Signal interruption repairing method and device of digital camera and storage medium

Abstract

The invention discloses a signal interruption repair method for a digital camera. The method comprises the following steps: S1, a first network connection module and a second network connection module are built in the digital camera in advance; s2, after disconnection, an interrupt signal is sent to a network setting module for detection; s3, a network setting module detects network setting parameters of the digital camera; s4, forbidding the first network connection module, and starting the second network connection module; s5, acquiring abnormal parameters of disconnection of the camera, and repairing logs and network settings of the router; s6, the serial number and the network parameters of the fault camera are sent to a master control background system, and maintenance and repair requests are sent to a user; the problems that in the prior art, whether a network fault belongs to a hardware reason or a software reason cannot be judged, and the network fault of the digital camera cannot be automatically repaired are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital cameras, and in particular to a method, device and storage medium for repairing signal interruption of a digital camera. Background Art

[0002] In today's digital age, digital cameras are widely used in many fields, such as security monitoring, video conferencing, and distance learning. Among them, digital cameras connected through wireless networks provide users with a convenient user experience, but in actual applications, the stability of their wireless network connections is restricted by many factors. In the existing technology, the network settings of the camera software are crucial to ensure its correct connection with the wireless network, but there are often connection problems caused by improper settings. Most of the factors are summarized into two parts. One is based on the network settings of the digital camera, and the other is that the network settings and security settings of the router lead to the shielding of the connection signal of the digital camera. The existing technology cannot determine whether the network failure is caused by hardware or software, nor can it automatically repair the network failure of the digital camera. It can only be repaired and maintained manually. Therefore, there is an urgent need for a signal interruption repair method for digital cameras. Summary of the invention

[0003] In order to solve the above-mentioned technical problems, the present invention provides a signal interruption repair method, device and storage medium for a digital camera.

[0004] The technical solution of the present invention is achieved in this way:

[0005] A method for repairing signal interruption of a digital camera comprises the following steps:

[0006] S1, pre-installing a first network connection module and a second network connection module in a digital camera;

[0007] S2, monitoring the received wireless signal connection in real time through the wireless network card, and sending an interruption signal to the network setting module for detection after the connection is disconnected;

[0008] S3, the network setting module detects the network setting parameters of the digital camera, resets the network setting parameters, and then detects again whether the network connection signal is reconnected;

[0009] S4, when the wireless network signal is still in a disconnected state after the reset according to step S3, the wireless network signal is searched again and reconnected, and when the wireless network signal is still in a disconnected state, the first network connection module is disabled and the second network connection module is started;

[0010] S5, the second network connection module starts the data connection mode, obtains the connection with the main control background system, sends the network setting parameters of the faulty camera to the main control background system, the main control background system connects to the router before the camera is disconnected and obtains the network log of the router, obtains the abnormal parameters of the camera disconnection, and repairs the faulty camera in the log and network settings of the router;

[0011] S6, enable the first network connection module and disable the second network connection module at the same time, obtain the network connection status, and when the connection with the router is still disconnected, disable the first network connection module and enable the second network connection module at the same time, determine it as a hardware failure, send the number and network parameters of the faulty camera to the main control background system, and send a maintenance and repair request to the user.

[0012] Preferably, the first network connection module and the second network connection module in step S1 are respectively a wireless WIFI network and a data roaming network of a secondary SIM card.

[0013] Preferably, in step S2, the wireless network card monitors the real-time connection signal strength, sends a detection data packet to the router, and the router sends a receiving signal to the wireless network card as a complete signal judgment cycle, and sets the time end threshold of the detection data packet sending and receiving signal to i, and the failure of sending or receiving within i time is judged as a network abnormal state, and sends a network repair request signal to the network setting module;

[0014] Preferably, the network setting module receives the network repair request signal and the interruption signal, and processes them according to step S3;

[0015] Preferably, in step S1, the first network connection module and the second network connection module of the digital camera record a network log, recording network setting parameters, connection status and signal strength, and the total amount of data received and sent. The network setting parameters for the normal connection state are set to Table Y, the network abnormal state is set to Table T, and the signal interruption state is set to Table N.

[0016] A device includes at least one processor, at least one memory and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the above-mentioned signal interruption repair method of a digital camera is implemented.

[0017] A storage medium stores computer program instructions, wherein the computer program instructions are executed by a processor to implement the above-mentioned signal interruption repair method for a digital camera.

[0018] The present invention solves the problem that the prior art cannot determine whether a network failure is caused by hardware or software, and cannot automatically repair a network failure of a digital camera. The present invention increases the way to determine and repair the failure through a dual network connection module, thereby increasing the possibility of restoring the connection. At the same time, it monitors in real time and sets a time end threshold to determine network anomalies, thereby promptly discovering problems and initiating repair requests, thereby reducing the impact of interruptions. The present invention can also record various types of information with the help of network logs, making it easy to reset setting parameters based on historical normal states and improve repair accuracy. Fourth, there are targeted processing procedures in different connection anomalies, which can quickly locate and attempt to solve the problem. Fifth, the fault information can be fed back to the main control background system, which is convenient for unified management and maintenance and repair arrangements, ensuring the stability and continuity of the camera network connection, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of a signal interruption repair method of a digital camera of the present invention. DETAILED DESCRIPTION

[0020] In order to further explain the technical means and effects taken by the present invention to achieve the predetermined invention purpose, exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of methods and systems consistent with some aspects of the present application as detailed in the attached claims.

[0021] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0022] Example 1

[0023] A method for repairing signal interruption of a digital camera comprises the following steps:

[0024] S1, pre-installing a first network connection module and a second network connection module in a digital camera;

[0025] Preferably, the first network connection module and the second network connection module in step S1 are respectively a wireless WIFI network and a data roaming network of a secondary SIM card;

[0026] Preferably, in step S1, the first network connection module and the second network connection module of the digital camera record a network log, recording network setting parameters, connection status and signal strength, and the total amount of data received and sent, the network setting parameters of the normal connection state are set to table Y, the network abnormal state is set to table T, and the signal interruption state is set to table N;

[0027] The digital camera is pre-installed with a first network connection module and a second network connection module. The first network connection module is a wireless WIFI network, which is used to achieve network connection through a nearby wireless router in a normal environment to meet daily video transmission and other needs; the second network connection module is a data roaming network of the SIM card secondary card, which is used as a backup network connection method to provide an alternative network access path when the WIFI network fails and cannot be connected normally, ensuring that the camera can still maintain data transmission capabilities to a certain extent.

[0028] At the same time, both network connection modules have the function of recording network logs, which record in detail network setting parameters (such as IP address, subnet mask, gateway, network name, password, etc.), connection status (connected, connecting, disconnected, etc.), signal strength, and total amount of data received and sent. In order to facilitate the rapid identification and processing of different states in the future, the network setting parameters of the normal connection state are organized into Table Y, the network abnormal state is set in Table T, and the signal interruption state is set in Table N.

[0029] S2, monitoring the received wireless signal connection in real time through the wireless network card, and sending an interruption signal to the network setting module for detection after the connection is disconnected;

[0030] Preferably, in step S2, the wireless network card monitors the real-time connection signal strength, sends a detection data packet to the router, and the router sends a receiving signal to the wireless network card as a complete signal judgment cycle, and sets the time end threshold of the detection data packet sending and receiving signal to i, and the failure of sending or receiving within i time is judged as a network abnormal state, and sends a network repair request signal to the network setting module;

[0031] Preferably, the network setting module receives the network repair request signal and the interruption signal, and processes them according to step S3;

[0032] The wireless network card in the digital camera has the important task of real-time monitoring of the connection status of the received wireless signal. It adopts a comprehensive monitoring method, not just limited to simply detecting the signal strength, but by actively sending detection data packets to the router and waiting for the router to send the received signal back to the wireless network card, thus forming a complete and dynamic signal judgment cycle;

[0033] This method can more comprehensively and accurately evaluate the stability and quality of wireless signal connections. In each signal judgment cycle, the wireless network card will analyze the sent and received signals according to preset rules and algorithms to obtain information about signal strength, signal integrity, transmission delay, etc., so as to have an in-depth understanding of the current wireless signal connection status;

[0034] In order to detect network anomalies in a timely manner, the time threshold for detecting data packet sending and receiving signals is set to i. The setting of this time threshold needs to take into account a variety of factors, such as the complexity of the network environment, the processing power of the equipment, and the normal delay range of data transmission. For example, in a general home or office network environment, i can be initially set to 5 seconds, but in some more complex network environments (such as large public places, industrial plants, etc.), it may be necessary to appropriately extend or shorten the threshold according to actual conditions;

[0035] Within this set time threshold i, if the sending of the detection data packet fails, that is, the wireless network card fails to successfully send the data packet within the specified time, or fails to receive the receiving signal sent back by the router, then it will be determined as a network abnormality. Once the network is determined to be abnormal, the wireless network card will immediately trigger the corresponding mechanism, generate and send a network repair request signal to the network setting module, so as to start the subsequent repair process in time to avoid long-term interruption of the camera function due to network problems.

[0036] S3, the network setting module detects the network setting parameters of the digital camera, resets the network setting parameters, and then detects again whether the network connection signal is reconnected;

[0037] Preferably, in step S3, the network setting module resets the real-time network setting to the network setting parameters of the most recent normal connection state through the network log;

[0038] When the network setting module receives a network repair request signal or interruption signal from the wireless network card, it will immediately start a comprehensive detection process for the network setting parameters of the digital camera. First, it will go deep into the previously recorded network logs, accurately locate the network setting parameter record corresponding to the current moment, and conduct a detailed comparison and analysis with the network setting parameters of the most recent normal connection state (i.e. the parameters recorded in Table Y);

[0039] During the comparison process, each key network setting parameter will be checked one by one, including whether the IP address has changed, whether the subnet mask matches, whether the gateway setting is correct, whether the network name (SSID) and network password are accurate, etc. Through this comprehensive and detailed comparison, possible parameter setting anomalies can be quickly discovered, which are likely to be the direct cause of signal interruption or network anomalies;

[0040] Once a difference or anomaly is found during the comparative analysis, the network setting module will automatically start the parameter reset function to accurately reset the real-time network settings to the network setting parameters of the most recent normal connection state (i.e. reset according to the parameter values ​​in Table Y). This step is intended to try to restore the previous normal connection configuration to eliminate the signal interruption problem caused by parameter setting errors or anomalies, so that the camera's network connection can be restored to normal as soon as possible;

[0041] When resetting parameters, the network setting module will strictly follow the preset procedures and rules to ensure that each parameter can be accurately reset to the correct value. At the same time, in order to ensure the stability and reliability of the reset process, the relevant parameters will be checked multiple times before and after the reset to prevent new problems caused by reset errors;

[0042] After completing the reset of the network setting parameters, the network setting module will not stop there, but will immediately detect whether the network connection signal can be reconnected. It will try to re-establish the connection with the external network (such as a router) by cooperating with related hardware components such as the wireless network card, and monitor various signal feedback and status changes during the connection establishment process;

[0043] In this way, you can preliminarily determine whether the signal interruption problem can be solved by simply resetting the parameters. If during the reconnection detection process, it is found that the connection can be successfully established and the network signal is stable, then it means that the signal interruption is likely caused by abnormal network setting parameters and has been successfully fixed by resetting the parameters; on the contrary, if the connection still cannot be established, then you need to further investigate other possible causes of signal interruption and proceed to the subsequent repair steps.

[0044] S4, when the wireless network signal is still in a disconnected state after the reset according to step S3, the wireless network signal is searched again and reconnected, and when the wireless network signal is still in a disconnected state, the first network connection module is disabled and the second network connection module is started;

[0045] Preferably, in step S4, the wireless network signal is re-searched and reconnected, and after resetting the network setting parameters, the name of the router that was last connected is obtained according to the network log, and the router with the name is reconnected, and a reconnection threshold is preset. When the router name cannot be searched, it is determined that the router is abnormal. When the router name is retrieved and the connection cannot be established, it is determined that the state of the first network connection module is abnormal, the first network connection module is disabled, and the second network connection module is started;

[0046] According to step S3, if the network setting parameters are still disconnected after being reset, the wireless network signal needs to be searched again more deeply and reconnected. In this process, the network setting module extracts the name information of the router that was last connected based on the previously recorded network log.

[0047] Then, with the name of this router as the target, start a new search and connection attempt for the router. During the re-search process, the wireless network card will send a search signal within its detectable range at a certain frequency (such as every few seconds) to try to find the wireless signal emitted by the target router. At the same time, the searched wireless signals will be preliminarily screened and identified to ensure that the correct signal found is indeed emitted by the target router, rather than other interfering signals or signals emitted by routers with similar names.

[0048] In order to avoid unlimited search and connection attempts, which would lead to waste of resources and long repair time, a reconnection threshold is preset. This reconnection threshold can be flexibly set according to the actual situation, for example, the number of reconnection attempts can be set to 3 times. At each reconnection attempt, the network settings module will record the number of connection attempts and compare it with the reconnection threshold.

[0049] If the router name cannot be found during the search process, that is, after multiple searches (reaching the reconnection threshold), the wireless signal from the target router cannot be found, then it is considered that the router is abnormal. This may be caused by reasons such as the router itself being faulty, the router being turned off, or problems with the wireless signal transmission function of the router.

[0050] If the router name is retrieved, but the connection cannot be established after multiple attempts (reaching the reconnection threshold), it is determined that the first network connection module is abnormal. This may be due to hardware failure, software failure, driver problem, etc. of the first network connection module (wireless WIFI network module) itself, which makes it unable to establish a normal connection with the router.

[0051] When it is determined that the status of the first network connection module is abnormal, in order to try to restore the data connection through the backup network connection method and ensure that the basic functions of the camera are not greatly affected, the first network connection module (i.e., the wireless WIFI network module) will be disabled and the second network connection module (i.e., the data roaming network module of the SIM card secondary card) will be started.

[0052] When executing the module switching operation, the first network connection module will be shut down first, and all operations related to the network connection will be stopped, including stopping sending and receiving wireless signals, shutting down related hardware drivers, etc. Then, the second network connection module will be started, including initializing related hardware devices, loading drivers, configuring network parameters, etc., to ensure that the second network connection module can enter the working state as soon as possible and try to establish a connection with the external network through the backup network connection method.

[0053] S5, the second network connection module starts the data connection mode, obtains the connection with the main control background system, sends the network setting parameters of the faulty camera to the main control background system, the main control background system connects to the router before the camera is disconnected and obtains the network log of the router, obtains the abnormal parameters of the camera disconnection, and repairs the faulty camera in the log and network settings of the router;

[0054] Establish a connection with the main control backend system:

[0055] When the router is judged to be abnormal, the first network connection module is disabled and the second network connection module is activated. The second network connection module will start the data connection mode and actively establish a connection with the main control background system. During the connection establishment process, certain communication protocols and security mechanisms will be followed to ensure the stability of the connection and the security of data transmission.

[0056] For example, encrypted communication protocols, such as SSL / TLS, may be used to encrypt the transmitted data to prevent the data from being stolen or tampered with during transmission. At the same time, identity authentication operations will be performed to ensure that both parties in the connection (the camera and the main control background system) can accurately identify each other's identity to avoid illegal access.

[0057] Data transmission and analysis:

[0058] Once the connection is established with the main control system, the camera will send its complete network setting parameters to the main control system. These network setting parameters include all relevant information previously recorded in the network log, such as IP address, subnet mask, gateway, network name (SSID), network password, etc., so that the main control system can fully understand the network settings of the camera.

[0059] After receiving these parameters, the main control backend system will immediately establish a connection with the router before the camera was disconnected. During the connection process, the corresponding communication protocols and security mechanisms will also be followed to ensure the legitimacy and stability of the connection. Then, the main control backend system will obtain the network log and network setting parameters of the router. Through detailed analysis of this information, it can accurately obtain the abnormal parameters of the camera disconnection, and then perform targeted repair operations on the router log and network settings.

[0060] Router repair operations:

[0061] When repairing the router's logs and network settings, the main control backend system will adjust the router's related settings based on the abnormal parameters obtained. For example, if the router's IP address is found to be set incorrectly, it will be corrected to the correct value; if the network name (SSID) or network password does not match, it will be adjusted or reset accordingly.

[0062] At the same time, for other issues that may affect network connection reflected in the network log of the router, such as network congestion, signal interference, etc., the main control backend system will also take corresponding measures to deal with them according to the specific situation. For example, for network congestion problems, it may be alleviated by adjusting the bandwidth allocation strategy of the router; for signal interference problems, it may be recommended that users adjust the location of the router or change the frequency band, etc.

[0063] Exception handling:

[0064] If the network connection fails during the connection between the main control backend system and the router, it is considered that the router network connection is abnormal, and a maintenance and repair request is sent to the user in a timely manner. When sending the request, the user will be clearly informed that the router may have a serious network problem and needs further inspection and repair. At the same time, some possible cause analysis and suggestions will be provided to help the user better understand the problem and how to solve it.

[0065] S6, enable the first network connection module and disable the second network connection module at the same time, obtain the network connection status, and when the connection with the router is still disconnected, disable the first network connection module and enable the second network connection module at the same time, determine it as a hardware failure, send the number and network parameters of the faulty camera to the main control background system, and send a maintenance and repair request to the user.

[0066] Preferably, when it is determined that the router is abnormal, the first network connection module is disabled, the second network connection module is started, the connection with the main control background system is obtained through the second network connection module, the main control background system is connected to the router and obtains the network log and network setting parameters of the router, and the router is repaired abnormally. Preferably, when the main control background system cannot establish a network connection with the router, it is determined that the router network connection is abnormal, and a maintenance and repair request is sent to the user.

[0067] A device includes at least one processor, at least one memory and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the above-mentioned signal interruption repair method of a digital camera is implemented.

[0068] A storage medium stores computer program instructions, wherein the computer program instructions are executed by a processor to implement the above-mentioned signal interruption repair method for a digital camera.

[0069] Example 2

[0070] The present embodiment provides a method for repairing signal interruption of a digital camera, comprising the following steps:

[0071] S1, determine the scope of data collection, comprehensively collect data related to digital camera signal interruption from multiple sources, and ensure the diversity and completeness of the data to provide rich information for neural network training.

[0072] Camera data: In-depth mining of the camera's own operating log, which covers the dynamic changes of various key parameters over time. For example, detailed records of real-time values ​​of signal strength, changes in frame rate, resolution settings, and fluctuations in internal device temperature. At the same time, accurately capture the specific timestamp of each signal interruption, as well as the overall device status of the camera just before the interruption, such as whether it is in different operating modes such as busy recording, live broadcasting, or relatively static shooting.

[0073] Network environment data: Comprehensively collect information about the network environment where the camera is located. This includes detailed logs of the router, focusing on real-time changes in network traffic, the number of devices currently connected to the router, and the usage of each frequency band. In addition, it is also necessary to investigate possible wireless signal interference sources in the area, such as the frequency bands and transmission power used by other nearby wireless devices, as these factors may affect the signal transmission of the camera.

[0074] Manually record data: Assign a dedicated person to record the surrounding environmental conditions and specific camera operations each time a signal interruption occurs. Record in detail environmental factors such as light intensity, ambient temperature, humidity, and the specific operations the camera is performing (such as recording high-definition video, live broadcasting, simple static shooting, etc.). At the same time, record the various repair measures taken for signal interruptions and the actual results achieved after these measures are implemented, such as whether the signal is successfully restored and the stability of the signal after restoration.

[0075] S2, data cleaning and preliminary organization, the collected raw data are carefully cleaned and preliminarily organized to improve data quality, ensure that the data can accurately reflect the actual situation, and lay a good foundation for subsequent neural network training.

[0076] Handling missing values: For the missing value problem in the data set, appropriate filling methods are used according to the characteristics of different parameters. For example, for the key parameter of signal strength, if missing values ​​appear, the trend of signal strength changes in the previous and next time periods can be analyzed first, and then the average filling method can be used, that is, the average value of signal strength in the previous and next adjacent time periods is calculated, and the average value is filled into the position of the missing value. For other similar numerical parameters, such as device temperature, similar reasonable filling methods can also be used according to specific circumstances.

[0077] Identify and handle outliers: Identify outliers in the data set by setting a reasonable threshold range. For example, based on past experience and industry standards, it is determined that the normal signal strength range should be within a certain interval (such as -30dBm to -10dBm). If a signal strength value exceeds this range, it is considered an outlier. For the identified outliers, further analyze the cause of their generation. If the outlier is caused by a temporary equipment failure or short-term interference, but it returns to normal later, the data can be retained and annotated; if it is obviously wrong data (such as extremely large or extremely small unreasonable values ​​of signal strength), it will be deleted directly to avoid interference with subsequent analysis and training.

[0078] Remove duplicate data: Carefully check the data set and delete duplicate data records to ensure that each data has unique information value and avoid inaccurate patterns learned by the model due to duplicate data during the neural network training process.

[0079] S3, data labeling and classification, accurately labels and classifies the cleaned and preliminarily organized data, so that the neural network can clearly identify signal interruptions of different states and types, thereby improving the prediction accuracy of the model.

[0080] Label the signal status: Label each data record in the data set according to the actual situation of the signal. Label the time period when the signal is transmitting normally as "normal", and the time period when the signal is interrupted as "interrupted". Through this simple and clear labeling method, the neural network can first distinguish the two basic states of the signal: normal and interrupted.

[0081] Segmented interruption cause labeling: On the basis of labeling signal interruptions as "interruptions", the data is further segmented and labeled according to the specific causes of the interruptions. For example, the interruption caused by low signal strength is labeled as "weak signal interruption"; the interruption caused by network congestion due to excessive data transmission in the network is labeled as "network congestion interruption"; the interruption caused by the high temperature of the camera device due to long-term operation, which affects the signal transmission, is labeled as "device overheating interruption"; the interruption caused by the camera's own hardware failure (such as wireless network card damage, antenna failure, etc.) is labeled as "other hardware failure interruption"; the interruption caused by software problems (such as camera driver failure, related application conflicts, etc.) is labeled as "software problem interruption", etc. Through such detailed segmentation and labeling, the neural network can more accurately learn the characteristic patterns of signal interruptions caused by different reasons during the training process, so that it can accurately determine the cause of the interruption and take targeted repair measures in subsequent fault judgment.

[0082] S4, data formatting and set partitioning: The cleaned and labeled data sets are standardized and organized in a format suitable for neural network input, and reasonably divided into different subsets for model training, verification and testing to ensure the scientificity and effectiveness of model training.

[0083] S41, data formatting, organize each data record in a format acceptable to the neural network. Usually, each data record is organized into a vector form, and each element of the vector corresponds to a parameter value related to the signal interruption and a signal interruption mark. For example, a vector may contain elements such as signal strength value, network traffic value, device temperature value, camera operation mode code (such as the number 1 for recording, 2 for live broadcast, 3 for static shooting, etc.) and signal interruption mark (such as 0 for normal, 1 for interruption). Through this formatting process, the data can be smoothly input into the neural network for processing.

[0084] S42, data set division: divide the sorted data set into training set, validation set and test set according to a certain ratio. The common division ratio is 70% for training set, 20% for validation set and 10% for test set. In specific operations, the data set can be divided flexibly according to the actual size of the data set. For example, if 1,000 valid data records are collected after cleaning and annotation, 700 of them are used as training set, 200 as validation set and 100 as test set. The training set is used to allow the neural network to learn the patterns and rules in the data; the validation set is used to evaluate and adjust the performance of the model during the training process to prevent overfitting; the test set is used to evaluate the final performance of the model after the model training is completed to determine whether the model can accurately predict the actual situation.

[0085] S5, neural network model selection and construction;

[0086] S51, analyze data characteristics and requirements, and select the appropriate neural network architecture. According to the characteristics of the data collected, organized and analyzed in the early stage, as well as the specific needs of digital camera signal interruption repair, carefully select the most suitable neural network architecture to ensure that the model can effectively process the input data and accurately predict the signal interruption situation.

[0087] S52, Multilayer Perceptron (MLP) Consideration: If the collected data is mainly presented as some discrete parameter values, and the relationship between these parameters is relatively simple and direct, such as single numerical parameters such as signal strength, device temperature, network traffic, and their relationship with signal interruption is relatively clear, then Multilayer Perceptron (MLP) may be a more appropriate choice. MLP can handle this kind of feature vector-based input data well, and through its multi-layer neuron structure, it can perform nonlinear transformation on the input data, thereby realizing the classification or prediction of signal interruption.

[0088] S53, Convolutional Neural Network (CNN) Consideration: When the data has certain spatial or temporal correlation, Convolutional Neural Network (CNN) may be more advantageous. For example, if we consider that the video frame data of the camera may have some potential correlation with the signal interruption (for example, the image features in the video frame may reflect some abnormal conditions before the signal interruption), or the signal strength change data in a continuous time period has certain spatial distribution characteristics (such as the change trend of the signal strength in a certain area in different time periods), then CNN can use its unique structures such as convolutional layers and pooling layers to explore the relationship between the potential features in the video frame image and the signal interruption, or capture the change rules of parameters such as signal strength at different time points and their association with the interruption.

[0089] S54, Recurrent Neural Network (RNN) Consideration: If the data presents obvious time series characteristics, that is, the changes of various parameters (such as signal strength, device temperature, etc.) are continuous and dependent over time, then Recurrent Neural Network (RCCN) and its variants (such as Long Short-Term Memory Network (LSTM), Gate Recurrent Unit (GRU), etc.) may be a better choice. RNN can handle such data that changes with time series well. Through its internal loop structure, it remembers the state information of the previous moment, thereby capturing the change law of parameters such as signal strength at different time points and their association with interrupts.

[0090] S55, determining the specific parameter settings of the neural network. After selecting a suitable neural network architecture, it is necessary to further determine the specific parameter settings of the network, including the number of nodes in the input layer, hidden layer, and output layer, etc., to ensure that the network can accurately process the input data and output the expected prediction results.

[0091] S551, input layer setting: Determine the number of nodes of the input layer according to the dimension of the input data vector, that is, the number of parameters related to signal interruption considered. For example, if 10 related parameters such as signal strength, network traffic, device temperature, camera operation mode, etc. are considered in the data collection stage, then the input layer is set to 10 nodes, so that each node corresponds to an input parameter, so that the data can be accurately input into the neural network for processing.

[0092] S552, Hidden layer settings: The number of hidden layers and the number of nodes in each layer need to be determined through experiments and adjustments. Generally speaking, you can set a smaller number of hidden layers and nodes at the beginning, and then gradually increase or adjust them according to the performance during training. For example, first set 2 hidden layers, each with 20 nodes. During the training process, pay close attention to evaluation indicators such as accuracy and recall on the validation set. If you find that the performance is not ideal, try to increase the number of hidden layers or nodes. At the same time, when increasing the number of hidden layers or nodes, be careful to avoid overfitting, that is, the model fits the training data too much, resulting in a decrease in performance on the test set.

[0093] S553 Output layer setting: Determine the number of nodes in the output layer according to the target to be predicted. In the digital camera signal interruption repair scenario, the output layer can be set to 2 nodes, representing the two states of "normal" and "interruption", so that the neural network can directly determine whether the signal is interrupted; or set multiple nodes according to different interruption reasons, such as setting to 5 nodes, corresponding to different types of interruption situations such as "weak signal interruption", "network congestion interruption", "device overheating interruption", "other hardware failure interruption", "software problem interruption", etc., so as to more accurately determine the cause of the interruption and take targeted repair measures.

[0094] S6, model training, setting training parameters. Reasonable setting of neural network training parameters has a crucial impact on the training effect and performance of the model. It is directly related to whether the model can accurately learn the patterns and laws in the data and play a good role in subsequent fault judgment.

[0095] S61, learning rate setting: The learning rate determines the step size of the model's weight update at each iteration. A learning rate that is too large may cause the model to fail to converge, that is, the model cannot find a stable optimal solution during the training process, so that the error between the predicted result and the actual result cannot be continuously reduced; a learning rate that is too small may make the training process too slow, and it will take a lot of time for the model to achieve good performance. Generally, the learning rate can be set to 0.01 first, and then adjusted according to the performance of the model on the validation set during the training process. If it is found that the accuracy, recall rate and other indicators of the model on the validation set have not been significantly improved, or there are large fluctuations, it may be necessary to adjust the learning rate appropriately, such as increasing or decreasing the learning rate by a certain proportion (such as a step size of 0.005), and then retraining.

[0096] S62, Iteration number setting: Iteration number refers to the number of rounds of model training. Usually, as the number of iterations increases, the performance of the model will gradually improve, but after a certain extent, overfitting may occur, that is, the model overfits the training data, resulting in a decrease in performance on the test set. At the beginning, the number of iterations can be set to 1000, and the performance on the validation set can be observed during the training process. If there are signs of overfitting, such as the accuracy and recall rate on the validation set starting to decrease after a certain stage, the number of iterations can be appropriately reduced, such as reducing the number of iterations to 800 or other appropriate values, and then retraining.

[0097] S63, Batch size setting: Batch size refers to the amount of data input into the model during each training. A suitable batch size can improve training efficiency. Common batch sizes include 32 and 64. You can first select 32 as the batch size and then adjust it according to the training effect. If you find that the model converges slowly during training, or there are problems such as insufficient memory, you can consider increasing the batch size, such as adjusting the batch size to 64; if you find that the model is overfitting during training, you can also try to reduce the batch size, such as adjusting the batch size to 16, and then retrain.

[0098] S64, start training, input the training set data into the constructed neural network model, start training according to the set training parameters, let the model continuously learn the patterns and rules in the data, adjust its own weights and biases, so as to minimize the error between the predicted results and the actual results.

[0099] S65, for the multi-layer perceptron (MLP) model: the training process is to continuously update the weights and biases of the network through the back-propagation algorithm, so as to minimize the error between the predicted results output by the network and the actual results. Specifically, in each iteration, a batch of training set data (according to the set batch size) is first input into the network, and the output result of the network is obtained after the forward propagation calculation of the network. Then, based on the error between the output result and the actual result, the gradient of each node is calculated through the back-propagation algorithm, and then the weights and biases of the network are updated according to the gradient. By repeating this process continuously until the set number of iterations is reached, the error between the output result of the network and the actual result is gradually reduced, and finally reaches a relatively stable minimum value.

[0100] S66, for the convolutional neural network (CNN) model: it is also trained based on the back-propagation algorithm, but because CNN has unique structures such as convolutional layers and pooling layers, its training process is relatively complicated. In each iteration, a batch of training set data is first input into the network, and the output result of the network is obtained after a series of operations such as convolution operations of the convolutional layer and pooling operations of the pooling layer. Then, based on the error between the output result and the actual result, the gradient of each node is calculated through the back-propagation algorithm, and then the weight and bias of the network are updated according to the gradient. By repeating this process continuously until the set number of iterations is reached, the error between the output result of the network and the actual result gradually decreases, and finally reaches a relatively stable minimum value.

[0101] S67, for the recurrent neural network (RNN) model: its training process is also based on the back-propagation algorithm, but because RNN has an internal loop structure, its training process also has some special features. In each iteration, a batch of training set data is first input into the network, and then processed by the RNN loop structure to obtain the output result of the network. Then, based on the error between the output result and the actual result, the gradient of each node is calculated through the back-propagation algorithm, and then the weight and bias of the network are updated according to the gradient. By repeating this process continuously until the set number of iterations is reached, the error between the output result of the network and the actual result gradually decreases, and finally reaches a relatively stable minimum value.

[0102] S7, model evaluation and adjustment, evaluate model performance on the validation set. During the model training process, regularly evaluate the model performance on the validation set to timely understand the model training effect, identify possible problems, and adjust the model according to the evaluation results to ensure that the model can accurately predict the actual situation.

[0103] S71 Select evaluation indicators: Select appropriate evaluation indicators to measure the performance of the model according to the specific situation. Common evaluation indicators include accuracy, recall, F1 value, etc. Accuracy refers to the ratio of the number of correctly predicted samples to the total number of predicted samples; recall refers to the ratio of the number of correctly predicted samples to the number of actual signal interruption samples; F1 value is an indicator that comprehensively considers accuracy and recall, and the calculation formula is: F1 = 2 * (accuracy * recall) / (accuracy + recall). These indicators reflect the prediction ability of the model from different angles. By comprehensively analyzing these indicators, you can fully understand the performance of the model.

[0104] S72, calculate the evaluation index: on the validation set, calculate the corresponding evaluation index value according to the prediction results and actual results of the model. For example, assuming that on the validation set, the number of samples predicted correctly is 80 and the total number of predicted samples is 100, then the accuracy rate = 80 / 100 = 0.8; assuming that the number of samples with actual signal interruption is 60, then the recall rate = 80 / 60 = 1.33 (the recall rate is greater than 1 here because the number of samples predicted correctly is greater than the number of samples with actual signal interruption, which may exist in practice, such as predicting some situations that were originally thought to be normal but are actually interrupted); F1 value = 2*(0.8*1.33) / (0.8+1.33) = 1.02 (this is just to demonstrate the calculation process, and the F1 value should be between 0 and 1 in practice). By regularly calculating these evaluation indicators, it is possible to timely understand the performance changes of the model on the validation set so that timely measures can be taken to make adjustments.

[0105] S73. Adjust the model according to the evaluation results. Based on the evaluation results on the validation set, if the performance of the model is found to be unsatisfactory, such as low accuracy, recall or F1 value, the model needs to be adjusted according to the specific situation to improve the performance of the model so that it can more accurately predict the actual situation.

[0106] S74, dealing with overfitting problems: If the performance is not ideal due to overfitting of the model, you may need to take the following measures to make adjustments. First, you can try to reduce the number of hidden layers or the number of nodes in each layer, which can reduce the fitting ability of the model so that it does not overfit the training data, thereby improving the performance on the test set. For example, if you find that the accuracy of the model on the validation set is low, and after analysis it is found that it is because the model is overfitting, you can try to reduce the hidden layers of the neural network model from 2 layers to 1 layer, or add an L2 regularization term to the loss function to improve the performance of the model. Adding a regularization term can limit the fitting ability of the model to a certain extent, so that it pays more attention to the general laws of the data during training, rather than focusing too much on the details of the training data.

[0107] S75, dealing with underfitting problems: If the performance is not ideal due to underfitting of the model, the following measures may be needed for adjustment. First, you can try to increase the number of hidden layers or the number of nodes in each layer, which can improve the model's fitting ability and enable it to better learn the patterns and rules in the data. For example, if it is found that the accuracy of the model on the validation set is low, and after analysis it is found that it is because the model is underfitting, then you can try to increase the hidden layers of the neural network model from 2 to 3, or increase the number of nodes in each layer from the original 20 to 30, etc. (the specific increase can be determined based on actual conditions and multiple tests). At the same time, you can also adjust the training parameters such as the learning rate appropriately. If the learning rate is set too low, it may cause the model to update the weight step size too small during the training process, making it difficult for the model to quickly learn the effective information in the data, resulting in underfitting. At this time, you can try to increase the learning rate appropriately, such as from the original 0.001 to 0.01 (similarly, the specific adjustment range needs to be determined in combination with the actual training effect), so that the model can update the weight with a more appropriate step size during training, speed up the learning speed, and better fit the data. In addition, you can also consider extending the number of iterations and giving the model more training rounds to fully learn the patterns and regularities in the data. For example, if the number of iterations was originally set to 500, you can try to increase it to 800 or even more. However, when increasing the number of iterations, you must continue to pay attention to the performance of the model on the validation set to prevent overfitting problems. Through these comprehensive adjustment measures, it is expected that the unsatisfactory model performance caused by underfitting will be improved, so that the model can more accurately predict and judge the signal interruption of digital cameras.

[0108] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for repairing signal interruption of a digital camera, characterized in that: The steps include: S1, pre-installing a first network connection module and a second network connection module in a digital camera; S2, monitoring the received wireless signal connection in real time through the wireless network card, and sending an interruption signal to the network setting module for detection after the connection is disconnected; S3, the network setting module detects the network setting parameters of the digital camera, resets the network setting parameters, and then detects again whether the network connection signal is reconnected; S4, when the wireless network signal is still in a disconnected state after the reset according to step S3, the wireless network signal is searched again and reconnected, and when the wireless network signal is still in a disconnected state, the first network connection module is disabled and the second network connection module is enabled; S5, the second network connection module starts the data connection mode, obtains the connection with the main control background system, sends the network setting parameters of the faulty camera to the main control background system, the main control background system connects to the router before the camera is disconnected and obtains the network log of the router, obtains the abnormal parameters of the camera disconnection, and repairs the faulty camera in the log and network settings of the router; S6, enable the first network connection module and disable the second network connection module at the same time, obtain the network connection status, and when the connection with the router is still disconnected, disable the first network connection module and enable the second network connection module at the same time, determine it as a hardware failure, send the number and network parameters of the faulty camera to the main control background system, and send a maintenance and repair request to the user.

2. A method for repairing signal interruption of a digital camera according to claim 1, characterized in that: The first network connection module and the second network connection module in step S1 are respectively a wireless WIFI network and a data roaming network of a secondary SIM card.

3. The method for repairing signal interruption of a digital camera according to claim 1, characterized in that: In step S2, the wireless network card monitors the real-time connection signal strength by sending a detection data packet to the router, and the router sends a receiving signal to the wireless network card as a complete signal judgment cycle, and sets the time end threshold of the detection data packet sending and receiving signal to i. Failure to send or receive within i time is judged as a network abnormal state, and a network repair request signal is sent to the network setting module.

4. The method for repairing signal interruption of a digital camera according to claim 1, characterized in that: The network setting module receives the network repair request signal and the interruption signal, and processes them according to step S3.

5. The method for repairing signal interruption of a digital camera according to claim 1, characterized in that: In step S1, the first network connection module and the second network connection module of the digital camera record a network log, recording network setting parameters, connection status and signal strength, and the total amount of data received and sent. The network setting parameters of the normal connection state are set to Table Y, the network abnormal state is set to Table T, and the signal interruption state is set to Table N.

6. The method for repairing signal interruption of a digital camera according to claim 1, characterized in that: In step S3, the network setting module resets the real-time network setting to the network setting parameters of the most recent normal connection state through the network log.

7. The method for repairing signal interruption of a digital camera according to claim 1, characterized in that: In step S4, the wireless network signal is re-searched and reconnected. After resetting the network setting parameters, the name of the router that was last connected is obtained according to the network log, and the router with this name is reconnected. A reconnection threshold is preset. When the router name cannot be searched, it is determined that the router is abnormal. When the router name is retrieved and the connection cannot be established, it is determined that the state of the first network connection module is abnormal, the first network connection module is disabled, and the second network connection module is started.

8. The method for repairing signal interruption of a digital camera according to claim 1, characterized in that: When it is determined that the router is abnormal, the first network connection module is disabled, the second network connection module is started, and a connection is obtained with the main control background system through the second network connection module. The main control background system is connected to the router and obtains the network log and network setting parameters of the router, and the router is repaired abnormally. Preferably, when the main control background system cannot establish a network connection with the router, it is determined that the router network connection is abnormal, and a maintenance and repair request is sent to the user.

9. A device comprising at least one processor, at least one memory and computer program instructions stored in the memory, wherein when the computer program instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

10. A storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method described in any one of claims 1 to 8 is implemented.

Images