A background control signal processing system and method for a smart door lock

Abstract

The application discloses a kind of background control signal processing system and method for intelligent door lock, it is related to data analysis technical field, including: setting a kind of intelligent door lock;The intelligent door lock is connected with smart home device by internet of things;Smart home device is equipped with data transmission function's shooting device, based on the shooting device gets shooting snapshot, obtains the historical use data of smart home device, calculates the use rate of smart home device;And by calculating the failure rate and emergency handling rate of smart home device, the equipment use evaluation value of user to smart home device and the comprehensive evaluation value of user are obtained;When the intelligent door lock executes locking operation, the shooting device is detected to smart home device by internet of things, and the comprehensive evaluation value of equipment use evaluation value and user is calculated in real time and corresponding early warning is carried out.The application realizes the fusion perception of user behavior and equipment state, and can avoid the risk caused by forgetting to turn off the appliance or abnormal not disposal.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, and particularly relates to a background control signal processing system and method for a smart door lock. BACKGROUND

[0002] With the rapid development of the Internet of Things and smart home technology, the smart door lock, as the core interactive entrance in the smart home system, has been widely applied in home security, access management and other scenes. The existing smart door lock usually has functions of identity recognition, remote unlocking, abnormal alarm and the like, can be linked with part of home devices, and realizes basic security management. However, the existing technology mainly focuses on the security of the door lock, and lacks deep perception of the use state of indoor smart home devices and user behaviors.

[0003] In the smart home scene, air conditioners, televisions, lighting, electric water heaters and other devices are frequently used. These devices may have faults such as overload, temperature anomaly, communication interruption and the like during operation. If the user fails to turn off the device in time when going out or locking, or fails to effectively deal with the fault when the device fails, energy waste, safety hazards and even fire risks are easily caused. At present, some smart home systems can collect the operation data of the devices and generate use records, but are usually limited to start-stop monitoring at the device level, and it is difficult to realize comprehensive quantitative evaluation of the user individual use habit, device fault occurrence rate and emergency handling capacity.

[0004] In addition, the warning mechanism of the traditional smart door lock mainly depends on a single sensor or simple rules, such as triggering an alarm when detecting that the door is not closed, violent lock picking and the like, and cannot dynamically judge based on the interaction process of the user and the home device. Thus, the safety and intelligent level of the smart home as a whole are affected.

[0005] Therefore, how to perform the locking operation of the smart door lock at the same time, combine the use rate, fault rate and emergency handling rate of the indoor smart home device and the user, establish a quantitative method for user comprehensive evaluation and device use evaluation, and make real-time warning based on the quantitative method, has become a problem to be solved for improving the safety and intelligent level of the smart door lock and the smart home system. SUMMARY

[0006] The present application aims to provide a background control signal processing system and method for a smart door lock to solve the problems in the prior art.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a background control signal processing method for a smart door lock, specifically comprising the following steps:

[0008] An intelligent door lock is provided; the intelligent door lock is connected with smart home devices through the Internet of Things;

[0009] The smart home device is equipped with a shooting device with data transmission function, a snapshot is obtained based on the shooting device, historical use data of the smart home device is acquired, and the use rate of the smart home device is calculated according to the operation time length in the historical use data;

[0010] A set of fault events of different smart home devices is acquired, and the fault rate and emergency handling rate of the smart home device are calculated based on the statistical fault occurrence number and the response time length of emergency handling;

[0011] Based on the use rate, fault rate and emergency handling rate of the smart home device, a device use evaluation value of the smart home device and a comprehensive evaluation value of the user are calculated;

[0012] When the smart door lock performs a locking operation, a shooting device is called through the Internet of Things to detect the smart home device, and the device use evaluation value and the comprehensive evaluation value of the user are calculated in real time and corresponding warning is given.

[0013] A smart door lock is provided;

[0014] The smart door lock comprises a local database and a warning device;

[0015] The local database is used to store user face recognition information and warning records;

[0016] The smart door lock is connected with the smart home device through the Internet of Things, and is connected to the user mobile device through the Internet;

[0017] The warning device is used for warning.

[0018] For the smart home device, the smart home device is equipped with a shooting device with data transmission function, which is used to record the use data of the smart home device;

[0019] The historical use data of the smart home device is acquired; the smart home device is recorded as a1, …, ai, …, an; wherein a1, …, ai, …, an represents the 1st, …, i, …, n smart home device; the snapshot of the shooting device is analyzed, and the user is marked, and the user is recorded as b1, …, bj, …, bm; wherein b1, …, bj, …, bm represents the 1st, …, j, …, m user;

[0020] Through continuous snapshot, the operation time length t of a user bj using any smart home device ai once is recorded bj ai At the same time, the total time length T of collecting the use of the smart home device once is compared, and the use rate k(bj_ai) of the user bj to the smart home device ai is calculated, which is represented as: k(bj_ai)=t bjai / T; sequentially obtaining the usage rates of different smart home devices by all users;

[0021] Further, the acquisition of the fault event set of different smart home devices, based on the statistical fault occurrence times and the response time of emergency handling, calculates the fault rate and emergency handling rate of smart home devices, specifically:

[0022] The total duration of the use of the smart home device once refers to the duration from the opening of the device to the closing of the device.

[0023] For a smart home device ai, define the fault event set E of the smart home device ai, represented as: E = [e1,..., el,..., eq]; wherein e1,..., el,..., eq represents the 1st,..., lth,..., qth fault type appeared in the history of the smart home device ai; for a user bj, calculate the fault rate p(bj) of the fault type el triggered in the use of the smart home device ai once; represented as: p(bj) = N emg (ai,el) / N total (ai); wherein N emg (ai,el) represents the number of times of triggering el fault of the smart home device ai within a certain period; N total (ai) represents the number of times of use of the smart home device ai by the user bj;

[0024] For a fault el, obtain the average duration of the occurrence of the fault el in the history; obtain the response time of the emergency handling of the user bj to the occurred fault el; take the average duration of the occurrence of the fault el and the response time of the emergency handling of the user bj to the occurred fault el as the benchmark, calculate the emergency handling rate of the user bj to the fault el in the smart home device ai;

[0025] Preferably, for a fault el, obtain the average duration of the occurrence of the fault el in the history; obtain the response time of the emergency handling of the user bj to the occurred fault el; take the average duration of the occurrence of the fault el and the response time of the emergency handling of the user bj to the occurred fault el as the benchmark, calculate the emergency handling rate of the user bj to the fault el in the smart home device ai, specifically:

[0026] Step 1. Based on the response time of the emergency handling of the user bj to the fault el in the smart home device ai, construct a response time set {t1,..., tu,..., tc}; wherein t1,..., tu,..., tc represents the response time of the emergency handling of the 1st,..., uth,..., cth fault el; take the response time of the emergency handling of the cth fault el as the base, get the experience cumulative distribution function of the emergency handling of the user bj to the fault el in the smart home device ai , characterized as: ; wherein, represents the probability that the response time t of the user bj to handle the fault el in the smart home device ai is less than the empirical quantile parameter x; x represents the empirical quantile parameter; t represents the response time identifier of the emergency handling;

[0027] Step 2. Quantify the response time performance score S of the emergency handling of the user bj to the fault el in the smart home device ai time , characterized as: ; wherein, tv represents the average duration of the occurrence of the fault el in the history; tu represents the response time of the user bj to the emergency handling of the occurred fault el; σ represents the standard deviation of the response time set; f represents an adjustment coefficient;

[0028] Step 3. Pre-set the empirical quantile parameter as x', and obtain ; wherein, characterizes the good or bad degree of the performance of the user in one emergency handling relative to the historical sample;

[0029] Step 4. Calculate the emergency handling rate g(bj, ai_el) of the user bj to the fault el in the smart home device ai; ; wherein, α and β represent the weight factors of the response time performance score and the emergency handling rate respectively, and α+β=1.

[0030] Further comprising:

[0031] S1, the emergency handling rates of the user bj to all faults in the smart home device ai are calculated by the method of step 1-step 4 in turn, denoted as [g(bj, ai_e1), …, g(bj, ai_el), …, g(bj, ai_eq)]; g(bj, ai_e1), …, g(bj, ai_el), …, g(bj, ai_eq) represent the emergency handling rates of the user bj to the 1st, …, lth, …, qth class of faults in the smart home device ai;

[0032] According to the emergency handling rates of the user bj to the 1st, …, lth, …, qth class of faults in the smart home device ai, the device use evaluation value Z(bj_ai) of the user bj to the smart home device ai is calculated, characterized as:

[0033] ; wherein, w l represents the occurrence probability of the lth class of faults;

[0034] S2. Calculate the emergency response rate of user bj for all faults in different smart home devices in sequence. Based on the emergency response rate of user bj for all faults in different smart home devices, calculate the comprehensive evaluation value R(bj) of user bj, which is represented as: R(bj) = Σ n Z(bj_ai);

[0035] The comprehensive evaluation values ​​of different users are obtained sequentially and denoted as [R(b1),…,R(bj),…,R(bm)]; where R(b1),…,R(bj),…,R(bm) represent the comprehensive evaluation values ​​of the 1st,…,jth,…,mth users, respectively.

[0036] Furthermore, including:

[0037] When the smart door lock performs the locking operation, it performs user face recognition and calls the shooting device through the Internet of Things. When the smart home device is turned on, it takes a snapshot of the preset area of ​​the smart home device. If the snapshot taken by the shooting device does not detect the user, it issues an alert and sends the corresponding smart home device to the mobile terminal of the smart door lock that identifies the user in real time through a pop-up window.

[0038] Otherwise, the user in the snapshot is detected, and the device usage evaluation value of the detected user on the current smart home device is calculated based on the method in S1. When the device usage evaluation value is less than the preset first safety threshold, a real-time warning is issued.

[0039] When multiple smart home devices are detected, a comprehensive evaluation value of the detected user is calculated based on the method in S2. When the comprehensive evaluation value is less than a preset second safety threshold, a real-time warning is issued.

[0040] A background control signal processing system for smart door locks includes a data acquisition and storage module, a signal control and data transmission module, a fitting calculation module, and an early warning module;

[0041] The data acquisition and storage module is used to equip smart home devices with a shooting device that has data transmission function, obtain snapshots based on the shooting device, acquire historical usage data of smart home devices, and support data storage.

[0042] The signal control and data transmission module is used to connect the smart door lock to smart home devices via the Internet of Things. When the smart door lock performs a locking operation, it calls the camera device through the Internet of Things to detect the smart home devices and transmits the detection results to the fitting calculation module.

[0043] The fitting calculation module is used to calculate the usage rate of smart home devices based on the operation time in the historical usage data; by statistically analyzing the number of failures and the response time of emergency handling, it calculates the failure rate and emergency handling rate of smart home devices; and then, based on the usage rate, failure rate, and emergency handling rate of smart home devices, it calculates the user's device usage evaluation value and the user's comprehensive evaluation value.

[0044] The early warning module is used to issue early warnings.

[0045] It also includes an access control module;

[0046] The permission control module is used to control the shooting permissions of the shooting device and the access permissions for shooting snapshots.

[0047] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention establishes a multi-dimensional comprehensive evaluation mechanism by combining the operating status of indoor smart home devices, failure rate, and user response time to emergency handling when the smart door lock performs the locking operation. Compared with existing technologies, this not only achieves the integrated perception of user behavior and device status, avoiding risks caused by forgetting to turn off appliances or failing to handle abnormalities, but also quantifies the user's emergency handling capabilities, intuitively reflecting their efficiency in handling different device failures, thereby improving the accuracy and foresight of early warnings. At the same time, this solution can proactively issue reminders or warnings when the user is away, enhancing the security and intelligence level of the smart home system, and can dynamically adjust the evaluation threshold according to the device types, usage habits, and user characteristics of different households, possessing good scalability and adaptability. Attached Figure Description

[0048] Figure 1 This is a flowchart illustrating a background control signal processing method for a smart door lock according to the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Example: Figure 1 As shown, the present invention provides a technical solution, a method for processing backend control signals for smart door locks, specifically including the following steps:

[0051] A smart door lock is installed; the smart door lock is connected to smart home devices via the Internet of Things (IoT);

[0052] Install a smart door lock;

[0053] The smart lock includes a local database and an early warning device;

[0054] The local database is used to store user facial recognition information and early warning records;

[0055] The smart door lock connects to smart home devices via the Internet of Things (IoT) and to the user's mobile device via the Internet;

[0056] The warning device is used for issuing warnings.

[0057] The smart home device is equipped with a camera device that has data transmission function. A snapshot is taken based on the camera device to obtain historical usage data of the smart home device. The usage rate of the smart home device is calculated based on the operation time in the historical usage data.

[0058] Obtain a set of fault events for different smart home devices, and calculate the fault rate and emergency response rate of smart home devices based on the number of fault occurrences and the response time of emergency handling.

[0059] For smart home devices, the smart home devices are equipped with a camera device with data transmission function to record the usage data of the smart home devices;

[0060] Acquire historical usage data of smart home devices; the smart home devices are denoted as a1, ..., ai, ..., an; where a1, ..., ai, ..., an represents the 1st, ..., i, ..., nth smart home device; analyze the snapshots taken by the camera device, mark the users, and denot the users as b1, ..., bj, ..., bm; where b1, ..., bj, ..., bm represents the 1st, ..., j, ..., mth user;

[0061] By continuously taking snapshots, the duration t of a user bj's operation on any smart home device AI is recorded. bj ai Simultaneously, by comparing the total usage time T of the smart home devices with the data collected per use, the usage rate k(bj_ai) of the user bj for the smart home device ai is calculated, represented as: k(bj_ai) = t bj ai / T; This will sequentially obtain the usage rate of different smart home devices for all users;

[0062] Furthermore, the process of obtaining a set of fault events for different smart home devices, and calculating the fault rate and emergency response rate of smart home devices based on the statistical frequency of fault occurrences and emergency response time, specifically involves:

[0063] The total usage time of a smart home device refers to the duration from when the device is turned on to when it is turned off.

[0064] For a smart home device ai, define a set of fault events E for the smart home device ai, represented as: E=[e1,…,el,…,eq]; where e1,…,el,…,eq represent the 1st,…,l,…,qth fault types that occur in the history of the smart home device ai; for a user bj, calculate the fault rate p(bj) of triggering fault type el in one use of the smart home device ai; represented as: p(bj=N emg (ai,el) / N total (ai); where N emg (ai,el) represents the number of times the smart home device ai triggers an el fault within a certain period; N total (ai) represents the number of times user bj uses the smart home device ai;

[0065] For a certain fault el, obtain the average duration of the fault el in history; obtain the response time of a certain user bj to the fault el; based on the average duration of the fault el and the response time of user bj to the fault el, calculate the emergency handling rate of user bj for the fault el in the smart home device ai.

[0066] Preferably, for a certain fault el, the average duration of the fault el in history is obtained; the response time of a user bj in handling the fault el is obtained; based on the average duration of the fault el and the response time of user bj in handling the fault el, the emergency handling rate of user bj for fault el in smart home device AI is calculated, specifically as follows:

[0067] Step 1. Based on the response times of historical user bj to emergency handling of faults in smart home device ai, construct a response time set {t1, ..., tu, ..., tc}; where t1, ..., tu, ..., tc represent the response times of emergency handling of the 1st, ..., uth, ..., cth faults in el; using the response times of the cth emergency handling of el as the basis, obtain the empirical cumulative distribution function of user bj's emergency handling of faults in smart home device ai. It is characterized as follows: ;in, This indicates the probability that the response time t of user bj in handling a fault el in smart home device ai is less than the empirical quantile parameter x; x represents the empirical quantile parameter; t represents the emergency handling response time identifier.

[0068] Step 2. Quantify the response time efficiency score (S) of user bj for emergency handling of AI malfunctions in smart home devices. time It is characterized as follows: Where tv represents the average duration of the fault el in history; tu represents the response time of user bj to the fault el; σ represents the standard deviation of the response time set; and f is the adjustment coefficient.

[0069] It should be noted that if the user handles the situation quickly during the fault, A score close to 1; if the processing time is close to or exceeds the average duration, the score approaches 0.

[0070] The average duration tv = (t1 + ... + t + ... + tc) / c, and the standard deviation σ are also existing technologies, which will not be elaborated on here. The adjustment coefficient f is used to differentiate and quantify the responses of different faults of different smart home devices, and can be adjusted according to the actual situation.

[0071] Step 3. Preset the empirical quantile parameter to x', and obtain ;in, It characterizes the degree to which a user performs better or worse in an emergency response compared to historical samples;

[0072] Step 4. Calculate the emergency response rate g(bj, ai_el) of user bj to the fault el in smart home device ai; Where α and β represent the weighting factors of response time performance score and emergency response rate, respectively, and α+β=1.

[0073] It is important to note that Indicates "than" in history Faster or equal to The proportion of "if" The smaller value indicates that the current response is faster than most historical times, which is a good performance. There are different options depending on the different smart home devices;

[0074] It is not an evaluation of absolute time, but rather a comparison of user response time with historical distribution to see whether the user is "above average" or "below average"; the numerical range is [0,1]; the closer to 1, the faster the user's response is compared with most historical samples (excellent); the closer to 0, the slower the user's response is compared with most historical samples (poor).

[0075] Based on the usage rate, failure rate, and emergency response rate of the smart home devices, calculate the user's device usage evaluation value and the user's comprehensive evaluation value for the smart home devices.

[0076] Furthermore, including:

[0077] S1. Calculate the emergency response rate of user bj for all faults in smart home device ai using the methods in steps 1-4, denoted as [g(bj, ai_e1), ..., g(bj, ai_el), ..., g(bj, ai_eq)]; g(bj, ai_e1), ..., g(bj, ai_el), ..., g(bj, ai_eq) represent the emergency response rate of user bj for the first, ..., l, ..., q types of faults in smart home device ai;

[0078] Based on user bj's emergency response rate for type 1, ..., l, ..., q faults in smart home device ai, calculate user bj's device usage evaluation value Z(bj_ai), which is represented as:

[0079] Among them, w l This represents the probability of occurrence of type l fault;

[0080] The probability of occurrence of type l faults is calculated using historical data.

[0081] S2. Calculate the emergency response rate of user bj for all faults in different smart home devices in sequence. Based on the emergency response rate of user bj for all faults in different smart home devices, calculate the comprehensive evaluation value R(bj) of user bj, which is represented as: R(bj) = Σ n Z(bj_ai);

[0082] The comprehensive evaluation values ​​of different users are obtained sequentially and denoted as [R(b1),…,R(bj),…,R(bm)]; where R(b1),…,R(bj),…,R(bm) represent the comprehensive evaluation values ​​of the 1st,…,jth,…,mth users, respectively.

[0083] When the smart door lock performs the locking operation, the camera device is called through the Internet of Things to detect smart home devices, calculate the device usage evaluation value and the user's comprehensive evaluation value in real time, and issue corresponding warnings.

[0084] Furthermore, including:

[0085] When the smart door lock performs the locking operation, it performs user face recognition and calls the shooting device through the Internet of Things. When the smart home device is turned on, it takes a snapshot of the preset area of ​​the smart home device. If the snapshot taken by the shooting device does not detect the user, it issues an alert and sends the corresponding smart home device to the mobile terminal of the smart door lock that identifies the user in real time through a pop-up window.

[0086] Otherwise, the user in the snapshot is detected, and the device usage evaluation value of the detected user on the current smart home device is calculated based on the method in S1. When the device usage evaluation value is less than the preset first safety threshold, a real-time warning is issued.

[0087] When multiple smart home devices are detected, a comprehensive evaluation value of the detected user is calculated based on the method in S2. When the comprehensive evaluation value is less than a preset second safety threshold, a real-time warning is issued.

[0088] It should be noted that the shooting device should be pre-set with shooting permissions, which should be set to the area where the device to be monitored is located.

[0089] Among them, smart home devices should be selected based on actual conditions.

[0090] It should be noted that the first security threshold can be set as the average value of the device usage evaluation of the corresponding smart home device in history; similarly, the second security threshold can be obtained.

[0091] When multiple users are detected, the comprehensive evaluation values ​​of all detected users are summed.

[0092] A background control signal processing system for smart door locks includes a data acquisition and storage module, a signal control and data transmission module, a fitting calculation module, and an early warning module;

[0093] The data acquisition and storage module is used to equip smart home devices with a shooting device that has data transmission function, obtain snapshots based on the shooting device, acquire historical usage data of smart home devices, and support data storage;

[0094] The signal control and data transmission module is used to connect the smart door lock to smart home devices via the Internet of Things (IoT). When the smart door lock performs the locking operation, it calls the camera device through the IoT to detect the smart home devices and transmits the detection results to the fitting calculation module.

[0095] The fitting calculation module is used to calculate the usage rate of smart home devices based on the operation time in the historical usage data; by statistically analyzing the number of failures and the response time of emergency handling, it calculates the failure rate and emergency handling rate of smart home devices, and then, based on the usage rate, failure rate, and emergency handling rate of smart home devices, it calculates the user's device usage evaluation value and the user's comprehensive evaluation value.

[0096] The early warning module is used to issue early warnings.

[0097] It also includes a privacy protection module;

[0098] It also includes an access control module;

[0099] The access control module is used to control the shooting permissions of the shooting device and access permissions for shooting snapshots;

[0100] This includes: the shooting area of ​​the shooting device should be set in advance;

[0101] Implement access control for viewing captured snapshots.

[0102] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention establishes a multi-dimensional comprehensive evaluation mechanism by combining the operating status of indoor smart home devices, failure rate, and user response time to emergency handling when the smart door lock performs the locking operation. Compared with existing technologies, this not only achieves the integrated perception of user behavior and device status, avoiding risks caused by forgetting to turn off appliances or failing to handle abnormalities, but also quantifies the user's emergency handling capabilities, intuitively reflecting their efficiency in handling different device failures, thereby improving the accuracy and foresight of early warnings. At the same time, this solution can proactively issue reminders or warnings when the user is away, enhancing the security and intelligence level of the smart home system, and can dynamically adjust the evaluation threshold according to the device types, usage habits, and user characteristics of different households, possessing good scalability and adaptability.

[0103] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for processing backend control signals for smart door locks, characterized in that: Specifically, the steps include the following: A smart door lock is installed; the smart door lock is connected to smart home devices via the Internet of Things (IoT); The smart home device is equipped with a camera device that has data transmission function. A snapshot is taken based on the camera device to obtain historical usage data of the smart home device. The usage rate of the smart home device is calculated based on the operation time in the historical usage data. Obtain a set of fault events for different smart home devices, and calculate the fault rate and emergency response rate of smart home devices based on the number of fault occurrences and the response time of emergency handling. The calculation of the emergency response rate specifically includes the following steps: Step 1. Based on the response times of historical user bj to emergency handling of fault el in smart home device ai, construct a response time set {t1, ..., tu, ..., tc}; where ai represents the i-th smart home device, i∈[1,n]; bj represents the j-th user, j∈[1,m]; t1, ..., tu, ..., tc represent the response times of emergency handling of fault el for the 1st, ..., u, ..., cth faults; using the response times of the cth emergency handling of fault el as the basis, obtain the empirical cumulative distribution function of user bj's emergency handling of fault el in smart home device ai. It is characterized as follows: ;in, This indicates the probability that the response time t of user bj in handling a fault el in smart home device ai is less than the empirical quantile parameter x; x represents the empirical quantile parameter; t represents the emergency handling response time identifier. Step 2. Quantify the response time efficiency score (S) of user bj for emergency handling of AI malfunctions in smart home devices. time It is characterized as follows: Where tv represents the average duration of the fault el in history; tu represents the response time of user bj to the fault el; σ represents the standard deviation of the response time set; and f is the adjustment coefficient. Step 3. Preset the empirical quantile parameter to x', and obtain ;in, It characterizes the degree to which a user performs better or worse in an emergency response compared to historical samples; Step 4. Calculate the emergency response rate g(bj, ai_el) of user bj to the fault el in smart home device ai; Where α and β represent the weighting factors of response time performance score and emergency response rate, respectively, and α+β=1; Based on the usage rate, failure rate, and emergency response rate of the smart home devices, calculate the user's device usage evaluation value and the user's comprehensive evaluation value for the smart home devices. When the smart door lock performs the locking operation, the camera device is called through the Internet of Things to detect smart home devices, calculate the device usage evaluation value and the user's comprehensive evaluation value in real time, and issue corresponding warnings.

2. The background control signal processing method for a smart door lock according to claim 1, characterized in that: include: The smart lock includes a local database and an early warning device; The local database is used to store user facial recognition information and early warning records; The smart lock connects to the user's mobile device via the Internet; The warning device is used for issuing warnings.

3. The background control signal processing method for a smart door lock according to claim 2, characterized in that: include: The smart home device is equipped with a camera with data transmission function to record the usage data of the smart home device; Acquire historical usage data of smart home devices; the smart home devices are denoted as a1, ..., ai, ..., an; where a1, ..., ai, ..., an represents the 1st, ..., i, ..., nth smart home device; analyze the snapshots taken by the camera device, mark the users, and denot the users as b1, ..., bj, ..., bm; where b1, ..., bj, ..., bm represents the 1st, ..., j, ..., mth user; By continuously taking snapshots, the duration t of a user bj's operation on any smart home device AI is recorded. bj ai Simultaneously, by comparing the total usage time T of the smart home devices with the total usage time T, the usage rate k(bj) of the user bj for the smart home device ai is calculated, which is represented as: k(bj_ai) = t bj ai / T; This will sequentially obtain the usage rate of different smart home devices for all users; The total usage time of a smart home device refers to the duration from when the device is turned on to when it is turned off.

4. The background control signal processing method for a smart door lock according to claim 3, characterized in that: The process of obtaining a set of fault events for different smart home devices, and calculating the fault rate and emergency response rate of smart home devices based on the statistical frequency of fault occurrences and emergency response time, specifically involves: For a smart home device ai, define a set of fault events E for the smart home device ai, represented as: E=[e1,…,el,…,eq]; where e1,…,el,…,eq represent the 1st,…,l,…,qth fault types that occur in the history of the smart home device ai; for a user bj, calculate the fault rate p(bj) of triggering fault type el in one use of the smart home device ai; represented as: p(bj=N emg (ai,el) / N total (ai); where N emg (ai,el) represents the number of times the smart home device ai triggers an el fault within a certain period; N total (ai) represents the number of times user bj uses the smart home device ai.

5. The background control signal processing method for a smart door lock according to claim 4, characterized in that: include: S1. Calculate the emergency response rate of user bj for all faults in smart home device ai using the methods in steps 1-4, denoted as [g(bj, ai_e1), ..., g(bj, ai_el), ..., g(bj, ai_eq)]; g(bj, ai_e1), ..., g(bj, ai_el), ..., g(bj, ai_eq) represent the emergency response rate of user bj for the first, ..., l, ..., q types of faults in smart home device ai; Based on user bj's emergency response rate for type 1, ..., l, ..., q faults in smart home device ai, calculate user bj's device usage evaluation value Z(bj_ai), which is represented as: Among them, w l This represents the probability of occurrence of type l fault; S2. Calculate the emergency response rate of user bj for all faults in different smart home devices in sequence. Based on the emergency response rate of user bj for all faults in different smart home devices, calculate the comprehensive evaluation value R(bj) of user bj, which is represented as: R(bj) = Σ n Z(bj_ai); The comprehensive evaluation values ​​of different users are obtained sequentially and denoted as [R(b1),…,R(bj),…,R(bm)]; where R(b1),…,R(bj),…,R(bm) represent the comprehensive evaluation values ​​of the 1st,…,jth,…,mth users, respectively.

6. The background control signal processing method for a smart door lock according to claim 5, characterized in that: include: When the smart door lock performs the locking operation, it performs user face recognition and calls the shooting device through the Internet of Things. When the smart home device is turned on, it takes a snapshot of the preset area of ​​the smart home device. If the snapshot taken by the shooting device does not detect the user, it issues an alert and sends the corresponding smart home device to the mobile terminal of the smart door lock that identifies the user in real time through a pop-up window. Otherwise, the user in the snapshot is detected, and the device usage evaluation value of the detected user on the current smart home device is calculated based on the method in S1. When the device usage evaluation value is less than the preset first safety threshold, a real-time warning is issued. When multiple smart home devices are detected, a comprehensive evaluation value of the detected user is calculated based on the method in S2. When the comprehensive evaluation value is less than a preset second safety threshold, a real-time warning is issued.

7. A background control signal processing system for a smart door lock, employing the background control signal processing method for a smart door lock as described in any one of claims 1-6, characterized in that: It includes a data acquisition and storage module, a signal control and data transmission module, a fitting calculation module, and an early warning module; The data acquisition and storage module is used to equip smart home devices with a shooting device that has data transmission function, obtain snapshots based on the shooting device, acquire historical usage data of smart home devices, and support data storage. The signal control and data transmission module is used to connect the smart door lock to smart home devices via the Internet of Things. When the smart door lock performs a locking operation, it calls the camera device through the Internet of Things to detect the smart home devices and transmits the detection results to the fitting calculation module. The fitting calculation module is used to calculate the usage rate of smart home devices based on the operation time in the historical usage data. By statistically analyzing the number of failures and the response time of emergency handling, the failure rate and emergency handling rate of smart home devices are calculated. Then, based on the usage rate, failure rate, and emergency handling rate of the smart home devices, the user's device usage evaluation value and the user's comprehensive evaluation value are calculated. The early warning module is used to issue early warnings.

8. A background control signal processing system for a smart door lock according to claim 7, characterized in that: It also includes an access control module; The permission control module is used to control the shooting permissions of the shooting device and the access permissions for shooting snapshots.

Images