A risk detection method, device and electronic equipment based on onboard software

Abstract

The present specification discloses a risk detection method, device and electronic device based on onboard software, specifically including: determining the first round of abnormality assessment results based on the operating parameter data of the target application. According to the first round of abnormality assessment results, the monitoring strategy is adjusted at least once, and based on the adjusted monitoring strategy, the operating parameter data corresponding to the target application is obtained, so as to determine the abnormality assessment results corresponding to each adjustment round. According to the first round of abnormality assessment results and the abnormality assessment results corresponding to at least one round of adjustment, the operation process of the target application is risk detected. Through the method of the present specification, a more suitable and accurate monitoring strategy can be selected when facing different abnormal problems, so as to ensure that the abnormality is discovered and handled before a serious fault occurs as much as possible, effectively improving the efficiency of repairing abnormal problems of onboard software and the accuracy of abnormality detection, while also greatly ensuring the stability of the satellite system in the ever-changing space.

Description

Technical Field

[0001] This specification relates to the field of satellite aerospace, and in particular to a risk detection method, device and electronic equipment based on satellite-borne software. Background Art

[0002] With the continuous development and progress of science and technology, satellite aerospace technology in the aerospace field has become more and more mature. By applying appropriate onboard software in satellite systems, many aerospace missions can be achieved, such as information exchange with the ground, data monitoring and collection in space, etc.

[0003] With the current technology, various situations and sudden changes in the space environment are difficult to predict, which can easily affect the normal operation of the satellite's onboard software. Therefore, it is very important to effectively monitor whether there are risky abnormalities when the onboard software is working.

[0004] At present, most traditional monitoring methods for onboard software use pre-set and non-easily changed monitoring rules and parameter thresholds to detect satellite operation data. The overall monitoring process is very limited and lacks the ability to flexibly adjust to different space environments. This kind of monitoring method with poor flexibility generally has low accuracy and low practicality for abnormal monitoring of onboard software on satellites, which can easily cause serious abnormal operation problems in the operation of software applications in satellites, which not only seriously drags down the work efficiency and progress of the overall satellite system, but also requires contact with the ground center due to repair problems, increasing the resources and time consumption of both parties. If communication with the ground is blocked due to space environment problems during the repair process, it will further affect and delay the task execution process of the satellite system and the onboard software, making it difficult to meet real-time requirements and causing serious losses.

[0005] Therefore, how to conduct accurate and correct risk detection on the operating status of onboard software in space satellites to effectively avoid the occurrence of abnormal failures is an extremely important issue. Summary of the invention

[0006] This specification provides a risk detection method, device and electronic device based on satellite-borne software to partially solve the above-mentioned problems existing in the prior art.

[0007] This manual adopts the following technical solutions:

[0008] This specification provides a risk detection method based on onboard software, including:

[0009] Based on a preset monitoring strategy, obtaining operation parameter data corresponding to a target application within a preset time period, wherein the target application is a software application running in the satellite;

[0010] Determine, according to the operating parameter data, a first round of abnormality assessment result corresponding to the target application;

[0011] According to the first round of abnormality assessment results, the monitoring strategy is adjusted for at least one round, wherein for each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormality assessment results corresponding to the previous round of adjustment to obtain the monitoring strategy after the round of adjustment, and based on the monitoring strategy after the round of adjustment, the corresponding operating parameter data within a preset time after the target application completes the round of adjustment is obtained, so as to determine the abnormality assessment result corresponding to the target application after the round of adjustment according to the corresponding operating parameter data within the preset time after the target application completes the round of adjustment as the abnormality assessment result corresponding to the round of adjustment, and adjusting the monitoring strategy at least includes: adjusting the monitoring frequency of the target application and adjusting the monitoring data content of the target application;

[0012] According to the first round of abnormality assessment results and the abnormality assessment results corresponding to at least one round of adjustment, risk detection is performed on the operation process of the target application to obtain a risk detection result.

[0013] Optionally, the operating parameter data includes static parameter data and dynamic parameter data corresponding to the target application in a preset duration, and the dynamic parameter data is used to represent a dynamic parameter time series formed by combining parameter data of the target application collected at each time point divided according to preset time intervals within the preset duration in a chronological order;

[0014] Determining the first round of abnormality assessment results corresponding to the target application according to the operating parameter data, specifically including:

[0015] Determine the static anomaly assessment result corresponding to the target application according to the static parameter data in the operating parameter data, and input the dynamic parameter data in the operating parameter data into a preset anomaly assessment model, so that the anomaly assessment model determines the dynamic anomaly assessment result corresponding to the target application according to the dynamic parameter data;

[0016] A first-round anomaly assessment result corresponding to the target application is determined according to the static anomaly assessment result and the dynamic anomaly assessment result.

[0017] Optionally, for each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormal evaluation result corresponding to the previous round of adjustment to obtain the monitoring strategy adjusted in the current round, which specifically includes:

[0018] For each round of adjustment, according to the abnormal evaluation result corresponding to the previous round of adjustment, the abnormal parameter data corresponding to the previous round of adjustment is determined from the operation parameter data corresponding to the target application within the preset time after the previous round of adjustment;

[0019] According to the abnormal parameter data, a target abnormal monitoring strategy corresponding to the abnormal parameter data is screened out from preset abnormal monitoring strategies;

[0020] According to the target abnormality monitoring strategy, the monitoring strategy adjusted in the previous round is adjusted as the monitoring strategy adjusted in this round.

[0021] Optionally, according to the target abnormality monitoring strategy, the monitoring strategy adjusted in the previous round is adjusted, specifically including:

[0022] For each round of adjustment, the adjustment range of the monitoring strategy adjusted in the previous round is determined according to the abnormal evaluation result corresponding to the target application after the previous round of adjustment;

[0023] According to the adjustment range, determine the monitoring frequency adjustment range and monitoring content accuracy adjustment range of the monitoring strategy adjusted in the previous round for this round;

[0024] According to the target abnormal monitoring strategy, determine the corresponding part of the monitoring strategy adjusted in the previous round that can be adjusted;

[0025] According to the monitoring frequency adjustment range, the monitoring content accuracy adjustment range and the partially adjustable monitoring strategies, the monitoring strategies adjusted in the previous round are adjusted.

[0026] Optionally, according to the first round of abnormality assessment results and the abnormality assessment results corresponding to at least one round of adjustment, risk detection is performed on the operation process of the target application to obtain a risk detection result, which specifically includes:

[0027] When the first round of abnormality assessment result is greater than a preset abnormality risk threshold, it is determined that there is an operational abnormality risk in the operation process of the target application;

[0028] When the first round of abnormal assessment results is not greater than the preset abnormal risk threshold, then for each round of adjustment, it is determined whether the abnormal assessment result corresponding to the target application after the round of adjustment is greater than the abnormal risk threshold. If it is determined that the abnormal assessment result corresponding to the target application after the round of adjustment is greater than the preset abnormal risk threshold, it is determined that there is an operational abnormality risk during the operation of the target application.

[0029] Optionally, the method further includes:

[0030] When it is determined according to the risk detection result that there is an operation abnormality risk in the operation process of the target application, determining the risk abnormal process corresponding to the target application according to the operation parameter data corresponding to the abnormal assessment result used to determine that the risk detection result indicates that there is an operation abnormality risk, and generating a process recovery instruction for the risk abnormal process;

[0031] According to the process recovery instruction, a recovery operation is performed on the risk abnormal process, wherein the recovery operation at least includes an application process restart operation and an increase resource allocation operation.

[0032] Optionally, the method further includes:

[0033] When the recovery operation of the risk abnormal process according to the process recovery instruction fails, replacing the risk abnormal process with a preset redundant process corresponding to the target application;

[0034] The process task corresponding to the risk abnormal process continues to be executed based on the redundant process.

[0035] This specification provides a risk detection device based on onboard software, including:

[0036] An acquisition module, used to acquire operating parameter data corresponding to a target application within a preset time period based on a preset monitoring strategy, wherein the target application is a software application running in a satellite;

[0037] An abnormality assessment module, used to determine a first round of abnormality assessment results corresponding to the target application according to the operating parameter data;

[0038] A strategy adjustment module, configured to perform at least one round of adjustment on the monitoring strategy according to the first round of abnormality assessment results, wherein for each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormality assessment results corresponding to the previous round of adjustment to obtain the monitoring strategy after the round of adjustment, and based on the monitoring strategy after the round of adjustment, obtain the corresponding operating parameter data within a preset time after the target application completes the round of adjustment, so as to determine the abnormality assessment result corresponding to the target application after the round of adjustment according to the corresponding operating parameter data within the preset time after the target application completes the round of adjustment, as the abnormality assessment result corresponding to the round of adjustment, and adjusting the monitoring strategy at least includes: adjusting the monitoring frequency of the target application and adjusting the monitoring data content of the target application;

[0039] The risk detection module is used to perform risk detection on the operation process of the target application according to the first round of abnormal evaluation results and the abnormal evaluation results corresponding to at least one round of adjustment to obtain risk detection results.

[0040] The present specification provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned risk detection method based on onboard software is implemented.

[0041] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned risk detection method based on onboard software when executing the program.

[0042] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0043] It can be seen from the above method that in the risk detection method based on onboard software provided in this specification, the first round of abnormal evaluation results corresponding to the target application can be determined based on the operating parameter data of the target application within the preset time length obtained based on the preset monitoring strategy. Then, according to the first round of abnormal evaluation results, the monitoring strategy is adjusted for at least one round. For each round of adjustment, according to the adjusted monitoring strategy, the operating parameter data corresponding to the target application within the preset time length after the round of adjustment is obtained. Next, according to the operating parameter data obtained later, the abnormal evaluation results corresponding to the round of adjustment are determined for the target application. Based on the first round of abnormal evaluation results and the abnormal evaluation results corresponding to at least one round of adjustment, the operation process of the target application is subjected to risk detection, thereby obtaining the corresponding risk detection results.

[0044] From the above content, it can be seen that the risk detection method based on onboard software provided in this specification can determine the first round of abnormal evaluation results corresponding to the target application according to the obtained operating parameter data of the target application, and make at least one round of reasonable adjustments to the current monitoring strategy according to the first round of abnormal evaluation results, and obtain the operating parameter data corresponding to each round of adjustment, and determine the abnormal evaluation results corresponding to each round of adjustment of the target application. Finally, according to the first round of abnormal evaluation results and the abnormal evaluation results corresponding to at least one round of adjustment, the operation process of the target application is risk-detected to obtain the corresponding risk detection results. Through the method of this specification, when facing different abnormal problems and space environments, a more suitable, accurate and effective monitoring strategy can be flexibly selected for the target application, so as to ensure that the abnormal problems are discovered and handled as much as possible before they cause serious failures, effectively improving the efficiency of repairing abnormal problems of onboard software, and also greatly ensuring the stability of the satellite system in the space environment with changing conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0046] Figure 1 A flowchart of a risk detection method based on onboard software provided in this specification;

[0047] Figure 2 A schematic diagram of the overall structure of a risk detection method based on onboard software provided in this specification;

[0048] Figure 3 A schematic diagram of a risk detection device based on onboard software provided in this specification;

[0049] Figure 4 A method provided in this specification corresponding to Figure 1 Schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0051] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0052] Figure 1 The following is a flow chart of a risk detection method based on onboard software provided in this specification, comprising the following steps:

[0053] S101: Based on a preset monitoring strategy, obtain operating parameter data corresponding to a target application within a preset duration.

[0054] At present, the gradual maturity of satellite aerospace technology has brought great convenience to various technical fields and people's daily lives. The various types of satellite-borne software carried in satellites have provided favorable support and assistance for fields such as space exploration and information communication. There are many uncontrollable and unpredictable factors in the space environment, which makes the normal operation of various application software in the satellite very easy to be affected, resulting in abnormal problems. At present, the monitoring methods for satellite-borne software in technology are mostly based on preset monitoring rules and parameter thresholds, which have obvious limitations and cannot adjust the monitoring strategy according to the severity of the abnormal problems. When a more serious abnormal situation occurs, it is too late to issue an early warning, which affects the normal operation of the satellite system and seriously reduces the abnormal repair rate, resulting in time waste and resource loss. Therefore, it is crucial to accurately detect risks in the operation process of satellite-borne software.

[0055] To this end, this specification provides a risk detection method based on satellite-borne software, wherein the execution subject used by the method provided in this specification can be a terminal device preset on a space satellite, such as a desktop computer, a laptop computer, etc., or a server preset on a space satellite. In addition, the execution subject of this specification can also be a subject in the form of software, such as a client installed in a terminal device of a space satellite. For the sake of ease of explanation, this specification below only uses the terminal device preset on the space satellite as the execution subject to explain the risk detection method based on satellite-borne software.

[0056] Based on this, the terminal device that uses the risk detection method based on satellite software provided in this specification can determine the first round of abnormal evaluation results for the target application based on the acquired operating parameter data corresponding to the target application, and adjust the current monitoring strategy of the target application at least once based on the first round of abnormal evaluation results. Based on the monitoring strategy adjusted after each round, the operating parameter data corresponding to the target application is acquired, and the corresponding abnormal evaluation results are determined for the target application after each round of adjustment. The terminal device can perform accurate risk detection on the operation process of the target application based on the first round of abnormal evaluation results and the abnormal evaluation results corresponding to at least one round of adjustment.

[0057] Among them, the specific application scenario of the terminal device for risk detection of onboard software can be determined according to different actual space environments and application requirements. For example, in a scenario where the space environment changes dramatically, the terminal device using the method in this specification in the satellite can collect the operating parameter data corresponding to the target application in the satellite in real time, and first determine the first round of abnormal evaluation results, and judge the impact of the current space environment on the operating state of the current target application. Next, based on the first round of abnormal evaluation results, the monitoring strategy is appropriately adjusted for at least one round, so that more attention is paid to the impact and interference of changes in the space environment or other factors on the operation of the target application, and the abnormal evaluation results corresponding to the target application are determined in time based on the adjusted operating parameter data. According to the first round of abnormal evaluation results and the abnormal evaluation results corresponding to at least one round of adjustments, the operation process of the target application is risk-detected, so as to timely judge whether the current changing space environment may have an adverse effect on the operation of the target application, collect relevant data and notify the ground department, so as to avoid the occurrence of serious abnormal failure problems to a great extent.

[0058] For another example, in the scenario of scheduled maintenance of space satellites, the terminal device can determine the first round of abnormal evaluation results corresponding to the target application based on the operating parameter data of the target application in the historical period, and adjust the current monitoring strategy based on the first round of abnormal evaluation results, focusing on the relevant data with minor abnormal phenomena in the operating parameter data, so as to obtain the operating parameter data corresponding to the target application in the subsequent operating period, thereby determining the abnormal evaluation results corresponding to the target application after at least one round of adjustment. Based on the first round of abnormal evaluation results and the abnormal evaluation results, the operation process of the target application is risk identified. This method can effectively identify potential problems in the operation process of the target application during the scheduled maintenance process, collect data and feedback in a timely manner to eliminate abnormal failures in advance before they occur, effectively ensuring the efficiency of repairing abnormal problems, and also ensuring the stability of normal operation of the target application in the satellite system.

[0059] In this specification, the terminal device can obtain the operating parameter data corresponding to the target application within the preset operating time of the preset time based on the monitoring strategy preset in the satellite system. It should be noted in advance that the target application is a software application on a satellite that performs tasks in a space environment. The specific application category and the corresponding tasks performed on the satellite are not strictly limited in this specification and can be flexibly adjusted according to actual application scenarios and needs.

[0060] The above-mentioned collected operation parameter data includes static parameter data and dynamic parameter data corresponding to the target application in the historical preset operation time. Regarding static parameter data, the data change process corresponding to this type of data in the operation means is usually not strongly dependent on the time change, and is generally discrete data with a large change time interval.

[0061] The specific data content of static parameter data may include, but is not limited to: component health data corresponding to system components used in the satellite system when the target application is running (for example, the working status of key equipment such as antennas, thrusters, scientific instruments, component rotation speed, angular velocity, fuel consumption, etc.), failure rate and maintenance records of each system component occupied by the target application, software logs generated during the operation of the target application and stored error records, and rendezvous and docking data (for example, data related to the relative position and speed of the target application with other satellites or spacecraft recorded when performing multi-satellite coordination or rendezvous and docking missions).

[0062] As for the dynamic parameter data in the operating parameter data mentioned above, the obvious difference between it and the static parameter data is that the change process of the dynamic parameter data is bound to the change of the running time of the target application and has a strong time dependence. The corresponding data form can be used to represent the dynamic parameter time series composed of the parameter data collected for the target application at each time point divided according to the preset monitoring time interval within the preset running time.

[0063] The specific data content of dynamic parameter data may include, but is not limited to: the satellite's operating attitude and orbit data (such as the satellite's pitch angle, yaw angle and roll angle, orbit altitude, inclination, ascending node longitude and other related data when the target application performs related tasks to manipulate the satellite to move in the space environment), the satellite's power and energy data (such as the battery power, voltage, temperature, charge and discharge rate, solar panel power generation efficiency, light intensity, current, voltage, and real-time power consumption of each system component when the target application performs power manipulation tasks), communication data (such as communication signal strength, data transmission rate, packet loss rate, delay, telemetry parameters and other data when the target application performs communication tasks), system operating temperature and thermal management data (such as the temperature data of each system device and subsystem when the target application performs system heat dissipation tasks, and the working status of the radiator, heat pipe, cooling system and other data), vibration and shock data (such as the data of the accelerometer or vibration sensor when the target application performs related tasks, the record data of the shock event suffered by the satellite, etc.), and the sensor data corresponding to the sensors used by the target application (such as the usage data of gyroscopes, accelerometers, magnetometers, imaging and optical sensors, cameras, spectrometers, etc.).

[0064] It should be noted that, whether it is the static parameter data or the dynamic parameter data in the operating parameter data, the terminal device can collect data at a corresponding number of time points in the preset duration of the target application according to the preset time interval, but the data changes in the time series data corresponding to the static parameter data are relatively discrete or unchanged, while the time series data corresponding to the dynamic parameter data has obvious time dependence. For the acquisition process of the operating parameter data, please refer to the following formula:

[0065]

[0066] in, Used to indicate the time that the terminal device has been targeting the target application within the preset time. The corresponding data set, time Belongs to the preset time series time point in the . Used to indicate time The number of data points when collecting operating parameter data for the target application, Used to indicate the time when the target application in the satellite system is within the preset time. The data source of the runtime parameter data storage record Through the operation process of the above formula, the terminal device can obtain the time series At each time point The operating data set corresponding to the target application is used as the operating parameter data corresponding to the target application.

[0067] In addition, in this specification, after obtaining the operating parameter data corresponding to the target application, before determining the first round of abnormal assessment results, the operating parameter data can also be pre-processed to ensure the accuracy of the data content and the accuracy of the subsequent risk detection process. For details, please refer to the following formula:

[0068]

[0069] in, It is used to represent the operating parameter data corresponding to the target application obtained by the above method. Used to indicate the operation parameter data The specific processing process of the preset preprocessing function includes but is not limited to data format unification and conversion, invalid data filtering and obvious outlier detection. The specific formula content of the preprocessing function is not strictly limited in this manual. There are many types of target applications in the satellite system, which can be flexibly set according to actual application scenarios and needs. Through this formula, the operating parameter data corresponding to the target application can be Perform preprocessing operations to obtain preprocessed operating parameter data , in order to effectively improve the processing efficiency and accuracy of the subsequent risk detection process.

[0070] S102: Determine a first round of abnormality assessment result corresponding to the target application according to the operating parameter data.

[0071] In this specification, after the terminal device obtains the operating parameter data corresponding to the target application within a preset time, it can determine the first round of abnormal evaluation results corresponding to the target application based on the operating parameter data. Among them, for the static parameter data and dynamic parameter data in the operating parameter data, the terminal device can respectively determine the abnormal evaluation results corresponding to different types of data.

[0072] Specifically, for the static parameter data in the operating parameter data, the terminal device can input the static parameter data into a pre-set and pre-trained data reconstruction model, so that the data reconstruction model can extract the data features corresponding to the static parameter data according to the received static parameter data, and perform a reconstruction operation to obtain the reconstructed data corresponding to the static parameter data. Furthermore, the terminal device uses the reconstruction error between the static parameter data and the reconstructed data corresponding to the static parameter data as the static anomaly assessment result corresponding to the target application.

[0073] The above data reconstruction model is a pre-trained mathematical model. During the training process, the reconstruction error is used to judge the effect of model training and determine whether the data reconstruction model has accurate feature extraction capabilities. When the trained data reconstruction model is used in actual applications, the normal static parameter data of the target application should be low when calculating the reconstruction error. When the reconstruction error is determined for the static parameter data affected by the abnormal operation of the application, there will be obvious data fluctuations. Therefore, it is possible to indirectly determine whether there are abnormalities in the static parameter data corresponding to the target application by determining the reconstruction error of the static parameter data.

[0074] The specific operation process of determining the static anomaly assessment result corresponding to the target application can be referred to the following formula:

[0075]

[0076]

[0077]

[0078] in, Specifically used to represent the static parameter data in the operating parameter data input into the data reconstruction model. Specifically used to represent the activation function of the data reconstruction model for feature extraction, Specifically used to represent the static parameter data of the hidden layer set in the data reconstruction model Process the obtained data features. Specifically used to represent the data reconstruction model based on data characteristics , the reconstructed data corresponding to the static parameter data obtained by reconstruction, and and It is the preset weight and bias corresponding to the feature extraction part in the data reconstruction model. and Yes, the data reconstruction part in the data reconstruction model corresponds to the preset weights and biases.

[0079] By calculating the reconstructed data corresponding to each data in the static parameter data And each data in the static parameter data The square of the Euclidean distance between , and then take the average value to determine the static anomaly assessment result corresponding to the target application, that is, .

[0080] It should be noted that the specific model category of the data reconstruction model mentioned above is not strictly limited in this specification. Specifically, a mathematical model with feature extraction and data reconstruction capabilities such as an autoencoder neural network (Autoencoder) can be used, which can be flexibly set according to actual application scenarios and application requirements.

[0081] As for the process of determining the abnormality assessment results for the dynamic parameter data in the operating parameter data, the terminal device can input the dynamic parameter data in the form of time series data into a preset abnormality assessment model, so that the preset abnormality assessment model can determine the dynamic abnormality assessment results corresponding to the target application based on the received dynamic parameter data.

[0082] It should be noted that the specific model categories of the anomaly assessment models involved in this specification are not strictly limited and can be flexibly set according to the actual application scenario. In order to facilitate the understanding of the specific determination process of the dynamic anomaly assessment results, the following application example of determining the dynamic anomaly assessment results through a long short-term memory network (LSTM) is used for explanation. For details, please refer to the following formula:

[0083]

[0084]

[0085]

[0086] Among them, the terminal device can obtain the time series data , predict the corresponding prediction data at the next time point through the abnormal evaluation model (such as the above LSTM model) . According to the actual value at the corresponding time point and predicted values , the terminal device can determine the prediction error Then, the terminal device can , through the calculation method of the third line of the above formula, determine the abnormal score corresponding to the dynamic parameter data in the running parameter data , and used as the dynamic anomaly assessment result corresponding to the target application.

[0087] Regarding the process of LSTM model predicting data based on dynamic parameter data, you can refer to the following formula:

[0088]

[0089]

[0090]

[0091] The basic structure of the LSTM model is divided into input gate, forget gate and output gate, which correspond to the first three lines of the above formula. The input gate can be used to determine which dynamic parameter data needs to be added to the cell state. For the first The input gate vector at time t is used to represent The degree of influence of the dynamic parameter data corresponding to the moment on the unit state, with a value range of [0, 1]. is the preset Sigmoid activation function, and They are respectively represented as the bias vector and weight matrix preset for the input gate part, Used to indicate the The hidden state vector at the moment can be understood as the hidden information retained by the LSTM model from the past time steps. It is used to represent the dynamic parameter data in the form of time series. The data at the moment. Through the first line of formula, the terminal device can determine the input gate vector of the LSTM model .

[0092] and They are respectively represented as the preset bias vector and weight matrix for the forget gate part of the LSTM model, , as well as The meaning is the same as the formula in the first row. Through the forget gate formula in the second row, the terminal device can determine the part of the cell state that needs to be forgotten through the LSTM model, that is, For example, suppose the current time step is After receiving a set of dynamic parameter data, such as power and energy data, the forget gate in the LSTM model can combine the hidden state of the previous moment and the current input To decide whether to retain the previous energy state information. If the energy state of a device has been stable in the past but suddenly changes, the forget gate may reduce its dependence on the previous state and be more adaptable to the current changes.

[0093] and They are respectively represented as the bias vector and weight matrix preset for the output gate part of the LSTM model, , as well as The meaning is the same as the formula in the first row. Through the output gate formula in the third row, the terminal device can use the LSTM model to determine which data information in the data processed by the forget gate may affect the corresponding hidden state, that is, . Assume that at a certain time step, the attitude data of the satellite system suddenly changes significantly. This change can be captured by the LSTM model in the current time step. The output gate can determine whether this change should be reflected in the current hidden state, thereby affecting the input and forgetting processing of subsequent time steps. Assuming that the satellite attitude data changes significantly, the output gate in the LSTM model will pass this significant change information through Mapping to dynamic parameter data hidden state middle.

[0094] Then, the terminal device can update the unit state corresponding to each moment of the dynamic parameter data according to the data calculated by each part. For details, please refer to the following formula:

[0095]

[0096]

[0097]

[0098] Among them, regarding the first row of formulas, Used to represent the cell state at the current time step, Used to represent the cell state at the previous time step, which can retain information from all previous moments. is the output data of the forget gate part in the above formula, which can be used to determine the unit state of the previous time step Which parts of are retained to the current time step. It is the output of the input gate part in the above formula, which can be used to determine which data information of the current time step needs to be added to the current unit state.

[0099] In the second line of the above formula, It is used to represent the candidate unit state, which can specifically represent the data generated based on the current input and the previous hidden state. and are the bias vector and weight matrix preset for the candidate unit state. It is a generator of new information, which is generated by nonlinear transformation based on the current input data and the hidden state corresponding to the previous moment, and can be added to the current unit state. In. Candidate unit status It is the potentially important information corresponding to each time step. It is the function processing result of the current input data and the previous hidden state. Specifically, it can be understood as indicating that the LSTM model needs to add the unit state at the current time step. data information.

[0100] In the third line of the above formula, It can be expressed as The hidden state vector at time t, It is the output data of the output gate part in the above formula, which can be used to determine the unit status information The degree to which the current hidden state will be affected. This formula can be used to determine the hidden state vector corresponding to each moment in the dynamic parameter data, thereby determining the hidden state sequence corresponding to the dynamic parameter data. . Thus, the terminal device can use the LSTM model to calculate the hidden state sequence , predict the corresponding prediction data at the next time point , in order to obtain the dynamic anomaly assessment results corresponding to the target application .

[0101] In addition, this manual takes into account the resource shortage and allocation issues in the space environment. In order to reduce the resource consumption of the anomaly assessment model when determining the dynamic anomaly assessment results, the anomaly assessment model can be quantized and parameter pruned. The following still takes the LSTM model as an example to explain the model quantization and parameter pruning process.

[0102] Regarding the parameter pruning process, the terminal device can prune the parameters of the LSTM model to reduce the number of parameters in the LSTM model, thereby retaining more important connection parameters, removing useless connection parameters that have little impact on the prediction process, reducing the overall complexity of the model, and reducing resource consumption during normal use. For details, please refer to the following formula:

[0103]

[0104] in, are the matrix elements in the parameter matrix, is the preset pruning threshold. Through this calculation formula, the terminal device can The matrix elements are directly replaced with 0, thereby reducing the overall complexity of the matrix parameters and optimizing the model structure.

[0105] Regarding the model quantization process, the terminal device can quantize the anomaly assessment model that has undergone the training process, specifically by reducing the floating-point weights of the model to a lower precision, such as an 8-bit integer. For details, please refer to the following formula:

[0106]

[0107] in, , are used to represent the minimum and maximum values ​​in the weight matrix of the model parameters, respectively. The number of bits for the preset model quantization, such as 8 bits or 16 bits, etc. After calculation by this formula, each model parameter in the anomaly assessment model (such as the LSTM model) can be effectively quantized, which can reduce the memory requirements of the model when it is working normally to a certain extent, thereby reducing resource consumption in the space environment.

[0108] In addition, in this specification, the anomaly assessment model to be trained in the terminal device can also be trained and optimized. Specifically, the loss value in the training process can be reduced to adjust the model parameters, and the anomaly assessment model with anomaly score assessment for dynamic parameter data can be trained. The loss function corresponding to the loss value in the training process can be specifically referred to the following formula:

[0109]

[0110] in, Is the loss value, which is used to represent the loss error during the training process. is the standard value corresponding to the sample data during training, and It is used to represent the predicted value predicted by the anomaly assessment model to be trained based on the sample data. The terminal device can minimize the loss value As the goal, adjust the model parameters in the anomaly assessment model , so as to train and optimize the anomaly assessment model to be trained. The trained anomaly assessment model can be used to perform the anomaly scoring for the dynamic operation parameters in the above method.

[0111] It should be noted that before inputting the dynamic parameter data in the form of time series into the anomaly assessment model, the terminal device can also normalize the dynamic parameter data to eliminate the differences in different data scales between the data in the time series. For details, please refer to the following formula:

[0112]

[0113] in, Used to represent the original data, that is, the time series data in the dynamic parameter data, is the mean value corresponding to the dynamic parameter data, and It is used to represent the standard deviation corresponding to the dynamic parameter data. Through the normalization process of the above formula, the normalized data corresponding to the dynamic parameter data can be obtained. Furthermore, in the process of determining the dynamic anomaly evaluation result in the above method, the terminal device can determine the normalized data corresponding to the dynamic parameter data determined by the above formula. , determine the dynamic anomaly assessment results corresponding to the target application.

[0114] At this point, the terminal device can determine the static anomaly assessment results and dynamic anomaly assessment results corresponding to the target application based on the operating parameter data. Next, the terminal device can determine the first round of anomaly assessment results corresponding to the target application based on the static anomaly assessment results and the dynamic anomaly assessment results. The determination process can be specifically referred to the following formula:

[0115]

[0116] Among them, Reconstruction Error is used to represent the static anomaly evaluation result corresponding to the target application determined by the above method, and LSTM Score is used to represent the dynamic anomaly evaluation result corresponding to the target application determined by the above method, that is, the dynamic anomaly evaluation result in the above steps. , and α and β are preset weight parameters for static anomaly assessment results and dynamic anomaly assessment results, respectively, to balance the impact of anomalies in static parameter data and dynamic parameter data on the overall target application operation status. By weighting and summing the static anomaly assessment result Reconstruction Error and the dynamic anomaly assessment LSTM Score through the above formula, the first round of anomaly assessment results Anomaly Score corresponding to the target application can be determined. The specific data content can be represented by the anomaly assessment score, and the score is positively correlated with the severity of the anomaly of the target application.

[0117] S103: According to the results of the first round of abnormality assessment, the monitoring strategy is adjusted for at least one round, wherein for each round of adjustment, the monitoring strategy after the previous round of adjustment is adjusted according to the abnormality assessment results corresponding to the previous round of adjustment to obtain the monitoring strategy after the round of adjustment, and based on the monitoring strategy after the round of adjustment, the operating parameter data corresponding to the preset time after the target application completes the round of adjustment is obtained, so as to determine the abnormality assessment result corresponding to the target application after the round of adjustment according to the operating parameter data corresponding to the preset time after the target application completes the round of adjustment, as the abnormality assessment result corresponding to the round of adjustment.

[0118] In this specification, the terminal device can make at least one round of policy adjustments to the monitoring strategy currently set for the target application based on the first round of abnormality evaluation results corresponding to the target application determined through the above steps. For each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormality evaluation results corresponding to the previous round of adjustment, thereby obtaining the monitoring strategy adjusted in the current round. At the same time, based on the monitoring strategy adjusted in the current round, the terminal device can obtain the corresponding operating parameter data within the preset time after the target application completes the current round of adjustment.

[0119] Specifically, for each round of adjustment of the monitoring strategy, the terminal device can determine the abnormal parameter data with numerical abnormalities after the last round of adjustment from the corresponding operating parameter data of the target application within the preset time after the last round of adjustment based on the corresponding abnormal evaluation results after the last round of adjustment. Then, the terminal device can filter out the target abnormal monitoring strategy corresponding to the abnormal parameter data from the preset abnormal monitoring strategy based on the determined abnormal parameter data. It should be separately explained that the abnormal evaluation results based on the first round of adjustment of the preset monitoring strategy are the first round of abnormal evaluation results determined in the above steps.

[0120] The so-called preset abnormal monitoring strategy can be understood as a monitoring strategy with special monitoring frequency or content settings for some parameter data in the target application that is pre-set by the developer of the target application. The determined target abnormal monitoring strategy can be understood as a monitoring strategy with special monitoring frequency or content settings corresponding to the abnormal parameter data of the operating parameter data.

[0121] Regarding the specific determination process of the target abnormal monitoring strategy, first, in the above-mentioned preset abnormal monitoring strategy, the current monitoring strategy of the target application can be preset as the basic strategy, and it includes special monitoring strategies for specific operating parameters or specific tasks during the operation of the target application (for example: enhanced monitoring strategies for the temperature of each component used when the target application is running in a high-temperature environment, and monitoring data with high precision requirements when important application tasks are executed). In addition, a dynamic adjustment mechanism for the target abnormal monitoring strategy can also be set in the terminal device to dynamically adjust the selected target abnormal monitoring strategy according to the specific numerical size and type of the abnormal parameter data, so as to improve the practicality of the determined target abnormal monitoring strategy.

[0122] Then, the terminal device can determine the task status information (including but not limited to the task type, execution progress, priority, etc. of the target task), execution environment information (including but not limited to component temperature, radiation intensity, communication status, etc.), and historical data information (including but not limited to past monitoring record information, task execution process information, abnormal problem record information, etc.) of the target task executed by the target application within the preset time after the last round of adjustment based on the corresponding operating parameter data of the target application within the preset time after the last round of adjustment.

[0123] Next, the terminal device can determine the data features corresponding to each data based on the determined task status information, execution environment information, historical data information, and the abnormal parameter data determined based on the abnormal evaluation results corresponding to the previous round of adjustments. Thus, based on the four data features, the target abnormal monitoring strategy corresponding to the abnormal parameter data determined by the monitoring strategy adjusted in the previous round is determined from the above-mentioned pre-set abnormal monitoring strategies. The specific processing process can refer to the following formula:

[0124]

[0125] in, Specifically, they are used to represent the task status information, execution environment information, historical data information, and abnormal parameter data mentioned above. , the terminal device can determine the adjustment range of special monitoring strategies for abnormal parameter data The dynamic adjustment range of the monitoring strategy determined based on task status information, execution environment information, and historical data information Then, in the basic monitoring strategy (which can be the target application's current unadjusted monitoring strategy), the terminal device can adjust the amplitude according to the determined special monitoring strategy Dynamic adjustment of monitoring strategies , determine the target abnormality monitoring strategy corresponding to the abnormal parameter data from the abnormality monitoring strategies preset by the terminal device mentioned above .

[0126] Regarding the two types of changes involved in the above formula: Special monitoring strategy adjustment range Dynamic adjustment of monitoring strategies , the specific determination process can be uniformly referred to the following formula:

[0127]

[0128] in, Used to indicate the strategy adjustment range, that is, the special monitoring strategy adjustment range mentioned above Or monitor the dynamic adjustment range of the strategy . Adjust the scale factor for a preset amplitude, and It is the change factor under different adjustment situations. The specific value varies according to different abnormal data content or environmental data such as task status. The change rule can be determined according to the actual application scenario and needs.

[0129] At this point, for each adjustment round, the process of determining the target abnormality monitoring strategy corresponding to the adjustment of this round has been completed, but it should be noted that in addition to the above-mentioned process of determining the target abnormality monitoring strategy for the current monitoring strategy of the target application, in this specification, the terminal device can also actively perform a monitoring strategy recovery operation when the abnormal problem disappears or is repaired through abnormal alarms and problem repairs in subsequent processes.

[0130] The main working scenario of the satellite system is the space environment. Environmental problems are changeable and the number of resources is limited. Therefore, how to reasonably allocate resource occupation and consumption is the top priority to ensure that the satellite performs its target tasks. This manual takes into account that appropriate monitoring strategy settings can achieve reasonable planning of resource usage allocation, and allocate more resources and computing power to perform abnormal investigations when abnormalities occur, so as to fix the problems as soon as possible and prevent serious abnormal failures. When no abnormalities occur or the abnormal problems are resolved, the resource allocation of the monitoring strategy can be appropriately reduced to ensure that the target applications in the overall satellite system are monitored while increasing the resource usage of other task processes, thereby improving the work efficiency of the overall satellite system. The specific recovery process of the monitoring strategy can refer to the following formula:

[0131]

[0132] in, The target anomaly monitoring strategy determined by the above steps is used for the target application to adjust the preset monitoring strategy before determining the first round of anomaly evaluation results. It is used to represent the response factor. The specific data is positively correlated with the response progress of the abnormal problem corresponding to the target application. is the preset recovery coefficient. Through the above steps, the terminal device can gradually restore the adjusted monitoring strategy corresponding to the target application. The resource configuration occupied by the monitoring strategy is allocated step by step. When the abnormal problem is completely solved, the monitoring strategy corresponding to the target application can be changed back to the preset monitoring strategy before the first round of abnormal evaluation results are determined.

[0133] Furthermore, still for each adjustment round, after determining the target abnormality monitoring strategy corresponding to the abnormal parameter data during the operation of the target application, the terminal device can adjust the monitoring strategy of the target application after the previous round of adjustment according to the corresponding abnormal assessment results and target abnormality monitoring strategy of the previous round of adjustment.

[0134] Specifically, the terminal device can first determine the monitoring frequency adjustment range and monitoring content accuracy adjustment range of the monitoring strategy after the last round of adjustment of the target application based on the abnormal evaluation results corresponding to the last round of adjustment of the target application and the preset policy adjustment threshold. The monitoring frequency adjustment range can be used to specifically indicate the adjustment of the time interval between each data collection time point in the monitoring strategy, and the monitoring content accuracy adjustment range can be used to specifically indicate the adjustment of the accuracy or data type and content of the collected data in the monitoring strategy.

[0135] To facilitate understanding of the process of determining the above two adjustment ranges, an example is given below: From the above content, it can be seen that the abnormality assessment results corresponding to the target application can be specifically expressed in the form of scores. Taking the first round of adjustments to the preset monitoring strategy as an example, it is assumed that the first round of abnormality assessment results are between 0 and 0.5, indicating a low abnormality, between 0.5 and 0.8, indicating a low abnormality, and greater than 0.8, indicating a high abnormality.

[0136] When it is determined that the first round of abnormal evaluation results corresponding to the target application is between 0 and 0.5, the terminal device can determine that the operating status of the target application in the corresponding operating period is a low abnormality, and the corresponding monitoring frequency adjustment range can be expressed as a small increase in the time interval between the acquisition time points in the current monitoring strategy, or no adjustment when resource allocation in the satellite system is tight. The monitoring content accuracy adjustment range is similar, and the accuracy of the collected data in the current monitoring strategy can be slightly improved or no adjustment is made when resources are tight, and the current monitoring strategy is continued for continuous monitoring.

[0137] During the first round of adjustments to the preset monitoring strategy, when it is determined that the first round of abnormal evaluation results corresponding to the target application is between 0.5 and 0.8, the terminal device can determine that the operating status of the target application in the corresponding period is a medium abnormal situation, and the corresponding monitoring frequency adjustment range can be expressed as a certain increase in the time interval between the collection time points in the current monitoring strategy, for example, the frequency of data collection changes from once every 5 seconds to once every 2 seconds. Similarly, the monitoring content accuracy adjustment range will also increase to a certain extent, and the accuracy of the collected data in the current monitoring strategy can be improved to a certain extent, for example, the data accuracy is adjusted from an integer to two decimal places, and the data content is adjusted from only obtaining one type of data A to simultaneously obtaining data A and related data B and data C.

[0138] When it is determined that the first round of abnormal evaluation results corresponding to the target application is greater than 0.8, the terminal device can determine that the operating status of the target application in the corresponding period is a high abnormal situation, and the corresponding monitoring frequency adjustment range can be expressed as a significant increase in the time interval between the acquisition time points in the current monitoring strategy, for example, the frequency of data acquisition changes from once every 5 seconds to once every 0.5 seconds. Similarly, the monitoring content accuracy adjustment range will also be greatly increased, and the accuracy of the collected data in the current monitoring strategy can be greatly improved. For example, the data accuracy is adjusted from an integer to three decimal places, and the data content is adjusted from only obtaining one type of data A to simultaneously obtaining data A and all related data of data A. According to different scenarios of abnormal problems, targeted dynamic adjustments can also be made. For example, in the abnormal occurrence scenario related to high temperature problems, the temperature anomaly detection threshold can be appropriately lowered, so that when obtaining temperature data in the subsequent process, an early response can be achieved before the high temperature anomaly occurs.

[0139] Through the above process, the terminal device can determine the monitoring frequency adjustment range and monitoring content accuracy adjustment range of the monitoring strategy after the previous round of adjustment. After the adjustment range is determined, the specific adjustment content can be determined. The terminal device can determine the corresponding part of the monitoring strategy after the previous round of adjustment based on the target abnormal monitoring strategy determined in the above steps.

[0140] When an abnormality occurs in the operation process of the target application, it may not be that all data have abnormal problems, but only a single or part of the data may have numerical abnormalities due to abnormal failures. At this time, if the overall monitoring strategy is adjusted comprehensively, each monitoring data is adjusted in frequency and content accuracy. First, the overall change is large and requires a lot of computing power support. Second, even if the adjustment is completed, subsequent monitoring will require more resources. In a space environment with such tight resource allocation, it is likely to affect the normal execution of other tasks in the satellite system. Therefore, this manual takes into account the negative impact that the above-mentioned problems may bring, and selects the part of the adjustable monitoring strategy that needs to be adjusted from the monitoring strategy to be adjusted according to the determined target abnormal monitoring strategy, so as to effectively ensure the effectiveness of the strategy adjustment while saving computing power and resource consumption.

[0141] For example, assume that the current monitoring strategy for the target application includes monitoring data for the temperature of the component in use, monitoring data for the target application's device memory usage, the number of processes consumed by the target application to execute the corresponding task and the task execution status, etc. If the target abnormal monitoring strategy obtained according to the above steps determines that the monitoring frequency and data content accuracy of the temperature monitoring data of the component in use during the operation of the target application need to be adjusted, the terminal device can adjust the strategy corresponding to the monitoring data for the temperature of the component in use in the current monitoring strategy of the target application according to the determined monitoring frequency adjustment range and monitoring content accuracy adjustment range, while the remaining monitoring strategies corresponding to the monitoring data such as the target application's device memory usage, the number of processes consumed by the target application to execute the corresponding task and the task execution status, etc., may not be adjusted.

[0142] However, if it is determined based on the results of the first round of anomaly assessment that the target application has a high abnormal situation during operation, the terminal device can also adjust the other monitoring strategies related to the part of the adjustable monitoring strategies corresponding to the target abnormal monitoring strategies in the monitoring strategies to be adjusted according to the determined monitoring frequency adjustment range and monitoring content accuracy adjustment range to determine whether the abnormal problems that cause abnormalities in some monitoring data may affect other monitoring data.

[0143] Furthermore, for each round of adjustment, after determining the corresponding part of the adjustable monitoring strategy in the monitoring strategy adjusted in the previous round, the terminal device can adjust the monitoring strategy of the target application after the previous round of adjustment according to the monitoring frequency adjustment range, the monitoring content accuracy adjustment range and the part of the adjustable monitoring strategy, thereby obtaining the monitoring strategy after the round of adjustment. Next, the terminal device can collect the corresponding operating parameter data of the target application within the preset time after the round of adjustment based on the monitoring strategy after the round of adjustment. The specific data type and collection method are exactly the same as in the above steps, so no excessive repetition will be given here.

[0144] Then, the terminal device can determine the abnormal evaluation results corresponding to the target application after the round of adjustment based on the newly collected operating parameter data of the monitoring strategy after the round of adjustment. The specific determination process of the abnormal evaluation results after each round of adjustment is exactly the same as the determination process of the first round of abnormal evaluation results mentioned above. According to the static parameter data and dynamic parameter data in the collected operating parameter data, the static abnormal evaluation results and dynamic abnormal evaluation results corresponding to the target application are determined respectively, and then according to the static abnormal evaluation results and dynamic abnormal evaluation results, the abnormal evaluation results corresponding to the target application after the round of adjustment are determined. Since the specific implementation means are basically the same as the determination process of the first round of abnormal evaluation results, it will not be elaborated here, and you can directly refer to the above content related to the determination process of the first round of abnormal evaluation results.

[0145] It should also be noted that the adjustment method for adjusting the monitoring strategy for at least one round mentioned in the above process is not strictly limited in this specification. It can be that when computing power and resources are sufficient, the monitoring frequency adjustment range and monitoring content precision adjustment range of the monitoring strategy for the target application after the previous round of adjustment are determined according to the corresponding abnormal evaluation results after the previous round of adjustment, and the partial adjustable monitoring strategy corresponding to the determined target abnormal monitoring strategy is not considered, and the current monitoring strategy of the target application is directly adjusted in all aspects. Of course, it can also be as introduced in the above steps, when adjusting the monitoring strategy after the previous round of adjustment, the target abnormal monitoring strategy determined by the above steps, as well as the monitoring frequency adjustment range and monitoring content precision adjustment range determined according to the corresponding abnormal evaluation results after the previous round of adjustment are considered. In addition, the corresponding monitoring frequency adjustment range and monitoring content precision adjustment range can also be directly preset in the determined target abnormal monitoring strategy. The specific monitoring strategy adjustment method is flexible and can be adjusted according to actual application scenarios and actual needs.

[0146] In addition, it should be noted that when the evaluation score of the first round of abnormal evaluation results or the abnormal evaluation results corresponding to the previous round of adjustments is too low, it means that there is no obvious abnormality in the target application within the preset time. According to the actual application scenario and needs, the terminal device can be set not to adjust the current monitoring strategy of the target application in this case, but will still collect the operating parameter data of the target application within the next preset time according to the unchanged monitoring strategy to determine the authenticity of the first round of abnormal evaluation results or the abnormal evaluation results corresponding to the previous round of adjustments, thereby realizing long-term operation monitoring of the target application and ensuring the normal operation of the target application in the satellite system.

[0147] S105: Perform risk detection on the operation process of the target application according to the first round of abnormality assessment results and the abnormality assessment results corresponding to at least one round of adjustment to obtain risk detection results.

[0148] In this specification, the terminal device can perform risk detection on the operation process of the target application according to the first round of abnormal evaluation results determined by the above steps and the abnormal evaluation results corresponding to the one-round adjustment, so as to obtain the risk detection result for the target application. The risk detection result can be used to indicate whether the target application may have risk abnormality problems during operation.

[0149] Among them, it can be seen from the above steps that there is an obvious time interval between the first round of abnormal evaluation results and the determination process of the abnormal evaluation results corresponding to one round of adjustment. The determination of the first round of abnormal evaluation results must be earlier than the generation of the corresponding abnormal evaluation results after the subsequent single or multiple adjustments. The terminal device in this specification can determine whether there is an operation risk in the operation process of the target application directly based on the first round of abnormal evaluation results and the preset abnormal risk threshold after determining the first round of abnormal evaluation results and not adjusting the current monitoring strategy for at least one round, that is, before the generation of the subsequent rounds of abnormal evaluation results. If the first round of abnormal evaluation results is greater than the preset abnormal risk threshold, the terminal device adjusts the monitoring strategy according to the first round of abnormal evaluation results and related data to determine at least one round of abnormal evaluation results, and determines that the risk detection result of the target application is specifically expressed as the existence of an operational risk abnormality in the operation process.

[0150] The setting of the abnormal risk threshold mentioned above can be determined according to the actual application scenario, and there is no direct correlation between it and the policy adjustment threshold mentioned in the above steps. Therefore, even when the target application is determined to be in a highly abnormal situation according to the policy adjustment threshold, the terminal device can also determine that there may be no operational risk in the operation process of the target application according to the preset abnormal risk threshold. When this happens, it is necessary to adjust the current monitoring strategy of the target application through the above steps to obtain operating parameter data with a higher monitoring frequency, richer data content and higher accuracy. After determining the corresponding abnormal assessment result after the adjustment, determine whether there may be risks in the operation process of the target application based on the relationship between the abnormal assessment result corresponding to at least one round of subsequent adjustments to the preset monitoring strategy and the abnormal risk threshold.

[0151] When it is determined that the first round of abnormal evaluation results is not greater than the preset abnormal risk threshold, for each round of adjustment, the terminal device can determine whether there is a risk abnormality in the operation process of the target application based on the abnormal evaluation results corresponding to the round, that is, when the abnormal evaluation results corresponding to the round are greater than the preset abnormal risk threshold, the terminal device can determine that there is an operation risk in the operation process of the target application, and obtain a risk detection result indicating that there is an operation risk abnormality in the operation process of the target application. Only when the first round of abnormal evaluation results and the abnormal evaluation results corresponding to all subsequent adjustment rounds are not greater than the preset abnormal risk threshold, the terminal device will determine that there may be no risk abnormality in the operation process of the target application, but will not stop the monitoring process. At this time, the terminal device can restore the adjusted monitoring strategy to the monitoring strategy preset for the target application at the beginning through the above-mentioned steps, or maintain the adjusted monitoring strategy if resource allocation allows, and continue to monitor whether the target application is operating normally.

[0152] Among them, it should be noted that the number of adjustments to the monitoring strategy in the above steps is not strictly limited in this specification, at least one adjustment, and can be flexibly adjusted and set according to the actual application scenario, such as making an adjustment, and determining the abnormal evaluation result corresponding to the adjusted monitoring strategy after adjustment according to the first round of abnormal evaluation results, and executing the risk detection process, or it can also be based on the abnormal evaluation result corresponding to a round of adjustment, and there are still unclear abnormal data or problems. The server can adjust the monitoring strategy after a round of adjustment from different angles, and then obtain the operating parameter data of the target application according to the monitoring strategy after the second round of adjustment, and determine the abnormal evaluation result corresponding to the second round of adjustment. Then, according to the first round of abnormal evaluation results, the first round of adjustment, and the corresponding abnormal evaluation results after the second round of adjustment, jointly determine whether there is a risk abnormality in the operation process of the target application. Of course, in order to ensure that the operation of the target application in the satellite remains normal at all times, more rounds or permanent monitoring processes can be continued.

[0153] In addition to the above, in this specification, it is considered that in actual situations, when a target application of a satellite system has an operational abnormality, it is generally necessary to provide data feedback to ground personnel and obtain specific repair operation instructions. In this case, if the information transmission is disturbed and delayed due to the variability of the space environment, the efficiency of repairing the abnormal problem of the target application may be seriously reduced or stagnant, thereby affecting the task execution efficiency of the satellite system. Therefore, the terminal device using the method in this specification can actively perform abnormal self-healing repair operations when the target application has a serious abnormal situation due to an abnormal problem, thereby solving the abnormal fault problem as much as possible by itself and saving the communication process and time with ground personnel.

[0154] Specifically, the terminal device can preset different health status identifiers according to the operating status of the target application, which can be specifically expressed as ,in It can be used to indicate a certain type of health status during the operation of the target application, such as the more common normal operation, stopped operation, abnormal operation, etc., or a health status specially set according to the different tasks performed by the target application, such as the high-temperature operation state in high-temperature scenarios, the overclocked operation state, and the low-power operation state for saving resource consumption.

[0155] After presetting a plurality of operating health states for the target application, the terminal device can determine the abnormal probability distribution of the target application according to the abnormal evaluation results determined through the above steps when determining that the risk detection result of the target application indicates that there is an abnormal operating risk. The specific formula can be expressed as: , in the formula It can be expressed as the operating parameter data corresponding to the abnormal evaluation result, and the determined probability distribution can be expressed as the target application in the healthy state during the historical operation process. The probability of an exception occurring in a given situation.

[0156] Then, the terminal device can determine whether the target application needs to be self-healed according to the preset abnormal probability threshold. The specific processing process can refer to the following formula:

[0157]

[0158] Among them, as mentioned above, Specifically, it means that the target application is in a healthy state during its historical operation. The probability of an exception occurring in the case It is expressed as a preset abnormal probability threshold. Through this formula, the terminal device can and abnormal probability threshold to determine whether the target application needs to undergo a self-healing repair process, that is, to determine the Whether it is 1 or 0.

[0159] When it is determined that the target application has a serious abnormality during operation and needs to be self-healed, the above formula is determined. When it is 1, the terminal device can determine the risk abnormal process with operation abnormality corresponding to the target application based on the operation parameter data corresponding to the abnormal evaluation result indicating a serious abnormality, and generate a process recovery instruction corresponding to the risk abnormal process. Then, the terminal device can perform a process recovery operation on the risk abnormal process according to the process recovery instruction. The specific processing method of the process recovery operation may include but is not limited to restarting the application process or increasing resource allocation operations for the risk abnormal process. The specific processing process can refer to the following formula:

[0160]

[0161] in, Specifically, it can be expressed as the determined risk abnormal process. It is represented as a preset process recovery function, which can be specifically represented as a similar application process restart operation or resource allocation increase operation as mentioned above. Application process that transitions to normal state , in order to continue to complete the corresponding process tasks normally.

[0162] It should be noted that when the abnormality problem is extremely serious, the problem of abnormal process operation may not be solved by simply restarting the process or allocating resources. Therefore, in this manual, if the terminal device determines that the recovery operation for the risk abnormal process cannot be successfully completed through the above steps, the redundant process corresponding to the risk abnormal process will replace the risk abnormal process in the case of pre-setting a single or multiple redundant processes, and continue to execute the process task corresponding to the risk abnormal process based on the replaced redundant process. The specific processing process can refer to the following formula:

[0163]

[0164] in, Same as the above formula, expressed as the determined risk abnormal process, Indicated as preset Through the calculation process of this formula, the terminal device can select redundant processes from the redundant processes when it determines that the recovery operation for the risk abnormal process cannot be successfully completed. Determine the corresponding replacement process , thereby replacing the risk abnormal process Continue to execute the process task.

[0165] In addition, when multiple target applications or application processes have abnormal problems, the terminal device can determine the recovery priority according to the severity and the scope of impact on the entire satellite system. Then, according to the order of the recovery priority, the recovery operation is carried out in sequence. The specific processing process can be referred to the following formula:

[0166]

[0167] in, A collection of risky abnormal processes identified A risky abnormal process in It is used to indicate abnormal process according to risk The severity of the abnormal problem in the corresponding operating parameter data and the scope of impact on the entire satellite system determine the recovery priority. The specific data size is positively correlated with the severity and the scope of impact. This formula can be used to reasonably and orderly repair and sort when multiple risk abnormal processes exist, ensuring that serious problems are handled first while also improving the recovery efficiency of abnormal conditions.

[0168] In addition, the terminal device can also be preset with an adaptive optimization function for self-healing repair capabilities. By analyzing and summarizing the historical repair process data, the settings of various data parameters and repair strategies in the repair process are continuously optimized to improve the stability and repair efficiency of the self-healing repair process. The feedback optimization process can be specifically referred to the following formula:

[0169]

[0170] in, is the restoration effect data of the historical restoration process results, and It indicates the newly acquired operating parameter data. Through the preset feedback optimization function , the optimization adjustment data corresponding to the next repair moment can be determined , in order to improve the repair efficiency of the subsequent self-healing repair process.

[0171] In addition to the above-mentioned methods of anomaly detection and self-healing repair for target applications, in this specification, the terminal device can also be used to uniformly manage the task execution of various application software installed on the entire satellite system, as well as to select and determine the operating strategy of the overall satellite system when facing different operating environments.

[0172] Specifically, regarding the unified management of task execution of each application software, the terminal device can uniformly obtain and control the running status of each task process that executes the task. The specific processing process can refer to the following formula:

[0173]

[0174] in, Represented as a set of software processes composed of task processes corresponding to each target application on the satellite system A task process in Indicates the process The corresponding running status, which can be a preset process status collection Through the preset process control function, the terminal device can control and determine each task process in the satellite system. Next running time The corresponding operating status.

[0175] In order to improve the task execution efficiency of each target application, this manual can also execute multiple tasks in parallel through multi-threaded operation. By optimizing the parallel execution time, the task execution efficiency of the overall satellite system can be improved. For details, please refer to the following formula:

[0176]

[0177] in, It is the parallel execution time when multiple threads execute multiple tasks. Used to represent the task set that needs to be executed by multi-threaded tasks Each task in. By optimizing the parallel execution time , which can effectively reduce the execution time consumption corresponding to multiple target tasks in the satellite system, thereby improving the working efficiency of the overall satellite system.

[0178] In addition, the terminal device mentioned above can also make reasonable choices for the operation strategy of the overall satellite system when facing different operating environments. In this manual, the terminal device can determine the global situation awareness results for the overall satellite system based on the generated data obtained in the above steps, including abnormality assessment results, target abnormality monitoring strategies, adjusted monitoring strategies and other data. Therefore, based on the obtained global situation awareness results, the most appropriate operation strategy for the overall satellite system in the current environment is selected. The specific process of determining the global situation awareness results can refer to the following formula:

[0179]

[0180] in, Used to represent the global situation awareness results corresponding to the satellite system. It is represented by the quantitative data corresponding to the unified data structure determined by the above steps, and It is used to represent the results of different data in the global situation awareness The terminal device can use the global situation awareness results determined by this formula to As the status evaluation result of the satellite system in the current operating environment, the operating strategy that is more suitable for the current situation can be selected according to the evaluation result, such as flexibly adjusting resource allocation, changing the process operation status, etc.

[0181] In addition, the terminal device can also flexibly detect the current operating environment of the satellite system and adjust the operating strategy accordingly according to environmental changes. For details, please refer to the following formula:

[0182]

[0183] in, It is used to indicate the current operating environment of the satellite system detected by the terminal device. , the terminal device can select the policy that matches the current operating environment from the preset policy set Corresponding operation strategy set . Execute operational strategy sets by controlling satellite systems , in order to deal with potential problems that may exist in the current operating environment and effectively ensure the stability of the overall satellite system operation.

[0184] In addition to the above, this manual also takes into account that in the space environment, the satellite system may be seriously affected by some unexpected situations that cannot be responded to in time (such as SEU single-particle upset phenomenon), resulting in the overall monitoring department being seriously affected and stopping operation. This manual also provides a master-slave mutual protection function, which is divided into a master monitoring system and multiple slave monitoring systems to ensure that when a problem occurs in the master monitoring system, it can be replaced by a slave monitoring system in time to ensure the stability and consistency of the monitoring of various data in the satellite system.

[0185] Specifically, the specific architecture of mutual protection between master and slave in terminal equipment can be expressed as .in, As the main monitoring system, is the i-th slave monitoring system. The terminal device can control each slave monitoring system Regularly check the main system Health status , when an abnormal state is detected The recovery mechanism is triggered immediately.

[0186] Regarding the abnormal monitoring of the main monitoring system, please refer to the following formula:

[0187] The terminal device can mainly communicate data regularly through a lightweight protocol similar to the User Datagram Protocol (UDP). When the timestamp corresponding to the heartbeat packet of the main monitoring system is detected, Greater than the preset maximum time difference When the terminal device can determine the health status of the main monitoring system at this time Indicates that an exception exists, so recovery operations are performed directly.

[0188] As for the recovery process mentioned above, similar to the self-healing recovery process for risk abnormal processes in the above steps, the terminal device can first restart the abnormal main monitoring system through the slave monitoring system. If the abnormal monitoring disappears after the restart is successful, the main monitoring system can directly continue the monitoring task. If the health status of the main monitoring system still cannot be restored to normal or cannot be restarted at all after multiple restart operations, the terminal device can directly use the slave monitoring system as the new main monitoring system to take over the abnormal original main monitoring system to continue to perform monitoring tasks. The health status of the original main monitoring system can be marked as a state to be repaired, waiting for subsequent more targeted repair processing. After the repair is completed, the repaired original main monitoring system can also directly replace the previously replaced slave monitoring system to perform monitoring tasks.

[0189] In addition, in this manual, not only the slave monitoring system can monitor the status of the master monitoring system, but each slave monitoring system can also monitor each other, ensuring that each slave monitoring system is in a healthy state even when it is not directly executing the monitoring task.

[0190] In summary, in order to have an overall understanding of the risk detection method based on onboard software and the relationship between the various processing procedures provided in this specification, the following is an overall structural diagram of the risk detection method based on onboard software for explanation and introduction. Figure 2 as shown in .

[0191] Figure 2 The diagram is a schematic diagram of the overall structure of a risk detection method based on onboard software provided in this specification.

[0192] like Figure 2 As shown, the terminal device can be divided into multiple modules according to different processing processes, among which the data collection and software process status control module is responsible for data collection and software process status control. Through this module, the corresponding operating parameter data of the target application in the preset time can be obtained, and the task execution status corresponding to each application process can be promoted and controlled. After collecting the operating parameter data, the terminal device can determine the first round of abnormal evaluation results corresponding to the target application through the abnormal detection module, and according to the first round of abnormal evaluation results, determine the target abnormal monitoring strategy corresponding to the abnormal parameter data based on the operating parameter data through the context perception module.

[0193] Then, according to the target abnormal monitoring strategy and the first round of abnormal assessment results, the preset monitoring strategy is adjusted at least once through the adaptive monitoring module. For each round of adjustment, the operating parameter data of the target application is obtained based on the adjusted monitoring strategy, and then the abnormal assessment result corresponding to the target application after the round of adjustment is determined through the abnormal detection module. Then, according to the first round of abnormal assessment results and the abnormal assessment results corresponding to at least one round of adjustment, the risk detection results for the target application operation process are determined. Next, when it is determined that there is an abnormality in the operation process of the target application, the risk abnormal process is self-healed and recovered through the self-healing system module. In addition, a decision support module can also be provided in the terminal device to realize the reasonable selection of the operation strategy of the overall satellite system in the face of different operating environments mentioned in the above method, as well as the master-slave mutual protection function.

[0194] In addition to the above modules, the terminal device may also be provided with Figure 2 The communication and interaction modules shown in the figure are used to exchange information with ground personnel. When faced with serious abnormal situations that cannot be solved by self-repair, information feedback and help are provided to ground personnel in a timely manner to solve the abnormal fault problem as soon as possible and ensure the overall work efficiency and stable operation of the satellite system.

[0195] From the above content, it can be seen that the risk detection method based on satellite software provided in this specification can determine the first round of abnormal evaluation results corresponding to the target application based on the acquired operating parameter data of the target application within a preset time, and make at least one round of reasonable adjustments to the current monitoring strategy based on the first round of abnormal evaluation results, and obtain the corresponding operating parameter data based on the adjusted monitoring strategy, and then determine the abnormal evaluation results corresponding to each adjustment round for the target application. Finally, the operation process of the target application is risk-detected based on the first round of abnormal evaluation results and the abnormal evaluation results corresponding to at least one round of adjustment to obtain the risk detection results. In addition, when it is determined that there is a risk in the operation process, the method in this specification can also perform self-healing repair on the abnormal process to ensure the normal operation of the satellite system.

[0196] The method of this manual can flexibly select a more suitable, accurate and effective monitoring strategy when facing different abnormal problems, so as to ensure that the abnormal problems are discovered and handled before they cause serious failures. While effectively improving the efficiency of repairing abnormal problems in onboard software, it also greatly ensures the stability of the satellite system in the ever-changing space environment.

[0197] The above are one or more implementation methods of this specification. Based on the same idea, this specification also provides a corresponding risk detection device based on satellite-borne software, such as Figure 3 shown.

[0198] Figure 3 This is a schematic diagram of a risk detection device based on onboard software provided in this specification, including:

[0199] The acquisition module 301 is used to acquire the operation parameter data corresponding to the target application within a preset time period based on a preset monitoring strategy, wherein the target application is a software application running in the satellite;

[0200] An abnormality assessment module 302, used to determine a first round of abnormality assessment results corresponding to the target application according to the operating parameter data;

[0201] The strategy adjustment module 303 is used to adjust the monitoring strategy for at least one round according to the first round of abnormality evaluation results, wherein for each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormality evaluation results corresponding to the previous round of adjustment to obtain the monitoring strategy after the round of adjustment, and based on the monitoring strategy after the round of adjustment, the corresponding operating parameter data within the preset time after the target application completes the round of adjustment is obtained, so as to determine the abnormality evaluation result corresponding to the target application after the round of adjustment according to the corresponding operating parameter data within the preset time after the target application completes the round of adjustment, as the abnormality evaluation result corresponding to the round of adjustment, adjusting the monitoring strategy at least includes: adjusting the monitoring frequency of the target application and adjusting the monitoring data content of the target application;

[0202] The risk detection module 304 is used to perform risk detection on the operation process of the target application according to the first round of abnormality assessment results and the abnormality assessment results corresponding to at least one round of adjustment to obtain risk detection results.

[0203] Optionally, the operating parameter data includes static parameter data and dynamic parameter data corresponding to the target application in a preset duration, and the dynamic parameter data is used to represent a dynamic parameter time series formed by combining parameter data of the target application collected at each time point divided according to preset time intervals within the preset duration in a chronological order;

[0204] The anomaly assessment module 302 is specifically used to determine the static anomaly assessment result corresponding to the target application based on the static parameter data in the operating parameter data, and input the dynamic parameter data in the operating parameter data into a preset anomaly assessment model, so that the anomaly assessment model determines the dynamic anomaly assessment result corresponding to the target application based on the dynamic parameter data; and determines the first round of anomaly assessment results corresponding to the target application based on the static anomaly assessment result and the dynamic anomaly assessment result.

[0205] Optionally, the strategy adjustment module 303 is specifically used to, for each round of adjustment, determine the abnormal parameter data corresponding to the previous round of adjustment from the operating parameter data corresponding to the target application within a preset time period after the previous round of adjustment according to the abnormal evaluation results corresponding to the previous round of adjustment; based on the abnormal parameter data, filter out the target abnormality monitoring strategy corresponding to the abnormal parameter data from the preset abnormality monitoring strategies; based on the target abnormality monitoring strategy, adjust the monitoring strategy after the previous round of adjustment as the monitoring strategy after this round of adjustment.

[0206] Optionally, the policy adjustment module 303 is specifically used to determine, for each round of adjustment, an adjustment amplitude of the monitoring policy adjusted in the previous round according to the abnormal assessment results corresponding to the target application after the previous round of adjustment; determine, based on the adjustment amplitude, a monitoring frequency adjustment range and a monitoring content precision adjustment range of the monitoring policy adjusted in the previous round according to the adjustment amplitude; determine, based on the target abnormal monitoring strategy, the corresponding partially adjustable monitoring strategy in the monitoring policy adjusted in the previous round; and make policy adjustments to the monitoring policy adjusted in the previous round according to the monitoring frequency adjustment range, the monitoring content precision adjustment range and the partially adjustable monitoring strategy.

[0207] Optionally, the risk detection module 304 is specifically used to determine that there is an operation abnormality risk during the operation of the target application when the result of the first round of abnormal assessment is greater than a preset abnormal risk threshold; when the result of the first round of abnormal assessment is not greater than the preset abnormal risk threshold, then for each round of adjustment, it is determined whether the abnormal assessment result corresponding to the target application after the round of adjustment is greater than the abnormal risk threshold; if it is determined that the abnormal assessment result corresponding to the target application after the round of adjustment is greater than the preset abnormal risk threshold, it is determined that there is an operation abnormality risk during the operation of the target application.

[0208] Optionally, the device further comprises:

[0209] The self-healing repair module 305 is used to determine the risk abnormality process corresponding to the target application according to the operating parameter data corresponding to the abnormal assessment result used to determine that the risk detection result indicates the existence of the risk of operation abnormality when it is determined according to the risk detection result that there is an operation abnormality risk during the operation of the target application, and generate a process recovery instruction for the risk abnormality process; according to the process recovery instruction, perform a recovery operation on the risk abnormality process, wherein the recovery operation at least includes an application process restart operation and an increase in resource allocation operation.

[0210] Optionally, the self-healing repair module 305 is specifically used to, when the recovery operation of the risky abnormal process fails according to the process recovery instruction, replace the risky abnormal process with a preset redundant process corresponding to the target application; and continue to execute the process task corresponding to the risky abnormal process based on the redundant process.

[0211] This specification also provides a computer-readable storage medium, which stores a computer program, which can be used to execute the above Figure 1 A risk detection method based on onboard software is provided.

[0212] This manual also provides Figure 4 The one shown corresponds to Figure 1 A schematic diagram of the electronic device. Figure 4 As shown, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The risk detection method based on onboard software.

[0213] In the 1990s, it was very clear whether the improvement of a technology was hardware improvement (for example, improvement of the circuit structure of diodes, transistors, switches, etc.) or software improvement (improvement of the method flow). However, with the development of technology, many improvements of the method flow today can be regarded as direct improvements of the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that the improvement of a method flow cannot be implemented with hardware entity modules. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask chip manufacturers to design and make dedicated integrated circuit chips. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0214] The controller may be implemented in any suitable manner, for example, the controller may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (e.g., software or firmware) executable by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include but are not limited to the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, and the memory controller may also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that, in addition to implementing the controller in a purely computer-readable program code manner, the controller may be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller may be considered as a hardware component, and the devices for implementing various functions included therein may also be considered as structures within the hardware component. Or even, the devices for implementing various functions may be considered as both software modules for implementing the method and structures within the hardware component.

[0215] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0216] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0217] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0218] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, 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 device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0219] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0220] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0221] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0222] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0223] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0224] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0225] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0226] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including storage devices.

[0227] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0228] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A risk detection method based on onboard software, characterized in that: include: Based on a preset monitoring strategy, operating parameter data corresponding to a target application within a preset duration is obtained, wherein the target application is a software application running in a satellite, and the operating parameter data includes static parameter data and dynamic parameter data corresponding to the target application within the preset duration, wherein the static parameter data is discrete data in which there is no strong dependency relationship between a data change process and the running time of the target application, and the dynamic parameter data is continuous data in which there is a strong dependency relationship between a data change process and the running time of the target application; Determine, according to the operating parameter data, a first round of abnormality assessment result corresponding to the target application; According to the first round of abnormality assessment results, the monitoring strategy is adjusted for at least one round, wherein for each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormality assessment results corresponding to the previous round of adjustment to obtain the monitoring strategy after the round of adjustment, and based on the monitoring strategy after the round of adjustment, the corresponding operating parameter data within a preset time after the target application completes the round of adjustment is obtained, so as to determine the abnormality assessment result corresponding to the target application after the round of adjustment according to the corresponding operating parameter data within the preset time after the target application completes the round of adjustment as the abnormality assessment result corresponding to the round of adjustment, and adjusting the monitoring strategy at least includes: adjusting the monitoring frequency of the target application and adjusting the monitoring data content of the target application; According to the first round of abnormality assessment results and the abnormality assessment results corresponding to at least one round of adjustment, risk detection is performed on the operation process of the target application to obtain a risk detection result.

2. The method according to claim 1, characterized in that The operating parameter data includes static parameter data and dynamic parameter data corresponding to the target application in a preset duration, and the dynamic parameter data is used to represent a dynamic parameter time series formed by combining the parameter data of the target application collected at each time point divided according to preset time intervals within the preset duration in a chronological order; Determining the first round of abnormality assessment results corresponding to the target application according to the operating parameter data, specifically including: Determine the static anomaly assessment result corresponding to the target application according to the static parameter data in the operating parameter data, and input the dynamic parameter data in the operating parameter data into a preset anomaly assessment model, so that the anomaly assessment model determines the dynamic anomaly assessment result corresponding to the target application according to the dynamic parameter data; A first-round anomaly assessment result corresponding to the target application is determined according to the static anomaly assessment result and the dynamic anomaly assessment result.

3. The method according to claim 1, characterized in that For each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormal evaluation results corresponding to the previous round of adjustment to obtain the monitoring strategy adjusted in this round, which specifically includes: For each round of adjustment, according to the abnormal evaluation result corresponding to the previous round of adjustment, the abnormal parameter data corresponding to the previous round of adjustment is determined from the operation parameter data corresponding to the target application within the preset time after the previous round of adjustment; According to the abnormal parameter data, a target abnormality monitoring strategy corresponding to the abnormal parameter data is screened out from preset abnormality monitoring strategies; According to the target abnormality monitoring strategy, the monitoring strategy adjusted in the previous round is adjusted as the monitoring strategy adjusted in this round.

4. The method according to claim 3, characterized in that According to the target abnormal monitoring strategy, the monitoring strategy adjusted in the previous round is adjusted, including: For each round of adjustment, the adjustment range of the monitoring strategy adjusted in the previous round is determined according to the abnormal evaluation result corresponding to the target application after the previous round of adjustment; According to the adjustment range, determine the monitoring frequency adjustment range and monitoring content accuracy adjustment range of the monitoring strategy adjusted in the previous round for this round; According to the target abnormal monitoring strategy, determine the corresponding part of the monitoring strategy adjusted in the previous round that can be adjusted; According to the monitoring frequency adjustment range, the monitoring content accuracy adjustment range and the partially adjustable monitoring strategies, the monitoring strategies adjusted in the previous round are adjusted.

5. The method according to claim 1, characterized in that According to the first round of abnormality assessment results and the abnormality assessment results corresponding to at least one round of adjustment, risk detection is performed on the operation process of the target application to obtain risk detection results, which specifically include: When the first round of abnormality assessment result is greater than a preset abnormality risk threshold, it is determined that there is an operational abnormality risk in the operation process of the target application; When the first round of abnormal assessment results is not greater than the preset abnormal risk threshold, then for each round of adjustment, it is determined whether the abnormal assessment result corresponding to the target application after the round of adjustment is greater than the abnormal risk threshold. If it is determined that the abnormal assessment result corresponding to the target application after the round of adjustment is greater than the preset abnormal risk threshold, it is determined that there is an operational abnormality risk during the operation of the target application.

6. The method according to claim 1, characterized in that The method further comprises: When it is determined according to the risk detection result that there is an operation abnormality risk in the operation process of the target application, determining the risk abnormal process corresponding to the target application according to the operation parameter data corresponding to the abnormal assessment result used to determine that the risk detection result indicates that there is an operation abnormality risk, and generating a process recovery instruction for the risk abnormal process; According to the process recovery instruction, a recovery operation is performed on the risk abnormal process, wherein the recovery operation at least includes an application process restart operation and an increase resource allocation operation.

7. The method according to claim 6, characterized in that The method further comprises: When the recovery operation of the risk abnormal process according to the process recovery instruction fails, replacing the risk abnormal process with a preset redundant process corresponding to the target application; The process task corresponding to the risk abnormal process continues to be executed based on the redundant process.

8. A risk detection device based on onboard software, characterized in that: include: an acquisition module, configured to acquire operation parameter data corresponding to a target application within a preset duration based on a preset monitoring strategy, wherein the target application is a software application running in a satellite, and the operation parameter data includes static parameter data and dynamic parameter data corresponding to the target application within the preset duration, wherein the static parameter data is discrete data in which there is no strong dependency relationship between a data change process and the running time of the target application, and the dynamic parameter data is continuous data in which there is a strong dependency relationship between a data change process and the running time of the target application; An abnormality assessment module, used to determine a first round of abnormality assessment results corresponding to the target application according to the operating parameter data; A strategy adjustment module, configured to perform at least one round of adjustment on the monitoring strategy according to the first round of abnormality assessment results, wherein for each round of adjustment, the monitoring strategy adjusted in the previous round is adjusted according to the abnormality assessment results corresponding to the previous round of adjustment to obtain the monitoring strategy after the round of adjustment, and based on the monitoring strategy after the round of adjustment, obtain the corresponding operating parameter data within a preset time after the target application completes the round of adjustment, so as to determine the abnormality assessment result corresponding to the target application after the round of adjustment according to the corresponding operating parameter data within the preset time after the target application completes the round of adjustment, as the abnormality assessment result corresponding to the round of adjustment, and adjusting the monitoring strategy at least includes: adjusting the monitoring frequency of the target application and adjusting the monitoring data content of the target application; The risk detection module is used to perform risk detection on the operation process of the target application according to the first round of abnormal evaluation results and the abnormal evaluation results corresponding to at least one round of adjustment to obtain risk detection results.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 7 is implemented.

Images