Fault self-recovery method based on intelligent doorbell system

Abstract

The invention relates to the technical field of doorbell fault management, in particular to a fault self-recovery method based on an intelligent doorbell system. According to the method, non-direct fault repair demand analysis is carried out from two points of version updating and historical use performance of the target object to judge whether the target object needs to be subjected to system repair so as to reduce the fault risk of the target object, fault feature prediction and repair matching analysis are carried out in an information feedback mode, and the fault repair efficiency is improved. According to the method, rapid fault self-repairing is accurately carried out on the target object in a fault repairing and matching mode, so that the fault self-repairing efficiency of the target object is improved, and repairing and matching feasibility evaluation output analysis is carried out on the collected repairing record data in a deep mode; whether the repair feasibility of the preset repair scheme can be directly output and automatic repair is implemented or not is judged through analysis from the perspective of the repair feasibility of the preset repair scheme, and then the preset repair scheme is reasonably adopted to improve the self-repair effect of the target object.

Description

Technical Field

[0001] The present invention relates to the technical field of doorbell fault management, and in particular to a fault self-recovery method based on an intelligent doorbell system. Background Art

[0002] In recent years, with the continuous upgrading of the intelligent industry, smart homes have gradually entered the daily lives of ordinary people. In order to facilitate people's daily lives, it has become a greater demand for more homes to have sufficient smart technology, and smart doorbells have also emerged. Currently, smart doorbells on the market can meet people's needs for remote control or observation of home conditions through the wake-up function; However, in the prior art, it is impossible to effectively and reasonably manage the self-repair of the faults of the smart doorbell system, thereby reducing the self-repair efficiency of the smart doorbell system, and it is impossible to supervise the indirect fault repair needs from the two points of version update and historical usage performance, which increases the difficulty of self-repair of the smart doorbell system. At the same time, it is impossible to analyze and output the feasibility of the preset self-repair plan, and it is impossible to accurately understand the maintenance of the repair effect of the preset self-repair plan, which reduces the self-repair management efficiency of the smart doorbell system.

[0003] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a fault self-recovery method based on an intelligent doorbell system to solve the above-mentioned technical defects. The present invention performs non-direct fault repair demand analysis from two points of view: version update and historical usage performance of the target object, to determine whether the target object needs system repair, so as to reduce the fault risk of the target object. Fault feature prediction and repair matching analysis are performed by information feedback, that is, the target object is accurately and quickly self-repaired by fault repair matching, so as to improve the fault self-repair efficiency of the target object. The collected repair record data is analyzed in an in-depth manner to evaluate the feasibility of the repair matching, that is, by analyzing from the perspective of the repair feasibility of the preset repair plan, it is determined whether the repair feasibility of the preset repair plan can be directly output and automatically repaired, and then the preset repair plan is reasonably adopted to improve the self-repair effect of the target object.

[0005] The purpose of the present invention can be achieved by the following technical solution: A fault self-recovery method based on an intelligent doorbell system comprises the following steps: Step 1: Set the smart doorbell system as the target object, collect the current version information of the target object, perform version operation obstacle evaluation feedback analysis, and output the obtained version normal instructions or version risk instructions; Step 2: Conduct control obstacle repair evaluation and supervision analysis on the collected control IoT information from the perspective of the historical performance of the target object, perform discrimination processing on the obtained control obstacle evaluation coefficient, and output the obtained fault risk control instruction or stability instruction as feedback; Step 3: Based on the fault feature prediction and repair matching analysis of the target object under information feedback, the obtained revised evaluation coefficient is discriminated and processed. If a valid instruction is obtained, it goes to step 4. If a correction instruction is obtained, feedback is output; Step 4: Analyze the collected working condition information of the target object under the effective instruction, and perform judgment processing on the output result of the fault prediction model. If a fault instruction is obtained, proceed to step 5. If a standard instruction is obtained, output feedback; Step 5: Based on the repair matching feasibility evaluation output analysis under information progression, the obtained repair adoption evaluation coefficient is discriminated and processed, and the obtained repair feedback instructions or available instructions are output as feedback.

[0006] Preferably, the version operation obstacle evaluation feedback analysis process is as follows: The smart doorbell system is set as the target object, the running time period of the target object is collected and set as the time threshold, the current version information of the target object within the time threshold is obtained, the version information includes the version number and the version upgrade date, the text characters are extracted from the version information of the target object, and the string composed of the text characters extracted from the version information of the target object is set as the initial inspection and evaluation recognition string; The latest version information of the target object within the time threshold is obtained, and the string composed of text characters extracted from the latest version information of the target object is set as the standard evaluation identification string. The initial evaluation identification string is compared and analyzed with the standard evaluation identification string one by one to obtain normal version instructions or version risk instructions.

[0007] Preferably, the control obstacle repair assessment supervision analysis process is as follows: The control IoT information of the target object within the time threshold is obtained, and the control IoT information includes the control evaluation coefficient and the measurement and control response index. The number of control evaluation coefficients and measurement and control response indexes that are greater than or equal to the preset control evaluation coefficient threshold and the preset measurement and control response index threshold is set as the control obstacle evaluation coefficient, and the control obstacle evaluation coefficient is judged and processed to obtain a fault risk control instruction or a stability instruction.

[0008] Preferably, the control evaluation coefficient represents the average of the interval durations corresponding to the IoT defect characteristics of the target object, and the IoT defect characteristics include interruptions and freezes; the analysis process of the measurement and control response index is as follows: the response performance value corresponding to the historical control times of the target object is obtained, and the number of times the response performance value is less than a preset response performance value threshold is obtained, and it is set as the measurement and control response index, and the response performance value represents the time between sending an instruction to control the target object and the execution time of the target object.

[0009] Preferably, the fault feature prediction and repair matching analysis process is as follows: Obtain historical operating condition information of multiple groups of target objects within the time threshold, including temperature and abnormal sound value, divide the historical fault information into training set and verification set, preprocess the training set and verification set, preprocessing includes data cleaning and screening, build a fault prediction model based on the preprocessed training set, verify the built fault prediction model through the verification set, obtain the number of deviations between the output results of the fault prediction model and the known results, and set it as the revised evaluation coefficient; The revised evaluation coefficient is judged: if the revised evaluation coefficient is equal to zero, a valid instruction is generated; if the revised evaluation coefficient is not equal to zero, a correction instruction is generated.

[0010] Preferably, when generating a valid instruction, the operating condition information of the current target object within the time threshold is obtained, the operating condition information is input into the fault prediction model, the output result of the fault prediction model is obtained, and the output result of the fault prediction model is discriminated and processed to obtain a compliance instruction or a fault instruction.

[0011] Preferably, the repair matching feasibility evaluation output analysis process is as follows: The output result obtained belongs to the fault code corresponding to the preset fault list, and the preset repair plan is obtained based on the fault code, and the repair record data of the preset repair plan is obtained, the repair record data includes the repair feasibility and the repair performance coefficient, and the repair feasibility and the repair performance coefficient are compared and analyzed with the preset repair feasibility threshold and the preset repair performance coefficient threshold, and the number of repair feasibility and repair performance coefficient that are smaller than the preset repair feasibility threshold and the preset repair performance coefficient threshold is set as the repair adoption evaluation coefficient, and the repair adoption evaluation coefficient is discriminated and processed to obtain a repair feedback instruction or an available instruction.

[0012] Preferably, the continuous running time after each preset repair scheme in the total number of repairs performed using the preset repair scheme corresponding to the fault code is obtained, and the ratio of the number of repairs performed with the preset repair scheme corresponding to the fault code whose continuous running time is greater than the preset continuous running time threshold to the total number of repairs is set as the repair feasibility, and the continuous running time represents the time between the end of the repair using the preset repair scheme corresponding to the fault code and the moment when the same fault code appears again; the ratio of the number of times the response performance value is lower than the preset response performance value within the preset time after the repair of the preset repair scheme corresponding to the fault code is obtained to the total number of times, and it is set as the recovery capability value, and the ratio of the number of repairs performed with the preset repair scheme corresponding to the fault code whose recovery capability value is greater than the preset recovery capability value threshold to the total number of repairs is set as the repair performance coefficient.

[0013] The beneficial effects of the present invention are as follows: (1) The present invention performs indirect fault repair demand analysis from two perspectives: version update and historical performance of the target object, to determine whether the target object needs system repair, so as to reduce the fault risk of the target object. That is, the version operation obstacle evaluation feedback analysis is performed on the version information to determine whether the current version of the target object affects the operation, so as to timely perform version update. The fault risk and repair demand degree of the target object are determined from the perspective of historical performance, so as to timely perform repair management on the target object. (2) The present invention performs fault feature prediction and repair matching analysis by means of information feedback, that is, the target object is accurately and quickly self-repaired by means of fault repair matching, so as to improve the fault self-repair efficiency of the target object, and the repair matching feasibility evaluation output analysis is performed on the collected repair record data in an in-depth manner, that is, by analyzing from the perspective of the repair feasibility of the preset repair plan, it is determined whether the repair feasibility of the preset repair plan can be directly output and automatically repaired, and then the preset repair plan is reasonably adopted to improve the self-repair effect of the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below in conjunction with the accompanying drawings; Figure 1 It is a reference analysis diagram of the method of the present invention; Figure 2 This is a local analysis diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Embodiment 1: See also Figure 1 to Figure 2 As shown, the present invention is a fault self-recovery method based on an intelligent doorbell system, comprising the following steps: Step 1: Set the smart doorbell system as the target object, collect the current version information of the target object, perform version operation obstacle evaluation feedback analysis, and output the obtained version normal instructions or version risk instructions; Step 2: Conduct control obstacle repair evaluation and supervision analysis on the collected control IoT information from the perspective of the historical performance of the target object, perform discrimination processing on the obtained control obstacle evaluation coefficient, and output the obtained fault risk control instruction or stability instruction as feedback; Step 3: Based on the fault feature prediction and repair matching analysis of the target object under information feedback, the obtained revised evaluation coefficient is discriminated and processed. If a valid instruction is obtained, it goes to step 4. If a correction instruction is obtained, feedback is output; Step 4: Analyze the collected working condition information of the target object under the effective instruction, and perform judgment processing on the output result of the fault prediction model. If a fault instruction is obtained, proceed to step 5. If a standard instruction is obtained, output feedback; Step 5: Based on the repair matching feasibility evaluation output analysis under information progression, the obtained repair adoption evaluation coefficient is discriminated and processed, and the obtained repair feedback instruction or available instruction is output as feedback; The present invention performs repair demand analysis from two points of view: version update and historical usage performance of the target object, to determine whether the target object needs system repair, that is, to collect the current version information of the target object, and perform version operation obstacle evaluation feedback analysis on the version information to determine whether the current version of the target object affects the operation, so as to perform version update in time to reduce the failure risk of the target object. The specific version operation obstacle evaluation feedback analysis process is as follows: The smart doorbell system is set as the target object, the running time period of the target object is collected and set as the time threshold, the current version information of the target object within the time threshold is obtained, the version information includes the version number, version upgrade date, etc., the version information of the target object is extracted with text characters, and the string composed of the text character extraction of the version information of the target object is set as the initial inspection and evaluation recognition string; Get the latest version information of the target object within the time threshold, extract the text characters from the latest version information of the target object and set the string as the standard evaluation identification string, and compare and analyze the initial evaluation identification string with the standard evaluation identification string one by one: If the initial check evaluation identification string and the standard evaluation identification string are in one-to-one correspondence, a normal version instruction is generated; If the initial check evaluation identification string and the standard evaluation identification string are in one-to-one correspondence, a version risk instruction is generated, and a normal version instruction or a version risk instruction is output as feedback, so as to update the version information of the target object according to the information feedback to reduce the failure risk of the target object; In the embodiment of the present invention, the collected control IoT information is subjected to control obstacle repair evaluation and supervision analysis from the perspective of historical usage performance, that is, the failure risk and repair demand degree of the target object are judged from the perspective of historical usage performance, so as to timely perform repair management on the target object. The specific control obstacle repair evaluation and supervision analysis process is as follows: The control IoT information of the target object within the time threshold is obtained, and the control IoT information includes the control evaluation coefficient and the measurement and control response index. The number of control evaluation coefficients and measurement and control response indexes that are greater than or equal to the preset control evaluation coefficient threshold and the preset measurement and control response index threshold is set as the control obstruction evaluation coefficient, and the control obstruction evaluation coefficient is discriminated: If the control obstruction evaluation coefficient = 0 or the control obstruction evaluation coefficient = 1, a fault risk control instruction is generated; If the control obstacle evaluation coefficient = 2, a stable instruction is generated, and the fault risk control instruction or stable instruction is output and fed back, so as to conduct reasonable and targeted management of the target object based on the information feedback, so as to reduce the impact of long-term use on the operation of the target object, and at the same time help to ensure the continuous use and stable performance of the target object; In the embodiment of the present invention, the control evaluation coefficient represents the average value of the interval duration corresponding to the IoT defect characteristics of the target object. The IoT defect characteristics include interruption, freeze, etc. It should be noted that the larger the value of the control evaluation coefficient, the smaller the control abnormality risk of the target object; In an embodiment of the present invention, the analysis process of the measurement and control response index is as follows: the response performance value corresponding to the historical control times of the target object is obtained, the number of times the response performance value is less than the preset response performance value threshold is obtained, and it is set as the measurement and control response index. The response performance value represents the time between sending the instruction to control the target object and the execution time of the target object. It should be noted that the measurement and control response index is an influencing parameter reflecting the control performance of the target object. The larger the value of the measurement and control response index, the smaller the control abnormality risk of the target object.

[0017] Embodiment 2: When generating version risk instructions or fault risk control instructions, the fault feature prediction and repair matching analysis under the version update or historical performance abnormality of the target object is carried out, that is, the target object is accurately and quickly self-repaired through fault repair matching to improve the fault self-repair efficiency of the target object. The specific fault feature prediction and repair matching analysis process is as follows: Obtain historical operating condition information of multiple groups of target objects within the time threshold, including temperature, abnormal sound value, etc., divide the historical fault information into a training set and a verification set, preprocess the training set and the verification set, and preprocess the training set and the verification set. The preprocessing includes data cleaning and screening, etc., build a fault prediction model based on the preprocessed training set, verify the constructed fault prediction model through the verification set, obtain the number of deviations between the output results of the fault prediction model and the known results, and set it as the revised evaluation coefficient; In the embodiment of the present invention, the sound abnormality indicates that the decibel of the sound of the target object deviates from the preset range; Perform discriminant processing on the revised evaluation coefficient: If the revised evaluation coefficient is equal to zero, a valid instruction is generated; If the revised evaluation coefficient is not equal to zero, a correction instruction is generated. When the correction instruction is generated, a preset warning operation corresponding to the correction instruction is immediately performed, so as to perform targeted correction on the fault prediction model to improve the extraction accuracy of the fault prediction model; When a valid instruction is generated, the operating condition information of the current target object within the time threshold is obtained, the operating condition information is input into the fault prediction model, the output result of the fault prediction model is obtained, and the output result of the fault prediction model is discriminated: If the output result does not belong to the preset fault list, a compliance instruction is generated, and feedback is output; If the output result belongs to the preset fault list, a fault instruction is generated; When generating a fault instruction, the present invention analyzes the feasibility of the preset repair solution from the perspective of repair feasibility, that is, performs repair matching feasibility evaluation output analysis on the collected repair record data, that is, determines whether the repair feasibility of the preset repair solution can be directly output and automatically repaired, and then reasonably adopts the preset repair solution to improve the self-repair effect of the target object. The specific repair matching feasibility evaluation output analysis process is as follows: The output result is obtained to be a fault code corresponding to the preset fault list, and a preset repair plan is obtained based on the fault code, and the repair record data of the preset repair plan is obtained, the repair record data includes the repair feasibility and the repair performance coefficient, and the repair feasibility and the repair performance coefficient are compared and analyzed with the preset repair feasibility threshold and the preset repair performance coefficient threshold, and the number of repair feasibility and repair performance coefficient that are less than the preset repair feasibility threshold and the preset repair performance coefficient threshold is set as the repair adoption evaluation coefficient, and the repair adoption evaluation coefficient is discriminated: If the repair adoption evaluation coefficient = 1 or the repair adoption evaluation coefficient = 2, a repair feedback instruction is generated. When the repair feedback instruction is generated, a preset warning operation corresponding to the repair feedback instruction is immediately performed to remind the operation management personnel to adopt other methods to perform self-repair processing on the target object, thereby improving the self-repair management efficiency of the target object; If the repair adoption evaluation coefficient = 0, an available instruction is generated. When the available instruction is generated, the preset repair solution corresponding to the fault code is output and fed back, and then the target object is self-repaired according to the preset repair solution to improve the fault self-repair efficiency of the target object; In the embodiment of the present invention, the continuous operation time after the repair by each preset repair scheme in the total number of times of repair using the preset repair scheme corresponding to the fault code is obtained, and the ratio of the number of repairs corresponding to the preset repair scheme corresponding to the fault code whose continuous operation time is greater than the preset continuous operation time threshold to the total number of repairs is set as the repair feasibility. The continuous operation time represents the time between the end of the repair by the preset repair scheme corresponding to the fault code and the moment when the same fault code appears again. It should be noted that the repair feasibility is an influencing parameter reflecting the repair efficiency of the preset repair scheme corresponding to the fault code. The larger the numerical value of the repair feasibility, the higher the feasibility of the repair method by the preset repair scheme. In the embodiment of the present invention, the ratio of the number of times the response performance value is lower than the preset response performance value within the preset time after the fault code corresponding to the preset repair solution is repaired to the total number of times is obtained, and it is set as the recovery capability value, and the ratio of the number of times the recovery capability value is greater than the preset recovery capability value threshold corresponding to the preset repair solution repair times to the total number of times of repair is set as the repair performance coefficient. It should be noted that the larger the value of the repair performance coefficient, the higher the feasibility of the method of repairing by setting the preset repair solution; In summary, the present invention performs indirect fault repair demand analysis from two points of view: version update and historical usage performance of the target object, to determine whether the target object needs system repair, so as to reduce the fault risk of the target object, that is, performs version operation obstacle evaluation feedback analysis on the version information, to determine whether the current version of the target object affects the operation, so as to perform version update in time, and determines the fault risk and repair demand degree of the target object from the perspective of historical usage performance, so as to perform timely repair management on the target object in time; Fault feature prediction and repair matching analysis are performed through information feedback, that is, the target object is accurately and quickly self-repaired through fault repair matching to improve the fault self-repair efficiency of the target object, and the repair matching feasibility evaluation output analysis is performed on the collected repair record data in an in-depth manner, that is, by analyzing from the perspective of the repair feasibility of the preset repair plan, it is determined whether the repair feasibility of the preset repair plan can be directly output and automatically repaired, and then the preset repair plan is reasonably adopted to improve the self-repair effect of the target object.

[0018] The threshold is set to facilitate comparison. The threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data. It does not affect the proportional relationship between the parameter and the quantized value. The size of the coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding operating coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0019] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A fault self-recovery method based on an intelligent doorbell system, characterized in that: The following steps are involved: Step 1: Set the smart doorbell system as the target object, collect the current version information of the target object, perform version operation obstacle evaluation feedback analysis, and output the obtained version normal instructions or version risk instructions; Step 2: Conduct control obstacle repair evaluation and supervision analysis on the collected control IoT information from the perspective of the historical performance of the target object, perform discrimination processing on the obtained control obstacle evaluation coefficient, and output the obtained fault risk control instruction or stability instruction as feedback; Step 3: Based on the fault feature prediction and repair matching analysis of the target object under information feedback, the obtained revised evaluation coefficient is discriminated and processed. If a valid instruction is obtained, it goes to step 4. If a correction instruction is obtained, feedback is output; Step 4: Analyze the collected working condition information of the target object under the effective instruction, and perform judgment processing on the output result of the fault prediction model. If a fault instruction is obtained, proceed to step 5. If a standard instruction is obtained, output feedback; Step 5: Based on the repair matching feasibility evaluation output analysis under information progression, the obtained repair adoption evaluation coefficient is discriminated and processed, and the obtained repair feedback instructions or available instructions are output as feedback.

2. The fault self-recovery method based on the intelligent doorbell system according to claim 1 is characterized in that: The analysis process of the version operation obstacle evaluation feedback is as follows: The smart doorbell system is set as the target object, the running time period of the target object is collected and set as the time threshold, the current version information of the target object within the time threshold is obtained, the version information includes the version number and the version upgrade date, the text characters are extracted from the version information of the target object, and the string composed of the text characters extracted from the version information of the target object is set as the initial inspection and evaluation recognition string; The latest version information of the target object within the time threshold is obtained, and the string composed of text characters extracted from the latest version information of the target object is set as the standard evaluation identification string. The initial evaluation identification string is compared and analyzed with the standard evaluation identification string one by one to obtain normal version instructions or version risk instructions.

3. The fault self-recovery method based on the intelligent doorbell system according to claim 1 is characterized in that: The control obstacle remediation assessment supervision and analysis process is as follows: The control IoT information of the target object within the time threshold is obtained, and the control IoT information includes the control evaluation coefficient and the measurement and control response index. The number of control evaluation coefficients and measurement and control response indexes that are greater than or equal to the preset control evaluation coefficient threshold and the preset measurement and control response index threshold is set as the control obstacle evaluation coefficient, and the control obstacle evaluation coefficient is judged and processed to obtain a fault risk control instruction or a stability instruction.

4. The fault self-recovery method based on the intelligent doorbell system according to claim 3 is characterized in that: The control evaluation coefficient represents the average of the interval durations corresponding to the IoT defect characteristics of the target object, where the IoT defect characteristics include interruptions and freezes. The analysis process of the measurement and control response index is as follows: the response performance value corresponding to the historical control times of the target object is obtained, and the number of times the response performance value is less than the preset response performance value threshold is obtained, and it is set as the measurement and control response index, where the response performance value represents the duration between sending the instruction to control the target object and the execution time of the target object.

5. The fault self-recovery method based on the intelligent doorbell system according to claim 1 is characterized in that: The fault feature prediction and repair matching analysis process is as follows: Obtain historical operating condition information of multiple groups of target objects within the time threshold, including temperature and abnormal sound value, divide the historical fault information into training set and verification set, preprocess the training set and verification set, preprocessing includes data cleaning and screening, build a fault prediction model based on the preprocessed training set, verify the built fault prediction model through the verification set, obtain the number of deviations between the output results of the fault prediction model and the known results, and set it as the revised evaluation coefficient; The revised evaluation coefficient is judged: if the revised evaluation coefficient is equal to zero, a valid instruction is generated; if the revised evaluation coefficient is not equal to zero, a correction instruction is generated.

6. The fault self-recovery method based on the intelligent doorbell system according to claim 5 is characterized in that: When a valid instruction is generated, the operating condition information of the current target object within the time threshold is obtained, the operating condition information is input into the fault prediction model, the output result of the fault prediction model is obtained, and the output result of the fault prediction model is discriminated and processed to obtain a standard instruction or a fault instruction.

7. The fault self-recovery method based on the intelligent doorbell system according to claim 1 is characterized in that: The repair matching feasibility evaluation output analysis process is as follows: The output result obtained belongs to the fault code corresponding to the preset fault list, and the preset repair plan is obtained based on the fault code, and the repair record data of the preset repair plan is obtained, the repair record data includes the repair feasibility and the repair performance coefficient, and the repair feasibility and the repair performance coefficient are compared and analyzed with the preset repair feasibility threshold and the preset repair performance coefficient threshold, and the number of repair feasibility and repair performance coefficient that are smaller than the preset repair feasibility threshold and the preset repair performance coefficient threshold is set as the repair adoption evaluation coefficient, and the repair adoption evaluation coefficient is discriminated and processed to obtain a repair feedback instruction or an available instruction.

8. The fault self-recovery method based on the intelligent doorbell system according to claim 7 is characterized in that: The continuous operation time after each preset repair solution is repaired in the total number of times the preset repair solution corresponding to the fault code is obtained, and the ratio of the number of repair times corresponding to the preset repair solution corresponding to the fault code whose continuous operation time is greater than the preset continuous operation time threshold to the total number of repair times is set as the repair feasibility, and the continuous operation time represents the time from the end of the repair by the preset repair solution corresponding to the fault code to the time when the same fault code appears again; The ratio of the number of times the response performance value is lower than the preset response performance value within the preset time after the fault code corresponding to the preset repair solution is repaired to the total number of times is set as the recovery capability value, and the ratio of the number of times the recovery capability value is greater than the preset recovery capability value threshold corresponding to the preset repair solution repair number to the total number of repairs is set as the repair performance coefficient.

Images