiment of the present application includes the following modules:

[0136] The acquisition module 301 is configured to acquire user operation information when the vehicle is driving on the target path;

[0137] The element generation module 302 is configured to generate travelogue elements corresponding to the user operation information, and the travelogue elements include relevant information for generating a travelogue;

[0138] The travelogue generation module 303 is configured to generate a travelogue corresponding to the target path based on the travelogue elements.

[0139] The travel note generation device provided in this embodiment generates travel note elements corresponding to the user operation information according to the user operation information collected by the vehicle on the target path, and the travel note corresponding to the target path can be obtained by combining the travel note elements. According to the embodiments of the present application, relevant travel note elements are automatically generated in real time during the vehicle driving process according to the operation information of the user on the vehicle, and the travel note is automatically generated based on the travel note elements, without the need for manual writing of the travel note, which can reduce the time consumed by the user in writing the travel note. Moreover, since the travel note elements are generated in real time during the vehicle driving process, they are directly related to the vehicle driving path. Therefore, compared with the user sorting out the travel note after the play, this way of generating the travel note in real time is more in line with the actual tour experience and has higher readability.

[0140] As a possible implementation manner, the user operation information includes at least one of the following: vehicle control information, path interest point information, and user voice information.

[0141] As a possible implementation manner, the travel note elements include at least one of the following: background music, pictures, videos, titles, and copywriting.

[0142] As a possible implementation manner, the user operation information includes vehicle control information, and the vehicle control information includes the driving mode and the played music. The travel note element includes background music. The element generation module 302 is specifically configured to:

[0143] Input the driving mode and the played music into the music prediction model to obtain the target music feature corresponding to the driving mode and the played music output by the music prediction model. The music prediction model is trained based on the historical vehicle control information of the vehicle, the music feature of the historical vehicle control information, and the user's background music satisfaction degree. The background music satisfaction degree is used to indicate the satisfaction degree of the user with the background music determined based on the music feature of the historical vehicle control information;

[0144] Search for the target music matching the target music feature in the preset music library, and the music library stores the music with music features;

[0145] Use the target music as the background music corresponding to the vehicle control information in the travel note element.

[0146] As a possible implementation manner, the user operation information includes path interest point information, and the path interest point information includes the interest points in the path and the characteristics of the interest points. The travel note element includes a title. The element generation module 302 is specifically configured to:

[0147] Input the path point of interest information into the title prediction model to obtain the target point of interest features corresponding to the path point of interest information output by the title prediction model. The title prediction model is trained based on the vehicle's historical path point of interest information, the point of interest features of the historical path point of interest information, and the user's title satisfaction. The title satisfaction is used to indicate the degree of satisfaction of the user with the title determined based on the point of interest features of the historical path point of interest information;

[0148] Search for a title that matches the target point of interest features in a preset title library. The title library stores titles with point of interest features;

[0149] Use the title that matches the target point of interest features as the title corresponding to the path point of interest information in the travel notes elements.

[0150] As a possible implementation, the user operation information includes path point of interest information. The path point of interest information includes information about the points of interest (POIs) in the path. The travel notes elements include pictures and / or videos. The element generation module 302 is specifically configured to:

[0151] Input the path point of interest information into the shooting prediction model to obtain the first shooting features corresponding to the path point of interest information output by the shooting prediction model. The first shooting features include shooting parameters and / or video recording parameters. The shooting prediction model is trained based on the historical path point of interest information in the vehicle, the shooting features of the historical path point of interest information, and the user's first shooting result satisfaction. The first shooting result satisfaction is used to indicate the degree of satisfaction of the user with the pictures and / or videos taken based on the shooting features of the historical path point of interest information;

[0152] Control the image acquisition device in the vehicle to perform image acquisition based on the first shooting features to obtain the first pictures and / or the first videos;

[0153] Use the first pictures and / or the first videos as the pictures / or videos corresponding to the path point of interest information in the travel notes elements.

[0154] As a possible implementation, the user operation information includes user voice information. The travel notes elements include pictures and / or videos. The element generation module 302 is specifically configured to:

[0155] Input the user voice information into the first voice intent prediction model to obtain the second shooting features corresponding to the user voice information output by the first voice intent prediction model. The second shooting features include shooting parameters and / or video recording parameters. The first voice intent prediction model is trained based on the historical user voice information in the vehicle, the shooting features of the historical user voice information, and the user's second shooting result satisfaction. The second shooting result satisfaction is used to indicate the degree of satisfaction of the user with the pictures and / or videos taken based on the shooting features of the historical user voice information;

[0156] Based on the second shooting feature, control the image acquisition device in the vehicle to perform image acquisition, and obtain a second picture and / or a second video;

[0157] Use the second picture and / or the second video as the picture and / or video corresponding to the user voice information in the travel note elements.

[0158] As a possible implementation, the travel note elements further include text. The element generation module 302 is further configured to:

[0159] After obtaining the picture and / or video corresponding to the user operation information, use a preset image recognition model to extract the image features of the picture and / or video, and obtain target image features, where the target image features include at least one of the following: the style of the picture and / or video, the objects included in the picture and / or video;

[0160] Search for the first text that matches the target image features in a preset text library, and the text library stores texts with image features;

[0161] Use the first text as the text corresponding to the user operation information in the travel note elements.

[0162] As a possible implementation, the user operation information includes user voice information, the travel note elements include text, and the element generation module 302 is specifically configured to:

[0163] Input the user voice information into a second voice intention prediction model, and obtain the target expression intention features corresponding to the user voice information output by the second voice intention prediction model. The second voice intention prediction model is trained based on the historical user voice information in the vehicle, the expression intention features of the historical user voice information, and the user's text satisfaction degree, and the text satisfaction degree is used to indicate the satisfaction degree of the user with the text determined based on the expression intention features of the historical user voice information;

[0164] Search for the second text that matches the target expression intention features in a preset text library, and the text library stores texts with expression intention features;

[0165] Use the second text as the text corresponding to the user's voice information in the travel note elements.

[0166] As a possible implementation, the device may further include: an upload module, configured to:

[0167] After combining the travel note elements to obtain the travel note corresponding to the path, upload the travel note and the user operation information to the travel note server, so that the travel note client can obtain the travel note from the travel note server.

[0168] The travel note generation device provided by the embodiments of the present application can achieve Figures 1 to 2For the sake of avoiding repetition, the processes implemented by the method embodiments are not elaborated here.

[0169] Figure 4 FIG. shows a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application.

[0170] The electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0171] Specifically, the above-mentioned processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0172] The memory 402 may include a mass storage for data or instructions. By way of example and not limitation, the memory 402 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In a suitable case, the memory 402 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 402 may be internal or external to the integrated gateway disaster recovery device. In a specific embodiment, the memory 402 is a non-volatile solid-state memory.

[0173] The memory 402 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory 402 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any one of the travel note generation methods in the above embodiments.

[0174] The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement any one of the travel note generation methods in the above embodiments.

[0175] In one example, the electronic device may further include a communication interface 403 and a bus 410. Among them, as Figure 4 shown, the processor 401, the memory 402, and the communication interface 403 are connected through the bus 410 and complete communication with each other.

[0176] The communication interface 403 is mainly used to implement communication between various modules, devices, units, and / or equipment in the embodiments of the present application.

[0177] The bus 410 includes hardware, software, or both, and couples the components of the online data flow metering device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 410 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0178] In addition, in combination with the travel note generation method in the above embodiments, the embodiments of the present application may be implemented by providing a computer storage medium. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any one of the travel note generation methods in the above embodiments is implemented.

[0179] It should be clear that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0180] The functional blocks shown in the above-described structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via a data signal carried in a carrier wave. A "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0181] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0182] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general purpose processor, a special purpose processor, a special application processor, or a field programmable logic circuit. It should also be understood that each block in the block diagrams and / or flowcharts, and the combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0183] As described above, this is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A travel note generation method, characterized in that, it includes: Obtain user operation information collected when the vehicle travels on the target path; Generate travel note elements corresponding to the user operation information, where the travel note elements include relevant information for generating travel notes; Generate a travel note corresponding to the target path based on the travel note elements.

2. The method according to claim 1, characterized in that, The user operation information includes at least one of the following: Vehicle control information, path interest point information, user voice information.

3. The method according to claim 1, characterized in that, The travel note elements include at least one of the following: background music, pictures, videos, titles, copywriting.

4. The method according to claim 1, characterized in that, The user operation information includes vehicle control information, the vehicle control information includes the driving mode and the played music, the travel note elements include background music, and generating travel note elements corresponding to the user operation information includes: Input the driving mode and the played music into a music prediction model to obtain target music features output by the music prediction model corresponding to the driving mode and the played music. The music prediction model is trained based on the historical vehicle control information of the vehicle, the music features of the historical vehicle control information, and the user's background music satisfaction. The background music satisfaction is used to indicate the degree of satisfaction of the user with the background music determined based on the music features of the historical vehicle control information; Search for a target music that matches the target music features in a preset music library, where the music library stores music with music features; Use the target music as the background music corresponding to the vehicle control information in the travel note elements.

5. The method according to claim 1, characterized in that, The user operation information includes path interest point information, the path interest point information includes the attribute information of the interest points on the path and the characteristics of the interest points, the travel note elements include titles, and generating travel note elements corresponding to the user operation information includes: Input the path interest point information into a title prediction model to obtain target interest point features output by the title prediction model corresponding to the path interest point information. The title prediction model is trained based on the historical path interest point information of the vehicle, the interest point features of the historical path interest point information, and the user's title satisfaction. The title satisfaction is used to indicate the degree of satisfaction of the user with the title determined based on the interest point features of the historical path interest point information; Search for a title that matches the target interest point features in a preset title library, where the title library stores titles with interest point features; Use the title that matches the target interest point features as the title corresponding to the path interest point information in the travel note elements.

6. The method according to claim 1, characterized in that, The user operation information includes path point of interest information, and the path point of interest information includes the attribute information of the points of interest in the path and the characteristics of the points of interest. The travel note elements include pictures and / or videos. Generating the travel note elements corresponding to the user operation information includes: Inputting the path point of interest information into a shooting prediction model to obtain first shooting features corresponding to the path point of interest information output by the shooting prediction model. The first shooting features include photographing parameters and / or video recording parameters. The shooting prediction model is trained based on the historical path point of interest information in the vehicle, the shooting features of the historical path point of interest information, and the user's first shooting result satisfaction. The first shooting result satisfaction is used to indicate the degree of satisfaction of the user with the pictures and / or videos taken based on the shooting features of the historical path point of interest information; Controlling an image acquisition device in the vehicle to perform image acquisition based on the first shooting features to obtain first pictures and / or first videos; Using the first pictures and / or first videos as the pictures and / or videos corresponding to the path point of interest information in the travel note elements.

7. The method according to claim 1, wherein, the user operation information includes user voice information, the travel note elements include pictures and / or videos, and generating the travel note elements corresponding to the user operation information includes: Inputting the user voice information into a first voice intent prediction model to obtain second shooting features corresponding to the user voice information output by the first voice intent prediction model. The second shooting features include photographing parameters and / or video recording parameters. The first voice intent prediction model is trained based on the historical user voice information in the vehicle, the shooting features of the historical user voice information, and the user's second shooting result satisfaction. The second shooting result satisfaction is used to indicate the degree of satisfaction of the user with the pictures and / or videos taken based on the shooting features of the historical user voice information; Controlling an image acquisition device in the vehicle to perform image acquisition based on the second shooting features to obtain second pictures and / or second videos; Using the second pictures and / or second videos as the pictures and / or videos corresponding to the user voice information in the travel note elements.

8. The method according to claim 1, wherein, the user operation information includes user voice information, the travel note elements include text, and generating the travel note elements corresponding to the user operation information includes: Inputting the user voice information into a second voice intent prediction model to obtain target expression intent features corresponding to the user voice information output by the second voice intent prediction model. The second voice intent prediction model is trained based on the historical user voice information in the vehicle, the expression intent features of the historical user voice information, and the user's text satisfaction. The text satisfaction is used to indicate the degree of satisfaction of the user with the text determined based on the expression intent features of the historical user voice information; Search for a second piece of text in a preset text library that matches the target expression intention feature, where the text library stores texts with expression intention features; Use the second piece of text as the text corresponding to the user's voice information in the travel note elements.

9. The method according to claim 6 or 7, wherein, The travel note elements further include text, and generating the travel note elements corresponding to the user operation information further includes: After obtaining the pictures and / or videos corresponding to the user operation information, use a preset image recognition model to extract the image features of the pictures and / or the videos to obtain target image features, where the target image features include at least one of the following: the style of the pictures and / or the videos, the objects included in the pictures and / or the videos; Search for a first piece of text in a preset text library that matches the target image feature, where the text library stores texts with image features; Use the first piece of text as the text corresponding to the user operation information in the travel note elements.

10. The method according to any one of claims 1-8, wherein, After generating the travel note corresponding to the path based on the travel note elements, the method further includes: Upload the travel note and the user operation information to a travel note server so that a travel note client can obtain the travel note from the travel note server.

11. A travel note generation device, wherein, It includes: An acquisition module for acquiring user operation information collected when a vehicle travels on a target path; An element generation module for generating travel note elements corresponding to the user operation information, where the travel note elements include relevant information for generating travel notes; A travel note generation module for generating a travel note corresponding to the target path based on the travel note elements.

12. An electronic device, wherein, The electronic device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the steps of the travel note generation method according to any one of claims 1-10 are implemented.

13. A computer-readable storage medium, wherein, Computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, the steps of the travel note generation method according to any one of claims 1-10 are implemented.

14. A vehicle, wherein, It includes the travel note generation device according to claim 11.

Images