Pet status monitoring method, apparatus and device

Abstract

This application relates to the field of pet monitoring technology, and in particular to a pet status monitoring method, apparatus, and device. The method includes: acquiring pet monitoring information, wherein the monitoring information includes surveillance video and / or usage data from sensors in pet equipment; identifying pet behavior from the monitoring information, and obtaining corresponding behavioral status information based on the identified pet behavior; summarizing pet status information based on the pet behavior and the corresponding behavioral status information; converting the pet status information into text form, and generating a user reminder based on the text-based pet status information. The method of this application can solve the technical problem in existing pet status monitoring methods that are inconvenient for summarizing pet status and for pet owners to quickly understand the pet's status over a long period.

Description

Technical Field

[0001] This application relates to the field of pet monitoring technology, and in particular to a method, device and equipment for monitoring pet status. Background Technology

[0002] Existing pet status monitoring methods typically use monitoring devices such as cameras to monitor various behaviors of pets. Pet owners receive the transmitted monitoring information through corresponding terminals to check the status of their pets.

[0003] Therefore, existing pet condition monitoring methods only provide a visual monitoring and recording of a pet's condition through video. Pet care depends on the pet owner's attention to the monitoring information. Pet owners need to load all the pet monitoring videos and review them one by one to determine the pet's condition, which is cumbersome and time-consuming. It is not convenient for pet owners to quickly understand the pet's condition over a period of time or over a long period of time. Summary of the Invention

[0004] The main purpose of this application is to provide a pet condition monitoring method, device, and equipment, which aims to solve the technical problem that existing pet condition monitoring methods are not convenient for summarizing the pet's condition or for pet owners to quickly understand the pet's condition over a long period of time.

[0005] To achieve the aforementioned objectives, this application proposes a pet condition monitoring method, the method comprising:

[0006] Acquire monitoring information of the pet, wherein the monitoring information includes surveillance video and / or usage data of sensors in pet supplies;

[0007] The monitoring information is used to identify pet behavior, and the corresponding behavior status information is obtained based on the identified pet behavior. Pet status information is then obtained by summarizing the pet behavior and the corresponding behavior status information.

[0008] Convert the pet status information into text format.

[0009] User reminders are generated based on textual information about the pet's status.

[0010] Furthermore, when the monitoring information includes surveillance video, the steps of performing pet behavior recognition on the monitoring information, obtaining corresponding behavior status information based on the recognized pet behavior, and summarizing pet status information based on the pet behavior and the corresponding behavior status information include:

[0011] The pet's status frames are captured in the surveillance video.

[0012] The first frame of the state frame is set as the first initial state frame. The similarity between the first initial state frame and the remaining state frames is calculated according to the preset state frame similarity analysis rules to obtain the key frames of the pet's state change.

[0013] The pet's behavior is obtained by identifying the first initial state frame and the state change key frames;

[0014] Based on the time corresponding to the first initial state frame and the time corresponding to the state change key frame, determine the duration of each behavior state corresponding to the pet behavior.

[0015] The first pet status information is obtained based on the pet's behavior and the duration of the behavior state.

[0016] Further, the step of setting the first frame of the state frames as the first initial state frame, and calculating the similarity between the first initial state frame and the remaining state frames according to a preset state frame similarity analysis rule to obtain the key frames of the pet's state change includes:

[0017] Starting from the first initial state frame, calculate the similarity between two adjacent state frames;

[0018] Determine whether the similarity is higher than a first preset threshold;

[0019] If the similarity is lower than the first preset threshold, then the next state frame in the adjacent state frames is taken as the key frame for the pet's state change.

[0020] Further, the step of setting the first frame of the state frames as the first initial state frame, and calculating the similarity between the first initial state frame and the remaining state frames according to a preset state frame similarity analysis rule to obtain the key frames of the pet's state change includes:

[0021] Calculate the first similarity between the first initial state frame and state frames separated by a preset number of frames;

[0022] Determine whether the first similarity is higher than a second preset threshold;

[0023] If the first similarity is lower than the second preset threshold, then the state frames of the previous frame are obtained sequentially based on the state frames separated by a preset number of frames.

[0024] The second similarity between the first initial state frame and the previous state frame is calculated sequentially. Until the second similarity is higher than the third preset threshold, the first intermediate change frame is obtained by pushing forward one frame based on the current previous state frame. The first intermediate change frame is used as the first state change key frame of the pet.

[0025] And / or,

[0026] The third similarity between the state frame separated by a preset number of frames and the state frame of the previous frame is calculated sequentially. Until the third similarity is lower than the fourth preset threshold, the state frame of the previous frame is used as the reference, and the second intermediate change frame is obtained by pushing forward one frame. The second intermediate change frame is used as the second state change key frame of the pet.

[0027] Furthermore, when the first state change keyframe and the second state change keyframe are obtained, after the steps of using the first intermediate change frame as the pet's first state change keyframe and the second intermediate change frame as the pet's second state change keyframe, the method further includes:

[0028] Compare the first state change keyframe with the second state change keyframe;

[0029] When the first state change keyframe and the second state change keyframe are the same frame, the second state change keyframe is set as the first state change keyframe.

[0030] When the first state change keyframe and the second state change keyframe are not the same frame, a similarity calculation is performed on the first state change keyframe and the second state change keyframe to obtain the calculation result.

[0031] Based on the calculation results, it is determined whether there is a pet's state change keyframe between the first state change keyframe and the second state change keyframe.

[0032] Further, after the step of "if the first similarity is higher than the second preset threshold", the following steps are included:

[0033] Obtain the frame following the state frame that is separated by a preset number of frames;

[0034] The next frame is set as the second initial state frame. The similarity between the second initial state frame and the state frames after the second initial state frame is calculated according to the preset state frame similarity analysis rules. Based on the calculation results, it is determined whether there is a key frame between the second initial state frame and the state frames after the second initial state frame.

[0035] Furthermore, when the monitoring information includes usage data from sensors in pet supplies, the steps of identifying pet behavior in the monitoring information, obtaining corresponding behavioral status information based on the identified pet behavior, and summarizing pet status information based on the pet behavior and the corresponding behavioral status information include:

[0036] The pet behavior is determined based on the type of pet supplies;

[0037] The duration of each pet behavior state is determined based on the usage data.

[0038] The second pet status information is obtained based on the pet's behavior and the duration of the behavior state.

[0039] Furthermore, when pet supplies are included, the step of summarizing the pet status information based on the pet's behavior and the corresponding behavior status information, after which the steps include:

[0040] Obtain environmental information about the pet's surroundings;

[0041] Based on the environmental information, obtain the preset reminder rules corresponding to the environmental information;

[0042] Determine whether the pet behavior recorded in the pet status database and the duration of the corresponding behavior status meet the requirements of the reminder items in the preset reminder rules;

[0043] If not, control the generation of reminder messages for the corresponding pet supplies.

[0044] This application also provides a pet condition monitoring device, the device comprising:

[0045] The acquisition module is used to obtain real-time monitoring videos of pets and usage data of sensors in pet supplies;

[0046] The first pet status determination module is used to perform similarity analysis on the surveillance video to determine the first pet status information;

[0047] The third pet status determination module is used to determine the third pet status information based on the usage data.

[0048] The pet status sending module is used to generate text information about the pet's status based on the first pet status information and the third pet status information, and send it to the pet owner's terminal. The acquisition module is used to acquire the pet's monitoring information, wherein the monitoring information includes surveillance video and / or usage data from sensors in pet equipment.

[0049] The status determination module is used to identify pet behavior in the monitoring information, obtain corresponding behavior status information based on the identified pet behavior, and summarize the pet status information according to the pet behavior and the corresponding behavior status information.

[0050] The information conversion module is used to convert the pet status information into text format.

[0051] The reminder module is used to generate user reminders based on textual information about the pet's status.

[0052] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described above.

[0053] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0054] This application provides a pet status monitoring method that acquires pet monitoring information and extracts pet behavior, while further obtaining specific behavioral status data. After summarizing and organizing the pet behavior and specific behavioral status data into pet status information, the pet status information is converted into text information and recorded. Thus, more convenient text information replaces time-consuming and space-consuming video information, allowing owners to quickly understand their pet's status based on the text. It also allows owners to view only the parts they need, helping them to understand the pet's activities more specifically. Overall, it provides convenience for pet owners to monitor their pet's status. Attached Figure Description

[0055] Figure 1 This is a schematic flowchart of a pet status monitoring method according to an embodiment of this application;

[0056] Figure 2 This is a schematic block diagram of a pet status monitoring device according to an embodiment of this application;

[0057] Figure 3 This is a schematic block diagram of the structure of a computer device according to an embodiment of this application.

[0058] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this specification means the presence of features, integers, steps, operations, elements, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any modules and all combinations of one or more associated listed items.

[0061] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0062] Reference Figure 1 This invention provides a pet status monitoring method, including steps S1-S3, specifically:

[0063] S1. Obtain monitoring information of the pet, wherein the monitoring information includes monitoring videos and / or usage data of sensors in pet supplies;

[0064] S2. Perform pet behavior recognition on the monitoring information, and obtain corresponding behavior status information based on the recognized pet behavior. Summarize the pet status information based on the pet behavior and the corresponding behavior status information.

[0065] S3. Convert the pet status information into text form, and generate a user reminder based on the text-based pet status information.

[0066] Surveillance cameras are installed in the pet's activity area to capture video recordings of the pet. Each frame of the video is treated as a pet status frame, used to analyze the pet's condition. The current pet state can be identified, and by analyzing the similarity between status frames, it can be determined whether the pet's state has changed. Furthermore, based on the time corresponding to each status frame, the duration of each pet state can be determined, thus identifying the pet's status information. Alternatively, usage data from sensors in pet equipment can be used to determine pet status information based on the type of equipment and its usage duration, automatically summarizing the pet's state over a long period. The obtained pet status information is then used to generate corresponding textual information for each pet state. Different pet status information can be categorized and generated into different textual descriptions. These categories can be further summarized into corresponding textual directories, and hyperlinks can be generated between the directories and corresponding videos, allowing pet owners to quickly understand their pet's state over a long period.

[0067] As mentioned above, by acquiring pet monitoring information and extracting pet behavior, and further obtaining specific behavioral status data, the pet behavior and specific behavioral status data are summarized and organized into pet status information. This pet status information is then converted into text information records. Thus, more convenient text information replaces time-consuming and space-consuming video information, allowing owners to quickly understand their pet's status based on the text. It also allows owners to view only the parts they need, helping them to understand their pet's activities more specifically. Overall, it provides convenience for pet owners to monitor their pet's status.

[0068] In one embodiment, the steps of identifying pet behavior from the monitoring information, obtaining corresponding behavior status information based on the identified pet behavior, and summarizing pet status information based on the pet behavior and the corresponding behavior status information include:

[0069] S201. Obtain the pet's status frame from the surveillance video;

[0070] S202. Set the first frame of the state frame as the first initial state frame, and calculate the similarity between the first initial state frame and the remaining state frames according to the preset state frame similarity analysis rules to obtain the key frames of the pet's state change.

[0071] S203. Identify the first initial state frame and the state change key frame to obtain pet behavior;

[0072] S204. Determine the duration of each behavior state corresponding to the pet behavior based on the time corresponding to the first initial state frame and the time corresponding to the state change key frame.

[0073] S205. Based on the pet's behavior and the duration of the behavior state, obtain the first pet state information.

[0074] In some embodiments, the preset state frame similarity analysis rule may include at least two similarity calculation methods. For example, one method is to calculate the similarity between two adjacent state frames and determine whether the similarity is higher than a first preset threshold. If the similarity is lower than the first preset threshold, the second state frame is used as the key frame for the pet's state change. If the similarity is higher than the first preset threshold, the similarity between the second state frame and the next state frame is calculated, and it is determined whether the similarity is higher than the first preset threshold. The above steps are repeated until the similarity between two consecutive frames is lower than the first threshold.

[0075] Second, calculate the first similarity between the first initial state frame and state frames separated by a preset number of frames, and determine whether the first similarity is higher than a second preset threshold. If the first similarity is higher than the second preset threshold, calculate the first similarity between state frames separated by a preset number of frames and state frames separated by twice the preset number of frames. Repeat the above steps until the first similarity is lower than the second preset threshold.

[0076] When the first similarity is lower than the second preset threshold, taking the example that the first similarity between the first initial state frame and a state frame separated by a preset number of frames is lower than the second preset threshold, the second similarity between the first initial state frame and a state frame separated by a preset number of frames is further calculated to determine whether the second similarity is higher than the second preset threshold. If the second similarity is higher than the second preset threshold, the state frame separated by a preset number of frames is taken as the key frame for the pet's state change. The first preset threshold and the second preset threshold can be the same or different, and their specific values ​​can be set according to the actual situation. The specific value of the preset number of frames can be set according to the actual situation. The first initial state frame is the first state frame from which similarity calculation begins.

[0077] By performing similarity calculations based on preset state frame similarity analysis rules, state frames can be processed automatically to identify key frames of pet state changes, thereby determining the duration of each pet state.

[0078] By extracting the first initial state frame or key frame of state change of the pet from the surveillance video, and performing image recognition on the frame image based on a deep neural network, the corresponding pet state in a segment of surveillance video can be identified.

[0079] The duration of each pet state can be obtained by subtracting the time of the first state frame from the time of the keyframe corresponding to the state change of a certain state, from the time of the first state frame for which similarity calculation begins. Alternatively, the duration of each pet state can be obtained by calculating the number of frames between the keyframe corresponding to the state change of a certain state and the first state frame for which similarity calculation begins, and then multiplying the number of frames by the time of each frame.

[0080] Recording pet status and its duration in a pet status database creates a historical record, allowing owners to easily monitor their pets' daily activities and habit changes. The data in the pet status database can also be used to analyze pet needs, generating reminders for appropriate pet items (e.g., reminders for feeding, watering, etc.) to help owners promptly address their pets' needs and improve their quality of life.

[0081] In one embodiment, the step of setting the first frame of the state frames as the first initial state frame, and calculating the similarity between the first initial state frame and the remaining state frames according to a preset state frame similarity analysis rule to obtain the key frames of the pet's state change includes:

[0082] S208. Starting from the first initial state frame, calculate the similarity between two adjacent state frames.

[0083] S209. Determine whether the similarity is higher than a first preset threshold;

[0084] S210. If the similarity is lower than the first preset threshold, then the next state frame in the adjacent state frames is taken as the key frame for the pet's state change.

[0085] Assuming the initial state frame is 'a' and its adjacent state frame is 'a+1', first calculate the similarity between 'a' and 'a+1', and determine if the similarity is higher than a first preset threshold. If the similarity is lower than the first preset threshold, then 'a+1' is taken as the key frame for the pet's state change. The pet is in the same state from 'a' to 'a+1'. If the similarity is higher than the first preset threshold, calculate the similarity between 'a+1' and 'a+2', and determine if this similarity is higher than the first preset threshold. Repeat the above steps until the similarity between two consecutive frames is lower than the first threshold. Assuming the final calculated similarity between 'a+4' and 'a+5' is lower than the first threshold, then 'a+5' is taken as the key frame for the pet's state change, and the pet is in the same state from 'a' to 'a+5'. By calculating similarity frame by frame using this method, the similarity between each frame can be more accurately quantified and compared, improving the accuracy of judging pet state changes. The specific value of the first preset threshold can be set according to the actual situation.

[0086] In one embodiment, the step of setting the first frame of the state frames as the first initial state frame, and calculating the similarity between the first initial state frame and the remaining state frames according to a preset state frame similarity analysis rule to obtain the key frames of the pet's state change includes:

[0087] S211. Calculate the first similarity between the first initial state frame and state frames separated by a preset number of frames;

[0088] S212. Determine whether the first similarity is higher than the second preset threshold;

[0089] S213. If the first similarity is lower than the second preset threshold, then the state frames of the previous frame are obtained sequentially based on the state frames separated by a preset number of frames.

[0090] S214. Calculate the second similarity between the first initial state frame and the previous state frame in sequence. Until the second similarity is higher than the third preset threshold, take the current previous state frame as the benchmark, push one frame forward to obtain the first intermediate change frame, and take the first intermediate change frame as the first state change key frame of the pet.

[0091] And / or,

[0092] The third similarity between the state frame separated by a preset number of frames and the state frame of the previous frame is calculated sequentially. This process continues until the third similarity falls below a fourth preset threshold. Then, using the current state frame of the previous frame as a reference, one frame is pushed forward to obtain a second intermediate change frame. This second intermediate change frame is used as the key frame for the pet's second state change. Assuming the preset number of frames is b, the first similarity between the first initial state frame 1 and 1+b is calculated. It is then determined whether the first similarity is higher than a second preset threshold. If the first similarity is higher than the second preset threshold, the first similarity between 1+b and 1+2b is calculated. The above steps are repeated until the first similarity falls below the second preset threshold.

[0093] If the first similarity is lower than the second preset threshold, then the second similarity between a certain state frame 1 and the state frame of b is further calculated to determine whether the second similarity is higher than the third preset threshold. If the second similarity is higher than the third preset threshold, it means that the state of state frame 1 is similar to the state of state frame b. In this case, taking the state frame of the previous frame of b as the reference, one frame is pushed forward to obtain the first intermediate change frame b+1, and the first intermediate change frame b+1 is used as the first state change key frame of the pet. Otherwise, b is replaced with b-1, and the above similarity calculation and threshold comparison are repeated until the second similarity is higher than the third preset threshold.

[0094] A third similarity can be calculated between b+1 and b. If the third similarity is lower than a fourth preset threshold, using state frame b as a reference, push forward one frame to obtain the second intermediate change frame b+1, and use the second intermediate change frame b+1 as the key frame for the pet's second state change. Otherwise, continue to replace b with b-1, and repeat the above similarity calculation and threshold comparison until the third similarity is higher than the fourth preset threshold. Here, 1...b-2, b-1, b, 1+b, and 1+2b are all frame numbers.

[0095] Since the monitored target may remain in a state unchanged for a long period, such as when a pet is sleeping, the state between video frames is basically the same, so there is no need to calculate similarity frame by frame. The similarity calculation method in this embodiment can save computing resources and improve the efficiency of filtering key frames of pet state changes. When a change is detected between the initial state frame and state frames separated by a preset number of frames, then the similarity calculation is performed frame by frame to accurately determine the key frames of state changes and ensure the accuracy of the final pet state record.

[0096] The first, second, third, and fourth preset thresholds can be the same or different, and their specific values ​​can be set according to the actual situation. The specific value of the preset frame interval can also be set according to the actual situation.

[0097] In one embodiment, after the steps of using the first intermediate change frame as the pet's first state change keyframe and the second intermediate change frame as the pet's second state change keyframe when the first state change keyframe and the second state change keyframe are obtained, the method further includes:

[0098] S215. Compare the first state change keyframe and the second state change keyframe.

[0099] S216. When the first state change key frame and the second state change key frame are the same frame, set the second state change key frame as the first state change key frame.

[0100] S217. When the first state change keyframe and the second state change keyframe are not the same frame, perform similarity calculation on the first state change keyframe and the second state change keyframe to obtain the calculation result.

[0101] S218. Based on the calculation results, determine whether there is a pet's state change keyframe between the first state change keyframe and the second state change keyframe.

[0102] Compare the first state change keyframe and the second state change keyframe. For example, in the embodiments of steps S211 to S214, if the first state change keyframe and the second state change keyframe are the same frame b, then set the first state change keyframe or the second state change keyframe as the first state change keyframe, which is b.

[0103] When the first state change keyframe and the second state change keyframe are not the same frame, it indicates that there may be other state changes between the first state change keyframe and the second state change keyframe. Therefore, a similarity calculation is performed on the first state change keyframe and the second state change keyframe, executing the similarity calculation method as described in steps S208 to S210, or executing the similarity calculation method as described in steps S211 to S217, to obtain the calculation result. Based on the calculation result, it can be determined whether there is a pet state change keyframe between the first state change keyframe and the second state change keyframe. Through this step, other state change keyframes between the first state change keyframe and the second state change keyframe can be accurately identified, improving the accuracy of pet state changes. In one embodiment, after the step of "if the first similarity is higher than the second preset threshold", the following is included:

[0104] S219. Obtain the next frame of the state frame that is separated by a preset number of frames;

[0105] S220. Set the next frame as the second initial state frame, calculate the similarity between the second initial state frame and the state frames after the second initial state frame according to the preset state frame similarity analysis rules, and determine whether there is a key frame between the second initial state frame and the state frames after the second initial state frame based on the calculation results.

[0106] Once a state change keyframe is determined, the frame following that keyframe is obtained. This following frame is set as the second initial state frame, which represents the start time of the pet's next state. Starting from the second initial state frame, the similarity calculation method as described in steps S208 to S210, or the similarity calculation method as described in steps S211 to S217, is executed to obtain keyframes. The period between the second initial state frame and the keyframes represents the pet's next state.

[0107] In one embodiment, when the monitoring information includes usage data from sensors in pet supplies, the steps of identifying pet behavior in the monitoring information, obtaining corresponding behavioral status information based on the identified pet behavior, and summarizing pet status information based on the pet behavior and the corresponding behavioral status information include:

[0108] S301. Determine the pet behavior based on the type of the pet supplies;

[0109] S302. Determine the duration of each behavioral state corresponding to the pet's behavior based on the usage data;

[0110] S303. Obtain the second pet status information based on the pet's behavior status and the duration of the behavior status.

[0111] Pet supplies such as beds, feeders, water containers, and toys can be equipped with corresponding sensors. These sensors detect whether the pet is using the corresponding supplies and time the usage. Pet behavior can be determined based on the type of pet supply. The duration of the pet's status is determined based on the timing data from the sensors corresponding to the pet supplies, resulting in a second pet status duration. This method of obtaining pet status information is more direct than the similarity analysis method used in surveillance video, and can serve as another source of pet status information.

[0112] In one embodiment, when the monitoring information includes pet supplies, the step of summarizing the pet status information based on the pet behavior and the corresponding behavior status information, after which the following steps are included:

[0113] S601. Obtain environmental information about the pet's surroundings;

[0114] S602. Based on the environmental information, obtain the preset reminder rule corresponding to the environmental information;

[0115] S603. Determine whether the pet behavior and the corresponding duration of the behavior status recorded in the pet status database meet the requirements of the reminder items in the preset reminder rules;

[0116] S604. If not, control the generation of reminder information for the corresponding pet supplies.

[0117] When reminding pets based on their status, environmental conditions can also be considered. For example, if the current ambient temperature is higher than a specific temperature, a preset reminder rule can be implemented: the pet must drink water at least once within two hours, with each drink lasting more than 10 seconds. If no drinking status is found in the pet status database for the past two hours, or if a drinking status is found but the drinking duration is less than 10 seconds, the indicator light on the water container will flash, or a sound will be used to attract the pet's attention. Alternatively, the water container can activate or enhance a water spray effect to create a water flow sound, or use electronic controls to generate an electronic sound or play a drinking prompt voice message. This serves as a drinking reminder to attract the pet's attention, guiding it to perform the corresponding behavior, helping the owner promptly address the pet's needs, and improving the pet's quality of life.

[0118] Reference Figure 2 This is a structural block diagram of a pet status monitoring device according to an embodiment of this application. The device includes:

[0119] The acquisition module 100 is used to acquire monitoring information of the pet, wherein the monitoring information includes monitoring videos and / or usage data of sensors in pet supplies;

[0120] The status determination module 200 is used to identify pet behavior in the monitoring information, obtain corresponding behavior status information based on the identified pet behavior, and summarize the pet status information according to the pet behavior and the corresponding behavior status information.

[0121] The reminder module 300 is used to convert the pet status information into text form and generate a user reminder based on the text-based pet status information. In one embodiment, the above-mentioned pet status monitoring device further includes:

[0122] The first pet status determination submodule is used to acquire pet status frames from the surveillance video; set the first frame of the status frames as the first initial status frame; calculate the similarity between the first initial status frame and the remaining status frames according to a preset status frame similarity analysis rule to obtain key frames of pet status changes; identify the first initial status frame and the key frames of status changes to obtain pet behavior; determine the duration of each behavior state corresponding to the pet behavior based on the time corresponding to the first initial status frame and the time corresponding to the key frames of status changes; and obtain the first pet status information based on the pet behavior and the duration of the behavior state.

[0123] In one embodiment, the pet status monitoring device further includes:

[0124] The first similarity calculation module is used to calculate the similarity between two adjacent state frames starting from the first initial state frame; determine whether the similarity is higher than a first preset threshold; if the similarity is lower than the first preset threshold, then the next state frame in the adjacent state frames is taken as the key frame of the pet's state change.

[0125] In one embodiment, the pet status monitoring device further includes:

[0126] The second similarity calculation module is used to calculate a first similarity between the first initial state frame and state frames separated by a preset number of frames; determine whether the first similarity is higher than a second preset threshold; if the first similarity is lower than the second preset threshold, then based on the state frames separated by the preset number of frames, sequentially obtain the state frames of the previous frame; sequentially calculate a second similarity between the first initial state frame and the state frames of the previous frame; until the second similarity is higher than a third preset threshold, based on the current state frames of the previous frame, push forward one frame to obtain a first intermediate change frame, and use the first intermediate change frame as the first state change key frame of the pet; and / or, sequentially calculate a third similarity between the state frames separated by the preset number of frames and the state frames of the previous frame; until the third similarity is lower than a fourth preset threshold, based on the current state frames of the previous frame, push forward one frame to obtain a second intermediate change frame, and use the second intermediate change frame as the second state change key frame of the pet.

[0127] In one embodiment, the pet status monitoring device further includes:

[0128] The second pet state determination submodule is used to compare the first state change keyframe and the second state change keyframe; when the first state change keyframe and the second state change keyframe are the same frame, the second state change keyframe is set as the first state change keyframe; when the first state change keyframe and the second state change keyframe are not the same frame, a similarity calculation is performed on the first state change keyframe and the second state change keyframe to obtain a calculation result; based on the calculation result, it is determined whether there is a pet state change keyframe between the first state change keyframe and the second state change keyframe.

[0129] In one embodiment, the pet status monitoring device further includes:

[0130] The third pet state determination submodule is used to obtain the next frame after the state frame that is separated by a preset number of frames; set the next frame as the second initial state frame; perform similarity calculation on the second initial state frame and the state frames after the second initial state frame according to the preset state frame similarity analysis rules; and determine whether there is a key frame between the second initial state frame and the state frames after the second initial state frame based on the calculation results.

[0131] In one embodiment, the pet status monitoring device further includes:

[0132] The fourth pet status determination submodule is used to determine the pet behavior based on the type of pet supplies; determine the duration of the behavior status corresponding to each pet behavior based on the usage data; and obtain the second pet status information based on the pet behavior and the duration of the behavior status.

[0133] In one embodiment, the pet status monitoring device further includes:

[0134] The reminder submodule is used to obtain environmental information about the pet's environment; and to obtain the preset reminder rules corresponding to the environmental information.

[0135] Determine whether the pet behavior and the corresponding duration of the behavior recorded in the pet status database meet the requirements of the reminder items in the preset reminder rules; if not, control the corresponding pet supplies to generate reminder information.

[0136] Reference Figure 3 This application also provides a computer device, which may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores usage data during the pet status monitoring method. The network interface communicates with external terminals via a network connection. Furthermore, the computer device may also include input devices and a display screen. When the computer program is executed by the processor to implement the pet status monitoring method, it includes the following steps: acquiring pet monitoring information, wherein the monitoring information includes monitoring videos and / or usage data from sensors in pet equipment; identifying pet behavior based on the monitoring information, and obtaining corresponding behavioral status information based on the identified pet behavior; summarizing pet status information based on the pet behavior and the corresponding behavioral status information; converting the pet status information into text form, and generating user reminders based on the text-based pet status information.

[0137] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer equipment on which the present application is applied.

[0138] One embodiment of this application also provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a pet status monitoring method, including the following steps: acquiring pet monitoring information, wherein the monitoring information includes monitoring videos and / or usage data of sensors in pet equipment; performing pet behavior recognition on the monitoring information, and obtaining corresponding behavior status information based on the recognized pet behavior; summarizing pet status information according to the pet behavior and the corresponding behavior status information; converting the pet status information into text form, and generating a user reminder based on the text-form pet status information. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0139] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media provided in this application and in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAM bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0140] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0141] The above description is only a preferred embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural changes made based on the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for monitoring the condition of a pet, characterized in that, The method includes: Obtain monitoring information of the pet, wherein the monitoring information includes surveillance video; The monitoring information is used to identify pet behavior, and the corresponding behavior status information is obtained based on the identified pet behavior. Pet status information is then obtained by summarizing the pet behavior and the corresponding behavior status information. The pet status information is converted into text, and a user reminder is generated based on the textual pet status information. When the monitoring information includes surveillance video, the steps of performing pet behavior recognition on the monitoring information, obtaining corresponding behavior status information based on the recognized pet behavior, and summarizing pet status information based on the pet behavior and the corresponding behavior status information include: The pet's status frames are captured in the surveillance video. The first frame of the state frame is set as the first initial state frame. The similarity between the first initial state frame and the remaining state frames is calculated according to the preset state frame similarity analysis rules to obtain the key frames of the pet's state change. The pet's behavior is obtained by identifying the first initial state frame and the state change key frames; Based on the time corresponding to the first initial state frame and the time corresponding to the state change key frame, determine the duration of each behavior state corresponding to the pet behavior. The first pet status information is obtained based on the pet's behavior and the duration of the behavior state.

2. The pet status monitoring method according to claim 1, characterized in that, The step of setting the first frame of the state frames as the first initial state frame, and calculating the similarity between the first initial state frame and the remaining state frames according to a preset state frame similarity analysis rule to obtain the key frames of the pet's state change includes: Starting from the first initial state frame, calculate the similarity between two adjacent state frames; Determine whether the similarity is higher than a first preset threshold; If the similarity is lower than the first preset threshold, then the next state frame in the adjacent state frames is taken as the key frame for the pet's state change.

3. The pet status monitoring method according to claim 1, characterized in that, The step of setting the first frame of the state frames as the first initial state frame, and calculating the similarity between the first initial state frame and the remaining state frames according to a preset state frame similarity analysis rule to obtain the key frames of the pet's state change includes: Calculate the first similarity between the first initial state frame and state frames separated by a preset number of frames; Determine whether the first similarity is higher than a second preset threshold; If the first similarity is lower than the second preset threshold, then the state frames of the previous frame are obtained sequentially based on the state frames separated by a preset number of frames. The second similarity between the first initial state frame and the previous state frame is calculated sequentially. Until the second similarity is higher than the third preset threshold, the first intermediate change frame is obtained by pushing forward one frame based on the current previous state frame. The first intermediate change frame is used as the first state change key frame of the pet. And / or, The third similarity between the state frame separated by a preset number of frames and the state frame of the previous frame is calculated sequentially. Until the third similarity is lower than the fourth preset threshold, the state frame of the previous frame is used as the reference, and the second intermediate change frame is obtained by pushing forward one frame. The second intermediate change frame is used as the second state change key frame of the pet.

4. The pet status monitoring method according to claim 3, characterized in that, When the first state change keyframe and the second state change keyframe are obtained, after the steps of using the first intermediate change frame as the pet's first state change keyframe and the second intermediate change frame as the pet's second state change keyframe, the method further includes: Compare the first state change keyframe with the second state change keyframe; When the first state change keyframe and the second state change keyframe are the same frame, the second state change keyframe is set as the first state change keyframe. When the first state change keyframe and the second state change keyframe are not the same frame, a similarity calculation is performed on the first state change keyframe and the second state change keyframe to obtain the calculation result. Based on the calculation results, it is determined whether there is a pet's state change keyframe between the first state change keyframe and the second state change keyframe.

5. The pet status monitoring method according to claim 3, characterized in that, If the first similarity is higher than the second preset threshold, the following steps are included: Obtain the frame following the state frame that is separated by a preset number of frames; The next frame is set as the second initial state frame. The similarity between the second initial state frame and the state frames after the second initial state frame is calculated according to the preset state frame similarity analysis rules. Based on the calculation results, it is determined whether there is a key frame between the second initial state frame and the state frames after the second initial state frame.

6. The pet status monitoring method according to claim 1, characterized in that, The monitoring information also includes usage data from sensors in pet supplies. The steps of identifying pet behavior based on the monitoring information, obtaining corresponding behavioral status information based on the identified pet behavior, and summarizing pet status information based on the pet behavior and the corresponding behavioral status information include: The pet behavior is determined based on the type of pet supplies; The duration of each pet behavior state is determined based on the usage data. The second pet status information is obtained based on the pet's behavior and the duration of the behavior state.

7. The pet condition monitoring method according to claim 1 or 5, characterized in that, When the monitoring information includes pet supplies, the step of summarizing the pet status information based on the pet's behavior and the corresponding behavior status information, after which the following steps are included: Obtain environmental information about the pet's surroundings; Based on the environmental information, obtain the preset reminder rules corresponding to the environmental information; Determine whether the pet behavior recorded in the pet status database and the duration of the corresponding behavior status meet the requirements of the reminder items in the preset reminder rules; If not, control the generation of reminder messages for the corresponding pet supplies.

8. A pet status monitoring device for implementing the pet status monitoring method according to any one of claims 1-7, characterized in that, The device includes: The acquisition module is used to acquire monitoring information of the pet, wherein the monitoring information includes monitoring videos and / or usage data of sensors in pet supplies; The status determination module is used to identify pet behavior in the monitoring information, obtain corresponding behavior status information based on the identified pet behavior, and summarize the pet status information according to the pet behavior and the corresponding behavior status information. The reminder module is used to convert the pet status information into text form and generate user reminders based on the text-based pet status information.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

Images