Water heater control method, apparatus, device, and storage medium

Abstract

The application belongs to the technical field of household appliances, and particularly relates to a water heater control method, device, equipment and storage medium. The water heater control method comprises the following steps: determining a plurality of groups of historical water use behavior data corresponding to a water heater, each group of historical water use behavior data comprising a water use start time, a water use duration and a water use temperature; obtaining a predicted water use start time of the water heater by analyzing and processing a plurality of water use start times; obtaining a predicted water use duration of the water heater by analyzing and processing the plurality of water use start times and a plurality of water use durations; obtaining a predicted water use temperature of the water heater by analyzing and processing the plurality of water use start times, the plurality of water use durations and the plurality of water use temperatures; and controlling a heating operation of the water heater according to the predicted water use start time, the predicted water use duration and the predicted water use temperature. Thus, based on the prediction of the water use start time, the water use duration and the water use temperature, the water heater can accurately provide hot water for the user in advance.

Description

Technical Field

[0001] This application belongs to the field of household appliance technology, specifically relating to a water heater control method, device, equipment, and storage medium. Background Technology

[0002] With the development of water heater technology and artificial intelligence technology, gas water heaters have developed a variety of intelligent functions, such as the zero cold water function.

[0003] Gas water heaters with a zero-cold-water function recirculate cold water back into the heater for heating each time it is turned on, solving the problem of having to run some cold water through the shower or faucet before using hot water. However, due to factors such as heating speed and water circuit length, gas water heaters with a zero-cold-water function still require a waiting period before hot water is available each time they are turned on, affecting the user experience. Summary of the Invention

[0004] In order to solve the above-mentioned problems in the prior art, namely, the problem that gas water heaters with zero cold water function require a period of time to produce hot water after each turn-on, this application provides a water heater control method, device, equipment and storage medium.

[0005] In a first aspect, this application provides a water heater control method, including:

[0006] Determine multiple sets of historical water usage behavior data corresponding to the water heater. Each set of historical water usage behavior data includes the start time of water usage, the duration of water usage, and the water temperature.

[0007] By analyzing and processing multiple water usage start times in the multiple sets of historical water usage behavior data, the predicted water usage start time of the water heater is obtained;

[0008] By analyzing and processing multiple water usage start times and multiple water usage durations in the multiple sets of historical water usage behavior data, the predicted water usage duration of the water heater is obtained;

[0009] By analyzing and processing multiple water usage start times, multiple water usage durations, and multiple water usage temperatures from the multiple sets of historical water usage behavior data, the predicted water usage temperature of the water heater is obtained.

[0010] The heating operation of the water heater is controlled based on the predicted water usage start time, the predicted water usage duration, and the predicted water usage temperature.

[0011] In one possible implementation, the step of analyzing and processing multiple water usage start times from the multiple sets of historical water usage behavior data to obtain the predicted water usage start time of the water heater includes:

[0012] Clustering is performed on the multiple water usage start times to obtain clustering results;

[0013] Based on the clustering results, the predicted water usage start time is determined.

[0014] In one possible implementation, determining the predicted water use start time based on the clustering results includes:

[0015] Based on the center value of each cluster in the clustering results, multiple clusters in the clustering results are merged, and / or, based on the number of water use start times contained in each cluster in the clustering results, one or more clusters in the clustering results are discarded.

[0016] Based on the processed clustering results, the predicted water usage start time is determined.

[0017] In one possible implementation, the step of analyzing and processing multiple water usage start times and multiple water usage durations from the multiple sets of historical water usage behavior data to obtain the predicted water usage duration of the water heater includes:

[0018] The multiple water usage start times are grouped to obtain multiple first groups;

[0019] Based on the correspondence between the water usage start time and the water usage duration, determine the average water usage duration corresponding to the first group;

[0020] Based on the average water usage duration corresponding to the first group, the predicted water usage duration corresponding to the first group is determined.

[0021] In one possible implementation, the grouping of the plurality of water usage start times to obtain a plurality of first groups includes:

[0022] Based on multiple preset time points, the multiple water usage start times are divided into multiple first groups, wherein different first groups correspond to different preset time points.

[0023] In one possible implementation, the step of analyzing and processing multiple water usage start times, multiple water usage durations, and multiple water usage temperatures from the multiple sets of historical water usage behavior data to obtain the predicted water temperature of the water heater includes:

[0024] Based on the multiple water usage durations, a temperature score is determined for the multiple water usage temperatures;

[0025] The multiple water usage start times are grouped to obtain multiple second groups;

[0026] Based on the temperature score of the water temperature corresponding to the water start time in the second group, the predicted water temperature corresponding to the second group is determined.

[0027] In one possible implementation, the historical water usage data further includes the water usage date, and the step of determining the temperature scores of the multiple water usage temperatures based on the multiple water usage durations includes:

[0028] Based on the water usage date corresponding to the water temperature, determine the date influence factor corresponding to the water temperature;

[0029] Based on the water usage duration corresponding to the water temperature, determine the behavioral influencing factor corresponding to the water temperature;

[0030] The temperature score of the water temperature is determined based on the date influence factor corresponding to the water temperature and the behavior influence factor corresponding to the water temperature.

[0031] In one possible implementation, grouping the plurality of water usage start times to obtain a plurality of second groups includes:

[0032] Based on multiple preset time intervals, the multiple water usage start times are divided into multiple second groups, wherein different second groups correspond to different preset time intervals.

[0033] In one possible implementation, determining the predicted water temperature corresponding to the second group based on the temperature score of the water temperature corresponding to the water use start time in the second group includes:

[0034] For each of the second groups, among the water temperatures corresponding to the water usage start time included in the second group, determine the sum of temperature scores for the same water temperature;

[0035] The predicted water temperature corresponding to the second group is determined to be the water temperature with the largest sum of temperature scores among the water temperatures corresponding to the water use start time included in the second group.

[0036] In one possible implementation, controlling the heating operation of the water heater based on the predicted water usage start time, the predicted water usage duration, and the predicted water usage temperature includes:

[0037] Based on the predicted water usage start time, the predicted water usage duration, and the predicted water usage temperature, the predicted water usage behavior data of the water heater on the predicted date is determined;

[0038] Determine whether the predicted date meets the push time requirements;

[0039] If the predicted date meets the push time requirement, a control message is sent to the water heater, the control message containing the predicted water usage behavior data.

[0040] In one possible implementation, determining whether the predicted date meets the push time requirement includes:

[0041] Based on the actual number of days the water heater is used within a preset time period and / or the water usage interval of the water heater, determine whether the predicted date meets the push time requirement.

[0042] In one possible implementation, determining whether the predicted date meets the push time requirement includes:

[0043] Divide dates within a preset time period into multiple categories;

[0044] Based on the actual number of days in each of the multiple categories, the actual number of days of water usage in each of the multiple categories, and the category to which the predicted date belongs among the multiple categories, it is determined whether the predicted date meets the push time requirements.

[0045] Secondly, this application provides a water heater control device, comprising:

[0046] The determination module is used to determine multiple sets of historical water usage behavior data corresponding to the water heater. Each set of historical water usage behavior data includes the start time of water usage, the duration of water usage, and the water temperature.

[0047] The first prediction module is used to analyze and process multiple water use start times in the multiple sets of historical water use behavior data to obtain the predicted water use start time of the water heater;

[0048] The second prediction module is used to analyze and process multiple water use start times and multiple water use durations in the multiple sets of historical water use behavior data to obtain the predicted water use duration of the water heater.

[0049] The third prediction module is used to analyze and process multiple water use start times, multiple water use durations, and multiple water use temperatures in the multiple sets of historical water use behavior data to obtain the predicted water use temperature of the water heater.

[0050] The control module is used to control the heating operation of the water heater based on the predicted water usage start time, the predicted water usage duration, and the predicted water usage temperature.

[0051] Thirdly, this application provides an electronic device, comprising:

[0052] Processor and memory;

[0053] The memory stores computer programs;

[0054] When the processor executes the computer program stored in the memory, it implements the water heater control method provided in the first aspect or any possible implementation of the first aspect.

[0055] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the water heater control method provided in the first aspect or any possible embodiment of the first aspect.

[0056] Fifthly, this application provides a chip, comprising:

[0057] Processor and memory;

[0058] The memory stores computer programs;

[0059] When the processor executes the computer program stored in the memory, it implements the water heater control method provided in the first aspect or any possible implementation of the first aspect.

[0060] Sixthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the water heater control method provided in the first aspect or any possible implementation thereof.

[0061] Those skilled in the art will understand that in this application, based on determining the start time, duration, and temperature of water usage from multiple sets of historical water usage behavior data corresponding to the water heater, the predicted start time, duration, and temperature of water usage for the water heater are predicted. Based on these predicted start time, duration, and temperature, the heating operation of the water heater is controlled. Therefore, by predicting the user's start time, duration, and temperature of water usage, the water heater can preheat the water, providing hot water to the user promptly. In particular, water heaters with a zero-cold-water function can provide hot water promptly when this function is activated, avoiding user waiting, improving the intelligence of the water heater, and enhancing the user experience. Attached Figure Description

[0062] Preferred embodiments of the water heater control method, apparatus, device, and storage medium of this application will now be described with reference to the accompanying drawings. The drawings are as follows:

[0063] Figure 1 Example diagrams of application scenarios provided in the embodiments of this application;

[0064] Figure 2 A schematic flowchart of a water heater control method provided in one embodiment of this application;

[0065] Figure 3 A schematic flowchart of a water heater control method provided in another embodiment of this application;

[0066] Figure 4 A schematic flowchart of a water heater control method provided in another embodiment of this application;

[0067] Figure 5 A schematic flowchart of a water heater control method provided in another embodiment of this application;

[0068] Figure 6 A schematic diagram of the structure of a water heater control device provided in one embodiment of this application;

[0069] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0070] First, those skilled in the art should understand that these embodiments are merely for explaining the technical principles of this application and are not intended to limit the scope of protection of this application. Those skilled in the art can make adjustments as needed to adapt to specific application scenarios.

[0071] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms "a" and "the" as used in the embodiments of this application are also intended to include the plural forms unless the context clearly indicates otherwise.

[0072] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can be represented as: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0073] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0074] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0075] Currently, gas water heaters with zero-cold-water function are affected by factors such as heating speed and water circuit length, requiring a waiting period of time after being turned on before hot water is available, which affects the user experience.

[0076] To address the aforementioned problems, this application provides a water heater control method. In this method, based on multiple sets of historical water usage data corresponding to the water heater, the predicted water usage start time, predicted water usage duration, and predicted water temperature are determined. The heating operation of the water heater is then controlled according to these predicted start times, durations, and temperatures. Therefore, by predicting the water usage start time, duration, and temperature, the water heater can preheat the water, providing hot water to the user without waiting, effectively improving the water heater's intelligence and providing a better user experience.

[0077] Optionally, the water heater is a gas water heater with zero cold water function.

[0078] Figure 1 This is a schematic diagram illustrating an application scenario provided in an embodiment of this application. For example... Figure 1 As shown, the application scenario includes a water heater 101 and a server 102. The water heater 101 and the server 102 communicate, for example, through a network. After authorization by the user, the server 102 can obtain the user's water usage details on the water heater 101 and can also send control commands to the water heater 101 to control the heating of the water heater 101.

[0079] For example, the execution subject in this application embodiment is an electronic device, which can be a water heater or a server. Alternatively, the electronic device can also be a terminal, such as a central control device in a smart home environment. When the execution subject is a server, the server can determine the predicted water usage start time, predicted water usage duration, and predicted water usage temperature for multiple water heaters, and control the multiple water heaters.

[0080] In subsequent embodiments, the execution entity is described as a server.

[0081] Figure 2 This is a schematic flowchart of a water heater control method provided in one embodiment of this application. Figure 2 As shown, the method includes:

[0082] S201. Determine multiple sets of historical water usage behavior data corresponding to the water heater.

[0083] Each set of historical water use data includes the start time of water use, duration of water use, and water temperature.

[0084] In this embodiment, with user authorization, the water heater can report its operational data at multiple points in time to the server, either in real-time, periodically, or when it detects user water usage. The operational data at each point in time includes the water usage status and set temperature. The water usage status includes a first state indicating that the user is using water and a second state indicating that the user is not using water. For example, the first state has a value of T (true), and the second state has a value of F (false).

[0085] Next, after receiving the water heater's device operating data, the server can identify multiple device operating data points where the water usage status is continuously in the first state. Based on the time corresponding to these multiple device operating data points, the corresponding water usage period is determined. Based on the set temperatures in these multiple device operating data points, the corresponding water temperature for each water usage period is determined (e.g., the average of the set temperatures in the multiple device operating data points). In this way, multiple water usage periods and their corresponding water temperatures can be obtained. Based on these multiple water usage periods and their corresponding water temperatures, multiple sets of historical water usage behavior data are determined.

[0086] The water usage period includes the start and end times.

[0087] For example, in the equipment operation data reported by the water heater, the water usage status in multiple equipment operation data within the time period t1 to t2 is all in the first state, and the water usage status in multiple equipment operation data within the time period t3 to t4 is also all in the first state. Then, the time period t1 to t2 is determined to be one water usage period a1, and t3 to t4 is another water usage period a2. t1 is the start time of water usage period a1, t2 is the end time of water usage period a1, t3 is the start time of water usage period a2, and t4 is the end time of water usage period a2.

[0088] In one example, for each water usage period: the water usage duration can be determined based on the start and end times of the water usage period; the water usage duration corresponding to the water usage period is then used as the water usage duration in the historical water usage behavior data; the water usage start time of the water usage period is then used as the water usage start time in the historical water usage behavior data; and the water temperature of the water usage period is then used as the water temperature in the historical behavior data. In this way, multiple sets of historical water usage behavior data are obtained.

[0089] In another example, the historical water use behavior data for each group can directly include the start time of water use, the end time of water use, and the water temperature. In this way, the duration of water use in the historical water use behavior data can be indirectly reflected by the start time and end time of water use.

[0090] After obtaining multiple sets of historical water usage behavior data from the water heater, predicted water usage behavior data can be determined based on this data. This predicted water usage behavior data includes the predicted start time, predicted duration, and predicted temperature. The processes for determining the predicted start time, duration, and temperature are then described in steps S202, S203, and S204. Steps S202, S203, and S204 can be executed in parallel or sequentially; the specific order of execution is not restricted here.

[0091] S202. By analyzing and processing multiple water use start times in multiple sets of historical water use behavior data, the predicted water use start time of the water heater is obtained.

[0092] In this embodiment, the water usage start time in the historical behavior data can reflect the user's water usage time pattern. Therefore, multiple water usage start times can be obtained from multiple sets of historical behavior data of the water heater. By analyzing and processing multiple water usage start times, the predicted water usage start time of the water heater can be obtained.

[0093] In one example, the water start time that occurs more than a certain number of times among multiple water start times of the water heater can be determined as the predicted water start time of the water heater.

[0094] S203. By analyzing and processing multiple water use start times and multiple water use durations in multiple sets of historical water use behavior data, the predicted water use duration of the water heater is obtained.

[0095] In this embodiment, the duration of water usage by users typically varies at different times. For example, users are accustomed to showering at 6 PM, so their water usage is longer at 6 PM and shorter at other times. Therefore, to more accurately determine the predicted water usage duration for the water heater, multiple water usage start times and durations obtained from multiple sets of historical water usage behavior data are analyzed and processed to obtain the predicted water usage duration for the water heater.

[0096] During the prediction process, multiple water usage start times and corresponding water usage durations can be obtained from multiple sets of historical water usage behavior data of the water heater. The multiple water usage start times and corresponding water usage durations are then analyzed and processed to obtain the predicted water usage durations of the water heater at multiple times.

[0097] S204. By analyzing and processing multiple water usage start times, multiple water usage durations, and multiple water usage temperatures from multiple sets of historical water usage behavior data, the predicted water temperature of the water heater is obtained.

[0098] In this embodiment, the hot water temperature required by the user varies at different times. For example, the hot water temperature required by the user at night is lower than that required during the day. Different water usage behaviors also require different hot water temperatures; for example, the hot water temperature required when showering is higher than that required when brushing teeth or washing the face. Therefore, since the start time of water usage reflects the user's water usage time and the duration of water usage can distinguish different water usage behaviors, the predicted water temperature of the water heater can be obtained by analyzing multiple start times, durations, and temperatures from multiple sets of historical water usage behavior data, thus improving the accuracy of the predicted water temperature.

[0099] During the prediction process, multiple water usage start times, corresponding water usage durations, and corresponding water temperatures can be obtained from multiple sets of historical water usage behavior data of the water heater. The predicted water temperatures of the water heater at multiple times can be obtained by analyzing and processing these multiple water usage start times, corresponding water usage durations, and corresponding water temperatures.

[0100] S205. Control the heating operation of the water heater based on the predicted start time of water use, the predicted duration of water use, and the predicted water temperature.

[0101] In this embodiment, after obtaining the predicted water usage start time, the predicted water usage duration at multiple times, and the predicted water temperature at multiple times, the predicted water usage start time, the predicted water usage duration at multiple times, and the predicted water temperature at multiple times can be combined, for example, by combining them according to time, to obtain the predicted water usage behavior data of the water heater. The server can send the predicted water usage behavior data of the water heater to the water heater, and the water heater can perform heating operations according to the predicted water usage behavior data. Alternatively, the server can send control commands to the water heater according to the predicted water usage behavior data.

[0102] In this embodiment, based on multiple sets of historical water usage data from the water heater, a predicted water usage start time is determined according to multiple water usage start times. A predicted water usage duration is also determined based on these multiple start times and durations. Finally, a predicted water temperature is determined based on the multiple start times, durations, and end times. The heating operation of the water heater is then controlled based on these predicted start times, durations, and temperatures. Thus, by predicting the water usage start time, duration, and temperature, the water heater can preheat the water based on the prediction results, providing hot water to the user immediately upon use, eliminating waiting time. Furthermore, this embodiment employs targeted prediction methods for each of the three parameters, effectively improving prediction accuracy.

[0103] In some embodiments, after obtaining multiple sets of historical water use behavior data, at least one of the following processing operations can be performed on the multiple sets of historical water use behavior data:

[0104] Processing Operation 1: Considering that users may temporarily stop using water during a single water usage session, there may be cases where different sets of historical water usage data actually belong to the same water usage session. Therefore, historical water usage data from different sets of data with water usage intervals less than the water usage interval threshold can be merged.

[0105] Processing Operation 2: Considering that historical water use data with shorter durations have little effect on subsequent prediction processes, and may even have the opposite effect, affecting prediction accuracy, historical water use data with durations less than the duration threshold can be deleted from multiple sets of historical water use data.

[0106] Processing Operation 3: Considering that the water heater needs to preheat in order to prepare hot water of the corresponding temperature before the user uses water, the water use start time in the historical water use data can be pushed forward by a preset time for each group of historical water use data.

[0107] Processing Operation 4: To reduce the amount of data, merge historical water usage data that overlaps within the same time period.

[0108] In some embodiments, considering that the server needs to manage multiple water heaters, the historical water usage behavior data of each group of water heaters may also include the device identifier of the water heater, such as the media access control (MAC) address of the water heater.

[0109] When the historical behavior data of each water heater also includes the water heater's device identifier, when determining the predicted water use start time, predicted water use duration, and predicted water use temperature of the water heater, multiple water use start times, multiple water use durations, and multiple water use temperatures from the historical water use behavior data corresponding to the same device identifier are used to avoid data confusion in the prediction process of different water heaters.

[0110] When the historical behavior data of each water heater also includes the water heater's device identifier, after obtaining the predicted water usage start time, the correspondence between the water heater's device identifier and the predicted water usage start time can be obtained. Similarly, after obtaining the predicted water usage duration and predicted water temperature, the correspondence between the water heater's device identifier and the predicted water usage duration, as well as the correspondence between the water heater's device identifier and the predicted water temperature, can be obtained, thus avoiding confusion between the prediction results of different water heaters.

[0111] Furthermore, in the process of controlling the heating operation of the water heater based on the predicted water usage start time, predicted water usage duration, and predicted water temperature, the predicted water usage behavior data of the water heater can be determined based on the water heater's device identifier and the corresponding predicted water usage start time, predicted water usage duration, and predicted water temperature. Then, the heating operation of the water heater can be controlled based on the predicted water usage behavior. In other words, the device identifier is used as a key to determine the matching (i.e., the predicted water usage start time, predicted water usage duration, and predicted water temperature corresponding to the same device identifier).

[0112] In some embodiments, considering that the historical water usage behavior data for different groups correspond to different water usage dates (or collection dates), and that historical water usage behavior data for different data dates may be used to determine the predicted water usage behavior data of the water heater on different predicted dates, the water usage behavior data for each group of water heaters may also include the water usage date of that group of water usage behavior data.

[0113] Taking historical water usage data, including water usage date, start time, end time, and temperature, as an example, and using the start and end times to indirectly reflect water usage duration, Table 1 provides an example of historical water usage data:

[0114] Table 1

[0115] Water usage date Water usage start time Water usage end time water temperature 20210801 9:48 10:20 42 20210802 20:11 20:33 45 20210802 13:44 14:06 43 20210802 19:47 20:11 42 20210803 18:02 18:26 45 20210803 18:55 19:34 42 20210804 14:01 14:23 43 20210804 19:26 20:03 42 20210805 6:20 7:00 42 20210805 20:50 21:20 43

[0116] In some embodiments, considering that historical water usage behavior data from different data usage dates may be used to determine the predicted water usage behavior data of the water heater on different predicted dates, one possible implementation of S201 includes: determining multiple sets of historical water usage behavior data corresponding to the water heater based on the predicted date. Thus, historical water usage behavior data is obtained in a targeted manner based on the predicted date, improving prediction accuracy.

[0117] Optionally, based on the predicted date, multiple sets of historical water usage behavior data corresponding to the water heater are determined, including: subtracting a first preset number of days from the predicted date to obtain the end date, and subtracting a second preset number of days from the end date to obtain the start date, thus acquiring multiple sets of historical water usage behavior data where the water usage dates fall between the start and end dates. Therefore, on the end date preceding the predicted date, predictions can be made based on multiple sets of historical water usage behavior data, avoiding the problem of insufficient time to make predictions on the predicted date itself due to factors such as a large number of water heaters and a large amount of historical water usage behavior data.

[0118] For example, assuming the predicted date is T, the first preset number of days is 2, and the second preset number of days is 30, then multiple sets of historical water usage data within 30 days are obtained starting from day T-2.

[0119] In some embodiments, considering that water temperature is greatly affected by ambient temperature, and the difference in ambient temperature between the beginning and end of a month can be significant, water temperature prediction is highly time-sensitive. Predicting water temperature requires using historical water usage data with usage dates close to the prediction date; historical water usage data with usage dates far from the prediction date can interfere with the accuracy of water temperature prediction. Therefore, the usage dates used to determine the predicted water temperature in historical water usage data are different from those used to determine the predicted water usage start time and predicted water usage duration. Specifically, when the historical water usage data includes usage dates, one possible implementation of S202 includes: acquiring multiple water usage start times, multiple water usage durations, and multiple water temperatures from multiple sets of historical water usage data where the time interval between the usage date and the prediction date is less than a third preset number of days; and obtaining the predicted water temperature for the water heater by analyzing and processing the multiple water usage start times, multiple water usage durations, and multiple water temperatures. The third preset number of days is less than the second preset number of days. This improves the accuracy of the predicted water temperature.

[0120] The following examples expand on the process of determining the predicted water use start time, predicted water use duration, and predicted water use temperature. These examples can be combined with each other.

[0121] Figure 3 This is a schematic flowchart illustrating a water heater control method according to another embodiment of this application. Figure 3As shown, the method includes:

[0122] S301. Determine multiple sets of historical water usage behavior data corresponding to the water heater. Each set of historical water usage behavior data includes the start time of water usage, the duration of water usage, and the water temperature.

[0123] The implementation principle and technical effects of S301 are the same as those in the aforementioned embodiments, and will not be repeated here.

[0124] S302. By analyzing and processing multiple water use start times in multiple sets of historical water use behavior data, the predicted water use start time of the water heater is obtained.

[0125] S302 includes S3021 and S3022:

[0126] S3021. Cluster the multiple water use start times in multiple sets of historical water use behavior data to obtain clustering results. The clustering results include one or more clusters.

[0127] In this embodiment, hierarchical clustering can be performed on multiple water use start times in multiple sets of historical water use behavior data, and water use start times with high similarity can be grouped into one category, that is, clustered into one cluster.

[0128] In one example, the process of hierarchically clustering multiple water usage start times may include:

[0129] First, each water usage start time is grouped into a separate category, and the distance between any two categories is calculated, i.e., the similarity between any two water usage start times. Second, based on the distance between any two categories, classes are merged to reduce the number of classes. For example, the two closest classes are identified and merged, reducing the total number of classes by one. Next, the distance between the merged class and all other classes is calculated, and this merging process is repeated until the number of classes reaches a threshold. This results in multiple classes, each corresponding to a cluster.

[0130] Optionally, the average-linkage method can be used to determine the distance between two classes. In the average-linkage method, the distance between two classes is determined as the average of the distances between any two water usage start times.

[0131] S3022. Based on the clustering results, determine the predicted start time of water use for the water heater.

[0132] In this embodiment, multiple predicted water usage start times for the water heater can be determined based on the center value or mean value of multiple clusters in the clustering results. For example, the center value of each cluster can be determined as the predicted water usage start time for the water heater, or the mean value of each cluster can be determined as the predicted start time for the water heater.

[0133] In one possible implementation, S3022 includes: merging multiple clusters in the clustering result based on the center values ​​of each cluster in the clustering result, and / or discarding one or more clusters in the clustering result based on the number of water usage start times contained in each cluster; and determining the predicted water usage start time of the water heater based on the processed clustering result. Thus, by merging and / or discarding clusters, the clustering effect is improved, thereby increasing the accuracy of the predicted water usage start time.

[0134] In this implementation, among multiple clusters, the difference between the center values ​​of each cluster can be determined, and different clusters whose difference between center values ​​is less than a difference threshold are merged. And / or, among multiple clusters, clusters containing fewer water usage start times can be discarded, that is, clusters with fewer samples can be discarded.

[0135] S303. By analyzing and processing multiple water use start times and multiple water use durations in multiple sets of historical water use behavior data, the predicted water use duration of the water heater is obtained.

[0136] S304. By analyzing and processing multiple water usage start times, multiple water usage durations, and multiple water usage temperatures from multiple sets of historical water usage behavior data, the predicted water temperature of the water heater is obtained.

[0137] S305. Control the heating operation of the water heater based on the predicted start time of water use, the predicted duration of water use, and the predicted water temperature.

[0138] The implementation principles and technical effects of S303 to S305 are the same as those in the aforementioned embodiments and will not be repeated here.

[0139] In this embodiment, by predicting the start time, duration, and temperature of water use based on historical water usage data, the water heater is controlled to preheat the water, eliminating the need for users to wait for hot water. Furthermore, the accuracy of the predicted start time is improved by clustering multiple water use start times during the prediction process.

[0140] Figure 4 This is a schematic flowchart illustrating a water heater control method according to another embodiment of this application. Figure 4 As shown, the method includes:

[0141] S401. Determine multiple sets of historical water usage behavior data corresponding to the water heater. Each set of historical water usage behavior data includes the start time of water usage, the duration of water usage, and the water temperature.

[0142] S402. By analyzing and processing multiple water use start times in multiple sets of historical water use behavior data, the predicted water use start time of the water heater is obtained.

[0143] The implementation principles and technical effects of S401 to S402 are the same as those in the aforementioned embodiments and will not be repeated here.

[0144] S403. By analyzing and processing multiple water usage start times and multiple water usage durations in multiple sets of historical water usage behavior data, the predicted water usage duration of the water heater is obtained.

[0145] S403 includes S4031, S4032 and S4033:

[0146] S4031. Group the multiple water usage start times to obtain multiple first groups.

[0147] In this embodiment, considering that the duration of water use varies at different times, in order to improve the accuracy of water use duration prediction, multiple water use start times in multiple sets of historical water use behavior data are grouped and processed. Then, based on the water use duration corresponding to the water use start time in different groups, the predicted water use duration corresponding to different groups is predicted, thereby obtaining the predicted water use duration at different times.

[0148] In one possible implementation, S4031 includes: dividing multiple water usage start times into multiple first groups based on multiple preset time points, wherein different first groups correspond to different preset time points. Thus, by pre-setting the time points, the rationality of grouping water usage start times is improved.

[0149] In this implementation, multiple preset time points are identified, and each preset time point is assigned to a specific preset time point. For example, 11:30 belongs to the time point 11:00, and 12:15 belongs to the time point 12:00. Water use start times belonging to the same preset time point are grouped together.

[0150] Optionally, preset time points can be multiple hourly times within a day. For example, there are 12 preset time points, such as 00:00, 1:00, 2:00, ..., 23:00. This allows for the prediction of water usage duration at multiple hourly times within a day, improving the comprehensiveness and accuracy of predicting water heater usage duration.

[0151] In another possible implementation, multiple water usage start times can be grouped using clustering, such as the hierarchical clustering described above.

[0152] S4032. Determine the average water usage duration for the first group based on the correspondence between water usage start time and water usage duration.

[0153] In this embodiment, the water usage duration corresponding to the water usage start time refers to the water usage duration within the same group of historical water usage behavior data as the water usage start time. After dividing multiple water usage start times into multiple first groups, for each first group, the average water usage duration corresponding to all water usage start times within the first group can be determined, i.e., the average water usage duration corresponding to the first group.

[0154] S4033. Based on the average water usage duration corresponding to the first group, determine the predicted water usage duration corresponding to the first group, wherein the predicted water usage duration of the water heater includes the predicted water usage duration corresponding to the first group.

[0155] In this embodiment, for each first group, the predicted water usage time corresponding to the first group can be determined as the average water usage time corresponding to the first group, that is, the predicted water usage time of the water heater at different times is obtained. Compared with determining a single predicted water usage time, this embodiment takes into account the characteristic that the user's water usage time varies at different times, thus improving the accuracy of the predicted water usage time.

[0156] In one possible implementation, S4033 includes: for each first group, filtering the water usage start time corresponding to the water usage duration in the first group based on the average water usage duration corresponding to the first group; updating the average water usage duration corresponding to the first group based on the remaining water usage durations after filtering; and then determining the predicted water usage duration corresponding to the first group as the updated average water usage duration corresponding to the first group.

[0157] In this implementation, for each first group, the difference between the water usage duration corresponding to the start time of water usage in the first group and the average water usage duration of the first group is determined. If the absolute value of the difference is greater than the difference threshold, the water usage duration corresponding to the start time of water usage is determined to be an outlier and is filtered out.

[0158] As an example, in cases where each set of water usage behavior data includes the device identifier of the water heater, the following table 2 shows a sample of data for predicting the predicted water usage duration of the water heater:

[0159] Table 2

[0160]

[0161]

[0162] Table 2 shows the predicted water usage duration for the water heater with MAC address (device identifier) ​​"2C37C56A9ACC". The start and end times of water usage in multiple sets of historical water usage data reflect the duration of water usage. Based on the hourly time, the start times of water usage in the multiple sets of historical water usage data are grouped into three groups: 11:00, 18:00, and 20:00. The predicted water usage duration for each group is determined as the average of the water usage durations corresponding to all start times in that group. Therefore, the predicted water usage duration for 11:00 is 24, for 18:00 it is 26, and for 20:00 it is 26.

[0163] In Table 2, assuming the difference threshold is 30, in the "20:00" group, the average of the four numbers 24, 29, 25, and 70 is 37. Since |70-37|>30, the water usage duration of 70 corresponding to the water usage start time of 20:21 in the "20:00" group is an outlier and can be discarded. Then, based on the remaining water usage start times corresponding to the water usage durations in this group, the average water usage duration for this group can be determined to be (24+29+25) / 3=26, and thus the predicted water usage duration for this group is determined to be 26. The unit of water usage duration in Table 2 is minutes.

[0164] Optionally, the obtained predicted water usage duration can be expressed as the predicted water usage duration of the water heater corresponding to the device identifier at multiple times (especially multiple preset time points) on the predicted date.

[0165] Optionally, considering that the predicted water usage time may not be able to find a matching time point among multiple time points corresponding to the first group, the predicted water usage temperature corresponding to the default group can be preset. For the predicted water usage time that cannot find a matching time point among multiple time points corresponding to the first group, the predicted water usage temperature corresponding to the predicted water usage time can be determined as the predicted water usage temperature corresponding to the default group.

[0166] As an example, assuming the forecast date is August 21, 2021, the forecast water usage durations for multiple first groups can be obtained based on Table 2, as shown in Table 3:

[0167] Table 3

[0168] Device MAC Group 1 Predicted water usage duration Predicted date 2C37C56A9ACC 11:00 24 2021-08-12 2C37C56A9ACC 18:00 26 2021-08-12 2C37C56A9ACC 20:00 26 2021-08-12 2C37C56A9ACC default 25 2021-08-12

[0169] Table 3, based on multiple water usage start times and durations from various sets of historical water usage data, yields the predicted water usage durations for the water heater with device MAC address "2C37C56A9ACC" at 11:00, 18:00, and 20:00. After determining the predicted water usage start time, if the start time belongs to the 11:00 group, the predicted water usage duration is determined to be 24; if it belongs to the 18:00 group, the duration is determined to be 26; if it belongs to the 20:00 group, the duration is determined to be 26; otherwise, the predicted water usage duration is determined to be 25. For example, if the predicted water usage start time is 15:12, no predicted water usage duration corresponding to 15:00 can be found in Table 3, so the predicted water usage duration for this start time is determined to be 25.

[0170] Based on the above example, it can be seen that a combination of predicted water usage start time and predicted water usage duration can be achieved based on the device MAC address and predicted date. Furthermore, it can be understood that a combination of predicted water usage start time, predicted water usage duration, and predicted water temperature can also be achieved based on the device MAC address and predicted heat, thus obtaining the predicted water usage duration and predicted water temperature of the water heater at the predicted water usage start time.

[0171] S404. By analyzing and processing multiple water usage start times, multiple water usage durations, and multiple water usage temperatures from multiple sets of historical water usage behavior data, the predicted water temperature of the water heater is obtained.

[0172] S405. Control the heating operation of the water heater based on the predicted start time of water use, the predicted duration of water use, and the predicted water temperature.

[0173] The implementation principles and technical effects of S404 to S405 are the same as those in the aforementioned embodiments and will not be repeated here.

[0174] In this embodiment, by predicting the start time, duration, and temperature of water use based on historical water usage data, the water heater is controlled to preheat water, eliminating the need for users to wait for hot water. Specifically, during the prediction process, the start time of water use is grouped, and the predicted duration for each group is determined based on the corresponding duration. This improves the accuracy of the predicted water usage duration, thereby enhancing the accuracy of water heater control based on the predicted start time, duration, and temperature.

[0175] Figure 5This is a schematic flowchart illustrating a water heater control method according to another embodiment of this application. Figure 5 As shown, the method includes:

[0176] S501. Determine multiple sets of historical water usage behavior data corresponding to the water heater. Each set of historical water usage behavior data includes the start time of water usage, the duration of water usage, and the water temperature.

[0177] S502. By analyzing and processing multiple water use start times in multiple sets of historical water use behavior data, the predicted water use start time of the water heater is obtained.

[0178] S503. By analyzing and processing multiple water usage start times and multiple water usage durations in multiple sets of historical water usage behavior data, the predicted water usage duration of the water heater is obtained.

[0179] The implementation principles and technical effects of S501 to S503 are the same as those in the aforementioned embodiments and will not be repeated here.

[0180] S504. By analyzing and processing multiple water usage start times, multiple water usage durations, and multiple water usage temperatures from multiple sets of historical water usage behavior data, the predicted water temperature of the water heater is obtained.

[0181] S504 includes S5041, S5042 and S5043:

[0182] S5041. Determine temperature scores for multiple water usage times based on multiple water usage durations.

[0183] In this embodiment, the longer the water usage time, the more reliable and accurate the water temperature corresponding to that time. In other words, water usage time can reflect the quality of water temperature to a certain extent. Therefore, temperature scores can be determined based on multiple water usage times, each corresponding to a different water usage time.

[0184] In one possible implementation, the temperature score of the water temperature is determined to be the product of the water usage time corresponding to the water temperature and a preset proportional coefficient. Thus, by making the temperature score proportional to the water usage time, the longer the water usage time, the higher the temperature score of the water temperature.

[0185] In another possible implementation, when the historical water usage data for each group includes the date of water usage, considering that water temperature is more significantly affected by the date, and that water temperatures closer to the predicted date are better able to reflect the predicted water temperature, S5041 includes: determining the date influence factor corresponding to the water temperature based on the water usage date; determining the behavior influence factor corresponding to the water temperature based on the water usage duration; and determining the temperature score of the water temperature based on the date influence factor and the behavior influence factor. Thus, by combining the water usage date and water usage duration, the accuracy of scoring the water temperature is improved.

[0186] Among them, the date influence factor reflects the influence of time on water temperature prediction, while the behavior influence factor reflects the influence of user behavior (i.e., the duration of water usage) on water temperature prediction.

[0187] Among them, the water usage date and duration corresponding to water temperature refer to the water usage date and duration in the same set of historical water usage behavior data as the water temperature.

[0188] In this implementation, the further the water usage date is from the prediction date, the smaller the impact of the water temperature corresponding to that date on the predicted water temperature. Conversely, the larger the difference between the water usage date corresponding to that temperature and the prediction date, the smaller the date-related influence factor of the water temperature. Furthermore, the longer the water usage duration corresponding to that temperature, the larger the behavioral influence factor of that temperature.

[0189] Optionally, based on the water usage date corresponding to the water usage temperature, a date influence factor corresponding to the water usage temperature is determined, including: determining the total number of days in multiple sets of historical water usage data; determining the differences between multiple water usage dates in the multiple sets of historical water usage data and the predicted date; and for each water usage date, determining the date influence factor of the water usage temperature corresponding to the water usage date based on the ratio of the difference between the water usage date and the predicted date to the total number of days. This improves the accuracy of the date influence factor.

[0190] Furthermore, the formula for calculating the date impact factor can be expressed as:

[0191] f(x) = 1 - (x / n) 2

[0192] Where n is the total number of days of multiple sets of historical water use behavior data, x is the difference between the water use date corresponding to the water temperature and the predicted date, and f(x) is the date influence factor.

[0193] Taking the determination of the predicted water temperature for the water heater on August 7, 2021, using multiple sets of historical water usage data from August 1, 2021 to August 5, 2021 as an example, the data involved in the process of determining the predicted water temperature is shown in Table 4 below:

[0194] Table 4

[0195] date x n f(x) August 1, 2021 August 5th - August 1st x = 4 5 1-(4 / 5)2＝0.36 August 2, 2021 August 5th - August 2nd x = 3 5 1-(3 / 5)2＝0.64 August 3, 2021 August 5th - August 3rd x = 2 5 1-(2 / 5)2＝0.84 August 4, 2021 August 5th - August 4th x = 1 5 1-(1 / 5)2＝0.96 August 5, 2021 August 5th - August 5th x = 0 5 1-(0 / 5)2＝1

[0196] Optionally, based on the water usage duration corresponding to the water temperature, the behavioral influence factor corresponding to the water temperature can be determined, including: using a nonlinear function and the water usage duration corresponding to the water temperature to determine the behavioral influence factor. This utilizes a nonlinear function to improve the accuracy of the behavioral influence factor.

[0197] The nonlinear function can be expressed as:

[0198]

[0199] Where m and s are different duration thresholds, t indicates the water usage duration corresponding to the water temperature, g(t) is the behavior influence factor, and a, b, and c represent formula parameters.

[0200] Finally, the temperature score of the water temperature can be expressed as:

[0201] Z = f(x) × g(t)

[0202] Where Z represents the temperature score.

[0203] S5042. Group the multiple water use start times in multiple sets of historical water use behavior data to obtain multiple second groups.

[0204] In this embodiment, considering that the ambient temperature varies at different times and the water temperature required by users varies under different ambient temperatures, in order to improve the accuracy of water temperature prediction, multiple water use start times in multiple sets of historical water use behavior data are grouped. Then, based on the water temperature corresponding to the water use start time in different groups and the temperature score of the water temperature, the predicted water temperature corresponding to different groups is predicted, thereby obtaining the predicted water temperature at different times.

[0205] In one possible implementation, S5042 includes: dividing multiple water usage start times into multiple second groups based on multiple preset time intervals, wherein different second groups correspond to different preset time intervals. Specifically, water usage start times belonging to the same preset time interval can be grouped into the same second group, resulting in multiple second groups. Thus, grouping water usage start times based on preset time intervals makes the grouping more consistent with the characteristics that ambient temperatures may differ significantly in different time intervals but change less within the same time interval.

[0206] Optionally, to make the prediction results accurate to different times within a day, the day can be divided into multiple preset time intervals, thereby predicting the water temperature corresponding to multiple time intervals within a day, improving the accuracy of temperature control of the water heater, and enabling the water heater to provide users with hot water at a more accurate temperature according to the user's water usage in different time intervals.

[0207] Furthermore, multiple preset time intervals include daytime periods (e.g., 6:00 AM to 5:00 PM), evening periods (e.g., 5:00 PM to 11:00 PM), and sleep periods (e.g., 11:00 PM to 6:00 AM).

[0208] In another possible implementation, the clustering method and preset time point method described in the above embodiments can be used to divide multiple water use start times into multiple second groups, which will not be elaborated further.

[0209] S5043. Determine the predicted water temperature corresponding to the second group based on the temperature score of the water temperature corresponding to the water use start time in the second group.

[0210] In this embodiment, for each second group, the water temperature corresponding to the start time of all water use within the second group is determined. Based on the temperature scores of these multiple water temperatures, the predicted water temperature corresponding to the second group is determined from among these multiple water temperatures. For example, the water temperature with the highest temperature score is selected and determined as the predicted water temperature corresponding to the second group. In this way, the predicted water temperature corresponding to each second group is obtained.

[0211] In one possible implementation, S5043 includes: for each second group, determining the sum of temperature scores for the same water temperature among the water temperatures corresponding to the water use start times included in the second group; and determining the predicted water temperature corresponding to the second group as the water temperature with the largest sum of temperature scores among the water temperatures corresponding to the water use start times included in the second group.

[0212] In this implementation, considering that the water temperature corresponding to the water usage start time within the second group may have duplicate temperature values, the temperature scores of these duplicate temperature values ​​are summed to obtain the total temperature score for the same water temperature. The higher the total temperature score, the higher the probability that the user is likely to use that water temperature within the time corresponding to the second group. Therefore, the predicted water temperature corresponding to the second group can be determined as the water temperature with the largest total temperature score among the water temperatures corresponding to the water usage start time included in the second group.

[0213] Taking the historical water use behavior data shown in Table 1 as an example, the water use start time in the historical water use behavior data shown in Table 1 is grouped into time periods according to daytime (6:00-17:00), nighttime (17:00-23:00), and sleep time (23:00-6:00). The results are shown in Table 5 below:

[0214] Table 5

[0215]

[0216]

[0217] Taking the data from the evening period as an example:

[0218] Table 6

[0219] Water usage date Time period grouping Water usage start time Water usage end time water temperature 20210802 night 20:11 20:33 45 20210802 night 19:55 20:11 42 20210803 night 18:02 18:26 45 20210803 night 18:55 19:34 42 20210804 night 19:26 20:03 42 20210805 night 20:50 21:20 43

[0220] The water usage duration corresponding to multiple water temperatures during the nighttime period is obtained as follows:

[0221] Table 7

[0222] Water usage date water temperature Water usage duration 20210802 45 22 20210802 42 16 20210803 45 24 20210803 42 39 20210804 42 37 20210805 43 30

[0223] Calculate the date-related and behavioral-related factors of multiple water temperature readings during the evening period:

[0224] Table 8

[0225] Water usage date water temperature Water usage duration Date Influence Factor Behavioral Influencing Factors 20210802 45 22 0.64 0.396 20210802 42 16 0.64 0.001 20210803 45 24 0.84 0.513 20210803 42 39 0.84 0.876 20210804 42 37 0.96 0.847 20210805 43 30 1 0.714

[0226] Therefore, the temperature score is as follows:

[0227] Table 9

[0228] Water usage date water temperature Temperature rating 20210802 45 0.253 20210802 42 0.00064 20210803 45 0.431 20210803 42 0.736 20210804 42 0.813 20210805 43 0.714

[0229] As shown in Table 9, there were repeated water temperatures during the evening period: two at 45 degrees Celsius and three at 42 degrees Celsius. The sum of the temperature scores for the repeated water temperatures was calculated, and the results are shown in Table 10.

[0230] Table 10

[0231] water temperature Temperature rating sum 42 1.54964 43 0.714 45 0.684

[0232] Thus, the predicted water temperature for the evening period is 42 degrees Celsius.

[0233] Finally, the predicted water temperatures for daytime, nighttime, and sleep periods were obtained.

[0234] After obtaining the predicted water temperature, anomalies may occur. Therefore, in some embodiments, at least one of the following anomaly handling operations can be employed:

[0235] Anomaly Handling Procedure 1: If a predicted water temperature is greater than a first temperature threshold, then that predicted water temperature is designated as the first temperature threshold; if a predicted water temperature is less than a second temperature threshold, then that predicted water temperature is designated as the second temperature threshold. This ensures that the predicted water temperature remains within a reasonable range, improving the user experience. The first temperature threshold is greater than the second temperature threshold.

[0236] Anomaly Handling Operation Two: For each second group, if the temperature score (or the sum of temperature scores) of multiple water temperatures in the second group is the largest and the temperature scores (or the sum of temperature scores) are the same, then the water temperature whose water usage date is closest to the prediction date is determined as the final predicted water temperature.

[0237] Furthermore, if the water usage dates for these multiple water temperatures are also the same, then the water temperature with the latest water usage end time is determined as the final predicted water temperature.

[0238] Anomaly Handling Operation 3: If the predicted water temperature for a second group is empty, or if there is no corresponding predicted water temperature for a second group, the predicted water temperature for that second group can be determined from the predicted water temperatures for other second groups. For example, randomly select the predicted water temperature for another group as the predicted water temperature for that second group; or select the predicted water temperature with the higher temperature score from the predicted water temperatures for other groups as the predicted water temperature for that second group; or determine the predicted water temperature for the other group with the shortest time interval to that second group as the predicted water temperature for that second group.

[0239] Anomaly Handling Operation 4: If none of the second groups have a corresponding predicted water temperature, then determine that the predicted water temperature corresponding to the second group is the preset temperature.

[0240] S505. Control the heating operation of the water heater based on the predicted start time of water use, the predicted duration of water use, and the predicted water temperature.

[0241] The implementation principle and technical effects of S505 can be referred to in the aforementioned embodiments, and will not be repeated here.

[0242] In this embodiment, by predicting the start time, duration, and temperature of water use based on historical water usage data, the water heater is controlled to preheat the water, eliminating the need for users to wait for hot water. Specifically, during the prediction process, the start time of water use is grouped, and the water temperature is scored. Based on the grouping and scoring results, the predicted water temperature for each group is determined, thus improving the accuracy of the water heater's predicted water temperature.

[0243] In some embodiments, during the process of controlling the heating operation of the water heater based on the predicted water usage start time, predicted water usage duration, and predicted water usage temperature, it is necessary to combine the predicted water usage start time, predicted water usage duration, and predicted water usage temperature based on the water heater's device identifier and the predicted date to obtain the predicted water usage behavior data of the water heater on the predicted date. Then, based on the predicted water usage behavior data of the water heater on the predicted date, the water heater is heated and controlled on the predicted date.

[0244] Therefore, in determining the predicted water usage start time, predicted water usage duration, and predicted water usage temperature, it is necessary to simultaneously determine the equipment identifier and prediction date corresponding to the predicted water usage start time, the equipment identifier and prediction date corresponding to the predicted water usage duration, and the equipment identifier and prediction date corresponding to the predicted water usage temperature. Considering the possibility that some equipment identifiers and some prediction dates may have accurate prediction results, at least one of the following processing operations can be adopted in this case:

[0245] Processing Operation 1: If the predicted water usage duration for the water heater on the predicted date is not found based on the water heater's device identifier (this may be because the water heater's device identifier and / or the predicted date are not present in the prediction results), then the predicted water usage duration for the water heater on the predicted date is determined to be the preset duration.

[0246] Processing Operation 2: If the water heater's device identifier and prediction date appear in the prediction results but the target time point does not appear, determine the predicted water usage duration of the water heater at the target time point of the prediction date as the predicted water usage duration corresponding to the default group.

[0247] Processing Operation 3: If the predicted water temperature for the water heater on the predicted date cannot be found based on the water heater's device identifier (this may be because the water heater's device identifier and / or the predicted date are not present in the prediction results), then the predicted water temperature for the water heater on the predicted date is determined to be the preset temperature.

[0248] Processing Operation 4: If the water heater's device identifier and prediction date appear in the prediction results but the target time point does not appear, determine the predicted temperature of the water heater at the target time point of the prediction date as the predicted water temperature corresponding to the default group.

[0249] Optionally, the predicted water usage behavior data includes the water heater's device identifier, predicted water usage start time, predicted water usage duration, predicted water usage temperature, and predicted date.

[0250] In some embodiments, during the process of controlling the water heater's heating operation based on the predicted water usage start time, predicted water usage duration, and predicted water temperature, after determining the predicted water usage behavior data of the water heater on the predicted date based on the predicted water usage start time, predicted water usage duration, and predicted water temperature, it can be determined whether the predicted date meets the push time requirement. If the predicted date meets the push time requirement, a control message containing the predicted water usage behavior data is sent to the water heater. Thus, controlling the water heater's heating operation based on certain push rules improves the rationality and accuracy of the control operation.

[0251] One possible approach to determining whether a predicted date meets the push notification time requirement is to determine whether the predicted date meets the requirement based on the actual number of days the water heater uses water within a preset time period and / or the water usage interval of the water heater. Thus, based on user water usage patterns reflected by the actual number of days of water use within the time period, or user water usage patterns reflected by the water heater's water usage interval, it is determined whether to push a message on the predicted date.

[0252] In this implementation, the actual number of days the water heater uses water within a preset time period can be obtained. If the actual number of days used water is greater than or equal to a threshold number of days, it is determined that the user uses water every day, and the predicted date meets the push notification time requirement. If the actual number of days used water is less than the threshold number of days, it is determined that the user does not use water every day. For example, if the preset time period is 30 days and the threshold number of days is 25 days, if the actual number of days the water heater uses water within 30 days is greater than 25, the predicted date meets the push notification time requirement.

[0253] In this implementation, if the actual number of days of water use is less than the number of days threshold, the water usage interval of the water heater can be determined. If the interval between the predicted date and the last water usage date of the water heater is greater than or equal to the water usage interval of the water heater, the predicted date is determined to meet the push time requirement; otherwise, the predicted date is determined to not meet the push time requirement.

[0254] Optionally, when determining the water usage interval of the water heater, multiple actual water usage intervals can be obtained, and the final water usage interval can be derived based on these multiple actual water usage intervals. This improves the accuracy of the water usage interval. A weighted moving average method can be used to weight the multiple actual water usage intervals to obtain the final water usage interval of the water heater, as shown in the following formula:

[0255] d=round(p1*q1+p2*q2+……+p n *q n )

[0256] Where d represents the water usage interval of the water heater, and p1, p2, ..., p n The formula parameters are q1, q2, ..., q.n This represents the actual water usage interval of the water heater in the most recent n instances.

[0257] Another possible approach to determining whether a predicted date meets the push notification time requirement includes: dividing the dates within a preset time period into multiple categories; and determining whether the predicted date meets the push notification time requirement based on the actual number of days in each category, the actual number of days of water usage in each category, and the category to which the predicted date belongs. Thus, by classifying the dates within the preset time period, the accuracy of judging user water usage patterns is improved, thereby increasing the accuracy of determining whether the predicted date meets the push notification time requirement.

[0258] In this implementation, if the difference between the actual number of days in the preset time period of the category to which the predicted date belongs and the actual number of days of water use in the predicted actual period of the category is less than a preset threshold, then the predicted date can be determined to meet the push time requirements; otherwise, the predicted date is determined not to meet the push time requirements.

[0259] For example, taking a preset time period of one month, and predicting that the date categories within the time period are Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, and Sunday, the actual number of days and actual water usage days for each category within the preset time period are shown in Table 11:

[0260] Table 11

[0261] Date Category Actual number of days Actual number of days of water use Monday <![CDATA[X 11 ]]> <![CDATA[X 21 ]]> Tuesday <![CDATA[X 12 ]]> <![CDATA[X 22 ]]> Wednesday <![CDATA[X 13 ]]> <![CDATA[X 23 ]]> Thursday <![CDATA[X 14 ]]> <![CDATA[X 24 ]]> Friday <![CDATA[X 15 ]]> <![CDATA[X 25 ]]> Saturday <![CDATA[X 16 ]]> <![CDATA[X 26 ]]> Sunday <![CDATA[X 17 ]]> <![CDATA[X 27 ]]>

[0262] Assuming a preset threshold of 2, for each date category, if the date category satisfies X... 1i -X 2i If the value is less than 2, then the predicted date belonging to week i meets the push time requirement. Here, the value of i ranges from 1 to 7.

[0263] Figure 6 A schematic diagram of a water heater control device provided in one embodiment of this application. Figure 6 As shown, the water heater control device includes:

[0264] The determination module 601 is used to determine multiple sets of historical water use behavior data corresponding to the water heater. Each set of historical water use behavior data includes water use start time, water use duration and water use temperature.

[0265] The first prediction module 602 is used to analyze and process multiple water use start times in multiple sets of historical water use behavior data to obtain the predicted water use start time of the water heater.

[0266] The second prediction module 603 is used to analyze and process multiple water use start times and multiple water use durations in multiple sets of historical water use behavior data to obtain the predicted water use duration of the water heater.

[0267] The third prediction module 604 is used to analyze and process multiple water use start times, multiple water use durations and multiple water use temperatures in multiple sets of historical water use behavior data to obtain the predicted water use temperature of the water heater.

[0268] The control module 605 is used to control the heating operation of the water heater based on the predicted water usage start time, predicted water usage duration, and predicted water usage temperature.

[0269] In one possible implementation, the first prediction module 602 is specifically used to: cluster multiple water use start times to obtain clustering results; and determine the predicted water use start time based on the clustering results.

[0270] In one possible implementation, the first prediction module 602 is specifically used to: merge multiple clusters in the clustering result according to the center value of each cluster in the clustering result, and / or discard one or more clusters in the clustering result according to the number of water use start times contained in each cluster in the clustering result; and determine the predicted water use start time according to the processed clustering result.

[0271] In one possible implementation, the second prediction module 603 is specifically used to: group multiple water use start times to obtain multiple first groups; determine the average water use duration corresponding to the first group based on the correspondence between water use start time and water use duration; and determine the predicted water use duration corresponding to the first group based on the average water use duration corresponding to the first group.

[0272] In one possible implementation, the second prediction module 603 is specifically used to: divide multiple water use start times into multiple first groups according to multiple preset time points, wherein different first groups correspond to different preset time points.

[0273] In one possible implementation, the third prediction module 604 is specifically used to: determine temperature scores for multiple water usage temperatures based on multiple water usage durations; group multiple water usage start times to obtain multiple second groups; and determine the predicted water usage temperature corresponding to the second group based on the temperature scores of the water usage start times in the second groups.

[0274] In one possible implementation, the historical water use behavior data also includes the water use date. The third prediction module 604 is specifically used to: determine the date influence factor corresponding to the water use temperature based on the water use date corresponding to the water use temperature; determine the behavior influence factor corresponding to the water use temperature based on the water use duration corresponding to the water use temperature; and determine the temperature score of the water use temperature based on the date influence factor and the behavior influence factor corresponding to the water use temperature.

[0275] In one possible implementation, the third prediction module 604 is specifically used to: divide multiple water use start times into multiple second groups according to multiple preset time intervals, wherein different second groups correspond to different preset time intervals.

[0276] In one possible implementation, the third prediction module 604 is specifically used to: for each second group, determine the sum of temperature scores for the same water temperature among the water temperatures corresponding to the water use start times included in the second group; and determine the predicted water temperature corresponding to the second group as the water temperature with the largest sum of temperature scores among the water temperatures corresponding to the water use start times included in the second group.

[0277] In one possible implementation, the control module 605 is specifically used to: determine the predicted water usage behavior data of the water heater on the predicted date based on the predicted water usage start time, the predicted water usage duration, and the predicted water usage temperature; determine whether the predicted date meets the push time requirement; and if the predicted date meets the push time requirement, send a control message to the water heater, the control message containing the predicted water usage behavior data.

[0278] In one possible implementation, the control module 605 is specifically used to: determine whether the predicted date meets the push time requirements based on the actual number of days the water heater uses water within a preset time period and / or the water usage interval of the water heater.

[0279] In one possible implementation, the control module 605 is specifically used to: divide the dates within a preset time period into multiple categories; and determine whether the predicted date meets the push time requirements based on the actual number of days in each of the multiple categories, the actual number of water usage days in each of the multiple categories, and the category to which the predicted date belongs in the multiple categories.

[0280] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown below. Figure 7 As shown, the electronic device includes a processor 701 and a memory 702; the memory 702 stores a computer program; the processor 701 executes the computer program stored in the memory to implement the steps of the water heater control method in the above-described method embodiments.

[0281] In the aforementioned water heater, the memory 702 and the processor 701 are electrically connected directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines, such as a bus connection. The memory 702 stores computer-executable instructions for implementing data access control methods, including at least one software function module that can be stored in the memory 702 in the form of software or firmware. The processor 701 executes various functional applications and data processing by running the software program and module stored in the memory 702.

[0282] The memory 702 may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 702 stores programs, which are executed by the processor 701 upon receiving execution instructions. Furthermore, the software programs and modules within the memory 702 may include an operating system, which may include various software components and / or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.) and can communicate with various hardware or software components to provide an operating environment for other software components.

[0283] The processor 701 can be an integrated circuit chip with signal processing capabilities. The processor 701 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor.

[0284] An embodiment of this application also provides a chip, including: a processor and a memory; the memory stores a computer program, and when the processor executes the computer program stored in the memory, it implements the water heater control method provided in the above-described method embodiments.

[0285] An embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the water heater control methods provided in the above-described method embodiments.

[0286] An embodiment of this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the water heater control method provided in the above-described method embodiments.

[0287] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0288] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. Without departing from the principles of this application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of this application.

Claims

1. A water heater control method, characterized by, The method comprises: determining a plurality of groups of historical water use behavior data corresponding to the water heater, each group of historical water use behavior data comprising a water use start time, a water use duration, and a water use temperature; analyzing and processing a plurality of water use start times in the plurality of groups of historical water use behavior data to obtain a predicted water use start time of the water heater; grouping the plurality of water use start times in the plurality of groups of historical water use behavior data according to a plurality of preset time points to obtain a plurality of first groups; determining a water use duration mean value corresponding to the first groups according to a correspondence between the water use start time and the water use duration; determining a predicted water use duration corresponding to the first groups according to the water use duration mean value corresponding to the first groups; for each first group, the predicted water use duration corresponding to the first group is the water use duration mean value corresponding to the first group; determining temperature scores of the plurality of water use temperatures according to a date influence factor corresponding to the water use temperature and a behavior influence factor corresponding to the water use temperature; grouping the plurality of water use start times in the plurality of groups of historical water use behavior data according to a plurality of preset time intervals to obtain a plurality of second groups; determining a predicted water use temperature corresponding to the second groups according to temperature scores of water use temperatures corresponding to water use start times in the second groups; for each second group, a temperature score sum of a same water use temperature is determined among water use temperatures corresponding to water use start times included in the second group; determining the predicted water use temperature corresponding to the second groups as a water use temperature with a maximum temperature score sum among water use temperatures corresponding to water use start times included in the second group; controlling a heating operation of the water heater according to the predicted water use start time, the predicted water use duration, and the predicted water use temperature.

2. The water heater control method of claim 1, wherein, The method of analyzing and processing a plurality of water use start times in the plurality of groups of historical water use behavior data to obtain a predicted water use start time of the water heater comprises: clustering the plurality of water use start times to obtain a clustering result; determining the predicted water use start time according to the clustering result.

3. The water heater control method of claim 2, wherein, The method of determining the predicted water use start time according to the clustering result comprises: performing merging processing on a plurality of clusters in the clustering result according to center values of each cluster in the clustering result, and / or performing discarding processing on one or more clusters in the clustering result according to a number of water use start times included in each cluster in the clustering result; determining the predicted water use start time according to the processed clustering result.

4. The water heater control method of claim 1, wherein, Different first groups correspond to different preset time points.

5. The water heater control method of claim 1, wherein, The historical water use behavior data further comprises a water use date, and the method further comprises: determining a date influence factor corresponding to the water use temperature according to a water use date corresponding to the water use temperature; determining a behavior influence factor corresponding to the water use temperature according to a water use duration corresponding to the water use temperature.

6. The water heater control method of claim 1, wherein, Different second groups correspond to different preset time intervals.

7. The water heater control method of any one of claims 1 to 6, wherein, The method of controlling a heating operation of the water heater according to the predicted water use start time, the predicted water use duration, and the predicted water use temperature comprises: determining predicted water usage behavior data of the water heater on a predicted date according to the predicted water usage start time, the predicted water usage duration and the predicted water usage temperature; determining whether the predicted date meets a push time requirement; if the predicted date meets the push time requirement, sending a control message to the water heater, the control message containing the predicted water usage behavior data.

8. The water heater control method of claim 7, wherein, The determining whether the predicted date meets the push time requirement comprises: determining whether the predicted date meets the push time requirement according to actual water usage days of the water heater in a preset time period and / or water usage intervals of the water heater.

9. The water heater control method of claim 7, wherein, The determining whether the predicted date meets the push time requirement comprises: dividing dates in a preset time period into multiple categories; determining whether the predicted date meets the push time requirement according to actual days in each category of the multiple categories, actual water usage days in each category of the multiple categories and a category to which the predicted date belongs.

10. A water heater control apparatus, characterized by An apparatus for performing the water heater control method according to any one of claims 1-9, the apparatus comprising: a determining module configured to determine a plurality of sets of historical water usage behavior data corresponding to the water heater, each set of historical water usage behavior data comprising a water usage start time, a water usage duration and a water usage temperature; a first predicting module configured to obtain a predicted water usage start time of the water heater by analyzing and processing a plurality of water usage start times in the plurality of sets of historical water usage behavior data; a second predicting module configured to obtain a predicted water usage duration of the water heater by analyzing and processing the plurality of water usage start times and a plurality of water usage durations in the plurality of sets of historical water usage behavior data; a third predicting module configured to obtain a predicted water usage temperature of the water heater by analyzing and processing the plurality of water usage start times, the plurality of water usage durations and a plurality of water usage temperatures in the plurality of sets of historical water usage behavior data; a control module configured to control a heating operation of the water heater according to the predicted water usage start time, the predicted water usage duration and the predicted water usage temperature.

11. An electronic device, comprising: comprising: a processor and a memory; the memory stores a computer program; the processor executes the computer program stored in the memory to implement the water heater control method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the water heater control method according to any one of claims 1-9.

13. A computer program product, characterised in that, The computer program product contains a computer program, and the computer program is executed by the processor to implement the water heater control method according to any one of claims 1-9.

Images