Video generation method and device, electronic equipment and storage medium

Abstract

The invention discloses a video generation method and device, electronic equipment and a storage medium, and relates to the technical field of Internet of Vehicles. The method comprises the following steps: in response to a video generation request of a target user for a target travel, displaying a video generation interface to the target user; the video generation interface can be used for presenting a plurality of video attribute options, and each video attribute option can comprise at least one attribute value of a corresponding video attribute; generating a target video based on a video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target travel; wherein the driving data can comprise data acquired by various data acquisition devices on the target journey. By applying the technical scheme of the invention, the video generation requirement of the target user on the driving data can be better met.

Description

Technical Field

[0001] The present application relates to the technical field of Internet of Vehicles, and in particular to a video generation method, device, electronic device and storage medium. Background Art

[0002] With the rise of self-driving tours and short video culture, people are increasingly hoping to record beautiful moments while driving (such as driving scenery, etc.) for travel review or sharing on social platforms.

[0003] Although devices such as dashcams can capture or record these beautiful moments, they still face certain limitations in video recording and personalized expression. For example, the video generation capability is insufficient and the data collection is not comprehensive enough. This will not meet the user's demand for video generation of driving data. Summary of the invention

[0004] In view of the above problems, the present application provides a video generation method, device, electronic device and storage medium to better meet the user's needs for video generation of driving data.

[0005] According to one aspect of an embodiment of the present application, a video generation method is provided, the method comprising: In response to a target user's request for video generation for a target trip, displaying a video generation interface to the target user; the video generation interface is used to present a plurality of video attribute options, each video attribute option including at least one attribute value of a corresponding video attribute; A target video is generated based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip; wherein the driving data includes: data collected by multiple data acquisition devices on the target trip.

[0006] In an optional manner, before responding to a target user's request for generating a video of a target trip, the method includes: Determine a plurality of types of collected data corresponding to the plurality of data collection devices, and set data collection trigger conditions respectively for the plurality of types of collected data; Based on a plurality of data collection trigger conditions and the plurality of data collection devices, the driving data of the vehicle traveling on the target journey is obtained.

[0007] In an optional manner, based on multiple data collection trigger conditions and the multiple data collection devices, obtaining the driving data of the vehicle traveling on the target journey includes: If the vehicle starts and stops at least once during driving on the target journey, obtaining sub-driving data corresponding to the at least one start and stop respectively based on the multiple data collection trigger conditions and the multiple data collection devices; Based on the time information respectively corresponding to the at least one sub-driving data, data aggregation is performed on the at least one sub-driving data to obtain the driving data.

[0008] In an optional manner, the method further includes: For multiple events included in the driving data, the following operations are performed respectively: Determine at least one event identification method corresponding to an event; wherein each event identification method is used to determine whether the event is a special event or a non-special event; Perform event discrimination on each of the events based on the at least one event discrimination method to obtain at least one event discrimination sub-result; Based on the at least one event determination sub-result, an event determination result of the one event is obtained.

[0009] In an optional manner, obtaining the event identification result of the event based on the at least one event identification sub-result includes: If, among the at least one event identification sub-result, there is an event identification sub-result indicating that the one event is a special event, determining the event identification result as that the one event is a special event; If the at least one event discrimination sub-result indicates that the event is not a special event, the event discrimination result is obtained based on the at least one event discrimination sub-result and its corresponding weight factor; wherein each weight factor indicates the discrimination result priority of the corresponding event discrimination method.

[0010] In an optional manner, obtaining the event identification result of the event based on the at least one event identification sub-result includes: sorting the at least one event discrimination sub-result by discrimination result priority to obtain a target event discrimination sub-result with the highest discrimination result priority; The target event discrimination sub-result is used as the event discrimination result.

[0011] In an optional manner, generating a target video based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip includes: Based on the video duration determined by the video attribute selection operation, compressing the driving data to obtain compressed driving data; The target video is generated based on the compressed driving data.

[0012] In an optional manner, generating the target video based on the compressed driving data includes: Extending the playback duration corresponding to at least one special event in the compressed driving data to obtain at least one key frame; And, compressing the playback duration corresponding to at least one non-special event in the driving data after data compression to obtain at least one non-key frame; the total playback duration of the at least one non-key frame and the at least one key frame is the video duration; The target video is generated based on the at least one key frame and the at least one non-key frame.

[0013] In an optional manner, the method further includes: If the video attribute selection operation includes inserting a target event into the driving data, the insertion time of the target event into the target video is determined based on the occurrence time of the target event, the start time and the end time of the target trip.

[0014] According to another aspect of an embodiment of the present application, a video generating device is provided, the device comprising: A display module, in response to a target user's request for video generation for a target trip, displays a video generation interface to the target user; the video generation interface is used to present a plurality of video attribute options, each video attribute option including at least one attribute value of a corresponding video attribute; A generation module generates a target video based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip; wherein the driving data includes: data collected by multiple data acquisition devices on the target trip.

[0015] According to another aspect of an embodiment of the present application, an electronic device is also provided, including: a controller; and a memory for storing one or more programs, which, when the one or more programs are executed by the controller, execute the above-mentioned video generation method.

[0016] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer executes the above-mentioned video generation method.

[0017] According to another aspect of the embodiment of the present application, a computer program product or a computer program is also provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the above-mentioned video generation method.

[0018] In the video generation method provided in the embodiment of the present application, once a video generation request for a target trip is received from a target user, a video generation interface for customizing the generated video can be displayed to the target user. In this way, the target user can select a video attribute based on at least one attribute value corresponding to each of the multiple video attribute options presented on the video generation interface, thereby generating a target video that meets the needs of the target user based on the driving data corresponding to the target trip, thereby improving the video generation capability. In addition, since the driving data is data collected by multiple data acquisition devices on the target trip, the data collection is relatively complete. Therefore, the target user's video generation needs for driving data are better met.

[0019] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings: Figure 1 A schematic diagram of a process of a video generation method provided by the present application is shown; Figure 2 A schematic diagram of a scenario of driving data aggregation provided by the present application is shown; Figure 3 A schematic flow chart of a method for determining an event discrimination result of a first event provided by the present application is shown; Figure 4 A schematic diagram of a specific application scenario of special event discrimination provided by the present application is shown; Figure 5 This application provides a method based on Figure 2 Schematic diagram of the specific scene; Figure 6 A schematic diagram of the structure of a video generation device provided by the present application is shown; Figure 7 A schematic diagram of the structure of a computer system of an electronic device provided by the present application is shown. DETAILED DESCRIPTION

[0021] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0022] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0023] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0024] The term "multiple" as used in this application refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0025] The following is a brief introduction to the design concept of the embodiment of the present application: As vehicles gradually become the main or preferred choice for users to travel, recording the beautiful moments during the journey becomes more and more important. However, although devices such as dashcams can be used to capture these moments, users still face many problems when recording and expressing them in video form. For example, these may include but are not limited to the following problems or defects: (1) Insufficient automated video generation capabilities: Relevant technologies generally lack automated video generation capabilities, which means that users need to invest a lot of time and energy in manual editing when organizing and editing the large amount of video materials collected by dashcams.

[0026] (2) Incomplete data collection: Dash cams have limitations in data collection and fail to capture key features of the journey, such as abnormal weather changes, significant changes in altitude, and changes in the landscape along the way. These data are essential for fully recording the driving experience.

[0027] (3) Limited user customization: Most dash cam systems provide relatively basic editing functions and lack advanced editing tools and personalization options, which cannot meet users' needs for in-depth customization of video content.

[0028] (4) Lack of intelligent data aggregation and display: When faced with a large amount of video data stored on storage cards (such as secure digital (SD) cards) or in the cloud, users lack effective tools to quickly extract and display the highlights of their trip. The lack of intelligent data aggregation and display functions makes it difficult for users to quickly find and display memorable clips from massive amounts of data.

[0029] In view of this, in order to improve or solve the above problems, the embodiment of the present application provides a video generation method to better meet the user's demand for video generation of driving data. Figure 1 As shown, it is a flow chart of a video generation method provided by an embodiment of the present application. In the following introduction, for the convenience of description and understanding, the video generation method is applied to a server corresponding to a vehicle as an example. Figure 1 As shown, the specific implementation process of this method is as follows: S110: In response to a target user's request for generating a video for a target trip, displaying a video generation interface to the target user.

[0030] The target itinerary is the itinerary of the vehicle from the departure point to the destination. For example, the target itinerary may be the itinerary from the departure point to the tourist destination in a certain tourist trip of the target user.

[0031] The video generation interface described above can be used to present a variety of video attribute options, wherein each video attribute option includes at least one attribute value of the corresponding video attribute. Exemplarily, the aforementioned various video attribute options may include, but are not limited to: a map scale corresponding to a custom map created for a target itinerary, a video playback rate, a special event list, and a video style, etc.

[0032] The attribute value corresponding to the map scale can be any value between 1 and 30 km / cm, that is, 1 cm on the custom map corresponds to any value between 1 and 30 km in the target journey. If the map scale selected by the target user is 10 km / cm and the target journey is 300 km, then the target journey on the custom map created for the target journey can be determined to be 30 cm.

[0033] The video playback rate may be related to the map scale. Optionally, the video playback rate is N times the map scale per second, where N may be a positive rational number. Still taking the map scale selected by the target user as 10 km / cm as an example, the video playback rate may be 1 to 5 times the map scale per second, such as 2 cm / s. In addition, the video playback rate may affect the video duration of the generated target video. For example, assuming that the target trip is still 300 km, it may be determined that the video duration of the subsequently generated target video is 150 seconds.

[0034] The video playback rate determined based on the above method will also affect the speed of the vehicle's movement on the custom map. If the video playback rate is higher, the vehicle's movement on the custom map is faster; if the video playback rate is lower, the vehicle's movement on the custom map is slower.

[0035] The special event list includes a variety of special events. The target user can select a special event in the special event list, and then add the special event to the video in subsequent video generation.

[0036] The video style may include, but is not limited to, fresh and energetic style, modern and simple style, grand and majestic style, emotional resonance style, creative and unique style, etc. The video style may represent the presentation method of the video elements in the generated target video, and may also include background music, etc.

[0037] It can be seen that the video generation interface allows the target user to customize the video content. In the video generation interface, each material is displayed at the minimum granularity (i.e., video attributes), and the target user can edit and reorganize according to personal needs, thereby realizing the granular display of the material.

[0038] In addition, the above-mentioned video generation interface is also a user interface (UI) or a user interface. Of course, it can also be called a first interface or other names, which is not limited in the embodiments of the present application.

[0039] S120: Generate a target video based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip.

[0040] The driving data may include data collected by various data collection devices on the target trip. Optionally, the aforementioned various data collection devices may include, but are not limited to, various sensors or devices related to navigation, trip recording, driving behavior collection, etc.

[0041] For example, when the vehicle is traveling on a target itinerary, the vehicle's bus system (e.g., controller area network (CAN)) and external sensors can be used to collect vehicle itinerary and environmental data in real time, and the user's driving data and feature data on the route can be automatically collected according to the navigation to serve as relevant material for the final automatic generation of a video itinerary (i.e., the driving data corresponding to the target itinerary).

[0042] The above-mentioned driving data may include vehicle status data, user behavior data, environmental data, and trip event data. Among them, the vehicle status data may include data such as the speed, fuel consumption, and engine status of the vehicle on the target trip. The user behavior data may include data such as the navigation operation and driving mode selection of the target user (such as the driver) on the target trip. The environmental data may include data such as weather conditions, temperature, humidity, altitude, and light during the vehicle's driving on the target trip. The trip event data may include data such as special road conditions and traffic events during the vehicle's driving on the target trip.

[0043] Exemplarily, the driving data may specifically include 14 types of data, including route data, feature data, weather events, altitude changes, landscape features, vehicle status, user behavior, environmental data, tourist activities, digital video recorder (DVR) data, timestamp, location, data validity, and user permissions. Optionally, the field names, data types, and field descriptions corresponding to the aforementioned 14 types of data are shown in Table 1: Table 1 Field names, data types and field description examples corresponding to driving data Among them, structured data represents structured data, enum represents enumeration data, decimal represents decimal data, boolean represents Boolean data, video clip represents video clip or video clip data, datetime represents date and time data, and geo-coordinates represents geographic coordinate data.

[0044] In order to obtain relatively rich or complete driving data through the above-mentioned multiple data acquisition devices. In an optional implementation, the server may first determine the multiple types of acquisition data corresponding to the multiple data acquisition devices before executing step S120, and set data acquisition trigger conditions for the multiple types of acquisition data, so as to obtain the driving data of the vehicle on the target journey based on the multiple data acquisition trigger conditions and the multiple data acquisition devices.

[0045] Each data collection trigger condition can be determined according to the occurrence time of the corresponding data in the target trip. In this way, the server can also determine the opening and closing of the corresponding data collection device according to the occurrence time of different types of data, thereby avoiding the problem of turning on multiple data collection devices after the vehicle starts driving on the target trip to ensure that driving data including multiple data types can be successfully collected, resulting in the need to consume more power to maintain the data collection device in normal working state.

[0046] For example, for some basic data, the data collection trigger condition of at least one data collection device that collects the basic data is: when the vehicle starts, or when the at least one of the aforementioned data collection devices is initialized. For vehicle status data and environmental data, the data collection trigger condition of at least one data collection device that collects vehicle status data and environmental data is: during vehicle driving. For special events, the data collection trigger condition of at least one data collection device that collects special events is: when encountering special events. For the end data of the target trip, the data collection trigger condition of at least one data collection device that collects the end data is: when the target trip ends.

[0047] In order to ensure the security and privacy of data, the server needs to obtain explicit authorization from the target user through permission management before it can obtain travel data from the above-mentioned data collection devices. That is, before using the data from the above-mentioned data collection devices, the server needs to prompt the target user to allow relevant permissions, including the acquisition and use of navigation data, driving behavior data, driving recorder data, etc.

[0048] Since the target trip may be recorded as multiple trips due to the fact that the vehicle may cross days or the trip may be interrupted during the target trip, the target trip may be recorded as multiple trips. In order to ensure that the complete driving data of the target trip can be obtained accurately and quickly when the driving data corresponding to the target trip is generated.

[0049] Based on the above-mentioned multiple data collection trigger conditions and the above-mentioned multiple data collection devices, the server can obtain sub-driving data corresponding to at least one start and stop of the vehicle during its driving on the target journey, and then aggregate at least one sub-driving data based on the time information corresponding to the at least one sub-driving data to obtain driving data.

[0050] See also Figure 2As shown, it is a schematic diagram of a scenario of driving data aggregation provided by an embodiment of the present application. Assuming that the target trip is from city A to city B, the first start time of the vehicle (i.e., the time of departure from city A) is "2024.11.15 13:27:22", the first stop time is "2024.11.15 13:55:37", the second start time is "2024.11.15 13:58:09", the second stop time is "2024.11.15 14:42:12", the third start time is "2024.11.15 14:50:00", and the third stop time (i.e., the time of arrival at city B) is "2024.11.15 16:02:53".

[0051] The server can aggregate the first sub-driving data corresponding to "2024.11.15 13:27:22 - 2024.11.15 13:55:37", the second sub-driving data corresponding to "2024.11.15 13:58:09 - 2024.11.15 14:42:12", and the third sub-driving data corresponding to "2024.11.15 14:50:00 - 2024.11.15 16:02:53", thereby obtaining the driving data of the vehicle traveling from city A to city B.

[0052] Based on the above method, multiple sub-driving data caused by multiple startups and shutdowns (i.e., power off) on the target trip can be aggregated. In other words, since temporary emergencies are prone to occur in the target trip, resulting in interruptions to the target trip, it supports aggregating multiple sub-trips into one trip (i.e., the target trip). In addition, the total time, total mileage, and average speed of multiple sub-trips are used as the time, mileage, and average speed of the final trip (i.e., the target trip). Optionally, if the selected multiple sub-trips span multiple days, the date element can be reflected in the target video generated subsequently.

[0053] Multi-trip aggregation is applicable to resetting the trip due to refueling or repairs at a service area, and is also applicable to scenarios where it takes more than one day to reach the destination. Therefore, flexible settings can help target users customize the generation of the required video trip report (i.e. driving data).

[0054] Optionally, if the driving time corresponding to a single subtrip is short, the subtrip can be considered as not a valid trip, and the subtrip needs to be aggregated with the adjacent previous subtrip or next subtrip. For example, if the vehicle is powered on and off within 10 minutes on subtrip B, subtrip B can be considered not a valid trip from the perspective of trip reporting, and subtrip B needs to be aggregated with the adjacent subtrips.

[0055] Since the various special events encountered by the vehicle during the target trip are usually more likely to be the moments that the target user needs to record, therefore, accurately identifying or classifying special events can improve the ability of video generation, thereby better meeting the video generation needs of the target user.

[0056] In an optional implementation, for any one of the multiple events included in the driving data, such as the first event, refer to Figure 3 As shown, the server performs the following operations: S310: Determine at least one event identification method corresponding to the first event.

[0057] Exemplarily, when executing step S310, the server can quickly determine at least one event identification method corresponding to the first event based on the event type of the first event and the correspondence between the preset event type and the event identification method. Of course, other methods can also be used to determine at least one event identification method corresponding to the first event, and the embodiments of the present application do not specifically limit this.

[0058] Each event identification method can be used to determine whether the first event is a special event or a non-special event. Exemplarily, the at least one event identification method includes but is not limited to: an event identification method based on a binary model, an event identification method based on a threshold usability evaluation model, and an event identification method based on an error rate usability evaluation model.

[0059] The binary model can determine whether the first event is a special event according to a predefined special event set or special event determination rule. Taking the first event as a landscape event as an example, if the first event is a landscape event manually marked by the target user, then the first event can be determined to be a special landscape (i.e., a special event).

[0060] Taking the first event as a weather event as an example, if the first event is a weather event in a preset special weather set, it can be determined that the first event is special weather (i.e., a special event). The preset special weather set may include a variety of special (or extreme) weather as shown in Table 2.

[0061] Table 2 Examples of various special weather types included in the special weather set The server can monitor the weather changes during the trip, and the extreme weather conditions shown in Table 2 are considered special weather. Moreover, the video data of special weather can be captured by data acquisition equipment (such as a dash cam) and tagged according to the category of special weather. In addition, the recorded video material can be automatically cropped horizontally, and the best quality video clips can be obtained and stored through the set algorithm, so that the special weather can be inserted into the target video as a special event later.

[0062] The threshold-based availability evaluation model can determine whether the first event is a special event based on the relationship between the first event and the special event discrimination threshold set for the first event. For example, taking the first event as an altitude change as an example, the threshold-based availability evaluation model can determine whether the first event is a special event based on the set altitude change threshold and the altitude change value corresponding to the first event.

[0063] One or more altitude change thresholds can be set for the target trip, and the altitude threshold can be set dynamically based on the altitude difference of the target trip area. Using statistical analysis methods, the altitude change distribution of each region (such as provincial administrative units) can be determined by calculating the standard deviation from historical driving data. For example, a minimum increment parameter (i.e., standard deviation) δ (generally between 2% and 4%) is set to determine the altitude change threshold. The specific value of this parameter can be adjusted according to the altitude change characteristics of the region to ensure the scientificity and rationality of the threshold. Then, when the altitude change in the target trip is greater than δ, it can be considered that the altitude change exceeds the threshold and reaches the "special" standard, that is, the first event can be determined as a special event; otherwise, the first event can be determined as a non-special event.

[0064] For example, see Figure 4 As shown, if the maximum altitude difference during the target trip from point a to point d in region 1 exceeds 500m, that is, it is greater than the altitude change threshold δ set for region 1, then the altitude change corresponding to the target trip (that is, the first event) can be determined as a special event.

[0065] The availability evaluation model based on error rate is mainly aimed at abnormal services of vehicles. For abnormal services of vehicles, the server can count the failure rate or error rate within a period of time (for example, one minute, one hour or one day). If the error rate of a certain service of the vehicle is higher than the set error rate threshold (for example, 50%), it can be determined that the event corresponding to the service is a special event; conversely, if the error rate is lower than the set error rate threshold, it can be determined that the event corresponding to the service is a non-special event.

[0066] Taking traffic service anomalies as an example, the road conditions within the trip are monitored and real-time data of the trip navigation is obtained, such as long congestion, rockfall, traffic accidents, etc. The data collection equipment (such as driving recorders, etc.) is automatically called to record the traffic conditions and mark them with labels, that is, mark them as special events.

[0067] Taking vehicle operation abnormality as an example, the vehicle operation status during the journey is monitored to obtain abnormal conditions and data of the vehicle itself, such as a tire blowout (i.e., tire pressure is 0) or a vehicle breakdown (e.g., engine failure, brake failure, etc.). The VHR data is automatically called and labeled as a special event.

[0068] S320: Perform event discrimination on the first event based on at least one event discrimination method to obtain at least one event discrimination sub-result.

[0069] For example, assuming that the server determines that the event discrimination method corresponding to the first event includes an event discrimination method based on a binary model, an event discrimination method based on a threshold usability evaluation model, and an event discrimination method based on an error rate usability evaluation model, then the server performs special event discrimination on the first event based on the above three event discrimination methods, and can obtain three event discrimination sub-results.

[0070] S330: Obtaining an event identification result of the first event based on at least one event identification sub-result.

[0071] In an optional implementation, when executing step S330, if there is an event identification sub-result that indicates that the first event is a special event in at least one of the above event identification sub-results, the server can determine that the event identification result is that the first event is a special event. In this way, any event identification method can be used to determine whether the first event is a special event, so as to avoid the situation where a single event identification method may fail to timely identify the first event as a special event due to problems such as failure.

[0072] Take the event discrimination sub-result as a value in [0, 1] as an example, where 0 indicates that the first event is a non-special event, and 1 indicates that the first event is a special event. Assuming that the special event discrimination threshold set for the event discrimination sub-result is 0.75, if the event discrimination sub-result obtained by the event discrimination method based on the binary model is 0.56, the event discrimination sub-result obtained by the event discrimination method based on the threshold usability evaluation model is 0.85, and the event discrimination sub-result obtained by the event discrimination method based on the error rate usability evaluation model is 0.67. Then, since the event discrimination sub-result obtained by the event discrimination method based on the threshold usability evaluation model is 0.85, which is greater than 0.75, it can be determined that the first event is a special event.

[0073] In order to ensure the accuracy of the event identification result of the first event and avoid the problem that the accuracy of a single event identification method may be relatively low. The server can combine the three event identification sub-results to determine the event identification result of the first event. Optionally, if at least one of the above event identification sub-results characterizes the first event as a non-special event, then the event identification result is obtained based on at least one event identification sub-result and its corresponding weight factor. The above-mentioned method for determining the event identification result can be specifically expressed as follows: in, represents the event discrimination result of the first event, Indicates The event discrimination sub-results corresponding to the event discrimination methods, N represents the number of event discrimination methods for the first event, Indicates the event discriminator result The weight factor of .

[0074] Optionally, the at least one event discrimination sub-result and its corresponding weight factor may be determined according to the discrimination result priority corresponding to the at least one event discrimination method. That is, the weight factor of each event discrimination sub-result may represent the discrimination result priority of the corresponding event discrimination method.

[0075] For example, although the binary model, the threshold-based usability evaluation model, and the error rate-based usability evaluation model operate independently, when two or more models are triggered at the same time to perform special event discrimination on the first event, the discrimination result priority can be: binary model > threshold-based usability evaluation model > error rate-based usability evaluation model.

[0076] In an optional implementation, when executing step S330, the server may also prioritize the discrimination results of at least one event discrimination sub-result, obtain the target event discrimination sub-result with the highest discrimination result priority, and use the target event discrimination sub-result as the event discrimination result. In this way, the event discrimination sub-result obtained by the most reliable event discrimination method can be directly used as the event discrimination result of the first event. Therefore, while improving the efficiency of special event discrimination for the first event, the accuracy of the event discrimination result of the first event is also ensured to a certain extent.

[0077] Based on the above method, after the server has completed the event determination of whether the multiple events included in the driving data are special events, it can display the special event list to the target user in the subsequent process of generating the target video. In this way, the target user can quickly filter out the target special event from the special event list and then add the target special event to the target video.

[0078] Since the time span of the target trip is usually large (e.g., several hours or more than a day), the amount of driving data corresponding to the target trip is also large. Therefore, in order to more completely display the driving status of the vehicle on the target trip in a shorter video.

[0079] In an optional implementation, when executing step S120, the server may compress the driving data based on the video duration determined by the video attribute selection operation to obtain the compressed driving data, thereby generating a target video based on the compressed driving data.

[0080] Taking the target trip as a trip from City C to City D with a total of 1,200 km as an example, if the video duration determined based on the video attribute selection operation is 20 seconds, the server can compress the driving data corresponding to the target trip according to the map scale of 30 km / cm and the video playback rate of 2 cm / s, thereby generating the target video based on the compressed driving data. It can be seen that based on the aforementioned data compression method, each 60 km of sub-driving data can be compressed into 1 second of video data.

[0081] Optionally, there may be a preset mapping relationship between the size of the map scale and the total mileage of the target trip. The aforementioned mapping relationship may be determined based on the actual simulation effect and user feedback, or may be determined in other ways, which is not specifically limited in the present application embodiment. For example, the corresponding relationship between the total mileage of the trip and the map scale is shown in Table 3: Table 3 Example of the correspondence between the total mileage of a trip and the map scale Based on the correspondence between the total mileage of the trip and the map scale recorded in Table 3 above, the trips with very different total mileage can be scaled proportionally to the corresponding map scale, and the final duration difference in the video is relatively small. Taking a 300km long-distance trip as an example, the server restores the long-distance trip on the map with a map scale of 20km / cm, that is, each cm of length on the screen corresponds to 20km of the long-distance trip. Then, the total distance of the long-distance trip is 15 scale units. If the video playback rate is 2 scale units / second, it can be determined that the total video duration corresponding to the long-distance trip is 7.5s. Moreover, the length change of 15cm in the video length can clearly express the entire trip.

[0082] Taking a short-distance trip of 10 km as an example, the server restores the short-distance trip on the map at a map scale of 1 km / cm, that is, each cm on the screen corresponds to 1 km. Then, the total route length of the short-distance trip is 10 scale units. Still assuming that the video playback rate is 2 scale units / second, it can be determined that the total video duration corresponding to the short-distance trip is 5 seconds. Therefore, it can be found that the video length of a long-distance trip of 300 km and a short-distance trip of 10 km is relatively small.

[0083] Table 3 shows that the duration of the final generated video is correlated with the total mileage of the trip, and the change in the route (i.e., the map scale) is also positively correlated with the total mileage of the trip. In addition, proportional scaling adapts to different trips and can obtain a reasonable screen ratio and video duration.

[0084] In order to highlight the key time and scenes corresponding to special events during the time period when there are special events, the playback duration corresponding to at least one special event included in the compressed travel data can be adjusted to reduce the video playback rate of the time period corresponding to the special event.

[0085] Therefore, the server can expand the playback duration corresponding to at least one special event in the driving data after data compression to obtain at least one key frame; and compress the playback duration corresponding to at least one non-special event in the driving data after data compression to obtain at least one non-key frame; finally, generate the target video based on at least one key frame and at least one non-key frame.

[0086] Optionally, the total playback duration of the at least one non-key frame and the at least one key frame is the video duration. That is, the server flexibly adjusts the playback durations corresponding to special events and non-special events, respectively, and while ensuring that the video duration of the target video generated in the end remains unchanged, the playback duration corresponding to special events is extended, and the playback duration corresponding to non-special events is shortened.

[0087] When identifying and analyzing special events, key frames or time periods with specific meaning or visual appeal can be marked. Without affecting the overall video smoothness, a time aggregation algorithm is used to compress non-key frame video content to shorten the overall playback time. When the video plays to the key frame or marked time period, the video playback rate is dynamically reduced to expand the originally compressed time to show more details and information. When the video switches from a compressed state to a slowed state for special events, and when the video returns from a slowed state to a compressed state for non-special events, seamless transition technology is used to ensure that the viewing experience of the target user is consistent and natural. High-quality video output is maintained throughout the process to ensure that the clarity and visual effects of key scenes are not affected even after the video playback rate is adjusted.

[0088] Moreover, it can be seen that the video components of the target video may include: background map and special events. The background map may be obtained by scaling the satellite map data corresponding to the target itinerary in proportion according to the map scale, restoring the geographical features (such as plains and mountains) in the target itinerary.

[0089] In order to make the content in the subsequent target video more focused and reduce the amount of data, the point of interest (POI) data on the satellite map data (such as train stations, parks, scenic spots, and residences, etc.) can be removed, and only the district / county name, city name, provincial administrative region name, etc. can be retained.

[0090] In addition, the video components of the target video may also include: driving route, vehicle model, driving direction and trip data statistics. Among them, the driving route focuses on the departure point to the destination in the target trip, that is, only pays attention to the user's trip route, and does not care whether it stops or starts during the route. The vehicle model can be constructed by obtaining the vehicle model data through the application programming interface (API) provided by the manufacturer. The driving direction is the direction of the destination relative to the departure point. For example, if the destination city A is east of the departure city B, the driving direction of the vehicle in the target video is from west to east, which is consistent with the actual running direction. On the contrary, the driving direction of the vehicle in the target video is from east to west. Trip data statistics may include: total mileage, total driving time (i.e. total time), average speed, fastest speed, etc. These data reflect the core data of the target trip in the target video. For example, the end of the target video can show the total time, total mileage and total energy consumption data of this trip.

[0091] In an optional implementation, if the video attribute selection operation includes inserting a target event in the driving data, the server can determine the insertion time of the target event in the target video based on the occurrence time of the target event, the start time and the end time of the target trip, so as to insert the target event into the target video at the aforementioned insertion time to ensure the accuracy of video generation. The aforementioned target event can be a special event or a non-special event.

[0092] Exemplarily, the calculation formula of the above insertion time can be expressed as: the insertion time Tx of the target event in the target video = percentage × video duration = (occurrence time of the target event - start time of the target trip) / (end time of the target trip - start time of the target trip) × video duration. Among them, the start time of the target trip can also be called the start time of the target trip, and the end time of the target trip can also be called the end time of the target trip, which is not limited in the embodiment of the present application.

[0093] See also Figure 5 As shown, it is a schematic diagram of a specific scenario of video generation provided by an embodiment of the present application. After the server compresses the driving data corresponding to the target journey in proportion according to the map scale, it can obtain the compressed driving data with a time span of T0~Tn, where T0 is the time when the vehicle departs from the departure point and Tn is the time when the vehicle arrives at the destination. Then, when adding a target event, it can be decided whether to compress or expand the playback duration corresponding to the target event based on whether the target event is a special event. Figure 5 As shown, the server can insert the above four target events (i.e., weather 1, weather 2, altitude, and scenery) into the generated video according to the insertion time and event type corresponding to the four target events, thereby obtaining the target video after the target event is inserted, and the corresponding playback time span of the target video is T0~Ty. Optionally, Ty can be equal to T0. In this way, when formulating a video driving report (i.e., target video), it is ensured that the video content can accurately reflect the vehicle's driving trajectory (i.e., target trip), and can also display detailed scenes (i.e., special events) at critical moments.

[0094] In summary, in the video generation method provided in the embodiment of the present application, once a video generation request for a target trip is received from a target user, a video generation interface for customizing the generated video can be displayed to the target user. In this way, the target user can select a video attribute using at least one attribute value corresponding to each of the multiple video attribute options presented on the video generation interface, thereby generating a target video that meets the needs of the target user based on the driving data corresponding to the target trip, thereby improving the video generation capability. In addition, since the driving data includes data collected by multiple data acquisition devices on the target trip, the data collection is relatively complete, which better meets the target user's video generation needs for driving data.

[0095] In other words, the embodiments of the present application provide target users with a solution that can automatically collect key trip features, provide comprehensive data collection, support highly personalized editing, and have intelligent data processing and display capabilities to enhance the experience of recording and sharing vehicle travel experiences.

[0096] Among them, the automated data collection and video generation process reduces the time for target users to edit videos. In addition, target users can also customize video content and style according to personal preferences and needs, which can better meet the target users' needs for video generation of driving data. Furthermore, by collecting key feature data during the trip, more comprehensive and rich trip data is provided. In addition, intelligent data aggregation technology can also help target users quickly extract valuable information from large amounts of data. Therefore, high-quality video trip reports (target video generation) enhance the target users' driving experience and memories.

[0097] Another aspect of the present application also provides a video generation device, see Figure 6 As shown, it is a schematic diagram of the structure of a video generation device provided in an embodiment of the present application. The video generation device 600 includes: a display module 610, a generation module 620, a collection module 630 and a determination module 640; wherein, Display module 610, in response to the target user's request for video generation for the target trip, displays a video generation interface to the target user; the video generation interface is used to present a plurality of video attribute options, each video attribute option includes at least one attribute value of the corresponding video attribute; The generation module 620 generates a target video based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip; wherein the driving data includes: data collected by multiple data collection devices on the target trip.

[0098] In an optional manner, before responding to the target user's request for generating a video of the target trip, the acquisition module 630 is specifically configured to: Determine the various types of data collected corresponding to the various data collection devices, and set data collection trigger conditions for the various types of data collected; Based on multiple data collection trigger conditions and multiple data collection devices, the driving data of the vehicle on the target journey is obtained.

[0099] In an optional manner, when obtaining driving data of a vehicle traveling on a target trip based on multiple data collection trigger conditions and multiple data collection devices, the collection module 630 is specifically used to: If the vehicle starts and stops at least once during driving on the target journey, then based on multiple data collection trigger conditions and multiple data collection devices, sub-driving data corresponding to the at least one start and stop are obtained; Based on the time information respectively corresponding to the at least one sub-driving data, data aggregation is performed on the at least one sub-driving data to obtain the driving data.

[0100] In an optional manner, the determination module 640 is specifically used for: For multiple events included in the driving data, perform the following operations respectively: Determine at least one event discrimination method corresponding to an event; wherein each event discrimination method is used to determine whether an event is a special event or a non-special event; Perform event discrimination on each event based on at least one event discrimination method to obtain at least one event discrimination sub-result; Based on at least one event discrimination sub-result, an event discrimination result of an event is obtained.

[0101] In an optional manner, when obtaining an event identification result of an event based on at least one event identification sub-result, the identification module 640 is specifically configured to: If there is an event discrimination sub-result indicating that an event is a special event in at least one event discrimination sub-result, then determining the event discrimination result as an event being a special event; If at least one event discrimination sub-result indicates that an event is a non-special event, an event discrimination result is obtained based on at least one event discrimination sub-result and its corresponding weight factor; wherein each weight factor indicates the discrimination result priority of the corresponding event discrimination method.

[0102] In an optional manner, after obtaining an event discrimination result of an event based on at least one event discrimination sub-result, the discrimination module 640 is specifically configured to: Prioritizing at least one event discrimination sub-result to obtain a target event discrimination sub-result with the highest discrimination result priority; The target event discriminant result is taken as the event discriminant result.

[0103] In an optional manner, when generating a target video based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip, the generation module 620 is specifically used to: Based on the video duration determined by the video attribute selection operation, the driving data is compressed to obtain the compressed driving data; Generate target video based on the compressed driving data.

[0104] In an optional manner, when generating the target video based on the compressed driving data, the generating module 620 is specifically used to: Extending the playback duration corresponding to at least one special event in the compressed driving data to obtain at least one key frame; And, compressing the playback duration corresponding to at least one non-special event in the driving data after data compression to obtain at least one non-key frame; the total playback duration of at least one non-key frame and at least one key frame is the video duration; A target video is generated based on at least one key frame and at least one non-key frame.

[0105] In an optional manner, the generating module 620 is further configured to: If the video attribute selection operation includes inserting a target event in the driving data, the insertion time of the target event in the target video is determined based on the occurrence time of the target event, the start time and the end time of the target trip.

[0106] The video generating device provided in the above embodiment and the video generating method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here.

[0107] Another aspect of the present application also provides an electronic device. Figure 7 As shown, it shows a schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the electronic device.

[0108] See also Figure 7 As shown, the electronic device includes: a controller; a memory for storing one or more programs, and when the one or more programs are executed by the controller, the above-mentioned video generation method is executed. Figure 7 As shown, the computer system 700 of the electronic device includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 702 or the program loaded from the storage part 708 to the random access memory (RAM) 703, such as executing the method in the above embodiment. In the RAM 703, various programs and data required for system operation are also stored. The CPU 701, the ROM 702 and the RAM 703 are connected to each other through the bus 704. The input / output (I / O) interface 705 is also connected to the bus 704.

[0109] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 709, and / or installed from a removable medium 711. When the computer program is executed by the CPU 701, various functions defined in the system of the present application are executed.

[0110] Another aspect of the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the video generation method described above is implemented. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0111] Another aspect of the present application also provides a computer program product or a computer program, which includes at least one executable instruction. When the executable instruction is run on a video generating device or an electronic device, the video generating device or the electronic device executes the video generating method as described above.

[0112] The computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM, ROM, an erasable programmable read only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0113] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0114] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0115] According to one aspect of the embodiment of the present application, a computer system is also provided, including a CPU, which can perform various appropriate actions and processes according to the program stored in the ROM or the program loaded from the storage part into the random access memory RAM, such as executing the method in the above embodiment. Various programs and data required for system operation are also stored in the RAM. The CPU, ROM and RAM are connected to each other through a bus. The I / O interface is also connected to the bus.

[0116] The following components are connected to the I / O interface: an input section including a keyboard, a mouse, etc.; an output section including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section including a hard disk, etc.; and a communication section including a network interface card such as a local area network (LAN) card, a modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., are installed on the drive as needed so that a computer program read therefrom is installed into the storage section as needed.

[0117] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. A person skilled in the art can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

Claims

1. A video generation method, characterized in that: The method comprises: In response to a target user's request for video generation for a target trip, displaying a video generation interface to the target user; the video generation interface is used to present a plurality of video attribute options, each video attribute option including at least one attribute value of a corresponding video attribute; A target video is generated based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip; wherein the driving data includes: data collected by multiple data acquisition devices on the target trip.

2. The method according to claim 1, characterized in that Before responding to a target user's request for generating a video of a target trip, the method includes: Determine a plurality of types of collected data corresponding to the plurality of data collection devices, and respectively set data collection trigger conditions for the plurality of types of collected data; Based on a plurality of data collection trigger conditions and the plurality of data collection devices, the driving data of the vehicle traveling on the target journey is obtained.

3. The method according to claim 2, characterized in that Based on the multiple data collection trigger conditions and the multiple data collection devices, the driving data of the vehicle traveling on the target trip is obtained, including: If the vehicle starts and stops at least once during driving on the target journey, obtaining sub-driving data corresponding to the at least one start and stop respectively based on the multiple data collection trigger conditions and the multiple data collection devices; Based on the time information respectively corresponding to the at least one sub-driving data, data aggregation is performed on the at least one sub-driving data to obtain the driving data.

4. The method according to claim 1, characterized in that The method further comprises: For multiple events included in the driving data, the following operations are performed respectively: Determine at least one event identification method corresponding to an event; wherein each event identification method is used to determine whether the event is a special event or a non-special event; Perform event discrimination on the one event based on the at least one event discrimination method to obtain at least one event discrimination sub-result; Based on the at least one event determination sub-result, an event determination result of the one event is obtained.

5. The method according to claim 4, characterized in that Obtaining an event discrimination result of the event based on the at least one event discrimination sub-result includes: If, among the at least one event identification sub-result, there is an event identification sub-result indicating that the one event is a special event, determining the event identification result as that the one event is a special event; If the at least one event discrimination sub-result indicates that the event is not a special event, the event discrimination result is obtained based on the at least one event discrimination sub-result and its corresponding weight factor; wherein each weight factor indicates the discrimination result priority of the corresponding event discrimination method.

6. The method according to claim 4, characterized in that Obtaining an event discrimination result of the event based on the at least one event discrimination sub-result includes: sorting the at least one event discrimination sub-result by discrimination result priority to obtain a target event discrimination sub-result with the highest discrimination result priority; The target event discrimination sub-result is used as the event discrimination result.

7. The method according to any one of claims 1 to 6, characterized in that Based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip, a target video is generated, including: Based on the video duration determined by the video attribute selection operation, compressing the driving data to obtain compressed driving data; The target video is generated based on the compressed driving data.

8. The method according to claim 7, characterized in that Generating the target video based on the compressed driving data includes: Extending the playback duration corresponding to at least one special event in the compressed driving data to obtain at least one key frame; And, compressing the playback duration corresponding to at least one non-special event in the driving data after data compression to obtain at least one non-key frame; the total playback duration of the at least one non-key frame and the at least one key frame is the video duration; The target video is generated based on the at least one key frame and the at least one non-key frame.

9. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: If the video attribute selection operation includes inserting a target event into the driving data, the insertion time of the target event into the target video is determined based on the occurrence time of the target event, the start time and the end time of the target trip.

10. A video generating device, characterized in that: The device comprises: A display module, in response to a target user's request for video generation for a target trip, displays a video generation interface to the target user; the video generation interface is used to present a plurality of video attribute options, each video attribute option including at least one attribute value of a corresponding video attribute; A generation module generates a target video based on the video attribute selection operation of the target user on the video generation interface and the driving data corresponding to the target trip; wherein the driving data includes: data collected by multiple data acquisition devices on the target trip.

11. An electronic device, characterized in that: include: Controller; A memory for storing one or more programs, which, when executed by the controller, enables the controller to implement the video generation method according to any one of claims 1 to 7.

12. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction, and when the executable instruction is executed on the video generating device / equipment, the video generating device / equipment performs the operation of the video generating method according to any one of claims 1 to 7.

Images