A pet feeding machine control method, control system and pet feeding machine

Abstract

The application provides a pet feeding machine control method, a control system and a pet feeding machine. The pet feeding machine control method comprises the following steps: in step S1, based on the data measured by a weighing sensor, the pet feeding machine detects whether there is a pet drinking water. If not, the visual sensor is kept closed. If yes, the visual sensor is turned on to collect images, and then step S2 is entered. In step S2, the pet feeding machine judges the time interval between the last water changing time and the current time. If the time interval is less than or equal to a preset value, it is determined that water changing is not needed. If the time interval is greater than the preset value, it is determined that water changing is needed. The pet feeding machine detects whether water changing is needed based on the data measured by the weighing sensor and records the water changing time. The pet feeding machine control method improves the utilization rate of the weighing sensor, enables the pet feeding machine to realize more functions without adding new hardware structures, shortens the product development cycle, and greatly reduces the cost of the pet feeding machine.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pet feeding machines, in particular to a pet feeding machine control method, a pet feeding machine control system and a pet feeding machine. BACKGROUND

[0002] With the continuous improvement of the living standards of residents, more and more families choose to raise pets, and there are also many intelligent feeding machines on the market that can help the owners to feed pets. The main function of the intelligent feeding machine is to provide drinking water and food for pets, and also has the functions of counting the food and drink of the pet and recording the food and drink state of the pet. The pet feeding machine on the market currently counts the food and drink of the pet by weighing the weight of the water through a weighing sensor. However, the weighing sensor only has this function and is not reused, and the function is relatively single. SUMMARY

[0003] The present application provides a pet feeding machine control method, a pet feeding machine control system and a pet feeding machine, and the specific technical solutions are as follows:

[0004] A pet feeding machine control method, the pet feeding machine control method comprising: step S1, based on the data measured by the weighing sensor, the pet feeding machine detects whether there is a pet drinking water, if not, the visual sensor is kept closed, if yes, the visual sensor is opened to collect images, and then step S2 is entered; step S2, the pet feeding machine judges the time interval between the last water changing time and the current time, if the time interval is less than or equal to a preset value, it is determined that there is no need to change water, if the time interval is greater than the preset value, it is determined that the water needs to be changed; wherein the pet feeding machine detects whether to change water based on the data measured by the weighing sensor and records the water changing time.

[0005] Further, in the step S1, based on the data measured by the weighing sensor, the method for the pet feeding machine to detect whether there is a pet drinking water comprises: step S11, when the pet feeding machine detects a weight decrease through the data measured by the weighing sensor, it is judged whether the decrease value is within a preset range, if not, it is determined that there is no pet drinking water, if yes, step S12 is entered; step S12, the pet feeding machine judges whether the weight continuously decreases within a preset time and the decrease value is within a preset range, if not, it is determined that there is no pet drinking water, if yes, it is determined that there is a pet drinking water.

[0006] Further, in the step S11, when the pet feeding machine detects a weight decrease through the data measured by the weighing sensor, if it is judged that the decrease value is within a preset range, the visual sensor is opened to collect images, and then it is continuously detected whether there is a pet drinking water, if it is determined that there is a pet drinking water, the image collection is continuously performed, if it is determined that there is no pet drinking water, the collected images are deleted and the visual sensor is closed.

[0007] Further, when the pet feeding machine determines that the pet is drinking water, the pet feeding machine determines whether the weight remains unchanged within a preset time range based on the data measured by the weighing sensor during the process of opening the visual sensor to collect images. If not, it is determined that the pet is still drinking water. If yes, it is determined that the pet stops drinking water and the visual sensor is closed.

[0008] Further, the method for detecting whether the water is changed and recording the water changing time based on the data measured by the weighing sensor in step S2 includes: step S21, after the pet feeding machine detects that the weight decreases based on the data measured by the weighing sensor, it determines whether the decrease value exceeds the weight of the water storage container. If not, it is determined as non-water changing state. If yes, it is determined as water changing state, and then step S22 is entered; step S22, the pet feeding machine continues to detect. When the weight increases and the increase value exceeds the weight of the water storage container, it is determined that the water changing is completed, and the time of completing the water changing is recorded as the water changing time.

[0009] Further, when the pet feeding machine opens the visual sensor to collect images or determines that the water needs to be changed, the collected images or determination results are transmitted to the intelligent terminal.

[0010] Further, the pet feeding machine control method further includes: step S3, based on the data measured by the weighing sensor, in a use cycle of the pet feeding machine, a time stamp is set every preset time interval, and the weight data corresponding to each time stamp is recorded; step S4, in the use cycle, the mutation data is found out and deleted, and then the calibration coefficient is calculated based on the difference value of adjacent data; step S5, based on the calibration coefficient and the estimated pet drinking water amount in the use cycle, the actual pet drinking water amount is calculated and obtained.

[0011] Further, in step S4, the method for finding out the mutation data includes: step S41, in the use cycle, the weight data corresponding to the time stamp involved in the drinking water time period is marked as first mutation data; step S42, the use cycle is divided into a plurality of first time blocks by taking the first mutation data as a boundary, and the first mutation data is not included in the first time blocks; step S43, for each first time block, the average absolute deviation method is used to find out the abnormal value in each first time block, and all the abnormal values are marked as second mutation data; wherein, the mutation data includes the first mutation data and the second mutation data.

[0012] Further, the step S41, the method for obtaining the drinking water time period comprises: a step S411, when the pet feeding machine detects the weight reduction, judging whether the reduction value is within the preset weight range, if yes, determining that the pet is drinking water, and marking the time stamp at this time as the starting drinking water time stamp; a step S412, the pet feeding machine continues to detect, when the weight remains unchanged within the preset time range, determining that the pet stops drinking water, and marking the time stamp at this time as the ending drinking water time stamp; wherein the drinking water time period is the time period between the starting drinking water time stamp and the ending drinking water time stamp.

[0013] Further, the step S4, the method for calculating the calibration coefficient based on the difference value of adjacent data comprises: a step S44, dividing the use period into a plurality of second time blocks with the mutation data as the boundary, and the second time blocks do not include the mutation data; a step S45, for each second time block, calculating the absolute value of the difference value of adjacent data and obtaining the mean value to obtain the calibration coefficient corresponding to each second time block.

[0014] Further, the step S5, the method for calculating the actual pet drinking water amount based on the calibration coefficient and the estimated pet drinking water amount in the use period comprises: a step S51, multiplying the number of time stamps 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; a step S52, adding the calibration values corresponding to each second time block to obtain the total calibration value; a step S53, subtracting the total calibration value from the estimated pet drinking water amount in the use period to obtain the actual pet drinking water amount.

[0015] Further, the step S53, the method for obtaining the estimated pet drinking water amount in the use period comprises: a step S531, recording the weight data corresponding to the starting time stamp of the use period and marking it as the starting weight; a step S532, recording the weight data corresponding to the ending time stamp of the use period and marking it as the ending weight; a step S533, subtracting the ending weight from the starting weight to obtain the estimated pet drinking water amount in the use period.

[0016] A pet feeding machine, which is used to implement the pet feeding machine control method.

[0017] A pet feeding machine control system, which comprises the pet feeding machine and further comprises an intelligent terminal, the intelligent terminal being used to receive and display the data transmitted by the pet feeding machine.

[0018] The pet feeding machine control method described in the present application, in addition to the function of weighing the weight of drinking water, the pet feeding machine can also detect whether the pet drinks water and whether to change water by using the weighing sensor, improve the utilization rate of the weighing sensor, so that the pet feeding machine can realize more functions without increasing new hardware structure, shorten the product development cycle, and greatly reduce the cost of the pet feeding machine. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 The flowchart of the pet feeding machine control method according to an embodiment of the present application is described. EMBODIMENTS

[0020] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0021] It should be understood that the term "comprises" as used in this application indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should also be understood that the term "and / or" as used in this application refers to any combination of one or more of the associated listed items and all possible combinations thereof, and includes these combinations.

[0022] As used in this application, the term "if" can be construed to mean "when" or "once" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be construed to mean "once it is determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]", depending on the context.

[0023] In addition, references in the specification to "one embodiment" or "an embodiment" or "some embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase "in one embodiment" or "in some embodiments" in various places in the specification are not necessarily all referring to the same embodiment, although it can. The terms "including," "comprising," "having" and variations thereof are meant to encompass the items listed thereafter and equivalents thereof as well as additional items. The terms "coupled" and "connected," along with variations thereof, are used broadly and encompass both direct and indirect couplings or connections.

[0024] With the continuous improvement of the living standards of residents, more and more families choose to raise pets, and there are also many intelligent feeding machines on the market that can help the owners to feed pets. The main function of the intelligent feeding machine is to provide drinking water and food for pets, and also has the functions of counting the food and drink of pets and recording the food and drink state of pets. However, the current pet feeding machine on the market generally has the problems of complex design and random stacking of functions, resulting in high cost. The current pet feeding machine on the market counts the food and drink of pets by weighing the weight of water with a weighing sensor. However, the weighing sensor only has this function and is not reused, and the function is relatively single.

[0025] In order to solve the above technical problems, the pet feeding machine control method provided by the embodiments of the present application can detect whether the pet drinks water and whether the water is changed by using the weighing sensor in addition to the function of weighing the weight of drinking water, thereby improving the utilization rate of the weighing sensor, enabling the pet feeding machine to realize more functions without increasing new hardware structures, shortening the product development cycle, and greatly reducing the cost of the pet feeding machine.

[0026] As Figure 1As shown, the pet feeding machine control method comprises: step S1, based on the data measured by the weighing sensor, the pet feeding machine detects whether there is a pet drinking water, if not, the visual sensor is kept off, if yes, the visual sensor is turned on to collect images, and then step S2 is entered; step S2, the pet feeding machine judges the time interval between the last water changing time and the current time, if the time interval is less than or equal to the preset value, it is determined that there is no need to change water, if the time interval is greater than the preset value, it is determined that the water needs to be changed; wherein the pet feeding machine detects whether to change water based on the data measured by the weighing sensor and records the water changing time. It should be noted that in the embodiment of the present application, the weighing sensor has the function of weighing the weight of drinking water, which is used to count the basic function of the amount of water drunk by the pet (which is also the basic function possessed by the existing products). In addition, the visual sensor provided by the pet feeding machine is used to record or take videos or photos of the pet drinking water, which is generally in an off state to protect the privacy of the user.

[0027] As one of the embodiments, in step S1, based on the data measured by the weighing sensor, the pet feeding machine detects whether there is a pet drinking water, which comprises: step S11, when the pet feeding machine detects that the weight decreases through the data measured by the weighing sensor, it is judged whether the decrease value is within the preset range, if not, it is determined that there is no pet drinking water, if yes, step S12 is entered; step S12, the pet feeding machine judges whether the weight continuously decreases within the preset time and the decrease value is within the preset range, if not, it is determined that there is no pet drinking water, if yes, it is determined that there is a pet drinking water. Since the weight decreased by the pet drinking a sip of water is predictable, when the weight of the drinking water is detected to decrease by a certain value, it is considered that the pet is drinking water. The method described in the embodiment of the present application does not need to add new hardware structure, and whether there is a pet drinking water can be known through the analysis of the data of the weighing sensor, which is convenient and fast.

[0028] As one of the embodiments, in step S11, when the pet feeding machine detects that the weight decreases through the data measured by the weighing sensor, if it is judged that the decrease value is within the preset range, the visual sensor is turned on to collect images, and then it is continued to detect whether there is a pet drinking water, if it is determined that there is a pet drinking water, it is continued to collect images, if it is determined that there is no pet drinking water, the collected images are deleted and the visual sensor is turned off. The method described in the embodiment of the present application can avoid missing some wonderful moments of pet activities, and can also deal with unnecessary images after misjudgment.

[0029] As one of the embodiments, when the pet feeding machine determines that the pet is drinking water, the pet feeding machine determines whether the weight remains unchanged within a preset time range based on the data measured by the weighing sensor during the process of opening the visual sensor to collect images. If not, it is determined that the pet is still drinking water. If yes, it is determined that the pet stops drinking water and the visual sensor is closed. The method described in the embodiments of the application closes the visual sensor after the pet stops drinking water, avoiding the risk of leaking user privacy.

[0030] As one of the embodiments, the method for detecting whether the water is changed and recording the water changing time based on the data measured by the weighing sensor in step S2 includes: step S21, after the pet feeding machine detects that the weight decreases based on the data measured by the weighing sensor, determining whether the decreased weight exceeds the weight of the water storage container. If not, it is determined as a non-water changing state. If yes, it is determined as a water changing state, and then step S22 is entered; step S22, the pet feeding machine continuously detects, and when the weight increases and the increased weight exceeds the weight of the water storage container, it is determined that the water changing is completed, and the time of completing the water changing is recorded as the water changing time. The decreased weight refers to the weight decreased at the moment when the weight decrease is detected, and the increased weight refers to the weight increased at the moment when the weight increase is detected. It should be noted that the water changing is not simply adding water, but pouring out the original drinking water and adding clean drinking water. Generally, the water changing process also includes the step of cleaning the water storage container. It can be considered that the water changing is to ensure the health of the pet, so the user needs to change the water regularly. Although there is a scheme of setting a water level sensor and an automatic water changing device in the prior art, which can change the water regularly by itself, this scheme has obvious defects, i.e., the pet feeding machine needs to be set at the water source and the cleaning of the water storage container cannot be realized. The method described in the embodiments of the application can know whether the water is changed through the analysis of the weighing sensor data without adding new hardware structures, which is convenient and fast.

[0031] As one of the embodiments, when the pet feeding machine detects that the weight of the drinking water is less than a preset weight, it is determined that the water needs to be supplemented. The method described in the embodiments of the application can detect whether the drinking water is sufficient so as to supplement in time.

[0032] As one of the embodiments, when the pet feeding machine opens the visual sensor to collect images or determines that the water needs to be changed, the collected images or determination results are transmitted to the intelligent terminal. The method described in the embodiments of the application can realize human-computer interaction and improve the practicability of the pet feeding machine.

[0033] As one of the embodiments, the pet feeding machine control method further comprises: step S3, based on the data measured by the weighing sensor, setting a time stamp every preset time interval in a use cycle of the pet feeding machine, and recording the weight data corresponding to each time stamp; step S4, finding out the mutation data and deleting it in the use cycle, and then calculating the calibration coefficient based on the difference of adjacent data; step S5, based on the calibration coefficient and the estimated pet drinking water in the use cycle, calculating the actual pet drinking water.

[0034] In a basic embodiment, a use cycle of the pet feeding machine refers to the period from when the pet feeding machine is filled with drinking water (or a sufficient amount of drinking water for the pet to drink) to when the drinking water is finished (or almost finished) by the pet. During this use cycle, no water is added or changed. Therefore, the simple algorithm for calculating the pet's drinking water is to subtract the weight when the drinking water is finished from the weight when the drinking water is just added. Although this calculation method is simple and effective, it does not take into account the error caused by the natural loss of drinking water, such as evaporation, spilling, slight leakage or absorption by some objects, etc., which causes the water to be lost little by little, resulting in a deviation in the final calculation of the pet's drinking water. Moreover, the longer the use cycle, the greater the deviation. It should be noted that the start and end times of the use cycle can be detected by the pet feeding machine through changes in weight, such as detecting that the weight exceeds a certain value to indicate that the drinking water has been filled, and detecting that the weight is below a certain value to indicate that the drinking water has been finished. It can also be detected by the installation and removal of the water container, or it can be determined by the user in a self-defined manner.

[0035] In a particular embodiment, the use cycle of the pet feeding machine includes the case of adding water or changing water. In this embodiment, the pet's drinking water needs to consider the weight of the newly added drinking water. For example, if water is added in the middle, the pet feeding machine calculates the weight of the newly added water by subtracting the weight before adding water from the weight after adding water, and adds it to the total weight. As for how the pet feeding machine detects the addition of water or the change of water, it is not the protection content of the present application and will not be described here. It should be noted that the above basic embodiment is used as the object of the present application to describe the scheme to be protected.

[0036] In step S3, the weight data refers to the weight of the drinking water. In actual detection, if the weight detected by the pet feeding machine is the total weight of the drinking water and the container, it is automatically converted into the weight of the drinking water according to the known weight of the container.

[0037] As one of the embodiments, the method of finding out the mutation data in step S4 includes: step S41, marking the weight data corresponding to the time stamp involved in the drinking water time period as first mutation data in the use cycle; step S42, dividing the use cycle into several first time blocks with the first mutation data as the boundary, and the first time block does not include the first mutation data; step S43, respectively for each first time block, finding out the abnormal value in each first time block by the average absolute deviation method, and marking all abnormal values as second mutation data; wherein the mutation data includes the first mutation data and the second mutation data. The mutation data described in this embodiment is not natural loss, which needs to be excluded to avoid interfering with the calculation of the actual pet drinking water.

[0038] In step S41, since the pet drinking water has a duration, it involves multiple time stamps, and the corresponding multiple weight data need to be marked as first mutation data. In step S42, the first mutation data as the boundary means that the judgment is made from the start time stamp of the use cycle, if the first mutation data is encountered in the time period, the non-first mutation data time stamp before the time period is divided into the first first time block, and then the judgment is continued, all time stamps between the time period and the next first mutation data time period (if there is no next one, it is the last time stamp of the use cycle) are divided into the second first time block, and so on until the end of the use cycle. In step S43, the average absolute deviation method is a parameter-free method, which does not depend on the assumption of distribution (such as normal distribution), and can be used to calculate the difference between each data point and the sample mean, then the average value of these differences is calculated, and the average value is called the average absolute deviation (MAD), then the deviation between each data point and the sample mean is calculated, if the deviation of a certain data point is greater than 2.5 times the MAD, it can be regarded as an abnormal value. The abnormal value in the first time block is caused by uncontrollable factors, such as the data mutation caused by the pet putting its paw on the pet feeding machine.

[0039] As one of the embodiments, in step S41, the method of obtaining the drinking water time period includes: step S411, when the pet feeding machine detects a weight decrease, it is judged whether the decrease value is within a preset weight range, if yes, it is determined that the pet is drinking water, and the time stamp at this time is marked as the start drinking water time stamp; step S412, the pet feeding machine continues to detect, when the weight remains unchanged within a preset time range, it is determined that the pet stops drinking water, and the time stamp at this time is marked as the end drinking water time stamp; wherein the drinking water time period is the time period between the start drinking water time stamp and the end drinking water time stamp. Since the weight decrease caused by the pet drinking a sip of water is predictable, when the weight of the drinking water is detected to decrease by a certain value, it is considered that the pet is drinking water.

[0040] As one of the implementations, in the step S4, the method for calculating the calibration coefficient based on the difference between the adjacent data comprises: a step S44, dividing the use period into several second time blocks by taking the mutation data as the boundary, and the mutation data is not included in the second time blocks; a step S45, for each second time block, calculating the absolute value of the difference between the adjacent data and taking the average to obtain the calibration coefficient corresponding to each second time block. In the step S44, the method for dividing the second time block is the same as the method for dividing the first time block, which will not be repeated here. In the step S45, since the weather conditions, the placement position of the pet feeding machine or the drinking method of the pet may be different in different time blocks, the calibration coefficients of different time blocks may also be different. Calculating the calibration coefficient corresponding to each second time block respectively can accurately calculate the calibration value of each time block, thereby improving the accuracy of the final calculation of the actual pet drinking water amount.

[0041] As one of the implementations, in the step S5, the method for calculating the actual pet drinking water amount based on the calibration coefficient and the estimated pet drinking water amount in the use period comprises: a step S51, multiplying the number of time stamps 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; a step S52, adding the calibration values corresponding to each second time block to obtain a total calibration value; and a step S53, subtracting the total calibration value from the estimated pet drinking water amount in the use period to obtain the actual pet drinking water amount. The method described in the embodiments of the present application eliminates the error caused by the natural loss of drinking water, so that the user can accurately grasp the actual drinking water amount of the pet, and the longer the use period, the more obvious the effect.

[0042] As one of the implementations, in the step S53, the method for obtaining the estimated pet drinking water amount in the use period comprises: a step S531, recording the weight data corresponding to the start time stamp of the use period and marking it as the start weight; a step S532, recording the weight data corresponding to the end time stamp of the use period and marking it as the end weight; and a step S533, subtracting the end weight from the start weight to obtain the estimated pet drinking water amount in the use period. The method described in the embodiments of the present application can simply and quickly calculate the drinking water amount of the pet.

[0043] The embodiments of the present application provide a chip, which comprises the pet feeding machine control method. The chip can detect whether the pet drinks water and whether the water is changed by using the weighing sensor in the pet feeding machine, thereby improving the utilization rate of the weighing sensor, enabling the pet feeding machine to realize more functions without adding new hardware structures, shortening the product development cycle and greatly reducing the cost of the pet feeding machine.

[0044] The pet feeding machine provided by the embodiments of the present application comprises the chip. The pet feeding machine can detect pets and detect whether to change water by using the weighing sensor in the pet feeding machine, thereby improving the utilization rate of the weighing sensor, without adding new hardware structures to realize corresponding functions, shortening the product development cycle, and greatly reducing the cost of the pet feeding machine.

[0045] The pet feeding machine control system provided by the embodiments of the present application comprises the pet feeding machine and further comprises an intelligent terminal configured to receive and display data transmitted by the pet feeding machine. The intelligent terminal comprises any one of a mobile phone, a tablet computer or a smart television. The intelligent terminal is configured to receive videos or photos recorded or taken by the pet feeding machine, and a user can select a video recording function or a photo taking function through the intelligent terminal. The intelligent terminal is further configured to receive a result of determining whether to change water or supplement water transmitted by the pet feeding machine, so that the user can change water or supplement water in time.

[0046] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, the processes of the embodiments of the above-mentioned methods can be included. In the embodiments of the present application, the references to the memory, storage, database or other medium can include non-volatile and / or volatile memory. The non-volatile memory can include read-only memory (ROM), programmable memory (PROM), electrically programmable memory (DPROM), electrically erasable programmable memory (DDPROM) or flash memory. The volatile memory can include random access memory (RAM) or external cache memory.

[0047] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0048] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent application range. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of the present application.

Claims

1. A method for controlling a pet feeding machine, characterized in that, The pet feeding machine control method includes: Step S1: Based on the data measured by the weighing sensor, the pet feeder detects whether a pet is drinking water. If not, the vision sensor remains off. If so, the vision sensor is turned on to acquire an image, and then the process proceeds to step S2. Step S2: The pet feeder determines the time interval between the last water change and the current time. If the time interval is less than or equal to a preset value, it determines that no water change is needed. If the time interval is greater than the preset value, it determines that a water change is needed. Among them, the pet feeder detects whether the water needs to be changed based on data measured by a weighing sensor and records the water change time; The pet feeding machine control method further includes: Step S3: Based on the data measured by the weighing sensor, during one usage cycle of the pet feeder, a timestamp is set at a preset time interval, and the weight data corresponding to each timestamp is recorded. Step S4: During the usage cycle, identify and delete mutated data, and then calculate the calibration coefficient based on the difference between adjacent data. Step S5: Calculate the actual pet water consumption based on the calibration coefficient and the estimated pet water consumption over the usage period. In step S4, the method for identifying mutation data includes: Step S41: During the usage period, mark the weight data corresponding to the timestamps involved in the drinking time period as the first mutation data; Step S42: Using the first mutation data as the boundary, the usage period is divided into several first time blocks, and the first time blocks do not include the first mutation data; Step S43: For each first time block, outliers are identified using the mean absolute deviation method, and all outliers are marked as second mutation data. The mutation data includes first mutation data and second mutation data; In step S41, the method for obtaining the drinking time period includes: Step S411: When the pet feeder detects a decrease in weight, it determines whether the decrease is within the 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 S412: The pet feeder continuously monitors the water supply. When the weight remains constant within a preset time range, it determines that the pet has stopped drinking water and marks the timestamp of this time as the end of drinking water timetamp. The drinking time period is the time period from the start drinking timestamp to the end drinking timestamp. In step S4, the method for calculating the calibration coefficient based on the difference between adjacent data includes: Step S44: Using mutation data as the boundary, the usage period is divided into several second time blocks, which do not include mutation data. Step S45: For each second time block, calculate the absolute value of the difference between adjacent data and take the mean to obtain the calibration coefficient corresponding to each second time block; In step S5, 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 S51: 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 S52: Add the calibration values ​​corresponding to each second time block to obtain the total calibration value; Step S53: Subtract the total calibration value from the estimated pet water consumption during the usage period to obtain the actual pet water consumption. In step S53, the method for obtaining the estimated pet water consumption during the usage period includes: Step S531: Record the weight data corresponding to the start timestamp of the usage period and mark it as the starting weight; Step S532: Record the weight data corresponding to the end timestamp of the usage period and mark it as the end weight; Step S533: Subtract the ending weight from the starting weight to obtain the estimated pet water consumption during the usage period.

2. The pet feeding machine control method according to claim 1, characterized in that, In step S1, the method by which the pet feeder detects whether a pet is drinking water based on data measured by the weighing sensor includes: Step S11: When the pet feeder detects a decrease in weight through the data measured by the weighing sensor, it determines whether the decrease is within a preset range. If not, it determines that no pet is drinking water. If so, it proceeds to step S12. Step S12: The pet feeder determines whether the weight continues to decrease within a preset time and the decrease value is within a preset range. If not, it is determined that no pet is drinking water; if so, it is determined that a pet is drinking water.

3. The pet feeding machine control method according to claim 2, characterized in that, In step S11, when the pet feeder detects a decrease in weight through the data measured by the weighing sensor, if the decrease is within a preset range, the vision sensor is turned on to collect an image, and then the system continues to detect whether a pet is drinking water. If it is determined that a pet is drinking water, the system continues to collect an image. If it is determined that no pet is drinking water, the collected image is deleted and the vision sensor is turned off.

4. The pet feeding machine control method according to claim 3, characterized in that, When the pet feeder detects that a pet is drinking water, it activates the vision sensor to capture images. Based on the data measured by the weighing sensor, the pet feeder determines whether the weight remains constant within a preset time range. If not, it determines that the pet is still drinking water; if so, it determines that the pet has stopped drinking water and turns off the vision sensor.

5. The pet feeding machine control method according to claim 1, characterized in that, In step S2, the method by which the pet feeder detects whether the water needs to be changed and records the water change time based on data measured by the weighing sensor includes: Step S21: When the pet feeder detects a decrease in weight through the data measured by the weighing sensor, it determines whether the decrease exceeds the weight of the water storage container. If not, it is determined to be in a non-water-changing state; if so, it is determined to be in a water-changing state, and then proceeds to step S22. Step S22: The pet feeder continuously monitors the water supply. When the weight increases and the increase exceeds the weight of the water storage container, it is determined that the water change is complete, and the time when the water change is completed is recorded as the water change time.

6. The pet feeding machine control method according to claim 1, characterized in that, When the pet feeder activates its visual sensor to collect images or determines that the water needs to be changed, it transmits the collected images or the determination results to the smart terminal.

7. A pet feeder, characterized in that, The pet feeder is used to implement the pet feeder control method according to any one of claims 1 to 6.

8. A pet feeding machine control system, characterized in that, The pet feeder control system includes the pet feeder of claim 7, and further includes a smart terminal for receiving and displaying data transmitted by the pet feeder.

Images