A vision warning system for robots

Abstract

The present invention relates to the field of robot vision technology, and discloses a visual warning system for a robot. The visual warning system includes a management mobile terminal, a pet activity information module, a feeding information collection module, and an analysis module: The management mobile terminal includes a pet basic information module and a pet feed information module, and the feeding information collection module includes an image collection module and a weight collection module; pet basic information data is obtained through the pet basic information module; pet feed information data is obtained through the pet feed information module; the weight value of the pet feed in the feeding tray is collected through the weight collection module; pet activity data is obtained through the pet activity information module; finally, the analysis module analyzes the basic information data, the pet activity data in a preset past time period, and the pet feed information data to obtain the feeding amount; and the feeding amount is intelligently adjusted according to the growth situation and physical condition of the pet.

Description

Technical Field

[0001] The present invention relates to the technical field of robot vision, and specifically to a visual warning system for robots. Background Art

[0002] With the improvement of living standards, pets play an increasingly important role in people's lives. With the popularity of pet culture, keeping pets has become a fashion trend. More and more people begin to pay attention to the living quality and health problems of pets. Among them, most pet owners are busy with work and have a fast-paced life. Especially for pet owners who need to go out frequently, in order to ensure that pets can be fed regularly and quantitatively, they generally choose pet feeding robots to feed pets regularly and quantitatively to avoid problems such as pets being hungry or overeating.

[0003] In the prior art, a pet robot intelligent feeding method, chip and robot with the publication number "CN114467782B" can automatically identify the pet's face and automatically record the pet's intake, and automatically set the pet's feeding amount according to the pet's intake in the feeding training. The pet that has completed the feeding training is fed regularly according to the pet's feeding amount.

[0004] However, the above technology still has relatively large defects. For example, when determining the pet's feeding amount in the above technology, it does not consider that the pet's feeding amount is different in different periods; nor does it consider the pet's nutritional needs. If the pet's intake is too much or too little, it is easy to cause health problems such as obesity or malnutrition. Summary of the Invention

[0005] The purpose of the present invention is to provide a visual warning system for robots to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A visual warning system for robots, applicable to feeding robots, the feeding robot includes a feeder and a feeding tray; the visual warning system includes a management mobile terminal, a pet activity information module, a feeding information acquisition module and an analysis module:

[0008] The management mobile terminal includes a pet basic information module and a pet feed information module; the pet basic information module is used to obtain pet basic information data; the pet feed information module is used to obtain pet feed information data; the pet feed information data is the first feed image data;

[0009] The feeding information acquisition module includes an image acquisition module for obtaining the second feed image data of the feeding tray and a weight acquisition module for collecting the weight value of the pet feed in the feeding tray;

[0010] The pet activity information module is used to obtain the activity data of the pet;

[0011] The analysis module is used to analyze based on the basic information data, the activity data of the pet in a past preset time period, and the pet food information data to obtain the feeding amount; the analysis module is also used to analyze the first feed image data and the second feed image data of the feeding tray by the feeder during the feeding process of the feeder to obtain a feed risk index, and judge whether the pet food is abnormal according to the feed risk index. If it is abnormal, send a warning message to the management terminal and suspend feeding; otherwise, continue feeding.

[0012] As a further solution of the present invention: the basic information data includes the pet's birth date, pet breed, and the pet's current growth parameters; the pet food information data includes the nutrient composition table and the production date; the image acquisition module is arranged above the feeding tray; the weight acquisition module is arranged at the bottom of the feeding tray.

[0013] As a further solution of the present invention: the working process of the visual warning system includes the following steps:

[0014] S1: According to the pet breed and the pet's birth date, obtain the current preset growth parameters and growth period of the pet of this breed;

[0015] S2: Obtain a growth compliance coefficient according to the preset growth parameters and the pet's current growth parameters; analyze according to the growth compliance coefficient, the current growth period of the pet, the activity data of the pet in a past preset time period, and the pet food information data to determine the feeding amount;

[0016] S3: When the feeder feeds, first feed the feeding tray for a preset time and then stop;

[0017] S4: Obtain the second feed image data of the feeding tray and the pet food weight value through the image acquisition module and the weight acquisition module;

[0018] S5: Analyze the second feed image data and the first feed image data of the feeding tray to obtain a feed risk index;

[0019] S6: Then judge whether the pet food is abnormal according to the feed risk index. If it is abnormal, send a warning message to the management terminal and suspend feeding; otherwise, continue feeding until the pet food in the feeding tray reaches the feeding amount.

[0020] As a further solution of the present invention: the growth period includes infancy, adulthood, and old age.

[0021] As a further solution of the present invention: the preset growth parameters include a preset body length and a preset body weight; the pet's current growth parameters include the current body length and the current body weight. Through the formula:

[0022] ;

[0023] Calculate the growth compliance coefficient ;

[0024] Wherein, is the first judgment function. When When ; When When ; is the current weight of the pet; is the preset weight of the pet breed; is the basic error of the preset weight; is the growth parameter error adjustment coefficient of the current growth period of the pet breed; is the current body length of the pet; is the preset body length of the pet breed; is the basic error of the preset body length; is the first preset adjustment coefficient; is the first weight coefficient; is the second weight coefficient; is the first preset constant; is the second preset constant.

[0025] As a further solution of the present invention: Through the formula:

[0026] Calculate the feeding amount for the th time today

[0027] Wherein, is the daily calorie consumption per unit weight of the pet breed in the current growth period; is the predicted activity calorie consumption of the pet today; is the number of daily feedings in the current growth period; ; is the feeding coefficient for the th feeding per day, ; is the calorie of the pet food per unit weight.

[0028] As a further solution of the present invention: Through the formula:

[0029] ;

[0030] Calculate the stability index of the activity calorie consumption in the past preset time period ;

[0031] Wherein, is the second judgment function. When occurs, ; when occurs, ; is the number of days in the past preset time period, ; is the calorie consumption of activities on the th day in the past preset time period; is the preset standard deviation.

[0032] As a further solution of the present invention: The predicted calorie consumption of the pet's activities today is obtained as follows:

[0033] When or occurs, ;

[0034] When and occur, ;

[0035] When and occur, ;

[0036] Among them, is the minimum value of the daily calorie consumption of activities in the past preset time period days; is the maximum value of the daily calorie consumption of activities in the past preset time period days.

[0037] As a further solution of the present invention: Through the formula:

[0038] ;

[0039] calculate the feed risk index ;

[0040] Among them, is the preset feed color similarity; is the actual feed color similarity;

[0041] When occurs, the pet feed is normal;

[0042] When occurs, the pet feed is abnormal.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] The present invention obtains pet basic information data through a pet basic information module; obtains pet feed information data through a pet feed information module; obtains second feed image data of a feeding tray through an image acquisition module; collects the weight value of pet feed in the feeding tray through a weight acquisition module; connects with a pet wearable device through a pet activity information module to obtain pet activity data; finally, the analysis module analyzes the basic information data, the pet activity data within a preset past time period, and the pet feed information data to obtain the feeding amount; intelligently adjusts the feeding amount according to the growth and physical conditions of the pet, and also analyzes the first feed image data and the second feed image data of the feeding tray by the analysis module during the feeding process of the feeder to obtain a feed risk index, and determines whether the pet feed is abnormal according to the feed risk index; discovers feed abnormalities in a timely manner, thereby ensuring the safety of the fed feed and avoiding health problems caused by pets eating spoiled pet feed. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention will be further described below with reference to the accompanying drawings.

[0046] Figure 1 It is a system module framework diagram of an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0048] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention belongs. The "first", "second", and similar terms used in the present invention do not indicate any order, quantity, or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0049] Please refer to Figure 1 As shown, in one embodiment, a visual warning system for a robot is provided, which is applicable to a feeding robot. The feeding robot includes a feeder and a feeding tray; the visual warning system includes a management mobile terminal, a pet activity information module, a feeding information acquisition module, and an analysis module:

[0050] The management mobile terminal includes a pet basic information module and a pet feed information module; the pet basic information module is used to obtain pet basic information data; the basic information data includes the pet's birth date, pet breed, and the pet's current growth parameters; the pet feed information module is used to obtain pet feed information data; the pet feed information data includes a nutritional composition table, a production date, and first feed image data; the nutritional composition table includes the calories of the pet feed per unit weight.

[0051] The feeding information acquisition module includes an image acquisition module disposed above the feeding tray and a weight acquisition module disposed at the bottom of the feeding tray; the image acquisition module is used to obtain second feed image data of the feeding tray; the weight acquisition module is used to collect the weight value of the pet feed in the feeding tray.

[0052] The pet activity information module is used to obtain the pet's activity data.

[0053] The analysis module is used to analyze based on the basic information data, the pet's activity data in a past preset time period, and the pet feed information data to obtain the feeding amount; the analysis module is also used to analyze the first feed image data and the second feed image data of the feeding tray by the feeder during the feeding process of the feeder to obtain a feed risk index, and determine whether the pet feed is abnormal according to the feed risk index. If it is abnormal, a warning message is sent to the management terminal and the feeding is paused; otherwise, the feeding continues.

[0054] Through the above technical solutions, in this embodiment, the pet basic information data is obtained through the pet basic information module; the pet feed information data is obtained through the pet feed information module; the second feed image data of the feeding tray is obtained through the image acquisition module; the weight value of the pet feed in the feeding tray is collected through the weight acquisition module; the pet activity information module is connected to the pet wearable device to obtain the pet's activity data; finally, the analysis module analyzes based on the basic information data, the pet's activity data in a past preset time period, and the pet feed information data to obtain the feeding amount; the feeding amount is intelligently adjusted according to the growth and physical conditions of the pet. The analysis module also analyzes the first feed image data and the second feed image data of the feeding tray by the feeder during the feeding process of the feeder to obtain a feed risk index, and determines whether the pet feed is abnormal according to the feed risk index; the feed abnormality is detected in time, thereby ensuring the safety of the fed feed and avoiding the occurrence of health problems caused by the pet eating spoiled pet feed.

[0055] It should be noted that the pet basic information data can be obtained by manual input; the pet feed information data can be obtained by manual input or photo recognition; both are prior arts and will not be elaborated here.

[0056] As an implementation manner of the present invention, the working process of the visual warning system includes the following steps:

[0057] S1: According to the breed of the pet and the pet's date of birth, obtain the current preset growth parameters and growth period of the pet of this breed;

[0058] S2: Obtain the growth compliance coefficient according to the preset growth parameters and the current growth parameters of the pet; analyze according to the growth compliance coefficient, the current growth period of the pet, the activity data of the pet in the past preset time period, and the pet feed information data to determine the feeding amount;

[0059] S3: When the feeder feeds, first feed the feeding tray for a preset time and then stop;

[0060] S4: Obtain the second feed image data of the feeding tray and the pet feed weight value through the image acquisition module and the weight acquisition module;

[0061] S5: Analyze the second feed image data and the first feed image data of the feeding tray to obtain the feed risk index;

[0062] S6: Then judge whether the pet feed is abnormal according to the feed risk index. If it is abnormal, send a warning message to the management terminal and suspend feeding; otherwise, continue feeding until the pet feed in the feeding tray reaches the feeding amount;

[0063] Through the above technical solution, in this embodiment, first, according to the breed of the pet and the pet's date of birth, obtain the current preset growth parameters and growth period of the pet of this breed; then obtain the growth compliance coefficient according to the preset growth parameters and the current growth parameters of the pet; analyze according to the growth compliance coefficient, the current growth period of the pet, the activity data of the pet in the past preset time period, and the pet feed information data to determine the feeding amount; when the feeder feeds, first feed the feeding tray for a preset time and then stop; obtain the second feed image data of the feeding tray and the pet feed weight value through the image acquisition module and the weight acquisition module; analyze the second feed image data and the first feed image data of the feeding tray to obtain the feed risk index; then judge whether the pet feed is abnormal according to the feed risk index. If it is abnormal, send a warning message to the management terminal and suspend feeding; otherwise, continue feeding until the pet feed in the feeding tray reaches the feeding amount; first feed the feeding tray for a preset time and then stop. The preset time is short, so that the pet feed in the feeding tray is less, which is convenient for identifying the feed in the second feed image data. Moreover, if the feed in the feeding tray is abnormal, the pet feed in the feeding tray is less. Even if the pet eats it, it will not eat too much, resulting in discomfort for the pet.

[0064] As an implementation manner of the present invention, the growth period includes infancy, adulthood, and old age.

[0065] As an implementation manner of the present invention, the preset growth parameters include a preset body length and a preset body weight; the current growth parameters of the pet include the current body length and the current body weight. Through the formula:

[0066] ;

[0067] Calculate the growth compliance coefficient ;

[0068] Wherein, is the first judgment function. When , ; when , ; is the current body weight of the pet; is the preset body weight of the pet breed; is the preset body weight basic error; is the growth parameter error adjustment coefficient of the current growth period of the pet breed; is the current body length of the pet; is the preset body length of the pet breed; is the preset body length basic error; is the first preset adjustment coefficient; is the first weight coefficient; is the second weight coefficient; is the first preset constant; is the second preset constant;

[0069] Through the above technical solution, in this embodiment is the ratio of the current body weight of the pet to the preset body weight; is the absolute value of the ratio of the difference between the current body weight and the preset body weight of the pet to the preset body weight, is the preset body weight error of the current growth period of the pet breed; is the difference between the absolute value of the ratio of the difference between the current body weight and the preset body weight of the pet to the preset body weight and the preset body weight error of the current growth period of the pet breed; In the formula , the judgment function in refers to , refers to , which is used to judge whether the absolute value of the ratio of the difference between the current body weight and the preset body weight of the pet to the preset body weight exceeds the preset body weight error of the current growth period of the pet breed; when , it indicates that the current body weight of the pet is within a reasonable range, so ; when , it indicates that the current body weight of the pet is not within a reasonable range, so ; Similarly, in this embodiment is the ratio of the current body length of the pet to the preset body length; is the absolute value of the ratio of the difference between the current body length and the preset body length of the pet to the preset body length, is the preset body length error in the current growth period of the pet breed; is the difference between the absolute value of the ratio of the difference between the current body length and the preset body length of the pet to the preset body length and the preset body length error in the current growth period of the pet breed; In the formula the first judgment function in refers to , refers to , and is used to judge whether the absolute value of the ratio of the difference between the current body length and the preset body length of the pet to the preset body length exceeds the preset body length error in the current growth period of the pet breed; When , it indicates that the current body length of the pet is within a reasonable range, so ; When , it indicates that the current body length of the pet is not within a reasonable range, so ; The physical condition of the pet is evaluated through the formula ;

[0070] It should be noted that the first preset adjustment coefficient , the first weight coefficient , the second weight coefficient , the first preset constant , the second preset constant and the growth parameter error adjustment coefficient of the current growth period of the pet breed are preset values, obtained based on experience and not elaborated here.

[0071] As an implementation manner of the present invention, through the formula:

[0072] calculate the feeding amount for the th time today;

[0073] Among them, is the daily calorie consumption per unit weight of the pet breed in the current growth period; is the predicted activity calorie consumption of the pet today; is the number of daily feedings in the current growth period; ; is the feeding coefficient for the th feeding per day, ; is the calorie of the pet food per unit weight;

[0074] Through the above technical solution, in this embodiment is the daily calorie consumption for the current weight of the pet, and the daily calorie consumption for the current weight of the pet The more, the more calories need to be ingested today. is the total predicted calorie consumption today; the more the total predicted calorie consumption today, the more calories need to be ingested today. When it indicates that the body length or weight of the pet does not meet the standard, and the intake needs to be increased. Therefore, the calories to be ingested today increase; when it indicates that the body length of the pet grows too fast or the weight is heavy, and the intake needs to be reduced. Therefore, the calories to be ingested today are reduced; is the feeding amount today; the feeding amount for the day is reasonably allocated according to the feeding coefficient;

[0075] It should be noted that the daily calorie consumption per unit weight of the pet breed in the current growth period is a preset value, obtained based on experience and not elaborated here.

[0076] It should be noted that the number of daily feedings in the current growth period is based on and the feeding coefficient for the th feeding per day is determined according to the current growth period and is a preset value, not elaborated here.

[0077] As an implementation manner of the present invention, through the formula:

[0078] ;

[0079] Calculate the stability index of the activity calorie consumption in the past preset time period ;

[0080] Among them, is the second judgment function. When , ; when , ; is the number of days in the past preset time period, ; is the activity calorie consumption on the th day in the past preset time period; is the preset standard deviation;

[0081] Through the above technical solution, in this embodiment is the standard deviation of the daily activity calorie consumption in the past preset time period days; the standard deviation of the daily activity calorie consumption in the past preset time period days The larger it is, it indicates that the daily activity volume of the pet in the past preset time period is unstable. is the standard deviation of the daily activity calorie consumption in the past preset time period days minus the preset standard deviation ; in the formula , the second judgment function in refers to , and is used to judge whether the standard deviation of the daily activity calorie consumption in the past preset time period days exceeds the preset standard deviation; when , it indicates that the daily activity volume of the pet in the past preset time period is relatively stable, so ; when , it indicates that the daily activity volume of the pet in the past preset time period is unstable, so ;

[0082] It should be noted that the preset standard deviation is a preset value, obtained based on experience, and will not be elaborated here.

[0083] The process of obtaining the predicted activity calorie consumption of the pet on the current day is as follows:

[0084] When or , ;

[0085] When and , ;

[0086] When and , ;

[0087] Among them, is the minimum value of the daily activity calorie consumption in the past preset time period days; is the maximum value of the daily activity calorie consumption in the past preset time period days;

[0088] Through the above technical solution, in this embodiment, when or , it indicates that the daily activity volume of the pet in the past preset time period is relatively stable or both the body length and weight of the pet are within a reasonable range. Therefore, the predicted activity calorie consumption of the pet on the current day is set to the average value of the daily activity calorie consumption in the past preset time period days; when and When it indicates that the daily activity level of the pet was unstable within the past preset time period and the body length or weight of the pet exceeded the standard, it is necessary to reduce the calorie intake. Therefore, the predicted calorie consumption of the pet's activity today is set to the minimum value of the daily calorie consumption of the pet's activity in the past preset time period to reduce the intake; when days and When it indicates that the daily activity level of the pet was unstable within the past preset time period and the body length or weight of the pet did not meet the standard, it is necessary to increase the calorie intake. Therefore, the predicted calorie consumption of the pet's activity today is set to the maximum value of the daily calorie consumption of the pet's activity in the past preset time period to increase the intake.

[0089] As an implementation manner of the present invention, through the formula:

[0090] ;

[0091] calculate the feed risk index ;

[0092] wherein, is the preset feed color similarity; is the actual feed color similarity;

[0093] When , the pet feed is normal;

[0094] When , the pet feed is abnormal;

[0095] Through the above technical solution, in this embodiment, the second feed image data and the first feed image data of the feeding tray are recognized, the feeds in the second feed image data and the first feed image data are respectively recognized, and the actual feed color similarity is obtained by analyzing the feeds in the second feed image data and the first feed image data. This process is analyzed by a trained convolutional neural network model. The training process is prior art and will not be elaborated here; when , it indicates that the actual feed color similarity is higher than the preset feed color similarity. Therefore, the pet feed is normal; when , it indicates that the actual feed color similarity is lower than the preset feed color similarity, indicating that the feed may be deteriorated. Therefore, the pet feed is abnormal; during the feeding process, the feed is evaluated to prevent the pet from eating deteriorated feed, thus causing health problems;

[0096] It should be noted that the preset feed color similarity is a preset value, obtained according to experience and will not be elaborated here.

[0097] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A visual warning system for a robot, applicable to a feeding robot, the feeding robot comprising a feeder and a feeding tray; characterized in that, The visual warning system includes a management mobile terminal, a pet activity information module, a feeding information collection module, and an analysis module: The management mobile terminal includes a pet basic information module and a pet feed information module; the pet basic information module is used to obtain pet basic information data; the pet feed information module is used to obtain pet feed information data; the pet feed information data is the first feed image data; The feeding information collection module includes an image collection module for obtaining the second feed image data of the feeding tray and a weight collection module for collecting the weight value of the pet feed in the feeding tray; The pet activity information module is used to obtain the activity data of the pet; The analysis module is used to analyze based on the basic information data, the activity data of the pet in the past preset time period, and the pet feed information data to obtain the feeding amount; the analysis module is also used to analyze the first feed image data and the second feed image data of the feeding tray by the feeder during the feeding process of the feeder to obtain a feed risk index, and judge whether the pet feed is abnormal according to the feed risk index. If it is abnormal, send a warning message to the management terminal and suspend feeding; otherwise, continue feeding; The working process of the visual warning system includes the following steps: S1: According to the breed of the pet and the pet's birth date, obtain the current preset growth parameters and growth period of the pet of this breed; S2: Obtain a growth compliance coefficient according to the preset growth parameters and the current growth parameters of the pet; analyze according to the growth compliance coefficient, the current growth period of the pet, the activity data of the pet in the past preset time period, and the pet feed information data to determine the feeding amount; S3: When the feeder feeds, first feed the feeding tray for a preset time and then stop; S4: Obtain the second feed image data of the feeding tray and the weight value of the pet feed through the image collection module and the weight collection module; S5: Analyze the second feed image data and the first feed image data of the feeding tray to obtain a feed risk index; S6: Then judge whether the pet feed is abnormal according to the feed risk index. If it is abnormal, send a warning message to the management terminal and suspend feeding; otherwise, continue feeding until the pet feed in the feeding tray reaches the feeding amount; The preset growth parameters include a preset body length and a preset body weight; the current growth parameters of the pet include the current body length and the current body weight. Through the formula: ； Calculate the growth compliance coefficient ; Among them, is the first judgment function. When , ; when , ; is the current weight of the pet; is the preset weight of the pet breed; is the basic error of the preset weight; is the growth parameter error adjustment coefficient of the current growth period of the pet breed; is the current body length of the pet; is the preset body length of the pet breed; is the basic error of the preset body length; is the first preset adjustment coefficient; is the first weight coefficient; is the second weight coefficient; is the first preset constant; is the second preset constant; Through the formula: ； Calculate the feeding amount for the time today; Among them, is the daily calorie consumption per unit weight in the current growth period of this pet breed; is the predicted calorie consumption of this pet's activities today; is the number of daily feedings in the current growth period; ; is the th feeding coefficient for the th feeding of the day, is the calorie content of the pet food per unit weight.

2. The visual warning system for a robot according to claim 1, characterized in that, The basic information data includes the pet's birth date, pet breed, and current growth parameters of the pet; the pet feed information data includes a nutrition composition table and a production date; the image collection module is arranged above the feeding tray; the weight collection module is arranged at the bottom of the feeding tray.

3. The visual warning system for a robot according to claim 2, wherein, The growth period includes infancy, adulthood, and old age.

4. A vision warning system for a robot according to claim 3, wherein, Through the formula: ； Calculate the stability index of the calorie consumption during activities in the past preset time period ; Among them, is the second judgment function. When , ; when , ; is the number of days in the past preset time period, ; is the calorie consumption of the activity on the th day in the past preset time period; is the preset standard deviation.

5. The visual warning system for a robot according to claim 4, wherein, The calories consumed in the pet's daily prediction activity The acquisition process is as follows: When or then ; When and then ; When and then ; Among them, is the minimum value of the calories consumed by daily activities in the past preset time period days; is the maximum value of the calories consumed by daily activities in the past preset time period days.

6. The visual warning system for a robot according to claim 5, wherein, Through the formula: ； Calculate the feed risk index ; Among them, is the preset feed color similarity; is the actual feed color similarity; When the pet food is normal; When the pet food is abnormal.

Images