Information prompt method, device, equipment, storage medium and vehicle

Abstract

The present application relates to an information prompt method, device, equipment, storage medium and vehicle, and relates to the field of vehicle technology. The method includes: collecting current road condition data of the current road of the vehicle, and determining the road condition state of the current road according to the current road condition data. When the road condition state is a complex state, output prompt information; the prompt information is used to prompt the driver of the vehicle not to start the intelligent driving mode. It is used to reduce the number of times the intelligent driving mode is exited.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to an information prompting method, device, equipment, storage medium and vehicle. Background Art

[0002] Intelligent driving technology is a technology that uses artificial intelligence, computer vision, sensor technology and communication technology to achieve autonomous navigation, traffic planning and safety control during vehicle driving and control. With the technological progress of various hardware, software, computing power and other aspects, intelligent driving technology has made great progress.

[0003] In order to improve the safety of intelligent driving technology, accurate identification of driving scenes is the current main research direction. For example, the relevant technology discloses a method for identifying dangerous scenes in urban traffic environments based on graph classification, which uses graph classification to realize the identification of dangerous scenes in urban traffic environments, clusters driving operation information and vehicle driving information to obtain dangerous scene labels, generates labels that are more in line with data distribution characteristics, and accurately identifies dangerous scenes in traffic scenes through driving information, thereby improving the accuracy of traffic dangerous scene identification. The relevant technology also discloses an intelligent driving feature analysis method, which divides the preset road into uphill sections, flat sections, and downhill sections, and compares the driving feature indicators of manual driving and intelligent driving vehicles of the same model under these three typical sections, thereby determining the best driving feature indicators under each section of the preset road.

[0004] It can be seen that the relevant technical solutions are all about how to accurately identify the road condition. However, when complex road conditions are identified, in order to ensure the driving safety of the vehicle, the vehicle will frequently exit the intelligent driving mode and hand over the control to the driver. Summary of the invention

[0005] One of the purposes of the present application is to provide an information prompt method, device, equipment, storage medium and vehicle to reduce the number of times the intelligent driving mode is exited.

[0006] In order to achieve the above purpose, the technical solution adopted in this application is as follows:

[0007] According to the first aspect of the present application, an information prompt method is provided, the method comprising: collecting current road condition data of the current road on which the vehicle is traveling, and determining the road condition state of the current road according to the current road condition data. When the road condition state is a complex state, outputting prompt information; the prompt information is used to prompt the driver of the vehicle not to start the intelligent driving mode.

[0008] According to the above technical means, the current road condition data is collected, and the road condition status of the current driving road is determined based on the current road condition data. Furthermore, when the road condition status is a complex state, information is output to prompt the driver not to start the intelligent driving mode. In this way, when complex road conditions are identified, the driver is prompted not to start the intelligent driving mode, so that the driver can actively exit the intelligent driving mode under complex road conditions and no longer start the intelligent driving function, thereby reducing the number of times the intelligent driving mode is actively exited. In addition, since complex road conditions can be identified in a timely manner and prompt information is given, the driver is given a psychological expectation, which reduces the insecurity and complaints caused by the driver suddenly taking over, and lets the driver know the vehicle's accurate judgment of complex road conditions when it is passable, thereby improving the user experience.

[0010] In one possible manner, the above-mentioned "determining the road condition status of the current driving road based on the current road condition data" includes: determining the road condition status of the current driving road based on the current road condition data and a trained road condition determination model; the trained road condition determination model is trained based on the intelligent driving road condition data set and the human driving road condition data set, the data in the intelligent driving road condition data set is the road condition data collected when the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold, and the data in the human driving road condition data set is the road condition data collected when the driver's driving action parameters are greater than or equal to a second preset threshold within a second preset time period; the driving action parameters include the operating amplitude and / or operating frequency of the driver's operation of the vehicle.

[0011] According to the above technical means, since the trained road condition determination model is trained based on the intelligent driving road condition data set and the human driving road condition data set, the trained road condition determination model can learn the characteristics of complex road conditions recognized by the driver and the characteristics of complex road conditions recognized by the vehicle. In this way, the trained road condition determination model can more accurately identify the road condition status of complex road conditions, thereby providing the driver with more timely and accurate reminders.

[0012] In one possible manner, before determining the road condition of the current driving road based on the road condition data and the road condition determination model, the method further includes: obtaining an intelligent driving road condition data set and a human driving road condition data set, and determining a complex road condition data set based on the intelligent driving road condition data set and the human driving road condition data set. The road condition data in the complex road condition data set are road condition data whose similarity between the intelligent driving road condition data set and the human driving road condition data set is greater than or equal to a similarity threshold. The initial road condition determination model is trained based on the complex road condition data set to obtain a trained road condition determination model.

[0013] According to the above technical means, the road condition data with similarity greater than or equal to the similarity threshold in the intelligent driving road condition data set and the human driving road condition data set is taken as complex road condition data. Further, the initial road condition determination model is trained according to the complex road condition data to obtain a trained road condition determination model. Such a trained road condition determination model can more accurately identify the road condition state of the complex road condition considered by the driver.

[0014] In one possible manner, determining the road condition state of the current driving road based on the current road condition data includes: calculating the similarity between the current road condition data and the road condition data in the human driving road condition data set, and determining the road condition state of the current driving road based on the similarity. The data in the human driving road condition data set is the road condition data collected when the driver's driving action parameter is greater than or equal to the second preset threshold value within a second preset time period. The driving action parameter includes the operation amplitude and / or operation frequency of the driver's operation of the vehicle.

[0015] According to the above technical means, the current road condition data is compared with the data in the human driving road condition data set, and the road condition status of the current driving road is determined based on the similarity. In this way, the identified road condition status matches the road condition status determined by the driver, thereby providing the driver with more timely and accurate reminders.

[0016] In one possible manner, calculating the similarity between the current road condition data and the road condition data in the human driving road condition data set includes: determining a current driving scene corresponding to the current road condition data, and determining target road condition data from the human driving road condition data set according to the current driving scene. The driving scene corresponding to the target road condition data is the same as the current driving scene. Calculating the similarity between the current road condition data and the target road condition data.

[0017] In one possible manner, the complex state includes a first-level complex state and a second-level complex state, and the road condition state of the current driving road is determined according to the similarity, including: when the similarity is greater than or equal to the first similarity, the road condition state of the current driving road is determined to be a first-level complex state. When the similarity is greater than or equal to the second similarity and less than the first similarity, the road condition state of the current driving road is determined to be a second-level complex state. The first similarity is greater than the second similarity.

[0018] In one possible manner, when the road condition is a complex state, outputting prompt information includes: when the road condition is a complex state, determining prompt information corresponding to the complexity level of the complex state according to the complexity level of the complex state and the level prompt mapping relationship, and outputting the prompt information. The level prompt mapping relationship includes multiple complexity levels and prompt information corresponding to each complexity level.

[0019] According to the above technical means, a user reminder mechanism is designed according to the complexity level, so that users can identify the complex scene level in time. According to the second aspect provided by the present application, an information prompt device is provided, and the device includes: a collection unit, a determination unit and an output unit. The collection unit is used to collect the current road condition data of the current driving road of the vehicle. The determination unit is used to determine the road condition status of the current driving road according to the current road condition data. The output unit is used to output prompt information when the road condition status is a complex state. The prompt information is used to prompt the driver of the vehicle not to start the intelligent driving mode.

[0020] In one possible manner, the determination unit is specifically used to determine the road condition status of the current driving road based on the current road condition data and the trained road condition determination model. The trained road condition determination model is obtained by training based on the intelligent driving road condition data set and the human driving road condition data set. The data in the intelligent driving road condition data set is the road condition data collected when the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold value, and the data in the human driving road condition data set is the road condition data collected when the driver's driving action parameters are greater than or equal to a second preset threshold value within a second preset time period. The driving action parameters include the operating amplitude and / or operating frequency of the driver's operation of the vehicle.

[0021] In one possible manner, the device further includes an acquisition unit and a processing unit. The acquisition unit is used to acquire an intelligent driving road condition data set and a human driving road condition data set. The determination unit is used to determine a complex road condition data set based on the intelligent driving road condition data set and the human driving road condition data set. The road condition data in the complex road condition data set are road condition data whose similarity between the intelligent driving road condition data set and the human driving road condition data set is greater than or equal to a similarity threshold. The processing unit is used to train an initial road condition determination model based on the complex road condition data set to obtain a trained road condition determination model.

[0022] In one possible manner, the determination unit is specifically used to calculate the similarity between the current road condition data and the road condition data in the human driving road condition data set, and determine the road condition state of the current driving road according to the similarity. The data in the human driving road condition data set is the road condition data collected when the driver's driving action parameter is greater than or equal to the second preset threshold value within a second preset time period. The driving action parameter includes the operation amplitude and / or operation frequency of the driver's operation of the vehicle.

[0023] In one possible manner, the determination unit is specifically configured to: determine a current driving scene corresponding to the current road condition data, and determine target road condition data from the human driving road condition data set according to the current driving scene. The driving scene corresponding to the target road condition data is the same as the current driving scene. Calculate the similarity between the current road condition data and the target road condition data.

[0024] In one possible manner, the complex state includes a first-level complex state and a second-level complex state, and the determination unit is specifically used to: when the similarity is greater than or equal to the first similarity, determine that the road condition state of the current driving road is a first-level complex state. When the similarity is greater than or equal to the second similarity and less than the first similarity, determine that the road condition state of the current driving road is a second-level complex state. The first similarity is greater than the second similarity.

[0025] In one possible manner, the output unit is specifically used to: when the road condition is a complex state, determine the prompt information corresponding to the complexity level of the complex state according to the complexity level of the complex state and the level prompt mapping relationship, and output the prompt information. The level prompt mapping relationship includes multiple complexity levels and the prompt information corresponding to each complexity level.

[0026] According to the third aspect provided by the present application, an electronic device is provided, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0027] According to the fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of a processing device, the processing device is enabled to execute the method in the above-mentioned first aspect and any possible implementation method thereof.

[0028] According to the fifth aspect provided by the present application, a computer program product is provided, the computer program product comprising computer instructions, and when the computer instructions are executed on a processing device, the processing device executes the method of the above-mentioned first aspect and any possible implementation manner thereof.

[0029] Therefore, the above technical features of the present application have the following beneficial effects:

[0030] (1) Collect current road condition data, and determine the road condition of the current road based on the current road condition data. Furthermore, when the road condition is complex, output information to prompt the driver not to start the intelligent driving mode. In this way, when complex road conditions are identified, the driver is prompted not to start the intelligent driving mode, so that the driver can actively exit the intelligent driving mode under complex road conditions and no longer start the intelligent driving function, thereby reducing the number of times the intelligent driving mode is actively exited. In addition, under complex road conditions, it is possible to avoid inaccurate road condition recognition by the intelligent driving function, which may lead to safety problems.

[0031] (2) Since the trained road condition determination model is trained based on the intelligent driving road condition data set and the human driving road condition data set, the trained road condition determination model can learn the characteristics of complex road conditions recognized by the driver and the characteristics of complex road conditions recognized by the vehicle. In this way, the trained road condition determination model can more accurately identify the road condition status of complex road conditions, thereby providing the driver with more timely and accurate reminders.

[0032] (3) The road condition data with similarity greater than or equal to the similarity threshold between the intelligent driving road condition data set and the human driving road condition data set is regarded as complex road condition data. Further, the initial road condition determination model is trained according to the complex road condition data to obtain a trained road condition determination model. Such a trained road condition determination model can more accurately identify the road condition state of the complex road condition considered by the driver.

[0033] (4) Compare the current road condition data with the data in the human driving road condition data set, and determine the road condition status of the current driving road based on the similarity. In this way, the identified road condition status matches the road condition status determined by the driver, thereby providing the driver with more timely and accurate reminders. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of the structure of an information prompt system shown in an exemplary embodiment provided by the present application;

[0035] Figure 2 One of the flowcharts of an information prompting method shown in an exemplary embodiment provided by the present application;

[0036] Figure 3 A second flow chart of an information prompting method shown in an exemplary embodiment provided by the present application;

[0037] Figure 4 A third flowchart of an information prompting method shown in an exemplary embodiment provided by the present application;

[0038] Figure 5 A schematic diagram of a model update process is shown for an exemplary embodiment provided by the present application;

[0039] Figure 6 A schematic diagram of the structure of an information prompting device shown as an exemplary embodiment provided by the present application;

[0040] Figure 7 The present invention is a schematic diagram of an electronic device according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0043] Intelligent driving technology is a technology that uses artificial intelligence, computer vision, sensor technology and communication technology to achieve autonomous navigation, traffic planning and safety control during vehicle driving and control. With the technological progress of various hardware, software, computing power and other aspects, intelligent driving technology has made great progress.

[0044] In order to improve the safety of intelligent driving technology, accurate identification of driving scenes is the current main research direction. For example, the relevant technology discloses a method for identifying dangerous scenes in urban traffic environments based on graph classification, which uses graph classification to realize the identification of dangerous scenes in urban traffic environments, clusters driving operation information and vehicle driving information to obtain dangerous scene labels, generates labels that are more in line with data distribution characteristics, and accurately identifies dangerous scenes in traffic scenes through driving information, thereby improving the accuracy of traffic dangerous scene identification. The relevant technology also discloses an intelligent driving feature analysis method, which divides the preset road into uphill sections, flat sections, and downhill sections, and compares the driving feature indicators of manual driving and intelligent driving vehicles of the same model under these three typical sections, thereby determining the best driving feature indicators under each section of the preset road.

[0045] It can be seen that the relevant technical solutions are all about how to accurately identify road conditions. However, when complex road conditions are identified, in order to ensure the driving safety of the vehicle, the vehicle will frequently exit the intelligent driving mode and hand over control to the driver. For example, under complex road conditions, the vehicle exits the intelligent driving mode. Subsequently, when the driver activates the intelligent driving mode again, the vehicle will exit the intelligent driving mode again.

[0046] In order to solve the above technical problems, the present application provides an information prompt method, which includes: collecting current road condition data of the current road of the vehicle, and determining the road condition state of the current road according to the current road condition data. When the road condition state is a complex state, output prompt information. The prompt information is used to prompt the driver not to start the intelligent driving mode.

[0047] According to the above technical means, the current road condition data is collected, and the road condition state of the current driving road is determined according to the current road condition data. Furthermore, when the road condition state is a complex state, information is output to prompt the driver not to start the intelligent driving mode. In this way, when a complex road condition is identified, the driver is prompted not to start the intelligent driving mode, so that the driver can actively exit the intelligent driving mode under complex road conditions, thereby reducing the number of times the intelligent driving mode is actively exited.

[0048] like Figure 1 As shown, Figure 1 Schematic diagram of the structure of an information prompt system 100 provided in an embodiment of the present application. The information prompt system 100 may include a server 101 and a plurality of vehicles ( Figure 1 3 vehicles are shown as an example: vehicle 1, vehicle 2 and vehicle 3. In actual application, there may be more or fewer vehicles.) The server 101 is connected to communicate with the plurality of vehicles.

[0049] The server 101 is used to obtain the intelligent driving road condition data set and the human driving road condition data set collected by the target vehicle, and train the initial road condition determination model according to the intelligent driving road condition data set and the human driving road condition data set to obtain a trained road condition determination model. Further, the server 101 sends the trained road condition determination model to the target vehicle. The target vehicle is any one of the multiple vehicles.

[0050] Accordingly, the target vehicle receives the trained road condition determination model sent from the server 101. Further, the target vehicle collects the current road condition data of the vehicle's current driving road, and determines the road condition state of the current driving road according to the current road condition data. Subsequently, when the road condition state is a complex state, the target vehicle outputs a prompt message. The prompt message is used to prompt the driver not to start the intelligent driving mode.

[0051] The target vehicle is also used to send the current road condition data and the complex state to the server 101 when the road condition is in a complex state.

[0052] The server 101 is also used to receive current road condition data and complex state sent from the target vehicle, and retrain the trained road condition determination model according to the current road condition data and complex state.

[0053] The server 101 is also used to optimize the trained road condition determination model according to the current road condition data and complex state sent by the target vehicle to obtain an optimized road condition determination model, and send the optimized road condition determination model to the target vehicle.

[0054] The server in the embodiment of the present application may be a single server, a server cluster, or a cloud server, which is not limited by the embodiment of the present application.

[0055] For ease of understanding, the information prompt method provided by the present application is specifically introduced below with reference to the accompanying drawings.

[0056] Figure 2 According to a flowchart of an information prompting method shown in an exemplary embodiment, the information prompting method is applied to an electronic device, and the method includes: S201-S203.

[0057] S201. Collect current road condition data of the current road on which the vehicle is traveling.

[0058] In some embodiments, the electronic device collects the current road condition data of the vehicle's current driving road in real time or periodically.

[0059] In some embodiments, the electronic device collects current road condition data through vehicle-mounted sensors, which include one or more of cameras, radars, and laser radars.

[0060] Exemplarily, the electronic device collects current road condition data via a camera.

[0061] In some embodiments, when the driving mode of the vehicle is an intelligent driving mode, current road condition data of the vehicle is collected.

[0062] S202: Determine the road condition of the current driving road according to the current road condition data.

[0063] In some embodiments, the electronic device determines the road condition of the current driving road according to the current road condition data and the trained road condition determination model. This embodiment is described in detail in S2021 below and will not be described in detail here.

[0064] In some embodiments, the electronic device calculates the similarity between the current road condition data and the road condition data in the human driving road condition data set, and determines the road condition state of the current driving road according to the similarity. This embodiment is described in detail in S2022 below and will not be repeated here.

[0065] In other embodiments, the electronic device calculates the similarity between the current road condition data and the complex scene data, and determines the road condition of the current driving road based on the similarity.

[0066] S203: When the road condition is complex, output prompt information.

[0067] Among them, the prompt information is used to prompt the driver of the vehicle not to start the intelligent driving mode.

[0068] As a possible implementation method, the electronic device determines whether the road condition is a complex state after determining the road condition, and obtains prompt information corresponding to the complex state if the road condition is a complex state. Further, the electronic device outputs the prompt information.

[0069] In some embodiments, the complex state includes multiple complexity levels. When the road condition is a complex state, the electronic device determines prompt information according to the complexity level of the complex state and the level prompt mapping relationship. The level prompt mapping relationship includes multiple complexity levels and prompt information corresponding to each complexity level.

[0070] Exemplarily, the complexity level includes a first-level complexity state and a second-level complexity state. When the road condition state is a first-level complexity state, the electronic device determines that the prompt information corresponding to the first-level complexity state is a voice message of "The current road is a particularly complex section, and intelligent driving is not recommended"; when the road condition state is a second-level complexity state, the electronic device determines that the prompt information corresponding to the second-level complexity state is a voice message of "The current road is a complex section, please use intelligent driving with caution".

[0071] In some embodiments, the prompt information includes one or more of a voice prompt, a light prompt, and a video prompt.

[0072] In another case, the road condition of the road to be traveled is determined based on the current road condition data and the trained road condition model. Furthermore, when the road condition of the road to be traveled is a complex state, prompt information is output. In this way, when it is predicted that the road to be traveled is a complex road condition, prompt information is output to give the driver a psychological expectation, reduce the insecurity and complaints caused by the driver suddenly taking over, and let the driver know the vehicle's judgment on complex road conditions when it is passable, thereby improving the user experience.

[0073] The information prompt method provided by the embodiment of the present application at least brings the following beneficial effects: collecting current road condition data, and determining the road condition status of the current driving road based on the current road condition data. Furthermore, when the road condition status is complex, output information prompting the driver not to start the intelligent driving mode. In this way, when complex road conditions are identified, the driver is prompted not to start the intelligent driving mode, so that the driver can actively exit the intelligent driving mode under complex road conditions, thereby reducing the number of times the intelligent driving mode is actively exited.

[0074] In one possible design, the above S202 includes: S2021.

[0075] S2021. Determine the road condition status of the current driving road based on the current road condition data and the trained road condition determination model.

[0076] The trained road condition determination model is obtained by training based on the intelligent driving road condition data set and the human driving road condition data set. The data in the intelligent driving road condition data set is the road condition data collected when the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold, and the data in the human driving road condition data set is the road condition data collected when the driver's driving action parameters are greater than or equal to a second preset threshold within a second preset time period. The driving action parameters include the operating amplitude and / or operating frequency of the driver's operation of the vehicle.

[0077] In some embodiments, the electronic device inputs the current road condition data into a trained road condition determination model to obtain the road condition status output by the trained road condition determination model.

[0078] In a possible design, before the above S2021, it includes: S204-S206.

[0079] S204: Obtain an intelligent driving road condition dataset and a human driving road condition dataset.

[0080] As a possible implementation method, the electronic device obtains an intelligent driving road condition data set and a human driving road condition data set within a historical time period.

[0081] In some embodiments, when the vehicle is in the intelligent driving mode, it is determined whether the number of times the intelligent driving mode exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold. When the number of times the vehicle exits the intelligent driving mode within the first preset time period is greater than or equal to the first preset threshold, the target camera is started to obtain road condition video data, and the road condition video data is placed in the intelligent driving road condition data set. Alternatively, the road condition video data captured by the target camera in a working state is obtained, and the road condition video data is placed in the intelligent driving road condition data set. The target camera is used to collect road condition data of the vehicle, and the number of target cameras can be one or more. In this way, the road condition data in the intelligent driving road condition data set is obtained.

[0082] For example, when the target camera is in sleep mode, if the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold, the target camera is started and road condition video data is collected. Furthermore, if it is detected that the vehicle is traveling on a non-complex road, the camera is turned off and the collected road condition video data is put into the intelligent driving road condition data set.

[0083] Alternatively, when the target camera is in working mode, if the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold, the road condition data from the first time the vehicle exits the intelligent driving mode within the first preset time period to the time when the vehicle is detected to be traveling on a non-complex road is put into the intelligent driving road condition data set.

[0084] In some embodiments, when the vehicle is in manual driving mode, the driver's operating parameters are collected. The driver's operating parameters include steering wheel rotation frequency and amplitude, accelerator and brake pedaling frequency and depth, etc. Further, the electronic device determines whether the driver's driving action parameters are greater than or equal to the second preset threshold value within a second preset time period, and when the driver's driving action parameters are greater than or equal to the second preset threshold value within the second preset time period, the target camera is started to obtain road condition video data, and the road condition video data is placed in a human driving road condition data set. Alternatively, the road condition video data captured by the target camera in a working state is obtained, and the road condition video data is placed in a human driving road condition data set. In this way, the road condition data in the human driving road condition data set is obtained.

[0085] In some embodiments, the electronic device collects road condition data from a human driving road condition data set and an intelligent driving road condition data set.

[0086] In other embodiments, the electronic device obtains the collected driving road condition data set and the intelligent driving road condition data set.

[0087] It should be noted that the first preset threshold, historical time period, second preset threshold, first preset time period and second preset time period are pre-set by operation and maintenance personnel. The embodiment of the present application does not specifically limit the numerical values ​​of the first preset threshold, historical time period, second preset threshold, first preset time period and second preset time period.

[0088] In some embodiments, the traffic data in the intelligent driving traffic data set and the human driving traffic data set are divided into video segments of fixed length according to preset timestamps.

[0089] In some embodiments, the road condition data in the intelligent driving road condition data set and the human driving road condition data set are data obtained by denoising and standardizing the collected video data.

[0090] S205. Determine a complex road condition data set based on the intelligent driving road condition data set and the human driving road condition data set.

[0091] Among them, the road condition data in the complex road condition data set are road condition data whose similarity between the intelligent driving road condition data set and the human driving road condition data set is greater than or equal to the similarity threshold.

[0092] In some embodiments, when the electronic device obtains the intelligent driving road condition data set and the human driving road condition data set, it determines the feature vector of each road condition data in the intelligent driving road condition data set and the human driving road condition data set. Furthermore, the electronic device calculates the similarity between the feature vector of the first road condition data in the intelligent driving road condition data set and the feature vector of the second road condition data in the human driving road condition data set, and when the similarity between the first road condition data and the second road condition data is greater than or equal to the similarity threshold, the first road condition data in the intelligent driving road condition data set and the second road condition data in the human driving road condition data set are placed in a complex road condition data set to obtain a complex road condition data set. The first road condition data in the intelligent driving road condition data set is any one of the road condition data in the intelligent driving road condition data, and the second road condition data in the human driving road condition data set is a road condition data in the human driving road condition data set.

[0093] In some embodiments, when the similarity between the first road condition data and the second road condition data is greater than or equal to a similarity threshold, the electronic device puts the feature vector of the first road condition data in the intelligent driving road condition data set and the feature vector of the second road condition data in the human driving road condition data set into a complex road condition data set to obtain a complex road condition data set.

[0094] It should be noted that the similarity threshold is data pre-set by the operation and maintenance personnel.

[0095] In some embodiments, the electronic device calculates the similarity between the first traffic condition data and the second traffic condition data using cosine similarity or Euclidean distance.

[0096] It can be understood that calculating the similarity between the first road condition data and the second road condition data is to calculate the similarity between the video clips collected in the manual driving mode and the video clips collected in the intelligent driving mode.

[0097] S206: Train the initial road condition determination model according to the complex road condition data set to obtain a trained road condition determination model.

[0098] In some embodiments, when the electronic device obtains a complex road condition data set, it labels the data in the complex road condition data set as complex road conditions, and trains an initial road condition determination model based on the labeled complex road condition data set to obtain a trained road condition determination model.

[0099] In other embodiments, the electronic device obtains a labeled non-complex road condition data set and a labeled complex road condition data set to train the initial road condition determination model to obtain a trained road condition determination model. The data in the non-complex road condition data set may be the data in the intelligent driving road condition data set and / or the human driving road condition data set except the data put into the complex road condition data set.

[0100] In some embodiments, the initial road condition determination model is a model trained on other tasks. For example, the initial road condition determination model is a road condition determination model trained on other vehicles. In this way, the training process is accelerated through transfer learning.

[0101] In one possible design, the above S202 includes: S2022-S2023.

[0102] S2022. Calculate the similarity between the current road condition data and the road condition data in the human driving road condition data set.

[0103] In some embodiments, the electronic device calculates the similarity between the current road condition data and each road condition data in the human driving road condition data set to obtain multiple similarities.

[0104] For example, the human driving road condition data set includes 50 road condition data sets. The electronic device calculates the similarity between the current road condition data and each road condition data set in the human driving road condition data set to obtain 50 similarities.

[0105] In other embodiments, the electronic device determines the current driving scene corresponding to the current road condition data, and determines the target road condition data from the human driving road condition data set according to the current driving scene. The driving scene corresponding to the target road condition data is the same as the current driving scene. Further, the electronic device calculates the similarity between the current road condition data and the target road condition data.

[0106] Exemplarily, the current driving scene corresponding to the current road condition data is a city scene. The electronic device searches for target road condition data with a city scene label from the human driving road condition data set, and calculates the similarity between the current road condition data and the target road condition data.

[0107] S2023. Determine the road condition of the current driving road according to the similarity.

[0108] As a possible implementation method, the electronic device, when obtaining multiple similarities, determines the road condition of the current driving road according to the highest similarity among the multiple similarities and a preset similarity.

[0109] In some embodiments, the electronic device determines whether the highest similarity among multiple similarities is greater than or equal to a preset similarity, and determines that the traffic state of the current driving road is a complex traffic state if the highest similarity is greater than or equal to the preset similarity.

[0110] In other embodiments, the electronic device determines that the road condition of the current driving road is a level one complex state when the highest similarity is greater than or equal to the first similarity; and determines that the road condition of the current driving road is a level two complex state when the highest similarity is greater than or equal to the second similarity and less than the first similarity.

[0111] As another possible implementation method, the electronic device determines the road condition of the current driving road according to the highest similarity among multiple similarities and the similarity mapping relationship. The similarity mapping relationship includes multiple similarities and the road condition corresponding to each similarity.

[0112] It should be noted that the preset similarity, the first similarity and the second similarity are preset by operation and maintenance personnel.

[0113] Figure 3 According to a flowchart of an information prompting method shown in an exemplary embodiment, the method includes: S301-S312.

[0114] S301. Collect driver operation parameters.

[0115] In some embodiments, the electronic device collects in real time or periodically the frequency and amplitude of operating parameters such as steering, accelerator, and brake pedal during manual driving by the driver.

[0116] S302: The electronic device determines whether the driving action parameter is greater than or equal to a second preset threshold value within a second preset time period.

[0117] In some embodiments, the electronic device calculates the driving action parameter within a second preset time period, and determines whether the driving action parameter within the second preset time period is greater than or equal to a second preset threshold.

[0118] For example, the electronic device determines whether the frequency of turning the steering wheel within the second preset time period is greater than or equal to the first frequency threshold and whether the amplitude of turning the steering wheel is greater than or equal to the first amplitude threshold. For example, the electronic device determines whether the frequency of stepping on the brake pedal within the second preset time period is greater than or equal to the second frequency threshold and whether the amplitude of stepping on the brake pedal is greater than or equal to the second amplitude threshold. For another example, the electronic device determines whether the amplitude of turning the steering wheel within the second preset time period is greater than or equal to the third amplitude threshold and whether the amplitude of stepping on the accelerator pedal is greater than or equal to the fourth amplitude threshold.

[0119] It should be noted that the second preset threshold is the average value of the operating parameters of multiple vehicles, which may be the average value of the historical operating parameters of the current vehicle, or the average value of the operating parameters of multiple vehicles and the average value of the historical operating parameters of the current vehicle weighted together to obtain a value, which is not limited in the embodiments of the present application. The first amplitude threshold, the second amplitude threshold, the third amplitude threshold, the fourth amplitude threshold, the first frequency threshold, and the second frequency threshold are preset by the operation and maintenance personnel.

[0120] If yes, execute S305, if no, execute S301.

[0121] S303: Collect driving parameters of the vehicle.

[0122] In the embodiment of the present application, the driving parameter includes a parameter for exiting the intelligent driving mode. The driving parameter may also include one or more of vehicle speed, acceleration, and vehicle position.

[0123] In some embodiments, the electronic device collects driving parameters of the vehicle when the vehicle is in an intelligent driving mode.

[0124] S304: Determine whether the number of times the intelligent driving mode is exited within a first preset time period is greater than or equal to a first preset threshold.

[0125] In an embodiment of the present application, exiting the smart driving mode includes the user actively taking over the control of the vehicle and / or automatically exiting the smart driving mode. For example, the electronic device calculates the number of times the smart driving mode is automatically exited within a first preset time period, and determines whether the number of times the smart driving mode is automatically exited is greater than or equal to a first preset threshold. For another example, the electronic device calculates the sum of the number of times the smart driving mode is automatically exited within the first preset time period and the number of times the user actively takes over the control of the vehicle, and determines whether the sum of the numbers is greater than or equal to the first preset threshold.

[0126] If yes, execute S305; if no, execute S303.

[0127] S305: Collecting traffic data and uploading the traffic data to the cloud server. Correspondingly, the cloud server receives the traffic data sent from the electronic device.

[0128] In some embodiments, if the driving action parameter is greater than or equal to the second preset threshold value within the second preset time period, the target camera collects road condition data to obtain the road condition data in the human driving road condition data set. If the number of times the intelligent driving mode is exited within the first preset time period is greater than or equal to the first preset threshold value, the target camera collects road condition data to obtain the road condition data in the intelligent driving data set.

[0129] For example, if the driving action parameter is greater than or equal to the second preset threshold value within the second preset time period, the first road condition data including the first identifier is collected and generated by the target camera. The first identifier is used to indicate that the first road condition data is put into the human driving road condition data set. If the number of times the intelligent driving mode is exited within the first preset time period is greater than or equal to the first preset threshold value, the second road condition data including the second identifier is collected and generated by the target camera. The second identifier is used to indicate that the second road condition data is put into the intelligent driving road condition data set.

[0130] In some embodiments, the electronic device divides the collected video data into segments of fixed length according to preset timestamps, and uploads the segmented video data to the cloud server.

[0131] It can be understood that when it is identified that the vehicle is in a complex road condition, the road condition data corresponding to the complex road condition is collected and uploaded to the cloud server.

[0132] S306: The cloud server pre-processes the video data.

[0133] In some embodiments, the cloud server performs denoising and normalization on the video data.

[0134] S307: The cloud server performs feature extraction and vector encoding.

[0135] In some embodiments, the cloud server extracts features of the video data and encodes the features of the video data to obtain a feature vector.

[0136] For example, the cloud server uses computer vision algorithms to extract features in key frames of video data, including but not limited to traffic sign video frames, key road video frames, and pedestrian video frames.

[0137] S308: The cloud server performs scene recognition and classification.

[0138] In some embodiments, the cloud server identifies the scene of the video data based on features of the video data, and classifies the video data sent by a vehicle based on the scene of the video data.

[0139] Specifically, the features of the video data are input into a deep learning model to obtain the scene of the video data points. The deep learning model may be a convolutional neural network (CNN).

[0140] In other embodiments, the cloud server trains a diffusion transform model (DiT) based on the video data so that the diffusion transform model acquires dynamic change characteristics of road conditions and road condition characteristics of complex road conditions.

[0141] S309: The cloud server calculates the similarity.

[0142] In some embodiments, the cloud server calculates the similarity of the video data based on the feature vectors of the video data.

[0143] In other embodiments, the cloud server converts the features of the video data into feature points in a vector space, and calculates the similarity of the video data based on the distance of the feature points. For example, the cloud server obtains the first feature point of the road condition data in the intelligent driving road condition data set, and the second feature point of the road condition data in the human driving road condition data set. Further, the cloud server calculates the similarity between each first feature point and any second feature point.

[0144] S310: The cloud server determines an initial complex road condition data set.

[0145] In some embodiments, when the similarity between the first road condition data in the intelligent driving road condition data set and the second road condition data in the human driving road condition data set is greater than or equal to a similarity threshold, the cloud server puts the first road condition data in the intelligent driving road condition data set and the second road condition data in the human driving road condition data set into a complex road condition data set to obtain an initial complex road condition data set.

[0146] S311. The cloud server determines a target complex road condition data set.

[0147] In some embodiments, the cloud server performs noise processing on the candidate road condition data to obtain processed road condition data. The candidate road condition data is data in the human driving road condition data set or the intelligent driving road condition data set except the data in the complex road condition data set. Further, the cloud server calculates the similarity between the processed road condition data and the road condition data in the complex road condition data set, obtains multiple similarities, and when the largest similarity among the multiple similarities is greater than or equal to the similarity threshold, the processed road condition data is placed in the complex road condition data set.

[0148] S312: The cloud server trains the initial road condition determination model to obtain a trained road condition determination model.

[0149] Figure 4 According to a flowchart of another information prompting method shown in an exemplary embodiment, the method includes: S401-S409.

[0150] S401. Collect road condition data in real time.

[0151] S402: Determine the road condition characteristics of the road condition data.

[0152] S403: Determine target similarity based on the road condition characteristics of the road condition data and the complex road condition data set.

[0153] The target similarity is the maximum similarity between the road condition feature and each road condition feature in the complex road condition dataset.

[0154] S404: Determine whether the target similarity is greater than or equal to the first similarity.

[0155] If yes, then execute S405. If no, then execute S407.

[0156] S405: Determine that the road condition is a first-level complex state.

[0157] S406: Output the first prompt information.

[0158] In some embodiments, the first prompt information is used to remind the driver not to start the intelligent driving function through hearing and vision.

[0159] S407: Determine whether the target similarity is greater than or equal to the second similarity.

[0160] If yes, execute S408.

[0161] S408: Determine that the road condition is a secondary complex state.

[0162] S409: output second prompt information.

[0163] It is understandable that different prompt information is designed according to the complexity level of complex road conditions to distinguish the visual, auditory or tactile feedback of the first-level complex scene and the second-level complex scene. For example, it is not recommended to use smart driving in the first-level complex scene, and the second-level complex scene reminds you to use smart driving with caution. In addition, according to the prompt information, the driver can be reminded of complex road conditions in a timely manner, thereby helping the driver to better deal with potential risks and thus improve driving safety.

[0164] In some embodiments, the second prompt information is used to remind the driver to start the intelligent driving function with caution through auditory and / or visual reminders.

[0165] In order to better understand the information prompt method provided in the embodiment of the present application, Figure 5 As shown, a schematic diagram of a model update process is shown, including: S501-S504.

[0166] S501: Identify the road condition at the location of the vehicle.

[0167] S502: When the traffic condition is complex, synchronize the traffic condition data to the cloud server.

[0168] S503: Optimize the parameters of the road condition determination model according to the synchronized road condition data to obtain an updated road condition determination model.

[0169] S504: Send the updated road condition determination model to the vehicle.

[0170] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the communication device includes a hardware structure and / or software module corresponding to each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0171] Figure 6 FIG. 1 is a schematic diagram showing a structure of an information prompting device according to an exemplary embodiment. Figure 6 The information prompting device 60 includes: a collecting unit 601, a determining unit 602 and an output unit 603.

[0172] The collection unit 601 is used to collect the current road condition data of the current road on which the vehicle is traveling.

[0173] The determination unit 602 is used to determine the road condition of the current driving road according to the current road condition data.

[0174] The output unit 603 is used to output a prompt message when the road condition is complex. The prompt message is used to prompt the driver of the vehicle not to start the intelligent driving mode.

[0175] In one possible manner, the determination unit 602 is specifically used to determine the road condition status of the current driving road based on the current road condition data and the trained road condition determination model. The trained road condition determination model is obtained by training based on the intelligent driving road condition data set and the human driving road condition data set. The data in the intelligent driving road condition data set is the road condition data collected when the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold value, and the data in the human driving road condition data set is the road condition data collected when the driver's driving action parameters are greater than or equal to a second preset threshold value within a second preset time period. The driving action parameters include the operating amplitude and / or operating frequency of the driver's operation of the vehicle.

[0176] One possible approach is Figure 6 As shown, the information prompting device 60 further includes an acquisition unit 604 and a processing unit 605. The acquisition unit 604 is used to acquire an intelligent driving road condition data set and a human driving road condition data set.

[0177] The determination unit 602 is used to determine a complex road condition data set according to the intelligent driving road condition data set and the human driving road condition data set. The road condition data in the complex road condition data set are road condition data whose similarity between the intelligent driving road condition data set and the human driving road condition data set is greater than or equal to a similarity threshold.

[0178] The processing unit 605 is used to train the initial road condition determination model according to the complex road condition data set to obtain a trained road condition determination model.

[0179] In one possible manner, the determination unit 602 is specifically used to calculate the similarity between the current road condition data and the road condition data in the human driving road condition data set, and determine the road condition state of the current driving road according to the similarity. The data in the human driving road condition data set is the road condition data collected when the driver's driving action parameter is greater than or equal to the second preset threshold value within a second preset time period. The driving action parameter includes the operation amplitude and / or operation frequency of the driver's operation of the vehicle.

[0180] In one possible manner, the determination unit 602 is specifically configured to: determine a current driving scene corresponding to the current road condition data, and determine target road condition data from the human driving road condition data set according to the current driving scene. The driving scene corresponding to the target road condition data is the same as the current driving scene. Calculate the similarity between the current road condition data and the target road condition data.

[0181] In one possible manner, the complex state includes a first-level complex state and a second-level complex state, and the determination unit 602 is specifically used to: when the similarity is greater than or equal to the first similarity, determine that the road condition state of the current driving road is a first-level complex state. When the similarity is greater than or equal to the second similarity and less than the first similarity, determine that the road condition state of the current driving road is a second-level complex state. The first similarity is greater than the second similarity.

[0182] In one possible manner, the output unit 603 is specifically used to: when the road condition is a complex state, determine the prompt information corresponding to the complexity level of the complex state according to the complexity level of the complex state and the level prompt mapping relationship, and output the prompt information. The level prompt mapping relationship includes multiple complexity levels and the prompt information corresponding to each complexity level.

[0183] Figure 7 FIG. 1 is a schematic diagram of an electronic device according to an exemplary embodiment. Figure 7 As shown, the processing device includes but is not limited to: a processor 701 and a memory 702 .

[0184] The memory 702 is used to store executable instructions of the processor 701. It can be understood that the processor 701 is configured to execute instructions to implement the model training method and SOC estimation method in the above embodiment.

[0185] It should be noted that those skilled in the art can understand that Figure 7 The processing device structure shown in the figure does not constitute a limitation on the processing device, and the processing device may include Figure 7 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0186] The processor 701 is the control center of the processing device. It uses various interfaces and lines to connect various parts of the entire processing device. By running or executing software programs and / or modules stored in the memory 702, and calling data stored in the memory 702, it performs various functions of the processing device and processes data, thereby monitoring the processing device as a whole. The processor 701 may include one or more processing units. Optionally, the processor 701 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 701.

[0187] The memory 702 may be used to store software programs and various data. The memory 702 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as a determination unit, a processing unit, etc.), etc. In addition, the memory 702 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0188] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 702 including instructions, and the above instructions can be executed by a processor 701 of a processing device to implement the method in the above embodiment.

[0189] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0190] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, and the one or more instructions can be executed by the processor 701 of the processing device to complete the method in the above embodiment.

[0191] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the processing device, the various processes of the above-mentioned method embodiment are implemented, and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0192] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0193] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0194] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0195] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0196] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0197] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An information prompting method, characterized in that: The method comprises: Collecting current road condition data of a current driving road of the vehicle, and determining a road condition state of the current driving road according to the current road condition data; When the road condition is in a complex state, a prompt message is output; the prompt message is used to prompt the driver of the vehicle not to start the intelligent driving mode.

2. The method according to claim 1, characterized in that Determining the road condition of the current driving road according to the current road condition data includes: The road condition status of the current driving road is determined based on the current road condition data and the trained road condition determination model; the trained road condition determination model is obtained by training based on the intelligent driving road condition data set and the human driving road condition data set, the data in the intelligent driving road condition data set is the road condition data collected when the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold, and the data in the human driving road condition data set is the road condition data collected when the driving action parameters of the driver are greater than or equal to a second preset threshold within a second preset time period; the driving action parameters include the operating amplitude and / or operating frequency of the driver's operation of the vehicle.

3. The method according to claim 2, characterized in that Before determining the road condition state of the current driving road according to the road condition data and the road condition determination model, the method further includes: Acquire the intelligent driving road condition data set and the human driving road condition data set, and determine a complex road condition data set according to the intelligent driving road condition data set and the human driving road condition data set; the road condition data in the complex road condition data set is the road condition data whose similarity between the intelligent driving road condition data set and the human driving road condition data set is greater than or equal to a similarity threshold; The initial road condition determination model is trained according to the complex road condition data set to obtain the trained road condition determination model.

4. The method according to claim 1, characterized in that: The determining the road condition of the current driving road according to the current road condition data includes: Calculate the similarity between the current road condition data and the road condition data in the human-driving road condition data set, and determine the road condition status of the current driving road based on the similarity; the data in the human-driving road condition data set are road condition data collected when the driving action parameters of the driver are greater than or equal to a second preset threshold value within a second preset time period; the driving action parameters include the operating amplitude and / or operating frequency of the driver's operation of the vehicle.

5. The method according to claim 4, characterized in that The calculating the similarity between the current road condition data and the road condition data in the human driving road condition data set includes: Determine a current driving scene corresponding to the current road condition data, and determine target road condition data from the human-driving road condition data set according to the current driving scene; the driving scene corresponding to the target road condition data is the same as the current driving scene; The similarity between the current road condition data and the target road condition data is calculated.

6. The method according to claim 4 or 5, characterized in that: The complex state includes a primary complex state and a secondary complex state, and determining the road condition of the current driving road according to the similarity includes: When the similarity is greater than or equal to the first similarity, determining that the road condition of the current driving road is the first-level complex state; When the similarity is greater than or equal to the second similarity and less than the first similarity, it is determined that the road condition of the current driving road is the second-level complex state; and the first similarity is greater than the second similarity.

7. The method according to claim 6, characterized in that When the road condition is a complex state, outputting prompt information includes: When the road condition is a complex state, prompt information corresponding to the complexity level of the complex state is determined according to the complexity level of the complex state and the level prompt mapping relationship, and the prompt information is output; the level prompt mapping relationship includes multiple complexity levels and prompt information corresponding to each complexity level.

8. An information prompting device, characterized in that: The device comprises: a collection unit, a determination unit and an output unit; The collecting unit is used to collect the current road condition data of the current road on which the vehicle is traveling; The determining unit is used to determine the road condition of the current driving road according to the current road condition data; The output unit is used to output prompt information when the road condition is in a complex state; the prompt information is used to prompt the driver of the vehicle not to start the intelligent driving mode.

9. The device according to claim 8, characterized in that The determining unit is specifically configured to: Determine the road condition state of the current driving road according to the current road condition data and the trained road condition determination model; the trained road condition determination model is obtained by training based on the intelligent driving road condition data set and the human driving road condition data set, the data in the intelligent driving road condition data set is the road condition data collected when the number of times the vehicle exits the intelligent driving mode within a first preset time period is greater than or equal to a first preset threshold, and the data in the human driving road condition data set is the road condition data collected when the driving action parameter of the driver is greater than or equal to a second preset threshold within a second preset time period; The driving action parameters include an operation amplitude and / or an operation frequency of the driver operating the vehicle.

10. An electronic device, characterized in that: including memory and processor; The memory is coupled to the processor; The memory is used to store computer program code, wherein the computer program code includes computer instructions; When the processor executes the computer instructions, the electronic device performs the method as claimed in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of a processing device, the processing device can perform the method according to any one of claims 1 to 7.

12. A vehicle, characterized in that: The vehicle includes the electronic device as claimed in claim 10.

Images