Methods and apparatus for confirming sterilization instructions, storage media and electronic devices

Abstract

This application discloses a method and apparatus for confirming sterilization commands, a storage medium, and an electronic device, relating to the field of smart home technology. The method for confirming sterilization commands includes: acquiring behavioral statistics of a target object; wherein the behavioral statistics are behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers; predicting the target behavioral characteristics of the target object in the Kth time interval of the N+1th period based on the behavioral statistics; and, given that the opening duration of the storage device in the K-1th time interval of the N+1th period has been acquired, determining whether to issue a sterilization command to the device based on the target behavioral characteristics and the opening duration.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to a method and apparatus for confirming sterilization commands, a storage medium, and an electronic device. Background Technology

[0002] With increasing demands for hygiene in home appliances, more and more smart refrigerators support automatic sterilization functions. However, rising environmental awareness also presents a dual challenge: timely and effective sterilization while maintaining energy efficiency. In related technologies, manufacturers often optimize the timing and frequency of sterilization by using periodic sterilization or allowing users to set the sterilization frequency within smart applications. However, these methods may not simultaneously meet the requirements for high efficiency and energy saving in sterilization, or they may impose additional tasks on users, resulting in a poor user experience.

[0003] For example, prolonged door opening can cause changes in temperature and humidity inside the smart refrigerator, introducing outside air and negatively impacting food preservation. Furthermore, if the user opens the refrigerator again during or immediately after the sterilization process, sterilization may not be completed or the effect may be too short-lived, resulting in inefficient sterilization. Therefore, while existing smart refrigerators may have sterilization functions, offer multiple sterilization modes, or optimize the structure of sterilization areas or devices, they lack the ability to optimize sterilization based on user behavior. This creates a conflict between user actions and the sterilization process, leading to low sterilization efficiency.

[0004] In response to the problems in related technologies, such as the conflict between the sterilization process of storage devices and the use of the target object, resulting in low sterilization effect and poor user experience of the storage device by the target object, no effective technical solution has been proposed. Summary of the Invention

[0005] This invention provides a method and apparatus for confirming sterilization instructions, a storage medium, and an electronic device to at least solve the problems in related technologies, such as the conflict between the sterilization process of the storage device and the use of the target object, resulting in low sterilization effect and poor user experience of the storage device by the target object.

[0006] According to an embodiment of the present invention, a method for confirming a sterilization command is provided, comprising: acquiring behavioral statistics of a target object; wherein the behavioral statistics are behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals having the same duration and each time interval having at least one adjacent time interval, N being greater than 1, and N and K being positive integers; predicting the target behavioral characteristics of the target object in the Kth time interval of the (N+1)th period based on the behavioral statistics; and, if the open duration of the storage device corresponding to the (K-1)th time interval of the (N+1)th period has been acquired, determining whether to issue a sterilization command to the device based on the target behavioral characteristics and the open duration.

[0007] In one exemplary embodiment, the above-mentioned behavioral characteristics include at least one of the following: the number of times the target object opens the storage device, the cumulative duration of the target object opening the storage device, and the duration from the last time the target object opens the storage device to the end of the time interval before closing the storage device.

[0008] In an exemplary embodiment, after obtaining the behavioral statistics of the target object, the method further includes: determining the average value and standard deviation of the behavioral characteristics of the target object in the (M-1)th time interval, the Mth time interval, and the (M+1)th time interval of each of the N periods; wherein, M+1 is less than or equal to K, and the three time intervals (M-1, M, and M+1) have the same duration; determining the feature matrix of the target object corresponding to the N periods based on the average value and the standard deviation; adding feature labels to the first feature in the feature matrix according to preset category features to obtain a second feature for classification, wherein the feature labels are used to identify whether the target object has opened a storage device in each time interval.

[0009] In an exemplary embodiment, after adding feature labels to the first feature in the feature matrix according to preset category features to obtain a second feature for classification, the method further includes: corresponding the second feature to the behavioral features of the target object in K time intervals of the Nth period to obtain a training sample; inputting the training sample into a preset model to obtain a classification model for classifying the behavioral statistics of the target object through training; determining the feature set corresponding to the N periods in the behavioral statistics of the target object, inputting the feature set into the classification model to obtain target feature labels corresponding to the K time intervals of the N periods respectively; and determining the first probability that the target object opens the storage device in each time interval based on the target feature labels.

[0010] In one exemplary embodiment, predicting the target behavior characteristics of the target object in the Kth time interval of the N+1th period based on the behavioral statistics includes: determining a first probability that the target object will open the storage device in the Kth time interval of the Nth period, based on the first probability, a second probability that the target object will not open the storage device in the Kth time interval of the N+1th period; wherein the second probability indicates the probability that the target object will not open the storage device in the Kth time interval of the N+1th period; and predicting the target behavior characteristics of the target object based on the second probability.

[0011] In an exemplary embodiment, given that the storage device's open duration in the (K-1)th time interval of the (N+1)th cycle has been obtained, determining whether to issue a sterilization command to the storage device based on the target behavior feature and the open duration includes: obtaining a second probability corresponding to the target behavior feature; calculating a first target value by adding the second probability to a first constant; taking the logarithm of the first target value to obtain a first logarithmic value; calculating a second target value by dividing the storage device's open duration by the sum of the second constant and the first constant; taking the logarithm of the second target value to obtain a second logarithmic value; adding the product of the first logarithmic value and a first weight to the second logarithmic value to obtain a recommendation index; and comparing the recommendation index with a preset threshold to determine whether to issue a sterilization command to the storage device.

[0012] In one exemplary embodiment, comparing the suggested index with a preset threshold to determine whether to issue a sterilization command to the storage device includes: issuing a sterilization command to the storage device and prompting the target object that the storage device will activate the sterilization function if the suggested index is greater than or equal to the preset index threshold; and prohibiting the issuance of a sterilization command to the storage device if the suggested index is less than the preset index threshold.

[0013] According to another embodiment of the present invention, a device for confirming a sterilization command is provided, comprising: an acquisition module, configured to acquire behavioral statistics of a target object; wherein the behavioral statistics are behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers; a prediction module, configured to predict the target behavioral characteristics of the target object in the Kth time interval of the N+1th period based on the behavioral statistics; and a determination module, configured to determine whether to issue a sterilization command to the device based on the target behavioral characteristics and the opening duration, provided that the opening duration of the storage device corresponding to the K-1th time interval in the N+1th period has been acquired.

[0014] In an exemplary embodiment, the above-described apparatus further includes: a feature module, configured to determine the average value and standard deviation of the behavioral characteristics of the target object in the (M-1)th time interval, the Mth time interval, and the (M+1)th time interval of each of the N periods; wherein, M+1 is less than or equal to K, and the three time intervals (M-1, M, and M+1) have the same duration; to determine a feature matrix of the target object corresponding to the N periods based on the average value and the standard deviation; and to add feature labels to the first feature in the feature matrix according to preset category features to obtain a second feature for classification, wherein the feature labels are used to identify whether the target object has opened a storage device in each time interval.

[0015] In one exemplary embodiment, the above-mentioned feature module further includes:

[0016] A sample unit is used to correspond the second feature with the behavioral features of the target object in K time intervals of the Nth period to obtain a training sample;

[0017] The training unit is used to input the training samples into a preset model and obtain a classification model for classifying the statistical data of the target object's behavior through training.

[0018] A classification unit is used to determine the feature set corresponding to the N periods in the target object behavior statistics, input the feature set into the classification model, and obtain the target feature labels corresponding to the K time intervals of the N periods respectively;

[0019] The determining unit is used to determine the first probability that the target object will open the storage device in each time interval based on the target feature label.

[0020] In an exemplary embodiment, the prediction module is further configured to, upon determining a first probability that the target object will open the storage device in the Kth time interval of the Nth period, determine a second probability of the target object in the Kth time interval of the N+1th period based on the first probability; wherein the second probability is used to indicate the probability that the target object will not open the storage device in the Kth time interval of the N+1th period; and predict the target behavior characteristics of the target object based on the second probability.

[0021] In an exemplary embodiment, the determining module is further configured to: obtain a second probability corresponding to the target behavior feature; calculate a first target value by adding the second probability to a first constant; take the logarithm of the first target value to obtain a first logarithmic value; calculate a second target value by dividing the storage device open duration by the sum of the second constant and the first constant; take the logarithm of the second target value to obtain a second logarithmic value; add the product of the first logarithmic value and the first weight to the second logarithmic value to obtain a suggestion index; and compare the suggestion index with a preset threshold to determine whether to issue a sterilization command to the storage device.

[0022] In an exemplary embodiment, the determining module is further configured to, when the suggested index is greater than or equal to a preset index threshold, issue a sterilization command to the storage device and prompt the target object that the storage device will activate the sterilization function; and when the suggested index is less than the preset index threshold, prohibit the issuance of a sterilization command to the storage device.

[0023] According to yet another embodiment of the present invention, a storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0024] According to yet another embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0025] This invention obtains behavioral statistics of a target object; wherein the behavioral statistics are the behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers; based on the behavioral statistics, the target behavioral characteristics of the target object in the Kth time interval of the N+1th period are predicted; given that the opening duration of the storage device in the K-1th time interval of the N+1th period has been obtained, a determination is made on whether to issue a sterilization command to the device based on the target behavioral characteristics and the opening duration. In other words, by predicting the target object's behavioral characteristics in the (N+1)th period based on the target object's behavioral characteristics over N periods, and then combining this with the corresponding open duration of the storage device, it is determined whether the current storage device needs to be sterilized, and a sterilization command to activate the storage device's sterilization function is sent. Therefore, this solves the problems in the prior art where the sterilization process of the storage device conflicts with the use of the target object, resulting in low sterilization effect and poor user experience for the target object. This allows the sterilization operation of the storage device to be temporarily suspended when the target object uses the storage device frequently or is about to use it, and the storage device to quickly enter the sterilization process after the target object finishes using the storage device. This improves the user experience of the target object while increasing the sterilization efficiency of the storage device, and avoids the situation where the sterilization effect is reduced due to the target object using the storage device during the sterilization process. Attached Figure Description

[0026] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0027] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the hardware environment for a method of confirming a sterilization command according to an embodiment of this application;

[0029] Figure 2 This is a flowchart of a method for confirming a sterilization command according to an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of the overall architecture of a sterilization system according to an optional embodiment of the present invention;

[0031] Figure 4This is a flowchart illustrating the prediction module according to an optional embodiment of the present invention;

[0032] Figure 5 This is a structural block diagram of a device for confirming sterilization commands according to an embodiment of the present invention. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] According to one aspect of the embodiments of this application, a method for confirming a sterilization command is provided. This method for confirming a sterilization command is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned method for confirming a sterilization command can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0036] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0037] This embodiment provides a method for confirming sterilization commands. Figure 2 This is a flowchart of a method for confirming a sterilization command according to an embodiment of the present invention, the process including the following steps:

[0038] Step S202: Obtain behavioral statistics of the target object; wherein, the behavioral statistics are the behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers;

[0039] Optionally, N represents the number of days, and K represents the Kth time interval among multiple equally spaced moments within a day, with the duration of each interval measured in seconds. For example, if a day is divided into 24 hours, then one time interval is 1 hour. The aforementioned K time intervals are consecutive intervals with the same duration, and this application does not impose further restrictions on this.

[0040] Step S204: Based on the behavioral statistics, predict the target behavior characteristics of the target object in the Kth time interval of the N+1th cycle;

[0041] Step S206: Given that the opening duration of the storage device in the K-1 time interval of the N+1th cycle has been obtained, determine whether to issue a sterilization command to the device based on the target behavior characteristics and the opening duration.

[0042] Through the above steps, behavioral statistics of the target object are obtained; wherein, the behavioral statistics are the behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers; based on the behavioral statistics, the target behavioral characteristics of the target object in the Kth time interval of the N+1th period are predicted; given that the opening duration of the storage device in the K-1th time interval of the N+1th period has been obtained, a sterilization command is determined based on the target behavioral characteristics and the opening duration. In other words, by predicting the target object's behavioral characteristics in the (N+1)th period based on the target object's behavioral characteristics over N periods, and then combining this with the corresponding open duration of the storage device, it is determined whether the current storage device needs to be sterilized, and a sterilization command to activate the storage device's sterilization function is sent. Therefore, this solves the problems in the prior art where the sterilization process of the storage device conflicts with the use of the target object, resulting in low sterilization effect and poor user experience for the target object. This allows the sterilization operation of the storage device to be temporarily suspended when the target object uses the storage device frequently or is about to use it, and the storage device to quickly enter the sterilization process after the target object finishes using the storage device. This improves the user experience of the target object while increasing the sterilization efficiency of the storage device, and avoids the situation where the sterilization effect is reduced due to the target object using the storage device during the sterilization process.

[0043] In one exemplary embodiment, the above-mentioned behavioral characteristics include at least one of the following: the number of times the target object opens the storage device, the cumulative duration of the target object opening the storage device, and the duration from the last time the target object opens the storage device to the end of the time interval before closing the storage device.

[0044] In short, to ensure a comprehensive understanding of a target's use of storage devices through behavioral statistics, corresponding behavioral characteristics can be determined based on the target's historical data. For example, when the storage device is a smart refrigerator, the target's statistical characteristics are determined based on each time period of the day. The time period can be one hour or longer, but it's recommended that the duration be longer than the sterilization process. The timing point can be any time at equal intervals, such as the hour. Statistical values ​​are calculated for each time period of the day, with duration in seconds and counts in times. Specifically, this includes: the number of times the target opened the door in each time period; the total cumulative door opening time in each time period; and the time from the last door opening in the time period to the door closing at the timing point.

[0045] In an exemplary embodiment, after obtaining the behavioral statistics of the target object, the method further includes: determining the average value and standard deviation of the behavioral characteristics of the target object in the (M-1)th time interval, the Mth time interval, and the (M+1)th time interval of each of the N periods; wherein, M+1 is less than or equal to K, and the three time intervals (M-1, M, and M+1) have the same duration; determining the feature matrix of the target object corresponding to the N periods based on the average value and the standard deviation; adding feature labels to the first feature in the feature matrix according to preset category features to obtain a second feature for classification, wherein the feature labels are used to identify whether the target object has opened a storage device in each time interval.

[0046] Optionally, when the storage device is a smart refrigerator, based on the historical characteristics of the target object's use of the smart refrigerator, the statistical values ​​of the target object in each time period of each day are calculated. Given the statistical values, the average and standard deviation of the statistical values ​​are calculated by day (i.e., N). Then, the characteristics of the target object in the k-th time period may include: (1) the average number of times the target object opens the door in time period k-1; (2) the standard deviation of the number of times the target object opens the door in time period k-1; (3) the average number of times the target object opens the door in time period k; (4) the standard deviation of the number of times the target object opens the door in time period k; (5) the average number of times the target object opens the door in time period k+1; (6) the standard deviation of the number of times the target object opens the door in time period k+1; (7) the average total duration of the target object's door opening in time period k-1; (8) the standard deviation of the total duration of the target object's door opening in time period k-1; and (9) the average total duration of the target object's door opening in time period k. (10) The standard deviation of the total opening time of the target object in time period k; (11) The average total opening time of the target object in time period k+1; (12) The standard deviation of the total opening time of the target object in time period k+1; (13) The average closing time from the last opening of the target object in time period k-1 to the closing time at the time point of time period k-1; (14) The standard deviation of the closing time from the last opening of the target object in time period k-1 to the time point of time period k-1; (15) The average closing time from the last opening of the target object in time period k to the time point of time period k; (16) The standard deviation of the closing time from the last opening of the target object in time period k to the time point of time period k; (17) The average closing time from the last opening of the target object in time period k+1 to the time point of time period k; (18) The standard deviation of the closing time from the last opening of the target object in time period k+1 to the time point of time period k. In summary, when the period is one day and divided into K time period intervals, the feature matrix dimension of each target object is K*18.

[0047] After determining the feature matrix of the target object on different days, in order to facilitate the analysis and prediction of subsequent data, feature labels for classification are added to the first feature corresponding to each time period in the feature matrix based on the target object's door opening and closing behavior of the smart refrigerator, so as to obtain the second feature that can determine whether the target object has door opening behavior in that time period.

[0048] In an exemplary embodiment, after adding feature labels to the first feature in the feature matrix according to preset category features to obtain a second feature for classification, the method further includes: corresponding the second feature to the behavioral features of the target object in K time intervals of the Nth period to obtain a training sample; inputting the training sample into a preset model to obtain a classification model for classifying the behavioral statistics of the target object through training; determining the feature set corresponding to the N periods in the behavioral statistics of the target object, inputting the feature set into the classification model to obtain target feature labels corresponding to the K time intervals of the N periods respectively; and determining the first probability that the target object opens the storage device in each time interval based on the target feature labels.

[0049] In one exemplary embodiment, predicting the target behavior characteristics of the target object in the Kth time interval of the N+1th period based on the behavioral statistics includes: determining a first probability that the target object will open the storage device in the Kth time interval of the Nth period, based on the first probability, a second probability that the target object will not open the storage device in the Kth time interval of the N+1th period; wherein the second probability indicates the probability that the target object will not open the storage device in the Kth time interval of the N+1th period; and predicting the target behavior characteristics of the target object based on the second probability.

[0050] For example, when the storage device is a smart refrigerator, the door opening records of the target object are taken for each time period on day N. If there is a door opening behavior in the k-th time period, it is classified as 1; otherwise, it is classified as 0. Furthermore, the features and feature labels of a target object for a time period are determined to form a sample. A pre-set classifier is trained using the sample to obtain a Gaussian Bayes classifier for feature determination of the target object. In other words, this Gaussian Bayes classifier can transform the feature matrix into a classification feature matrix labeled with 0 and 1. When there is a classification result for the Kth time segment of N days, by determining the classification results of the Kth time segment before the Nth day, the classification result of the target object in the Kth time segment of the N+1th day can be predicted. This gives the probability that the target object will open the smart refrigerator in the Kth time segment of the N+1th day (classified as 1) or close it in the Kth time segment (classified as 0). This gives the first probability that the target object may open the door in the Kth time segment of the N+1th day, and the second probability that the target object may close the door in the Kth time segment of the N+1th day. This allows us to determine whether the target object has used the storage device, avoiding usage interference when executing the sterilization command.

[0051] In an exemplary embodiment, given that the storage device's open duration in the (K-1)th time interval of the (N+1)th cycle has been obtained, determining whether to issue a sterilization command to the storage device based on the target behavior feature and the open duration includes: obtaining a second probability corresponding to the target behavior feature; calculating a first target value by adding the second probability to a first constant; taking the logarithm of the first target value to obtain a first logarithmic value; calculating a second target value by dividing the storage device's open duration by the sum of the second constant and the first constant; taking the logarithm of the second target value to obtain a second logarithmic value; adding the product of the first logarithmic value and a first weight to the second logarithmic value to obtain a recommendation index; and comparing the recommendation index with a preset threshold to determine whether to issue a sterilization command to the storage device.

[0052] In one exemplary embodiment, comparing the suggested index with a preset threshold to determine whether to issue a sterilization command to the storage device includes: issuing a sterilization command to the storage device and prompting the target object that the storage device will activate the sterilization function if the suggested index is greater than or equal to the preset index threshold; and prohibiting the issuance of a sterilization command to the storage device if the suggested index is less than the preset index threshold.

[0053] For example, when the storage device is a smart refrigerator, the probability that each target object will not be opened in the k-th time period on day N+1, predicted by the classification result of the classifier, is recorded as p(u,k) (equivalent to the second probability in the embodiment of the present invention). On day N+1, at the timing point of each time period (equivalent to the time period interval in the embodiment of the present invention), the total duration of the target object being opened in the time period before that timing point is counted. For example, at the timing point of the k-th time period, the total duration of the target object being opened in the k-1 time period (equivalent to the opening duration in the embodiment of the present invention) is counted and recorded as c(u,k-1), in seconds. At the beginning of the k-th time period, calculate the sterilization suggestion index Idx(u,k) for a target object in the k-th time period. The formula for calculating the sterilization suggestion index Idx(u,k) is: Idx=log(c(u,k-1) / a+e)+b*log(p(u,k)+e); where p(u,k) and c(u,k-1) are input data determined based on historical data, where a, b, and e are constants, with suggested values: a=3600, e=0.000000001, b=1.2; after generating the index, if Idx>threshold T, a sterilization command is issued, with a suggested T=-15; otherwise, no sterilization command is issued.

[0054] It should be noted that the above-mentioned storage devices can also include disinfection cabinets, washing machines, etc., and this invention does not impose excessive limitations on them.

[0055] To better understand the process of confirming the above-mentioned sterilization command, the following describes the confirmation process of the above-mentioned sterilization command in conjunction with several optional embodiments.

[0056] As an optional embodiment, a smart refrigerator sterilization method is proposed. This method identifies and predicts user door opening and closing behavior, calculating a suggested index for activating the smart refrigerator's sterilization function in real time. When the user keeps the door open for an extended period, the suggested sterilization index is increased; conversely, when it is predicted that the user is likely to open the door again in the next period, the suggested index is decreased for energy conservation. This approach ensures timely and effective sterilization while improving efficiency by predicting the user's next door opening behavior. Thus, it simultaneously considers both the timeliness of sterilization and energy efficiency. Furthermore, equipment maintenance providers and users can adjust the activation threshold of the suggested index to achieve personalized sterilization plans, allowing for more flexible adjustments that prioritize either timely cleanliness or energy efficiency.

[0057] Figure 3 This is a schematic diagram of the overall architecture of a sterilization system according to an optional embodiment of the present invention; specifically, it includes: a prediction module 32, a real-time statistics module 34, and a sterilization start-up module 36;

[0058] Optionally, the prediction module 32 is responsible for constructing statistical features based on the user's historical refrigerator door opening and closing data, training the prediction model, and predicting the probability of each user opening the refrigerator door at various times of the next day.

[0059] Optionally, when determining whether to perform sterilization, the real-time statistics module 34 calculates the total duration of the user's door opening in the previous time period.

[0060] Optionally, the sterilization start module 36 generates a sterilization index based on the predicted probability output by the prediction module 32 and the door opening time output by the real-time statistics module 34, and compares it with a threshold. When the index is greater than the threshold, a refrigerator sterilization command is issued.

[0061] As an optional implementation method, Figure 4 This is a flowchart illustrating a prediction module according to an optional embodiment of the present invention, including:

[0062] Step 1: Constructing Features to Generate Features for Training the Classifier (equivalent to behavioral features in the embodiments of this invention): Based on historical (0, N-1) days of data (N is recommended to be 15-29 days), generate statistical features for users (equivalent to the target objects mentioned above) based on each day and time period. The time period can be one hour or more, and it is recommended that the duration be longer than the duration required for the sterilization process. The timing points can be any time at equal intervals, such as the hour of each hour. Calculate the statistical values ​​for each time period each day, with the duration in seconds and the number of times in cycles. Specifically, this includes:

[0063] a) Number of times a user opens the door per time period;

[0064] b) Total cumulative door-opening time for each user during each time period;

[0065] c) The duration from the last time the door was opened during the user's time period to the time when the door was closed at the timing point;

[0066] Calculate the average and standard deviation of the above statistics over days (i.e., N). The user's characteristics in the k-th time period are:

[0067] (1) The average number of times a user opens the door during the k-1 time period;

[0068] (2) Standard deviation of the number of times a user opens the door during the k-1 time period;

[0069] (3) The average number of times a user opens the door during time period k;

[0070] (4) Standard deviation of the number of times a user opens the door during time period k;

[0071] (5) Average number of times a user opens the door during time period k+1;

[0072] (6) Standard deviation of the number of times a user opens the door during time period k+1;

[0073] (7) The average total time users have opened the door during the k-1 time period;

[0074] (8) Standard deviation of the total cumulative door opening time of users during the k-1 time period;

[0075] (9) The average total time a user opens the door during time period k;

[0076] (10) Standard deviation of the total cumulative door opening time of the user during time period k;

[0077] (11) The average total time a user opens the door during the k+1 time period;

[0078] (12) Standard deviation of the total cumulative door opening time of users in time period k+1;

[0079] (13) The average duration from the last time the door was opened during the user's time period to the closing time at the k-1 time period timing point;

[0080] (14) The standard deviation of the time from the last door opening during the user's time period to the door closing time at the k-1 time period;

[0081] (15) The average duration from the last door opening during the user's time period to the door closing time at the k-time period's timing point;

[0082] (16) The standard deviation of the time from the last door opening during the user's time period to the door closing time at the k-time period's timing point;

[0083] (17) The average duration from the last time the door was opened during the user's time period to the closing time at the k+1 time period point;

[0084] (18) The standard deviation of the time from the last door opening during the user's time period to the door closing time at the k+1 time period;

[0085] Furthermore, if a day is divided into K time periods, then the feature matrix dimension for each user is K*18.

[0086] Step 2: Predictive model training. Determine category labels (equivalent to feature labels in the above embodiment) for the preset classifier model to be trained: Take the user's door opening records for each time period on day N. If there is a door opening behavior in the k-th time period, classify it as 1; otherwise, classify it as 0. A sample is formed by combining the features of a user for a time period and the corresponding category label. The preset classifier model is trained using this sample, thus determining the classifier used for classification.

[0087] Step 3: Perform prediction. Based on the user behavior statistical features of the historical data of (0, N days), input the user behavior statistical features into the classifier above, and output the probability of each sample belonging to different categories (0: not open, 1: open) in each time period. Combined with the user door opening record on day N, predict the probability of each user not opening the door in the k-th time period on day N+1 as p(u,k).

[0088] As an optional implementation, the real-time statistics module 34 is used to count the total duration of user door opening in the previous time period at each time point on the N+1th day. For example, at the time point of the kth time period, the total duration of user door opening in the k-1th time period is counted and denoted as c(u,k-1), with the unit being seconds.

[0089] The aforementioned sterilization activation module also includes: a sterilization index generation unit 42, a threshold judgment unit 44, and a sterilization command sending unit 46. Specifically, the sterilization index generation unit 42 is used to calculate the sterilization recommendation index Idx(u,k) of a target object at the beginning of time period k. The inputs are p(u,k) output by the prediction module 32 and c(u,k-1) output by the real-time statistics module. The sterilization index is calculated using the following formula: Idx=log(c(u,k-1) / a+e)+b*log(p(u,k)+e); where a, b, and e are constants, with recommended values ​​of: a=3600, e=0.000000001, b=1.2. After generating the index, if Idx>threshold T, a sterilization command is issued. Optionally, it is recommended that T=-15.

[0090] In summary, by constructing statistical features based on users' historical refrigerator door opening and closing records; using Gaussian Bayes methods to predict the probability of door opening in each future time period based on historical data; combining the predicted probability of door opening in each future time period with the calculation of the sterilization index based on real-time door opening duration; and generating a personalized sterilization index in real-time based on each user's historical data, this overall process can meet the need for timely sterilization after a long period of time, while avoiding the waste of sterilization caused by opening the door during or immediately after sterilization. It reduces energy consumption and equipment lifespan reduction caused by activating the sterilization system while ensuring the cleanliness of the refrigerator interior. This solves the problem in existing technologies that cannot automatically adjust the sterilization function activation scheme based on users' historical and real-time behavior.

[0091] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the confirmation of the sterilization instructions described in the various embodiments of the present invention.

[0092] This embodiment also provides a device for confirming sterilization commands. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0093] Figure 5 This is a structural block diagram of a sterilization command confirmation device according to an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes:

[0094] (1) Acquisition module 52, used to acquire behavioral statistics of the target object; wherein, the behavioral statistics are the behavioral characteristics of the target object in K time intervals in N cycles of the same duration, each time interval in the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers;

[0095] (2) Prediction module 54, used to predict the target behavior characteristics of the target object in the Kth time interval of the N+1th cycle based on the behavior statistics;

[0096] (3) Determining module 56 is used to determine whether to issue a sterilization command to the device based on the target behavior characteristics and the opening duration when the opening duration of the storage device in the K-1 time interval of the N+1th cycle has been obtained.

[0097] Using the aforementioned device, behavioral statistics of the target object are obtained; wherein, the behavioral statistics are the behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers; based on the behavioral statistics, the target behavioral characteristics of the target object in the Kth time interval of the N+1th period are predicted; given that the opening duration of the storage device in the K-1th time interval of the N+1th period has been obtained, a sterilization command is determined based on the target behavioral characteristics and the opening duration. In other words, by predicting the target object's behavioral characteristics in the (N+1)th period based on the target object's behavioral characteristics over N periods, and then combining this with the corresponding open duration of the storage device, it is determined whether the current storage device needs to be sterilized, and a sterilization command to activate the storage device's sterilization function is sent. Therefore, this solves the problems in the prior art where the sterilization process of the storage device conflicts with the use of the target object, resulting in low sterilization effect and poor user experience for the target object. This allows the sterilization operation of the storage device to be temporarily suspended when the target object uses the storage device frequently or is about to use it, and the storage device to quickly enter the sterilization process after the target object finishes using the storage device. This improves the user experience of the target object while increasing the sterilization efficiency of the storage device, and avoids the situation where the sterilization effect is reduced due to the target object using the storage device during the sterilization process.

[0098] In an exemplary embodiment, the above-described apparatus further includes: a feature module, configured to determine the average value and standard deviation of the behavioral characteristics of the target object in the (M-1)th time interval, the Mth time interval, and the (M+1)th time interval of each of the N periods; wherein, M+1 is less than or equal to K, and the three time intervals (M-1, M, and M+1) have the same duration; to determine a feature matrix of the target object corresponding to the N periods based on the average value and the standard deviation; and to add feature labels to the first feature in the feature matrix according to preset category features to obtain a second feature for classification, wherein the feature labels are used to identify whether the target object has opened a storage device in each time interval.

[0099] In one exemplary embodiment, the above-mentioned feature module further includes:

[0100] A sample unit is used to correspond the second feature with the behavioral features of the target object in K time intervals of the Nth period to obtain a training sample;

[0101] The training unit is used to input the training samples into a preset model and obtain a classification model for classifying the statistical data of the target object's behavior through training.

[0102] A classification unit is used to determine the feature set corresponding to the N periods in the target object behavior statistics, input the feature set into the classification model, and obtain the target feature labels corresponding to the K time intervals of the N periods respectively;

[0103] The determining unit is used to determine the first probability that the target object will open the storage device in each time interval based on the target feature label.

[0104] In an exemplary embodiment, the prediction module is further configured to, upon determining a first probability that the target object will open the storage device in the Kth time interval of the Nth period, determine a second probability of the target object in the Kth time interval of the N+1th period based on the first probability; wherein the second probability is used to indicate the probability that the target object will not open the storage device in the Kth time interval of the N+1th period; and predict the target behavior characteristics of the target object based on the second probability.

[0105] In an exemplary embodiment, the determining module is further configured to: obtain a second probability corresponding to the target behavior feature; calculate a first target value by adding the second probability to a first constant; take the logarithm of the first target value to obtain a first logarithmic value; calculate a second target value by dividing the storage device open duration by the sum of the second constant and the first constant; take the logarithm of the second target value to obtain a second logarithmic value; add the product of the first logarithmic value and the first weight to the second logarithmic value to obtain a suggestion index; and compare the suggestion index with a preset threshold to determine whether to issue a sterilization command to the storage device.

[0106] In an exemplary embodiment, the determining module is further configured to, when the suggested index is greater than or equal to a preset index threshold, issue a sterilization command to the storage device and prompt the target object that the storage device will activate the sterilization function; and when the suggested index is less than the preset index threshold, prohibit the issuance of a sterilization command to the storage device.

[0107] In the description of this invention, it should be understood that the terms "center," "upper," "lower," "front," "rear," "left," and "right," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0108] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. When a component is referred to as being "fixed to" or "set on" another element, it can be directly on the other component or there may be an intervening component. When a component is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intervening component. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0109] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0110] Embodiments of the present invention also provide a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0111] In one exemplary embodiment, the storage medium described above may be configured to store a computer program for performing the following steps:

[0112] S1, Obtain behavioral statistics of the target object; wherein, the behavioral statistics are the behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers;

[0113] S2, based on the behavioral statistics, predict the target behavior characteristics of the target object in the Kth time interval of the N+1th cycle;

[0114] S3, having already obtained the opening duration of the storage device within the K-1 time interval of the N+1th cycle, determine whether to issue a sterilization command to the device based on the target behavior characteristics and the opening duration.

[0115] In one exemplary embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0116] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0117] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0118] In one exemplary embodiment, the processor described above may be configured to perform the following steps via a computer program:

[0119] S1, Obtain behavioral statistics of the target object; wherein, the behavioral statistics are the behavioral characteristics of the target object in K time intervals within N periods of equal duration, each of the K time intervals has the same duration and each time interval has at least one adjacent time interval, N is greater than 1, and N and K are positive integers;

[0120] S2, based on the behavioral statistics, predict the target behavior characteristics of the target object in the Kth time interval of the N+1th cycle;

[0121] S3, having already obtained the opening duration of the storage device within the K-1 time interval of the N+1th cycle, determine whether to issue a sterilization command to the device based on the target behavior characteristics and the opening duration.

[0122] In an exemplary embodiment, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0123] It will be apparent to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. In one exemplary embodiment, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device. Furthermore, in some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be implemented as a single integrated circuit module. Thus, the present invention is not limited to any particular hardware and software combination.

[0124] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of confirming a sterilization instruction, characterized by, The method comprises: acquiring behavior statistics of a target object; wherein the behavior statistics are behavior characteristics of the target object in K time interval sections in N cycles with the same time length, each of the K time interval sections has the same time length and at least one adjacent time interval section, N is greater than 1, and N and K are positive integers; predicting target behavior characteristics of the target object in a K time interval section in an N+1 cycle according to the behavior statistics; in a case where an opening time length corresponding to a storage device in a K-1 time interval section in the N+1 cycle has been acquired, determining whether to issue a sterilization instruction to the device based on the target behavior characteristics and the opening time length; wherein the target behavior characteristics are used to indicate characteristics of the opening and closing door behavior of the target object on the storage device; the determination of whether to issue the sterilization instruction to the device based on the target behavior characteristics and the opening time length comprises: acquiring a second probability corresponding to the target behavior characteristics, calculating a first target value obtained by adding the second probability to a first constant, taking a logarithm of the first target value to obtain a first logarithm value; calculating a second target value obtained by dividing the opening time length of the storage device by a second constant and adding the second constant to the first constant, and taking a logarithm of the second target value to obtain a second logarithm value; adding a product of the first logarithm value and a first weight to the second logarithm value to obtain a suggestion index; comparing the suggestion index with a preset threshold to determine whether to issue the sterilization instruction to the storage device.

2. The method of claim 1, wherein the decontamination instruction is confirmed by a user. The behavior characteristics include at least one of the following: the number of times the target object opens the storage device, the cumulative opening time length of the target object on the storage device, and the time length from the last time the target object opens the storage device to the closing of the storage device before the end of the time interval section.

3. The method of claim 1, wherein the decontamination instruction is confirmed by a user. After acquiring the behavior statistics of the target object, the method further comprises: determining average values and standard deviations corresponding to behavior characteristics of the target object in an M-1 time interval section, an M time interval section, and an M+1 time interval section of each of the N cycles; wherein M+1 is less than or equal to K, and the M-1 time interval section, the M time interval section, and the M+1 time interval section correspond to the same time length; determining a feature matrix corresponding to the N cycles of the target object based on the average values and the standard deviations; adding a feature label to a first feature in the feature matrix according to a preset category feature to obtain a second feature for classification, wherein the feature label is used to identify whether the target object has an opening storage device behavior in each time interval section.

4. The method of claim 3, wherein the decontamination instruction is confirmed by a user. After adding the feature label to the first feature in the feature matrix according to the preset category feature to obtain the second feature for classification, the method further comprises: corresponding the second feature to the behavior characteristics of the target object in the K time interval sections in the N cycle to obtain a training sample; inputting the training sample into a preset model to obtain a classification model for classifying the behavior statistics of the target object through training; and determine a feature set corresponding to the N periods in the target object behavior statistical data, input the feature set into the classification model, and obtain target feature labels corresponding to K time interval periods of the N periods respectively; determine a first probability of the target object opening a storage device in each time interval period according to the target feature labels.

5. The method of claim 1, wherein the decontamination instruction is confirmed by a user. predict a target behavior feature of the target object in a Kth time interval period in an N+1th period according to the behavior statistical data, including: in a case where it is determined that the target object opens the storage device in the Kth time interval period in the Nth period, determine a second probability of the target object opening the storage device in the Kth time interval period in the N+1th period according to the target first probability; the second probability is used to indicate a probability of the target object not opening the storage device in the Kth time interval period in the N+1th period; predict the target behavior feature of the target object according to the second probability.

6. The method of claim 1, wherein the decontamination command is confirmed if the pressure in the chamber is less than or equal to a predetermined pressure. compare the size of the recommendation index and a preset threshold to determine whether to issue a sterilization instruction to the storage device, including: in a case where the recommendation index is greater than or equal to a preset index threshold, issue the sterilization instruction to the storage device, and prompt the target object that the storage device will start the sterilization function; in a case where the recommendation index is less than the preset index threshold, prohibit the sterilization instruction to be issued to the storage device.

7. A device for confirming sterilization commands, characterized in that, including: an acquisition module configured to acquire behavior statistical data of a target object; the behavior statistical data is a behavior feature of the target object in K time interval periods in N periods with the same time length, each of the K time interval periods has the same time length and at least one adjacent time interval period, N is greater than 1, and N and K are positive integers; a prediction module configured to predict a target behavior feature of the target object in a Kth time interval period in an N+1th period according to the behavior statistical data; a determination module configured to, in a case where the opening time length of the storage device in a K-1th time interval period in the N+1th period has been acquired, determine whether to issue a sterilization instruction to the device based on the target behavior feature and the opening time length of the storage device; the target behavior feature is used to indicate a feature of the opening and closing door behavior of the target object on the storage device; the determination module is further configured to acquire a second probability corresponding to the target behavior feature, calculate a first target value obtained by adding the second probability and a first constant, take a logarithm of the first target value to obtain a first logarithm value, calculate a second target value obtained by dividing the opening time length of the storage device by a second constant and adding the first constant, take a logarithm of the second target value to obtain a second logarithm value, add a product of the first logarithm value and a first weight to the second logarithm value to obtain a recommendation index, and compare the size of the recommendation index and a preset threshold to determine whether to issue the sterilization instruction to the storage device.

8. A computer readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program runs to execute the method of any one of claims 1 to 6. 9.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to execute the method in any one of claims 1 to 6 by using the computer program.

Images