Method, device and medium for predicting software upgrade time

Abstract

The application discloses a software upgrade time prediction method, device, equipment and medium. The software upgrade time prediction method comprises the following steps: acquiring a plurality of historical relative time data, wherein each historical relative time data represents the relationship between the time required for software upgrade at the vehicle end and the software data size; obtaining target sequence data based on the plurality of historical relative time data and a plurality of data numbers corresponding to the plurality of historical relative time data; performing data processing based on the target sequence data to obtain a time prediction model; predicting the target relative time data required for software upgrade at the vehicle end based on the target data number by using the time prediction model; and sending the target relative time data to the vehicle end, so that the vehicle end determines the time required for software upgrade based on the target relative time data and the software data size. The time prediction model obtained through data processing can improve the accuracy of the predicted software upgrade time.

Description

Technical Field

[0001] This application relates to the technical fields of vehicle networking and software upgrades, and in particular to a method, apparatus, device, and medium for predicting software upgrade time. Background Technology

[0002] With the development of vehicle-to-everything (V2X) technology, more and more software needs to be installed in vehicles. Due to considerations such as software stability, security, and market competitiveness, software installed in vehicles inevitably needs to be upgraded after a certain period. Vehicles can download upgrade packages from cloud OTA servers using Over-the-Air Technology (OTA) to update the software system. During the vehicle software upgrade process, software developers often design progress bars to display the upgrade time, aiming to provide feedback to users and enhance the user experience. However, these progress bars are based on the developers' experience and estimates of the installation time and progress based on software testing. These estimates are often inaccurate, frequently resulting in uneven progress bar changes or the bar getting stuck at a certain point. Summary of the Invention

[0003] In view of the above problems, this application provides a method, apparatus, device and medium for predicting software upgrade time, which can effectively solve the problem of inaccurate prediction of software upgrade time in the prior art.

[0004] In a first aspect, embodiments of this application provide a method for predicting software upgrades, comprising: acquiring multiple historical relative time data, wherein each historical relative time data represents the relationship between the time required for a software upgrade on the vehicle and the size of the software data; obtaining target sequence data based on the multiple historical relative time data and multiple data numbers corresponding to the multiple historical relative time data; performing data processing based on the target sequence data to obtain a time prediction model; using the time prediction model based on the target data numbers to predict the target relative time data required for a software upgrade on the vehicle; and sending the target relative time data to the vehicle so that the vehicle can determine the time required for the software upgrade based on the target relative time data and the size of the software data.

[0005] In the technical solution of this application embodiment, a time prediction model is obtained by processing multiple historical relative time data. The target relative time data required for the vehicle-side software upgrade is obtained based on the target data number using the time prediction model. After obtaining the target relative time data, the software upgrade time can be further obtained. This can remove the developer's personal experience and the estimation of software installation time and progress in the software testing situation. It can also remove interference factors such as computer performance and hardware configuration, making the predicted software upgrade time more accurate and improving the prediction accuracy of the software upgrade time.

[0006] In some embodiments, data processing based on target sequence data to obtain a time prediction model includes: performing data fitting on the target sequence data to obtain a fitting line, wherein the fitting line represents the relationship between data number and relative time data, wherein when multiple historical relative time data come from multiple vehicle terminals, multiple data numbers correspond one-to-one with multiple vehicle terminals; and determining the fitting line as the time prediction model.

[0007] In the technical solution of this application embodiment, a fitted line is obtained by fitting the target sequence data. This fitted line is then used as a time prediction model to predict the time required for vehicle software upgrades. This method can intuitively represent the prediction results of the time prediction model, and the data fitting method has low computational complexity and yields a highly accurate time prediction model. Furthermore, the more data used to train the time prediction model, the more accurate the fitted line becomes through processing a large amount of data, leading to more precise predictions of the vehicle software upgrade time.

[0008] In some embodiments, the plurality of historical relative time data includes at least one of a plurality of first historical relative time data and a plurality of second historical relative time data; the plurality of first historical relative time data is the relative time required for the first software upgrade previously performed on the vehicle, the plurality of second historical relative time data is the relative time required for the second software upgrade previously performed on the vehicle, and the plurality of data numbers includes a plurality of first data numbers and a plurality of second data numbers, the plurality of first data numbers corresponding to the plurality of first historical relative time data, and the plurality of second data numbers corresponding to the plurality of second historical relative time data; wherein, obtaining target sequence data based on the plurality of historical relative time data and the plurality of data numbers corresponding to the plurality of historical relative time data includes: determining the plurality of first historical relative time data and the plurality of first data numbers as target sequence data; or obtaining target sequence data based on the plurality of first historical relative time data, the plurality of first data numbers, the plurality of second historical relative time data, and the plurality of second data numbers.

[0009] In the technical solution of this application embodiment, the multiple historical relative time data used to train the time prediction model can be the relative time data used when the vehicle underwent its first software upgrade, the relative time data used when the vehicle underwent its second upgrade, or a combination of the relative time data used when the vehicle underwent two previous upgrades. This allows for the recording of a large amount of training data for the time prediction model. Training data can be selected according to actual needs, making the selection of training data very flexible. For example, target sequence data obtained based on the first historical relative time data can be used for training, reducing training complexity and increasing training speed. Alternatively, training can be based on the first and second historical relative time data, enriching the training data and improving the prediction accuracy of the time prediction model. The trained time prediction model can not only significantly improve the accuracy of predicting software upgrade times but also predict relatively accurate software upgrade times based on different types of software upgrades.

[0010] In some embodiments, obtaining target sequence data based on multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers includes: predicting historical relative time data based on multiple first historical relative time data and multiple first data numbers; and determining the predicted historical relative time data, the data number corresponding to the predicted historical relative time data, multiple second historical relative time data, and multiple second data numbers as target sequence data.

[0011] In the technical solution of this application embodiment, when training based on first historical relative time and second historical relative time data, a first data fitting can be performed based on target sequence data obtained from multiple first historical relative time data to obtain predicted historical relative time data. Then, a second data fitting is performed based on target sequence data obtained from predicted historical relative time data and second historical relative time data. The amount of data in the predicted historical relative time data is usually smaller than the amount of data in the original multiple first historical relative time data. Therefore, the result of the first data fitting is referenced during the second data fitting, which makes the computational amount of the time prediction model smaller, ensuring fitting accuracy while further reducing the computational amount and improving the computational speed.

[0012] In some embodiments, obtaining target sequence data based on multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers includes: predicting historical relative time data based on multiple first historical relative time data and multiple first data numbers; and determining multiple first historical relative time data, multiple first data numbers, predicted historical relative time data, data numbers corresponding to the predicted historical relative time data, multiple second historical relative time data, and multiple second data numbers as target sequence data.

[0013] In the technical solution of this application embodiment, when training is performed based on first historical relative time and second historical relative time data, a first data fitting can be performed based on target sequence data obtained from multiple first historical relative time data to obtain predicted historical relative time data. Then, a second data fitting is performed based on target sequence data obtained from predicted historical relative time data and second historical relative time data. The second data fitting process not only refers to the original multiple first historical relative time data, but also refers to the result of the first data fitting (predicted historical relative time data). The second data fitting is performed based on rich training data (predicted historical relative time data, first historical relative time data and second historical relative time data), which greatly improves the fitting accuracy and thus improves the prediction accuracy.

[0014] In some embodiments, obtaining target sequence data based on multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers includes: determining multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers as target sequence data.

[0015] In the technical solution of this application embodiment, when training is performed based on the first historical relative time and the second historical relative time data, the first data fitting can be performed based on the first historical relative time data. In the second data fitting, the target sequence data can be obtained directly based on the original first historical relative time data and the original second historical relative time data. This not only improves the richness of the target sequence data, but also avoids additional data errors due to the original first historical relative time data and the original second historical relative time data, thereby improving the fitting accuracy to a certain extent and thus improving the prediction accuracy.

[0016] On the other hand, embodiments of this application provide a method for displaying software upgrades on a vehicle, comprising: receiving target relative time data required for software upgrades on the vehicle, wherein the target relative time data is obtained according to the method of any of the above embodiments; determining the time required for software upgrades based on the target relative time data and the size of the software data; and displaying the time required for software upgrades during the software upgrade process.

[0017] In the technical solution of this application embodiment, the received target relative time data shows the time required for software upgrade, which improves the display accuracy of software upgrade time and thus enhances the user experience.

[0018] On the other hand, embodiments of this application provide a cloud platform capable of executing the steps of the methods in any of the above embodiments.

[0019] On the other hand, embodiments of this application provide a vehicle-side device, and the cloud can execute the steps of the methods of any of the above embodiments.

[0020] On the other hand, embodiments of this application provide a software upgrade time prediction device, comprising: an acquisition module for acquiring multiple historical relative time data, wherein each historical relative time data represents the relationship between the time required for a software upgrade on the vehicle and the size of the software data; a first acquisition module for obtaining target sequence data based on the multiple historical relative time data and multiple data numbers corresponding to the multiple historical relative time data; a second acquisition module for performing data processing based on the target sequence data to obtain a time prediction model; a prediction module for using the time prediction model to predict the target relative time data required for a software upgrade on the vehicle based on the target data numbers; and a sending module for sending the target relative time data to the vehicle so that the vehicle can determine the time required for the software upgrade based on the target relative time data and the size of the software data.

[0021] On the other hand, embodiments of this application provide a vehicle-mounted software upgrade display device, comprising: a receiving module for receiving target relative time data required for software upgrade on the vehicle-mounted device, wherein the target relative time data is obtained based on the aforementioned software upgrade time prediction device; a determining module for determining the time required for software upgrade based on the target relative time data and the software data size; and a display module for displaying the time required for software upgrade during the software upgrade process.

[0022] On the other hand, this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method of any of the above embodiments.

[0023] On the other hand, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method of any of the above embodiments.

[0024] On the other hand, this application provides a computer program product that includes instructions that, when executed by a processor of a computer device, enable the computer device to perform the steps of the method described in any of the above embodiments.

[0025] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0026] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0027] Figure 1 A flowchart illustrating the software upgrade time prediction method provided in this application embodiment;

[0028] Figure 2 This illustration shows a data fitting diagram based on the first OTA upgrade, according to an embodiment of this application.

[0029] Figure 3 This illustration shows a data fitting diagram based on a second OTA upgrade, according to an embodiment of this application.

[0030] Figure 4 A schematic diagram of data fitting based on a second OTA upgrade, according to another embodiment of this application, is shown;

[0031] Figure 5 A flowchart illustrating the vehicle-side software upgrade display method provided in this embodiment of the application;

[0032] Figure 6 A schematic diagram of the OTA flashing process provided for the implementation of this application;

[0033] Figure 7 A schematic diagram of a software upgrade time prediction device provided for an embodiment of this application;

[0034] Figure 8 A schematic diagram of a vehicle-mounted software upgrade display device provided in an embodiment of this application. Detailed Implementation

[0035] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0036] 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 pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0037] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0038] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0039] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0040] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0041] In the description of the embodiments of this application, the technical terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0042] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0043] With the rapid growth of digital media content, 3D models are receiving increasing attention due to their importance in applications such as games, movies, and virtual reality. To protect the copyright of 3D models, it is usually necessary to add specific identifying information to them. Digital watermarking technology is an information hiding technology used for copyright protection. It embeds specific identifying information (such as watermarks) into digital media (such as images, audio, and video) to achieve the purposes of copyright identification, content authentication, and prevention of unauthorized alteration.

[0044] In some embodiments, the prediction of software upgrade time is based on the developer's relevant experience and the software testing situation to estimate the software installation time and progress. The estimated software installation time is often inaccurate. Moreover, the actual software upgrade time is also affected by computer performance and hardware configuration. In the actual software upgrade process, the software upgrade time estimated by the above method differs greatly from the actual software upgrade time based on different computer performance and hardware configuration. It is common for the progress bar to change unevenly or get stuck at a certain position.

[0045] In view of this, embodiments of this application provide a method for predicting software upgrade time.

[0046] Figure 1 A flowchart illustrating the software upgrade time prediction method provided in this application embodiment.

[0047] like Figure 1As shown, the software upgrade time prediction method 100 provided in this application includes steps S110-S150, for example. In one example, the method can be executed by the cloud.

[0048] Step S110: Obtain multiple historical relative time data, wherein each historical relative time data represents the relationship between the time required for the vehicle to perform a software upgrade and the size of the software data.

[0049] For example, historical relative time data represents the relationship between the time required for a previous software upgrade on the vehicle and the size of the software data. In one example, the ratio between the time required for a previous software upgrade on the vehicle and the size of the software data can be used as historical relative time data; that is, historical relative time includes the time required for a unit size of software data during the software upgrade.

[0050] In some embodiments, the cloud can directly receive historical relative time data uploaded directly from the vehicle. In other embodiments, the cloud can receive the time required for a software upgrade and the size of the software data uploaded by the vehicle, and then calculate the historical relative time data based on the time required for the software upgrade and the size of the software data.

[0051] Step S120: Based on multiple historical relative time data and multiple data numbers corresponding to the multiple historical relative time data, the target sequence data is obtained.

[0052] For example, each historical relative time data point and its corresponding data number form a data pair, and multiple data pairs can constitute the target sequence data. In another example, the target sequence data could be a two-dimensional array (x, y), where one dimension x represents the data number and the other dimension y represents the historical relative time data.

[0053] Step S130: Data processing is performed based on the target sequence data to obtain a time prediction model.

[0054] In some embodiments, data processing may include model modeling, model training, and data fitting. For example, the target sequence data can be used as samples for model training or model building to obtain a time prediction model. The time prediction model can be an artificial intelligence model, such as a time series model, which includes AR (Autoregressive model), MA (moving average model), ARMA (Auto-Regressive and Moving Average Model), and so on. Alternatively, data fitting can be performed based on the target sequence data to obtain a model that characterizes the changing trend of the target sequence data.

[0055] Step S140: Using a time prediction model based on the target data number, predict the target relative time data required for the vehicle-side software upgrade.

[0056] In some embodiments, the target data number may be different from the multiple data numbers corresponding to multiple historical relative time data. The target data number may be obtained based on multiple data numbers according to a preset rule, or the target data number may be determined by referring to multiple data numbers.

[0057] In some examples, the target data number can be a number immediately adjacent to multiple data numbers corresponding to multiple historical relative time data. In some embodiments, the target data number can be separated from the multiple data numbers by multiple numbers.

[0058] By inputting the target data number into the time prediction model, the model can output the target relative time data required for the software upgrade. The target relative time represents the time required for future software upgrades on the vehicle.

[0059] Step S150: Send the target relative time data to the vehicle terminal so that the vehicle terminal can determine the time required for the software upgrade based on the target relative time data and the software data size.

[0060] After the target relative time is predicted in the cloud, the cloud can send the target relative time to the vehicle so that the vehicle can calculate the time required for the software upgrade based on the target relative time data and the software data size. For example, the vehicle can multiply the target relative time data by the software data size to get the time required for the software upgrade.

[0061] In the technical solution of this application embodiment, a time prediction model is obtained by processing multiple historical relative time data. The time prediction model is then used to obtain the target relative time data required for software upgrades on the vehicle side based on the target data number. After obtaining the target relative time data, the software upgrade time can be further obtained. The aforementioned multiple historical relative time data are obtained by dividing the actual upgrade time in previous software upgrades on the vehicle side by the software package size. Both the actual upgrade time and the software package size are objective data recorded in previous software upgrades on the vehicle side. This avoids the problem of inaccurate software installation time caused by estimating the software installation time and progress based on relevant experience and software testing. It also effectively removes interference factors such as computer performance and hardware configuration, improving the accuracy of software upgrade time prediction.

[0062] In another embodiment, taking the data fitting to obtain a time prediction model as an example, the time prediction model is obtained by data processing based on the target sequence data, including: performing data fitting on the target sequence data to obtain a fitting line, wherein the fitting line represents the relationship between data number and relative time data, wherein when multiple historical relative time data come from multiple vehicle terminals, multiple data numbers correspond one-to-one with multiple vehicle terminals; and determining the fitting line as the time prediction model.

[0063] For example, data processing of target sequence data can involve data fitting, such as obtaining a time prediction model as a fitted line. When multiple historical relative time data come from multiple vehicle terminals (e.g., N vehicle terminals), the N vehicle terminals can represent the 1st, 2nd, 3rd...Nth vehicle, and the multiple data numbers correspond one-to-one with the multiple vehicle terminals, which can also be represented as 1, 2, 3...N. In this case, the target sequence data can be represented as a two-dimensional array (x, y), where the horizontal axis x can be represented as 1, 2, 3...N, and the vertical axis y can represent the corresponding historical relative time data.

[0064] As can be seen, by fitting the target sequence data to obtain a fitted line, and using this fitted line as a time prediction model, the prediction time required for vehicle software upgrades can be predicted more intuitively. Furthermore, the data fitting method has low computational complexity and yields a relatively accurate time prediction model. In addition, the more data used to train the time prediction model, the more accurate the fitted line becomes through processing large amounts of data, leading to more precise predictions of vehicle software upgrade times.

[0065] In another embodiment, the plurality of historical relative time data includes at least one of a plurality of first historical relative time data and a plurality of second historical relative time data; the plurality of first historical relative time data is the relative time required for the first software upgrade previously performed on the vehicle, the plurality of second historical relative time data is the relative time required for the second software upgrade previously performed on the vehicle, and the plurality of data numbers includes a plurality of first data numbers and a plurality of second data numbers, the plurality of first data numbers corresponding to the plurality of first historical relative time data, and the plurality of second data numbers corresponding to the plurality of second historical relative time data.

[0066] For example, the target sequence data used for data fitting can be obtained in a variety of ways.

[0067] In the embodiments of this application, the multiple historical relative time data may include multiple first historical relative time data, multiple second historical relative time data, or multiple first historical relative time data and multiple second historical relative time data.

[0068] In one example, multiple first historical relative time data and multiple first data numbers can be identified as target sequence data.

[0069] For example, when multiple historical relative time data include multiple first historical relative time data, the multiple first historical relative time data and the multiple first data numbers corresponding to the multiple first historical relative time data are determined as the target sequence data.

[0070] As can be seen from the embodiments of this application, the time prediction model is trained on target sequence data obtained from the first historical relative time data, which can reduce training complexity and improve training speed, enabling the time prediction model to quickly predict the time required for the next software upgrade based on objective historical training data.

[0071] In another example, the target sequence data can be obtained based on multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers.

[0072] For example, when multiple historical relative time data include multiple first historical relative time data and multiple second historical relative time data, the multiple first historical relative time data and multiple first data numbers corresponding to the multiple first historical relative time data, as well as the multiple second historical relative time data and multiple second data numbers corresponding to the multiple second historical relative time data, are determined as the target sequence data.

[0073] As can be seen from the embodiments of this application, the time prediction model is trained based on the first historical relative time and the second historical relative time data, which can enrich the training data and improve the prediction accuracy of the time prediction model.

[0074] In the embodiments of this application, the multiple historical relative time data used to train the time prediction model can be the relative time data used when the vehicle underwent its first software upgrade, the relative time data used when the vehicle underwent its second software upgrade, or a combination of the relative time data used when the vehicle underwent two previous upgrades. Thus, a large amount of training data can be recorded for training the time prediction model, and the selection of training data is very flexible. The trained time prediction model can not only greatly improve the accuracy of predicting software upgrade time, but also predict more accurate software upgrade time based on different types of software upgrades.

[0075] For ease of understanding, several examples are given below in conjunction with the accompanying drawings. It should be understood that the following embodiments are only one implementation of this application, and this application is not limited to the following implementation.

[0076] Figure 2A schematic diagram of fitting based on multiple first historical relative time data is shown in an embodiment of this application.

[0077] like Figure 2 As shown, multiple first historical relative time data and multiple first data numbers corresponding to the multiple first historical relative time data are identified as target sequence data, so as to perform the first data fitting to obtain the fitted line.

[0078] For example, the Y-axis of the Cartesian coordinate system represents relative time data, which includes multiple first historical relative time data required for the first software upgrade of the vehicle terminal. The X-axis of the Cartesian coordinate system represents multiple first data numbers corresponding to the multiple first historical relative time data. The multiple first data numbers are associated with the vehicle terminal. For example, the multiple first data numbers represent the number of vehicle terminals, with 1 representing the first vehicle terminal, 2 representing the second vehicle terminal, ..., and 17 representing the seventeenth vehicle terminal.

[0079] Multiple first historical time data can be denoted as T1.1, T1.2, T1.3 to T1.N. Figure 2 Taking N=17 as an example, multiple historical relative time data can be calculated using the following formula: Historical relative time data = upgrade time / software package size, where upgrade time is the time required for the first software upgrade on the vehicle side, expressed in seconds (S), and software package size is the software size of the first software upgrade on the vehicle side, expressed in megabytes (M). The multiple historical relative time data calculated in this way include multiple first historical relative times required for the first software upgrade on the vehicle side, expressed in megabytes per second (S / M).

[0080] Multiple first historical relative time data and multiple first data numbers are identified as target sequence data. Data fitting is then performed based on the identified target sequence data to obtain, as shown below. Figure 2 The fitted line shown represents the time prediction model. After fitting the time prediction model, the target data number can be input into the model, and the target relative time data will be output. For example, if the target data number specified by the rule based on the first data number is "18", the target data number "18" is input as the value of X into the fitted line, and the value of Y is output. The value of Y is represented as T1, for example, and T1 is the predicted target relative time data. It can be seen that the time prediction model can predict the relative time T1 of the next (e.g., the second) software upgrade. Then, by multiplying the predicted relative time T1 of the next software upgrade by the software package size of the next software upgrade, the time required for the next software upgrade can be predicted.

[0081] In the embodiments of this application, a time prediction model is trained based on multiple first historical relative time data, which can reduce training complexity and improve training speed. The trained time prediction model can obtain the predicted relative time data by inputting the target data number. The overall operation of predicting software upgrade time is relatively simple and has strong applicability in daily production.

[0082] The following describes three examples of obtaining target sequence data based on multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers. These three examples are, for instance, data fitting performed after a second software upgrade. Figure 3 One example is shown. Figure 4 The second example is shown, and the third example can be obtained by improving the second example.

[0083] Figure 3 A schematic diagram of data fitting based on the second OTA upgrade is shown in an embodiment of this application.

[0084] exist Figure 2 Based on reference Figure 3 As shown, historical relative time data is predicted based on multiple first historical relative time data and multiple first data numbers; the predicted historical relative time data, the data numbers corresponding to the predicted historical relative time data, multiple second historical relative time data, and multiple second data numbers are determined as target sequence data.

[0085] For example, after the first software upgrade on the vehicle, multiple first historical relative time data are obtained. Based on these first historical relative time data and multiple first data numbers, target sequence data is determined. Then, the target sequence data undergoes a first data processing step to obtain a time prediction model. This model is used to predict the relative time data required for the next upgrade, and this predicted relative time data is used as the predicted historical relative time data. After the second software upgrade on the vehicle, multiple second historical relative time data are obtained. Next, the predicted historical relative time data, the corresponding data numbers, the multiple second historical relative time data, and the multiple second data numbers are determined as the target sequence data required for the second data processing step. Based on this target sequence data, a second data processing step is performed to obtain a time prediction model trained using the relative time data required for the second software upgrade. This model is then used to predict the time required for a third software upgrade on the vehicle in the future.

[0086] For example, in Figure 3In this Cartesian coordinate system, the Y-axis represents relative time data, and the X-axis represents multiple data numbers corresponding to the relative time data. The relative time data includes predicted historical relative time data and multiple second historical relative time data points required for the vehicle's second software upgrade. The predicted historical relative time data is derived from multiple first historical relative time data points required for the vehicle's first software upgrade. The multiple data numbers include data numbers corresponding to the predicted historical relative time data and multiple second data numbers corresponding to the multiple second historical relative time data points.

[0087] Multiple second historical relative time data can be denoted as T2.1, T2.2, T2.3 to T2.N. Figure 3 Taking N=17 as an example, the historical relative time data obtained from the first prediction based on the first historical relative time data is denoted as T1. The predicted historical relative time data T1, the data number corresponding to the predicted historical relative time data T1, multiple second historical relative time data, and multiple second data numbers are determined as the target sequence data. For example, the data number corresponding to the predicted historical relative time data T1 is... Figure 3 N' on the horizontal axis shown Figure 3 It can be in Figure 2 Based on the relative time required for the next (e.g., the second) software upgrade, the time prediction model is trained using this data to obtain a fitted line. This is based on certain preset rules, such as the first and second software upgrades being of the same type or at the same stage. Figure 3 The fitted line shown can continue to use the previous prediction result. Figure 2 Data number 18 in the data can be converted to N'.

[0088] Based on the determined target sequence data, data fitting is performed to obtain, as follows: Figure 3 The fitted line shown is used to define the time prediction model. After obtaining the time prediction model, the target data number (e.g., "18") can be input as the value of X into the time prediction model. The time prediction model can predict the target relative time T2 (the value of Y) for the next software upgrade (e.g., the third one). Then, based on the predicted relative time T2 for the next software upgrade multiplied by the package size for the next software upgrade, the time required for the next software upgrade can be predicted.

[0089] Figure 4 A schematic diagram of data fitting based on a second OTA upgrade is shown in another embodiment of this application.

[0090] exist Figure 2 and Figure 3 Based on, refer to Figure 4 The second example shown, which involves data fitting after a second software upgrade, obtains target sequence data based on multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers. This includes: predicting historical relative time data based on multiple first historical relative time data and multiple first data numbers; and determining the multiple first historical relative time data, multiple first data numbers, predicted historical relative time data, data numbers corresponding to the predicted historical relative time data, multiple second historical relative time data, and multiple second data numbers as the target sequence data.

[0091] For example, after the first software upgrade on the vehicle, multiple first historical relative time data are obtained. Based on these first historical relative time data and multiple first data numbers, target sequence data is determined. Then, the target sequence data undergoes a first data processing step to obtain a time prediction model. This model is used to predict the relative time data required for the next upgrade, and this predicted relative time data is used as the predicted historical relative time data. After the second software upgrade on the vehicle, multiple second historical relative time data are obtained. Next, the multiple first historical relative time data, multiple first data numbers, the predicted historical relative time data, the data numbers corresponding to the predicted historical relative time data, the multiple second historical relative time data, and the multiple second data numbers are determined as the target sequence data. Data processing is performed on the target sequence data to obtain a time prediction model trained using the relative time data required for the first and second software upgrades and the predicted relative time data required for the software upgrade. This time prediction model can predict the time required for a third software upgrade on the vehicle in the future.

[0092] For example, in Figure 4 In this Cartesian coordinate system, the Y-axis represents the relative time data required for the first and second software upgrades, as well as the predicted relative time data required for the software upgrade. The X-axis represents the data number corresponding to the aforementioned relative time data. Multiple second historical relative time data can be denoted as T2.1, T2.2, T2.3, up to T2.N. Figure 4 Taking N=17 as an example, the data numbers can be set from 1 to 17, corresponding one-to-one with the multiple second historical relative time data mentioned above. The predicted historical relative time data obtained from the first prediction based on the first historical relative time data can be denoted as T1, and the data number corresponding to the predicted historical relative time data can be denoted as N'. Based on the determined multiple first historical relative time data, multiple first data numbers, predicted historical relative time data, data numbers corresponding to the predicted historical relative time data, multiple second historical relative time data, and multiple second data numbers, the target sequence data is determined.

[0093] Based on the determined target sequence data, data fitting is performed to obtain, as follows: Figure 4 The fitted line shown is used to define the time prediction model. After obtaining the time prediction model, the target data number (e.g., "18") can be input as the value of X into the time prediction model. The time prediction model can predict the target relative time T2 (the value of Y) for the next software upgrade (e.g., the third one). Then, based on the predicted relative time T2 for the next software upgrade multiplied by the package size for the next software upgrade, the time required for the next software upgrade can be predicted.

[0094] For example, after a vehicle completes its third, fourth, or even more software upgrades, a time prediction model can be obtained by fitting the relative time data required for multiple software upgrades, the data numbers corresponding to the relative time data required for multiple software upgrades, the predicted relative time data required for the software upgrades, and the data numbers corresponding to the predicted relative time data required for the software upgrades. As the vehicle undergoes multiple upgrades, the amount of data used for data fitting gradually increases, improving the sample size of the time prediction model and making the prediction of software upgrade times more accurate.

[0095] For example, software upgrades may have multiple phases depending on different annual plans or project plans. For instance, software upgrades could be divided into four phases based on time: Phase 1, Phase 2, Phase 3, and Phase 4. After the Phase 1 software upgrade is completed, a Phase 1 time prediction model can be obtained based on the relative time data and corresponding data numbers required for the Phase 1 upgrade. In Phase 2, this Phase 1 time prediction model can be used to predict the time required for the Phase 2 upgrade. In Phase 3, the Phase 1 time prediction model can be used to predict the time required for the Phase 3 upgrade, or a Phase 2 time prediction model can be obtained based on the predicted time required for the next software upgrade in Phase 1 and the relative time data and corresponding data numbers required for the Phase 2 upgrade. The same logic applies to Phase 4. The Phase 1 time prediction model can be used to predict the time required for the Phase 4 upgrade, or the Phase 2 time prediction model can be used to predict the time required for the Phase 4 upgrade, or a Phase 3 time prediction model can be obtained based on the predicted time required for the next software upgrade in Phase 2 and the relative time data and corresponding data numbers required for the Phase 3 upgrade. The method for combining historical relative time data to obtain time prediction models trained from different data sets can be determined based on the purpose or content of software upgrades at different stages.

[0096] As can be seen from the embodiments of this application, when training is performed based on first historical relative time and second historical relative time data, a first data fitting can be performed based on the target sequence data obtained from multiple first historical relative time data to obtain the predicted historical relative time data. Then, a second data fitting is performed based on the target sequence data obtained from the predicted historical relative time data and the second historical relative time data. The second data fitting process not only refers to the original multiple first historical relative time data, but also refers to the result of the first data fitting (the predicted historical relative time data). The second data fitting is performed based on rich training data (the predicted historical relative time data, the first historical relative time data, and the second historical relative time data), which greatly improves the fitting accuracy and thus improves the prediction accuracy.

[0097] For example, in Figure 4 Another example can be obtained by improving upon the example shown, in which the target sequence data is removed. Figure 4 The example shows the predicted relative time data T1. In this example, multiple first historical relative time data, multiple first data numbers, multiple second historical relative time data, and multiple second data numbers are identified as the target sequence data.

[0098] As can be seen from the embodiments of this application, when training is performed based on the first historical relative time and the second historical relative time data, the first data fitting can be performed based on the first historical relative time data. In the second data fitting, the target sequence data can be obtained directly based on the original first historical relative time data and the original second historical relative time data. This not only improves the richness of the target sequence data, but also avoids additional data errors due to the original first historical relative time data and the original second historical relative time data, thereby improving the fitting accuracy to a certain extent and thus improving the prediction accuracy.

[0099] It is worth noting that the time prediction model in this application can also be an artificial intelligence model, a fitted curve, etc., and the data processing methods also include model modeling, model training, data fitting, etc. The fitted straight line mentioned above is only an example of one solution in this application and should not be taken as the only solution in this application.

[0100] Figure 5 This is a flowchart illustrating the vehicle-side software upgrade display method provided in an embodiment of this application.

[0101] like Figure 5 As shown, the vehicle-side software upgrade display method 500 provided in this application embodiment includes, for example, steps S510-S530.

[0102] Step S510: Receive the target relative time data required for the vehicle-side software upgrade, wherein the target relative time data is obtained according to any of the methods described above.

[0103] Step S520: Determine the time required for the software upgrade based on the target relative time data and the software data size.

[0104] In some embodiments, the time required for a software upgrade can be calculated using the formula: Time required for software upgrade = Target relative data * Software data size.

[0105] Step S530: During the software upgrade process, the time required for the software upgrade is displayed.

[0106] In some embodiments, the time required for a software upgrade can be displayed on the vehicle-mounted display screen using a progress bar or percentage.

[0107] In the embodiments of this application, the received target relative time data can display the time required for software upgrade, improving the accuracy of software upgrade time display and thus enhancing the user experience.

[0108] Figure 6 This is a schematic diagram of the OTA flashing process provided in an embodiment of this application.

[0109] like Figure 6 As shown, when the vehicle is undergoing an OTA upgrade, the vehicle first establishes a connection with the cloud via a cellular network. The cloud server transmits the electronic control unit upgrade package to be updated to the vehicle. The OTA controller on the vehicle then distributes the electronic control unit upgrade package to the corresponding electronic control unit and performs the flashing operation.

[0110] During the first OTA update on the vehicle, the vehicle uploads the relative time data used for this OTA update to the cloud server. The cloud server collects the relative time data used for all OTA updates on all vehicles during this update, processes the data, obtains a fitted curve, and then predicts the relative time data for the next OTA update. During the second OTA update, the predicted relative time data for the next OTA update is multiplied by the software package size to predict the time required for this update. Similarly, the cloud server collects the relative time used for all OTA updates on all vehicles during the second OTA update, processes the data, obtains a fitted curve, and then predicts the relative time data for the next OTA update. This process continues, and after multiple OTA updates, the time prediction model learns and trains based on a large amount of recorded test data, thus enabling it to predict relatively accurate times.

[0111] This application provides a software upgrade time prediction device 700. Please refer to [link to relevant documentation]. Figure 7 The software upgrade time prediction device 700 includes:

[0112] The acquisition module 710 is used to acquire multiple historical relative time data, wherein each historical relative time data represents the relationship between the time required for the vehicle to perform a software upgrade and the size of the software data.

[0113] The first acquisition module 720 is used to obtain target sequence data based on multiple historical relative time data and multiple data numbers corresponding to the multiple historical relative time data.

[0114] The second acquisition module 730 is used to perform data processing based on the target sequence data to obtain a time prediction model;

[0115] Prediction module 740 is used to predict the target relative time data required for vehicle-side software upgrades based on the target data number using a time prediction model;

[0116] The sending module 750 is used to send the target relative time data to the vehicle terminal so that the vehicle terminal can determine the time required for software upgrade based on the target relative time data and the size of the software data.

[0117] It is understood that for a detailed description of the software upgrade time prediction device 700, please refer to the description of the software upgrade time prediction method above.

[0118] This application provides a vehicle-mounted software upgrade display device 800. Please refer to [link to relevant documentation]. Figure 8 The vehicle-mounted software upgrade display device 800 includes:

[0119] The receiving module 810 is used to receive the target relative time data required for the vehicle to perform software upgrades, wherein the target relative time data is obtained based on the software upgrade time prediction device mentioned above.

[0120] The determination module 820 is used to determine the time required for software upgrades based on target relative time data and software data size.

[0121] Display module 830 is used to display the time required for software upgrade during the software upgrade process.

[0122] It is understood that for a detailed description of the vehicle-side software upgrade display device 800, please refer to the description of the vehicle-side software upgrade display method above.

[0123] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method in any of the above embodiments.

[0124] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0125] One embodiment of this application provides a computer program product including instructions that, when executed by a processor of a computer device, enable the computer device to perform the steps of the method described in any of the above embodiments.

[0126] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this application, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0127] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for predicting software upgrade time, characterized in that, The method includes: Acquire multiple historical relative time data, where each historical relative time data represents the relationship between the time required for the vehicle to perform a software upgrade and the size of the software data; Based on the multiple historical relative time data and the multiple data numbers corresponding to the multiple historical relative time data, the target sequence data is obtained; Based on the target sequence data, a time prediction model is obtained through data processing. The time prediction model is used to predict the target relative time data required for vehicle-side software upgrades based on the target data number. The target relative time data is sent to the vehicle terminal so that the vehicle terminal can determine the time required for software upgrade based on the target relative time data and the software data size.

2. The method according to claim 1, characterized in that, The process of processing the target sequence data to obtain a time prediction model includes: The target sequence data is fitted to obtain a fitted line, wherein the fitted line represents the relationship between data number and relative time data, wherein when the multiple historical relative time data come from multiple vehicle terminals, the multiple data numbers correspond one-to-one with the multiple vehicle terminals; The fitted line is determined as the time prediction model.

3. The method according to claim 1 or 2, characterized in that, The plurality of historical relative time data includes at least one of a plurality of first historical relative time data and a plurality of second historical relative time data; the plurality of first historical relative time data is the relative time required for the first software upgrade on the vehicle side, the plurality of second historical relative time data is the relative time required for the second software upgrade on the vehicle side, and the plurality of data numbers includes a plurality of first data numbers and a plurality of second data numbers, the plurality of first data numbers corresponding to the plurality of first historical relative time data, and the plurality of second data numbers corresponding to the plurality of second historical relative time data; The step of obtaining the target sequence data based on the plurality of historical relative time data and the plurality of data numbers corresponding to the plurality of historical relative time data includes: The plurality of first historical relative time data and the plurality of first data numbers are determined as the target sequence data; or The target sequence data is obtained based on the plurality of first historical relative time data, the plurality of first data numbers, the plurality of second historical relative time data, and the plurality of second data numbers.

4. The method according to claim 3, characterized in that, The process of obtaining the target sequence data based on the plurality of first historical relative time data, the plurality of first data numbers, the plurality of second historical relative time data, and the plurality of second data numbers includes: Based on the plurality of first historical relative time data and the plurality of first data numbers, historical relative time data is predicted; The predicted historical relative time data, the data number corresponding to the predicted historical relative time data, the plurality of second historical relative time data, and the plurality of second data numbers are determined as the target sequence data.

5. The method according to claim 3 or 4, characterized in that, The process of obtaining the target sequence data based on the plurality of first historical relative time data, the plurality of first data numbers, the plurality of second historical relative time data, and the plurality of second data numbers includes: Based on the plurality of first historical relative time data and the plurality of first data numbers, historical relative time data is predicted; The target sequence data is determined by taking multiple first historical relative time data, the multiple first data numbers, the predicted historical relative time data, the data numbers corresponding to the predicted historical relative time data, the multiple second historical relative time data, and the multiple second data numbers.

6. The method according to any one of claims 3-5, characterized in that, The process of obtaining the target sequence data based on the plurality of first historical relative time data, the plurality of first data numbers, the plurality of second historical relative time data, and the plurality of second data numbers includes: The plurality of first historical relative time data, the plurality of first data numbers, the plurality of second historical relative time data, and the plurality of second data numbers are determined as the target sequence data.

7. A method for displaying software upgrades on a vehicle-side device, characterized in that, The method includes: The system receives target relative time data required for software upgrades on the receiving end, wherein the target relative time data is obtained according to the method of any one of claims 1-6; Based on the target relative time data and the software data size, determine the time required for the software upgrade; During the software upgrade process, the time required for the upgrade is displayed.

8. A cloud platform, characterized in that, The cloud platform is capable of executing the steps of the method according to any one of claims 1-6.

9. A vehicle end, characterized in that, The vehicle end is capable of performing the steps of the method described in claim 7.

10. A device for predicting software upgrade time, characterized in that, The device includes: The acquisition module is used to acquire multiple historical relative time data, where each historical relative time data represents the relationship between the time required for the vehicle to perform a software upgrade and the size of the software data. The first obtaining module is used to obtain target sequence data based on the plurality of historical relative time data and the plurality of data numbers corresponding to the plurality of historical relative time data; The second acquisition module is used to perform data processing based on the target sequence data to obtain a time prediction model; The prediction module is used to use the time prediction model to predict the target relative time data required for the vehicle-side software upgrade based on the target data number. The sending module is used to send the target relative time data to the vehicle terminal, so that the vehicle terminal can determine the time required for software upgrade based on the target relative time data and the software data size.

11. A vehicle-mounted software upgrade display device, characterized in that, The device includes: A receiving module is used to receive target relative time data required for software upgrades on the vehicle end, wherein the target relative time data is obtained according to the apparatus of claim 10; The determination module is used to determine the time required for the software upgrade based on the target relative time data and the software data size; The display module is used to show the time required for the software upgrade process.

12. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images