Pet management method and device for smart community

Abstract

The invention discloses a pet management method for a smart community, and the method comprises the steps: determining a target pet corresponding to video data in the video data corresponding to a target community through employing a pet recognition algorithm; performing feature extraction on the target pet by using a preset extraction model to determine a pet feature vector corresponding to the target pet; encoding the pet feature vector by using a preset encoding algorithm to determine a unique identifier corresponding to the pet feature vector; associating the unique identifier with a resident information base corresponding to the target community to determine a target resident corresponding to the unique identifier; and when it is detected that the target pet has the preset early warning behavior, sending prompt information to the target resident. The invention provides a comprehensive and efficient pet management solution, and the level of community pet management is improved.

Description

Technical Field

[0001] The present application relates to the field of smart communities, and in particular to a pet management method and device for smart communities. Background Art

[0002] With the acceleration of urbanization, more and more people choose to keep pets in the community. However, the existing pet management methods have many shortcomings and are in urgent need of improvement. Traditional pet management methods mainly rely on manual records and management, which is inefficient and prone to errors. For example, the identity information of pets is not fully recorded, making it difficult to achieve accurate management and tracking.

[0003] Secondly, there is a lack of effective means to manage stray pets, which has led to an increasing number of stray pets, which has had a negative impact on the community environment and residents' lives. In addition, existing pet management systems often lack intelligent functions and cannot monitor pet behavior and issue early warnings in a timely manner, resulting in residents being unable to take timely measures when pets get lost or have accidents.

[0004] Application Contents

[0005] The present application provides a pet management method and device for a smart community, which are used to overcome the above-mentioned problems or at least partially solve the problem of low efficiency of the current method of manually recording and managing pets.

[0006] In a first aspect, the present application provides a pet management method for a smart community, comprising:

[0007] Using a pet recognition algorithm, in the video data corresponding to the target community, determine the target pet corresponding to the video data;

[0008] Using a preset extraction model, feature extraction is performed on the target pet to determine a pet feature vector corresponding to the target pet;

[0009] Encoding the pet feature vector using a preset encoding algorithm to determine a unique identifier corresponding to the pet feature vector;

[0010] Associating the unique identifier with the household information database corresponding to the target community to determine the target household corresponding to the unique identifier;

[0011] When the target pet is detected to have a preset warning behavior, a prompt message is sent to the target resident.

[0012] In a second aspect, the present application provides a pet management device for a smart community, including:

[0013] A target pet determination module is configured to determine a target pet corresponding to the video data in the video data corresponding to the target community using a pet recognition algorithm;

[0014] A pet feature vector determination module is configured to perform feature extraction on a target pet using a preset extraction model to determine a pet feature vector corresponding to the target pet;

[0015] A unique identification determination module is configured to encode the pet feature vector using a preset encoding algorithm to determine a unique identification corresponding to the pet feature vector;

[0016] A target resident determination module is configured to associate the unique identifier with a resident information database corresponding to the target community to determine the target resident corresponding to the unique identifier;

[0017] The warning module is configured to send a prompt message to the target resident when it detects that the target pet has a preset warning behavior.

[0018] In a third aspect, the present application provides a readable medium comprising execution instructions. When a processor of an electronic device executes the execution instructions, the electronic device executes any method described in the first aspect.

[0019] In a fourth aspect, the present application provides an electronic device, comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor executes any method described in the first aspect.

[0020] The present application provides a pet management method for a smart community, which uses a pet recognition algorithm to determine the target pet corresponding to the video data in the video data corresponding to the target community; uses a preset extraction model to extract features of the target pet to determine the pet feature vector corresponding to the target pet; uses a preset encoding algorithm to encode the pet feature vector to determine the unique identifier corresponding to the pet feature vector; associates the unique identifier with the resident information database corresponding to the target community to determine the target resident corresponding to the unique identifier; and sends a prompt message to the target resident when a preset warning behavior is detected in the target pet. The present application provides a comprehensive and efficient pet management solution, which improves the level of community pet management.

[0021] The further effects of the above-mentioned non-conventional preferred manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the existing technical solutions, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 A flowchart of a pet management method for a smart community provided in one embodiment of the present application;

[0024] Figure 2 A flowchart of another pet management method for a smart community provided in one embodiment of the present application;

[0025] Figure 3 A flowchart of another pet management method for a smart community provided in one embodiment of the present application;

[0026] Figure 4 A flowchart of another pet management method for a smart community provided in one embodiment of the present application;

[0027] Figure 5 It is a structural diagram of a pet management device for a smart community provided by an embodiment of the present application;

[0028] Figure 6 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0030] With the acceleration of urbanization, more and more people choose to keep pets in the community. However, the existing pet management methods have many shortcomings and are in urgent need of improvement. Traditional pet management methods mainly rely on manual records and management, which is inefficient and prone to errors. For example, the identity information of pets is not fully recorded, making it difficult to achieve accurate management and tracking.

[0031] Secondly, there is a lack of effective means to manage stray pets, which has led to an increasing number of stray pets, which has had a negative impact on the community environment and residents' lives. In addition, existing pet management systems often lack intelligent functions and cannot monitor pet behavior and issue early warnings in a timely manner, resulting in residents being unable to take timely measures when pets get lost or have accidents.

[0032] These problems seriously affect the efficiency and safety of community pet management, and an intelligent and efficient pet management method is urgently needed to solve these problems. Therefore, the present application embodiment proposes a pet management method for a smart community, aiming to solve the problem of low efficiency of the current manual recording and management of pets. In this embodiment, a pet management method for a smart community includes:

[0033] Step 101: using a pet recognition algorithm, determine the target pet corresponding to the video data in the video data corresponding to the target community.

[0034] The video data of a smart community is the image and video information captured by surveillance cameras installed in various areas of the community. These cameras usually cover the public areas of the community, such as gates, parking lots, green belts, entertainment areas, etc., and can record the dynamics of the community in real time 24 hours a day. The video data includes the activities of various objects such as people, vehicles, pets, etc. in the community, providing basic data support for the community's security management, facility monitoring and service optimization.

[0035] In the pet management system of the smart community, the target pet is first identified from the video data through the pet recognition algorithm. This process relies on the pre-definition and learning of the types and characteristics of pets. The system will build a database containing various types of pets, including the typical appearance characteristics and population images of each pet. Through the real-time video data captured by the camera, the system uses the target detection algorithm to automatically scan the screen and locate possible pet objects in the screen.

[0036] The recognition algorithm will match and compare with the preset pet database to confirm the type and specific individual of the pet in the image. The algorithm can identify the main characteristics of the pet, such as shape, color, hair structure, etc., to ensure that the system can accurately distinguish different types of pets.

[0037] Step 102: Use a preset extraction model to perform feature extraction on the target pet to determine a pet feature vector corresponding to the target pet.

[0038] Based on the known information in the pet database, the type and characteristic parts of the target pet are identified. The characteristic parts of pets usually include ears, tails, hair color and texture, body size, etc. These features can not only distinguish different types of pets, but also further distinguish different individuals of the same type.

[0039] The preset extraction model can use deep learning or computer vision technology to perform a detailed analysis of these characteristic parts and extract the characteristic vector of each part. For example, the system can generate corresponding numerical vectors for information such as the shape of the ears, the length of the tail, and the color of the eyes, indicating the position and characteristics of each feature in the digital space. Then, these part vectors are aggregated to form a complete pet feature vector, which is the unique characteristic data of the target pet.

[0040] This feature vector not only ensures the uniqueness of the pet in the system, but can also be used in the subsequent encoding and identification process. Whether it is daily behavior monitoring of pets, identity confirmation, or tracking when they are lost or have abnormal behavior, feature vectors play an important role. By extracting the model, the system can better capture the uniqueness of each pet, greatly improving the accuracy of recognition.

[0041] Step 103: Encode the pet feature vector using a preset encoding algorithm to determine a unique identifier corresponding to the pet feature vector.

[0042] Through the preset coding algorithm, the system converts the extracted pet feature vector into a unique code to generate a unique identification for the pet. This unique identification is the core data for identifying and managing pets within the system, similar to the ID card of each pet.

[0043] Specifically, the pet's feature vector includes information about various characteristic parts, such as ear shape, hair color, body size, etc. Each feature is represented in the form of a numerical vector. The preset encoding algorithm will compress, integrate and map these vectors according to specific rules, and finally generate a concise but unique code. The code is usually composed of a string of numbers, letters or symbols to ensure that it can be quickly recognized by the system and is not easily confused with other pets.

[0044] Through this coding process, the system can ensure that every pet in the community has a unique identity. No matter how similar they look or how similar they are in breed, the system can rely on this code to distinguish individuals. The application of coding algorithms not only improves the automation level of pet management, but also greatly reduces the errors and confusion that may occur in traditional manual recording and management of pet information, laying a solid foundation for intelligent pet management.

[0045] Step 104: Associating the unique identifier with the household information database corresponding to the target community to determine the target household corresponding to the unique identifier.

[0046] The system uses community video data to track the activities of pets and infer the pet's guardian by analyzing clues such as the pet's entry and exit paths and behavior patterns. For example, when a pet enters and exits a household together, the system can automatically record and analyze their interactive behaviors. In addition, through other data such as access control and community activity records, the system can further confirm whether the pet belongs to a specific household.

[0047] Once the guardian's identity is determined, the system will retrieve the guardian's identity information from the resident information database, such as the resident's room number, contact information, and other residents corresponding to the room number. Then, the system will bind the pet's unique identifier with the resident's identity information to ultimately determine which resident the pet belongs to. This association process is not only accurate, but can also verify the relationship between the pet and the resident multiple times to avoid errors or confusion.

[0048] In addition to automatically associating pets with residents through video surveillance and behavioral analysis, the pet management system of the smart community also allows residents to take the initiative to report to the property for registration. Residents can go to the property management office or submit pet information through the community's online platform. Residents usually need to provide photos, breeds, feature descriptions, and basic health information of the pet. This information will be entered into the community's pet management system, and a unique pet identifier will be generated through the coding algorithm in the system. At the same time, the resident's resident information will also be entered, and the system will associate the resident information with the pet's unique identifier.

[0049] Step 105: When it is detected that the target pet has a preset warning behavior, a prompt message is sent to the target resident.

[0050] Warning behavior refers to the system's analysis of the pet's real-time behavior to detect possible abnormal or dangerous situations. Common warning behaviors include pets getting lost, entering restricted areas, or exhibiting other abnormal activity patterns. For example, if a pet leaves its regular range of activities or appears in a dangerous area within the community, the system will mark this behavior as abnormal.

[0051] When the warning behavior is triggered, the system will record the time, location and specific circumstances of the incident and generate a detailed warning message. Subsequently, the system will immediately send the information to the target resident associated with the pet's unique identifier through SMS, community APP, etc. The prompt information usually includes a brief description of the abnormal event, the time and location, and may even include the pet's real-time location or activity trajectory in the community monitoring, so that residents can quickly understand the situation.

[0052] Through this function, community residents can be informed in time when their pets encounter potential risks, reducing the chances of accidents such as getting lost or getting injured. The system's real-time monitoring and quick reminder mechanism not only improves the safety of pets, but also enhances residents' trust in the pet management system, making the overall community environment more intelligent and safer.

[0053] Through the above technical solution, it can be seen that the beneficial effects of this embodiment are:

[0054] The embodiment of the present application provides a pet management method for a smart community, which uses a pet identification algorithm to determine the target pet corresponding to the video data in the video data corresponding to the target community; uses a preset extraction model to extract features of the target pet to determine the pet feature vector corresponding to the target pet; uses a preset encoding algorithm to encode the pet feature vector to determine the unique identifier corresponding to the pet feature vector; associates the unique identifier with the resident information database corresponding to the target community to determine the target resident corresponding to the unique identifier; and sends a prompt message to the target resident when a preset warning behavior is detected in the target pet. The present application provides a comprehensive and efficient pet management solution, which improves the level of community pet management.

[0055] Figure 1 What is shown is only a basic embodiment of a pet management method for a smart community of the present application. By making certain optimizations and expansions thereon, other preferred embodiments of a pet management method for a smart community can be obtained.

[0056] like Figure 2 As shown, another specific embodiment of a pet management method for a smart community of the present application.

[0057] In this embodiment, a pet management method for a smart community includes the following steps:

[0058] Step 201: Using a pet recognition algorithm, determine the target pet corresponding to the video data in the video data corresponding to the target community.

[0059] Step 202: Obtain population images corresponding to known pet types in a preset pet database.

[0060] The preset pet database contains a large number of pet image samples, covering the types, breeds and appearance characteristics of various common pets. Population images refer to typical images that can represent a certain type of pet. They not only contain the overall appearance of the pet, but also include some detailed features, such as hair color, body size, ear and tail shape, etc.

[0061] The pet database is constructed through the accumulation and classification of a large amount of data, and usually includes diverse images of common pets such as dogs and cats. In order to ensure that the system can accurately identify different pets, the database stores image samples of various pets in different postures, angles, and lighting conditions. The population images are not limited to a single breed, but also include the diverse characteristics of different breeds to cope with the wide range of pet species and individual differences.

[0062] Step 203: According to the population image, a target detection algorithm is used to determine the pet image data corresponding to the population image in the video data.

[0063] The population image provides typical appearance features of a certain type of pet, such as the body shape, hair color, ear shape, eye size, etc. of different pet breeds. These features are the standards for the system to compare and identify. The target detection algorithm applies these standards to the actual video footage, scanning the video data in real time to find areas that match the population image features. For example, when the system captures the outline or movement of a pet similar to that in the population image from the video, the algorithm will lock on to the area and mark it as a possible pet object.

[0064] The target detection algorithm determines which image areas may contain pets by analyzing pixel information, edge contours, and color distribution in the video. This algorithm can cope with a variety of complex environments. For example, when there are other objects in the background or the light changes, the system can still accurately distinguish between pets and surrounding non-target objects. Especially in dynamic video scenes, the algorithm can continuously track the movement trajectory of the pet to ensure the accuracy of recognition.

[0065] When the target detection algorithm determines that a certain part of the video data meets the characteristics of the population image, the system will extract the pet image data in that area. At this point, the information in the image data will be further parsed to confirm whether the pet meets the preset characteristics and provide a basis for subsequent feature extraction, encoding and other steps. This automated detection process greatly improves the efficiency of pet identification, reduces the need for human intervention, and ensures the adaptability of the system in complex environments.

[0066] Step 204: parse the pet image data to determine the target pet.

[0067] The process of parsing pet image data mainly involves in-depth analysis of the extracted image areas to determine the type and individual characteristics of the pet in the image. The process focuses on key information in the image, such as the pet's body shape, hair color, markings, ear shape, tail length, eye position and other unique biological characteristics. These features are compared with the population images in the preset pet database to confirm which type or breed the pet belongs to.

[0068] This parsing process usually involves image processing techniques such as image segmentation, edge detection, and feature extraction. Through these techniques, the system can separate the pet in the image from the surrounding background and further focus on specific parts of the pet, such as the face and limbs. Then, using feature matching algorithms, the system accurately matches the features of these parts with the population images in the database, thereby confirming that the pet in the image belongs to a specific known species.

[0069] During the analysis process, the system can also combine historical data and other video clips to improve the accuracy of recognition. If the pet has been registered in the system before, the system will automatically match its features to avoid duplicate entry. At the same time, if the pet image data is blurred or partially blocked, the system will also use deep learning technology to infer and complete the missing information to ensure the integrity of the recognition process.

[0070] Step 205: Use a preset extraction model to perform feature extraction on the target pet to determine a pet feature vector corresponding to the target pet.

[0071] Step 206: Determine the characteristic parts corresponding to the pet type of the target pet in the pet database.

[0072] Each pet type has its own unique physical features and appearance marks, and these characteristic parts are particularly critical for automated identification and management. The pet database stores characteristic information of various pet types, covering various common pet breeds, such as dogs, cats, and typical appearance features of other pets. The system uses this database to identify and classify the type of target pets, and determines the characteristic parts associated with each pet type based on the biological characteristics of different pet breeds in the database. These characteristic parts are usually areas that are visually easy to identify and distinguish, such as the head, ears, eyes, tail, limbs, hair, etc. These parts not only have obvious differences between different breeds, but even between different individuals of the same breed, there may be subtle differences in characteristics.

[0073] For example, the shape of the ears and tail of a dog are important features. Some breeds have erect ears, while others have drooping ears; the tail may be curly, straight, or short and inconspicuous. For cats, the shape of the eyes, the pointiness of the ears, and the color and texture of the fur are more easily distinguished features. For other pets, such as rabbits or birds, the length of the ears or the color and distribution of the feathers are the main identification basis.

[0074] By identifying these specific parts in the database, the system can generate an identification template for the target pet, which can be further compared with the image in the video data to accurately identify the pet. The determination of characteristic parts is not just a simple analysis of the pet's appearance, it is also based on long-term accumulated image data and experience, ensuring that the system can accurately identify pets in different environments.

[0075] Step 207: Using a feature extraction algorithm, extract the part vector corresponding to each feature part.

[0076] The main goal of the feature extraction algorithm is to digitize the appearance features of the pet, especially those parts that vary greatly between individuals. The feature extraction algorithm analyzes the key parts in the pet image and converts these features into vector form that can be calculated and processed, making it easier for the system to match and encode in subsequent steps. These parts usually include ears, eyes, nose, hair texture, tail shape, etc., which can best reflect the individual characteristics of the pet visually. The extraction algorithm analyzes these characteristic parts one by one and converts them into independent part vectors, which can represent information such as the shape, size, color and position of the pet parts.

[0077] The working principle of the algorithm is similar to the edge detection, contour analysis and color recognition techniques in image processing. First, the system segments the pet image and accurately locates the areas where each characteristic part is located. Then, the system analyzes the specific features of these areas and extracts information such as the length of the ears, the curvature of the tail, and the color distribution of the hair. Each feature will be converted into a vector, that is, a digitized data point, representing the specific parameters of the feature. This vector will contain information about the shape, size, color, etc. of the feature part, allowing the system to efficiently match and store it in the database.

[0078] Step 208: Aggregate the vectors of each part to determine the pet feature vector corresponding to the target pet.

[0079] The aggregation process is to integrate multiple independent part vectors into a comprehensive vector. Each part vector represents the characteristic information of different parts of the pet, such as the shape of the ears, the color of the hair, the length of the tail, etc. These parts are independent and have unique characteristics, but only by aggregating them together can the overall appearance and characteristics of the pet be fully described. Therefore, the system will conduct a comprehensive analysis of all the extracted part vectors, combine them through algorithms, and generate a global feature vector that represents the entire pet.

[0080] This aggregation process involves multiple technical steps. First, the system normalizes the vectors of each part to ensure that the features of different parts can be compared and calculated on the same data dimension. Then, the system weights these vectors, giving higher weights to certain more recognizable parts, such as facial features or hair color, to ensure that they account for a larger proportion in the final feature vector. This weighting process can improve the accuracy of recognition because some features are more prominent in distinguishing individuals.

[0081] Finally, after aggregation processing, the complete pet feature vector generated by the system can be used as the unique identifier of the pet. This pet feature vector is a high-dimensional data structure that contains all the key feature information of the pet. Whether in the community monitoring system or in the subsequent pet management or alarm system, the feature vector can help the system quickly and accurately identify the pet.

[0082] Step 209: Encode the pet feature vector using a preset encoding algorithm to determine a unique identifier corresponding to the pet feature vector.

[0083] Step 210: Associating the unique identifier with the household information database corresponding to the target community to determine the target household corresponding to the unique identifier.

[0084] Step 211: When it is detected that the target pet has a preset warning behavior, a prompt message is sent to the target resident.

[0085] It can be seen from the above technical solutions that the beneficial effects of this embodiment are: it can automatically and efficiently identify and track target pets in the community, reduce dependence on manual management, and improve management efficiency; through the precise extraction of pet features and the generation of pet feature vectors, the system can accurately distinguish individual pets and enhance recognition accuracy.

[0086] like Figure 3 FIG. 1 is another specific embodiment of a pet management method for a smart community of the present application. This embodiment is further described on the basis of the above-mentioned embodiment.

[0087] In this embodiment, a pet management method for a smart community includes the following steps:

[0088] Step 301: Using a pet recognition algorithm, determine the target pet corresponding to the video data in the video data corresponding to the target community.

[0089] Step 302: Use a preset extraction model to perform feature extraction on the target pet to determine a pet feature vector corresponding to the target pet.

[0090] Step 303: Encode the pet feature vector using a preset encoding algorithm to determine a unique identifier corresponding to the pet feature vector.

[0091] Step 304: associate the unique identifier with the household information database corresponding to the target community to determine the target household corresponding to the unique identifier.

[0092] Step 305: Track the activity behavior of the target pet based on the video data.

[0093] Through the surveillance video data in the community, the system can obtain the behavior information of the target pet in real time, so as to achieve a comprehensive understanding and tracking of the pet's dynamics. The tracking process first relies on the high-definition surveillance cameras deployed in the community, which cover the main entrances and exits of the community, public activity areas, and the surroundings of each residential building. Through the pet recognition algorithm, the system first locks the target pet, identifies its pet feature vector, and accurately captures the pet's activity screen from the video data. Then, the system continuously monitors and records the pet's activity trajectory to ensure that the system can track its dynamic position regardless of whether the pet is stationary or moving.

[0094] During the tracking process, the system not only captures the changes in the pet's spatial position, but also records its behavior patterns, such as the areas it often appears in, the frequency and duration of its activities. For example, if a pet often appears at the door of a resident or frequently moves in a specific area of ​​the community, the system will be able to establish a connection between the pet and these locations. This tracking is not limited to a single area, but will cover the entire community through a chain reaction of cameras, ensuring that the pet can be continuously tracked by the system no matter where it moves.

[0095] Step 306: Analyze the activity behavior using an analysis algorithm to determine the guardian corresponding to the target pet.

[0096] The system will conduct an in-depth analysis of the pet's activities and behaviors, and use algorithms to analyze the frequency and pattern of interaction between pets and specific residents. For example, when a pet frequently enters and exits a resident's home, or spends a long time with and interacts with the resident in public areas, the system will automatically identify this behavior and preliminarily determine that the resident may be the pet's guardian.

[0097] In addition, the system can further verify the relationship between pets and residents by combining time periods and behavior patterns. For example, if a pet appears at the doorstep of a resident at a fixed time every day and accompanies the resident in and out of the community, the system can identify this regular behavior and determine the resident's responsibility for caring for the pet. Through such behavior patterns, the system can screen out potential guardian candidates.

[0098] To further ensure accuracy, the analysis algorithm can also conduct a comprehensive comparison of repeated behaviors in multiple video clips. For example, if a pet interacts with a resident in the same place many times, or often moves with the resident in public areas, the system will further confirm that the resident is the primary guardian of the target pet through the accumulation of these repeated behaviors. By repeatedly verifying these behaviors, the system can improve the accuracy of recognition and ensure that there will be no misjudgment.

[0099] Step 307: Determine the identity information corresponding to the guardian.

[0100] In the process of pet behavior tracking and guardian identification, the system will preliminarily identify residents who are closely related to the target pet based on the image and activity trajectory of the residents in the video through feature matching and behavior analysis algorithms. In order to further confirm the identity of these residents, the system will combine other relevant data resources in the community. For example, the community's access control system records the residents' entry and exit information, while the smart door lock system records the residents' door opening operations. These data can be cross-checked with the behavior of the people in the video to verify the consistency of the identity.

[0101] The system can also use high-quality video surveillance footage to capture the faces of residents who frequently interact with the target pet. Through advanced facial recognition algorithms, the system can quickly extract the resident's facial features, such as eyes, nose, mouth and other key feature points, and generate feature vectors, which can uniquely represent the resident's facial information and serve as the guardian's identity information.

[0102] Step 308: Determine the target household corresponding to the target pet in the user information database using the identity information.

[0103] The user information database is the core database of community property management, which records the registration information, check-in history, family structure and other detailed information of all residents. The database not only stores the personal identity information of each resident, but also contains the detailed address, family members and other ancillary information related to the resident. Therefore, when the system inputs the guardian's identity information, it can quickly find the resident record that matches the identity information in the information database.

[0104] The system can also compare the recognized facial features with existing facial data in the community resident information database. The resident information database usually contains photos or identity information provided by residents when registering to move in, including facial images for identity verification. When the system captures the facial image of the target resident, it can quickly confirm the identity of the resident by comparing its features with the photos in the information database one by one.

[0105] By matching key information such as the resident's name, photo, access card number, etc., the system can accurately identify the target resident corresponding to the target pet. This matching process ensures that the association between the pet and the resident is accurate, so that when a pet management event occurs, the system can quickly contact the correct resident. For example, when a pet exhibits warning behavior or management needs, the system will know which resident should send the information to for processing.

[0106] When the identified target pet is a stray pet, that is, if the unique identifier cannot be associated with the resident information database, the stray pet information corresponding to the target pet is generated based on the unique identifier; the stray pet information is published to the adoption platform corresponding to the target community; when the target pet is adopted on the adoption platform, the target resident corresponding to the unique identifier is determined based on the adoption information corresponding to the adoption platform and the resident information database.

[0107] During the process of identifying a pet, if the system finds that the pet does not match the identity information of any resident, it will also generate a unique identification for the pet and record its appearance characteristics, behavior patterns, location of discovery and other detailed information. This data will be stored in the system's database as information about stray pets. At the same time, the system can also take photos of the stray pets and automatically upload them to the community's stray pet management platform.

[0108] The system will also publish the generated stray pet information to the adoption platform corresponding to the target community. This platform is a service platform dedicated to finding adopters for stray pets. Community residents or other interested persons can browse the stray pet information on the platform and view the pet's detailed information and related conditions. In this way, the community can find new homes for stray pets, and residents can also easily adopt pets through the platform.

[0109] When a resident claims a target pet on the adoption platform, the system will record the adoption and automatically associate the adopter's identity information with the unique identifier of the stray pet. The adopter needs to provide his or her basic identity information, which will be matched with the community's resident information database. Through this matching, the system can associate the unique identifier of the stray pet with the resident information of the new guardian, and officially determine that the adopting resident is the guardian of the target pet.

[0110] This process not only helps stray pets find new guardians quickly, but also ensures the compliance and traceability of adoption behavior. When a pet is successfully adopted, the system will update the pet's status information and remove it from the list of stray pets. In this way, the pet management system of the smart community can not only effectively manage stray pets in the community, but also promote adoption activities, realize the humanization and intelligence of pet management, and improve the overall ecological environment of the community.

[0111] When the target pet needs to be fostered, the target user submits a fostering request through the fostering platform corresponding to the target community; the fostering time and foster resident corresponding to the fostering request are determined; the unique identifier is associated with the foster resident during the fostering time, and the foster resident is determined as the target resident.

[0112] The target resident (i.e. the original guardian of the pet) initiates a foster care request through the smart community's foster care platform. The foster care platform is an online platform designed specifically for community residents. Residents can browse other residents or community pet foster care centers that can provide foster care services and select suitable foster care providers. When submitting a foster care request, the target user needs to fill in the foster care time period, foster care requirements, and basic information about the pet so that the foster resident can better take care of the pet.

[0113] Foster residents can be other residents in the community or staff of the community foster care center. At the same time, the foster care platform can also match the most suitable foster residents according to the specific needs of the pets, ensuring that the pets can receive safe and healthy care during the foster care period.

[0114] After the foster resident and foster period are determined, the system will associate the unique ID of the target pet with the foster resident during the foster period. This means that during the entire foster period, the foster resident will temporarily serve as the guardian of the target pet, and the system will transfer the relevant management tasks of the pet to the foster resident.

[0115] When the original target resident decides to send the pet to a foster resident for care, the system will automatically associate the pet's unique ID with the foster resident. During this period, the foster resident acts as a temporary guardian and is responsible for the pet's daily care, health management, and behavior monitoring. The original target resident can choose whether to unbind the pet's unique ID during the foster period according to their own needs.

[0116] In this way, the smart community's foster care platform not only provides residents with convenient pet foster care services, but also ensures the safety and orderly management of pets during the foster care period. The system can automatically handle the association and management of foster care information, allowing residents to foster pets with peace of mind, while ensuring the transparency and standardization of foster residents and pet management.

[0117] Step 309: When it is detected that the target pet has a preset warning behavior, a prompt message is sent to the target resident.

[0118] It can be seen from the above technical solutions that the beneficial effects of this embodiment are: by tracking the activities of pets, dynamic information can be obtained in a timely manner to ensure the safety of pets. In addition, the use of analytical algorithms to analyze activities helps to quickly identify the guardian of the pet, thereby improving the efficiency and accuracy of pet management. Moreover, verification in the user information database in combination with the identity information of the guardian not only enhances the security of the system, but also ensures the effective supervision of pets by residents. This series of measures has improved the level of intelligence of community pet management and enhanced the trust and satisfaction of residents.

[0119] like Figure 4 FIG. 1 is another specific embodiment of a pet management method for a smart community of the present application. This embodiment is further described on the basis of the above-mentioned embodiment.

[0120] In this embodiment, a pet management method for a smart community includes the following steps:

[0121] Step 401: Using a pet recognition algorithm, determine the target pet corresponding to the video data in the video data corresponding to the target community.

[0122] Step 402: Use a preset extraction model to perform feature extraction on the target pet to determine a pet feature vector corresponding to the target pet.

[0123] Step 403: Encode the pet feature vector using a preset encoding algorithm to determine a unique identifier corresponding to the pet feature vector.

[0124] Step 404: associate the unique identifier with the household information database corresponding to the target community to determine the target household corresponding to the unique identifier.

[0125] Step 405: When it is detected that the target pet has a preset warning behavior, a prompt message is sent to the target resident.

[0126] Step 406: Determine the warning event corresponding to the preset warning behavior.

[0127] Based on a large amount of historical data and pet behavior patterns, the system sets some common warning behaviors. For example, pets leaving the safe area set by the owner without permission, staying in a dangerous area for a long time, barking continuously or running wildly may indicate that the pet is in distress or abnormal state. These behaviors are defined by combining machine learning algorithms and historical data to ensure that they can accurately cover various abnormal situations that may occur in the community.

[0128] When the system detects that the pet's behavior meets the preset abnormal standards, it will generate a corresponding warning event. For example, when a pet leaves the safe area, the system will generate a "pet out of bounds" warning event. These events can be classified and prioritized according to the different nature of the behavior.

[0129] Step 407: Record the time and location corresponding to the warning event.

[0130] Time recording means that the system accurately captures the moment when the warning event occurs. This is usually achieved through the clock function inside the system to ensure the accuracy of the timestamp. Accurate time recording is crucial for the subsequent processing of the event. For example, if a pet behaves abnormally late at night, the time information can help the resident judge the urgency of the event and decide whether to take immediate action. In addition, the time data can be compared with historical behavior patterns to analyze the behavior change trend of the pet, providing data support for future management and optimization of the warning mechanism.

[0131] Location records involve the specific geographic location of the pet when the incident occurred. Through surveillance cameras, sensors or other positioning technologies installed in the community, the system can obtain the pet's location data in real time. This geographic location information not only helps residents quickly locate the current location of the pet, but also provides the context of the surrounding environment. For example, when the pet is active in the park, the system can record the specific area; if the pet crosses the safety boundary, the recorded location information can indicate the potential dangers that the pet may face.

[0132] By recording the time and location of warning events, the system not only improves the monitoring capabilities of pet safety, but also provides important basis for subsequent incident response. This information helps residents respond in time to avoid unexpected situations for pets, and also provides data support for the system to formulate more effective pet management strategies.

[0133] Step 408: Generate prompt information according to the warning event, time and location.

[0134] The system will clearly identify the nature of the alert event, such as unusual pet activity, leaving a safe area, or health issues. This event description provides residents with the necessary context to help them quickly understand the severity and urgency of the matter. The system will then record the specific time of the event to ensure that the alert information is timely. By marking the time, residents can determine the context of the event and better evaluate the response measures that need to be taken.

[0135] In addition, the system records the pet’s exact location at the time of the incident, ensuring that this critical information is included in the alert message. By indicating the area where the pet is located, residents can quickly locate the pet’s actual location and take timely action to prevent the pet from getting lost or encountering potential danger.

[0136] The generated prompt information can also include recommended follow-up actions, such as "Please go to the community park to find your pet immediately." By providing specific action guidelines, the system can effectively enhance residents' responsiveness and help them make decisions quickly.

[0137] Step 409: Send the prompt information to the target resident according to the resident information database.

[0138] After the reminder is generated, the system will search for the resident information associated with the unique identifier of the specific pet according to the resident information database. The resident information database usually contains basic information of each resident, such as name, contact information and address. The accuracy of this information directly affects the efficiency of sending reminders. Therefore, the system will ensure that the data in the information database is up to date to avoid communication failures caused by incorrect contact information.

[0139] The system will use effective communication channels to send reminder information to target residents. These channels can include mobile phone text messages or push notifications from community applications. Through a variety of communication methods, the system can meet the preferences of different residents and ensure that information can be delivered quickly.

[0140] It can be seen from the above technical solutions that the beneficial effects of this embodiment are: the prompt information generated by combining warning events, time and location not only improves the efficiency of monitoring pet behavior, but also enhances the residents' sense of participation and responsibility in pet safety management, ultimately achieving more efficient smart community pet management.

[0141] like Figure 5 As shown in the figure, a specific embodiment of a pet management device for a smart community of the present application is shown. Figures 1 to 4 A physical device of a pet management method for a smart community. Its technical solution is essentially consistent with the above embodiment, and the corresponding description in the above embodiment is also applicable to this embodiment. In this embodiment, a pet management device for a smart community includes:

[0142] The target pet determination module 501 is configured to determine the target pet corresponding to the video data in the video data corresponding to the target community by using a pet recognition algorithm;

[0143] The pet feature vector determination module 502 is configured to perform feature extraction on the target pet using a preset extraction model to determine the pet feature vector corresponding to the target pet;

[0144] The unique identification determination module 503 is configured to encode the pet feature vector using a preset encoding algorithm to determine the unique identification corresponding to the pet feature vector;

[0145] The target resident determination module 504 is configured to associate the unique identifier with a resident information database corresponding to the target community to determine the target resident corresponding to the unique identifier;

[0146] The warning module 505 is configured to send a prompt message to the target resident when it is detected that the target pet has a preset warning behavior.

[0147] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0148] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0149] The memory is used to store execution instructions. Specifically, the execution instructions are computer programs that can be executed. The memory may include internal memory and non-volatile memory, and provides execution instructions and data to the processor.

[0150] In one possible implementation, the processor reads the corresponding execution instructions from the non-volatile memory into the memory and then runs them, and can also obtain the corresponding execution instructions from other devices to form a pet management device for a smart community at the logical level. The processor executes the execution instructions stored in the memory to implement a pet management method for a smart community provided in any embodiment of the present application through the execution of the execution instructions.

[0151] The above application Figure 5The method performed by a pet management device of a smart community provided in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0152] The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0153] The embodiment of the present application also proposes a readable medium, which stores an execution instruction. When the stored execution instruction is executed by the processor of the electronic device, the electronic device can execute a pet management method for a smart community provided in any embodiment of the present application, and is specifically used to execute the following: Figure 1 or Figure 2 or Figure 3 or Figure 4 The method shown.

[0154] The electronic device in each of the aforementioned embodiments may be a computer.

[0155] Those skilled in the art should understand that the embodiments of the present application can be provided as methods or computer program products. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware.

[0156] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0157] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0158] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A pet management method for a smart community, characterized in that: include: Using a pet recognition algorithm, in the video data corresponding to the target community, determine the target pet corresponding to the video data; Using a preset extraction model, feature extraction is performed on the target pet to determine a pet feature vector corresponding to the target pet; Encoding the pet feature vector using a preset encoding algorithm to determine a unique identifier corresponding to the pet feature vector; Associating the unique identifier with a household information database corresponding to the target community to determine the target household corresponding to the unique identifier; When it is detected that the target pet has a preset warning behavior, a prompt message is sent to the target resident.

2. The method according to claim 1, characterized in that The method of using a pet identification algorithm to determine, in the video data corresponding to the target community, the target pet corresponding to the video data comprises: Obtaining population images corresponding to known pet types in a preset pet database; According to the population image, using a target detection algorithm in the video data, determining the pet image data corresponding to the population image; The pet image data is parsed to determine the target pet.

3. The method according to claim 2 is characterized in that the use of a preset extraction model to extract features of the target pet to determine the pet feature vector corresponding to the target pet comprises: In the pet database, determining a characteristic part corresponding to the pet type of the target pet; Using a feature extraction algorithm, extracting a part vector corresponding to each of the feature parts; The part vectors are aggregated to determine the pet feature vector corresponding to the target pet.

4. The method according to claim 1, characterized in that The step of associating the unique identifier with a household information database corresponding to the target community to determine the target household corresponding to the unique identifier includes: Tracking the activity behavior of the target pet according to the video data; Analyzing the activity behavior using an analysis algorithm to determine the guardian corresponding to the target pet; Determine the identity information corresponding to the guardian; The target household corresponding to the target pet is determined in the user information database using the identity information.

5. The method according to claim 1, characterized in that Also includes: If the unique identifier cannot be associated with the resident information database, generating stray pet information corresponding to the target pet according to the unique identifier; Publishing the stray pet information to the adoption platform corresponding to the target community; When the target pet is adopted on the adoption platform, the target resident corresponding to the unique identifier is determined according to the adoption information corresponding to the adoption platform and the resident information database.

6. The method according to claim 1, characterized in that Also includes: When the target pet has a fostering need, the target user submits a fostering request through the fostering platform corresponding to the target community; Determine the foster care period and foster resident corresponding to the foster care request; The unique identifier is associated with the foster resident during the foster period, and the foster resident is determined as the target resident.

7. The method according to any one of claims 1 to 6, characterized in that: When the target pet is detected to have a preset warning behavior, sending a prompt message to the target resident includes: Determine the warning event corresponding to the preset warning behavior; Record the time and location corresponding to the warning event; Generate the prompt information according to the warning event, the time and the location; The prompt information is sent to the target resident according to the resident information database.

8. A pet management device for a smart community, characterized in that: include: A target pet determination module is configured to determine, in the video data corresponding to the target community, a target pet corresponding to the video data using a pet recognition algorithm; A pet feature vector determination module is configured to perform feature extraction on the target pet using a preset extraction model to determine a pet feature vector corresponding to the target pet; A unique identification determination module is configured to encode the pet feature vector using a preset encoding algorithm to determine a unique identification corresponding to the pet feature vector; A target resident determination module is configured to associate the unique identifier with a resident information database corresponding to the target community to determine the target resident corresponding to the unique identifier; The warning module is configured to send a prompt message to the target resident when it is detected that the target pet has a preset warning behavior.

9. A computer-readable storage medium storing a computer program, wherein the computer program is used to execute the pet management method for a smart community as described in any one of claims 1 to 7.

10. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the pet management method for a smart community as described in any one of claims 1-7 above.

Images