Vehicle scene restoration method and device, electronic device and readable storage medium

Abstract

The embodiments of the present application provide a method and device for restoring a vehicle usage scene, an electronic device, and a readable storage medium, which relate to the field of big data. The method includes: collecting vehicle signals, the vehicle signals including vehicle control signals in different driving states and buried point signals of each interactive component inside the vehicle; determining the user action corresponding to the vehicle signal according to the jump logic of the vehicle signal; grouping the user actions based on the time interval between each user action to obtain at least one user action set; determining a target action set from the at least one user action set according to the execution frequency of the user action set; and determining the target vehicle usage scene of the vehicle according to the characteristic information of the user action in the target action set. Through the above method, while ensuring the objectivity of the data, the complexity of the data is reduced, and the accuracy of the restoration of the vehicle usage scene is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a method and device for restoring vehicle usage scenarios, an electronic device, and a readable storage medium. Background Art

[0002] Cars are a primary means of transportation in today's society. In recent years, an emerging trend in the automotive industry has been intelligent, connected vehicles (ICVs), combining autonomous driving technology with the Internet of Vehicles (IoV). With the development of IOCs, user personal information, user interaction data, vehicle status data, and surrounding environmental data can now be collected and uploaded to the cloud, where they can be used for autonomous driving algorithm training, vehicle diagnostics, and data analysis. This collected IoV information can be used to identify frequently occurring scenarios when users use their vehicles. These scenarios can then be used to categorize or recommend users. Therefore, identifying frequently occurring scenarios through big data analysis is crucial.

[0003] In related technologies, users' car usage scenarios are classified based on the designer's experience, and then targeted designs are made for the scenarios based on customer survey data. However, these subjectively designed car usage scenarios are not objective enough and lack objective data support, making it impossible to accurately restore the user's actual car usage scenarios. Summary of the Invention

[0004] The present application provides a method and device for restoring a vehicle usage scene, an electronic device and a readable storage medium to solve the problem that the existing technology cannot accurately restore the user's actual vehicle usage scene due to the lack of objective data support when restoring the vehicle usage scene; the second purpose is to provide a vehicle usage scene restoration device; the third purpose is to provide an electronic device; the third purpose is to provide a readable storage medium.

[0005] In order to achieve the above objectives, the technical solutions adopted in this application are as follows:

[0006] A method for restoring a vehicle usage scene, comprising:

[0007] Collecting vehicle signals, including vehicle control signals in different driving states and buried point signals of various interactive components inside the vehicle;

[0008] Determining a user action corresponding to the vehicle signal according to a transition logic of the vehicle signal;

[0009] Grouping the user actions based on the time intervals between the user actions to obtain at least one user action set, wherein the time interval between two consecutive user actions in the user action set is less than a preset threshold;

[0010] Determining a target action set from the at least one user action set according to an execution frequency of the user action set; the execution frequency of the target action set is greater than a preset frequency;

[0011] The target usage scenario of the vehicle is determined based on feature information of the user action in the target action set.

[0012] Further, the user action set includes a first action set, and the first action set includes a second action set;

[0013] The grouping of the user actions based on the time intervals between the user actions to obtain at least one user action set includes:

[0014] Grouping the user actions according to the vehicle identification code of the source vehicle of the vehicle signal to obtain a first action set;

[0015] Calculating the time interval between two consecutive user actions in the first action set;

[0016] Two consecutive user actions in the first action set whose time interval does not exceed a preset threshold are added to the same second action set.

[0017] Furthermore, before grouping the user actions based on the time intervals between the user actions to obtain at least one user action set, the method further includes:

[0018] The user action is encoded to obtain an encoded value of the user action.

[0019] Furthermore, determining a target action set from the at least one user action set according to the execution frequency of the user action set includes:

[0020] performing deduplication processing on the user actions in the user action set to obtain a third action set;

[0021] sequentially connecting the user actions in the third action set according to the coding values;

[0022] Counting the execution frequency of the third action set;

[0023] The third action set whose execution frequency exceeds the preset frequency threshold is determined as the target action set.

[0024] Furthermore, determining the user action corresponding to the vehicle signal according to the transition logic of the vehicle signal includes:

[0025] parsing the vehicle signal to obtain an attribute value of the vehicle signal;

[0026] Deleting the vehicle signal with missing attribute values ​​to obtain the first vehicle signal with complete attribute values;

[0027] performing correction processing on the attribute value of the first vehicle signal to obtain a second vehicle signal;

[0028] A user action corresponding to the vehicle signal is determined according to the transition logic of the second vehicle signal.

[0029] Furthermore, the method further comprises:

[0030] When a preset user operation is received, a target instruction is generated; the target instruction is used to control the target component corresponding to the target action set.

[0031] Furthermore, the method further comprises:

[0032] In the case that the target vehicle usage scenario does not meet the preset conditions, the preset threshold is adjusted according to the target vehicle usage scenario, and the target vehicle usage scenario is re-determined according to the adjusted preset threshold until the target vehicle usage scenario meets the preset conditions.

[0033] A vehicle scene restoration device, comprising:

[0034] A signal acquisition module is used to collect vehicle signals, including vehicle control signals of the vehicle in different driving states and buried point signals of various interactive components inside the vehicle;

[0035] A user action determination module, configured to determine a user action corresponding to the vehicle signal according to a transition logic of the vehicle signal;

[0036] a grouping module, configured to group the user actions based on the time intervals between the user actions to obtain at least one user action set, wherein the time interval between two consecutive user actions in the user action set is less than a preset threshold;

[0037] a target action set determining module, configured to determine a target action set from the at least one user action set according to an execution frequency of the user action set; the execution frequency of the target action set being greater than a preset frequency;

[0038] The target vehicle usage scenario determination module is used to determine the target vehicle usage scenario of the vehicle based on the feature information of the user action in the target action set.

[0039] An electronic device comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of any of the aforementioned vehicle usage scene restoration methods.

[0040] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any of the aforementioned vehicle usage scene restoration methods.

[0041] Beneficial effects of this application:

[0042] The embodiment of the present application provides a method for restoring a vehicle usage scenario. After collecting a vehicle signal, the method determines the user action corresponding to the vehicle signal based on the transition logic of the vehicle signal. The method then groups the user actions based on the time intervals between the user actions to obtain at least one user action set. The method further determines a target action set from the at least one user action set based on the execution frequency of the user action set. Finally, the target vehicle usage scenario of the vehicle is determined based on the characteristic information of the user actions in the target action set. In the above method, full coverage of vehicle usage information is achieved only through vehicle control signals and buried point signals, which reduces the complexity of data processing and helps to improve the efficiency of scene restoration. The method determines the user action corresponding to the vehicle signal based on the transition logic of the vehicle signal without worrying about data interference caused by the user's subjective behavior, which helps to more accurately restore the vehicle usage scenario. Therefore, compared with the method of restoring the vehicle usage scenario based on customer survey data in the related art, the method of inferring the user action based on the vehicle signal and then determining the vehicle usage scenario based on the user action set not only reduces the complexity of the data and ensures the accuracy of the vehicle usage scenario restoration, but also enhances the universality of the vehicle usage scenario restoration, which helps to improve the user experience.

[0043] The vehicle usage scene restoration device, electronic device, and readable storage medium in this application all have the same or similar beneficial effects as any of the aforementioned vehicle usage scene restoration methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flowchart showing the steps of a first method for restoring a vehicle usage scene according to an embodiment of the present application is shown;

[0045] Figure 2 A flowchart showing the steps of a second method for restoring a vehicle usage scene according to an embodiment of the present application is shown;

[0046] Figure 3 A flowchart showing the steps of a method for grouping user actions in an embodiment of the present application is shown;

[0047] Figure 4 A structural schematic diagram of a vehicle usage scene restoration device in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] The following will describe the embodiments of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the 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 embodiments, 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 the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0049] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0050] Reference Figure 1 As shown, it shows a flowchart of the steps of the first vehicle scene restoration method in an embodiment of the present application. The method may include the following steps:

[0051] Step 101: Collect vehicle signals, which include vehicle control signals of the vehicle in different driving states and buried point signals of various interactive components inside the vehicle.

[0052] Compared with taking vehicle users as the research object, restoring vehicle usage scenarios using vehicles as the research object can obtain a more realistic vehicle status, is not affected by subjective factors, and helps to restore more objective, accurate and reliable vehicle usage scenarios.

[0053] In the embodiments of this application, vehicle control signals refer to vehicle signals related to vehicle driving, such as vehicle chassis control signals, power system signals, and driving signals. Buried point signals are pre-buried point collection of functional components in the vehicle that can interact with the user, such as air conditioning knobs, music components on the vehicle display, etc. This application does not limit this. After collecting the vehicle signal, the relevant data of the vehicle signal can be encapsulated into a standard format of "ID+Data+timestamp", which facilitates subsequent unified processing and improves processing efficiency.

[0054] Vehicle control signals help understand the user's driving scenario, and buried point signals help understand the vehicle's functional scenario. In the initial stage of restoring the vehicle usage scenario, full coverage of vehicle usage information is achieved only through vehicle control signals and buried point signals, which helps to improve the efficiency of vehicle usage scenario restoration while ensuring the accurate restoration of subsequent vehicle usage scenarios.

[0055] Step 102: Determine a user action corresponding to the vehicle signal according to the transition logic of the vehicle signal.

[0056] Users can issue instructions to specific vehicle components by changing vehicle signals, so the user's behavior can be restored through the vehicle's jump logic. For example, when the user rotates the air-conditioning temperature knob to 26 degrees, the air-conditioning switch component will generate a jump signal of the temperature control signal accordingly after receiving the user's rotation instruction, thereby adjusting the air-conditioning temperature.

[0057] Therefore, the jump logic based on vehicle signals can more accurately reflect the user actions corresponding to vehicle signals. The jumps of different vehicle signals can also reflect the characteristic information of the current scene to a certain extent. Moreover, determining the user actions corresponding to vehicle signals based on the jump logic of vehicle signals is more objective than directly collecting relevant user data. There is no need to worry about data interference caused by user subjective behavior, which helps to more accurately restore the vehicle usage scene.

[0058] Furthermore, in order to facilitate subsequent data processing, a table with reasonable fields can be designed according to actual conditions, and the relevant data of the restored user actions can be stored in the same table.

[0059] Step 103 : grouping the user actions based on the time intervals between the user actions to obtain at least one user action set, wherein the time interval between two consecutive user actions in the user action set is less than a preset threshold.

[0060] Determining user scenarios based solely on a single action is too one-sided and has low application value. Therefore, considering the strong correlation between different actions in the same scenario, we can group highly correlated actions into the same action set through screening. Because the actions in the same user action set are highly correlated, it's easy to identify the vehicle usage scenarios corresponding to multiple actions.

[0061] Specifically, the time interval between two consecutive actions can be measured to determine whether the two actions occurred in the same scenario. When combining actions, the interval between adjacent actions can be continuously adjusted to flexibly combine actions. The appropriate time interval threshold, or preset threshold, can be selected based on different business objectives. For example, if the preset threshold is 1 minute, if the interval between action 1 and action 2 is less than 1 minute, then action 1 and action 2 belong to the same user action set. Conversely, if the interval between action 1 and action 2 is greater than 1 minute, then action 1 and action 2 are not in the same user action set.

[0062] Step 104 : determining a target action set from the at least one user action set according to the execution frequency of the user action set; the execution frequency of the target action set is greater than a preset frequency.

[0063] User action sets with low execution frequency are more random and do not have high research value. For example, if a set of 10 consecutive actions only occurs once a month, there is no need to mine the corresponding car usage scenarios based on these 10 actions to classify or recommend users, which has little effect on improving user experience.

[0064] Therefore, based on the preset frequency, a target action set with a higher execution frequency can be determined from the user action set obtained in step 103. If the problem that some necessary action sets have a lower execution frequency is taken into consideration, the remaining user action sets can be screened after the action set with a higher execution frequency is determined to ensure that the target action set is frequently executed by users and is necessary.

[0065] Step 105 : determining a target usage scenario for the vehicle based on feature information of the user action in the target action set.

[0066] Specifically, characteristic information such as the time, location, and environment in which the user's actions occur can be used to determine the commonalities of different action sets in the same target action set. Based on these commonalities, it is helpful to judge the user's intention to perform the action set and determine the target car usage scenario. These defined car usage scenarios can facilitate subsequent classification and analysis of users. In particular, user needs can be analyzed based on the target car usage scenario, and then more user-friendly functions or content can be pushed to users based on their needs, thereby improving user experience.

[0067] For example, in an action set, action 1 is for the user to open the car door, action 2 is for the user to turn on the air conditioning and heating, and action 3 is for the user to turn on the seat heating switch. It can be known that the user performs the above actions 1-3 in an environment with relatively low temperature. Therefore, it can be determined that the car usage scenario corresponding to this action set is just getting in the car in winter. Based on this scenario, technicians can design an integrated component on the car key. When the car door is opened by wireless remote control of the car key, the vehicle automatically turns on the air conditioning and seat heating at the same time.

[0068] In this application, full coverage of vehicle usage information is achieved only through vehicle control signals and buried point signals, which reduces the complexity of data processing and helps to improve the efficiency of scene restoration; the user action corresponding to the vehicle signal is determined according to the jump logic of the vehicle signal, without worrying about the data interference caused by the user's subjective behavior, which helps to more accurately restore the vehicle usage scene. Therefore, the method of inferring the user action based on the vehicle signal and then determining the vehicle usage scene through the user action set, compared with the method of restoring the vehicle usage scene based on the customer survey data in the related art, not only reduces the complexity of the data and ensures the accuracy of the vehicle usage scene restoration, but also enhances the universality of the vehicle usage scene restoration, which helps to improve the user experience.

[0069] Reference Figure 2 As shown, it shows a flowchart of the steps of the second vehicle scene restoration method in an embodiment of the present application. The method may include the following steps:

[0070] Step 201: Collect vehicle signals, including vehicle control signals in different driving states and buried point signals of various interactive components inside the vehicle.

[0071] This step can refer to the content described in the aforementioned step 101, and this application will not elaborate on it here.

[0072] Step 202: pre-process the vehicle signal to obtain a second vehicle signal.

[0073] Considering that the collected vehicle signals may have problems such as interference and data missing, it is necessary to perform preprocessing such as data cleaning and data correction on the collected vehicle signals to avoid the impact of problematic vehicle signals on scene restoration.

[0074] Step 203: Determine the user action corresponding to the vehicle signal according to the transition logic of the second vehicle signal.

[0075] This step can refer to the content described in the aforementioned step 102, and this application will not go into details here.

[0076] Step 204 : Group the user actions according to the vehicle identification code of the source vehicle of the vehicle signal to obtain a first action set.

[0077] Considering the impact of different vehicles on vehicle signals, user actions can be initially grouped according to the source vehicle of the vehicle signal. Specifically, each vehicle has a unique vehicle identification number (VIN). Therefore, user actions can be grouped according to the VIN code of the vehicle signal source, and user actions corresponding to vehicle signals from the same vehicle can be placed in the same first action set.

[0078] Step 205: Calculate the time interval between two consecutive user actions in the first action set.

[0079] In the embodiment of the present application, the correlation between two actions can be measured by the time interval between the two actions. To facilitate calculation and data statistics, the user actions in the first action set can be sorted according to the execution time of the user actions, and then the time interval between two consecutive user actions can be calculated.

[0080] The strength of the correlation between two actions can be calculated quickly and conveniently based on the time interval. Of course, factors such as space and environmental conditions can be added to the time factor to measure the strength of the correlation between user actions. This application does not limit this.

[0081] Step 206: Add two consecutive user actions in the first action set whose time interval does not exceed a preset threshold to the same second action set.

[0082] Reference Figure 3 As shown, it shows a step flow chart of a user action grouping method in an embodiment of the present application, where N represents the number of actions of the current first user set.

[0083] As an example, for a single first action set, first construct a new second sample set, then starting from the first user action in the first action set, calculate the time interval between two consecutive actions A and B. If the time interval does not exceed the preset threshold, A and B are added to the current second sample set. If the time interval exceeds the preset threshold, check whether the current second sample set is an empty set. If the current second sample set is an empty set, B is added to the current second sample set. If the current second sample set is not an empty set, the current second sample set is directly output. Under the condition that there are subsequent actions in the first action set, continue to construct new second sample sets until all user actions in the first action set have been added to the corresponding second sample sets.

[0084] Optionally, second action sets with the same action composition but not belonging to the same first action set, i.e., the same vehicle, can be appropriately merged to ensure the universality of the vehicle usage scenarios while retaining the particularity of the vehicle usage scenarios for different vehicles.

[0085] Step 207 : determining a target action set from the at least one user action set according to the execution frequency of the user action set; the execution frequency of the target action set is greater than a preset frequency.

[0086] This step can refer to the content described in the aforementioned step 104, and this application will not elaborate on it here.

[0087] Step 208 : determining a target usage scenario for the vehicle based on feature information of the user action in the target action set.

[0088] This step can refer to the content described in the aforementioned step 104, and this application will not elaborate on it here.

[0089] Step 209, when the target vehicle usage scenario does not meet the preset conditions, adjust the preset threshold according to the target vehicle usage scenario, and re-determine the target vehicle usage scenario according to the adjusted preset threshold until the target vehicle usage scenario meets the preset conditions.

[0090] The preset conditions can be set based on actual conditions. If the target vehicle usage scenario does not meet the preset conditions, the preset threshold is adjusted and steps 205-208 are re-executed based on the adjusted preset threshold until the target vehicle usage scenario meets the preset conditions. For example, if the target vehicle usage scenario is too limited, the preset threshold can be appropriately increased; if the target vehicle usage scenario is too broad, the preset threshold can be appropriately lowered to achieve the desired target vehicle usage scenario.

[0091] In this application, full coverage of vehicle usage information is achieved only through vehicle control signals and buried point signals, which reduces the complexity of data processing and helps to improve the efficiency of scene restoration; the user action corresponding to the vehicle signal is determined according to the jump logic of the vehicle signal, without worrying about the data interference caused by the user's subjective behavior, which helps to more accurately restore the vehicle usage scene. Therefore, the method of inferring the user action based on the vehicle signal and then determining the vehicle usage scene through the user action set, compared with the method of restoring the vehicle usage scene based on the customer survey data in the related art, not only reduces the complexity of the data and ensures the accuracy of the vehicle usage scene restoration, but also enhances the universality of the vehicle usage scene restoration, which helps to improve the user experience.

[0092] Optionally, before grouping the user actions based on the time intervals between the user actions to obtain at least one user action set in step 103, the method further includes:

[0093] Step S11 , encoding the user action to obtain an encoded value of the user action.

[0094] In order to facilitate subsequent statistics and action sorting, user actions can be encoded. Specifically, the encoded values ​​can be sorted according to the execution time of the user actions, which is not limited in this application.

[0095] Optionally, the determining of the target action set from the at least one user action set according to the execution frequency of the user action set in step 104 includes:

[0096] Step S21, performing deduplication processing on the user actions in the user action set to obtain a third action set;

[0097] Step S22, sequentially connecting the user actions in the third action set according to the coding values;

[0098] Step S23, counting the execution frequency of the third action set;

[0099] Step S24: determining the third action set whose execution frequency exceeds the preset frequency threshold as the target action set.

[0100] Deduplication can refer to deleting consecutive repeated user actions in a user action set to eliminate the possibility of repeated user operations, or it can refer to merging user action sets with the same user action composition but different execution orders, retaining only one of them. Deduplication can be selectively performed based on actual circumstances, and this application does not limit this. The preset frequency threshold can be selected based on actual circumstances.

[0101] Optionally, the preprocessing of the vehicle signal to obtain the second vehicle signal in step 202 includes:

[0102] Step S31, parsing the vehicle signal to obtain an attribute value of the vehicle signal;

[0103] Step S32, deleting the vehicle signal with missing attribute values ​​to obtain the first vehicle signal with complete attribute values;

[0104] Step S33, correcting the attribute value of the first vehicle signal to obtain a second vehicle signal;

[0105] Step S34: determining the user action corresponding to the vehicle signal according to the transition logic of the second vehicle signal.

[0106] Among them, the correction processing can specifically refer to correcting vehicle signals with unreasonable errors such as attribute value errors, format errors, logical errors and data inconsistencies, so as to ensure the accuracy of vehicle signal related data used for scene restoration.

[0107] Optionally, the method further includes:

[0108] Step S41: upon receiving a preset user operation, generating a target instruction; the target instruction is used to control a target component corresponding to the target action set.

[0109] After determining the target vehicle usage scenario, the corresponding in-vehicle functions in the target vehicle usage scenario can be integrated and processed to quickly meet the user's needs in the target vehicle usage scenario, which helps to improve the user experience. For example, in an action set, action 1 is for the user to turn on the air conditioning and heating, and action 2 is for the user to turn on the seat heating switch. It can be known that the user performs the above actions 1-2 in a low temperature environment. Therefore, it can be determined that the vehicle usage scenario corresponding to the action set is a scenario with a low temperature inside the car. The technician can set a scene card in a certain part of the car according to this scenario. When the user clicks on the scene card, the in-vehicle control system can generate a target instruction. The target instruction can directly control the turning on of the air conditioning and seat heating, or the target instruction can simultaneously generate an air conditioning turning-on instruction for the air conditioning component and a seat heating instruction for the seat heating component, thereby turning on the air conditioning and seat heating functions at the same time.

[0110] Reference Figure 4 , which shows a schematic structural diagram of a vehicle scene restoration device according to an embodiment of the present application. The device 300 may include:

[0111] The signal acquisition module 301 is used to collect vehicle signals, including vehicle control signals of the vehicle in different driving states and buried point signals of various interactive components inside the vehicle;

[0112] A user action determination module 302 is configured to determine a user action corresponding to the vehicle signal according to a transition logic of the vehicle signal;

[0113] A grouping module 303 is configured to group the user actions based on the time intervals between the user actions to obtain at least one user action set, wherein the time interval between two consecutive user actions in the user action set is less than a preset threshold;

[0114] a target action set determining module 304, configured to determine a target action set from the at least one user action set according to an execution frequency of the user action set; the execution frequency of the target action set being greater than a preset frequency;

[0115] The target vehicle usage scenario determination module 305 is configured to determine the target vehicle usage scenario of the vehicle based on feature information of user actions in the target action set.

[0116] Optionally, the user action set includes a first action set, and the first action set includes a second action set; and the grouping module includes:

[0117] A first action set submodule, configured to group the user actions according to the vehicle identification code of the source vehicle of the vehicle signal to obtain a first action set;

[0118] a time interval calculation submodule, configured to calculate the time interval between two consecutive user actions in the first action set;

[0119] The second action set submodule is configured to add two consecutive user actions in the first action set whose time interval does not exceed a preset threshold to the same second action set.

[0120] Optionally, the device may further include:

[0121] The encoding module is used to encode the user actions to obtain the encoded values ​​of the user actions before grouping the user actions based on the time intervals between the user actions to obtain at least one user action set.

[0122] Optionally, the target action set determination module includes:

[0123] a deduplication submodule, configured to perform deduplication processing on the user actions in the user action set to obtain a third action set;

[0124] a connecting submodule, configured to sequentially connect the user actions in the third action set according to the coding values;

[0125] a statistics submodule, configured to count the execution frequency of the third action set;

[0126] The target action set determination submodule is configured to determine the third action set whose execution frequency exceeds a preset frequency threshold as the target action set.

[0127] Optionally, the user action determination module includes:

[0128] A parsing submodule, configured to parse the vehicle signal to obtain an attribute value of the vehicle signal;

[0129] A deletion submodule, configured to delete the vehicle signal with missing attribute values ​​and obtain the first vehicle signal with complete attribute values;

[0130] a correction submodule, configured to perform correction processing on the attribute value of the first vehicle signal to obtain a second vehicle signal;

[0131] The user action determination submodule is configured to determine the user action corresponding to the vehicle signal according to the transition logic of the second vehicle signal.

[0132] Optionally, the device may further include:

[0133] The target instruction generation module is used to generate a target instruction when a preset user operation is received; the target instruction is used to control the target component corresponding to the target action set.

[0134] Optionally, the device may further include:

[0135] A loop module is used to adjust the preset threshold according to the target vehicle usage scenario when the target vehicle usage scenario does not meet the preset conditions, and to re-determine the target vehicle usage scenario according to the adjusted preset threshold until the target vehicle usage scenario meets the preset conditions.

[0136] In this application, full coverage of vehicle usage information is achieved only through vehicle control signals and buried point signals, which reduces the complexity of data processing and helps to improve the efficiency of scene restoration; the user action corresponding to the vehicle signal is determined according to the jump logic of the vehicle signal, without worrying about the data interference caused by the user's subjective behavior, which helps to more accurately restore the vehicle usage scene. Therefore, the method of inferring the user action based on the vehicle signal and then determining the vehicle usage scene through the user action set, compared with the method of restoring the vehicle usage scene based on the customer survey data in the related art, not only reduces the complexity of the data and ensures the accuracy of the vehicle usage scene restoration, but also enhances the universality of the vehicle usage scene restoration, which helps to improve the user experience.

[0137] The vehicle usage scene restoration device has the same or similar beneficial effects as any of the aforementioned vehicle usage scene restoration methods, and they can be referenced with each other. In order to avoid repetition, they will not be described here.

[0138] The present application also provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and runnable on the processor. When the computer program is executed by the processor, it implements any step of the aforementioned vehicle usage scene restoration method.

[0139] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0140] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0141] An embodiment of the present application also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the aforementioned vehicle usage scene restoration methods are implemented.

[0142] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0143] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the relevant technology, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, air conditioner, or network equipment, etc.) to execute the methods described in each embodiment of the present application.

[0144] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are protected by this application.

Claims

1. A method for restoring a vehicle usage scene, characterized in that: The method comprises: Collecting vehicle signals, including vehicle control signals in different driving states and buried point signals of various interactive components inside the vehicle; Determining a user action corresponding to the vehicle signal according to a transition logic of the vehicle signal; grouping the user actions based on time intervals between the user actions to obtain at least one user action set, wherein the time interval between two consecutive user actions in the user action set is less than a preset threshold; the user action set includes a first action set, and the first action set includes a second action set; Determining a target action set from the at least one user action set according to an execution frequency of the user action set; the execution frequency of the target action set is greater than a preset frequency; Determining a target usage scenario for the vehicle based on feature information of user actions in the target action set; The grouping of the user actions based on the time intervals between the user actions to obtain at least one user action set includes: Grouping the user actions according to the vehicle identification code of the source vehicle of the vehicle signal to obtain a first action set; Calculating the time interval between two consecutive user actions in the first action set; Two consecutive user actions in the first action set whose time interval does not exceed a preset threshold are added to the same second action set.

2. The method according to claim 1, characterized in that Before grouping the user actions based on the time intervals between the user actions to obtain at least one user action set, the method further includes: The user action is encoded to obtain an encoded value of the user action.

3. The method according to claim 2, characterized in that The determining a target action set from the at least one user action set according to the execution frequency of the user action set includes: performing deduplication processing on the user actions in the user action set to obtain a third action set; sequentially connecting the user actions in the third action set according to the coding values; Counting the execution frequency of the third action set; The third action set whose execution frequency exceeds the preset frequency threshold is determined as the target action set.

4. The method according to claim 1, wherein The determining, according to the transition logic of the vehicle signal, the user action corresponding to the vehicle signal includes: parsing the vehicle signal to obtain an attribute value of the vehicle signal; Deleting the vehicle signal with missing attribute values ​​to obtain the first vehicle signal with complete attribute values; performing correction processing on the attribute value of the first vehicle signal to obtain a second vehicle signal; A user action corresponding to the vehicle signal is determined according to the transition logic of the second vehicle signal.

5. The method according to claim 1, wherein The method further comprises: When a preset user operation is received, a target instruction is generated; the target instruction is used to control the target component corresponding to the target action set.

6. The method according to claim 1, characterized in that The method further comprises: In the case that the target vehicle usage scenario does not meet the preset conditions, the preset threshold is adjusted according to the target vehicle usage scenario, and the target vehicle usage scenario is re-determined according to the adjusted preset threshold until the target vehicle usage scenario meets the preset conditions.

7. A vehicle scene restoration device, characterized in that: include: A signal acquisition module is used to collect vehicle signals, including vehicle control signals of the vehicle in different driving states and buried point signals of various interactive components inside the vehicle; A user action determination module, configured to determine a user action corresponding to the vehicle signal according to a transition logic of the vehicle signal; a grouping module, configured to group the user actions based on the time intervals between the user actions to obtain at least one user action set, wherein the time interval between two consecutive user actions in the user action set is less than a preset threshold; the user action set includes a first action set, and the first action set includes a second action set; a target action set determining module, configured to determine a target action set from the at least one user action set according to an execution frequency of the user action set; the execution frequency of the target action set being greater than a preset frequency; a target vehicle usage scenario determination module, configured to determine a target vehicle usage scenario for the vehicle based on feature information of user actions in the target action set; Wherein, the grouping module includes: A first action set submodule, configured to group the user actions according to the vehicle identification code of the source vehicle of the vehicle signal to obtain a first action set; a time interval calculation submodule, configured to calculate the time interval between two consecutive user actions in the first action set; The second action set submodule is configured to add two consecutive user actions in the first action set whose time interval does not exceed a preset threshold to the same second action set.

8. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the vehicle usage scene restoration method as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the vehicle usage scene restoration method as described in any one of claims 1 to 6 are implemented.

Images