OTA upgrading method based on Internet of Vehicles, cloud server and computer program product

Abstract

The invention relates to a method for OTA upgrading based on the Internet of Vehicles, and the method comprises the steps: analyzing and processing vehicle state information received from each vehicle and stored OTA fault data, so as to determine an OTA common mode of each vehicle; calculating the OTA upgrade failure probability of each OTA common mode based on the vehicle state data related to the OTA common mode of each vehicle; and selecting candidate vehicles to be subjected to OTA upgrading based on the OTA common mode of each vehicle and the OTA upgrading failure probability. The invention also relates to a cloud server and a computer program product. According to the method and the device, the vehicle with relatively low OTA upgrading failure probability can be automatically selected as the candidate vehicle to be subjected to OTA upgrading. Through the mode, OTA upgrading faults of a large number of vehicles due to the state problem of the same vehicle can be avoided, and the OTA upgrading efficiency and the user experience feeling are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of Internet of Vehicles, and in particular to a method for OTA upgrade based on Internet of Vehicles, a cloud server, and a computer program product for at least assisting in implementing steps of the method according to the present application. BACKGROUND

[0002] In the process of OTA upgrade based on Internet of Vehicles, upgrade failure may occur, and the cause of upgrade failure usually needs to be determined through manual analysis for a certain period of time. During manual analysis and maintenance, other vehicles in OTA upgrade may also have the same upgrade failure, which greatly affects the success rate of OTA upgrade process and even affects the acceptance of OTA upgrade by users.

[0003] Therefore, there is room for improvement in the current OTA upgrade method. SUMMARY

[0004] The present application aims to provide a method for OTA upgrade based on Internet of Vehicles, a cloud server, and a computer program product to at least partially solve the problems in the prior art.

[0005] According to a first aspect of the present application, a method for OTA upgrade based on Internet of Vehicles is provided, which can include:

[0006] vehicle state information received from each vehicle and stored OTA failure data to determine the OTA common mode of each vehicle;

[0007] calculating the OTA upgrade failure probability of each OTA common mode based on the vehicle state data of each vehicle related to the OTA common mode; and

[0008] selecting candidate vehicles to be executed OTA upgrade based on the OTA common mode of each vehicle and the OTA upgrade failure probability.

[0009] The core idea of the present application is to determine the OTA common mode of each vehicle by analyzing and processing vehicle state information received from each vehicle and stored OTA failure data with the help of a deep learning network model, and to calculate the OTA upgrade failure probability of each OTA common mode, thereby automatically selecting vehicles with lower OTA upgrade failure probability as candidate vehicles to be executed OTA upgrade. In this way, the same OTA upgrade failure can be avoided for a large number of vehicles, effectively improving the efficiency and user experience of OTA upgrade.

[0010] According to an optional embodiment of the present application, the vehicle status information can include a vehicle identification code, vehicle metadata, and vehicle OTA upgrade result, etc. Optionally, the vehicle metadata can include, for example, a vehicle software / hardware directory, log information, electrical and electronic signals, diagnostic information, driving behavior information, user behavior information, and / or vehicle environment information, etc. Optionally, the vehicle OTA upgrade result can include, for example, an OTA upgrade failure state or an OTA upgrade success state, etc.

[0011] According to another optional embodiment of the present application, similarity of the vehicle status information received from each vehicle can be evaluated based on the vehicle metadata, and an OTA common mode of each vehicle can be determined based on the evaluated similarity and the stored OTA failure data.

[0012] According to another optional embodiment of the present application, the OTA common mode can include an OTA failure code, a log-based feature, an index-based feature, vehicle environment information, and / or a vehicle software / hardware version number, etc.

[0013] According to another optional embodiment of the present application, the stored OTA failure data can include a determined OTA failure type, OTA failure ticket information, and / or user complaint information, etc.

[0014] According to another optional embodiment of the present application, a vehicle with an OTA upgrade failure probability less than or equal to a preset probability threshold can be selected as a candidate vehicle to be executed with OTA upgrade. Optionally, a vehicle with an OTA upgrade failure probability greater than the preset probability threshold can be canceled for OTA upgrade. Optionally, a vehicle with an OTA upgrade failure probability greater than the preset probability threshold can be added to an OTA prohibited list.

[0015] According to another optional embodiment of the present application, the method can further include:

[0016] determining an OTA failure factor of the vehicle based on the vehicle status data of each vehicle related to the OTA common mode and the stored OTA failure data, and issuing notification information about the OTA failure factor of the vehicle to the vehicle.

[0017] According to another optional embodiment of the present application, an OTA upgrade failure probability of each vehicle can be determined based on an OTA upgrade failure probability of each OTA common mode, and a candidate vehicle to be executed with OTA upgrade can be selected according to the OTA upgrade failure probability of each vehicle, and OTA data can be issued to the corresponding candidate vehicle according to a vehicle identification code.

[0018] According to a second aspect of the present application, a cloud server is provided, which is used to execute the method according to the present application, wherein the cloud server can include the following components:

[0019] an OTA characteristic evaluation module configured to analyze the vehicle status information received from the respective vehicles and the stored OTA failure data to determine OTA common patterns of the respective vehicles, and to calculate an OTA upgrade failure probability of each OTA common pattern based on the vehicle status data of the respective vehicles related to the OTA common pattern; and

[0020] a vehicle selection module configured to select candidate vehicles to be performed OTA upgrade based on the OTA common patterns of the respective vehicles and the OTA upgrade failure probability.

[0021] According to a third aspect of the present application, a computer program product, e.g. a computer readable program carrier, comprising or storing computer program instructions, which, when executed by a processor, assist in at least implementing the steps of the method according to the present application. BRIEF DESCRIPTION OF DRAWINGS

[0022] The principles, features and advantages of the present application can be better understood by the following detailed description of the application, taken in conjunction with the accompanying drawings. The drawings show:

[0023] Figure 1 a workflow diagram of a method for OTA upgrade based on vehicle networking according to one example embodiment of the present application;

[0024] Figure 2 a workflow diagram of a method for OTA upgrade based on vehicle networking according to another example embodiment of the present application; and

[0025] Figure 3 a schematic block diagram of a cloud server according to one example embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the technical problems to be solved by the present application, the technical solutions and the beneficial technical effects more clear, the present application will be further described in detail below in conjunction with the drawings and multiple example embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the protection scope of the present application.

[0027] Figure 1 a workflow diagram of a method for OTA upgrade based on vehicle networking according to one example embodiment of the present application. The following example embodiments describe the method according to the present application in more detail.

[0028] As Figure 1As shown, the method can include steps S1 to S3. In step S1, vehicle status information received from each vehicle and stored OTA failure data can be analyzed to determine an OTA common pattern of each vehicle. In the current embodiment of the present application, each vehicle can upload its vehicle status information to the cloud server 10 during the process of performing OTA upgrade by the vehicle or in the case of preparing OTA upgrade by the vehicle, wherein the vehicle status information can include vehicle identification code, vehicle metadata, and vehicle OTA upgrade result, etc. Here, the vehicle identification code is particularly the vehicle VIN code to indicate the identity information of the vehicle. The vehicle metadata is descriptive information of the vehicle data and its attributes to support the functions of networked management of data, tracking of data changes, effective discovery of information resources, search, integrated organization, etc. For example, the vehicle metadata can include vehicle software / hardware directory, log information, electrical and electronic signals, diagnostic information, driving behavior information, user behavior information, and / or vehicle environment information, etc. The vehicle OTA upgrade result can include OTA upgrade failure status or OTA upgrade success status, which is uploaded after the vehicle OTA upgrade is completed. Figure 3

[0029] Here, a deep learning network model can be provided in the server 10, which can include a convolutional neural network, a recurrent neural network, and / or a model based on an attention mechanism, etc. The deep learning network model can evaluate the similarity of the vehicle status information received from each vehicle based on the vehicle metadata, and determine the OTA common pattern of each vehicle based on the evaluated similarity and the stored OTA failure data. In the sense of the present application, the OTA common pattern is a key feature that can determine whether the OTA upgrade of the vehicle will appear a certain type of OTA failure and the probability of appearing this type of OTA failure, i.e., the vehicle containing the key feature will appear this type of OTA failure with a certain probability.

[0030] ​Exemplarily, the OTA common mode can include an OTA fault code, wherein based on the diagnostic information and the vehicle OTA upgrade result received from each vehicle, it can be determined that the part of vehicles with OTA upgrade failure have the same or similar OTA fault code, thereby assigning the OTA fault code as the OTA common mode for this part of vehicles. Optionally, the OTA common mode can also include a log-based feature, wherein based on the log information and the vehicle OTA upgrade result received from each vehicle, it can be determined that the part of vehicles with OTA upgrade failure have the same or similar log-based feature, thereby assigning the log-based feature as the OTA common mode for this part of vehicles. Optionally, the OTA common mode can also include vehicle environment information, wherein based on the vehicle environment information received from each vehicle, it can be determined that the part of vehicles with OTA upgrade failure have the same or similar vehicle environment information, thereby assigning the vehicle environment information as the OTA common mode for this part of vehicles. Optionally, the OTA common mode can also include a soft / hardware version number, wherein based on the soft / hardware directory received from each vehicle, it can be determined that the part of vehicles with OTA upgrade failure have the same or similar soft / hardware version number, thereby assigning the soft / hardware version number as the OTA common mode for this part of vehicles. Optionally, the OTA common mode can also be based on a feature of an index, wherein based on the index information such as electrical and electronic signal, driving behavior information and / or user behavior information received from each vehicle, it can be determined that the part of vehicles with OTA upgrade failure have the same or similar index-based feature, thereby assigning the index-based feature as the OTA common mode for this part of vehicles, and so on.

[0031] Meanwhile, in the cloud server 10, a database about OTA fault data can be stored, and the stored OTA fault data includes, for example, the determined OTA fault type, OTA fault work order information, and / or user complaint information, etc. Here, based on the determined OTA fault type, the OTA fault that can occur in the vehicle can be classified; based on the OTA fault work order and / or user complaint, the supplementary information for the vehicle OTA upgrade result can be provided, and the credibility of the vehicle OTA upgrade result can be verified, thereby improving the data accuracy of the vehicle OTA upgrade result.

[0032] In step S2, the OTA upgrade failure probability of each OTA common mode can be calculated based on the vehicle state data of each vehicle related to the OTA common mode. Here, the deep learning network model can filter out the vehicle state data related to a certain OTA common mode, e.g. the vehicle state data related to a certain software / hardware version number, from the vehicle state data based on the vehicle metadata, and count the proportion of the OTA upgrade failure state in the vehicle OTA upgrade results under the software / hardware version number, thereby calculating the OTA upgrade failure probability of the OTA common mode. Due to the large amount of calculation data, the deep learning network model does not calculate the OTA upgrade failure probability in real time, but calculates the OTA upgrade failure probability in batches at certain time intervals based on the received vehicle state data, and stores the calculated OTA upgrade failure probability in the cloud server 10, thereby improving the operation efficiency of the deep learning network model.

[0033] In step S3, candidate vehicles to be executed OTA upgrade can be selected based on the OTA common mode of each vehicle and the OTA upgrade failure probability. In the case where the OTA common mode of each vehicle has been determined, the deep learning network model can determine the OTA upgrade failure probability of each vehicle based on the OTA upgrade failure probability of each OTA common mode, automatically select candidate vehicles to be executed OTA upgrade according to the OTA upgrade failure probability of each vehicle, and issue OTA data to the corresponding candidate vehicles (e.g. the second vehicle 2 in Figure 3 here) according to the vehicle identification code. Here, vehicles with OTA upgrade failure probability less than or equal to a preset probability threshold can be selected as candidate vehicles to be executed OTA upgrade, and vehicles with OTA upgrade failure probability greater than the preset probability threshold can be added to the OTA prohibited list, thereby ensuring that the candidate vehicles to be executed OTA upgrade all have a lower upgrade failure probability. For example, for the first vehicle 1 that is being OTA upgraded, the OTA upgrade of vehicles with OTA upgrade failure probability greater than the preset probability threshold can be cancelled to avoid errors in the OTA upgrade process of the first vehicle 1. For example, in the case where the OTA common mode of a vehicle is a certain software / hardware version number and the OTA upgrade failure probability of the vehicle is greater than the preset probability threshold, the vehicle with this software / hardware version number can be included in the OTA prohibited list, and / or the OTA upgrade process of the vehicle with this software / hardware version number can be cancelled, until the vehicle with this software / hardware version number is removed from the OTA prohibited list through manual inspection to solve the OTA failure caused by this software / hardware version number.

[0034] According to the above embodiments of the present application, the OTA common mode of each vehicle is determined by means of a deep learning network model by analyzing and processing the vehicle status information received from each vehicle and the stored OTA failure data, and the OTA upgrade failure probability of each OTA common mode is calculated, thereby automatically selecting the vehicle with lower OTA upgrade failure probability as the candidate vehicle to be executed OTA upgrade. In this way, it can avoid a large number of vehicles from appearing OTA upgrade failure due to the same vehicle state problem, effectively improving the efficiency and user experience of OTA upgrade.

[0035] Figure 2 A workflow diagram of a method for OTA upgrade based on Internet of Vehicles according to another exemplary embodiment of the present application is shown. The following only sets forth the differences from the embodiments shown in Figure 1 , while the same steps are not described again for the sake of brevity.

[0036] As shown in Figure 2 , the method can further include step S4. In step S4, the OTA failure factor of the vehicle can be determined based on the vehicle status data related to the OTA common mode of each vehicle and the stored OTA failure data, and the notification information about the OTA failure factor of the vehicle is issued to the vehicle. Here, the deep learning neural network can analyze and process the vehicle status data related to the OTA common mode of each vehicle and the stored OTA failure data, especially learn the OTA failure data not stored in the cloud server 10 and determine the OTA failure factor of the first vehicle 1, for example. The first vehicle 1 will notify the user of the received notification information about the OTA failure factor of the vehicle through a human-computer interaction unit, such as a central display screen, an instrument panel, a head-up display, and / or a vehicle-mounted voice device, etc.

[0037] In addition, it should be noted that the step numbers described herein do not necessarily represent the sequence, but are only a kind of figure mark, according to the specific circumstances, the sequence can be changed, as long as the technical purpose of the present application can be realized.

[0038] Figure 3 A schematic block diagram of a cloud server according to one exemplary embodiment of the present application is shown.

[0039] As shown in Figure 3 , the cloud server 10 for executing the method according to the present application can include the following components:

[0040] - an OTA characteristic evaluation module 11 configured to analyze and process the vehicle status information received from each vehicle and the stored OTA failure data to determine the OTA common mode of each vehicle, and calculate the OTA upgrade failure probability of each OTA common mode based on the vehicle status data related to the OTA common mode of each vehicle; and

[0041] - a vehicle selection module 12 configured for selecting, based on the OTA common pattern of each vehicle and the OTA upgrade failure probability, a candidate vehicle to perform an OTA upgrade.

[0042] It should be understood that the expressions "first", "second", "third", etc. are used herein only for descriptive purposes and should not be construed as indicating or implying relative importance, nor should they be construed as implying a specific number of the technical features indicated.

[0043] If an embodiment includes a "and / or" relationship between a first feature and a second feature, this is to be interpreted as: according to one implementation the embodiment has both the first feature and the second feature, according to another implementation the embodiment has only the first feature, and according to yet another implementation the embodiment has only the second feature.

[0044] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even if only a single embodiment is described with respect to a particular feature. The feature examples provided in the present disclosure are intended to be illustrative rather than restrictive. In practice, combinations of features can be made with one another according to the practical needs, provided that it is technically feasible. Various substitutions, modifications and changes can be conceived without departing from the spirit and scope of the present disclosure.

Claims

1. A method for vehicle-to-everything (V2X) based over-the-air (OTA) upgrade, the method comprising: analyzing vehicle status information received from respective vehicles and stored OTA failure data to determine OTA common patterns of the respective vehicles; calculating an OTA upgrade failure probability of each of the OTA common patterns based on vehicle status data of the respective vehicles related to the OTA common patterns; and selecting candidate vehicles to perform the OTA upgrade based on the OTA common patterns of the respective vehicles and the OTA upgrade failure probability. The vehicle status information includes a vehicle identification code, vehicle metadata, and vehicle OTA upgrade results, wherein the vehicle metadata includes, for example, a vehicle's software / hardware catalog, log information, electrical and electronic signals, diagnostic information, driving behavior information, user behavior information, and / or vehicle environment information, and the vehicle OTA upgrade results include an OTA upgrade failure status or an OTA upgrade success status.

2. The method of claim 1, wherein, The similarity of the vehicle status information received from the respective vehicles is evaluated based on the vehicle metadata, and the OTA common patterns of the respective vehicles are determined based on the evaluated similarity and the stored OTA failure data.

3. The method of any of the preceding claims, wherein, The OTA common patterns include OTA failure codes, log-based features, index-based features, vehicle environment information, and / or vehicle software / hardware version numbers.

4. The method according to any of the preceding claims, wherein, The stored OTA failure data includes determined OTA failure types, OTA failure ticket information, and / or user complaint information.

5. The method according to any of the preceding claims, wherein, The vehicles with an OTA upgrade failure probability less than or equal to a preset probability threshold are selected as the candidate vehicles to perform the OTA upgrade; and / or 6. The method of any of the preceding claims, wherein, The OTA upgrade of the vehicles with an OTA upgrade failure probability greater than the preset probability threshold is canceled; and / or The vehicles with an OTA upgrade failure probability greater than the preset probability threshold are added to an OTA blacklist. The method further comprises:

7. The method according to any of the preceding claims, wherein, determining an OTA failure factor of a vehicle based on vehicle status data of the vehicle related to the OTA common patterns and the stored OTA failure data, and issuing notification information about the OTA failure factor of the vehicle to the vehicle. The OTA upgrade failure probability of each vehicle is determined based on the OTA upgrade failure probability of each of the OTA common patterns, and candidate vehicles to perform the OTA upgrade are selected according to the OTA upgrade failure probability of each vehicle, and OTA data is issued to the respective candidate vehicles according to a vehicle identification code.

8. The method of any of the preceding claims, wherein, The cloud server (10) comprises the following components:

9. A cloud server (10) for performing the method according to any one of the preceding claims, wherein an OTA feature evaluation module (11) configured to analyze vehicle status information received from respective vehicles and stored OTA failure data to determine OTA common patterns of the respective vehicles, and to calculate an OTA upgrade failure probability of each of the OTA common patterns based on vehicle status data of the respective vehicles related to the OTA common patterns; and a vehicle selection module (12) configured to select candidate vehicles to perform the OTA upgrade based on the OTA common patterns of the respective vehicles and the OTA upgrade failure probability. ​ ​ 10. A computer program product, such as a computer readable program carrier, containing or storing computer program instructions, which, when executed by a processor, at least assist in implementing the steps of the method according to any one of claims 1 to 8.

Images