A pet water consumption calibration method, chip and pet feeding machine

Abstract

This application provides a method, chip, and pet feeder for calibrating pet drinking water volume. During one usage cycle of the pet feeder, the influence of sudden data changes is first eliminated, i.e., the influence of data with large fluctuations is eliminated. The calibration coefficient is obtained by calculating the natural loss rate of drinking water using data recorded under normal conditions. This calibration coefficient can calibrate the pet drinking water volume calculated using existing technology, thereby eliminating the error caused by the natural loss of drinking water, improving the detection accuracy of the pet feeder, and the effect is more obvious the longer the usage cycle, allowing users to accurately grasp the actual amount of water their pets drink.

Description

Technical Field

[0001] This application relates to the field of pet feeding machine technology, specifically to a pet water consumption calibration method, a chip, and a pet feeding machine. Background Technology

[0002] As living standards continue to improve, more and more families are choosing to keep pets, and many smart pet feeders have appeared on the market to help owners feed their pets. A major function of these smart pet feeders is to provide drinking water for pets and also to track their water intake. However, most pet feeders currently on the market suffer from poor detection accuracy and cannot eliminate errors caused by natural water loss, leading to inaccuracies in the tracking of pet water intake. Summary of the Invention

[0003] This application provides a method for calibrating pet water consumption, a chip, and a pet feeder, the specific technical solutions of which are as follows:

[0004] A method for calibrating pet water consumption includes: step S1, setting a timestamp at preset time intervals during one usage cycle of a pet feeder, and recording the weight data corresponding to each timestamp; step S2, identifying and deleting abrupt changes in data during the usage cycle, and then calculating a calibration coefficient based on the difference between adjacent data; and step S3, calculating the actual pet water consumption based on the calibration coefficient and the estimated pet water consumption during the usage cycle.

[0005] Further, in step S2, the method for finding mutation data includes: step S21, marking the weight data corresponding to the timestamps involved in the drinking time period as first mutation data within the usage period; step S22, dividing the usage period into several first time blocks using the first mutation data as the boundary, wherein the first time blocks do not include the first mutation data; step S23, for each first time block, finding outliers in each first time block using the mean absolute deviation method, and marking all outliers as second mutation data; wherein, mutation data includes first mutation data and second mutation data.

[0006] Further, in step S21, the method for obtaining the drinking time period includes: step S211, when the pet feeder detects a decrease in weight, it determines whether the decrease is within a preset weight range. If so, it determines that the pet is drinking water and marks the timestamp at this time as the start drinking timestamp; step S212, the pet feeder continues to detect, and when the weight remains unchanged within a preset time range, it determines that the pet has stopped drinking water and marks the timestamp at this time as the end drinking timestamp; wherein, the drinking time period is the time period from the start drinking timestamp to the end drinking timestamp.

[0007] Further, in step S2, the method for calculating the calibration coefficient based on the difference between adjacent data includes: step S24, dividing the usage period into several second time blocks with the mutation data as the boundary, wherein the second time blocks do not include mutation data; step S25, calculating the absolute value of the difference between adjacent data and taking the mean for each second time block to obtain the calibration coefficient corresponding to each second time block.

[0008] Further, in step S3, the method for calculating the actual pet water consumption based on the calibration coefficient and the estimated pet water consumption during the usage period includes: step S31, multiplying the number of timestamps involved in each second time block by the calibration coefficient corresponding to each second time block to obtain the calibration value corresponding to each second time block; step S32, adding the calibration values ​​corresponding to each second time block to obtain the total calibration value; step S33, subtracting the total calibration value from the estimated pet water consumption during the usage period to obtain the actual pet water consumption.

[0009] Further, in step S33, the method for obtaining the estimated pet water consumption during the usage period includes: step S331, recording the weight data corresponding to the start timestamp of the usage period and marking it as the start weight; step S332, recording the weight data corresponding to the end timestamp of the usage period and marking it as the end weight; step S333, subtracting the end weight from the start weight to obtain the estimated pet water consumption during the usage period.

[0010] A chip, the chip including the pet drinking water calibration method.

[0011] A pet feeder, the pet feeder including the chip.

[0012] The pet water consumption calibration method described in this application first eliminates the influence of sudden data changes, i.e., the influence of data with large fluctuations, during one usage cycle of the pet feeder. Then, it calculates the natural water consumption rate of drinking water using data recorded under normal conditions to obtain a calibration coefficient. This calibration coefficient can calibrate the pet water consumption calculated using existing technology, thereby eliminating errors caused by natural water consumption, improving the detection accuracy of the pet feeder, and the effect becomes more obvious the longer the usage cycle, allowing users to accurately grasp the actual water consumption of their pets. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating a method for calibrating pet water consumption according to one embodiment of this application. Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0015] It should be understood that, when used in this application, the term "comprising" indicates the presence of the described feature, integral, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof. It should also be understood that, as used in this application, the term "and / or" refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0016] As used in this application, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0017] Furthermore, in the description of this application, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0018] As living standards continue to improve, more and more families are choosing to keep pets, and many smart pet feeders have appeared on the market to help owners feed their pets. A major function of these smart pet feeders is to provide drinking water for pets and also to track their water intake. However, most pet feeders currently on the market suffer from poor detection accuracy and cannot eliminate errors caused by natural water loss, leading to inaccuracies in the tracking of pet water intake.

[0019] To address the aforementioned technical problems, this application provides a method for calibrating pet water consumption. During one usage cycle of a pet feeder, the influence of sudden data changes is first eliminated, i.e., the influence of data with large fluctuations is excluded. A calibration coefficient is obtained by calculating the natural water consumption rate using data recorded under normal conditions. This calibration coefficient can calibrate the pet water consumption calculated using existing technology, thereby eliminating errors caused by natural water consumption loss, improving the detection accuracy of the pet feeder, and showing a more significant effect over a longer usage cycle, allowing users to accurately grasp the pet's actual water consumption.

[0020] like Figure 1 As shown, the pet water consumption calibration method includes:

[0021] Step S1: During one usage cycle of the pet feeder, a timestamp is set at preset time intervals, and the weight data corresponding to each timestamp is recorded;

[0022] Step S2: During the usage cycle, identify and delete mutated data, and then calculate the calibration coefficient based on the difference between adjacent data.

[0023] Step S3: Calculate the actual pet water consumption based on the calibration coefficient and the estimated pet water consumption over the usage period.

[0024] In a basic embodiment, a usage cycle of a pet feeder refers to the period from when the feeder is filled with drinking water (or enough for the pet to drink) until the pet has finished drinking (or mostly finished drinking) the water. During this usage cycle, no water needs to be added or changed. Therefore, a simple calculation of the pet's water consumption is the weight of the water when it was first added minus the weight when it was finished. While this calculation method is simple and effective, it doesn't account for errors caused by the natural loss of drinking water, such as evaporation, splashing, minor leaks, or absorption by certain items. This leads to a slight deviation in the calculated pet's water consumption, and the longer the usage cycle, the greater the deviation. It should be noted that the start and end times of the usage cycle can be detected by the pet feeder through weight changes—for example, detecting a weight exceeding a certain value indicates the water is full, and detecting a weight below a certain value indicates the water is finished—or by detecting the installation and removal of the water container, or by a user-defined method.

[0025] In one particular embodiment, the pet feeder's usage cycle includes adding or changing water. In this embodiment, the pet's water intake needs to take into account the weight of the additional drinking water. For example, if water is added midway, the pet feeder calculates the weight of the additional water by subtracting the weight before adding water from the weight after adding water, and adds this to the total weight. How the pet feeder detects water addition or replacement is not the focus of this application and will not be elaborated here. It should be noted that, for ease of description, this application describes the solution to be protected using the above basic embodiment as the object.

[0026] In step S1, the weight data refers to the weight of the drinking water. In actual testing, if the weight detected by the pet feeder is the total weight of the drinking water and the container, it is automatically converted to the weight of the drinking water based on the known weight of the container.

[0027] In one implementation, step S2, the method for identifying mutation data, includes: step S21, marking the weight data corresponding to the timestamps of the drinking time periods within the usage period as first mutation data; step S22, dividing the usage period into several first time blocks using the first mutation data as boundaries, where each first time block does not include the first mutation data; and step S23, for each first time block, identifying outliers using the mean absolute deviation method, and marking all outliers as second mutation data. The mutation data includes both the first and second mutation data. The mutation data described in this embodiment is not natural loss and needs to be excluded to avoid interfering with the calculation of actual pet water consumption.

[0028] In step S21, since the pet's drinking water has a duration, multiple timestamps are involved, and the corresponding weight data need to be marked as the first mutation data. In step S22, using the first mutation data as the boundary means that starting from the beginning timestamp of the usage period, the judgment is performed sequentially. If the time period containing the first mutation data is encountered, the timestamps of non-first mutation data before that time period are divided into the first first time block. Then, the judgment continues, and all timestamps between that time period and the next time period containing the first mutation data (or the last timestamp of the usage period if there is no next one) are divided into the second first time block, and so on until the end of the usage period. In step S23, the mean absolute deviation method is a parameter-free method that does not rely on the assumption of a distribution (such as a normal distribution). It can be used to calculate the difference between each data point and the sample mean, and then calculate the average of these differences, which is called the mean absolute deviation (MAD). Then, the deviation between each data point and the sample mean is calculated. If the deviation of a data point is greater than 2.5 times the MAD, it can be considered an outlier. Outliers in the first time block are caused by uncontrollable factors, such as a pet putting its paw on a pet feeder, causing a data mutation.

[0029] In one implementation, step S21, the method for obtaining the drinking time period, includes: Step S211, when the pet feeder detects a decrease in weight, it determines whether the decrease is within a preset weight range. If so, it determines that the pet is drinking water, and marks the timestamp at this time as the start drinking timestamp; Step S212, the pet feeder continues to detect, and when the weight remains unchanged within the preset time range, it determines that the pet has stopped drinking water, and marks the timestamp at this time as the end drinking timestamp; wherein, the drinking time period is the time period from the start drinking timestamp to the end drinking timestamp. In step S211, since the weight reduction caused by the pet taking a sip of water is predictable, when the weight of the drinking water is detected to decrease by a specific value, it is considered that the pet is drinking water.

[0030] In one implementation, step S2, the method for calculating the calibration coefficient based on the difference between adjacent data, includes: step S24, dividing the usage period into several second time blocks using abrupt change data as a boundary, where the second time blocks do not include abrupt change data; step S25, calculating the absolute value of the difference between adjacent data and averaging it for each second time block to obtain the calibration coefficient corresponding to each second time block. In step S24, the method for dividing the second time blocks is the same as the method for dividing the first time blocks, and will not be described again. In step S25, since weather conditions, the placement of the pet feeder, or the pet's drinking method may differ in different time blocks, the calibration coefficients for different time blocks may also differ. Calculating the calibration coefficient corresponding to each second time block separately allows for accurate calculation of the calibration value for each time block, improving the accuracy of the final calculated actual pet water consumption.

[0031] In one implementation, step S3, the method for calculating the actual pet water consumption based on the calibration coefficient and the estimated pet water consumption during the usage period, includes: step S31, multiplying the number of timestamps involved in each second time block by the calibration coefficient corresponding to each second time block to obtain the calibration value corresponding to each second time block; step S32, summing the calibration values ​​corresponding to each second time block to obtain the total calibration value; and step S33, subtracting the total calibration value from the estimated pet water consumption during the usage period to obtain the actual pet water consumption. The method described in this application eliminates errors caused by natural water loss, allowing users to accurately grasp the pet's actual water consumption, and the effect becomes more pronounced the longer the usage period.

[0032] In one implementation, step S33, the method for obtaining the estimated pet water consumption during the usage period, includes: step S331, recording the weight data corresponding to the start timestamp of the usage period and marking it as the start weight; step S332, recording the weight data corresponding to the end timestamp of the usage period and marking it as the end weight; step S333, subtracting the end weight from the start weight to obtain the estimated pet water consumption during the usage period. The method described in this embodiment can quickly and easily calculate the pet's water consumption.

[0033] This application provides a chip that includes the pet water consumption calibration method. During one usage cycle of a pet feeder, the chip first eliminates the influence of sudden data fluctuations, i.e., it eliminates the influence of data with large fluctuations. It then calculates a calibration coefficient based on the natural water consumption rate obtained from data recorded under normal conditions. This calibration coefficient can calibrate the pet water consumption calculated using existing technology, thereby eliminating errors caused by natural water consumption loss, improving the detection accuracy of the pet feeder, and the effect becomes more pronounced with longer usage cycles, allowing users to accurately grasp the pet's actual water consumption.

[0034] This application provides a pet feeder, which includes the chip. The pet feeder can eliminate errors caused by natural water loss, improve the detection accuracy of the pet feeder, and the effect becomes more pronounced with longer use, allowing users to accurately monitor their pet's actual water consumption.

[0035] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. References to memory, storage, databases, or other media used in the embodiments provided in this application can all include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable memory (PROM), electrically programmable memory (DPROM), electrically erasable programmable memory (DDPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0036] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0037] The above embodiments are merely illustrative of several implementations of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these modifications and improvements all fall within the protection scope of this application.

Claims

1. A method of calibrating the amount of water consumed by a pet, characterized by, The pet water consumption calibration method comprises: Step S1, in a use cycle of the pet feeding machine, a timestamp is set every preset time interval, and weight data corresponding to each timestamp is recorded; Step S2, in the use cycle, find out the mutation data and delete it, and then calculate the calibration coefficient based on the difference value of adjacent data; Step S3, based on the calibration coefficient and the estimated pet water consumption in the use cycle, the actual pet water consumption is calculated; In step S2, the method for finding out the mutation data comprises: Step S21, in the use cycle, the weight data corresponding to the timestamps involved in the water drinking time period is marked as first mutation data; Step S22, divide the use cycle into a plurality of first time blocks with the first mutation data as the boundary, and the first mutation data is not included in the first time blocks; Step S23, for each first time block, find out the abnormal value in each first time block by the average absolute deviation method, and mark all abnormal values as second mutation data; Wherein, the mutation data includes the first mutation data and the second mutation data; In step S21, the method for obtaining the water drinking time period comprises: Step S211, when the pet feeding machine detects weight reduction, determine whether the reduction value is within the preset weight range, if yes, determine that the pet is drinking water, and mark the timestamp at this time as the start water drinking timestamp; Step S212, the pet feeding machine continues to detect, when the weight remains unchanged within the preset time range, it is determined that the pet stops drinking water, and the timestamp at this time is marked as the end water drinking timestamp; Wherein, the water drinking time period is the time period between the start water drinking timestamp and the end water drinking timestamp; In step S2, the method for calculating the calibration coefficient based on the difference value of adjacent data comprises: Step S24, divide the use cycle into a plurality of second time blocks with the mutation data as the boundary, and the mutation data is not included in the second time blocks; Step S25, for each second time block, calculate the absolute value of the difference value of adjacent data and obtain the calibration coefficient corresponding to each second time block; In step S3, based on the calibration coefficient and the estimated pet water consumption in the use cycle, the actual pet water consumption is calculated, which comprises: Step S31, multiply the number of timestamps involved in each second time block by the calibration coefficient corresponding to each second time block to obtain the calibration value corresponding to each second time block; Step S32, add the calibration values corresponding to each second time block to obtain the total calibration value; Step S33, subtract the total calibration value from the estimated pet water consumption in the use cycle to obtain the actual pet water consumption; In step S33, the method for obtaining the estimated pet water consumption in the use cycle comprises: Step S331, record the weight data corresponding to the start timestamp of the use cycle and mark it as the start weight; Step S332, record the weight data corresponding to the end timestamp of the use cycle and mark it as the end weight; Step S333, subtract the end weight from the start weight to obtain the estimated pet water consumption in the use cycle.

Images