Bird food supplement reminder method, device, electronic device and readable medium

Abstract

The embodiments of the present disclosure disclose a method, device, electronic device and readable medium for prompting bird feed replenishment. A specific implementation of the method includes: identifying an occluder on a target video; in response to the occluder type being a bird occluder type, identifying a bird on the target video; in response to the presence of an occluder, determining a first bird feed consumption amount based on the head-down duration and the first bird unit feeding amount; in response to the absence of an occluder, determining a second bird unit feeding amount based on the bird body shape information; determining a second bird feed consumption amount based on the head-down duration and the second bird unit feeding amount; updating a bird feed storage amount of a bird feed storage device included in a bird feeder based on the first bird feed consumption amount or the first bird feed consumption; in response to the updated bird feed storage amount satisfying a bird feed replenishment prompt condition, sending a bird feed replenishment prompt to the target client. This implementation enables timely reminders when bird feed is missing.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a bird feed supplement prompt method, device, electronic device, and readable medium. Background Art

[0002] A bird feeder is a device used to feed wild birds. It can attract wild birds and is beneficial for wild bird observation, bird migration analysis, and bird distribution statistics. At present, when replenishing bird feeders with bird food, regular inspections are usually carried out to replenish bird feeders that are short of bird food.

[0003] However, when the above method is adopted, the following technical problems often occur:

[0004] Since bird feeders are often set up in the wild and patrol inspections are used, it is impossible to replenish bird feeders that are short of bird food immediately, which in turn affects the accuracy of subsequent analysis of bird migration and bird distribution.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure provide a bird feed supplement reminder method, device, electronic device and readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a method for replenishing bird food, the method comprising: obtaining a target video, wherein the target video is collected by a camera set in a bird feeder, and the camera is controlled to be turned on and collect video through an infrared sensor; performing occlusion recognition on the target video to determine the type of occlusion, wherein the occlusion type includes: a bird occlusion type and a non-bird occlusion type; in response to the occlusion type being a bird occlusion type, performing bird recognition on the target video to generate bird information, wherein the bird information includes: bird type, head-down duration, and bird body shape information; determining whether a first bird unit food intake exists in a bird food intake database, wherein the first bird unit food intake is related to current weather information, current season information, current location of the bird feeder, and The unit feeding amount of birds matched with the above-mentioned bird type, wherein the current position of the bird feeder represents the location of the above-mentioned bird feeder, the above-mentioned weather information represents the real-time weather corresponding to the current position of the bird feeder, and the above-mentioned current season information represents the real-time season corresponding to the current position of the bird feeder; in response to existence, determining the first bird feed consumption according to the above-mentioned head-down time and the above-mentioned first bird feed unit feeding amount; in response to non-existence, determining the second bird feed unit feeding amount according to the above-mentioned bird body shape information; determining the second bird feed consumption according to the above-mentioned head-down time and the above-mentioned second bird feed unit feeding amount; updating the bird feed storage amount of the bird feed storage device included in the above-mentioned bird feeder according to the above-mentioned first bird feed consumption or the above-mentioned first bird feed consumption; in response to the updated bird feed storage amount satisfying the bird feed replenishment prompt condition, sending a bird feed replenishment prompt to the target client.

[0009] In a second aspect, some embodiments of the present disclosure provide a bird food replenishment reminder device, the device comprising: an acquisition unit, configured to acquire a target video, wherein the target video is captured by a camera arranged in a bird feeder, and the camera is controlled to be turned on and capture video by an infrared sensor; an occlusion recognition unit, configured to perform occlusion recognition on the target video to determine the occlusion type, wherein the occlusion type includes: a bird occlusion type and a non-bird occlusion type; a bird recognition unit, configured to perform bird recognition on the target video in response to the occlusion type being a bird occlusion type to generate bird information, wherein the bird information includes: bird type, head-down duration, and bird body shape information; a first determination unit, configured to determine whether a first bird unit food intake exists in a bird food intake database, wherein the first bird unit food intake is related to the current weather information, current season information, current position of the bird feeder and the bird unit feeding amount matched with the above-mentioned bird type, wherein the above-mentioned current position of the bird feeder represents the location of the above-mentioned bird feeder, the above-mentioned weather information represents the real-time weather corresponding to the current position of the bird feeder, and the above-mentioned current season information represents the real-time season corresponding to the current position of the bird feeder; a second determining unit is configured to determine the first bird feed consumption amount in response to the existence according to the above-mentioned head-down time and the above-mentioned first bird unit feeding amount; a third determining unit is configured to determine the second bird unit feeding amount in response to the absence according to the above-mentioned bird body shape information; a fourth determining unit is configured to determine the second bird feed consumption amount according to the above-mentioned head-down time and the above-mentioned second bird unit feeding amount; an updating unit is configured to update the bird feed storage amount of the bird feed storage included in the above-mentioned bird feeder according to the above-mentioned first bird feed consumption or the above-mentioned first bird feed consumption;

[0010] The bird food replenishment prompting unit is configured to send a bird food replenishment prompting to a target client in response to the updated bird food storage amount satisfying a bird food replenishment prompting condition.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0013] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the bird feed supplement prompt method of some embodiments of the present disclosure, timely reminders are realized when the bird feeder is short of bird feed. Specifically, the reason for the failure to provide timely reminders is that since the bird feeders are often set in the wild, the inspection method is adopted, so that the bird feeders that are short of bird feed cannot be supplemented with bird feed even if the bird feeders are short of bird feed, thereby affecting the accuracy of subsequent analysis of bird migration and bird distribution. Based on this, the bird feed supplement prompt method of some embodiments of the present disclosure first obtains a target video, wherein the target video is collected by a camera set in the bird feeder, and the camera is controlled to open and collect video through an infrared sensor. Since the bird feeder often includes a camera for collecting bird images, the subsequent bird feed supplement prompt can be realized without adding hardware by obtaining the target video. Secondly, the occluder is identified on the target video to determine the type of occluder, wherein the occluder type includes: bird occluder type and non-bird occluder type. In practice, since bird feed may attract wild animals other than birds, it is necessary to judge the type of occluder. Next, in response to the above-mentioned occlusion type being a bird occlusion type, the above-mentioned target video is subjected to bird recognition to generate bird information, wherein the above-mentioned bird information includes: bird type, head-down duration, and bird body information. Further, it is determined whether there is a first bird unit feeding amount in the bird feeding amount database, wherein the first bird unit feeding amount is a bird unit feeding amount that matches the current weather information, the current season information, the current position of the bird feeder, and the above-mentioned bird type, wherein the current position of the bird feeder represents the location of the above-mentioned bird feeder, the above-mentioned weather information represents the real-time weather corresponding to the current position of the above-mentioned bird feeder, and the above-mentioned current season information represents the real-time season corresponding to the current position of the above-mentioned bird feeder. In addition, in response to existence, the first bird feed consumption is determined according to the above-mentioned head-down duration and the above-mentioned first bird unit feeding amount. In this way, the bird feed consumption of a single time is calculated in combination with the head-down time and the unit feeding amount. Next, in response to non-existence, the second bird unit feeding amount is determined according to the above-mentioned bird body information. In practice, the bird food intake database often fails to record the food intake data of all birds in a timely manner. Therefore, the unit food intake corresponding to birds of the same size can be determined in combination with the body size of the birds. In addition, the second bird food consumption is determined based on the above-mentioned head-down duration and the above-mentioned second bird unit food intake. In addition, the bird food storage capacity of the bird food storage device included in the above-mentioned bird feeder is updated based on the above-mentioned first bird food consumption or the above-mentioned first bird food consumption. The remaining bird food in the bird food storage device is automatically updated in this way. Finally, in response to the updated bird food storage capacity meeting the bird food replenishment prompt condition, a bird food replenishment prompt is sent to the target client. In this way, the automatic estimation of the remaining bird food is achieved, so that timely reminders can be given when bird food is missing. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0015] Figure 1 is a flow chart of some embodiments of the bird feed supplement prompt method according to the present disclosure;

[0016] Figure 2 is a schematic structural diagram of some embodiments of the bird feed supplement prompt device according to the present disclosure;

[0017] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] refer to Figure 1, shows a process 100 of some embodiments of the bird feed supplement prompt method according to the present disclosure. The bird feed supplement prompt method comprises the following steps:

[0025] Step 101, obtaining a target video.

[0026] In some embodiments, the execution subject (e.g., a computing device) of the bird food supplementation prompt method can obtain the above-mentioned target video through a wired connection or a wireless connection. The above-mentioned target video is collected by a camera set in the bird feeder, and the above-mentioned camera is controlled to be turned on and the video is collected by an infrared sensor. In practice, the infrared sensor can be used to detect whether there is an obstruction in front of the bird feeder. The camera can be used to collect bird images.

[0027] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future.

[0028] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as a single software or software module. No specific limitation is made here.

[0029] Step 102: perform occlusion recognition on the target video to determine the type of occlusion.

[0030] In some embodiments, the above-mentioned execution subject may perform occlusion identification on the target video to determine the type of occlusion. In practice, the above-mentioned execution subject may perform occlusion identification on the target video through an occlusion detection model to determine the type of occlusion. Among them, the occlusion types include: bird occlusion type and non-bird occlusion type. Among them, the bird occlusion type characterizes that the occlusion is a bird. The non-bird occlusion type characterizes that the occlusion is a non-bird. For example, when the occlusion is other animals other than birds, the above-mentioned occlusion type is a non-bird occlusion type. In practice, the occlusion detection model can be implemented using a recurrent neural network model + a binary classifier.

[0031] In some optional implementations of some embodiments, the execution subject performs occlusion recognition on the target video to determine the type of the occlusion, which may include the following steps:

[0032] In the first step, image features are extracted from each frame of the target video to generate a first image feature and obtain a first image feature sequence.

[0033] In practice, the above execution entity can extract image features from video images through a feature pyramid network, where the feature pyramid network includes: 3 convolutional layers with different receptive fields and 1 feature fusion layer.

[0034] The second step is to determine the feature difference between each first image feature and the second image feature in the first image feature sequence as the third image feature, and obtain a third image feature sequence.

[0035] Among them, the above-mentioned second image feature is the image feature corresponding to the video image in the unobstructed state collected by the above-mentioned camera. In practice, as the seasons and weather change, the second image feature can also be updated accordingly. In addition, since the obstruction often only occupies part of the position in the image, that is, the image feature reference importance of the position other than the obstruction is relatively low, therefore, the present disclosure determines the feature difference between the first image feature and the second image feature from the perspective of image change as the third image feature, thereby updating the image feature value of the unchanged area to 0, reducing the amount of numerical calculation in the subsequent feature processing process.

[0036] The third step is to filter the third image features satisfying the image feature filtering condition in the third image feature sequence to obtain a fourth image feature sequence.

[0037] The image feature filtering condition may be that each image feature value in the third image feature is less than a threshold value. In practice, not all video images in the target video may contain occluders. Therefore, the third image feature obtained by calculating the feature difference between the corresponding first image feature and the second image feature is often 0 or a small value close to 0. Therefore, this type of third image feature can be filtered to reduce the amount of subsequent feature processing.

[0038] The fourth step is to perform temporal occluder recognition on the fourth image feature sequence to obtain the occluder type.

[0039] In practice, the execution subject may use the occluder detection model to perform temporal occluder recognition on the fourth image feature sequence to obtain the occluder type.

[0040] In some optional implementations of some embodiments, after performing occluder recognition on the target video to determine the type of occluder, the method further includes:

[0041] The first step is to open the isolation door in response to the above-mentioned obstruction type being a bird obstruction type.

[0042] The isolation door is disposed between the bird food storage and the food bowl to control whether the bird food stored in the bird food storage flows into the food bowl. In practice, since the bird feeder is disposed outdoors, when the bird food accumulates in the food bowl and cannot be consumed in time, the bird food may become wet and deteriorate. In addition, the probability of attracting animals other than birds may also increase. Therefore, by providing the isolation door, when no birds are eating in the bird feeder, the bird food in the bird food storage is prevented from flowing into the food bowl.

[0043] In a second step, in response to the above-mentioned barrier type being a non-bird barrier type and the above-mentioned isolation door being in an open state, closing the above-mentioned isolation door.

[0044] Step 103 : In response to the occlusion type being a bird occlusion type, bird recognition is performed on the target video to generate bird information.

[0045] In some implementations, the execution subject may perform bird recognition on the target video in response to the occlusion type being a bird occlusion type to generate bird information. The bird information includes: bird type, head-down duration, and bird body information. The bird type characterizes the species of the bird. The head-down duration characterizes the duration of the bird's head-down. In practice, birds have obvious head-down behavior when feeding, so the feeding duration of the bird can be determined by determining the head-down duration. The bird body information can characterize the size of the bird.

[0046] In practice, the above-mentioned execution entity can use a bird recognition model to identify birds in the target video to generate bird information. In practice, the above-mentioned bird recognition model can reuse the above-mentioned occlusion detection model, and add a bird type classifier and a bird head-down duration classifier on the basis of the occlusion detection model. Bird body shape predictor. In practice, the bird type classifier is a multi-classifier. The bird head-down duration classifier is a binary classifier. The bird head-down duration classifier can be used to classify each video image to determine whether the bird in this frame of video image is lowering its head. By counting the proportion of video images classified as the bird head-down type in the target video, the bird head-down duration is obtained. The bird reminder predictor is implemented using an anchor frame-based detection head.

[0047] Step 104, determining whether the first bird unit food intake amount exists in the bird food intake amount database.

[0048] In some embodiments, the execution subject may determine whether there is a first bird unit feeding amount in the bird feeding amount database. The first bird unit feeding amount is a bird unit feeding amount that matches the current weather information, the current season information, the current position of the bird feeder and the bird type. The current position of the bird feeder represents the location of the bird feeder. The weather information represents the real-time weather corresponding to the current position of the bird feeder. The current season information represents the real-time season corresponding to the current position of the bird feeder. The bird feeding amount database may be a database of unit feeding amounts of different birds obtained by summarizing big data technology. The bird feeding amount database includes: a feeding amount information set. The feeding amount information in the feeding amount information set includes: weather type, season type, location fence, bird type, bird unit feeding amount and feeding amount information vector. The feeding amount information vector is obtained by encoding the corresponding weather type, season type and bird type. In practice, for the same bird, there are also differences in feeding amount in different weather and seasons. Therefore, the bird feeding amount database may further refine and store the unit bird feeding amount of birds in different weather and seasons. The food intake information in the food intake information set also includes: bird body shape characteristics.

[0049] In some optional implementations of some embodiments, the above-mentioned determination of whether the first bird unit food intake amount exists in the bird food intake database may include the following steps:

[0050] In the first step, the current weather information, the current season information and the bird type are respectively encoded to obtain the encoded current weather information, the encoded current season information and the encoded bird type.

[0051] In practice, since the number of weather types, season types and bird types is limited, the above-mentioned execution entity can use the unique hot encoding method to encode the above-mentioned current weather information, the above-mentioned current season information and the above-mentioned bird type respectively, and obtain the encoded current weather information, the encoded current season information and the encoded bird type.

[0052] In the second step, the encoded current weather information, the encoded current season information and the encoded bird type are concatenated to obtain a query vector.

[0053] The third step is to perform vector matching between the query vector and the appetite information vector included in each appetite information in the appetite information set to obtain vector similarity.

[0054] In practice, the execution subject may determine the vector similarity between the query vector and the appetite information vector included in the appetite information by calculating the cosine similarity.

[0055] In a fourth step, in response to determining that the target food intake information exists, determining whether the current position of the bird feeder is located within the position fence included in the target food intake information.

[0056] The target food intake information is food intake information in the food intake information set whose corresponding vector similarity satisfies the first screening condition. The first screening condition may be that the vector similarity is the maximum vector similarity.

[0057] In a fifth step, in response to determining that the current position of the bird feeder is located within the position fence included in the target feeding amount information, the bird unit feeding amount included in the target feeding amount information is determined as the first bird unit feeding amount.

[0058] In step 6, in response to determining that the target appetite information does not exist, the appetite information in the appetite information set is sorted in descending order according to the vector similarity corresponding to the appetite information to obtain an appetite information sequence.

[0059] As an example, the food intake information set may include food intake information A, food intake information B, and food intake information C. The vector similarity corresponding to food intake information A is 0.8, the vector similarity corresponding to food intake information B is 0.98, and the vector similarity corresponding to food intake information C is 0.82. Therefore, the obtained food intake information sequence may be: food intake information B, food intake information C, and food intake information A.

[0060] In the seventh step, in response to the number of food intake information in the food intake information sequence being ≥ 2K, the first K food intake information are selected as the first candidate food intake information to obtain the first candidate food intake information sequence, wherein the value of K is 3.

[0061] In the eighth step, position voting is performed based on the current position of the bird feeder and the position fence included in the first candidate food intake information in the first candidate food intake information sequence to obtain a second candidate food intake information sequence.

[0062] In practice, the execution subject may use the first candidate food intake information corresponding to the location fence including the current location of the bird feeder as the second candidate food intake information to obtain a second candidate food intake information sequence.

[0063] The ninth step is to perform a weighted summation on the unit food intake of birds included in each second candidate food intake information in the second candidate food intake information sequence as the first unit food intake of birds.

[0064] Step 105, in response to the existence, determining the first bird feed consumption according to the head-down duration and the first bird unit feed intake.

[0065] In some embodiments, the execution subject may determine the first bird feed consumption according to the head-down duration and the first bird feed unit intake in response to the presence. In practice, the execution subject may use the product of the head-down duration and the first bird feed unit intake as the first bird feed consumption.

[0066] Step 106: In response to the absence of the information, determine the second bird unit food intake according to the bird body size information.

[0067] In some embodiments, in response to the absence of, the execution subject may determine the second bird unit food intake amount based on the bird body shape information.

[0068] In some optional implementations of some embodiments, the execution subject determines the unit food intake of the second bird according to the bird body shape information, which may include the following steps:

[0069] The first step is to extract the bird body features from the above bird body information to obtain the target bird body features.

[0070] In practice, the execution entity may extract the body shape features of the bird through the YOLO model to obtain the body shape features of the target bird.

[0071] In the second step, the body shape characteristics of the target bird are matched with the body shape characteristics of the bird included in each food intake information in the food intake information set to obtain the body shape characteristic similarity.

[0072] The third step is to determine the unit food intake of the birds included in the food intake information of the above food intake information set, whose corresponding body feature similarity meets the second screening condition, as the above second unit food intake of the birds.

[0073] Among them, the second screening condition can be that the corresponding body feature similarity pair has the maximum body feature similarity.

[0074] Step 107, determining the second bird feed consumption according to the head-down duration and the second bird unit food intake.

[0075] In some embodiments, the execution subject may determine the second bird feed consumption according to the head-down time and the second bird unit feed intake. In practice, the execution subject may determine the second bird feed consumption as the product of the head-down time and the second bird unit feed intake.

[0076] Step 108: updating the bird food storage capacity of the bird food storage device included in the bird feeder according to the first bird food consumption amount or the first bird food consumption amount.

[0077] In some implementations, the execution entity may update the bird food storage amount of the bird food storage device included in the bird feeder according to the first bird food consumption amount or the second bird food consumption amount.

[0078] In some optional implementations of some embodiments, the execution subject updates the bird food storage amount of the bird food storage device included in the bird feeder according to the first bird food consumption amount or the second bird food consumption amount, which may include the following steps:

[0079] The first step is to initialize the basic bird food storage capacity of the bird food storage device.

[0080] In practice, since the volume of the bird food storage is fixed, but different types of bird food have different storage capacities under the same volume, the maximum bird food storage capacity of the bird food storage can be determined by initialization as the basic bird food storage capacity.

[0081] The second step is to update the basic bird feed storage capacity according to the first bird feed consumption or the second bird feed consumption.

[0082] In practice, the above-mentioned execution entity may use the difference between the basic bird food storage amount and the first bird food consumption amount as the updated bird food storage amount, or use the difference between the basic bird food storage amount and the second bird food consumption amount as the updated bird food storage amount.

[0083] Step 109 , in response to the updated bird food storage amount satisfying the bird food replenishment prompt condition, sending a bird food replenishment prompt to the target client.

[0084] In some embodiments, the execution subject may send a bird food replenishment reminder to the target client in response to the updated bird food storage volume satisfying the bird food replenishment reminder condition. The target client may be a client bound to a user account corresponding to the user of the bird feeder.

[0085] In some optional implementations of some embodiments, the above method further includes:

[0086] In response to failure to send, a bird food supplement prompt message is sent to a mobile terminal bound to the user account corresponding to the target client.

[0087] In practice, when the user is not logged in to the target client, there may be a situation where the bird food replenishment reminder cannot be received by the user in time. Therefore, the bird food replenishment reminder information can be sent to the mobile terminal bound to the user account by sending a reminder message to implement a message reminder.

[0088] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the bird feed supplement prompt method of some embodiments of the present disclosure, timely reminders are realized when the bird feeder is short of bird feed. Specifically, the reason for the failure to provide timely reminders is that since the bird feeders are often set in the wild, the inspection method is adopted, so that the bird feeders that are short of bird feed cannot be supplemented with bird feed even if the bird feeders are short of bird feed, thereby affecting the accuracy of subsequent analysis of bird migration and bird distribution. Based on this, the bird feed supplement prompt method of some embodiments of the present disclosure first obtains a target video, wherein the target video is collected by a camera set in the bird feeder, and the camera is controlled to open and collect video through an infrared sensor. Since the bird feeder often includes a camera for collecting bird images, the subsequent bird feed supplement prompt can be realized without adding hardware by obtaining the target video. Secondly, the occluder is identified on the target video to determine the type of occluder, wherein the occluder type includes: bird occluder type and non-bird occluder type. In practice, since bird feed may attract wild animals other than birds, it is necessary to judge the type of occluder. Next, in response to the above-mentioned occlusion type being a bird occlusion type, the above-mentioned target video is subjected to bird recognition to generate bird information, wherein the above-mentioned bird information includes: bird type, head-down duration, and bird body information. Further, it is determined whether there is a first bird unit feeding amount in the bird feeding amount database, wherein the first bird unit feeding amount is a bird unit feeding amount that matches the current weather information, the current season information, the current position of the bird feeder, and the above-mentioned bird type, wherein the current position of the bird feeder represents the location of the above-mentioned bird feeder, the above-mentioned weather information represents the real-time weather corresponding to the current position of the above-mentioned bird feeder, and the above-mentioned current season information represents the real-time season corresponding to the current position of the above-mentioned bird feeder. In addition, in response to existence, the first bird feed consumption is determined according to the above-mentioned head-down duration and the above-mentioned first bird unit feeding amount. In this way, the bird feed consumption of a single time is calculated in combination with the head-down time and the unit feeding amount. Next, in response to non-existence, the second bird unit feeding amount is determined according to the above-mentioned bird body information. In practice, the bird food intake database often fails to record the food intake data of all birds in a timely manner. Therefore, the unit food intake corresponding to birds of the same size can be determined in combination with the body size of the birds. In addition, the second bird food consumption is determined based on the above-mentioned head-down duration and the above-mentioned second bird unit food intake. In addition, the bird food storage capacity of the bird food storage device included in the above-mentioned bird feeder is updated based on the above-mentioned first bird food consumption or the above-mentioned first bird food consumption. The remaining bird food in the bird food storage device is automatically updated in this way. Finally, in response to the updated bird food storage capacity meeting the bird food replenishment prompt condition, a bird food replenishment prompt is sent to the target client. In this way, the automatic estimation of the remaining bird food is achieved, so that timely reminders can be given when bird food is missing.

[0089] Further references Figure 2As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a bird feed supplement prompt device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the bird food supplement reminder device can be specifically applied to various electronic devices.

[0090] like Figure 2 As shown, the bird feed replenishment prompt device 200 of some embodiments includes: an acquisition unit 201, an obstruction recognition unit 202, a bird recognition unit 203, a first determination unit 204, a second determination unit 205, a third determination unit 206, a fourth determination unit 207, an updating unit 208 and a bird feed replenishment prompt unit 209. Among them, the acquisition unit 201 is configured to acquire the target video, wherein the target video is collected by a camera set in the bird feeder, and the camera is controlled to be turned on and the video is collected by an infrared sensor; the occlusion recognition unit 202 is configured to perform occlusion recognition on the target video to determine the occlusion type, wherein the occlusion type includes: bird occlusion type and non-bird occlusion type; the bird recognition unit 203 is configured to perform bird recognition on the target video in response to the occlusion type being a bird occlusion type to generate bird information, wherein the bird information includes: bird type, head-down duration, and bird body shape information; the first determination unit 204 is configured to determine whether there is a first bird unit food intake in the bird feeding amount database, wherein the first bird unit food intake is a bird unit food intake that matches the current weather information, the current season information, the current position of the bird feeder and the above-mentioned bird type, wherein the above-mentioned feeder The current position of the bird feeder represents the position of the bird feeder, the weather information represents the real-time weather corresponding to the current position of the bird feeder, and the current season information represents the real-time season corresponding to the current position of the bird feeder; the second determining unit 205 is configured to determine the first bird feed consumption in response to existence according to the head-down time and the first bird unit feeding amount; the third determining unit 206 is configured to determine the second bird unit feeding amount in response to non-existence according to the bird body shape information; the fourth determining unit 207 is configured to determine the second bird feed consumption according to the head-down time and the second bird unit feeding amount; the updating unit 208 is configured to update the bird feed storage capacity of the bird feed storage included in the bird feeder according to the first bird feed consumption or the first bird feed consumption; the bird feed supplement prompting unit 209 is configured to send a bird feed supplement prompting to the target client in response to the updated bird feed storage capacity satisfying the bird feed supplement prompting condition.

[0091] It is understandable that the units described in the bird feed supplement prompt device 200 are similar to those described in the reference Figure 1Therefore, the operations, features and beneficial effects described above for the method are also applicable to the bird feed supplement prompt device 200 and the units included therein, and will not be described in detail here.

[0092] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0093] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory 302 or a program loaded from a storage device 308 into a random access memory 303. Various programs and data required for the operation of the electronic device 300 are also stored in the random access memory 303. The processing device 301, the read-only memory 302, and the random access memory 303 are connected to each other via a bus 304. An input / output interface 305 is also connected to the bus 304.

[0094] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0095] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the read-only memory 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0096] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0097] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0098] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains a target video, wherein the target video is captured by a camera installed in the bird feeder, and the camera is controlled to turn on and capture video through an infrared sensor; performs occlusion recognition on the target video to determine the type of occlusion, wherein the occlusion type includes: a bird occlusion type and a non-bird occlusion type; in response to the occlusion type being a bird occlusion type, performs bird recognition on the target video to generate bird information, wherein the bird information includes: bird type, head-down duration, and bird body shape information; determines whether there is a first bird unit food intake in the bird food intake database, wherein the first bird unit food intake is related to the current weather information, the current season information, The current position of the bird feeder and the bird unit feeding amount that matches the above-mentioned bird type, wherein the above-mentioned current position of the bird feeder represents the location of the above-mentioned bird feeder, the above-mentioned weather information represents the real-time weather corresponding to the current position of the bird feeder, and the above-mentioned current season information represents the real-time season corresponding to the current position of the bird feeder; in response to existence, determining a first bird feed consumption according to the above-mentioned head-down duration and the above-mentioned first bird unit feeding amount; in response to non-existence, determining a second bird unit feeding amount according to the above-mentioned bird body shape information; determining a second bird feed consumption according to the above-mentioned head-down duration and the above-mentioned second bird unit feeding amount; updating the bird feed storage amount of the bird feed storage device included in the above-mentioned bird feeder according to the above-mentioned first bird feed consumption or the above-mentioned first bird feed consumption; in response to the updated bird feed storage amount satisfying the bird feed replenishment prompt condition, sending a bird feed replenishment prompt to the target client.

[0099] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0100] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0101] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, an obstruction recognition unit, a bird recognition unit, a first determination unit, a second determination unit, a third determination unit, a fourth determination unit, an update unit, and a bird food replenishment prompt unit. Among them, the names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the bird food replenishment prompt unit may also be described as "a unit that sends a bird food replenishment prompt to a target client in response to the updated bird food storage amount satisfying a bird food replenishment prompt condition."

[0102] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0103] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for providing a bird food supplement reminder, comprising: Acquire a target video, wherein the target video is collected by a camera disposed in the bird feeder, and the camera is controlled to be turned on and to collect video through an infrared sensor; Performing occlusion recognition on the target video to determine the occlusion type, wherein the occlusion type includes: a bird occlusion type and a non-bird occlusion type; In response to the occlusion type being a bird occlusion type, performing bird recognition on the target video to generate bird information, wherein the bird information includes: bird type, head-down duration, and bird body size information; Determine whether there is a first bird unit food intake in a bird food intake database, wherein the first bird unit food intake is a bird unit food intake that matches current weather information, current season information, a current position of a bird feeder, and the bird type, wherein the current position of the bird feeder represents the location of the bird feeder, the weather information represents the real-time weather corresponding to the current position of the bird feeder, and the current season information represents the real-time season corresponding to the current position of the bird feeder; The step of determining whether the first bird unit food intake amount exists in the bird food intake database comprises: Encoding the current weather information, the current season information and the bird type respectively to obtain the encoded current weather information, the encoded current season information and the encoded bird type, wherein the bird food intake database includes: a food intake information set, the food intake information in the food intake information set includes: weather type, season type, location fence, bird type, bird unit food intake, food intake information vector and bird body characteristics, and the food intake information vector is obtained by encoding the corresponding weather type, season type and bird type; concatenating the encoded current weather information, the encoded current season information, and the encoded bird type to obtain a query vector; Performing vector matching between the query vector and the food intake information vector included in each food intake information in the food intake information set to obtain vector similarity; In response to determining that there is target food intake information, determining whether the current position of the bird feeder is located within the position fence included in the target food intake information, wherein the target food intake information is food intake information having a corresponding vector similarity in the food intake information set that satisfies a first screening condition; In response to determining that the current position of the bird feeder is located within the position fence included in the target feeding amount information, determining the bird unit feeding amount included in the target feeding amount information as the first bird unit feeding amount; In response to determining that the target food intake information does not exist, sorting the food intake information in the food intake information set in descending order according to the vector similarity corresponding to the food intake information to obtain a food intake information sequence; In response to the number of food intake information in the food intake information sequence being ≥ 2K, selecting first K food intake information in the food intake information sequence as first candidate food intake information to obtain a first candidate food intake information sequence, wherein the value of K is 3; Performing a position vote according to the current position of the bird feeder and the position fence included in the first candidate food intake information in the first candidate food intake information sequence to obtain a second candidate food intake information sequence; Taking a weighted sum of the bird unit food intake included in each second candidate food intake information in the second candidate food intake information sequence as the first bird unit food intake; In response to the presence, determining a first bird feed consumption amount according to the head-down duration and the first bird unit feeding amount; In response to the absence of the information, determining a second unit food intake of the bird based on the bird body size information; The step of determining the unit food intake of the second bird according to the bird body shape information includes: Extracting bird body shape features from the bird body shape information to obtain the target bird body shape features; Performing bird body feature matching on the target bird body feature with the bird body feature included in each food intake information in the food intake information set to obtain a body feature similarity; Determine the unit food intake of the bird included in the food intake information set whose corresponding body feature similarity meets the second screening condition as the second unit food intake of the bird; Determine the second bird feed consumption according to the head-down duration and the second bird feed unit intake; updating a bird food storage amount of a bird food storage device included in the bird feeder according to the first bird food consumption amount or the second bird food consumption amount; In response to the updated bird food storage amount satisfying the bird food replenishment prompt condition, a bird food replenishment prompt is sent to the target client.

2. The method according to claim 1, wherein: After performing occlusion recognition on the target video to determine the type of occlusion, the method further includes: In response to the type of the shielding object being a bird shielding object type, opening an isolation door, wherein the isolation door is disposed between the bird food storage device and the food bowl, and is used to control whether the bird food stored in the bird food storage device flows into the food bowl; In response to the shielding type being a non-bird shielding type and the isolation door being in an open state, closing the isolation door.

3. The method according to claim 2, wherein: The performing occlusion recognition on the target video to determine the type of the occlusion includes: Performing image feature extraction on each frame of video image in the target video to generate a first image feature and obtain a first image feature sequence; Determine a feature difference between each first image feature and a second image feature in the first image feature sequence as a third image feature, and obtain a third image feature sequence, wherein the second image feature is an image feature corresponding to a video image captured by the camera in an unobstructed state; Filtering the third image features satisfying the image feature filtering condition in the third image feature sequence to obtain a fourth image feature sequence; Perform temporal occluder recognition on the fourth image feature sequence to obtain the occluder type.

4. The method according to claim 3, wherein: The updating of the bird food storage amount of the bird food storage device included in the bird feeder according to the first bird food consumption amount or the second bird food consumption amount comprises: Initializing a basic bird food storage capacity of the bird food storage device; The basic bird feed storage amount is updated according to the first bird feed consumption amount or the second bird feed consumption amount.

5. The method according to claim 4, wherein: After sending a bird food replenishment prompt to the target client in response to the updated bird food storage amount satisfying the bird food replenishment prompt condition, the method further includes: In response to failure to send, a bird food supplement prompt message is sent to a mobile terminal bound to the user account corresponding to the target client.

6. A bird food supplement reminder device, comprising: An acquisition unit is configured to acquire a target video, wherein the target video is acquired by a camera disposed in the bird feeder, and the camera is controlled to be turned on and to acquire video through an infrared sensor; An occluder identification unit is configured to perform occluder identification on the target video to determine the occluder type, wherein the occluder type includes: a bird occluder type and a non-bird occluder type; A bird identification unit is configured to perform bird identification on the target video in response to the occluder type being a bird occluder type, so as to generate bird information, wherein the bird information includes: bird type, head-down duration, and bird body shape information; A first determining unit is configured to determine whether there is a first bird unit food intake in a bird food intake database, wherein the first bird unit food intake is a bird unit food intake that matches current weather information, current season information, a current position of a bird feeder, and the bird type, wherein the current position of the bird feeder represents the location of the bird feeder, the weather information represents the real-time weather corresponding to the current position of the bird feeder, and the current season information represents the real-time season corresponding to the current position of the bird feeder; wherein the first determining unit is further configured to: Encoding the current weather information, the current season information and the bird type respectively to obtain the encoded current weather information, the encoded current season information and the encoded bird type, wherein the bird food intake database includes: a food intake information set, the food intake information in the food intake information set includes: weather type, season type, location fence, bird type, bird unit food intake, food intake information vector and bird body characteristics, and the food intake information vector is obtained by encoding the corresponding weather type, season type and bird type; concatenating the encoded current weather information, the encoded current season information, and the encoded bird type to obtain a query vector; Performing vector matching between the query vector and the food intake information vector included in each food intake information in the food intake information set to obtain vector similarity; In response to determining that there is target food intake information, determining whether the current position of the bird feeder is located within the position fence included in the target food intake information, wherein the target food intake information is food intake information having a corresponding vector similarity in the food intake information set that satisfies a first screening condition; In response to determining that the current position of the bird feeder is located within the position fence included in the target feeding amount information, determining the bird unit feeding amount included in the target feeding amount information as the first bird unit feeding amount; In response to determining that the target food intake information does not exist, sorting the food intake information in the food intake information set in descending order according to the vector similarity corresponding to the food intake information to obtain a food intake information sequence; In response to the number of food intake information in the food intake information sequence being ≥ 2K, selecting first K food intake information in the food intake information sequence as first candidate food intake information to obtain a first candidate food intake information sequence, wherein the value of K is 3; Performing a position vote according to the current position of the bird feeder and the position fence included in the first candidate food intake information in the first candidate food intake information sequence to obtain a second candidate food intake information sequence; Taking a weighted sum of the bird unit food intake included in each second candidate food intake information in the second candidate food intake information sequence as the first bird unit food intake; a second determination unit, configured to determine a first bird food consumption amount in response to the presence of the bird according to the head-down duration and the first bird unit feeding amount; The third determining unit is configured to determine the second bird unit food intake according to the bird body shape information in response to the absence of the second bird unit food intake according to the bird body shape information; wherein the third determining unit is further configured to: Extracting bird body shape features from the bird body shape information to obtain the target bird body shape features; Performing bird body feature matching on the target bird body feature with the bird body feature included in each food intake information in the food intake information set to obtain a body feature similarity; Determine the unit food intake of the bird included in the food intake information set whose corresponding body feature similarity meets the second screening condition as the second unit food intake of the bird; A fourth determining unit is configured to determine a second bird feed consumption amount according to the head-down duration and the second bird feed unit intake amount; an updating unit configured to update a bird food storage amount of a bird food storage included in the bird feeder according to the first bird food consumption amount or the second bird food consumption amount; The bird food replenishment prompting unit is configured to send a bird food replenishment prompting to a target client in response to the updated bird food storage amount satisfying a bird food replenishment prompting condition.

7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images