AI intelligent pet nursing method and system based on Internet of Things

Abstract

The invention provides an AI intelligent pet nursing method and system based on the Internet of Things, and the method comprises the steps: a pet nursing service obtains user configuration information from a database, and a mobile client calls an interface of an intelligent pet feeder according to the user configuration information, and triggers the feeding operation of the intelligent pet feeder; the pet nursing service receives a feeding result of the intelligent pet feeder; when the intelligent pet feeder monitors that the pet takes food abnormally, the pet nursing service receives alarm information sent by the intelligent pet feeder; the pet nursing service combines the video information, the alarm information and the user configuration information to obtain a request parameter; the pet nursing service sends the request parameter to an artificial intelligence cloud service, so that the artificial intelligence cloud service performs AI analysis on the request parameter to obtain an analysis result; the pet nursing service counts the duration of all behaviors of the pet according to the analysis result; and the pet nursing service compares the duration with the user configuration information to obtain a comparison result.

Description

Technical Field

[0001] The present invention relates to the field of security technologies, and in particular to an AI intelligent pet care method and system based on the Internet of Things. Background Art

[0002] Modern intelligent camera technology enables families to monitor the living status of pets in real time by installing cameras and remotely view it through a mobile application even when they are out.

[0003] However, there are also certain deficiencies in this monitoring method. Most pet owners will use the playback function of the camera to view the video during their free time and try to understand the daily activities of their pets. This method is essentially "passive" monitoring and cannot capture abnormal behaviors of pets in real time, such as abnormal eating, staying still for a long time, inactivity, etc., and can only be known when reviewing the video afterwards, missing the opportunity for timely intervention. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an AI intelligent pet care method and system based on the Internet of Things, which can perform intelligent analysis and recognition on the abnormal behaviors of pets in a timely manner, and the system actively issues an alarm to help the owner discover and handle problems in the first time, greatly improving the real-time performance and efficiency of pet care.

[0005] In the first aspect, an embodiment of the present invention provides an AI intelligent pet care method based on the Internet of Things, which is applied to a pet care service. The method includes: The pet care service obtains user configuration information from a database, sends the user configuration information to a mobile client, so that the mobile client calls the interface of an intelligent pet feeder according to the user configuration information and triggers the feeding operation of the intelligent pet feeder; The pet care service receives the feeding result of the intelligent pet feeder and sends the feeding result to the mobile client, so that the mobile client displays the feeding result; When the intelligent pet feeder monitors that a pet has abnormal eating, the pet care service receives the alarm information sent by the intelligent pet feeder and sends the alarm information to the mobile client; The pet care service receives the video information sent by the intelligent pet feeder, and the video information includes the diet video information of the pet and the overall video information when the pet appears; The pet care service combines the video information, the alarm information and the user configuration information to obtain request parameters; The pet care service sends the request parameters to an artificial intelligence cloud service, so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result; The pet care service counts the duration of all the pet's behaviors according to the analysis result; The pet care service compares the duration with the user configuration information to obtain a comparison result.

[0006] Further, when the intelligent pet feeder monitors that the pet has abnormal eating, the pet care service receives the alarm information sent by the intelligent pet feeder and sends the alarm information to the mobile client, including: When the pet enters the next feeding time, the intelligent pet feeder generates an alarm information that the pet has not eaten for a long time after detecting that the food intake has not changed and the pet has not eaten. The pet care service receives the alarm information that the pet has not eaten for a long time sent by the intelligent pet feeder; The pet care service sends a first reminder message to the mobile client and pops up a window; When the intelligent pet feeder detects that the food intake in the top food bowl is less than the user-set capacity, the pet care service receives the alarm information of insufficient food storage sent by the intelligent pet feeder; The pet care service sends a second reminder message to the mobile client and pops up a window.

[0007] Further, the pet care service sends the request parameters to the artificial intelligence cloud service so that the artificial intelligence cloud service performs AI analysis on the request parameters, including: The pet care service sends the request parameters to the artificial intelligence cloud service so that the artificial intelligence cloud service performs frame extraction analysis on the video in the request parameters; Determine whether the pet is in the excretion area set by the user; If it is in the excretion area and stays for a long time, it is determined that the pet is excreting; Determine whether the pet is in a dangerous area; If the pet is in the dangerous area, return the staying time; Analyze the current behavior of the pet and perform time statistics on the current behavior; Determine whether there is abnormal sound in the audio in the video; If there is the abnormal sound, determine the type and duration of the abnormal sound and obtain the link of the corresponding video segment.

[0008] Further, the pet care service compares the duration with the user configuration information to obtain a comparison result, including: When the staying time of the pet in the dangerous area is greater than the first set time, the pet care service generates an alarm message; When the abnormal movement time of the pet is greater than the second set time, the pet care service generates the alarm message.

[0009] Furthermore, the method further includes: The pet care service counts the time period of the pet's eating time, the number of eating times, the amount of food eaten, the amount of water intake, the number of excretion times, the staying time in the dangerous area, the long lying time, the long absence time, and the abnormal movement time of the pet on the same day to obtain statistical data; The pet care service generates a daily report based on the statistical data and pushes it to the mobile client at a set time on the next day.

[0010] Furthermore, the method further includes: The pet care service extracts video segments of multiple different behaviors within a set time; The pet care service integrates each video segment of the different behaviors to obtain integrated data; The pet care service sends the integrated data to the mobile client.

[0011] Furthermore, the method further includes: The pet care service counts the daily food intake, the number of eating times, the eating time period, the weekly excretion number, and the daily activity of the pet to obtain pet daily statistical data; The pet care service performs interval value taking and averaging on the pet daily statistical data to obtain normal daily routine reference data; The pet care service determines whether there is an abnormality in the current daily routine of the pet according to the normal daily routine reference data; If so, it is determined that there is a monitoring risk for the pet, a difference information is generated, and the abnormal days are marked in the weekly report or daily report; wherein, the difference information includes the difference in the daily routine of the pet compared with the daily routine in other time periods.

[0012] Furthermore, the user configuration information includes: marked dangerous areas, alarm information for staying time in the dangerous area, marked excretion areas, set types of the pet, food output amount, food output time, frequency of the intelligent pet feeder, set alarm time periods, alarm information for the long absence of the pet, alarm information for the eating frequency of the pet, set eating time periods of the pet, alarm information for the non - eating of the pet, alarm information for the abnormal state of the pet itself, alarm information for the abnormal state of the pet to the outside world, set audio reminder information, set alarm voice broadcast content information.

[0013] Second aspect, an embodiment of the present invention provides an AI intelligent pet care system based on the Internet of Things, which is applied to pet care services. The system includes: An acquisition module, configured to obtain user configuration information from a database for the pet care service, and send the user configuration information to a mobile client, so that the mobile client calls an interface of an intelligent pet feeder according to the user configuration information and triggers a feeding operation of the intelligent pet feeder; An eating result receiving module, configured to receive an eating result of the intelligent pet feeder for the pet care service, and send the eating result to the mobile client, so that the mobile client displays the eating result; An alarm information receiving module, configured to receive alarm information sent by the intelligent pet feeder when the intelligent pet feeder detects abnormal eating of a pet for the pet care service, and send the alarm information to the mobile client; A video information receiving module, configured to receive video information sent by the intelligent pet feeder for the pet care service, where the video information includes diet video information of the pet and overall video information when the pet appears; A combination module, configured to combine the video information, the alarm information, and the user configuration information for the pet care service to obtain request parameters; A sending module, configured to send the request parameters to an artificial intelligence cloud service for the pet care service, so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result; A statistics module, configured to calculate the duration of all behaviors of the pet according to the analysis result for the pet care service; A comparison module, configured to compare the duration with the user configuration information for the pet care service to obtain a comparison result.

[0014] Third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor. A computer program is stored on the memory and can run on the processor. When the processor executes the computer program, the above-mentioned method is implemented.

[0015] The embodiments of the present invention provide an AI intelligent pet care method and system based on the Internet of Things, which are applied to pet care services and include: the pet care service obtains user configuration information from a database, sends the user configuration information to a mobile client, so that the mobile client calls the interface of an intelligent pet feeder according to the user configuration information and triggers the feeding operation of the intelligent pet feeder; the pet care service receives the feeding result of the intelligent pet feeder and sends the feeding result to the mobile client, so that the mobile client displays the feeding result; when the intelligent pet feeder monitors that the pet has abnormal eating, the pet care service receives the alarm information sent by the intelligent pet feeder and sends the alarm information to the mobile client; the pet care service receives the video information sent by the intelligent pet feeder, and the video information includes the diet video information of the pet and the overall video information when the pet appears; the pet care service combines the video information, the alarm information and the user configuration information to obtain request parameters; the pet care service sends the request parameters to an artificial intelligence cloud service, so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result; the pet care service counts the duration of all behaviors of the pet according to the analysis result; the pet care service compares the duration with the user configuration information to obtain a comparison result; the abnormal behaviors of the pet are intelligently analyzed and identified in a timely manner, and the system actively issues an alarm to help the owner discover and handle problems in the first time, greatly improving the real-time performance and efficiency of care.

[0016] Other features and advantages of the present invention will be described in the following specification, and in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification, claims and drawings.

[0017] In order to make the above objectives, features and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, makes the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0019] Figure 1 It is a flowchart of the AI intelligent pet care method based on the Internet of Things provided in Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of the AI intelligent pet care system provided in Embodiment 1 of the present invention; Figure 3It is a signaling diagram of the information configuration process provided by Embodiment 1 of the present invention; Figure 4 It is a schematic diagram of the intelligent pet feeder provided by Embodiment 1 of the present invention; Figure 5 It is a signaling diagram of the feeding process of the intelligent pet feeder provided by Embodiment 1 of the present invention; Figure 6 It is a signaling diagram of the analysis process of the pet care service provided by Embodiment 1 of the present invention; Figure 7 It is a signaling diagram of the request process of the mobile client provided by Embodiment 1 of the present invention; Figure 8 It is a schematic diagram of the AI intelligent pet care system based on the Internet of Things provided by Embodiment 2 of the present invention. Detailed implementation manners

[0020] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] This application combines AI behavior analysis, intelligent cameras and intelligent pet feeders, and intelligently monitors the daily activities of pets by uploading video data to the cloud for analysis. The artificial intelligence cloud service can identify whether a pet has not eaten or drunk water for a long time, count its food intake and drinking frequency, monitor whether the pet eats or drinks on time, and record its eating habits. In addition, the system can also identify the excretion situation of the pet, such as abnormal urination and defecation, and at the same time monitor the activity status and safety issues, including whether the pet does not move for a long time and whether there are abnormal activities (such as running around, jumping around, destroying household items, etc.). When the system finds that the pet has not appeared for a long time, is too active or abnormal, it will immediately push an alarm notification to the owner through the APP to ensure timely intervention and guarantee the safety and health of the pet.

[0022] The system can also monitor the food stock of the feeder. If the food is about to run out or the feeder fails, the system will automatically issue an alarm. At the same time, the artificial intelligence cloud service can identify the abnormal food intake of the pet, such as overeating or too little food intake for a long time, and judge whether there is a health risk through intelligent analysis. The feeder can set the automatic feeding time frequency and feeding amount, and at the same time remind the pet to eat through custom voice recording. If the pet enters an unsafe area, such as the kitchen, trash can or other high-risk areas, the system will also issue a warning.

[0023] Meanwhile, the pet care system will condense the pet's activities of a day into a short fast-forward video of less than five minutes, making it convenient for users to watch the pet's situation throughout the day. Based on the data statistics of a week or a month, it will provide the pet's daily routine, the number of meals and excretions per day, as well as potential abnormal behaviors during which time periods, and notify the user to pay special attention to the pet's condition during those time periods.

[0024] In this way, once the artificial intelligence cloud service detects abnormal food intake, abnormal urination and defecation, insufficient food in the feeder or other abnormal situations of the pet, the system will immediately push an alarm notification to the owner through the APP. The user can intervene in a timely manner by means of video connection with voice through the camera, ensuring that the owner can intervene in a timely manner to safeguard the safety and health of the pet. At the same time, through the daily fast-forward and weekly / monthly reports, users can understand the pet's routine, diet and excretion situation.

[0025] For the convenience of understanding this embodiment, the embodiments of the present invention will be introduced in detail below.

[0026] Embodiment 1: Figure 1 It is a flowchart of an AI intelligent pet care method based on the Internet of Things provided by Embodiment 1 of the present invention.

[0027] Referring to Figure 1 , applied to pet care services, the method includes the following steps: Step S101, the pet care service obtains user configuration information from the database and sends the user configuration information to the mobile client, so that the mobile client calls the interface of the intelligent pet feeder according to the user configuration information and triggers the feeding operation of the intelligent pet feeder; Specifically, referring to Figure 5 , the mobile client obtains the feeding configuration, feeding time, whether the feeding reminder voice is turned on, the feeding amount and the number of feedings in the user configuration information from the pet care service. When the configured time is the same as the current time, the APP will call the feeding interface of the intelligent pet feeder according to the user configuration information, thereby triggering the feeding operation of the intelligent pet feeder.

[0028] Step S102, the pet care service receives the feeding result of the intelligent pet feeder and sends the feeding result to the mobile client, so that the mobile client displays the feeding result; Specifically, the front camera of the intelligent pet feeder will detect the situation of the food in the basin and whether there is a pet approaching to eat. At the same time, the pressure sensing device at the bottom of the intelligent pet feeder is used to detect the pet's food intake. When the pet approaches and eats, it will transmit data such as the feeding time and the feeding amount to the pet care service. The pet care service saves and updates the data, and at the same time displays the feeding result (feeding time, feeding amount) on the APP.

[0029] Step S103: When the intelligent pet feeder detects abnormal pet eating, the pet care service receives the alarm information sent by the intelligent pet feeder and sends the alarm information to the mobile client. Step S104: The pet care service receives the video information sent by the intelligent pet feeder, where the video information includes the pet's diet video information and the overall video information when the pet appears. Specifically, referring to Figure 4 , the intelligent pet feeder includes a food storage module, a liquid storage module, a control center, a pressure sensing device, an intelligent camera, and a voice module.

[0030] An intelligent camera is built into the intelligent pet feeder. The intelligent camera can be a flat shooting camera. The intelligent camera monitors the pet's eating and drinking situations and sends the pet's diet video link to the pet care service in the form of an alarm. The control center is used for data interaction and controls the food and liquid output; the pressure sensing device is used to judge the specific food intake of the pet, and the voice module is used to provide voice recording and broadcasting or real-time voice connection through the APP.

[0031] The intelligent pet feeder also includes a top camera, which is used to shoot the overall video information when the pet appears. When the camera detects the appearance or movement of an infrared object under the monitoring camera, it will record the video. After the video recording reaches five minutes, it will upload the video recording to the cloud and generate a video link, and send it to the pet care service in the form of an alarm.

[0032] Step S105: The pet care service combines the video information, the alarm information, and the user configuration information to obtain request parameters. Step S106: The pet care service sends the request parameters to the artificial intelligence cloud service so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result. Step S107: The pet care service counts the duration of all pet behaviors according to the analysis result. Step S108: The pet care service compares the duration with the user configuration information to obtain a comparison result.

[0033] Referring to Figure 2The system includes a smart pet feeder, a pet care service, a mobile client, a top camera, and an artificial intelligence cloud service. The smart pet feeder is used to monitor pets, provide food and water, and obtain information about their eating status and amount; the pet care service is used to provide the mobile client's APP with an interface for storing configuration information, displaying statistical information, and other interfaces, and to provide an interface for obtaining the analysis results of the artificial intelligence cloud service (AIcloud), and an intermediate service that stores a series of data in the database; the mobile client is used to configure the pet care system data, obtain weekly and daily reports, one-day fast forward, abnormal alarms, etc.; the top camera is used to provide videos of pets.

[0034] Furthermore, the user configuration information includes: marked dangerous areas (such as windows), alarm information of the time spent in dangerous areas (i.e., configuring the time of staying in dangerous areas to trigger an alarm), marked excretion areas (such as cat litter boxes, toilets, etc., used to determine the excretion of pets), set the type of pet, the amount of food the smart pet feeder outputs, the time and frequency of feeding, set the time period for the alarm (whether it is the whole day or a certain time period during the day), set the alarm information of the pet's long absence (i.e., setting the time period for the pet's absence to trigger an alarm), and the alarm information of the pet's eating frequency (i.e., the pet's eating frequency is low). The alarm information includes: setting the time period for the pet to eat, setting the alarm information when the pet does not eat (whether to alarm when the pet does not eat), setting the alarm information of the pet's own abnormal state (i.e. how long the pet's abnormal running and abnormal shouting last before the alarm), the alarm information of the pet's abnormal state in the outside world (i.e. whether to alarm for abnormal collision sounds or sharp explosions of objects), setting audio reminder information (i.e. whether to turn on audio recording to remind eating), setting the alarm voice broadcast content information (i.e. setting the content of the voice broadcast after a certain alarm, for example, broadcasting the specified recorded audio set by the user when the pet runs abnormally).

[0035] Specifically, refer to Figure 3 , the user needs to open the APP configuration page, configure the information on the camera interface, and save the configuration information. The pet care service obtains the user configuration information and stores the user configuration information in the database. The pet care service queries the user configuration information from the database and returns the user configuration information to the APP.

[0036] The pet care service obtains the modified user configuration information and performs a legitimacy check on the modified user configuration information; for example, whether the coordinate demarcation range meets the standards, such as whether the numbers such as xmax and xmin are positive numbers, whether the values are too large, whether the demarcation of the area meets the requirements (such as whether the left and right intervals and the upper line interval are too small, etc., and the difference between xmax and xmin), the legitimacy of the set drinking frequency, and the legitimacy of the long absence time are checked.

[0037] After the verification passes, update the modified user configuration information to the database; the database returns a success message to the pet care service.

[0038] Further, step S103 includes the following steps: Step S201, when the pet enters the next feeding time, the intelligent pet feeder detects that the food intake has not changed and the pet has not eaten, and then generates an alarm message that the pet has not eaten for a long time. The pet care service receives the alarm message that the pet has not eaten for a long time sent by the intelligent pet feeder. Step S202, the pet care service sends a first reminder message to the mobile client and pops up a window. Specifically, if it reaches the next feeding time of the intelligent pet feeder, the bottom sensor of the intelligent pet feeder finds that the food intake has not changed, and the front camera detects that the pet has not eaten, then it sends an alarm message that the pet has not eaten for a long time to the pet care service. After receiving it, the pet care service first records it in the database, and pushes it to the APP and pops up a window or makes a phone reminder.

[0039] Step S203, when the intelligent pet feeder detects that the food volume in the top food bowl is less than the user-set capacity, the pet care service receives the alarm message of insufficient food storage sent by the intelligent pet feeder. Step S204, the pet care service sends a second reminder message to the mobile client and pops up a window.

[0040] Specifically, if the food volume in the top food bowl is less than the user-set capacity, it pushes an alarm to the pet care service, and the pet care service pushes an alarm message of insufficient food storage to the APP and pops up a window.

[0041] Further, step S106 includes the following steps: Step S301, the pet care service sends the request parameters to the artificial intelligence cloud service so that the artificial intelligence cloud service performs frame extraction analysis on the video in the request parameters. Step S302, determine whether the pet is in the user-set excretion area. Step S303, if it is in the excretion area and stays for a long time, determine that the pet is excreting. Step S304, determine whether the pet is in a dangerous area. Step S305, if the pet is in a dangerous area, return the stay time. Step S306, analyze the current behavior of the pet and perform time statistics on the current behavior. Step S307, determine whether there is abnormal sound in the audio of the video. Step S308, if there is abnormal sound, determine the type and duration of the abnormal sound, and obtain the link to the corresponding video segment.

[0042] Specifically, referring to Figure 6 , the pet care service obtains the alarm information of the front camera and the top camera in the intelligent pet feeder through PMS (Push Message Service), and stores it in the database. The pet care service combines the video information, alarm information, and user configuration information to obtain request parameters. The pet care service uploads the request parameters to the artificial intelligence cloud service for AI analysis.

[0043] Obtain the request parameters of the pet care service (including video information, alarm information, user configuration information, user ID, device serial number, etc.); perform AI analysis on the input video information. The artificial intelligence cloud service obtains the request body of the pet care service, performs frame extraction analysis on the video information, analyzes the pet's behavior, and determines whether it is in the excretion area designated by the user; if it is in the excretion area and stays for a long time, it is determined that the pet is excreting; analyze whether the pet is in a dangerous area, such as by the window or in the kitchen, and return the stay time. Analyze the pet's current behavior, such as lying down for a long time, not appearing for a long time, or pacing, running, jumping around frequently, and count the time of such behaviors.

[0044] At the same time, the analysis will also analyze the audio in the video to analyze whether there are explosion sounds, sharp sounds of object collisions, or howling sounds of pets, and send the analysis results (the type and duration of the sound) and the video link of this segment to the pet care service (for generating a one-day fast forward). Return the behavior statistics results to the pet care service through video and audio analysis.

[0045] Further, step S108 includes the following steps: Step S401, when the stay time of the pet in the dangerous area is greater than the first set time, the pet care service generates an alarm message; Step S402, when the abnormal movement time of the pet is greater than the second set time, the pet care service generates an alarm message.

[0046] Specifically, the pet care service obtains the analysis results from the artificial intelligence cloud service, updates and accumulates the analysis results for data statistics, and compares the duration of all behaviors with the user configuration information (for example, if the user configures that the stay time in the dangerous area is greater than 10s, an alarm will be issued; if the pet abnormal movement time is greater than 30s, an alarm will be issued; if the howling sound duration is greater than 30s, an alarm will be issued); if the alarm condition is met, an abnormal alarm will be pushed to the APP, such as not appearing for a long time, continuous howling, foreign object collision, and dangerous stay.

[0047] Further, the method further includes the following steps: Step S501, the pet care service counts the time period of the pet's feeding on the current day, the number of feedings, the amount of food eaten, the amount of water intake, the number of excretions of the pet, the time spent in dangerous areas, the duration of lying down for a long time, the duration of not appearing for a long time, and the duration of abnormal movements to obtain statistical data; Step S502, the pet care service generates a daily report from the statistical data and pushes it to the mobile client at a set time on the next day.

[0048] Specifically, the pet care service will count and integrate the data at zero o'clock every day, count the time period of the pet's feeding on the current day, the number of feedings, the amount of food eaten, the amount of water intake, the number of excretions of the pet, the time spent in dangerous areas, the duration of lying down for a long time, the duration of not appearing for a long time, and the duration of abnormal movements, generate a daily report, and push it to the mobile client at the user-set time on the next day for the user to view conveniently.

[0049] Furthermore, the method further includes the following steps: Step S601, the pet care service extracts video segments of multiple different behaviors within a set time; Step S602, the pet care service integrates each video segment of different behaviors to obtain integrated data; Step S603, the pet care service sends the integrated data to the mobile client.

[0050] Specifically, the pet care service extracts video segments of each different behavior at zero o'clock every day, integrates them through ffmpeg to obtain integrated data; if it exceeds five minutes, it will be processed by multiples and then pushed to the user.

[0051] Furthermore, the method further includes the following steps: Step S701, the pet care service counts the daily food intake, the number of feedings, the feeding time period of the pet, the weekly excretion times, and the daily activity conditions of the pet to obtain the pet's daily statistical data; Step S702, the pet care service performs interval value taking and averaging on the pet's daily statistical data to obtain the normal daily routine reference data; Step S703, the pet care service determines whether the pet's current daily routine is abnormal according to the normal daily routine reference data; Step S704, if so, it determines that there is a monitoring risk for the pet, generates difference information, and marks the abnormal days in the weekly report or daily report; among them, the difference information includes the difference between the pet's daily routine on the current day and the daily routine in other time periods.

[0052] Specifically, the pet care service generates weekly and monthly reports. It counts the amount and frequency of food intake, the time periods of daily feeding, the weekly excretion frequency, and the daily activities of the pet, and takes interval values and calculates the average of the statistical results as a reference for normal daily routines. If there are obvious differences in the pet's daily routine on a certain day or during a certain period compared to the normal routine, it is determined that there is a monitoring risk for the pet, and the abnormal day is marked in the weekly or daily report, along with the differences in the daily routine on that day compared to other time periods. (For example, in the case of an abnormal day, the number of feeding times on that day is less than the usual number of times, and the weekly excretion situation is less than the usual weekly excretion frequency).

[0053] Refer to Figure 7 , the user query APP requests the pet behavior statistical data of a certain day or all days from the pet care service, including information such as the number of feeding times (amount of food), excretion frequency, duration of lying down, activity duration, and duration of not appearing in the activity area.

[0054] The pet care service returns the pet's daily behavior statistical times according to the APP request through the database. The mobile client displays the pie chart statistical data for the user to observe, and the user can click on a certain behavior to find the segment playback.

[0055] This application combines an intelligent camera and AI behavior analysis, which can provide real-time feedback on the abnormal or high-risk behaviors of the pet and promptly push them to the pet owner for immediate handling. At the same time, the system facilitates the owner to query the pet's daily activities, comprehensively understand the pet's living status, helps to promptly discover potential health risks or abnormal living conditions, and provides a more efficient and convenient care plan.

[0056] Embodiment 2: Figure 8 It is a schematic diagram of an AI intelligent pet care system based on the Internet of Things provided in Embodiment 2 of the present invention.

[0057] Refer to Figure 8 , applied to the pet care service, the system includes: An acquisition module, used for the pet care service to obtain user configuration information from the database, send the user configuration information to the mobile client, so that the mobile client can call the interface of the intelligent pet feeder according to the user configuration information and trigger the feeding operation of the intelligent pet feeder; A feeding result receiving module, used for the pet care service to receive the feeding result of the intelligent pet feeder and send the feeding result to the mobile client, so that the mobile client can display the feeding result; An alarm information receiving module, used for when the intelligent pet feeder detects abnormal feeding of the pet, the pet care service receives the alarm information sent by the intelligent pet feeder and sends the alarm information to the mobile client; A video information receiving module, which is used for the pet care service to receive the video information sent by the intelligent pet feeder. The video information includes the diet video information of the pet and the overall video information when the pet appears; A combination module, which is used for the pet care service to combine the video information, alarm information and user configuration information to obtain request parameters; A sending module, which is used for the pet care service to send the request parameters to the artificial intelligence cloud service, so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result; A statistics module, which is used for the pet care service to count the duration of all behaviors of the pet according to the analysis result; A comparison module, which is used for the pet care service to compare the duration with the user configuration information to obtain a comparison result.

[0058] An embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the AI intelligent pet care method based on the Internet of Things provided in the above embodiment are implemented.

[0059] An embodiment of the present invention further provides a computer-readable medium having non-volatile program code executable by a processor. A computer program is stored on the computer-readable medium. When the computer program is run by the processor, the steps of the AI intelligent pet care method based on the Internet of Things in the above embodiment are executed.

[0060] The computer program product provided by the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the foregoing method embodiment. For specific implementation, reference can be made to the method embodiment, which will not be elaborated here.

[0061] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems and devices can refer to the corresponding processes in the foregoing method embodiments, which will not be elaborated here.

[0062] In addition, in the description of the embodiments of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0063] If the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0064] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0065] Finally, it should be noted that the above-mentioned embodiments are only specific implementation manners of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or make equivalent replacements for some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An AI intelligent pet care method based on the Internet of Things, characterized in that, Applied to pet care services, the method includes: The pet care service obtains user configuration information from a database, sends the user configuration information to a mobile client, so that the mobile client calls an interface of an intelligent pet feeder according to the user configuration information, and triggers a feeding operation of the intelligent pet feeder; The pet care service receives an eating result of the intelligent pet feeder, and sends the eating result to the mobile client, so that the mobile client displays the eating result; When the intelligent pet feeder detects that a pet has an abnormal eating situation, the pet care service receives an alarm message sent by the intelligent pet feeder, and sends the alarm message to the mobile client; The pet care service receives video information sent by the intelligent pet feeder, where the video information includes eating video information of the pet and overall video information when the pet appears; The pet care service combines the video information, the alarm message, and the user configuration information to obtain request parameters; The pet care service sends the request parameters to an artificial intelligence cloud service, so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result; The pet care service counts the duration of all behaviors of the pet according to the analysis result; The pet care service compares the duration with the user configuration information to obtain a comparison result.

2. The AI intelligent pet care method based on the Internet of Things according to claim 1, characterized in that When the intelligent pet feeder detects that a pet has an abnormal eating situation, the pet care service receives an alarm message sent by the intelligent pet feeder, and sends the alarm message to the mobile client, including: When the pet enters the next feeding time, the intelligent pet feeder generates an alarm message that the pet has not eaten for a long time after detecting that the food intake has not changed and the pet has not eaten, and the pet care service receives the alarm message that the pet has not eaten for a long time sent by the intelligent pet feeder; The pet care service sends a first reminder message to the mobile client and pops up a window; When the intelligent pet feeder detects that the food volume in the top food bowl is less than the user-set capacity, the pet care service receives an alarm message of insufficient food storage sent by the intelligent pet feeder; The pet care service sends a second reminder message to the mobile client and pops up a window.

3. The AI intelligent pet care method based on the Internet of Things according to claim 1, wherein The pet care service sends the request parameters to an artificial intelligence cloud service, so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result, including: The pet care service sends the request parameters to an artificial intelligence cloud service, so that the artificial intelligence cloud service performs frame extraction analysis on the video in the request parameters; Judge whether the pet is in an excretion area set by the user; If it is in the excretion area and stays for a long time, it is determined that the pet is excreting; Judge whether the pet is in a dangerous area; If the pet is in the dangerous area, return the staying time; Analyze the current behavior of the pet and perform time statistics on the current behavior; Judge whether there is abnormal sound in the audio in the video; If there is such abnormal sound, determine the type and duration of the abnormal sound, and obtain the link of the corresponding video clip.

4. The AI intelligent pet care method based on the Internet of Things according to claim 1, characterized in that The pet care service compares the duration with the user configuration information to obtain a comparison result, including: When the staying time of the pet in the dangerous area is greater than the first set time, the pet care service generates an alarm message; When the abnormal movement time of the pet is greater than the second set time, the pet care service generates the alarm message.

5. The AI intelligent pet care method based on the Internet of Things according to claim 1, characterized in that, The method further includes: The pet care service counts the time period of the pet's daily feeding, the number of feeding times, the amount of food eaten, the amount of water intake, the number of excretion times, the staying time in the dangerous area, the long lying time, the long absence time, and the abnormal movement time of the pet to obtain statistical data; The pet care service generates a daily report based on the statistical data and pushes it to the mobile client at a set time on the next day.

6. The AI intelligent pet care method based on the Internet of Things according to claim 1, characterized in that The method further includes: The pet care service extracts video clips of multiple different behaviors within a set time; The pet care service integrates each of the video clips of different behaviors to obtain integrated data; The pet care service sends the integrated data to the mobile client.

7. The AI intelligent pet care method based on the Internet of Things according to claim 1, characterized in that The method further includes: The pet care service counts the daily food intake, the number of feeding times, the feeding time period, the weekly excretion times, and the daily activity of the pet to obtain pet daily statistical data; The pet care service performs interval value taking and averaging on the pet daily statistical data to obtain normal schedule reference data; The pet care service determines whether there is an abnormality in the current schedule of the pet according to the normal schedule reference data; If so, determine that there is a monitoring risk for the pet, generate difference information, and mark the abnormal day in the weekly report or daily report; wherein, the difference information includes the difference in the pet's schedule on the current day compared with the schedule in other time periods.

8. The AI intelligent pet care method based on the Internet of Things according to claim 1, characterized in that The user configuration information includes: marked dangerous areas, alarm information for the staying time in the dangerous area, marked excretion areas, set types of the pet, the food output of the intelligent pet feeder, the food output time, the frequency, set alarm time periods, alarm information for the long absence of the pet, alarm information for the feeding frequency of the pet, set feeding time periods of the pet, alarm information for the non-feeding of the pet, alarm information for the abnormal state of the pet itself, alarm information for the abnormal state of the pet to the outside world, set audio reminder information, and set alarm voice broadcast content information.

9. An AI intelligent pet care system based on the Internet of Things, characterized in that, Applied to the pet care service, the system includes: An acquisition module, configured to enable the pet care service to acquire user configuration information from a database, send the user configuration information to a mobile client, so that the mobile client calls an interface of an intelligent pet feeder according to the user configuration information, and trigger a feeding operation of the intelligent pet feeder; A feeding result receiving module, configured to enable the pet care service to receive the feeding result of the intelligent pet feeder and send the feeding result to the mobile client, so that the mobile client displays the feeding result; An alarm information receiving module, configured to, when the intelligent pet feeder monitors that the pet has abnormal eating, the pet care service receives the alarm information sent by the intelligent pet feeder and sends the alarm information to the mobile client; A video information receiving module, configured to the pet care service receives the video information sent by the intelligent pet feeder, where the video information includes the diet video information of the pet and the overall video information when the pet appears; A combination module, configured to the pet care service combines the video information, the alarm information, and the user configuration information to obtain request parameters; A sending module, configured to the pet care service sends the request parameters to the artificial intelligence cloud service, so that the artificial intelligence cloud service performs AI analysis on the request parameters to obtain an analysis result; A statistics module, configured to the pet care service statistics the duration of all behaviors of the pet according to the analysis result; A comparison module, configured to the pet care service compares the duration with the user configuration information to obtain a comparison result.

10. An electronic device, comprising a memory and a processor, wherein a computer program capable of running on the processor is stored on the memory, characterized in that When the processor executes the computer program, it implements the method according to any one of claims 1 to 8 above.

Images