A control method and system for vehicle OTA security upgrade

Abstract

The application provides a kind of vehicle OTA security upgrade control method, it includes the following steps: step S10, periodically obtains the network parameter in current OTA upgrade;Step S11, network parameter is input to a trained time series model based on deep learning, obtain the OTA transceiver packet threshold prediction value after fixed time;Step S12, obtain the confidence of current time;Step S13, according to the confidence, adjust the current OTA transceiver packet threshold;Step S14, using the adjusted OTA transceiver packet threshold continues to carry out OTA security upgrade.The application also provides a corresponding system.Implementation of the application can be dynamically adjusted in the upgrading process, the efficiency of OTA upgrade is optimized, and the success rate of OTA upgrade is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of OTA upgrade, in particular to a control method and system for vehicle OTA safe upgrade. BACKGROUND

[0002] In some vehicles using intelligent software, the software or system is generally upgraded through a fixed OTA strategy. If the network is not smooth, it is upgraded through a "breakpoint resume" and the like. After the firmware is downloaded, the integrity is verified through a verification code.

[0003] In the existing OTA upgrade strategy, it is greatly affected by the network. For example, in some places with poor network, especially unmanned platforms such as intelligent small cars, which are more seriously affected by the network, the use of the existing OTA upgrade method usually leads to OTA upgrade discontinuity, and even some upgrade failure problems, which affect the safety of the vehicle. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a control method and system for vehicle OTA safe upgrade, which can dynamically adjust the OTA transceiving packet according to the implementation, optimize the efficiency of OTA upgrade, and improve the success rate of OTA upgrade.

[0005] To solve the above technical problems, as one aspect of the present application, a control method for vehicle OTA safe upgrade is provided, which comprises the following steps:

[0006] Step S10, periodically acquiring current network parameters in OTA upgrade, wherein the network parameters at least include: current time, network rate, network signal strength, network packet loss rate and current OTA transceiving packet threshold;

[0007] Step S11, inputting the network parameters into a trained deep learning-based time series model to obtain an OTA transceiving packet threshold prediction value after a fixed time;

[0008] Step S12, obtaining a confidence degree of the current time according to the historical network parameters in a predetermined time period before the current time and the OTA transceiving packet threshold prediction value corresponding to the historical time;

[0009] Step S13, adjusting the current OTA transceiving packet threshold according to the confidence degree and the OTA transceiving packet threshold prediction value after the fixed time;

[0010] Step S14, continuing the OTA safe upgrade by using the adjusted OTA transceiving packet threshold.

[0011] Further comprising the following steps:

[0012] Pre-collect network parameters during the OTA upgrade process over a period of time to form a training set;

[0013] A deep learning-based time series model is trained using the training set to obtain a trained deep learning-based time series model, which includes an input layer, multiple fully connected layers, and an output layer.

[0014] Step S12 further includes:

[0015] Step S120: Calculate the threshold error value MAPE at each time step according to the following formula:

[0016]

[0017] Where H is the total number of historical moments in the predetermined time period preceding each moment to be calculated, and y i The OTA packet sending and receiving thresholds corresponding to historical moments within the predetermined time period; The predicted OTA packet sending and receiving thresholds corresponding to historical moments within a predetermined time period;

[0018] Step S121: Obtain the threshold error values ​​corresponding to the two time points preceding the current time, and calculate the confidence level at the current time using the following formula:

[0019] TRUST=(MAPE(T-1)+MAPE(T-2)) / 2

[0020] Where MAPE(T-1) is the threshold error value corresponding to the previous time step of the current time step, and MAPE(T-2) is the threshold error value corresponding to the two time steps of the current time step.

[0021] Step S13 further includes:

[0022] Based on the confidence level at the current moment, and according to the pre-defined mapping relationship between the confidence level and the weight value, the weight value corresponding to the current confidence level is obtained;

[0023] The current OTA packet sending and receiving threshold is adjusted based on the predicted value of the OTA packet sending and receiving threshold after the fixed time and in combination with the weight value.

[0024] In step S13, the current OTA packet sending and receiving thresholds are adjusted using the following formula:

[0025] BS(new) = BS_P*W + BS*(1-W);

[0026] Wherein, BS(new) is the adjusted OTA transceiving packet threshold value, BS_P is the OTA transceiving packet threshold value prediction value after a fixed time, W is the weight value corresponding to the current confidence, and BS is the current OTA transceiving packet threshold value.

[0027] Wherein, in the step S13, the mapping relationship between the confidence and the weight value is specifically:

[0028] When the confidence is greater than or equal to 100, the weight value is 100%;

[0029] When the confidence is greater than or equal to 90 and less than 100, the weight value is 90%;

[0030] When the confidence is greater than or equal to 70 and less than 90, the weight value is 65%;

[0031] When the confidence is greater than or equal to 50 and less than 70, the weight value is 50%;

[0032] When the confidence is less than 50, the weight value is 0%.

[0033] Correspondingly, another aspect of the present application also provides a vehicle OTA safety upgrade control system, which comprises:

[0034] a network parameter acquisition unit, configured to periodically acquire current network parameters in OTA upgrade, wherein the network parameters at least include: current time, network rate, network signal strength, network packet loss rate and current OTA transceiving packet threshold value;

[0035] a transceiving packet threshold value prediction unit, configured to input the network parameters into a trained deep learning-based time series model to obtain an OTA transceiving packet threshold value prediction value after a fixed time;

[0036] a confidence acquisition unit, configured to obtain a confidence of a current time according to historical network parameters in a predetermined time period before the current time and a corresponding OTA transceiving packet threshold value prediction value of a historical time;

[0037] a transceiving packet threshold value adjustment unit, configured to adjust the current OTA transceiving packet threshold value according to the confidence and the OTA transceiving packet threshold value prediction value after the fixed time;

[0038] an upgrade processing unit, configured to continue OTA safety upgrade by using the adjusted OTA transceiving packet threshold value.

[0039] Wherein, the confidence acquisition unit further comprises:

[0040] an error value calculation unit, configured to calculate a threshold error value MAPE of each time according to the following formula:

[0041]

[0042] wherein, H is the total number of historical time points in a predetermined time period before each time point to be calculated, y i is the OTA transceiving packet threshold value corresponding to the historical time point in the predetermined time period; is the predicted OTA transceiving packet threshold value corresponding to the historical time point in the predetermined time period;

[0043] a confidence degree calculation unit, configured to obtain the threshold error values corresponding to two time points before the current time point, and calculate the confidence degree of the current time point by the following formula:

[0044] TRUST = (MAPE(T-1) + MAPE(T-2)) / 2

[0045] wherein, MAPE(T-1) is the threshold error value corresponding to the time point before the current time point, and MAPE(T-2) is the threshold error value corresponding to the time point before the time point before the current time point.

[0046] wherein, the transceiving packet threshold value adjustment unit further comprises:

[0047] a weight value obtaining unit, configured to obtain the weight value corresponding to the current confidence degree according to the mapping relationship between the confidence degree and the weight value pre-calibrated according to the confidence degree of the current time point;

[0048] an adjustment unit, configured to adjust the current OTA transceiving packet threshold value according to the OTA transceiving packet threshold value prediction value after the fixed time point and in combination with the weight value by the following formula:

[0049] BS(new) = BS_P*W + BS*(1-W);

[0050] wherein, BS(new) is the adjusted OTA transceiving packet threshold value, BS_P is the OTA transceiving packet threshold value prediction value after the fixed time point, W is the weight value corresponding to the current confidence degree, and BS is the current OTA transceiving packet threshold value.

[0051] wherein, the mapping relationship between the confidence degree and the weight value is specifically:

[0052] when the confidence degree is greater than or equal to 100, the weight value is 100%;

[0053] when the confidence degree is greater than or equal to 90 and less than 100, the weight value is 90%;

[0054] when the confidence degree is greater than or equal to 70 and less than 90, the weight value is 65%;

[0055] When the confidence is greater than or equal to 50 and less than 70, the weight value is 50%;

[0056] When the confidence is less than 50, the weight value is 0%.

[0057] The embodiment of the present application has the following beneficial effects:

[0058] The present application provides a kind of vehicle OTA safety upgrade control method and system. By periodically obtaining the network parameter in current OTA upgrade;The network parameter is input to a trained depth learning-based time series model, obtains the OTA transceiver packet threshold prediction value after fixed time;And obtain the confidence of current time;According to the confidence, current OTA transceiver packet threshold is adjusted. Wherein, the adjustment of OTA parameter is adjusted based on time series, and each adjustment is based on previous running result to predict, realizes the dynamic adjustment of OTA upgrade parameter.

[0059] Meanwhile, using confidence and weight calculation, OTA upgrade efficiency can be optimized, packet loss and other phenomena are reduced, OTA upgrade success rate is improved, advantage resources of OTA network are maximized to the greatest extent, especially applicable to poor network environment place, for example, it can be applied to intelligent small car and other unmanned driving platforms that can be seriously affected by network. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings obtained according to these drawings without creative labor are still within the scope of the present application.

[0061] Figure 1 The main flowchart of an embodiment of a vehicle OTA safety upgrade control method provided by the present application is shown in the figure.

[0062] Figure 2 The structure diagram of an embodiment of a vehicle OTA safety upgrade control system provided by the present application is shown in the figure.

[0063] Figure 3 For Figure 2 The structure diagram of the confidence obtaining unit is shown in the figure.

[0064] Figure 4 For Figure 2 The structure diagram of the transceiver packet threshold adjustment unit is shown in the figure. DETAILED DESCRIPTION

[0065] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings.

[0066] As shown in Figure 1 Fig. 1 shows a main flowchart of a vehicle OTA security upgrade control method provided by the present application. In the present embodiment, the vehicle can be a car, an electric vehicle or a logistics trolley with intelligent software, and the vehicle OTA security upgrade control method comprises the following steps:

[0067] Step S10, periodically obtaining current network parameters in OTA upgrade, wherein the network parameters at least include: current time, network rate, network signal strength, network packet loss rate and current OTA transceiving packet threshold;

[0068] Step S11, inputting the network parameters into a trained deep learning based time series model to obtain an OTA transceiving packet threshold prediction value after a fixed time;

[0069] It can be understood that in the method provided by the present application, the step of obtaining a trained deep learning based time series model in advance further comprises the following steps:

[0070] Pre-collecting network parameters in the OTA upgrade process within a period of time to form a training set;

[0071] Training a deep learning based time series model through the training set to obtain a trained deep learning based time series model, wherein the deep learning based time series model comprises an input layer, a plurality of fully connected layers and an output layer.

[0072] It can be understood that in the present embodiment, the prediction of the OTA transceiving packet threshold is actually the prediction of a single variable. For the point prediction problem of a single variable discrete time series, it can be abstracted as a time series: v1, v2, v3,..., vi,..., vT

[0073] Suppose we want to predict the value after H time points. For example, for the OTA transceiving packet threshold, we want to predict the size at the next time point, so H = 2, and the result we want to predict is:

[0074]

[0075] In the embodiment, only the variable value at time T after the current time needs to be predicted, so a forward prediction method can be adopted to achieve the prediction by a time series model based on deep learning. For example, a model having an input layer, four fully connected layers, and an output layer can be adopted, and an activation function ReLU() can be adopted in each fully connected layer. As for more specific content of the activation function, a known technique in the art can be adopted.

[0076] At step S12, the confidence at the current time is obtained according to historical network parameters in a predetermined time period before the current time and OTA threshold prediction values corresponding to historical times.

[0077] The step S12 further includes:

[0078] At step S120, the threshold error value MAPE at each time is calculated according to the following formula:

[0079]

[0080] wherein H is the total number of historical times in a predetermined time period before each time to be calculated, y i is the OTA threshold corresponding to the historical times in the predetermined time period; is the predicted OTA threshold corresponding to the historical times in the predetermined time period;

[0081] At step S121, the threshold error values corresponding to two times before the current time are obtained, and the confidence at the current time is calculated according to the following formula:

[0082] TRUST = (MAPE(T-1) + MAPE(T-2)) / 2

[0083] wherein MAPE(T-1) is the threshold error value corresponding to the time before the current time, and MAPE(T-2) is the threshold error value corresponding to the time before the time before the current time.

[0084] At step S13, the current OTA threshold is adjusted according to the confidence and the OTA threshold prediction value after the fixed time.

[0085] The step S13 further includes:

[0086] According to the confidence at the current time, a mapping relationship between the confidence and the weight value is obtained, and the weight value corresponding to the current confidence is obtained.

[0087] According to the OTA transceiving packet threshold prediction value after the fixed time and in combination with the weight value, the current OTA transceiving packet threshold is adjusted, and specifically, the adjusted OTA transceiving packet threshold can be set in real time through a curl command or the like.

[0088] In the step S13, the current OTA transceiving packet threshold is adjusted by using the following formula:

[0089] BS(new) = BS_P * W + BS * (1-W);

[0090] wherein, BS(new) is the adjusted OTA transceiving packet threshold, BS_P is the OTA transceiving packet threshold prediction value after the fixed time, W is the weight value corresponding to the current confidence degree, and BS is the current OTA transceiving packet threshold.

[0091] In a specific example, in the step S13, the mapping relationship between the confidence degree and the weight value is specifically as follows:

[0092] When the confidence degree is greater than or equal to 100, the weight value is 100%;

[0093] When the confidence degree is greater than or equal to 90 and less than 100, the weight value is 90%;

[0094] When the confidence degree is greater than or equal to 70 and less than 90, the weight value is 65%;

[0095] When the confidence degree is greater than or equal to 50 and less than 70, the weight value is 50%;

[0096] When the confidence degree is less than 50, the weight value is 0%.

[0097] It can be understood that, through the above mapping relationship, when the weight value is 100%, the current OTA transceiving packet threshold is adjusted by the OTA transceiving packet threshold prediction value after the fixed time; when the weight value is 0%, the current OTA transceiving packet threshold remains unchanged; and between the two weight values, the current OTA transceiving packet threshold needs to be adjusted in combination with the OTA transceiving packet threshold prediction value after the fixed time and the current OTA transceiving packet threshold. Therefore, the above method combines the ideas of dynamic adjustment and static adjustment.

[0098] In the step S14, the OTA security upgrade is continued by using the adjusted OTA transceiving packet threshold.

[0099] As shown in FIG. 1, an embodiment of a control system for vehicle OTA security upgrade is shown. Figure 2 As shown in FIG. 1, an embodiment of a control system for vehicle OTA security upgrade is shown.

[0100] The network parameter acquisition unit 10 is used to periodically acquire the current network parameters during OTA upgrade. The network parameters include at least: current time, network speed, network signal strength, network packet loss rate, and current OTA packet sending and receiving threshold.

[0101] The packet sending and receiving threshold prediction unit 11 is used to input the network parameters into a pre-trained deep learning-based time series model to predict the OTA packet sending and receiving threshold value after a fixed time.

[0102] The confidence acquisition unit 12 is used to obtain the confidence level at the current moment based on the historical network parameters within a predetermined time period before the current moment and the corresponding OTA packet sending and receiving threshold prediction value at the historical moment.

[0103] The packet sending and receiving threshold adjustment unit 13 is used to adjust the current OTA packet sending and receiving threshold based on the confidence level and the predicted value of the OTA packet sending and receiving threshold after a fixed time.

[0104] The upgrade processing unit 14 is used to continue OTA security upgrades using the adjusted OTA packet sending and receiving thresholds.

[0105] like Figure 3 As shown, in a specific example, the confidence acquisition unit 12 further includes:

[0106] Error calculation unit 120 is used to calculate the threshold error value MAPE at each time step according to the following formula:

[0107]

[0108] Where H is the total number of historical moments in the predetermined time period preceding each moment to be calculated, and y i The OTA packet sending and receiving thresholds corresponding to historical moments within the predetermined time period; The predicted OTA packet sending and receiving thresholds corresponding to historical moments within a predetermined time period;

[0109] The confidence calculation unit 121 is used to obtain the threshold error values ​​corresponding to the two time points before the current time point, and calculate the confidence level at the current time point using the following formula:

[0110] TRUST=(MAPE(T-1)+MAPE(T-2)) / 2

[0111] Where MAPE(T-1) is the threshold error value corresponding to the previous time step of the current time step, and MAPE(T-2) is the threshold error value corresponding to the two time steps of the current time step.

[0112] like Figure 4As shown, in one specific example, the transceiving packet threshold adjustment unit 13 further comprises:

[0113] The weight value acquisition unit 130 is configured to acquire, according to the confidence degree of the current time, a weight value corresponding to the current confidence degree according to a mapping relationship between the confidence degree and the weight value pre-calibrated.

[0114] More specifically, in one example, the mapping relationship between the confidence degree and the weight value is specifically as follows:

[0115] When the confidence degree is greater than or equal to 100, the weight value is 100%;

[0116] When the confidence degree is greater than or equal to 90 and less than 100, the weight value is 90%;

[0117] When the confidence degree is greater than or equal to 70 and less than 90, the weight value is 65%;

[0118] When the confidence degree is greater than or equal to 50 and less than 70, the weight value is 50%;

[0119] When the confidence degree is less than 50, the weight value is 0%.

[0120] The adjustment unit 131 is configured to adjust the current OTA transceiving packet threshold according to the OTA transceiving packet threshold prediction value after the fixed time and in combination with the weight value according to the following formula:

[0121] BS(new) = BS_P * W + BS * (1-W);

[0122] Wherein, BS(new) is the adjusted OTA transceiving packet threshold, BS_P is the OTA transceiving packet threshold prediction value after the fixed time, W is the weight value corresponding to the current confidence degree, and BS is the current OTA transceiving packet threshold.

[0123] More details can be referred to and combined with the foregoing description of Figure 1 , which will not be described here in detail.

[0124] The implementation of the embodiment of the present application has the following beneficial effects:

[0125] The present application provides a kind of vehicle OTA safety upgrade control method and system. By periodically obtaining the network parameter in current OTA upgrade;The network parameter is input to a trained time series model based on deep learning, and the OTA transceiving packet threshold prediction value after fixed time is obtained;And obtain the confidence degree of current time;According to the confidence degree, the current OTA transceiving packet threshold is adjusted. Wherein, the adjustment of OTA parameter is adjusted based on time series, and each adjustment is based on previous running result to predict, realizes the dynamic adjustment of OTA upgrade parameter.

[0126] At the same time, the OTA upgrade efficiency can be optimized by using the confidence and weight calculation, the packet loss phenomenon is reduced, the OTA upgrade success rate is improved, the advantage resources of the OTA network are maximized, and the application is especially suitable for places with poor network environment, for example, the application can be applied to a smart car and other unmanned platforms that can be seriously affected by the network.

[0127] Those skilled in the art will appreciate that embodiments of the application can be provided as methods, apparatus, or computer program products. Accordingly, the application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer-readable program code.

[0128] The application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a means for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 Figure 1 The apparatus for performing the functions specified in a flow or multiple flows and / or blocks.

[0129] The above disclosure is only a preferred embodiment of the application, and of course cannot limit the scope of the application, so the equivalent changes made according to the claims of the application are still within the scope of the application.

Claims

1. A control method for vehicle OTA security upgrades, characterized in that, Includes the following steps: Step S10: Periodically acquire the current network parameters during OTA upgrade. The network parameters include at least: current time, network speed, network signal strength, network packet loss rate, and current OTA packet sending and receiving threshold. Step S11: Input the network parameters into a pre-trained deep learning-based time series model to obtain the predicted OTA packet sending and receiving threshold values ​​after a fixed time. Step S12: Obtain the confidence level at the current moment based on the historical network parameters within the predetermined time period before the current moment and the corresponding OTA packet sending and receiving threshold prediction values ​​at the historical moments. Step S13: Adjust the current OTA packet sending and receiving threshold based on the confidence level and the predicted value of the OTA packet sending and receiving threshold after the fixed time. Step S14: Continue OTA security upgrade using the adjusted OTA packet sending and receiving thresholds.

2. The method as described in claim 1, characterized in that, Further steps include the following: Pre-collect network parameters during the OTA upgrade process over a period of time to form a training set; A deep learning-based time series model is trained using the training set to obtain a trained deep learning-based time series model, which includes an input layer, multiple fully connected layers, and an output layer.

3. The method as described in claim 1 or 2, characterized in that, Step S12 further includes: Step S120: Calculate the OTA packet transmission and reception threshold error value MAPE at each time step according to the following formula: Where H is the total number of historical moments in the predetermined time period preceding each moment to be calculated, and y i The OTA packet sending and receiving thresholds corresponding to historical moments within the predetermined time period; The predicted OTA packet sending and receiving thresholds corresponding to historical moments within a predetermined time period; Step S121: Obtain the OTA packet transmission and reception threshold error values ​​corresponding to the two time points preceding the current time, and calculate the confidence level at the current time using the following formula: TRUST=(MAPE(T-1)+MAPE(T-2)) / 2 Where MAPE(T-1) is the OTA packet transmission and reception threshold error value corresponding to the previous time step of the current time step, and MAPE(T-2) is the OTA packet transmission and reception threshold error value corresponding to the two time steps of the current time step.

4. The method as described in claim 3, characterized in that, Step S13 further includes: Based on the confidence level at the current moment, and according to the pre-defined mapping relationship between the confidence level and the weight value, the weight value corresponding to the confidence level at the current moment is obtained. The current OTA packet sending and receiving threshold is adjusted based on the predicted value of the OTA packet sending and receiving threshold after the fixed time and in combination with the weight value.

5. The method as described in claim 4, characterized in that, In step S13, the current OTA packet sending and receiving thresholds are adjusted using the following formula: BS(new) = BS_P*W + BS*(1-W); Wherein, BS(new) is the adjusted OTA packet sending and receiving threshold, BS_P is the predicted value of the OTA packet sending and receiving threshold after a fixed time, W is the weight value corresponding to the confidence level at the current time, and BS is the current OTA packet sending and receiving threshold.

6. The method as described in claim 5, characterized in that, In step S13, the mapping relationship between the confidence level and the weight value is specifically as follows: When the confidence level is greater than or equal to 100, its weight value is 100%; When the confidence level is greater than or equal to 90 and less than 100, its weight value is 90%. When the confidence level is greater than or equal to 70 and less than 90, its weight value is 65%; When the confidence level is greater than or equal to 50 and less than 70, its weight value is 50%. When the confidence level is less than 50%, its weight is 0%.

7. A control system for vehicle OTA security upgrades, characterized in that, include: The network parameter acquisition unit is used to periodically acquire the current network parameters during OTA upgrades. The network parameters include at least: current time, network speed, network signal strength, network packet loss rate, and current OTA packet sending and receiving thresholds. The packet sending and receiving threshold prediction unit is used to input the network parameters into a pre-trained deep learning-based time series model to predict the OTA packet sending and receiving threshold values ​​at a fixed time. The confidence level acquisition unit is used to obtain the confidence level at the current moment based on the historical network parameters within a predetermined time period before the current moment and the corresponding OTA packet sending and receiving threshold prediction values ​​at the historical moments. The packet sending and receiving threshold adjustment unit is used to adjust the current OTA packet sending and receiving threshold based on the confidence level and the predicted value of the OTA packet sending and receiving threshold after a fixed time. An upgrade processing unit is used to continue OTA security upgrades using the adjusted OTA packet sending and receiving thresholds.

8. The system as claimed in claim 7, characterized in that, The confidence level acquisition unit further includes: The error value calculation unit is used to calculate the OTA packet transmission and reception threshold error value (MAPE) at each time step according to the following formula: Where H is the total number of historical moments in the predetermined time period preceding each moment to be calculated, and y i The OTA packet sending and receiving thresholds corresponding to historical moments within the predetermined time period; The predicted OTA packet sending and receiving thresholds corresponding to historical moments within a predetermined time period; The confidence calculation unit is used to obtain the OTA packet transmission and reception threshold error values ​​corresponding to the two time points preceding the current time, and calculate the confidence level at the current time using the following formula: TRUST=(MAPE(T-1)+MAPE(T-2)) / 2 Where MAPE(T-1) is the OTA packet transmission and reception threshold error value corresponding to the previous time step of the current time step, and MAPE(T-2) is the OTA packet transmission and reception threshold error value corresponding to the two time steps of the current time step.

9. The system as described in claim 8, characterized in that, The packet sending and receiving threshold adjustment unit further includes: The weight value acquisition unit is used to obtain the weight value corresponding to the confidence level at the current time based on the confidence level at the current time and according to the pre-defined mapping relationship between the confidence level and the weight value. The adjustment unit is used to adjust the current OTA packet transmission and reception threshold according to the predicted value of the OTA transmission and reception threshold after the fixed time, and in combination with the weight value, using the following formula: BS(new) = BS_P*W + BS*(1-W); Wherein, BS(new) is the adjusted OTA packet sending and receiving threshold, BS_P is the predicted value of the OTA packet sending and receiving threshold after a fixed time, W is the weight value corresponding to the confidence level at the current time, and BS is the current OTA packet sending and receiving threshold.

10. The system as described in claim 9, characterized in that, The mapping relationship between the confidence level and the weight value is as follows: When the confidence level is greater than or equal to 100, its weight value is 100%; When the confidence level is greater than or equal to 90 and less than 100, its weight value is 90%. When the confidence level is greater than or equal to 70 and less than 90, its weight value is 65%; When the confidence level is greater than or equal to 50 and less than 70, its weight value is 50%. When the confidence level is less than 50%, its weight is 0%.

Images