Method and apparatus for parameter calibration

Abstract

The application provides a parameter calibration method and device, which can be applied to intelligent vehicles, new energy vehicles, networked vehicles, intelligent driving vehicles and the like. The method comprises the following steps: obtaining evaluation results of parameter combinations of a plurality of devices, wherein the evaluation results of the parameter combinations of the plurality of devices are obtained through calibration tests of the plurality of devices based on the parameter combinations of the plurality of devices in a first time period; and obtaining at least one adjusted parameter combination according to the evaluation results of the parameter combinations of the plurality of devices. The scheme of the application can improve the efficiency of parameter calibration.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, and more particularly, to a parameter calibration method and device. BACKGROUND

[0002] Parameter calibration refers to a process of finding a set of parameters applicable under various conditions, for example, under different hardware conditions or different environmental conditions. Taking vehicle calibration as an example, vehicle calibration refers to a process of optimizing parameters in control software in order to obtain satisfactory vehicle performance, meet requirements before vehicle delivery, and achieve relevant national standards after controller hardware, control software, and related sensors are determined.

[0003] Vehicle calibration results are important factors affecting vehicle performance. Before a vehicle is put on the market, experienced calibration engineers usually calibrate based on sample vehicles. In order to make the vehicle meet performance requirements under various working conditions, calibration experiments need to be performed under different working conditions to find suitable parameter combinations. Due to the limitations of working conditions, environment, etc., the calibration process is time-consuming and costly. Taking the braking system in a vehicle as an example, the parameter calibration in the braking system usually needs to go through a long calibration process of “two summers and one winter”, which seriously affects the calibration efficiency.

[0004] Therefore, how to improve the efficiency of parameter calibration is a problem to be solved. SUMMARY

[0005] The present application provides a parameter calibration method and device, which can improve the efficiency of parameter calibration.

[0006] In a first aspect, a parameter calibration method is provided, comprising: obtaining evaluation results of parameter combinations of a plurality of devices, the evaluation results of the parameter combinations of the plurality of devices being obtained by performing calibration experiments on the plurality of devices based on the parameter combinations of the plurality of devices in a first time period, the first time period being less than or equal to a first threshold; and obtaining at least one adjusted parameter combination according to the evaluation results of the parameter combinations of the plurality of devices.

[0007] According to the scheme of the embodiments of the present application, the plurality of devices perform calibration experiments in the same time period, which can improve the efficiency of data collection, is conducive to real-time adjustment of device parameters based on the evaluation results of the parameter combinations of the plurality of devices, and further improves the calibration efficiency, reduces the calibration period, and reduces the calibration cost.

[0008] The plurality of devices in the scheme of the embodiments of the present application can simultaneously perform calibration experiments under different working conditions, which improves the calibration efficiency and reduces the time cost and economic cost.

[0009] The multiple devices of the scheme of the embodiment of the application can be in different working conditions at the same time, and the real-time collection of data of the multiple devices and parameter optimization can be realized, which is beneficial to simultaneously finding a parameter combination compatible with multiple working conditions under the multiple working conditions, improving the stability of the parameters, and further improving the calibration efficiency.

[0010] In the scheme of the embodiment of the application, parameter calibration is performed based on the evaluation result of the test data of the multiple devices, which reduces the cognitive bias of different calibration engineers, improves the calibration quality, and is beneficial to avoiding the situation of recalling the devices after they are shipped.

[0011] The scheme of the embodiment of the application can also use an automatic optimization algorithm to complete calibration, which reduces the number of calibration engineers, reduces labor costs, and further reduces the influence of subjective preferences of the calibration engineers on the calibration result.

[0012] The calibration test of the multiple devices in the first time period can also be understood as that the multiple devices can perform the calibration test in the same time period, for example, the multiple devices can simultaneously perform the calibration test.

[0013] The parameters in the parameter combination are the parameters that need to be calibrated. The parameter combination includes at least one parameter.

[0014] The parameter calibration device can belong to the multiple devices, or can not belong to the multiple devices.

[0015] The parameter combinations of the multiple devices can be the same or different.

[0016] The evaluation result of the parameter combination of the multiple devices is used to indicate the quality of the parameter combination of the multiple devices. The evaluation result of the parameter combination can also be understood as the value of the parameter combination.

[0017] Specifically, the performance of the device can be evaluated based on one or more evaluation indexes to obtain the evaluation result of the parameter combination.

[0018] The at least one adjusted parameter combination can be the same or different.

[0019] In combination with the first aspect, in some implementations of the first aspect, the parameter combinations of the multiple devices are the same, the working conditions of the multiple devices are different, and the at least one adjusted parameter combination is obtained according to the evaluation result of the parameter combination of the multiple devices, including: processing the evaluation result of the parameter combination of the multiple devices to obtain a summary evaluation result; and obtaining the at least one adjusted parameter combination according to the summary evaluation result.

[0020] The aggregated evaluation result can be determined in various manners. For example, a weighted average of the evaluation results of the parameter combinations of the plurality of devices is taken as the aggregated evaluation result. For another example, the minimum value among the evaluation results of the parameter combinations of the plurality of devices is taken as the aggregated evaluation result. For another example, the maximum value among the evaluation results of the parameter combinations of the plurality of devices is taken as the aggregated evaluation result. The embodiments of this application do not limit the manner of determining the aggregated evaluation result.

[0021] In this way, the evaluation results of the same parameter combination under different working conditions are aggregated to obtain the aggregated evaluation result of the parameter combination, and the current parameter combination is optimized according to the aggregated evaluation result, which is beneficial to obtain a better parameter combination and further improve the calibration efficiency.

[0022] With reference to the first aspect, in some implementations of the first aspect, the method further includes: sending the at least one adjusted parameter combination to the at least one device.

[0023] With reference to the first aspect, in some implementations of the first aspect, the at least one device is determined according to at least one of the working conditions of the plurality of devices or the at least one adjusted parameter combination.

[0024] With reference to the first aspect, in some implementations of the first aspect, the evaluation result of the parameter combination of the plurality of devices is obtained by evaluating the test data of the plurality of devices, and the test data of the plurality of devices is determined according to data collected in the process of calibrating the test of the plurality of devices respectively based on the parameter combination of the plurality of devices in a first time period.

[0025] For example, the test data of the plurality of devices can be obtained by processing the data collected by the sensors in the process of calibrating the test of the plurality of devices respectively based on the parameter combination of the plurality of devices.

[0026] For example, processing the data collected by the sensors can include filtering, frequency reduction, noise reduction, or the like.

[0027] Alternatively, the test data of the plurality of devices can be the data collected by the sensors in the process of calibrating the test of the plurality of devices respectively based on the parameter combination of the plurality of devices.

[0028] With reference to the first aspect, in some implementations of the first aspect, the evaluation result of the parameter combination of the plurality of devices is obtained by evaluating the test data of the plurality of devices according to the working conditions of the plurality of devices.

[0029] In the embodiments of this application, the test data of the device is evaluated based on the working condition of the device, which can improve the accuracy of the evaluation result and further improve the effect of parameter calibration.

[0030] With reference to the first aspect, in some implementations of the first aspect, the evaluation result of the parameter combination of the plurality of devices can be obtained by evaluating test data of the plurality of devices according to configuration information of the plurality of vehicles.

[0031] In the embodiments of the present application, the test data of the device is evaluated based on the configuration information of the device, which can improve the accuracy of the evaluation result, and further improve the effect of parameter calibration.

[0032] With reference to the first aspect, in some implementations of the first aspect, the evaluation result of the parameter combination of the plurality of devices is obtained by user feedback.

[0033] In the embodiments of the present application, the evaluation result of the parameter combination can be obtained by user feedback, which can fully consider the user's feelings and is beneficial to improve the user experience.

[0034] With reference to the first aspect, in some implementations of the first aspect, the method further comprises: sending a to-be-executed action sequence of at least one device to the at least one device respectively, the to-be-executed action sequence of the at least one device comprising actions required to be executed by the at least one device in a calibration test based on an adjusted parameter combination of the at least one device.

[0035] The to-be-executed action sequence of the at least one device can be the same or different.

[0036] Exemplarily, the to-be-executed action sequence of the at least one device can also be determined by the at least one device itself.

[0037] Alternatively, the to-be-executed action sequence of the at least one device can be pre-set.

[0038] Alternatively, the to-be-executed action sequence of the at least one device can be determined by the user.

[0039] With reference to the first aspect, in some implementations of the first aspect, the to-be-executed action sequence of the at least one device is determined according to at least one of the following: an action covered by a parameter calibration requirement, a working condition of the at least one device, or an evaluation result of the parameter combination of the plurality of devices.

[0040] With reference to the first aspect, in some implementations of the first aspect, the plurality of devices comprises at least one of the following: a vehicle or a test bench.

[0041] With reference to the first aspect, in some implementations of the first aspect, the plurality of devices comprises a sensor.

[0042] In a second aspect, a method for parameter calibration is provided, including: obtaining an adjusted parameter combination, the adjusted parameter combination being obtained according to evaluation results of parameter combinations of a plurality of devices, the plurality of devices including a first device, the evaluation results of the parameter combinations of the plurality of devices being obtained by performing calibration tests by the plurality of devices respectively based on the parameter combinations of the plurality of devices within a first time period, the first time period being less than or equal to a first threshold; and controlling the first device to perform a calibration test based on the adjusted parameter combination.

[0043] According to the scheme of the embodiments of the present application, the plurality of devices perform calibration tests within the same time period, which can improve the efficiency of data collection, and is conducive to real-time adjustment of the parameters of the devices based on the evaluation results of the parameter combinations of the plurality of devices, thereby improving the calibration efficiency, reducing the calibration period, and reducing the calibration cost.

[0044] The plurality of devices of the scheme of the embodiments of the present application can perform calibration tests simultaneously under different working conditions, which improves the calibration efficiency and reduces the time cost and economic cost.

[0045] The plurality of devices of the scheme of the embodiments of the present application can be in different working conditions at the same time, which can realize real-time aggregation of data of the plurality of devices and parameter optimization, is conducive to finding a parameter combination compatible with a plurality of working conditions at the same time under the plurality of working conditions, improves the stability of the parameters, and thereby improves the calibration efficiency.

[0046] In the scheme of the embodiments of the present application, the parameter calibration is performed based on the evaluation results of the test data of the plurality of devices, which reduces the cognitive bias caused by different calibration engineers, improves the calibration quality, and is conducive to avoiding the situation that the devices are recalled after being shipped.

[0047] The scheme of the embodiments of the present application can also use an automatic optimization algorithm to complete the calibration, which reduces the number of calibration engineers, reduces the labor cost, and further reduces the influence of subjective preferences of the calibration engineers on the calibration results.

[0048] In combination with the second aspect, in some implementation manners of the second aspect, the parameter combinations of the plurality of devices are the same, the working conditions of the plurality of devices are different, and the adjusted parameter combination is obtained according to aggregated evaluation results, the aggregated evaluation results being obtained by processing the evaluation results of the parameter combinations of the plurality of devices.

[0049] In combination with the second aspect, in some implementation manners of the second aspect, the first device is determined according to at least one of the following: the working conditions of the plurality of devices or the adjusted parameter combination.

[0050] With reference to the second aspect, in some implementations of the second aspect, the evaluation result of the parameter combination of the plurality of devices is obtained by evaluating test data of the plurality of devices, and the test data of the plurality of devices is determined according to data collected in a process in which the plurality of devices respectively perform calibration experiments based on the parameter combination of the plurality of devices in the first time period.

[0051] With reference to the second aspect, in some implementations of the second aspect, the evaluation result of the parameter combination of the plurality of devices is obtained by user feedback.

[0052] With reference to the second aspect, in some implementations of the second aspect, the method further includes: obtaining, by the first device, a to-be-executed action sequence of the first device, the to-be-executed action sequence of the first device including actions that the first device needs to perform in a process in which the first device performs a calibration experiment based on the adjusted parameter combination.

[0053] With reference to the second aspect, in some implementations of the second aspect, the to-be-executed action sequence of the first device is determined according to at least one of the following: an action covered by the parameter calibration requirement, a working condition in which the first device is located, or the evaluation result of the parameter combination of the plurality of devices.

[0054] With reference to the second aspect, in some implementations of the second aspect, the first device is: a vehicle or a test bench.

[0055] The third aspect provides a parameter calibration apparatus, which includes modules or units for performing the method in the first aspect and any implementation of the first aspect.

[0056] The fourth aspect provides a parameter calibration apparatus, which includes modules or units for performing the method in the second aspect and any implementation of the second aspect.

[0057] It should be understood that the extensions, limitations, explanations and descriptions of related content in the above first aspect also apply to the same content in the second aspect, the third aspect and the fourth aspect.

[0058] The fifth aspect provides a parameter calibration apparatus, which includes: a memory for storing a program; and a processor for executing the program stored in the memory, and when the program stored in the memory is executed, the processor is configured to perform the method in any implementation of the first aspect.

[0059] Optionally, the apparatus can further include a communication interface.

[0060] In a sixth aspect, a parameter calibration apparatus is provided, the apparatus comprising: a memory configured to store a program; and a processor configured to execute the program stored in the memory, wherein the processor is configured to perform the method in any one of the implementation manners of the second aspect when the program stored in the memory is executed.

[0061] Optionally, the apparatus further comprises a communication interface.

[0062] In a seventh aspect, a computer readable medium is provided, the computer readable medium storing instructions for execution by an apparatus, the instructions configured to perform the method in any one of the implementation manners of the first aspect or the second aspect.

[0063] In an eighth aspect, a computer program product is provided, the computer program product comprising instructions configured to cause a computer to perform the method in any one of the implementation manners of the first aspect or the second aspect when the computer program product is run on the computer.

[0064] In a ninth aspect, a chip is provided, the chip comprising a processor and a communication interface, the processor configured to read instructions stored in a memory through the communication interface, and perform the method in any one of the implementation manners of the first aspect or the second aspect.

[0065] Optionally, the chip further comprises a memory, the memory storing instructions, and the processor is configured to execute the instructions stored in the memory, and perform the method in any one of the implementation manners of the first aspect or the second aspect when the instructions are executed.

[0066] In a tenth aspect, an electronic device is provided, the electronic device comprising the parameter calibration apparatus in any one of the implementation manners of the third aspect or the fourth aspect. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0068] Figure 2 is a schematic diagram of a calibration system provided by an embodiment of the present application;

[0069] Figure 3 is a schematic diagram of another calibration system provided by an embodiment of the present application;

[0070] Figure 4 is a schematic flowchart of a parameter calibration method provided by an embodiment of the present application;

[0071] Figure 5 is a schematic flowchart of another parameter calibration method provided by an embodiment of the present application;

[0072] Figure 6 is a schematic diagram of a device for parameter calibration provided by an embodiment of the present application;

[0073] Figure 7 is a schematic diagram of another device for parameter calibration provided by an embodiment of the present application. DETAILED DESCRIPTION

[0074] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0075] The solutions of the embodiments of the present application can be applied to vehicle calibration, sensor calibration and other fields of parameter calibration.

[0076] Parameter calibration refers to determining a set of parameters applicable under various conditions, for example, under different hardware conditions or different environmental conditions. Alternatively, parameter calibration refers to the process of optimizing parameters under various conditions.

[0077] The two application scenarios of vehicle calibration and sensor calibration will be described below.

[0078] (1) Vehicle calibration

[0079] Vehicle calibration refers to the process of optimizing parameters in control software in order to obtain satisfactory vehicle performance, meet the requirements before vehicle delivery and achieve relevant national standards after the controller hardware, control software and related sensors and other devices are determined.

[0080] The electronic control unit (ECU) in the vehicle, also known as "driving computer", uses data collected by various sensors to perform operations to obtain control signals to control various actuators in the vehicle to perform corresponding actions. Exemplarily, the control range of the ECU can include cruise control, light control, airbag control, suspension control, exhaust control or brake control, etc. Each ECU can exchange data through a bus. The parameters in the control software in the embodiments of the present application can be parameters in the ECU.

[0081] The existing parameter calibration process usually performs calibration experiments in different working conditions in a serial manner. Specifically, in one calibration experiment, the calibration engineer sets the parameters, performs the calibration experiment, and adjusts the parameters according to the data collected in the experiment. The above calibration experiment process is repeated under the same working condition, and after the parameter calibration under the working condition is completed, the calibration is transferred to the next working condition for calibration. The calibration efficiency of this scheme is low, and the calibration period is long.

[0082] By using the solutions of the embodiments of the present application, the efficiency of parameter calibration in the vehicle can be improved, and the time cost of calibration can be reduced.

[0083] (2) Sensor calibration

[0084] Part of the parameters of the sensor need to be calibrated in different environments before leaving the factory, for example, the distortion calibration matrix of the camera, the sensitivity of the inertial measurement unit (IMU), the deflection angle of the mobile phone laser radar, etc.

[0085] Taking the camera on the mobile phone as an example, the parameter calibration needs to be performed in different light conditions, different temperatures, different humidity environments, etc. before leaving the factory, so as to obtain the camera parameters applicable in different environments.

[0086] By using the scheme of the embodiments of the present application, the efficiency of parameter calibration in the sensor can be improved, and the time cost of calibration can be reduced.

[0087] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application is shown.

[0088] As Figure 1 shown, three vehicles of the same model are respectively located in three test fields of location 1, location 2 and location 3 for parameter calibration. As Figure 1 shown, the working conditions of the vehicle located at location 1 include: sunny, temperature 25℃, asphalt pavement. The working conditions of the vehicle located at location 2 include: sunny, temperature 6℃, ceramic tile pavement. The working conditions of the vehicle located at location 3 include: snow, temperature -30℃, ice surface.

[0089] The three vehicles can simultaneously perform parameter calibration by using the method of the embodiments of the present application. For example, the three vehicles can respectively perform calibration tests, and upload relevant data such as test data or evaluation results of parameter combinations to the cloud. The cloud sends the adjusted parameter combinations of each device to each vehicle respectively, and repeats the above process until the adjusted parameter combinations can meet the test requirements under the three working conditions, and the parameter calibration is completed. For specific description, please refer to the method 400 or the method 500 in the following.

[0090] The embodiments of the present application provide a parameter calibration method, which realizes parameter calibration based on the evaluation results of the parameter combinations of multiple devices, so as to improve the parameter calibration efficiency and reduce the time cost of calibration.

[0091] In order to better describe the scheme of the embodiments of the present application, the following will be combined with Figure 2 The calibration system provided by the embodiments of the present application is described.

[0092] As Figure 2As shown, the calibration system 200 can be deployed at the cloud side and the device side. Exemplarily, the cloud device 210 can be implemented by one or more servers. The device side includes a plurality of devices. The plurality of devices (e.g., the device 220 and the device 230) can interact with the cloud device 210. The plurality of devices includes modules that need to be calibrated. Exemplarily, the plurality of devices can include a smartphone, a tablet, a smart camera, a vehicle, a media consumption device, or a wearable device, etc. The plurality of devices can interact with the cloud device 210 through a communication network of any communication mechanism / standard, which can be the Internet, the World Wide Web, an intranet, a virtual private network, a wide area network, a local area network, a private network using a proprietary communication protocol of one or more companies, an Ethernet, WiFi, and HTTP, and various combinations of the foregoing. Such communication can be by any device capable of transmitting data to and from other computers, such as modems and wireless interfaces.

[0093] It should be noted that all the functions of the cloud device 210 can also be implemented by the plurality of devices. For example, the device 220 performs the functions of the cloud device 210 to provide calibration services for itself or for the device 230. In this case, the calibration system 200 does not need to be deployed at the cloud side. In other words, the cloud device 210 is optional.

[0094] It should be noted that the plurality of devices (e.g., the device 220 and the device 230) can be the same type of devices, or can be different types of devices. For example, the plurality of devices can include a plurality of vehicles. For another example, the plurality of devices can include a plurality of vehicles and a plurality of test benches.

[0095] Figure 3 A schematic block diagram of a calibration system is shown. Figure 3 It can be considered that Figure 2 A specific implementation of the calibration system 200 is shown.

[0096] As Figure 3 As shown, the calibration system 200 includes a data processing module 211, a calibration module 212, a first storage module 213, and a first communication module 214 deployed at the cloud device 210. The calibration system also includes a second communication module, a second storage module, a control module, and an execution module deployed at the plurality of devices at the device side. For example, the calibration system 200 also includes the second communication module 221, the second storage module 222, the control module 223, and the execution module 224 deployed at the device 220, and the second communication module 231, the second storage module 232, the control module 233, and the execution module 234 deployed at the device 230.

[0097] It should be understood that the "first" and "second" in the "first communication module" and "second communication module" in the embodiments of the present application are only used to distinguish the communication module on the cloud side and the communication module on the device side, and do not have other limiting effects. Correspondingly, the "first" and "second" in the "first storage module" and "second storage module" are only used to distinguish the storage module on the cloud side and the storage module on the device side, and do not have other limiting effects.

[0098] The first communication module 214 is used to realize the communication connection between the cloud side and the device side. The communication connection can be wired connection or wireless connection.

[0099] Specifically, the first communication module 214 is used to receive at least one of the following: data of the device 220 and the device 230, or evaluation results of the parameter combinations of the device 220 and the device 230.

[0100] Exemplarily, the data of the device includes data collected by the device based on the current parameter combination in the calibration test.

[0101] The current parameter combinations of the respective devices can be the same or different. The action sequences performed in the calibration test of the respective devices can be the same or different.

[0102] Optionally, the first communication module 214 can also be used to receive the working conditions in which the device 220 and the device 230 are located.

[0103] The data processing module 211 is used to process the data received by the first communication module 214.

[0104] Exemplarily, the data received by the first communication module 214 includes the data of the device 220 and the device 230. The data processing module 211 can be used to process the data of the device 220 and the device 230, and extract valid data, which is the data processed by the data processing module 211, that is, the "test data" in the following.

[0105] It should be noted that the data processing module 211 is an optional module. For example, if the data of the device only includes valid data, that is, if there is no need to process the data, there is no need to set the data processing module 211. For another example, if the data received by the first communication module 214 is the evaluation results of the parameter combinations of the device 220 and the device 230, there is no need to set the data processing module 211. For another example, the data processing module 211 can be executed by the calibration module 212 to process the data, and there is no need to additionally set the data processing module 211.

[0106] The calibration module 212 is used to obtain at least one parameter combination according to the evaluation results of the parameter combinations of the plurality of devices (for example, the device 220 and the device 230).

[0107] Optionally, the calibration module 212 can also be configured to evaluate the test data of the plurality of devices to obtain an evaluation result.

[0108] Optionally, the calibration module 212 can also be configured to determine the action sequence to be performed by at least one device of the plurality of devices.

[0109] Optionally, the calibration module 212 can also be configured to determine the at least one device.

[0110] The calibration module 212 can be specifically described with reference to steps S420 and S430 in the method 400, which will not be repeated here.

[0111] The first storage module 213 can be configured to store at least one of the following: test data of the devices 220 and 230, evaluation results of the parameter combinations of the devices 220 and 230, working conditions in which the devices 220 and 230 are located, or an action sequence set.

[0112] It should be understood that Figure 3 The first storage module is only taken as an example of one storage module in the first storage module 213, and in actual applications, the first storage module can include a plurality of storage modules. For example, the first storage module can include a working condition module configured to store working conditions in which a plurality of devices are located, for example, working conditions in which the devices 220 and 230 are located. For another example, the first storage module can include a calibration data module configured to store test data of a plurality of devices, for example, test data of the devices 220 and 230.

[0113] Optionally, the first communication module 214 can also be configured to send the adjusted parameter combinations of the at least one device to the at least one device respectively.

[0114] Optionally, the first communication module 214 can also be configured to send the action sequence to be performed by the at least one device to the at least one device respectively.

[0115] The modules included in the device 220 will be described below taking the device 220 as an example. The modules in the device 230 can perform the same functions as the modules in the device 220.

[0116] The second communication module 221 can be configured to cooperate with the first communication module 214 on the cloud side to realize the communication connection between the device 220 and the cloud device 210.

[0117] Specifically, the second communication module 221 can be configured to receive the adjusted parameter combinations of the device 220. The second communication module 221 can also be configured to send data of the device 220 or evaluation results of parameter combinations of the device 220 to the first communication module 214.

[0118] Optionally, the second communication module 221 can also be configured to send the working condition of the device 220 to the first communication module 214.

[0119] Optionally, the second communication module 221 can also be configured to receive the action sequence to be performed by the device 220.

[0120] The parameter combination of the device 220 received by the device 220 can be written into the control module 223. The control module 223 is configured to control the execution module 224 to perform the action sequence to be performed. The parameter in the control module 223 is the parameter that needs to be calibrated. Figure 3 In the examples, the calibration system can also not include the control module 223.

[0121] For example, the device 220 can be a vehicle. In this case, the control module 223 can be a vehicle-mounted ECU.

[0122] The execution module 224 is configured to perform the action sequence to be performed. The specific execution process can be in the form of automatic driving, or can also be performed by the driver.

[0123] Figure 3 In the examples, the calibration system can also not include the execution module 224.

[0124] The second storage module 222 is configured to store at least one of the following: the working condition of the device 220, the parameter combination of the device 220, and the action sequence to be performed by the device 220.

[0125] It should be understood that, Figure 3 In the examples, each device can include multiple storage modules. For example, the second storage module can include a working condition module, a parameter module, and an action module. The working condition module is configured to send the working condition of the device 220 to the cloud through the second communication module 221. The parameter module is configured to store the parameter combination of the device 220 and write the parameter into the control module 223. The action module is configured to store the action sequence to be performed by the device 220 and send the action sequence to be performed to the execution module 224.

[0126] It should be understood that, Figure 3 In the examples, the terminal device includes two vehicles, which does not limit the scheme of the embodiments of the present application. For example, the terminal device can also include more vehicles. For another example, Figure 3 The terminal device in the examples can also include other types of devices.

[0127] Figure 4 A schematic flowchart of a parameter calibration method according to an embodiment of the present application is shown. Figure 4The method 400 shown can also be performed by a parameter calibration device, which can be a cloud service device or a terminal device, such as a vehicle, a mobile phone, a test bench, etc., or a system composed of a cloud service device and a terminal device. Alternatively, the parameter calibration device can be deployed on a cloud service device or a terminal device, or a system composed of a cloud service device and a terminal device. The cloud service device can also be referred to as a cloud.

[0128] Exemplarily, the method 400 can be performed by Figure 3 the calibration system shown.

[0129] Figure 4 The method 400 shown includes steps S410 to S440.

[0130] S410, obtaining evaluation results of parameter combinations of a plurality of devices, the evaluation results of the parameter combinations of the plurality of devices being obtained by the plurality of devices respectively based on the parameter combinations of the plurality of devices to perform calibration tests in a first time period. The first time period is less than or equal to a first threshold.

[0131] For example, the first threshold can be 24 hours.

[0132] The first time period can be any time period as long as the time interval of the time period is less than or equal to the first threshold. The plurality of devices performing calibration tests in the first time period can also be understood as the plurality of devices can perform calibration tests in the same time period, for example, the plurality of devices can perform calibration tests at the same time.

[0133] The plurality of devices are devices that need to be calibrated. The parameters in the parameter combinations are the parameters that need to be calibrated. The parameter combinations include at least one parameter.

[0134] Specifically, in vehicle calibration, the parameters in the parameter combinations refer to part or all of the control parameters in the ECU.

[0135] For example, in transmitter calibration, the parameters in the parameter combinations include control parameters in the ECU related to the working state of the transmitter. For example, the parameter combinations can include spark advance angle, etc.

[0136] In the process of the plurality of devices respectively based on the parameter combinations of the plurality of devices to perform calibration tests, the plurality of devices respectively based on the parameter combinations of the plurality of devices perform action sequences of the plurality of devices.

[0137] The execution device of step S410 can be deployed in the plurality of devices, or can also be deployed on other devices other than the plurality of devices, for example, can be deployed on the cloud.

[0138] Optionally, the plurality of devices can be a plurality of vehicles.

[0139] For example, the plurality of devices are m devices, which can be m vehicles, m being an integer greater than 1.

[0140] In this case, the method 400 can be applied to a whole vehicle calibration scenario.

[0141] For example, the method 400 can be used to implement parameter calibration in an antilock brake system (ABS) scenario, a vehicle steering system scenario, or an electronic stability controller (ESC) system scenario in whole vehicle calibration.

[0142] Optionally, the plurality of devices can include a plurality of test benches.

[0143] For example, the plurality of devices are m devices, which can be m test benches, m being an integer greater than 1.

[0144] Optionally, the plurality of devices can include a vehicle and a test bench.

[0145] For example, the plurality of devices are m devices, which can include n vehicles and m-n test benches. m is an integer greater than 1, and n is a positive integer less than m.

[0146] In the case where the plurality of devices include test benches, the method 400 can be applied to a scenario of engine calibration or electric motor calibration in an electric vehicle.

[0147] Optionally, the plurality of devices can include a plurality of sensors. In this case, the method 400 can be applied to a sensor calibration scenario.

[0148] For example, a camera on a mobile phone needs to be calibrated in different environments, such as different light conditions, different temperatures, or different humidity, before leaving the factory. The method 400 can be used to implement parameter calibration of the camera on the mobile phone.

[0149] The parameter combinations of the plurality of devices can be the same or different.

[0150] In the embodiments of the present application, different parameter combinations refer to different values of at least one parameter in the parameter combination, rather than different parameter items in the parameter combination.

[0151] In order to improve the parameter calibration efficiency, the parameter items in the parameter combinations of the plurality of devices can be the same. For example, the plurality of devices simultaneously perform parameter calibration in an ABS scenario, and the parameter combinations of the plurality of devices all include a parameter item related to the ABS function, so that the parameter calibration efficiency in the ABS scenario can be improved.

[0152] For example, the parameter values in the parameter combination of each device can be determined randomly in a parameter space. The parameter space can also be understood as the value range of the parameter. Alternatively, the parameter values in the parameter combination of each device can be determined according to the parameter values of similar vehicle models. Alternatively, the parameter values in the parameter combination of each device can be set artificially. Alternatively, the initial parameter combination of each device can be determined according to the working conditions in which each device is located. The parameter combinations of the plurality of devices can be determined in the same way or in different ways. The embodiments of the present application do not limit the determination manner of the parameter values in the parameter combination of each device.

[0153] The action sequences of the plurality of devices can be the same or different.

[0154] The action sequences performed by the plurality of devices in the process of the calibration test can be different, which can also be understood as different calibration tests.

[0155] The following takes the scene of whole vehicle calibration as an example to explain the action sequence.

[0156] For example, when performing parameter calibration in the ABS scene, the vehicle performs the following action sequence in the process of calibration test: the vehicle drives to the starting position, accelerates to the target speed, maintains uniform speed driving, steps on the brake pedal to the bottom until the vehicle stops, and the vehicle drives out of the test area.

[0157] Among them, two action sequences including different target speeds can be regarded as different action sequences. In other words, two devices accelerate to different target speeds in the process of calibration test, which can be regarded as performing different action sequences.

[0158] For example, the action sequences of the plurality of devices can be determined randomly in the action sequence set. Alternatively, the action sequences of the plurality of devices can be determined according to at least one of the following: the action covered by the parameter calibration requirement, the working condition in which the at least one device is located, or the evaluation result of the parameter combination of the plurality of devices. Alternatively, the action sequences of the plurality of devices can also be set artificially. The action sequences of the plurality of devices can be determined in the same way or in different ways. The embodiments of the present application do not limit this.

[0159] Optionally, the plurality of devices satisfy at least one of the following: the working conditions in which the plurality of devices are located are different, the action sequences performed by the plurality of devices in the process of calibration test are different, or the parameter combinations of the plurality of devices are different.

[0160] Any two devices in the plurality of devices are in different working conditions, that is, the plurality of devices are considered to be in different working conditions.

[0161] Exemplarily, the method 400 is applied to a vehicle calibration scenario, and the working conditions can include at least one of the following: road conditions, temperature, humidity, weather, and the like.

[0162] The parameter combinations of any two of the plurality of devices are different, that is, the parameter combinations of the plurality of devices are different.

[0163] The action sequences performed by any two of the plurality of devices in the process of performing the calibration test are different, that is, the action sequences performed by the plurality of devices are different.

[0164] The working conditions, parameter combinations, and action sequences of the plurality of devices can be combined as needed.

[0165] Exemplarily, the devices in different working conditions perform the same action sequence based on the same parameter combination.

[0166] For example, one parameter in the parameter combination has a value range of (0, 1), and the plurality of devices in different working conditions perform the same action sequence when the parameter is 0.1.

[0167] Exemplarily, the plurality of devices in the same working condition perform the same action sequence based on different parameter combinations.

[0168] For example, one parameter in the parameter combination has a value range of (0, 1), and the plurality of devices in the same working condition perform the same action sequence when the parameter is in different values in the range of (0, 1).

[0169] Exemplarily, the devices in different working conditions perform different action sequences based on different parameter combinations.

[0170] In the embodiments of the present application, the plurality of devices are controlled to perform calibration tests in different working conditions, or the plurality of devices are controlled to perform calibration tests based on different parameter combinations, or the plurality of devices are controlled to perform different action sequences, which can improve the efficiency of the calibration test, faster obtain the evaluation results of the parameter combinations under various conditions, or in other words, collect more evaluation results of the parameter combinations under various conditions, so as to complete parameter calibration as soon as possible, which is beneficial to improve the efficiency of parameter calibration.

[0171] Optionally, the parameter combinations of the plurality of devices are the same, and the working conditions of the plurality of devices are different.

[0172] In this way, it is beneficial to summarize the evaluation results of the same parameter combination under different working conditions.

[0173] The evaluation results of the parameter combinations of the plurality of devices are used to indicate the quality of the parameter combinations of the plurality of devices. The evaluation results of the parameter combinations can also be understood as the value of the parameter combinations.

[0174] The evaluation of the parameter combination can also be understood as an evaluation of the performance of the device in the process of the calibration test based on the parameter combination.

[0175] Specifically, the performance of the device can be evaluated based on one or more evaluation indexes, to obtain an evaluation result of the parameter combination.

[0176] Illustratively, the performance of the device can be scored based on each evaluation index, to obtain a score corresponding to each index, which can be taken as the evaluation result of the parameter combination. Alternatively, the scores corresponding to each index are processed, and a comprehensive score obtained after processing is taken as the evaluation result of the parameter combination.

[0177] Optionally, the evaluation results of the parameter combinations of the plurality of devices can be obtained by evaluating test data of the plurality of devices. The test data of the plurality of devices is determined according to data collected in the process of the calibration test of the plurality of devices based on the parameter combinations of the plurality of devices, respectively.

[0178] Illustratively, the test data of the plurality of devices can be obtained by processing data collected by sensors in the process of the calibration test of the plurality of devices based on the parameter combinations of the plurality of devices, respectively.

[0179] For example, the processing of the data collected by the sensors can include filtering, frequency reduction, noise reduction, and the like.

[0180] Hereinafter, data filtering is taken as an example for illustration.

[0181] The data collected by the sensors can include valid data and invalid data. In other words, in the process of the calibration test, the sensors collect both valid data and invalid data. The valid data refers to data related to parameter calibration, or in other words, data that can be used to evaluate the parameter combination. The invalid data refers to data unrelated to parameter calibration, or in other words, data that cannot be used to evaluate the parameter combination.

[0182] In this case, the data collected by the sensors is filtered to extract valid data, and the valid data is taken as the test data.

[0183] For example, when calibrating the parameters of the ABS scenario, the vehicle sequentially performs the following actions in the process of the calibration test: the vehicle drives to the starting position, accelerates to the target speed, maintains a constant speed for a period of time, steps on the brake pedal to the bottom until the vehicle stops, and the vehicle drives out of the test area. Data is collected in the process of the vehicle performing all the above actions. The effective data is the data collected in the process of stepping on the brake pedal to the bottom until the vehicle stops. In this case, the collected data can be processed to extract the effective data, and the effective data is taken as the test data.

[0184] In an implementation manner, the process of processing the data collected by the sensors can be performed by the execution device of step S410, that is, the execution device of step S410 can receive the data collected by the sensors of the plurality of devices uploaded by the plurality of devices, and process the data collected by the sensors to obtain the test data.

[0185] In another implementation manner, the process of processing the data collected by the sensors can also be performed by the plurality of devices respectively. The plurality of devices sends the test data obtained after processing to the execution device of step S410.

[0186] Alternatively, the test data of the plurality of devices can be the data collected by the sensors in the process of calibrating the test based on the parameter combination of the plurality of devices respectively.

[0187] If the data collected by the sensors only includes effective data, in other words, only effective data is collected in the process of the calibration test, the collected data can also be taken as the test data.

[0188] For example, when calibrating the parameters of the ABS scenario, the vehicle sequentially performs the following actions in the process of the calibration test: the vehicle drives to the starting position, accelerates to the target speed, maintains a constant speed for a period of time, steps on the brake pedal to the bottom until the vehicle stops, and the vehicle drives out of the test area. Data is collected in the process of the vehicle performing all the above actions. The effective data is the data collected in the process of stepping on the brake pedal to the bottom until the vehicle stops. In this case, the collected data is effective data, and the effective data is taken as the test data.

[0189] Only effective data is collected in the process of the calibration test, which can reduce the operation of processing the collected data and improve the data processing efficiency, that is, improve the efficiency of parameter calibration.

[0190] As described above, the evaluation result of the parameter combination of the plurality of devices can be obtained by evaluating the test data of the plurality of devices.

[0191] In this case, the evaluation result of the parameter combination can also be understood as the value of the test data.

[0192] Specifically, the test data can be evaluated based on one or more evaluation indexes to obtain an evaluation result of the parameter combination.

[0193] For example, the test data can be processed by a cost function or a value function, and a cost value or a value value obtained can be used as the evaluation result of the parameter combination.

[0194] The parameter calibration in the ABS scenario is taken as an example below.

[0195] The evaluation indexes of the ABS include the wheel lock time and the vehicle yaw angle.

[0196] The test data is obtained based on the current parameter combination of the ABS, and the wheel lock time and the vehicle yaw angle can be determined from the test data. During braking, if the wheel lock time in the test data is longer and the vehicle yaw angle is larger, the braking performance of the current braking system is poorer, that is, the value of the test data is lower, or the current parameter combination is poorer.

[0197] For example, the wheel lock time and the vehicle yaw angle in the test data can be evaluated by a cost function respectively to obtain scores corresponding to the two indexes, and the scores corresponding to the two indexes can be used as the evaluation result of the current parameter combination. Alternatively, the wheel lock time and the vehicle yaw angle in the test data can be evaluated by a cost function to obtain a comprehensive score, and the comprehensive score can be used as the evaluation result of the current parameter combination.

[0198] Further, the evaluation results of the parameter combinations of the plurality of devices are obtained by evaluating the test data of the plurality of devices according to the working conditions of the plurality of devices.

[0199] For the same evaluation index, even if the test data in different working conditions is the same, the evaluation results of the parameter combinations corresponding to the test data in different working conditions can be different.

[0200] The parameter calibration in the ABS scenario is taken as an example below.

[0201] In the ABS scenario, the test data of the vehicle includes the braking distance. The braking distance refers to the braking distance obtained in the state of stepping on the brake to the bottom. The braking distance under the condition of the same initial speed when taking emergency braking is evaluated according to the road adhesion coefficient. Specifically, in the case of the same braking distance, the evaluation result of the parameter combination in the working condition of the smaller road adhesion coefficient is better.

[0202] As described above, when calibrating parameters in the ABS scenario, the vehicle performs the following action sequence in the process of calibration test: the vehicle drives to the starting position, accelerates to the target speed, keeps uniform speed, steps on the brake pedal to the bottom until the vehicle stops, and the vehicle drives out of the test area.

[0203] The step of stepping on the brake pedal to the bottom until the vehicle stops is emergency braking, and the initial speed when the emergency braking is taken is the target speed in the above action sequence.

[0204] For example, the vehicle performs the same calibration test based on different parameter combinations in two different working conditions, i.e., on the gravel road and on the asphalt road. Specifically, the vehicle in the working condition of the gravel road performs the above action sequence based on the parameter combination 1, and the braking distance collected by the sensor is a; the vehicle in the working condition of the asphalt road performs the above action sequence based on the parameter combination 2, and the braking distance collected by the sensor is b. The road adhesion coefficient of the gravel road is less than that of the asphalt road, and in the case of a and b being equal, the evaluation score of the parameter combination 1 in the vehicle on the gravel road is higher than that of the parameter combination 2 in the vehicle on the asphalt road. It should be noted that the same test data obtained in different working conditions is caused by different parameter combinations. That is, the same calibration test is performed based on different parameter combinations in different working conditions, and even if the test data is the same, the evaluation scores of different parameter combinations can still be different.

[0205] In the embodiments of the present application, the test data of the device is evaluated based on the working condition of the device, which can improve the accuracy of the evaluation result and further improve the effect of parameter calibration.

[0206] Further, the evaluation results of the parameter combinations of the plurality of devices can be obtained by evaluating the test data of the plurality of devices according to the configuration information of the plurality of vehicles.

[0207] For the same evaluation index, even if the test data obtained under different configurations is the same, the evaluation results of the parameter combinations corresponding to the test data under different configurations can be different.

[0208] The following takes the parameter calibration in the ABS scenario as an example for description.

[0209] In the ABS scenario, the test data of the vehicle includes the braking distance. The configuration information of the vehicle can include the load weight of the vehicle. The braking distance in the case of the same initial speed when emergency braking is taken is evaluated according to the load weight of the vehicle. Specifically, in the case of the same braking distance, the evaluation result of the parameter combination in the case of the larger load weight of the vehicle is better.

[0210] For example, the load weight of the vehicle is 70 kg, and the braking distance c is collected during the calibration test based on the parameter combination 3; the load weight of the vehicle is 150 kg, and the braking distance d is collected during the calibration test based on the parameter combination 4. In the case that c and d are equal, the evaluation score of the parameter combination 3 is less than the evaluation score of the parameter combination 4. Specifically, the braking distance can be multiplied by the coefficient corresponding to the braking distance, and then the evaluation is performed. The coefficient corresponding to the braking distance can be artificially set. The coefficient corresponding to the braking distance is negatively correlated with the load weight of the vehicle. For example, the load weight of the vehicle is 70 kg, and the coefficient corresponding to the braking distance is 1. During the calibration test based on the parameter combination 3, the braking distance c is collected, c is multiplied by 1, and then the evaluation score of the parameter combination 3 is obtained based on the processed braking distance; the load weight of the vehicle is 150 kg, and the coefficient corresponding to the braking distance is 0.95. During the calibration test based on the parameter combination 4, the braking distance d is collected, d is multiplied by 0.95, and then the evaluation result of the parameter combination 4 is obtained based on the processed braking distance.

[0211] In the embodiments of the present application, the test data of the device is evaluated based on the configuration information of the device, which can improve the accuracy of the evaluation result and further improve the effect of parameter calibration.

[0212] It should be understood that the above-mentioned evaluation method of the parameter combination is only an example, and the test data of the device can also be evaluated according to other methods, which is not limited in the embodiments of the present application.

[0213] Optionally, the evaluation result of the parameter combination of the plurality of devices can be obtained by user feedback.

[0214] In some application scenarios, the subjective feeling feedback of the user is required when performing parameter calibration. In other words, the user needs to evaluate the use experience during the calibration test to obtain the evaluation result of the parameter combination.

[0215] For example, the method 400 can be applied to the scene of whole vehicle calibration. During the calibration test of the vehicle based on the current parameter combination, the user can score the driving experience, and the score of the user can be used as the evaluation result of the current parameter combination.

[0216] For example, when performing parameter calibration of the vehicle steering system, the evaluation index includes the steering wheel assist effect. During the calibration test, the steering wheel assist effect can be scored by the user.

[0217] For example, the evaluation result of the user feedback can be written into the device through the human-computer interaction interface.

[0218] In this way, the feelings of the user can be fully considered, which is beneficial to improve the user experience.

[0219] Optionally, a first part of the evaluation results of the parameter combinations of the plurality of devices is obtained from the user feedback, and a second part of the evaluation results of the parameter combinations of the plurality of devices is obtained by evaluating the test data of the plurality of devices.

[0220] As described above, the performance of the devices can be evaluated based on the plurality of evaluation indexes to obtain the evaluation results of the parameter combinations.

[0221] Exemplarily, the evaluation results can be in the form of scores corresponding to the evaluation indexes, in other words, the evaluation results of a parameter combination can include a plurality of scores. Part of the plurality of scores (an example of the second part of the evaluation results) can be obtained by evaluating the test data of the plurality of devices, and the rest of the plurality of scores (an example of the first part of the evaluation results) can be obtained from the user feedback.

[0222] It should be understood that the above evaluation method of the parameter combinations is only an example, and other evaluation methods of the parameter combinations can also be used, which are not limited in the embodiments of the present application. For example, the results of the user feedback and the results obtained by evaluating the test data of the plurality of devices can be processed to obtain the evaluation results of the parameter combinations.

[0223] In an implementation manner, the execution device of step S410 can be deployed on other devices than the plurality of devices, for example, Figure 2 the cloud shown.

[0224] Step S410 can be implemented in various ways, and the specific implementation manner of step S410 is exemplarily described below by taking the cloud as an example.

[0225] Exemplarily, the cloud can receive the evaluation results of the parameter combinations of the plurality of devices.

[0226] For example, the cloud can receive the evaluation results of the parameter combinations of the plurality of devices obtained from the user feedback.

[0227] The plurality of devices can respectively send the evaluation results of the parameter combinations of the plurality of devices to the cloud. The plurality of devices include the first device, that is, the first device can send the evaluation results of the parameter combinations of the first device to the cloud.

[0228] Alternatively, the cloud can receive the test data of the plurality of devices, and evaluate the test data of the plurality of devices to obtain the evaluation results of the parameter combinations of the plurality of devices.

[0229] The plurality of devices can respectively send the test data of the plurality of devices to the cloud. The plurality of devices include the first device, that is, the first device can send the test data of the first device to the cloud.

[0230] Alternatively, the cloud can receive the evaluation result of the parameter combination of part of the plurality of devices and the test data of the rest of the devices, and evaluate the test data of the rest of the devices to obtain the evaluation result of the parameter combination of the rest of the devices.

[0231] Part of the plurality of devices sends the evaluation result of the respective parameter combination to the cloud, and the rest of the devices sends the respective test data to the cloud.

[0232] For example, the plurality of devices includes a first device and a second device. The second device sends the evaluation result of the parameter combination of the second device to the cloud. The first device sends the test data of the first device to the cloud. Alternatively, the first device sends the evaluation result of the parameter combination of the first device to the cloud. The second device sends the test data of the second device to the cloud.

[0233] Alternatively, the cloud can receive the first part of the evaluation result of the parameter combination of the plurality of devices and the test data of the plurality of devices, and evaluate the test data of the plurality of devices to obtain the second part of the evaluation result of the parameter combination of the plurality of devices.

[0234] The plurality of devices can respectively send the first part of the evaluation result of the parameter combination of the plurality of devices and the test data of the plurality of devices to the cloud.

[0235] For example, the plurality of devices includes a first device. The first device can send the first part of the evaluation result of the parameter combination of the first device and the test data of the first device to the cloud.

[0236] The cloud can receive various data in a wired or wireless manner through a communication module in the cloud, which is not limited in the embodiments of the present application.

[0237] In another implementation manner, the execution device of step S410 can be deployed in any device of the plurality of devices.

[0238] The execution device of step S410 can obtain the evaluation result of the local parameter combination in various ways.

[0239] For example, the execution device of step S410 can read the evaluation result of the local parameter combination. For example, the execution device of step S410 can read or receive the evaluation result of the local parameter combination from a storage module. For the convenience of description, the "receiving" or "reading" of the local data in the embodiments of the present application is collectively referred to as "reading".

[0240] Alternatively, the execution device of step S410 can also read the local test data and evaluate the local test data to obtain the local evaluation result of the parameter combination.

[0241] Alternatively, the execution device of step S410 can also read the first part of the evaluation result of the local parameter combination and the local test data, and evaluate the local test data to obtain the second part of the evaluation result of the local parameter combination. The first part can be obtained by user feedback.

[0242] The specific manner in which the execution device of step S410 obtains the evaluation result of the parameter combination of the other devices in the plurality of devices except the local device can refer to the foregoing manner of obtaining by the cloud, and details are not described herein again to avoid repetition.

[0243] It should be noted that the evaluation result of the parameter combination of the plurality of devices can be obtained at a single time, or can also be obtained at multiple times.

[0244] Optionally, the method 400 includes step S411 Figure 4 (not shown in the method 400).

[0245] S411, obtaining the working conditions in which the plurality of devices are located.

[0246] Exemplarily, the working conditions in which the plurality of devices are located can be collected by sensors in the plurality of devices, or can also be artificially set.

[0247] The specific obtaining manner can refer to step S410, and the "evaluation result of the parameter combination of the plurality of devices" in step S410 is replaced by "working conditions in which the plurality of devices are located", and details are not described herein again.

[0248] Optionally, the method 400 further includes step S412 Figure 4 (not shown in the method 400).

[0249] S412, obtaining configuration information of the plurality of devices.

[0250] Exemplarily, in the ABS scenario, the configuration information includes at least one of the following: tire characteristic parameters, a load weight of the vehicle, or a distribution of the load weight of the vehicle.

[0251] For example, the tire characteristic parameters can include at least one of the following: wear degree, section width, or flat ratio, etc.

[0252] For example, in the case where only the driver is on the vehicle, the load weight of the vehicle and the distribution of the load weight of the vehicle can be represented as [70 kg of body weight, distributed on the left front side of the car]; in the case where the driver and the co-driver are on the vehicle, the load weight of the vehicle and the distribution of the load weight of the vehicle can be represented as [150 kg of body weight, distributed on the front side of the car].

[0253] The specific acquisition manner can refer to step S410. The evaluation result of the parameter combination of the plurality of devices in step S410 is replaced by the configuration information of the plurality of devices. Details are not described herein again.

[0254] S420, obtaining at least one adjusted parameter combination according to the evaluation result of the parameter combination of the plurality of devices.

[0255] The at least one adjusted parameter combination can be the same or different.

[0256] Step S420 can be understood as optimizing the current parameter combination according to the evaluation result of the parameter combination of the plurality of devices. The specific optimization manner is implemented by using an existing optimization algorithm.

[0257] Exemplarily, step S420 can be implemented by using a Bayesian optimization algorithm.

[0258] Specifically, a Gaussian process is fitted based on the Bayesian principle according to the evaluation result of the parameter combination of the plurality of devices, and then the mean and variance of the evaluation result of each value point in the parameter distribution space are obtained. One value point is one parameter combination. The score of each value point is calculated, and the value point with the highest score is taken as the adjusted parameter combination. For example, the upper confidence bound (UCB) algorithm can be used to calculate the score of each value point. Specifically, the mean and variance of the evaluation result of each value point are brought into the UCB formula to calculate the score of each value point, and the at least one value point with the highest score is taken as the at least one adjusted parameter combination.

[0259] Exemplarily, step S420 can be implemented by using a genetic algorithm.

[0260] For example, the plurality of devices include m devices. The parameter combinations corresponding to the best p evaluation results in the evaluation result of the parameter combination of the m devices are subjected to operations such as crossover or mutation to obtain the at least one adjusted parameter combination. P is an integer less than m and greater than 1.

[0261] It should be understood that other optimization manners can also be used to obtain the adjusted parameter combination. The specific implementation manner of the optimization process is not limited in the embodiments of the present application.

[0262] Optionally, the parameter combinations of the plurality of devices are the same, and the working conditions of the plurality of devices are different. In this case, step S420 can be implemented by the following steps:

[0263] (1) Processing the evaluation result of the parameter combination of the plurality of devices to obtain a summary evaluation result.

[0264] The aggregated evaluation result can be determined in various manners. For example, a weighted average of the evaluation results of the parameter combinations of the plurality of devices is taken as the aggregated evaluation result. For another example, the minimum value among the evaluation results of the parameter combinations of the plurality of devices is taken as the aggregated evaluation result. For another example, the maximum value among the evaluation results of the parameter combinations of the plurality of devices is taken as the aggregated evaluation result. The embodiments of the present application do not limit the manner of determining the aggregated evaluation result.

[0265] (2) Obtain at least one adjusted parameter combination according to the aggregated evaluation result.

[0266] Step (2) can be understood as optimizing the current parameter combination according to the aggregated evaluation result. The specific optimization manner can refer to the description in the foregoing text, for example, when the Bayesian optimization algorithm is used, the "evaluation result of the parameter combination of the plurality of devices" in the optimization method in the foregoing text is replaced by the "aggregated evaluation result".

[0267] Since the parameter combinations of the devices are the same, the evaluation results under various working conditions can be aggregated to obtain the aggregated evaluation result of the parameter combination, and the current parameter combination is optimized according to the aggregated evaluation result, which is beneficial to obtaining a better parameter combination and further improving the calibration efficiency.

[0268] According to the scheme of the embodiments of the present application, the plurality of devices perform calibration tests in the same period, which can improve the efficiency of data acquisition, and is beneficial to adjusting the parameters of the devices in real time based on the evaluation results of the parameter combinations of the plurality of devices, thereby improving the calibration efficiency, reducing the calibration period, and reducing the calibration cost. For example, different devices can perform different action sequences, quickly cover the action sequences to be completed, and improve the efficiency of data acquisition. For another example, different devices can perform calibration tests based on different parameter combinations, quickly cover the parameter space, and improve the efficiency of data acquisition. For another example, different devices can be in different working conditions, quickly cover the working conditions required for calibration, and improve the efficiency of data acquisition.

[0269] The existing vehicle calibration process needs to be completed in different working conditions, parameters, and the like in a serial manner. After calibration is completed at one test site, the vehicle needs to be transported to another test site for parameter calibration. The plurality of devices of the scheme of the embodiments of the present application can simultaneously perform calibration tests in different working conditions, which improves the calibration efficiency and reduces the time cost and economic cost.

[0270] The existing calibration scheme usually needs to complete calibration in one working condition and then perform calibration in another working condition, and needs to return to the previous working condition for verification and adjustment after calibration. The scheme of the embodiment of the present application can simultaneously place multiple devices in different working conditions, can realize real-time collection of data of the multiple devices and parameter optimization, is beneficial to simultaneously finding a parameter combination compatible with multiple working conditions in the multiple working conditions, improves stability of the parameters, and further improves calibration efficiency.

[0271] In addition, subjective preferences of calibration engineers when performing calibration can affect accuracy of calibration results. In the scheme of the embodiment of the present application, parameter calibration is performed based on evaluation results of test data of multiple devices, reduces cognitive bias brought by different calibration engineers, improves calibration quality, and is beneficial to avoiding situations of recalling devices after the devices are shipped.

[0272] In addition, the scheme of the embodiment of the present application can also use an automatic optimization algorithm to complete calibration, reduces the number of calibration engineers, reduces labor costs, and further reduces influence of subjective preferences of the calibration engineers on calibration results.

[0273] The method 400 further includes step S430.

[0274] S430, send the at least one adjusted parameter combination to at least one device.

[0275] Optionally, the at least one device can be determined according to at least one of the following: a working condition in which the multiple devices are located or the at least one adjusted parameter combination.

[0276] For example, the at least one adjusted parameter combination is obtained by adjusting one or more parameter values in the current parameter combination, and the adjusted parameter item can be valid only for a working condition with a low adhesion coefficient and invalid for a working condition with a high adhesion coefficient. In this case, the at least one device can be a device in a working condition with a low adhesion coefficient.

[0277] For another example, the evaluation results of the parameter combinations of the multiple devices can be obtained multiple times. In this case, a device in the parameter combination of one or more devices obtained each time can be the at least one device. The at least one adjusted parameter combination can also be understood as an adjusted parameter combination of the at least one device. Step S420 can also be understood as adjusting the parameter combination of at least one device in the multiple devices according to the evaluation results of the parameter combinations of the multiple devices, to obtain an adjusted parameter combination of the at least one device. It should be noted that “adjusting the parameter combination of at least one device in the multiple devices” herein refers to adjusting the parameter combination of the at least one device stored in the execution device of step S410, and does not limit adjusting the parameter combination stored in the at least one device.

[0278] It should be understood that the above is only an example, and the at least one device can also be determined in other manners, which are not limited by the embodiments of the present application. For example, the at least one device can be determined randomly.

[0279] As described above, the at least one adjusted parameter combination can be the same or different.

[0280] For example, the at least one adjusted parameter combination can be the same, in which case the parameter combinations received by the at least one device are the same.

[0281] For another example, the at least one adjusted parameter combination can be one-to-one with the at least one device, in which case the parameter combinations received by the at least one device can be different.

[0282] The at least one device can continue to perform the calibration test based on the adjusted parameter combination. The method 400 can be repeatedly executed until the calibration is completed.

[0283] The at least one device includes a first device, and for the convenience of description, only the first device is taken as an example here, and other devices in the at least one device can perform the same actions as the first device.

[0284] One of the at least one adjusted parameter combination is sent to the first device. The first device acquires the adjusted parameter combination and performs a calibration test based on the adjusted parameter combination.

[0285] For the same device, the sequence of actions performed in each calibration test can be the same or different.

[0286] Taking the application of the method 400 to vehicle calibration as an example, the at least one device can write the adjusted parameter combination into the ECU in the at least one device, respectively, and then perform a calibration test based on the adjusted parameter combination.

[0287] It should be understood that step S430 is optional. When the execution device of step S410 is not deployed in the first device, the method 400 can also include step S430. When the execution device of step S410 is deployed in the first device, the execution device of step S410 can directly update the locally stored parameter combination to the adjusted parameter combination, without performing step S430.

[0288] Optionally, the method 400 further includes step S440.

[0289] S440, respectively sending the to-be-executed action sequence of the at least one device to the at least one device. The to-be-executed action sequence of the at least one device includes actions that the at least one device needs to perform in the process of performing the calibration test based on the adjusted parameter combination of the at least one device.

[0290] In other words, the content of the to-be-executed calibration test is sent to each device.

[0291] The to-be-executed action sequence of the at least one device can be the same or different.

[0292] The at least one device includes the first device. For ease of description, only the first device is taken as an example here. The other devices in the at least one device can perform the same actions as the first device.

[0293] The first device obtains the to-be-executed action sequence of the first device. The to-be-executed action sequence of the first device includes actions that the first device needs to perform in the process of performing the calibration test based on the adjusted parameter combination of the first device.

[0294] It should be understood that step S440 is optional. The to-be-executed action sequence of the at least one device can also be determined in the following manner.

[0295] For example, the to-be-executed action sequence of the at least one device can also be determined by the at least one device itself.

[0296] Alternatively, the to-be-executed action sequence of the at least one device can be pre-set.

[0297] Alternatively, the to-be-executed action sequence of the at least one device can be determined by a user.

[0298] For example, the first device can display one or more reference action sequences. The user can select the to-be-executed action sequence of the first device from the one or more reference action sequences. The one or more reference sequences can include action sequences in the first device that have not been completed. Alternatively, the one or more reference sequences can include all action sequences in the first device.

[0299] In this way, the user can be provided with a reference when selecting the to-be-executed action sequence, improving the user experience, avoiding the execution of repeated action sequences, and improving the calibration efficiency.

[0300] Optionally, the to-be-executed action sequence of the at least one device is determined from the action sequence set.

[0301] Part or all of the plurality of devices can share the action sequence set, that is, the action sequence set of part or all of the plurality of devices can be the same. Alternatively, the action sequence set of the plurality of devices can be different. Embodiments of the present application do not limit this.

[0302] Optionally, the action sequence to be executed by the at least one device is determined according to at least one of the following: an action covered by the parameter calibration requirement, a working condition in which the at least one device is located, or an evaluation result of a parameter combination of the plurality of devices.

[0303] Exemplarily, the action covered by the parameter calibration requirement can include an action covered by a national standard requirement.

[0304] Taking parameter calibration in an ABS scenario as an example, the action covered by the national standard requirement needs to cover low-speed, medium-speed and high-speed scenarios. That is, the target vehicle speed in the action sequence needs to include low-speed, medium-speed and high-speed. If the action sequence with the target vehicle speed of low-speed has been executed before, the action sequence to be executed can be the action sequence with the target vehicle speed of medium-speed or the action sequence with the target vehicle speed of high-speed.

[0305] Different working conditions have different requirements for the action sequence to be executed.

[0306] Taking parameter calibration in an ABS scenario as an example, on a road section with low adhesion coefficient, for example, on ice, slow acceleration is required, that is, the depth of the pedal of the accelerator pedal should not be too large. On a road section with high adhesion coefficient, for example, on asphalt road, fast acceleration is required, that is, the pedal of the accelerator pedal needs to be stepped to a large depth. For a device located on a road section with low adhesion coefficient, the depth of the pedal of the accelerator pedal used in the acceleration action in the action sequence to be executed is less than or equal to a first pedal threshold, for example, 30%; for a device located on a road section with high adhesion coefficient, the depth of the pedal of the accelerator pedal used in the acceleration action in the action sequence to be executed is greater than or equal to a second pedal threshold, for example, 90%.

[0307] If the evaluation result of the parameter combination obtained after performing the calibration test based on a parameter combination is poor, for example, the evaluation score is less than or equal to an evaluation threshold, after adjusting the parameter combination, the action sequence executed in the calibration test process can be used as the action sequence to be executed.

[0308] The specific execution mode of the action sequence to be executed can be set as needed.

[0309] Exemplarily, the method 400 can be applied to the scenario of whole vehicle calibration, and the at least one device, that is, the at least one vehicle, can execute the action sequence to be executed in an automatic driving manner to obtain test data.

[0310] Or, the driver on the at least one vehicle can control the at least one vehicle to perform the to-be-performed action sequence.

[0311] For example, the to-be-performed action sequence can be displayed on a display of the at least one vehicle, and the driver can control the vehicle to perform the corresponding to-be-performed action sequence.

[0312] If the at least one device includes two or more devices, the execution manners of the devices can be the same or different. For example, some vehicles can be automatically driven, and some vehicles can be driven by drivers.

[0313] After the at least one device performs the calibration test, test data of the at least one device or evaluation results of the parameter combinations of the at least one device can be obtained. Further, the method 400 can be repeatedly performed based on the test data of the at least one device, that is, the method 400 of the embodiment of the present application can be iteratively performed. For example, steps S410 to S420 are executed, or steps S410 to S430 are repeatedly executed, or steps S410 to S440 are repeatedly executed. The specific execution steps can be set as needed, and the embodiment of the present application does not limit this. For example, the evaluation results of the parameter combinations of the at least one device can be used as the evaluation results of the parameter combinations of the multiple devices in step S410, and then the method 400 is repeatedly executed. For another example, the evaluation results of the parameter combinations of the at least one device can be added to the evaluation results of the parameter combinations of the multiple devices in step S410, and then the method 400 is repeatedly executed. In this case, one device in step S410 can correspond to the evaluation results of the parameter combinations of the device obtained in multiple calibration tests, or the evaluation results of the parameter combinations of one device can include the evaluation results of the parameter combinations obtained in multiple calibration tests.

[0314] It should be noted that in the repeated execution of the method 400, the devices participating in the iteration each time, that is, the "at least one device" in the method 400, can be the whole set or a subset of the devices to be calibrated, that is, the whole set or a subset of the "multiple devices" in the method 400. In other words, the devices participating in the iteration each time can be the same or different, and the embodiment of the present application does not limit this.

[0315] Figure 5 A schematic flowchart of a parameter calibration method provided by an embodiment of the present application is shown. Figure 5 The method 500 in the above embodiment is described by taking vehicle calibration as an example, and does not limit the scheme of the embodiment of the present application. Figure 5 The method 500 in the above embodiment can be regarded as Figure 4A specific implementation of the method 400 shown can be described with reference to the method 400. In order to avoid unnecessary repetition, part of the repeated description is appropriately omitted when describing the method 500.

[0316] Exemplarily, the method 500 can be executed by Figure 3 the calibration system shown.

[0317] The method 500 includes steps S501 to S511. The steps in the method 500 can be executed once or multiple times, i.e., iteratively.

[0318] S501, the plurality of vehicles respectively upload working conditions in which the plurality of vehicles are located to the cloud.

[0319] The plurality of vehicles are vehicles to be calibrated. The vehicles to be calibrated can be vehicles of the same model. For example, Figure 5 As shown, the plurality of vehicles can include vehicle 1# and vehicle 2#. Vehicle 1# and vehicle 2# respectively upload working conditions in which each vehicle is located to the cloud.

[0320] It should be understood that Figure 5 only two vehicles are taken as examples in the foregoing description, and the number of vehicles to be calibrated in the embodiments of the present application is not limited.

[0321] Exemplarily, the working conditions in which the plurality of vehicles are located can be collected by sensors, or can also be set by humans.

[0322] Exemplarily, step S501 can be executed by Figure 3 the first communication module and the second communication module in the calibration system.

[0323] In other words, each vehicle uploads the working condition in which the vehicle is located to the first communication module of the cloud through the second communication module of the vehicle. The first communication module of the cloud can store the received working conditions of each vehicle to the first storage module. Specifically, the working conditions of each vehicle can be stored to the working condition module in the first storage module.

[0324] Exemplarily, the vehicle is in a moving state during the calibration test, and the first communication module and the second communication module can adopt a wireless communication mode for data transmission.

[0325] Further, step S501 can further include: the plurality of vehicles upload vehicle configuration information to the cloud.

[0326] Exemplarily, the vehicle configuration information can be collected by sensors, or can also be set by humans.

[0327] It should be noted that step S501 is an optional step.

[0328] S502, the cloud determines the initial parameter combination for the multiple vehicles.

[0329] The initial parameter combination of the multiple vehicles can be understood as an example of the parameter combination of the multiple devices in method 400.

[0330] The initial parameter combinations for these multiple vehicles can be the same or different.

[0331] For example, the initial parameter combination of the multiple vehicles can be determined separately according to the operating conditions of the multiple vehicles.

[0332] Alternatively, the initial parameter combination of the multiple vehicles can be randomly selected within a parameter space. The parameter space can be understood as the range of values ​​for each parameter.

[0333] Alternatively, the initial parameter combination of the multiple vehicles can be set based on historical parameters of similar vehicle models.

[0334] Alternatively, the initial parameter combination of the multiple vehicles can be determined manually.

[0335] It should be understood that the above method of determining the initial parameter combination is only an example. In practical applications, other methods can be used to initialize the parameter combination, and this application embodiment does not limit this.

[0336] For example, step S502 can be performed by Figure 3 The calibration module 212 in the middle is executed.

[0337] It should be noted that step S502 is an optional step. For example, the initial parameter combination of at least one of the multiple vehicles can also be preset in that at least one vehicle, without needing to be determined by the cloud.

[0338] If method 500 includes step S502, method 500 further includes step S503.

[0339] S503, the cloud sends the initial parameter combination of the multiple vehicles to the multiple vehicles respectively.

[0340] like Figure 5 As shown, the cloud sends the initial parameter combination X of vehicle 1 to vehicle 1, and the initial parameter combination Y of vehicle 2 to vehicle 2. The initial parameter combination X and the initial parameter combination Y can be the same or different.

[0341] For example, step S503 can be performed by Figure 3 The first and second communication modules in the process are executed.

[0342] In other words, the cloud sends the initial parameter combination of each vehicle to the second communication module of each vehicle through the first communication module. The second communication module of each vehicle can store the initial parameter combination into the second storage module of each vehicle. Specifically, the initial parameter combination is stored into the parameter module in the second storage module.

[0343] Further, the parameter module can write the initial parameter combination into the control module, for example, into the ECU.

[0344] Optionally, the method 500 comprises step S504a or step S504b.

[0345] S504a, the cloud determines the action sequence to be performed by the plurality of vehicles.

[0346] The action sequence to be performed by the plurality of vehicles can be the same or different.

[0347] Illustratively, the cloud can select the action sequence to be performed by the plurality of vehicles from the set of action sequences respectively.

[0348] Alternatively, the action sequence to be performed by the plurality of vehicles can be determined artificially.

[0349] Optionally, the cloud can determine the action sequence to be performed by the plurality of vehicles according to at least one of the following: the action coverage degree required by the national standard, the working condition or the evaluation result of the parameter combination of the plurality of vehicles.

[0350] The specific description can be referred to step S440 in method 400, which will not be repeated here.

[0351] Illustratively, step S504 can be performed by the calibration module 212 in Figure 3 .

[0352] S504b, the plurality of vehicles obtain the action sequence to be performed by the plurality of vehicles from user feedback.

[0353] As shown in Figure 5 , vehicle 1# obtains the action sequence to be performed by vehicle 1# from user feedback. Vehicle 2# obtains the action sequence to be performed by vehicle 2# from user feedback.

[0354] Illustratively, the vehicle can obtain the action sequence to be performed by the vehicle from user feedback through the human-computer interface.

[0355] Further, the vehicle can display one or more reference action sequences through the vehicle-mounted display. The one or more reference action sequences can be determined according to the set of action sequences and the completed action sequences.

[0356] It should be understood that the step S504a or the step S504b is only an example and does not limit the scheme of the embodiments of the present application. For example, the action sequence of at least one of the plurality of vehicles can also be selected by the at least one vehicle from the action sequence set. For another example, the user can also directly control the vehicle to perform the to-be-executed action sequence. That is, the user does not need to input the to-be-executed action sequence into the to-be-executed action sequence, but directly controls the vehicle to perform the corresponding action.

[0357] In the case where the method 500 includes the step S504a, the method 500 further includes a step S505a.

[0358] S505a, the to-be-executed action sequence of the plurality of vehicles is respectively sent to the plurality of vehicles.

[0359] As shown in FIG. 5, the to-be-executed action sequence M of the vehicle 1# is sent to the vehicle 1#, and the to-be-executed action sequence N of the vehicle 2# is sent to the vehicle 2#. Figure 5

[0360] Exemplarily, the step S505a can be performed by the first communication module and the second communication module in the vehicle. Figure 3

[0361] In other words, the cloud sends the to-be-executed action sequence of each vehicle to the second communication module of each vehicle through the first communication module. The second communication module of each vehicle can store the to-be-executed action sequence into the second storage module of each vehicle. Specifically, the to-be-executed action sequence is stored into the action module in the second storage module.

[0362] Further, the action module can send the to-be-executed action sequence to the execution module.

[0363] S506, the plurality of vehicles are respectively controlled to perform the calibration test.

[0364] Specifically, the plurality of vehicles are respectively controlled to perform the calibration test in the same time period.

[0365] As shown in FIG. 5, the vehicle 1# is controlled to perform the calibration test, and the vehicle 2# is controlled to perform the calibration test. Figure 5 The initial parameter combination X of the vehicle 1# is written into the ECU of the vehicle 1#, and the initial parameter combination Y of the vehicle 2# is written into the ECU of the vehicle 2#.

[0366] Since the initial parameter combinations of the plurality of vehicles have been written into the ECUs, the step S506 can be understood as that the plurality of vehicles respectively perform the calibration test based on the parameter combinations in the respective ECUs.

[0367]

[0368] ​​​For example, the step S506 can be to control the plurality of vehicles to respectively execute the action sequence to be executed of the plurality of vehicles. The vehicle 1# executes the action sequence to be executed M, and the vehicle 2# executes the action sequence to be executed N.

[0369] For example, the step S506 can be executed by the execution module of the plurality of vehicles, that is, the vehicle is controlled to execute the action sequence to be executed in an automatic driving manner.

[0370] Alternatively, the action sequence to be executed can be displayed to the driver through the vehicle display, and the driver controls the vehicle to execute the action sequence to be executed.

[0371] It should be noted that different vehicles in the plurality of vehicles can adopt different driving modes, or can adopt the same driving mode, and the embodiments of the present application do not limit this.

[0372] The method 500 includes steps S507a or S507b.

[0373] S507a, the plurality of vehicles respectively upload the data of the plurality of vehicles to the cloud.

[0374] As shown in the figure, the vehicle 1# uploads the data of the vehicle 1# to the cloud. The vehicle 2# uploads the data of the vehicle 2# to the cloud. Figure 5

[0375] For example, the data of the vehicle can include the data collected by the sensor of the vehicle in the process of performing the calibration test.

[0376] Further, the plurality of vehicles respectively upload the action sequence executed in the process of the calibration test to the cloud. That is, the action sequence actually executed by the vehicle in the process of the calibration test is uploaded to the cloud.

[0377] In one implementation mode, the data collected by the sensor can include valid data and invalid data.

[0378] In another implementation mode, the data collected by the sensor is valid data, and the valid data can be used as test data.

[0379] For specific description, please refer to the description in the step S410 in the method 400, which will not be repeated here.

[0380] It should be noted that the data uploaded by different vehicles in the plurality of vehicles can be in different forms, for example, the data uploaded by part of the vehicles includes valid data and invalid data, and the data uploaded by part of the vehicles only includes valid data. Alternatively, the data uploaded by the plurality of vehicles can also be in the same form, and the embodiments of the present application do not limit this.

[0381] For example, the step S507a can be executed by Figure 3 ​the first communication module and the second communication module in the cloud server execute.

[0382] In other words, each vehicle uploads its respective data to the first communication module of the cloud through its respective second communication module.

[0383] It should be understood that the time when different vehicles upload data can be different due to the fact that the time when each vehicle finishes performing the sequence of actions to be performed can be different.

[0384] S507b, the plurality of vehicles respectively upload the evaluation results of the parameter combinations of the plurality of vehicles to the cloud.

[0385] As shown in FIG. 5B, vehicle 1# uploads the evaluation result of the parameter combination of vehicle 1# to the cloud. Vehicle 2# uploads the evaluation result of the parameter combination of vehicle 2# to the cloud. Figure 5 Further, the plurality of vehicles respectively upload the sequence of actions performed in the calibration test to the cloud.

[0386] The evaluation results of the parameter combinations of the plurality of vehicles can be user feedback. In this case, the plurality of vehicles can obtain the evaluation results of the parameter combinations of the plurality of vehicles from user feedback.

[0387] For example, a vehicle can obtain the evaluation result of the parameter combination of the vehicle from user feedback through a human-computer interface, and upload the evaluation result of the parameter combination to the cloud.

[0388] Exemplarily, step S507b can be executed by the first communication module and the second communication module in the cloud server.

[0389] Figure 3 In other words, each vehicle uploads its respective evaluation result of the parameter combination to the first communication module of the cloud through its respective second communication module.

[0390] It should be understood that the time when different vehicles upload the evaluation results can be different due to the fact that the time when each vehicle finishes performing the sequence of actions to be performed can be different.

[0391] In another implementation mode, the method 500 can include step S507a and step S507b.

[0392] Specifically, the plurality of vehicles can upload a first part of the evaluation results of the parameter combinations of the plurality of vehicles and the data of the plurality of devices.

[0393]

[0394] ​​The evaluation result of the parameter combination of the vehicle can include a first part and a second part. The first part can be the user feedback. In this case, the vehicle can obtain the first part of the evaluation result of the parameter combination of the vehicle of the user feedback. The second part can be obtained by the cloud processing and evaluating the data uploaded by the vehicle.

[0395] It should be understood that the above steps S507a and S507b are only examples, and the specific description can be referred to the step S410 in the foregoing, which will not be described here again.

[0396] In the case where the method 500 includes the step S507a, the method 500 can further include a step S508a.

[0397] S508a, the cloud processes the received data of the vehicle.

[0398] Exemplarily, the step S508a includes performing data filtering, frequency reduction, noise reduction or the like on the received data of the vehicle to obtain the test data of the received vehicle.

[0399] Exemplarily, the step S508a can be performed by a data processing module in the cloud. Figure 3 Further, the data processing module can store the test data into a first storage module. Specifically, the data processing module can store the test data obtained after processing into a calibration data module in the first storage module.

[0400] It should be noted that the time when the data of different vehicles is uploaded can be different, and the time when the data uploaded by each vehicle is received by the cloud can be different.

[0401] In one implementation mode, the cloud can perform the step S508a on the data of all vehicles after receiving the data uploaded by all vehicles.

[0402] In another implementation mode, the cloud can perform the step S508a after receiving the data uploaded by part of the vehicles, for example, the cloud performs the step S507a on the data of any vehicle after receiving the data uploaded by the vehicle.

[0403] It should be noted that the step S508a is an optional step. For example, the data uploaded by the vehicle can be the test data obtained after processing, in which case there is no need to be processed by the cloud.

[0404] S509, the cloud judges whether the acceptance standard is met. If the acceptance standard is met, the process is ended, that is, the calibration is completed. If the acceptance standard is not met, in the case where the method 500 includes the step S507a, the step S510a is performed, and in the case where the method 500 does not include the step S507a, the step S511 is performed.

[0405] Exemplarily, step S509 can be executed by the calibration module in the cloud. Figure 3

[0406] If the method 500 comprises step S507a, step S509 can be executed in the following way.

[0407] In one implementation, the cloud can execute step S509 on the test data of all vehicles.

[0408] For example, the test data of the vehicles can be stored in the first storage module. The calibration module can monitor the first storage module, and execute step S509 after the test data of all vehicles in the plurality of vehicles are received by the first storage module.

[0409] In another implementation, the cloud can execute step S509 on the test data of part of the vehicles.

[0410] For example, the test data of the vehicles can be stored in the first storage module. The calibration module can monitor the first storage module, and execute step S509 based on the test data of any vehicle after the test data of the vehicle are received by the first storage module.

[0411] If the method 500 comprises step S5076b, step S509 can be executed in the following way.

[0412] In one implementation, the cloud can execute step S509 on the evaluation results of the parameter combinations of all vehicles.

[0413] For example, the evaluation results of the parameter combinations of the vehicles can be stored in the first storage module. The calibration module can monitor the first storage module, and execute step S509 after the evaluation results of the parameter combinations of all vehicles in the plurality of vehicles are received by the first storage module.

[0414] In another implementation, the cloud can execute step S508 on the evaluation results of the parameter combinations of part of the vehicles.

[0415] For example, the evaluation results of the parameter combinations of the vehicles can be stored in the first storage module. The calibration module can monitor the first storage module, and execute step S509 based on the evaluation results of the parameter combinations of any vehicle after the evaluation results of the parameter combinations of the vehicle are received by the first storage module.

[0416] S510a, the cloud evaluates the test data of the vehicle to obtain the evaluation results of the parameter combinations of the vehicle.

[0417] Optionally, the cloud evaluates the test data of the vehicle according to the working condition in which the vehicle is located to obtain the evaluation results of the parameter combinations of the vehicle. ​

[0418] The specific evaluation manner can be referred to step S410 in method 400, which will not be described here.

[0419] For example, step S510a can be performed by the calibration module in the cloud server. Figure 3

[0420] S511, the cloud server obtains at least one adjusted parameter combination according to the evaluation result of the parameter combination of the vehicle.

[0421] In an implementation manner, the cloud server can perform step S511 after obtaining the evaluation result of the parameter combination of part of the vehicles participating in the iteration this time. When performing step S511 for the first time, i.e., in the first iteration, the vehicles participating in the iteration are all the vehicles to be calibrated. For example, the cloud server can perform step S511 in real time after obtaining the evaluation result of the parameter combination of any vehicle.

[0422] For example, step S511 can be implemented by using a Bayesian optimization algorithm.

[0423] For example, the cloud server can use the Bayesian principle to fit the mean and variance of the evaluation result of each value point in the parameter distribution space based on the currently obtained evaluation result of the parameter combination of the vehicle, and then determine the at least one value point with the highest score according to the UCB formula, and take the at least one value point as the at least one adjusted parameter combination.

[0424] Alternatively, the cloud server can use the Bayesian principle to optimize the mean and variance of the evaluation result of each value point in the existing parameter distribution space based on the currently obtained evaluation result of the parameter combination of the vehicle, and then determine the parameter combination corresponding to the maximum value according to the UCB formula, and take the adjusted parameter combination as the at least one adjusted parameter combination.

[0425] The evaluation result of each value point in the existing parameter distribution space can be fitted based on the previously obtained evaluation result of the parameter combination of the vehicle.

[0426] Alternatively, step S511 can be implemented by using a genetic algorithm.

[0427] For example, in the case that the cloud server stores the evaluation result of the parameter combination of at least two vehicles, one or more parameter combinations with better evaluation result in the evaluation result of the parameter combination of the at least two vehicles are subjected to operations such as crossover or mutation, and the obtained parameter combination is taken as the at least one adjusted parameter combination.

[0428] In another implementation manner, the cloud server can perform step S511 after obtaining the evaluation result of the parameter combination of all the vehicles participating in the iteration this time.

[0429] ​Exemplarily, the step S511 can be implemented by using a Bayesian optimization algorithm.

[0430] For example, the cloud can use the Bayesian principle to fit the mean and variance of the evaluation results of each value point on the parameter distribution space based on the evaluation results of the parameter combination of the vehicle participating in this iteration, and then determine the at least one value point with the highest score according to the UCB formula, and take the at least one value point as the at least one adjusted parameter combination.

[0431] Alternatively, the cloud can use the Bayesian principle to optimize the mean and variance of the evaluation results of each value point on the existing parameter distribution space based on the evaluation results of the parameter combination of the vehicle participating in this iteration, and then determine the parameter combination corresponding to the maximum value according to the UCB formula, and take the parameter combination as the adjusted parameter combination.

[0432] The evaluation results of each value point on the existing parameter distribution space can be fitted based on the evaluation results of the parameter combination of the vehicle obtained before.

[0433] That is, in the process of repeatedly executing the step S511, the cloud can adjust the parameter combination of the vehicle according to the evaluation results of the parameter combination obtained in this iteration process and the evaluation results of the parameter combination obtained in the previous iteration process. In other words, the cloud can adjust the parameter combination of the vehicle according to all the evaluation results of the parameter combination obtained so far.

[0434] Alternatively, the step S511 can be implemented by using a genetic algorithm.

[0435] For example, in the case where the cloud stores the evaluation results of the parameter combination of at least two vehicles, one or more parameter combinations with better evaluation results of the parameter combination of the at least two vehicles are subjected to operations such as crossover or mutation, and the obtained parameter combination is taken as the at least one adjusted parameter combination.

[0436] The evaluation results of the parameter combination of the at least two vehicles can be obtained in one iteration process, or can be obtained in multiple iteration processes.

[0437] That is, in the process of repeatedly executing the step S511, the cloud can adjust the parameter combination of the vehicle according to the evaluation results of the parameter combination obtained in this iteration process and the evaluation results of the parameter combination obtained in the previous iteration process. In other words, the cloud can adjust the parameter combination of the vehicle according to all the evaluation results of the parameter combination obtained so far.

[0438] Further, in the case where the parameter combination of the vehicle participating in this iteration is the same, and the working conditions of the vehicle participating in this iteration are different, the step S511 can further include the following steps:

[0439] (1) processing the evaluation results of the parameter combinations of the vehicles participating in the current iteration to obtain a summary evaluation result.

[0440] For example, the summary evaluation result is a weighted average of the evaluation results of the parameter combinations of the devices participating in the current iteration. For another example, the summary evaluation result is the minimum value in the evaluation results of the parameter combinations of the devices participating in the current iteration. For another example, the summary evaluation result is the maximum value in the evaluation results of the parameter combinations of the devices participating in the current iteration. The embodiments of the present application do not limit the determination manner of the summary evaluation result.

[0441] (2) obtaining at least one adjusted parameter combination according to the summary evaluation result.

[0442] Step (2) can be understood as optimizing the current parameter combination according to the summary evaluation result. The specific optimization manner can refer to the description in the foregoing text, for example, when the Bayesian optimization algorithm is adopted, the “evaluation result of the parameter combination of the device” in the optimization method in the foregoing text is replaced by the “summary evaluation result”.

[0443] The at least one adjusted parameter combination is sent to at least one vehicle, i.e., a vehicle participating in the next iteration, the initial parameter combination in steps S504 to S511 is replaced by the adjusted parameter combination, and the plurality of vehicles in steps S504 to S511 is replaced by the at least one vehicle, and steps S504 to S511 are repeatedly executed until the calibration is completed. In other words, when steps S504 to S511 are executed for the first time, the vehicles participating in the iteration are all the vehicles to be calibrated and the plurality of vehicles. The parameter combinations of the plurality of vehicles are the initial parameter combinations of the plurality of vehicles. When steps S506 to S511 are executed thereafter, the vehicles participating in the iteration can be part or all of the plurality of vehicles each time, and the parameter combinations are the adjusted parameter combinations obtained in step S511.

[0444] For example, the at least one vehicle is determined according to at least one of the working conditions of the plurality of devices or the at least one adjusted parameter combination.

[0445] The at least one vehicle can be determined by the calibration module 212 in the server 200. Figure 3

[0446] Alternatively, the at least one vehicle can be the vehicle in the evaluation result of the parameter combination of the vehicle obtained at present. For example, the cloud executes step S511 in real time after obtaining the evaluation result of the parameter combination of vehicle 1#, in which case vehicle 1# can be one of the vehicles participating in the next iteration.

[0447] ​The determination method of the at least one vehicle can refer to step S430 in the foregoing method 400, which will not be described herein again.

[0448] The vehicles participating in each iteration can be the same or different.

[0449] It should be noted that the method 500 only takes vehicles as an example to describe the method of the embodiments of the present application, and does not limit the scheme of the embodiments of the present application.

[0450] In an implementation manner, part or all of the plurality of vehicles in the method 500 can be replaced by a test bench.

[0451] The test bench can simulate different working conditions. By replacing part or all of the vehicles with the test bench, the method can be applied to engine calibration or motor calibration scenarios, further reducing calibration costs, improving data acquisition efficiency, and further improving calibration efficiency.

[0452] Since the test bench can simulate different working conditions, when the working condition of the test bench changes, the updated working condition of the test bench can be uploaded to the cloud. The working condition of the same vehicle usually does not change during calibration, and the plurality of vehicles can upload the working condition once in step S501. The working condition of the test bench can be set as needed. After part or all of the plurality of vehicles are replaced by the test bench, when the working condition of the test bench changes, the updated working condition of the test bench can be uploaded to the cloud in real time.

[0453] When the test bench is used for calibration test, the first communication module and the second communication module can use wireless communication to transmit data, or can use wired communication to transmit data.

[0454] The parameter calibration apparatus can be deployed in a cloud environment. The cloud environment is an entity that provides cloud services to users by using basic resources in a cloud computing mode. The cloud environment includes a cloud data center and a cloud service platform. The cloud data center includes a large number of basic resources (including computing resources, storage resources, and network resources) owned by a cloud service provider. The computing resources included in the cloud data center can be a large number of computing devices (for example, servers).

[0455] The parameter calibration apparatus can be a server in the cloud data center for calibrating parameters. The parameter calibration apparatus can also be a software apparatus deployed on a server or a virtual machine in the cloud data center. The software apparatus is used for calibrating parameters. The software apparatus can be distributed on a plurality of servers, or distributed on a plurality of virtual machines, or distributed on virtual machines and servers.

[0456] The parameter calibration device is abstracted by a cloud service provider into a parameter calibration cloud service on a cloud service platform to provide a user, after the user purchases the cloud service, with a parameter calibration service by the cloud environment using the parameter calibration device, and the device data or the evaluation result of the parameter combination of the device can be uploaded to the cloud environment through a communication interface, the parameter combination of the device is optimized by the parameter calibration device, and the optimization result can be returned to the device of the user.

[0457] When the parameter calibration device is a software device, different modules of the parameter calibration device can be deployed in different environments or devices. For example, part of the parameter calibration device is deployed in a terminal device (such as a vehicle, a smart phone, a notebook computer, a tablet computer, a personal desktop computer, and a smart camera), and another part is deployed in a cloud data center (specifically, on a server or a virtual machine in the cloud data center).

[0458] The functions of the parameter calibration method are cooperatively implemented between the parts of the parameter calibration device deployed in different environments or devices. For example, the deployment of the parameter calibration device can refer to Figure 3 .

[0459] It can be understood that the present application does not limit which parts of the parameter calibration device are deployed in a terminal computing device and which parts are deployed in a cloud data center, and in actual application, adaptive deployment can be performed according to the computing power of the terminal computing device or specific application requirements.

[0460] When the parameter calibration device is a software device, the parameter calibration device can also be separately deployed on a computing device in any environment (for example, separately deployed on a terminal device or separately deployed on a computing device in a cloud data center).

[0461] The following describes the device of the embodiment of the present application. It should be understood that the device described below can perform the method of the foregoing embodiments of the present application, and in order to avoid unnecessary repetition, the repeated description is appropriately omitted when the device of the embodiment of the present application is introduced below. Figures 6 to 7 The device of the embodiment of the present application is described. It should be understood that the device described below can perform the method of the foregoing embodiments of the present application, and in order to avoid unnecessary repetition, the repeated description is appropriately omitted when the device of the embodiment of the present application is introduced below.

[0462] Figure 6 is a schematic block diagram of the parameter calibration device of the embodiment of the present application. Figure 6 The parameter calibration device 3000 shown includes an acquisition unit 3010 and a processing unit 3020.

[0463] The acquisition unit 3010 and the processing unit 3020 can be used to perform the parameter calibration method of the embodiments of the present application, specifically, can be used to perform the method 400 or the method 500.

[0464] In an implementation, the obtaining unit 3010 is configured to obtain evaluation results of parameter combinations of a plurality of devices, the evaluation results of the parameter combinations of the plurality of devices being obtained by respectively performing calibration tests on the plurality of devices based on the parameter combinations of the plurality of devices within a first time period, the first time period being less than or equal to a first threshold. The processing unit 3020 is configured to obtain at least one adjusted parameter combination according to the evaluation results of the parameter combinations of the plurality of devices.

[0465] Optionally, as an embodiment, the parameter combinations of the plurality of devices are the same, and the working conditions of the plurality of devices are different, and the processing unit 3020 is specifically configured to: process the evaluation results of the parameter combinations of the plurality of devices to obtain a summary evaluation result; and obtain the at least one adjusted parameter combination according to the summary evaluation result.

[0466] Optionally, as an embodiment, the apparatus further includes a sending unit 3030 configured to send the at least one adjusted parameter combination to at least one device.

[0467] Optionally, as an embodiment, the at least one device is determined according to at least one of the following: the working conditions of the plurality of devices or the at least one adjusted parameter combination.

[0468] Optionally, as an embodiment, the evaluation results of the parameter combinations of the plurality of devices are obtained by evaluating test data of the plurality of devices, the test data of the plurality of devices being determined according to data collected in the process of respectively performing calibration tests on the plurality of devices based on the parameter combinations of the plurality of devices within the first time period.

[0469] Optionally, as an embodiment, the evaluation results of the parameter combinations of the plurality of devices are obtained by user feedback.

[0470] Optionally, as an embodiment, the sending unit 3030 is further configured to: send a to-be-executed action sequence of the at least one device to the at least one device respectively, the to-be-executed action sequence of the at least one device including actions required to be executed by the at least one device in the process of performing the calibration test based on the adjusted parameter combination of the at least one device.

[0471] Optionally, as an embodiment, the to-be-executed action sequence of the at least one device is determined according to at least one of the following: actions covered by the parameter calibration requirement, the working conditions of the at least one device, or the evaluation results of the parameter combinations of the plurality of devices.

[0472] Optionally, as an embodiment, the plurality of devices include at least one of the following: a vehicle or a test bench.

[0473] In another implementation, the obtaining unit 30103 is configured to obtain the adjusted parameter combination, the adjusted parameter combination being obtained according to evaluation results of parameter combinations of a plurality of devices, the plurality of devices including the first device, the evaluation results of the parameter combinations of the plurality of devices being obtained by performing calibration tests on the plurality of devices based on the parameter combinations of the plurality of devices respectively within a first time period, the first time period being less than or equal to a first threshold.

[0474] The processing unit 3020 is configured to control the first device to perform the calibration test based on the adjusted parameter combination.

[0475] Optionally, as an embodiment, the parameter combinations of the plurality of devices are the same, the plurality of devices are in different working conditions, and the adjusted parameter combination is obtained according to a summary evaluation result, the summary evaluation result being obtained by processing the evaluation results of the parameter combinations of the plurality of devices.

[0476] Optionally, as an embodiment, the first device is determined according to at least one of the following: the working conditions of the plurality of devices or the adjusted parameter combination.

[0477] Optionally, as an embodiment, the evaluation results of the parameter combinations of the plurality of devices are obtained by evaluating test data of the plurality of devices, the test data of the plurality of devices being determined according to data collected in the process of performing the calibration tests on the plurality of devices based on the parameter combinations of the plurality of devices respectively within the first time period.

[0478] Optionally, as an embodiment, the evaluation results of the parameter combinations of the plurality of devices are obtained by user feedback.

[0479] Optionally, as an embodiment, the obtaining unit 3010 is further configured to obtain a to-be-executed action sequence of the first device, the to-be-executed action sequence of the first device including actions required to be performed by the first device in the process of performing the calibration test based on the adjusted parameter combination.

[0480] Optionally, as an embodiment, the to-be-executed action sequence of the first device is determined according to at least one of the following: actions covered by the parameter calibration requirement, the working conditions of the first device, or the evaluation results of the parameter combinations of the plurality of devices.

[0481] Optionally, as an embodiment, the first device is a vehicle or a test bench.

[0482] It should be noted that the apparatus 3000 is embodied in the form of functional units. The term “unit” herein can be implemented in the form of software and / or hardware, and no specific limitation is made.

[0483] For example, the "unit" can be a software program, a hardware circuit, or a combination of both, which implements the above functions. The hardware circuit can include an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor, or a group processor, etc.) and a memory for executing one or more software or firmware programs, a combination logic circuit, and / or other suitable components that support the described functions.

[0484] Therefore, the units of each example described in the embodiments of the present application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0485] Figure 7 FIG. 1 is a hardware structure schematic diagram of a parameter calibration device provided by an embodiment of the present application. Figure 7 The parameter calibration device 5000 (which can be a computer device in particular) shown includes a memory 5001, a processor 5002, a communication interface 5003, and a bus 5004. The memory 5001, the processor 5002, and the communication interface 5003 are in communication connection with each other through the bus 5004.

[0486] The memory 5001 can be a read only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 5001 can store a program, and when the program stored in the memory 5001 is executed by the processor 5002, the processor 5002 is configured to execute each step of the parameter calibration method of the embodiments of the present application. Specifically, the processor 5002 can execute the method 400 shown in the above Figure 4 The processor 5002 can execute the method 500 shown in the above Figure 5 The processor 5002 can execute the method 500 shown in the above

[0487] The processor 5002 can adopt a general central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, to execute a related program to implement the parameter calibration method of the embodiments of the present application.

[0488] The processor 5002 can also be an integrated circuit chip with signal processing capabilities. In implementation, each step of the parameter calibration method of this application can be completed through the integrated logic circuitry in the processor 5002 or through software instructions.

[0489] The processor 5002 described above can also be a general-purpose processor, 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, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 5001, and the processor 5002 reads the information in memory 5001 and combines it with its hardware to complete the task. Figure 6 The apparatus shown includes units that are required to perform functions, or to perform the methods described in this application. Figure 4 or Figure 5 The method for parameter calibration is shown.

[0490] The communication interface 5003 uses transceiver devices, such as, but not limited to, transceivers, to enable communication between the device 5000 and other devices or communication networks. For example, evaluation results of parameter combinations can be obtained through the communication interface 5003.

[0491] Bus 5004 may include a pathway for transmitting information between various components of device 5000 (e.g., memory 5001, processor 5002, communication interface 5003).

[0492] It should be noted that although the above-described device 5000 only shows a memory, processor, and communication interface, those skilled in the art should understand that in specific implementations, device 5000 may also include other devices necessary for normal operation. Furthermore, depending on specific needs, those skilled in the art should understand that device 5000 may also include hardware devices for implementing other additional functions. Moreover, those skilled in the art should understand that device 5000 may only include the devices necessary for implementing the embodiments of this application, and may not necessarily include... Figure 7all of the devices shown in the figures.

[0493] It should be appreciated that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0494] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0495] The above-described embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented by software, the above-described embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (for example, floppy disk, hard disk, magnetic tape), an optical medium (for example, DVD), or a semiconductor medium. The semiconductor medium can be a solid state disk.

[0496] The present application also provides a computer program product, which includes computer program code, when the computer program code is run on a computer, so that the computer executes the method in any one of the preceding method embodiments.

[0497] The present application also provides a computer-readable medium, which stores program code, when the program code is run on a computer, so that the computer executes the method in any one of the preceding method embodiments.

[0498] The present application also provides an electronic device, which includes the parameter calibration device in any one of the preceding device embodiments.

[0499] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application.

[0500] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0501] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0502] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0503] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0504] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0505] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0506] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for parameter calibration, characterized in that, include: The evaluation results of parameter combinations of multiple devices are obtained by calibration tests of each device based on the parameter combinations of the multiple devices in a first time period, where the first time period is less than or equal to a first threshold and the multiple devices are in different operating conditions. At least one adjusted parameter combination is obtained based on the evaluation results of the parameter combinations of the multiple devices.

2. The method according to claim 1, characterized in that, The multiple devices have the same combination of parameters, and The step of obtaining at least one adjusted parameter combination based on the evaluation results of the parameter combinations of the multiple devices includes: The evaluation results of the combined parameters of the multiple devices are processed to obtain a summary evaluation result; The at least one adjusted parameter combination is obtained based on the summarized evaluation results.

3. The method according to claim 1 or 2, characterized in that, The method further includes: The at least one adjusted parameter combination is sent to at least one device.

4. The method according to claim 3, characterized in that, The at least one device is determined according to at least one of the following: The operating conditions of the multiple devices or the at least one adjusted parameter combination.

5. The method according to claim 1 or 2, characterized in that, The evaluation result of the parameter combination of the multiple devices is obtained by evaluating the test data of the multiple devices. The test data of the multiple devices is determined based on the data collected during the calibration test of the multiple devices based on the parameter combination of the multiple devices in the first time period.

6. The method according to claim 1 or 2, characterized in that, The evaluation results of the parameter combination of the multiple devices are obtained from user feedback.

7. The method according to claim 3, characterized in that, The method further includes: The sequence of actions to be executed by the at least one device is sent to the at least one device respectively. The sequence of actions to be executed by the at least one device includes the actions that the at least one device needs to perform during the calibration test based on the adjusted parameter combination of the at least one device.

8. The method according to claim 7, characterized in that, The sequence of actions to be performed by the at least one device is determined based on at least one of the following: The parameter calibration requirements cover the actions, the operating conditions of the at least one device, or the evaluation results of parameter combinations of the multiple devices.

9. The method according to claim 1 or 2, characterized in that, The plurality of devices includes at least one of the following: a vehicle or a test bench.

10. A method for parameter calibration, characterized in that, include: The adjusted parameter combination is obtained based on the evaluation results of parameter combinations of multiple devices, including a first device. The evaluation results of the parameter combinations of the multiple devices are obtained by the multiple devices respectively conducting calibration tests based on the parameter combinations of the multiple devices in a first time period. The first time period is less than or equal to a first threshold, and the multiple devices are in different operating conditions. The first device is controlled to perform a calibration test based on the adjusted parameter combination.

11. The method according to claim 10, characterized in that, The multiple devices have the same parameter combination, and the adjusted parameter combination is obtained based on the summarized evaluation results, which are obtained by processing the evaluation results of the parameter combination of the multiple devices.

12. The method according to claim 10 or 11, characterized in that, The first device is determined according to at least one of the following: The operating conditions of the multiple devices or the adjusted parameter combination.

13. The method according to claim 10 or 11, characterized in that, The evaluation result of the parameter combination of the multiple devices is obtained by evaluating the test data of the multiple devices. The test data of the multiple devices is determined based on the data collected during the calibration test of the multiple devices based on the parameter combination of the multiple devices in the first time period.

14. The method according to claim 10 or 11, characterized in that, The evaluation results of the parameter combination of the multiple devices are obtained from user feedback.

15. The method according to claim 10 or 11, characterized in that, The method further includes: Obtain the sequence of actions to be performed by the first device, which includes the actions that the first device needs to perform during the calibration test based on the adjusted parameter combination.

16. The method according to claim 15, characterized in that, The sequence of actions to be performed by the first device is determined based on at least one of the following: The parameter calibration requirements cover the actions, the operating conditions of the first device, or the evaluation results of the parameter combinations of the multiple devices.

17. The method according to claim 10 or 11, characterized in that, The first device is: a vehicle or a test bench.

18. A parameter calibration device, characterized in that, include: An acquisition unit is used to acquire the evaluation results of parameter combinations of multiple devices. The evaluation results of parameter combinations of multiple devices are obtained by the multiple devices respectively conducting calibration tests based on the parameter combinations of the multiple devices in a first time period. The first time period is less than or equal to a first threshold, and the multiple devices are in different operating conditions. The processing unit is configured to obtain at least one adjusted parameter combination based on the evaluation results of the parameter combinations of the plurality of devices.

19. The apparatus according to claim 18, characterized in that, The multiple devices have the same combination of parameters, and The processing unit is specifically used for: The evaluation results of the combined parameters of the multiple devices are processed to obtain a summary evaluation result; The at least one adjusted parameter combination is obtained based on the summarized evaluation results.

20. The apparatus according to claim 18 or 19, characterized in that, The device further includes: A sending unit is used to send the at least one adjusted parameter combination to at least one device.

21. The apparatus according to claim 20, characterized in that, The at least one device is determined according to at least one of the following: The operating conditions of the multiple devices or the at least one adjusted parameter combination.

22. The apparatus according to claim 18 or 19, characterized in that, The evaluation result of the parameter combination of the multiple devices is obtained by evaluating the test data of the multiple devices. The test data of the multiple devices is determined based on the data collected during the calibration test of the multiple devices based on the parameter combination of the multiple devices in the first time period.

23. The apparatus according to claim 18 or 19, characterized in that, The evaluation results of the parameter combination of the multiple devices are obtained from user feedback.

24. The apparatus according to claim 20, characterized in that, The transmitting unit is further configured to: The sequence of actions to be executed by the at least one device is sent to the at least one device respectively. The sequence of actions to be executed by the at least one device includes the actions that the at least one device needs to perform during the calibration test based on the adjusted parameter combination of the at least one device.

25. The apparatus according to claim 24, characterized in that, The sequence of actions to be performed by the at least one device is determined based on at least one of the following: The parameter calibration requirements cover the actions, the operating conditions of the at least one device, or the evaluation results of parameter combinations of the multiple devices.

26. The apparatus according to claim 18 or 19, characterized in that, The plurality of devices includes at least one of the following: a vehicle or a test bench.

27. A parameter calibration device, characterized in that, include: An acquisition unit is used to acquire an adjusted parameter combination, which is obtained based on the evaluation results of parameter combinations of multiple devices, including a first device. The evaluation results of the parameter combinations of the multiple devices are obtained by the multiple devices respectively conducting calibration tests based on the parameter combinations of the multiple devices within a first time period. The first time period is less than or equal to a first threshold, and the multiple devices are in different operating conditions. The processing unit is used to control the first device to perform a calibration test based on the adjusted parameter combination.

28. The apparatus according to claim 27, characterized in that, The multiple devices have the same parameter combination, and the adjusted parameter combination is obtained based on the summarized evaluation results, which are obtained by processing the evaluation results of the parameter combination of the multiple devices.

29. The apparatus according to claim 27 or 28, characterized in that, The first device is determined according to at least one of the following: The operating conditions of the multiple devices or the adjusted parameter combination.

30. The apparatus according to claim 27 or 28, characterized in that, The evaluation result of the parameter combination of the multiple devices is obtained by evaluating the test data of the multiple devices. The test data of the multiple devices is determined based on the data collected during the calibration test of the multiple devices based on the parameter combination of the multiple devices in the first time period.

31. The apparatus according to claim 27 or 28, characterized in that, The evaluation results of the parameter combination of the multiple devices are obtained from user feedback.

32. The apparatus according to claim 27 or 28, characterized in that, The acquisition unit is also used for: Obtain the sequence of actions to be performed by the first device, which includes the actions that the first device needs to perform during the calibration test based on the adjusted parameter combination.

33. The apparatus according to claim 32, characterized in that, The sequence of actions to be performed by the first device is determined based on at least one of the following: The parameter calibration requirements cover the actions, the operating conditions of the first device, or the evaluation results of the parameter combinations of the multiple devices.

34. The apparatus according to claim 27 or 28, characterized in that, The first device is: a vehicle or a test bench.

35. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions for execution by a computing device, the instructions being used to implement the method for parameter calibration as claimed in any one of claims 1 to 9 or 10 to 17.

36. A computer program product containing instructions, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the parameter calibration method as claimed in any one of claims 1 to 9 or 10 to 17.

Images