Internet-based intelligent household electrical appliance fault monitoring, collecting and processing system and method
Through the Internet-based smart home appliance fault monitoring, acquisition and processing system, the fault detection model and machine learning optimization interaction function are used to solve the problem of smart home appliance interactive failures and improve user experience and performance.
Patent Information
- Application Number
- CN202411135063.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-19
AI Technical Summary
Smart home appliances may fail during the interaction process, resulting in a reduced user experience and it is difficult for users to diagnose themselves, requiring professional tools or after-sales service, which affects the frequency of use.
The Internet-based intelligent home appliance fault monitoring, acquisition and processing system uses interactive behavior to obtain response data, use fault detection models to identify faults, collect interaction related data, generate machine training sets, and use machine learning to optimize interaction functions to improve interaction accuracy.
Timely detect interactive failures, notify users, reduce maintenance needs, improve user experience, enhance the interaction accuracy between smart home appliances and users, and improve performance and satisfaction.
Smart Images

Figure CN119030900A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart home appliances, and in particular to an Internet-based smart home appliance fault monitoring, collection and processing system and method. Background Art
[0002] Smart home appliances refer to home appliances that are connected to the Internet or other wireless networks and have intelligent functions. These home appliances can be remotely controlled and monitored through smart terminal devices and have human-computer interaction interfaces such as voice recognition and touch screens. With the development of Internet technology and the improvement of consumer demand, different smart home appliances can be connected and communicated with each other to achieve the linkage of home appliances.
[0003] When users interact with smart appliances during actual use, the smart appliances may have abnormal recognition of user commands, resulting in no response or incorrect response. This may be because the instructions provided by the user are not clear or specific enough, or the smart appliances have not completed learning the user's preferences, resulting in problems with the settings of the smart appliances, causing the interactive functions of the smart appliances to malfunction, affecting the user's interactive experience. At the same time, most users find it difficult to self-diagnose the cause of the interaction failure and need to use professional diagnostic tools or contact the manufacturer's after-sales service for on-site inspections, which reduces the frequency of users' use of smart appliances and is not conducive to the development of smart appliances. Summary of the invention
[0004] The purpose of the present invention is to provide an Internet-based intelligent home appliance fault monitoring, collection and processing system and method to solve the problems raised in the above background technology.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for monitoring, collecting and processing faults of smart home appliances based on the Internet, comprising the following steps:
[0006] Step S100: monitor the interactive behavior of smart home appliances, obtain the response data and user reaction data of smart home appliances during interaction, and upload the data to the monitoring center after security processing;
[0007] Step S200: Processing the received data through the monitoring center, judging the interactive behavior of the smart home appliance based on the fault detection model, and executing step S300 when it is determined that there is a fault in the interactive behavior of the smart home appliance;
[0008] Step S300: the monitoring center initiates a communication request to the smart home appliance, obtains user authorization, collects interaction-related data of the smart home appliance, and generates a machine training set;
[0009] Step S400: Optimize the interactive functions of the smart home appliances based on the machine training set, and handle the interactive function failures of the smart home appliances through machine learning.
[0010] Furthermore, the response data of the smart home appliance during the interaction is specifically the first instruction data sent by the user received by the smart home appliance, and the execution result data returned to the system after the instruction is executed according to the preset conditions; the user reaction data is used to feedback the user performance after the smart home appliance executes the instruction, including user behavior data and second instruction data; the user behavior data is specifically the operation data of the user on the smart home appliance after the smart home appliance executes the instruction;
[0011] The data is securely processed and then uploaded, specifically, the data is encrypted using an encryption algorithm before transmission, the encrypted data is transmitted using a secure communication protocol, such as HTTPS, and the uploaded data is backed up locally;
[0012] The monitoring center is used to detect the interactive behavior of the smart home appliance and determine whether there is a fault in the interactive behavior of the smart home appliance.
[0013] Furthermore, the step S200 specifically includes the following steps:
[0014] S201: The monitoring center processes the received data to generate a data set to be tested, wherein the data set to be tested includes n groups of data to be tested, and the uth group of data to be tested in the data set to be tested is recorded as D u =(J u , X u , Y u , Z u ), u∈[1,n]; each set of test data includes four elements, namely the first instruction, the executed response code, the user behavior category score and the second instruction; where J u represents the first instruction received by the smart home appliance in the u-th group of test data, X u represents the response code executed by the smart home appliance in the u-th group of test data, Y u represents the user behavior category score after the smart home appliance executes the first instruction in the u-th group of test data, Z u Indicates the second instruction received by the smart home appliance in the u-th group of test data;
[0015] Among them, the user behavior categories include the first behavior category, the second behavior category and the third behavior category; the first behavior category indicates that the user uses the same instruction output method as the first instruction when operating, the second behavior category indicates that the user uses a different instruction output method than the first instruction when operating, and the third behavior category indicates that the user does not output an instruction when operating; specifically, the output methods of the first instruction and the second instruction include voice input, gesture input, home appliance button input, APP input and remote control input, etc.;
[0016] S202: Detect each group of test data in the test data set using the fault detection model, and calculate the user feedback score Score of the u-th group of test data in the test data set according to the following formula u :
[0017]
[0018] Among them, Score u Indicates that the smart appliance is executing the response behavior X u The user feedback scores obtained after
[0019] represents a relationship function between the response behavior code executed by the smart home appliance and the first instruction. When the instruction received by the smart home appliance corresponds to the executed response behavior code, When the instructions received by the smart appliance do not correspond to the response behavior code executed, g(Z u ) represents the relationship function between the second instruction issued by the user after the smart home appliance executes the response behavior and the first instruction. When g(Z u )=0, when Z u ∈J u When g(Z u )=1, when When g(Z u )=A,A>1; is the weight coefficient;
[0020] It should be noted that Z u ∈J u When , it indicates that the second instruction is a subordinate instruction of the first instruction and will not change the state of the smart appliance after the smart appliance executes the first instruction; , it indicates that the second instruction is a level instruction or a higher level instruction of the first instruction, and the execution of the second instruction will overwrite the state of the smart appliance executing the first instruction.
[0021] represents the user behavior category score corresponding to the j-th behavior data of the user on the smart appliance after the smart appliance executes the first instruction; ωj represents the influence coefficient corresponding to the user behavior category to which the jth behavior data belongs; j∈[1,m], where m represents the number of user behaviors on the smart appliance within a unit time after the smart appliance executes the first instruction;
[0022] S203: According to the detection result of the fault detection model, when more than B% of the test data in the test data set have user feedback scores exceeding a preset threshold value e, it is determined that there is a fault in the interactive behavior of the smart home appliance, and step S300 is executed.
[0023] Furthermore, the step S300 specifically includes the following steps:
[0024] S301: The monitoring center initiates a communication request to the smart home appliance, obtains user authorization, and collects interaction-related data of the smart home appliance, including: original data of a first instruction issued by the user, a response code of the smart home appliance executing the first instruction, user behavior data after the smart home appliance executes the first instruction, and original data of a second instruction issued by the user within a unit time;
[0025] S302: Process the collected interaction-related data to generate a machine training set, which includes W groups of training data, and any group of training data is recorded as (J, x, y, z); store the machine training set in a buffer. The four elements in the training data correspond to the original data of the user issuing the first instruction after data normalization, the response code of the smart home appliance executing the first instruction, the user behavior data after the smart home appliance executes the first instruction, and the original data of the user issuing the second instruction within a unit time.
[0026] Furthermore, the step S400 specifically includes the following steps:
[0027] S401: Randomly extract training data from the machine training set for learning, and calculate any set of extracted training data according to the following formula:
[0028]
[0029] Among them, P i represents the target value of the i-th group of training data, r represents the user feedback score obtained after the smart appliance executes the response behavior y, λ represents the discount factor, and θ' represents the parameters of the target network; Q(z, y'; θ') represents the target value of the optimal response y' calculated by the target network using the parameter θ' under the next instruction z;
[0030] Specifically, the above target network is implemented based on the Bellman equation;
[0031] S402: Calculate the predicted value based on the neural network and update the parameters of the online network by minimizing the loss function. The specific formula is:
[0032] Q(J, x; θ) = f(J; θ);
[0033]
[0034] Where, f is a neural network, and the calculation of the neural network is realized through matrix multiplication and vector addition; J represents the original data feature of the first instruction issued by the user, x represents the response behavior encoding executed by the smart home appliance, and θ represents the parameters of the neural network; Q(J, x; θ) represents the predicted value of the response behavior x executed by the smart home appliance under instruction J; L represents the loss function, N represents the number of extracted training data groups, i∈[1, N];
[0035] Through step S402, the network weight can be adjusted to reduce the gap between the target value and the predicted value;
[0036] S403: looping steps S401 and S402, after k trainings, copying the parameters of the online network to the target network; applying the updated interactive function to the smart home appliances. Through the above steps, the interactive identification module of the smart home appliances can be updated according to the user's preference data, and a personalized response execution for the user's behavior can be generated, thereby improving the accuracy of the interaction between the smart home appliances and the user, solving the interactive behavior failures of the smart home appliances, and optimizing the user experience.
[0037] The Internet-based intelligent home appliance fault monitoring, collection and processing system includes the following modules: home appliance monitoring module, fault detection module, data collection module and intelligent processing module;
[0038] The home appliance monitoring module is used to monitor the usage data of smart home appliances and obtain data related to the interaction between users and smart home appliances; by monitoring the usage data of smart home appliances, faults in interactive behaviors can be discovered in a timely manner and users can be notified in a timely manner, thereby reducing problems encountered by users during use and improving user experience.
[0039] The fault detection module is used to detect the monitoring data output by the home appliance monitoring module to determine whether there is a fault in the interactive behavior of the smart home appliance;
[0040] The data acquisition module is used to initiate a communication request to the smart home appliance, collect interaction-related data of the smart home appliance after obtaining user authorization, and generate a machine training set;
[0041] The intelligent processing module optimizes the interactive functions of the smart home appliances based on the machine training set, and processes the interactive function failures of the smart home appliances through machine learning.
[0042] Furthermore, the household appliance monitoring module includes a monitoring acquisition unit and a data transmission unit;
[0043] The monitoring acquisition unit is used to acquire the response data of the smart home appliance and the user reaction data during the interaction;
[0044] The data transmission unit is used to monitor the data acquired by the acquisition unit, process them securely and transmit them to the monitoring center.
[0045] Further, the fault detection module includes a data analysis unit and a fault determination unit;
[0046] The data analysis unit is used to process the data received by the monitoring center to generate a data set to be tested, the data set to be tested includes n groups of data to be tested, each group of data to be tested includes four elements, namely, a first instruction, an executed response code, a user behavior category score, and a second instruction;
[0047] The fault determination unit is used to detect each set of test data in the test data set according to the fault detection model, and determine whether there is a fault in the interactive behavior of the smart home appliance by calculating the user feedback score of the test data.
[0048] Further, the data acquisition module includes an authentication acquisition unit and a training set generation unit;
[0049] The authentication collection unit initiates a communication request to the smart home appliance based on the monitoring center, and collects the interaction-related data of the smart home appliance after obtaining the user's authorization, including: original data containing the first instruction issued by the user, the response code of the smart home appliance executing the first instruction, the user behavior data after the smart home appliance executes the first instruction, and the original data of the second instruction issued by the user within a unit time;
[0050] The training set generation unit is used to process the collected interaction-related data, generate a machine training set, and store the machine training set in a buffer.
[0051] Further, the intelligent processing module includes a machine learning unit and a function updating unit;
[0052] The machine learning unit is used to randomly extract training data from the machine training set for learning, and to update the parameters of the target network based on the online network, so that the interaction capability of the smart home appliance is more in line with the user's preference;
[0053] The function update unit is used to deploy the trained target network and apply the updated interactive function to the smart home appliances.
[0054] Compared with the prior art, the beneficial effects achieved by the present invention are:
[0055] By monitoring the usage data of smart home appliances, faults in interactive behaviors can be discovered in a timely manner and users can be notified in a timely manner, thereby reducing the problems encountered by users during use and improving user experience.
[0056] By using monitoring data and machine learning algorithms, it is possible to predict possible failures of smart appliances, reduce the need for maintenance, and avoid reduced frequency of use of smart appliances due to failures.
[0057] By analyzing user interaction data and the data on interaction between users and smart appliances, it is possible to update the interaction identification module of smart appliances based on user preference data, generate personalized response execution for user behavior, improve the accuracy of interaction between smart appliances and users, resolve interaction behavior failures of smart appliances, and improve the performance of smart appliances and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0059] Figure 1 It is a structural schematic diagram of the intelligent household appliance fault monitoring, collection and processing system based on the Internet of the present invention;
[0060] Figure 2 It is a flow chart of the method for monitoring, collecting and processing faults of intelligent household appliances based on the Internet according to the present invention. DETAILED DESCRIPTION
[0061] 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.
[0062] See also Figure 1 , in the first embodiment: a smart home appliance fault monitoring, collection and processing system based on the Internet is provided, comprising the following modules: a home appliance monitoring module, a fault detection module, a data collection module and an intelligent processing module;
[0063] The home appliance monitoring module is used to monitor the usage data of smart home appliances and obtain data related to the interaction between users and smart home appliances; it includes a monitoring acquisition unit and a data transmission unit; the monitoring acquisition unit is used to obtain the response data and user reaction data of smart home appliances during interaction; the data transmission unit is used to securely process the data obtained by the monitoring acquisition unit and transmit it to the monitoring center.
[0064] A fault detection module is used to detect the monitoring data output by the home appliance monitoring module to determine whether there is a fault in the interactive behavior of the smart home appliance; it includes a data analysis unit and a fault determination unit;
[0065] The data analysis unit is used to process the data received by the monitoring center to generate a test data set, which includes n groups of test data. Each group of test data includes four elements, namely, the first instruction, the executed response code, the user behavior category score, and the second instruction. The uth group of test data in the test data set is recorded as D u =(J u , X u , Y u , Z u ), u∈[1,n];
[0066] The fault determination unit is used to detect each group of test data in the test data set according to the fault detection model, and determine whether there is a fault in the interactive behavior of the smart home appliance by calculating the user feedback score of the test data. When the user feedback scores of more than 30% of the test data in the test data set exceed a preset threshold, it is determined that there is a fault in the interactive behavior of the smart home appliance.
[0067] When the fault detection model detects each set of test data in the test data set, the user feedback score Score of the u-th set of test data in the test data set is calculated according to the following formula: u :
[0068]
[0069] Among them, Score u Indicates that the smart appliance is executing the response behavior X u The user feedback scores obtained after
[0070] represents a relationship function between the response behavior code executed by the smart home appliance and the first instruction. When the instruction received by the smart home appliance corresponds to the executed response behavior code, When the instructions received by the smart appliance do not correspond to the response behavior code executed, g(Z u ) represents the relationship function between the second instruction issued by the user after the smart home appliance executes the response behavior and the first instruction. When g(Z u )=0, when Z u ∈J u When g(Z u )=1, when When g(Z u )=2; is the weight coefficient;
[0071] represents the user behavior category score corresponding to the j-th behavior data of the user on the smart appliance after the smart appliance executes the first instruction; ω j represents the influence coefficient corresponding to the user behavior category to which the j-th behavior data belongs; j∈[1, m], where m represents the number of user behaviors on the smart appliance within unit time after the smart appliance executes the first instruction.
[0072] The data collection module is used to initiate a communication request to the smart home appliance, collect the interaction-related data of the smart home appliance after obtaining the user's authorization, and generate a machine training set; the data collection module includes an authentication collection unit and a training set generation unit;
[0073] The authentication collection unit initiates a communication request to the smart home appliance based on the monitoring center, and collects the interaction-related data of the smart home appliance after obtaining the user's authorization, including: the original data of the first instruction issued by the user, the response code of the smart home appliance executing the first instruction, the user behavior data after the smart home appliance executes the first instruction, and the original data of the second instruction issued by the user within a unit time;
[0074] The training set generation unit is used to process the collected interaction-related data, generate a machine training set, and store the machine training set in a buffer.
[0075] Intelligent processing module, which optimizes the interactive functions of smart home appliances based on machine training sets and handles interactive function failures of smart home appliances through machine learning; it includes a machine learning unit and a function update unit;
[0076] The machine learning unit is used to randomly extract training data from the machine training set for learning, and to update the parameters of the target network based on the online network, so that the interactive capabilities of smart home appliances are more in line with user preferences;
[0077] The function update unit is used to deploy the trained target network and apply the updated interactive functions to smart home appliances.
[0078] See also Figure 2 In the second embodiment, a method for monitoring, collecting and processing faults of smart home appliances based on the Internet is provided, comprising the following steps:
[0079] Step S100: monitoring the interactive behavior of the smart home appliance, obtaining the first instruction data sent by the user and received by the smart home appliance, and returning the execution result data of the system after executing the instruction according to the preset conditions; obtaining the user performance after the smart home appliance executes the instruction, including the user's operation data on the smart home appliance after the smart home appliance executes the instruction and the second instruction data;
[0080] Exemplarily, the operation data of the smart home appliance may be adjusting the mode or parameter of the smart home appliance through an APP or a remote controller;
[0081] The acquired data is encrypted using an encryption algorithm, such as AES, RSA, etc., and the encrypted data is transmitted using a secure communication protocol, such as HTTPS, TLS, etc., and the uploaded data is backed up locally.
[0082] Step S200: Processing the received data through the monitoring center and judging the interactive behavior of the smart home appliance based on the fault detection model;
[0083] S201: The monitoring center processes the received data to generate a data set to be tested, wherein the data set to be tested includes n groups of data to be tested, and the uth group of data to be tested in the data set to be tested is recorded as D u =(J u , X u , Y u , Z u ), u∈[1,n]; each group of test data includes four elements, namely, the first instruction, the executed response code, the user behavior category score and the second instruction; wherein, the user behavior category includes the first behavior category, the second behavior category and the third behavior category; the first behavior category indicates that the user uses the same instruction output method as the first instruction when operating, the second behavior category indicates that the user uses a different instruction output method from the first instruction when operating, and the third behavior category indicates that there is no output instruction when the user operates; specifically, the output methods of the first instruction and the second instruction include voice input, gesture input, home appliance button input, APP input and remote control input, etc.;
[0084] S202: Detect each group of test data in the test data set using the fault detection model, and calculate the user feedback score Score of the u-th group of test data in the test data set according to the following formula u :
[0085]
[0086] Among them, Score u Indicates that the smart appliance is executing the response behavior X u The user feedback scores obtained after
[0087] represents a relationship function between the response behavior code executed by the smart home appliance and the first instruction. When the instruction received by the smart home appliance corresponds to the executed response behavior code, When the instructions received by the smart appliance do not correspond to the response behavior code executed, g(Z u ) represents the relationship function between the second instruction issued by the user after the smart home appliance executes the response behavior and the first instruction. When g(Z u )=0, when Zu ∈J u When g(Z u )=1, when When g(Z u )=2; is the weight coefficient;
[0088] It should be noted that Z u ∈J u When , it indicates that the second instruction is a subordinate instruction of the first instruction and will not change the state of the smart appliance after the smart appliance executes the first instruction; , it indicates that the second instruction is a level instruction or a higher level instruction of the first instruction, and the execution of the second instruction will overwrite the state of the smart appliance executing the first instruction.
[0089] represents the user behavior category score corresponding to the j-th behavior data of the user on the smart appliance after the smart appliance executes the first instruction; ω j represents the influence coefficient corresponding to the user behavior category to which the jth behavior data belongs; j∈[1,m], where m represents the number of user behaviors on the smart appliance within a unit time after the smart appliance executes the first instruction;
[0090] S203: According to the detection result of the fault detection model, if more than 30% of the user feedback scores of the test data set exceed the preset threshold value e, it is determined that there is a fault in the interactive behavior of the smart home appliance, and step S300 is executed.
[0091] Step S300: the monitoring center initiates a communication request to the smart home appliance, obtains user authorization, collects interaction-related data of the smart home appliance, and generates a machine training set;
[0092] S301: The monitoring center initiates a communication request to the smart home appliance, obtains user authorization, and collects interaction-related data of the smart home appliance, including: original data of a first instruction issued by the user, a response code of the smart home appliance executing the first instruction, user behavior data after the smart home appliance executes the first instruction, and original data of a second instruction issued by the user within a unit time;
[0093] S302: Process the collected interaction-related data to generate a machine training set, which includes W groups of training data, and any group of training data is recorded as (J, x, y, z); store the machine training set in a buffer. The four elements in the training data correspond to the original data of the user issuing the first instruction after data normalization, the response code of the smart home appliance executing the first instruction, the user behavior data after the smart home appliance executes the first instruction, and the original data of the user issuing the second instruction within a unit time.
[0094] Step S400: optimizing the interactive function of the smart home appliance based on the machine training set, and processing the interactive function failure of the smart home appliance by machine learning;
[0095] S401: Randomly extract training data from the machine training set for learning, and calculate any set of extracted training data according to the following formula:
[0096]
[0097] Among them, P i represents the target value of the i-th group of training data, r represents the user feedback score obtained after the smart appliance executes the response behavior y, λ represents the discount factor, and θ' represents the parameters of the target network; Q(z, y'; θ') represents the target value of the optimal response y' calculated by the target network using the parameter θ' under the next instruction z;
[0098] Specifically, the above target network is implemented based on the Bellman equation;
[0099] S402: Calculate the predicted value based on the neural network and update the parameters of the online network by minimizing the loss function. The specific formula is:
[0100] Q(J, x; θ) = f(J; θ);
[0101]
[0102] Wherein, f is a neural network, and the calculation of the neural network is implemented by matrix multiplication and vector addition, which is automatically completed by PyTorch in this embodiment; J represents the original data feature of the first instruction issued by the user, x represents the response behavior encoding executed by the smart home appliance, and θ represents the parameters of the neural network; Q(J, x; θ) represents the predicted value of the response behavior x executed by the smart home appliance under the instruction J represented by the original data feature of the first instruction issued by the user; L represents the loss function, N represents the number of extracted training data groups, i∈[1, N];
[0103] By analyzing the relationship between the instructions represented by the original data features of the first instruction issued by the user and the response behavior encoding executed by the smart home appliance, the meaning of the instructions issued by the user is parsed, the accuracy of smart home appliances in extracting instructions is improved, invalid operations caused by instruction recognition errors are avoided, and the effective response efficiency of smart home appliances to user instructions is enhanced.
[0104] S403: looping steps S401 and S402, after 10,000 trainings or when the stopping condition is reached, copying the parameters of the online network to the target network; applying the updated interactive function to the smart home appliances. Through the above steps, the interactive identification module of the smart home appliances can be updated according to the user's preference data, and a personalized response execution can be generated for the user's behavior, thereby improving the accuracy of the interaction between the smart home appliances and the user, resolving the interactive behavior failures of the smart home appliances, and optimizing the user experience.
[0105] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0106] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. An Internet-based intelligent household appliance fault monitoring, collection and processing method, characterized in that: The following steps are involved: Step S100: monitor the interactive behavior of smart home appliances, obtain the response data and user reaction data of smart home appliances during interaction, and upload the data to the monitoring center after security processing; Step S200: Processing the received data through the monitoring center, judging the interactive behavior of the smart home appliance based on the fault detection model, and executing step S300 when it is determined that there is a fault in the interactive behavior of the smart home appliance; Step S300: the monitoring center initiates a communication request to the smart home appliance, obtains user authorization, collects interaction-related data of the smart home appliance, and generates a machine training set; Step S400: Optimize the interactive functions of the smart home appliances based on the machine training set, and handle the interactive function failures of the smart home appliances through machine learning.
2. The method for monitoring, collecting and processing faults of smart home appliances based on the Internet according to claim 1 is characterized in that: The response data of the smart home appliance during the interaction is specifically the first instruction data sent by the user and received by the smart home appliance, and the execution result data returned to the system after the instruction is executed according to the preset conditions; the user reaction data is used to feedback the user performance after the smart home appliance executes the instruction, including user behavior data and second instruction data; The uploading of the data after secure processing specifically includes encrypting the data using an encryption algorithm before transmission, transmitting the encrypted data using a secure communication protocol, and locally backing up the uploaded data; The monitoring center is used to detect the interactive behavior of the smart home appliance and determine whether there is a fault in the interactive behavior of the smart home appliance.
3. The method for monitoring, collecting and processing faults of smart home appliances based on the Internet according to claim 1 is characterized in that: The step S200 specifically includes the following steps: S201: The monitoring center processes the received data to generate a data set to be tested, wherein the data set to be tested includes n groups of data to be tested, and the uth group of data to be tested in the data set to be tested is recorded as D u =(J u , X u , Y u , Z u ), u∈[1,n]; where J u represents the first instruction received by the smart home appliance in the u-th group of test data, X u represents the response code executed by the smart home appliance in the u-th group of test data, Y u represents the user behavior category score after the smart home appliance executes the first instruction in the u-th group of test data, Z u Indicates the second instruction received by the smart home appliance in the u-th group of test data; The user behavior category includes a first behavior category, a second behavior category and a third behavior category; the first behavior category indicates that the user uses the same instruction output method as the first instruction when operating, the second behavior category indicates that the user uses a different instruction output method than the first instruction when operating, and the third behavior category indicates that no instruction is output when the user operates; S202: Detect each group of test data in the test data set using the fault detection model, and calculate the user feedback score Score of the u-th group of test data in the test data set according to the following formula u : Among them, Score u Indicates that the smart appliance is executing the response behavior X u The user feedback scores obtained after represents a relationship function between the response behavior code executed by the smart home appliance and the first instruction. When the instruction received by the smart home appliance corresponds to the executed response behavior code, When the instructions received by the smart appliance do not correspond to the response behavior code executed, g(Z u ) represents the relationship function between the second instruction issued by the user after the smart home appliance executes the response behavior and the first instruction. When g(Z u )=0, when Z u ∈J u When g(Z u )=1, when When g(Z u )=A, A>1; is the weight coefficient; represents the user behavior category score corresponding to the j-th behavior data of the user on the smart appliance after the smart appliance executes the first instruction; ω j represents the influence coefficient corresponding to the user behavior category to which the jth behavior data belongs; j∈[1,m], where m represents the number of user behaviors on the smart appliance within a unit time after the smart appliance executes the first instruction; S203: According to the detection result of the fault detection model, when more than B% of the test data in the test data set have user feedback scores exceeding a preset threshold value e, it is determined that there is a fault in the interactive behavior of the smart home appliance, and step S300 is executed.
4. The method for monitoring, collecting and processing faults of smart home appliances based on the Internet according to claim 1 is characterized in that: The step S300 specifically includes the following steps: S301: The monitoring center initiates a communication request to the smart home appliance, obtains user authorization, and collects interaction-related data of the smart home appliance, including: original data of a first instruction issued by the user, a response code of the smart home appliance executing the first instruction, user behavior data after the smart home appliance executes the first instruction, and original data of a second instruction issued by the user within a unit time; S302: Process the collected interaction-related data to generate a machine training set, which includes W groups of training data, and any group of training data is recorded as (J, x, y, z); the four elements in the training data correspond to the original data of the first instruction issued by the user after data normalization, the response code of the smart home appliance executing the first instruction, the user behavior data after the smart home appliance executes the first instruction, and the original data of the second instruction issued by the user within a unit time; the machine training set is stored in a buffer.
5. The method for monitoring, collecting and processing faults of smart home appliances based on the Internet according to claim 1, characterized in that: The step S400 specifically includes the following steps: S401: randomly extract training data from the machine training set for learning, and calculate any set of extracted training data according to the following formula: Among them, P i represents the target value of the i-th group of training data, r represents the user feedback score obtained after the smart appliance executes the response behavior y, λ represents the discount factor, and θ' represents the parameters of the target network; Q(z, y'; θ') represents the target value of the optimal response y' calculated by the target network using the parameter θ' under the next instruction z; S402: Calculate the predicted value based on the neural network and update the parameters of the online network by minimizing the loss function. The specific formula is: Q(J, x; θ) = f(J; θ); Where f is a neural network, J represents the original data features of the first command issued by the user, x represents the response behavior code executed by the smart home appliance, and θ represents the parameters of the neural network; Q(J, x; θ) represents the predicted value of the response behavior x executed by the smart home appliance under command J; L represents the loss function, N represents the number of extracted training data groups, i∈[1, N]; S403: looping steps S401 and S402, after k trainings, copying the parameters of the online network to the target network; applying the updated interactive function to the smart home appliance.
6. The Internet-based intelligent household appliance fault monitoring, collection and processing system is characterized by: It includes the following modules: home appliance monitoring module, fault detection module, data acquisition module and intelligent processing module; The home appliance monitoring module is used to monitor the usage data of smart home appliances and obtain the interaction data between users and smart home appliances; The fault detection module is used to detect the monitoring data output by the home appliance monitoring module to determine whether there is a fault in the interactive behavior of the smart home appliance; The data acquisition module is used to initiate a communication request to the smart home appliance, collect interaction-related data of the smart home appliance after obtaining user authorization, and generate a machine training set; The intelligent processing module optimizes the interactive functions of the smart home appliances based on the machine training set, and processes the interactive function failures of the smart home appliances through machine learning.
7. The Internet-based intelligent household appliance fault monitoring, collection and processing system according to claim 6 is characterized in that: The household appliance monitoring module includes a monitoring acquisition unit and a data transmission unit; The monitoring acquisition unit is used to acquire the response data of the smart home appliance and the user reaction data during the interaction; The data transmission unit is used to monitor the data acquired by the acquisition unit, perform safe processing and transmit the data to the monitoring center.
8. The Internet-based intelligent household appliance fault monitoring, collection and processing system according to claim 6 is characterized by: The fault detection module includes a data analysis unit and a fault determination unit; The data analysis unit is used to process the data received by the monitoring center to generate a data set to be tested, the data set to be tested includes n groups of data to be tested, each group of data to be tested includes four elements, namely, a first instruction, an executed response code, a user behavior category score, and a second instruction; The fault determination unit is used to detect each set of test data in the test data set according to the fault detection model, and determine whether there is a fault in the interactive behavior of the smart home appliance by calculating the user feedback score of the test data.
9. The Internet-based intelligent household appliance fault monitoring, collection and processing system according to claim 6 is characterized in that: The data acquisition module includes an authentication acquisition unit and a training set generation unit; The authentication collection unit initiates a communication request to the smart home appliance based on the monitoring center, and collects the interaction-related data of the smart home appliance after obtaining the user's authorization, including: original data containing the first instruction issued by the user, the response code of the smart home appliance executing the first instruction, the user behavior data after the smart home appliance executes the first instruction, and the original data of the second instruction issued by the user within a unit time; The training set generation unit is used to process the collected interaction-related data, generate a machine training set, and store the machine training set in a buffer.
10. The Internet-based intelligent household appliance fault monitoring, collection and processing system according to claim 6, characterized in that: The intelligent processing module includes a machine learning unit and a function update unit; The machine learning unit is used to randomly extract training data from a machine training set for learning, and to update parameters of a target network based on an online network; The function update unit is used to deploy the trained target network and apply the updated interactive function to the smart home appliances.
Citation Information
Patent Citations
Intelligent household electrical appliance, cloud server and abnormity monitoring method
CN113064384A
Abnormality detection method and device
CN115185760A
Smart home safety early warning method and system suitable for Internet of Things
CN117614646A
Big data security processing method based on data analysis
CN118332597A
Human body behavior recognition and data acquisition system based on artificial intelligence
CN118430070A
