Livestock status monitoring method, device, storage medium and electronic device

Abstract

The present application discloses a method, device, storage medium and electronic device for monitoring the status of livestock, including: detecting whether there is first historical data recorded in a time series list of target livestock within a first historical time interval, the time series list is used to record the vital sign data transmitted by the detection device carried by the target livestock; if so, processing the first historical data according to a preset state recognition model to obtain the status detection result of the target livestock; when the status detection result indicates that the target livestock is in a state of leaving the pen, outputting prompt information that the target livestock is leaving the pen. By processing the first historical data recorded in the first historical time interval, the status detection result of the target livestock is obtained, and when the status detection result indicates that the target livestock is in a state of leaving the pen, prompt information can be output in time to remind the user, thereby ensuring the safety of the target livestock.

Description

Technical Field

[0001] The present application relates to the field of animal husbandry technology, and in particular to a method, device, storage medium and electronic device for monitoring livestock status. Background Art

[0002] As people's living standards improve, their demand for meat, eggs, dairy products and other foods continues to increase, which also promotes the development of animal husbandry.

[0003] Generally speaking, in the animal husbandry industry, livestock safety is often ensured through manual supervision. However, due to the large number of livestock, manual supervision obviously cannot meet the demand.

[0004] Therefore, there is an urgent need for a remote monitoring method to monitor the status of livestock leaving the pen in a timely manner to ensure the safety of the livestock. Summary of the invention

[0005] The embodiments of the present application provide a method, device, storage medium and electronic device for monitoring the status of livestock, which can remotely monitor the status of livestock leaving the pen.

[0006] In a first aspect, an embodiment of the present application provides a method for monitoring livestock status, comprising:

[0007] In a time series list of detecting the target livestock, whether first historical data is recorded in a first historical time interval, the time series list being used to record vital sign data transmitted by a detection device carried by the target livestock;

[0008] If yes, the first historical data is processed according to a preset state recognition model to obtain a state detection result of the target livestock;

[0009] When the status detection result indicates that the target livestock is in a state of leaving the pen, a prompt message of the target livestock leaving the pen is output.

[0010] In a second aspect, the present application also provides a livestock status monitoring device, including:

[0011] A detection module, used to detect whether first historical data is recorded in a time series list of the target livestock within a first historical time interval, the time series list being used to record vital sign data transmitted by a detection device carried by the target livestock;

[0012] A state recognition module, for processing the first historical data according to a preset state recognition model to obtain a state detection result of the target livestock if first historical data is recorded within a first historical time interval;

[0013] The information prompt module is used to output prompt information of the target livestock leaving the pen when the status detection result indicates that the target livestock is in the state of leaving the pen.

[0014] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program runs on a computer, the computer executes a livestock status monitoring method as provided in any embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application further provides an electronic device, including a processor and a memory, wherein the memory has a computer program, and the processor executes a livestock status monitoring method as provided in any embodiment of the present application by calling the computer program.

[0016] The technical solution provided by the embodiment of the present application is to detect the vital sign data of the target livestock through the detection device carried by the target livestock, and the time series list of the electronic device is used to record the vital sign data transmitted from the detection device. The electronic device detects whether the first historical data is recorded in the first historical time interval in the time series list of the target livestock, and when the first historical data is recorded in the first historical time interval, the first historical data is processed by a pre-trained state recognition model to obtain a state detection result, wherein the state detection result can indicate that the target livestock is in a state of leaving the pen or in the pen, thereby realizing remote monitoring of the state of the target livestock, facilitating the management of the target livestock by relevant personnel, and saving labor costs. Furthermore, when the state detection result indicates that the target livestock is in a state of leaving the pen, by outputting a prompt message that the target livestock has left the pen, it can remind the relevant personnel to promptly discover that the target livestock has left the pen, avoid the loss of the target livestock, and ensure the safety of the target livestock. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic diagram of an application scenario of the livestock status monitoring method provided in an embodiment of the present application.

[0019] Figure 2 A schematic flow chart of a method for monitoring livestock status provided in an embodiment of the present application.

[0020] Figure 3 A schematic diagram of a time sequence table in a method for monitoring livestock status provided in an embodiment of the present application.

[0021] Figure 4 A schematic diagram of the logic judgment of the livestock status monitoring method provided in an embodiment of the present application.

[0022] Figure 5A schematic diagram of the structure of a livestock status monitoring device provided in an embodiment of the present application.

[0023] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0025] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] The embodiment of the present application provides a method for monitoring the status of livestock. The execution subject of the method for monitoring the status of livestock can be the method for monitoring the status of livestock provided in the embodiment of the present application, or an electronic device integrating the method for monitoring the status of livestock. The method for monitoring the status of livestock can be implemented in hardware or software, and the electronic device can be a smart phone, a tablet computer, a PDA, a monitor, etc.

[0027] In order to better understand the technical solution provided by the embodiment of the present application, an application scenario is provided here to illustrate the technical solution provided by the embodiment of the present application. Figure 1 , Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application, wherein a breeding farm includes a confined area, the confined area is used to provide living space for livestock, and each livestock carries a detection device, the detection device is used to detect the vital sign data of the livestock, a base station is also provided in the confined area, and an electronic device is provided outside the confined area, the base station is used to connect the detection device and the electronic device to transmit the vital sign data detected by the detection device to the electronic device.

[0028] When the livestock is in the enclosure area, the detection device can establish a network connection with the base station to transmit the detected vital sign data to the electronic device. When the livestock is not in the enclosure area, the detection device cannot establish a network connection with the base station, and it is also impossible to transmit the detected vital sign data to the electronic device. Whenever the electronic device receives the vital sign data transmitted from the detection device, it records the vital sign data in a time series list, and processes the vital sign data recorded in the time series list to identify whether the livestock is in a state of leaving the pen or in a pen, thereby realizing remote monitoring of the state of the livestock in the enclosure area. Furthermore, when the livestock is in a state of leaving the pen, the electronic device can output a prompt message to promptly remind relevant personnel to manage the livestock that have left the pen.

[0029] It can be seen that the technical solution provided in the embodiment of the present application does not require improvement of existing facilities in the farm, thus saving the manpower cost of supervising livestock, and the method for identifying the status of livestock is simple, efficient and easy to implement.

[0030] It is understandable that the livestock mentioned in the embodiments of the present application may be pigs, cattle, sheep, etc., and the types and quantities of livestock in the enclosure area are not limited here. As long as the livestock can generate value in animal husbandry, they can be regarded as the livestock mentioned in the embodiments of the present application. Each livestock carries a detection device, which may be a sensor, an electronic tag, an ear tag, a wearable device, etc., and the detection device has a communication module, through which a communication connection can be established with a base station. Among them, the detection device is used to detect the vital signs data of the livestock in real time, and transmit the real-time detected vital signs data to the electronic device in real time by connecting to the base station. The vital signs data may be any one or more of temperature data, motion data, sound data, etc., as long as it is data that can characterize the life status of the livestock.

[0031] See also Figure 2 , Figure 2 A schematic diagram of a process flow of a method for monitoring livestock status provided in an embodiment of the present application. The specific process flow of the method for monitoring livestock status provided in an embodiment of the present application may be as follows:

[0032] 101. Detect whether first historical data is recorded in a time series list of a target livestock within a first historical time interval, the time series list being used to record vital sign data transmitted by a detection device carried by the target livestock.

[0033] In this embodiment, the target livestock carries a detection device, which can detect the vital sign data of the target livestock in real time. Therefore, the vital sign data detected by the detection device is continuously distributed on the time axis. The electronic device is used to record the vital sign data in the time series list of the target livestock. When the target livestock is in the enclosure area, the detection device can be connected to the base station, and the real-time detected vital sign data can also be transmitted to the electronic device in real time through the base station. Whenever the electronic device receives the vital sign data, the vital sign data is recorded in the time series list in chronological order, and the recording time is attached when recording the vital sign data. In this case, the vital sign data recorded in the time series list is continuously distributed. When the target livestock is not in the enclosure area, the detection device cannot be connected to the base station, that is, the real-time detected vital sign data cannot be transmitted to the electronic device through the base station, and the electronic device cannot record the vital sign data detected by the detection device during this period in the time series list. In this case, the vital sign data detected by the detection device during this period is not recorded in the time series list.

[0034] Exemplarily, the first historical time interval can be set to any length, such as 8 hours, 9 hours, 10 hours, 12 hours, etc., depending on actual needs and is not limited here.

[0035] Of course, the first historical time interval can also be set according to the activity of the target livestock, wherein the higher the activity of the target livestock, the shorter the first historical time interval is set, and the lower the activity of the target livestock, the longer the first historical time interval is set. For example, when the target livestock is a cow, the first historical time interval can be set to 8 hours due to the high activity of the cow, and when the target livestock is a pig, the first historical time interval can be set to 12 hours due to the low activity of the pig.

[0036] Exemplarily, the first historical time interval is calculated based on the current time, and the first historical time interval refers to a time period before the current time, wherein the vital sign data recorded in the first historical time interval in the time series list is referred to as the first historical data. For example, the current time is 16:00, and the first historical time interval indicates 9 hours, and detecting whether the first historical data is recorded in the first historical time interval is specifically detecting whether the vital sign data is recorded in the 9 hours from 5:00 to 16:00 in the time series list.

[0037] It is understandable that the vital sign data recorded in the time series list can be cleared at regular intervals to save storage space. It can also be continuously accumulated and recorded in chronological order to facilitate relevant personnel to check the vital sign data. The specific implementation method is not limited here. It is only necessary to explain that the time series list and detection device of each livestock are interrelated. The time series list and detection device of the livestock can be queried by the number set for each livestock.

[0038] In one embodiment, it is also possible to detect whether the first historical data is recorded in the first historical time interval in the time series list at every preset time length. The preset time length may be 0.2 hours, 0.5 hours, 0.8 hours, etc., which are not limited here. For example, the preset time length may be 0.5 hours, and the first historical time interval is 9 hours. The current time is 16:00, then what is detected is whether the vital sign data is recorded in the 9 hours from 5:00 to 16:00 in the time series list. After 0.5 hours, it continues to detect whether the first historical data is recorded in the first historical time interval in the time series list. At this time, the current time is 16:30, then what is detected is whether the vital sign data is recorded in the 9 hours from 5:30 to 16:30 in the time series list.

[0039] Of course, the preset duration can also be set according to the activity of the target livestock, wherein the preset duration is inversely proportional to the activity of the target livestock. When the activity of the target livestock is higher, a shorter preset duration can be set, and when the activity of the target livestock is lower, a longer preset duration can be set.

[0040] In another embodiment, it is also possible to continuously detect whether the first historical data is recorded in the first historical time interval in the time series list. For example, if the current time is 16:00, after detecting whether the vital sign data is recorded in the 9 hours from 5:00 to 16:00 in the time series list, it is then continued to detect whether the vital sign data is recorded in the 9 hours from 5:01 to 16:01 in the time series list, thereby realizing continuous detection of whether the vital sign data is recorded in the time series list.

[0041] 102. If first historical data is recorded within the first historical time interval, the first historical data is processed according to a preset state recognition model to obtain a state detection result of the target livestock.

[0042] When the first historical data is recorded in the first historical time interval, it means that the detection device can transmit the vital sign data to the electronic device at a certain moment in the first historical time interval, which can indicate that the detection device can transmit the vital sign data normally. When the detection device can transmit the vital sign data normally, the first historical data is input into the preset state recognition model for state recognition processing to obtain the state detection result of the target livestock, wherein the state detection result can indicate the state of the target livestock.

[0043] Exemplarily, the preset state recognition model is a classification model. For example, the machine learning methods that can be used in the model include logistic regression, decision tree, neural network, etc. The preset state recognition model learns the mapping relationship between sample data and state labels during the training phase, and the model parameters obtained through training represent this mapping relationship. After the trained preset state recognition model is obtained, the state detection result can be obtained by inputting the first historical data into the preset state recognition model for state recognition processing during the state recognition process.

[0044] In this embodiment, the state of the target livestock includes an out-of-pen state and an in-pen state. When the state detection result indicates that the target livestock is in the out-of-pen state, it means that the target livestock is not in the pen area. When the state detection result indicates that the target livestock is in the pen state, it means that the target livestock is in the pen area.

[0045] 103. When the status detection result indicates that the target livestock is in a state of leaving the pen, output prompt information that the target livestock has left the pen.

[0046] After the status detection result of the target livestock is obtained, the corresponding prompt information can be output. For example, when the status detection result indicates that the target livestock is in a state of leaving the pen, the prompt information of the target livestock leaving the pen is output, wherein the prompt information can be directly output by the electronic device, and the output mode can be any one or more of the following modes: text display, voice broadcast, vibration reminder, etc.

[0047] Of course, the prompt information of the target livestock leaving the pen can also be sent to other terminals through electronic devices, and the other terminals can give prompts. For example, the electronic device can be a monitoring device in the monitoring room of the farm, and the other terminal can be a mobile phone of a relevant person, or a loudspeaker set in the farm. When the other terminal is a mobile phone, the electronic device can send the prompt information of the target livestock leaving the pen to the mobile phone of the relevant person through any one or more methods such as phone, text message, and email. When the other terminal can be a loudspeaker, the electronic device can control the loudspeaker to broadcast the prompt information of the target livestock leaving the pen to remind the relevant person that the target livestock has left the pen.

[0048] For example, when the target livestock is detected to be in the out-of-pen state, the electronic device may mark the state of the target livestock as abnormal until the relevant personnel cancel the abnormal mark of the target livestock by operating the electronic device. Alternatively, when the target livestock is detected to be in the out-of-pen state, the electronic device may output a prompt message to remind the relevant personnel to mark the state of the target livestock as out-of-pen state.

[0049] When the status detection result indicates that the target livestock is in the pen, it is not necessary to output the prompt information, and the process can return to the step of continuing to detect whether the first historical data is recorded in the first historical time interval in the time series table.

[0050] In some embodiments, the above step 101 further includes:

[0051] If the first historical data is not recorded within the first historical time interval, a prompt message indicating abnormal data transmission is output.

[0052] When the first historical data is not recorded within the first historical time interval, it means that the detection device has abnormally transmitted the vital sign data, and a prompt message of abnormal data transmission can be issued to remind relevant personnel to check the abnormal situation of the detection device, wherein the abnormal situation of the detection device can be manifested as an abnormality in the software or hardware of the detection device itself, which in turn causes abnormalities in certain functions of the detection device. For example, when the detection device has abnormal conditions such as falling off, damage, or shutdown, the detection device cannot normally detect the vital sign data of the target livestock. For another example, when the detection device has abnormal conditions such as unstable network connection, network disconnection, and signal shielding, the detection device cannot transmit the detected vital sign data to the electronic device. It can be understood that the way in which the electronic device outputs the prompt message of abnormal data transmission can refer to the content mentioned in the above embodiment, which will not be repeated here.

[0053] In specific implementation, the present application is not limited by the execution order of the various steps described. If no conflict occurs, some steps can be performed in other orders or simultaneously.

[0054] The monitoring method of the livestock state provided in the embodiment of the present application can detect the vital sign data of the target livestock through the detection device carried by the target livestock, and set the time series list through the electronic device to record the vital sign data transmitted from the detection device in chronological order. When the state of the target livestock is identified, by detecting whether the first historical data is recorded in the first historical time interval in the time series list, when the first historical data is recorded in the first historical time interval, it means that the detection device can normally transmit the vital sign data, and then the first historical data is input into the preset state recognition model to obtain the state detection result of the target livestock, and the state detection result can indicate that the target livestock is in the state of leaving the pen or in the pen, so as to realize the real-time monitoring of the state of the target livestock, saving the manpower supervision cost. Furthermore, when the state detection result indicates that the target livestock is in the state of leaving the pen, it can also output the prompt information of the target livestock leaving the pen, and timely remind the relevant personnel that the target livestock is leaving the pen, so as to facilitate the relevant personnel to manage the target livestock, thereby preventing the target livestock from being lost and ensuring the safety of the target livestock.

[0055] The method described in the above embodiments is further described in detail below with examples.

[0056] In some embodiments, the first historical data is processed according to a preset state recognition model to obtain a state detection result of the target livestock, including:

[0057] Processing the first historical data according to a preset state recognition model to obtain a state parameter;

[0058] When the state parameter is a first preset value, whether second historical data is recorded in a second historical time interval in the detection time series list, the second historical time interval is smaller than the first historical time interval, and the first preset value indicates that the target livestock is in a state of leaving the pen;

[0059] If not, it is determined that the target livestock is in a state of being out of the pen;

[0060] If yes, it is determined that the target livestock is in the pen;

[0061] When the state parameter is a second preset value, it is determined that the target livestock is in the pen state.

[0062] In this embodiment, the first historical data is input into a preset state recognition model, and the output is a state parameter, wherein the state parameter includes a first preset value and a second preset value, the first preset value indicates that the target livestock is in a state of being out of the pen, and the second preset value indicates that the target livestock is in a state of being in the pen.

[0063] In this embodiment, the default state of the target livestock is set to the in-pen state. Only when it is determined that the target livestock is in the out-pen state, it is necessary to control the electronic device to output the prompt information of the target livestock leaving the pen; when the target livestock is in the in-pen state, it is not necessary to control the electronic device to output the prompt information of the target livestock leaving the pen. When the state parameter is the first preset value, it can be preliminarily determined that the target livestock may be in the out-pen state, and when the state parameter is the second preset value, it can be directly determined that the target livestock is in the in-pen state.

[0064] In order to avoid inaccurate state parameters obtained by the preset state recognition model, the state of the target livestock can be further determined, that is, when the state parameter is the first preset value, it is preliminarily determined that the target livestock may be in the out-of-fence state, and the time series list can be further detected to see whether the second historical data is recorded in the second historical time interval. If the second historical data is recorded in the second historical time interval, it indicates that the target livestock may be in the in-fence state. In this case, it cannot be determined that the target livestock is in the out-of-fence state, and the target livestock is still in the in-fence state by default; if the second historical data is not recorded in the second historical time interval, it continues to indicate that the target livestock is in the out-of-fence state. In this case, it can be determined that the target livestock is in the out-of-fence state. Exemplarily, the second historical time interval can be 0.1 hours, 0.2 hours, 0.3 hours, 0.4 hours, etc. before the current moment, as long as it is less than the first historical time interval. The vital sign data recorded in the second historical time interval is called the second historical data.

[0065] Among them, the second historical time interval is also calculated based on the current moment, and the second historical time interval is smaller than the first historical time interval. The explanation of the second historical time interval can refer to the explanation of the first historical time interval in the above embodiment, and will not be repeated here.

[0066] When detecting whether the second historical data is recorded in the second historical time interval in the time series table, the time series table can also be detected at intervals of a preset time length to determine whether the second historical data is recorded in the second historical time interval, or the second historical data can be continuously detected in the second historical time interval. The preset time length and the second historical time interval can also be adjusted in inverse proportion to the activity of the target livestock, and the details can be referred to the contents mentioned in the above embodiment.

[0067] In some embodiments, before determining that the target livestock is in a state of being released from the pen, the method further comprises:

[0068] If the second historical data is not recorded in the second historical time interval, then the time series table is checked to see whether the third historical data is recorded in the third historical time interval, and the third historical time interval is greater than the second historical time interval, and the third historical time interval is less than the first historical time interval;

[0069] If the third historical data is recorded in the third historical time interval, the step of determining that the target livestock is in a state of leaving the pen is executed.

[0070] In this embodiment, when the state parameter is a first preset value, it can be preliminarily determined that the target livestock may be in a state of leaving the pen, and when the second historical data is not recorded in the second historical time interval, it can be further determined that the target livestock may be in a state of leaving the pen, and then the time series list is further detected to see whether third historical data is recorded in a third historical time interval. If so, it can be directly determined that the target livestock is in a state of leaving the pen, and a prompt message of the target livestock leaving the pen is output, wherein the method of outputting the prompt message of the target livestock leaving the pen can refer to the content mentioned in the above embodiment, and will not be repeated here.

[0071] Among them, the third historical time interval is greater than the second historical time interval, and the third historical time interval is less than the first historical time interval. For example, referring to the first historical time interval and the second historical time interval listed in the above embodiment, the third historical time interval can be 5 hours, 6 hours, 7 hours, 8 hours, etc. before the current moment. The explanation of the third historical time interval can refer to the explanation of the first historical time interval in the above embodiment, which will not be repeated here. The vital sign data recorded in the third historical time interval is called the third historical data.

[0072] For the position relationship between the first historical time interval, the second historical time interval, and the third historical time interval in the time series table, see Figure 3 , Figure 3 A schematic diagram of a time series table in a method for monitoring livestock status provided in an embodiment of the present application. In the time series table, taking the current moment as a reference, the second historical time interval before the current moment is used to record the second historical data received during this period, the third historical time interval before the current moment is used to record the third historical data received during this period, and the first historical time interval before the current moment is used to record the first historical data received during this period.

[0073] In one embodiment, the third historical data within the third historical time interval may be detected at intervals of a preset time or continuously. The preset time and the third historical time interval may also be adjusted in inverse proportion to the activity of the target livestock. The specific implementation method may refer to the above-mentioned content and will not be described here.

[0074] In some embodiments, after detecting whether third historical data is recorded in the third historical time interval in the time series list, the method further includes:

[0075] If the third historical data is not recorded within the third historical time interval, it is determined that the performance of the detection device is abnormal, and prompt information of the abnormal performance of the detection device is output.

[0076] In this embodiment, when the first historical data is recorded in the first historical time interval, it means that the detection device can transmit the vital sign data normally, that is, the detection device can transmit the vital sign data normally in the first historical time interval before the third historical time interval, and when the third historical data is not recorded in the third historical time interval, it means that the detection device has a performance abnormality in the third historical time interval, for example, the power is exhausted and the detection function cannot be enabled, or it falls off the target livestock and cannot detect the vital sign data of the target livestock normally, or there is a network failure and it cannot connect to the base station to transmit the vital sign data to the electronic device, etc.

[0077] Therefore, a prompt message indicating that the detection device has abnormal performance can be output to remind relevant personnel to check the performance of the detection device so that the detection device can normally detect the vital sign data and transmit the detected vital sign data to the electronic device. The method of outputting the prompt message indicating that the detection device has abnormal performance can refer to the content of outputting the prompt message indicating that the target livestock has left the pen in the above embodiment, and will not be repeated here.

[0078] In some embodiments, before the electronic device records the vital sign data in the time series list, it also includes:

[0079] Filter out some of the vital sign data that is smaller than a preset threshold value;

[0080] The remaining part of the vital sign data is recorded in a time series table.

[0081] In this embodiment, the vital sign data transmitted from the detection device can be first screened, and then the vital sign data greater than or equal to the preset threshold value in the vital sign data is recorded in the time series list. For example, when the vital sign data includes temperature data, the preset threshold value is set to the lowest body temperature value of the livestock, so that the part of the temperature data greater than the lowest body temperature value is recorded in the time series list, and the transmission time of each part of the temperature data is recorded. Of course, another preset threshold value can also be set to filter out the part of the temperature data greater than the highest body temperature value of the livestock. When the vital sign data includes motion data, the preset threshold value is set to 0, or is set to the motion data of the target livestock when it is resting, so that the part of the motion data greater than 0, or greater than the motion data of the target livestock when it is resting, is recorded in the time series list, wherein the motion data may include the heart rate, pulse, speed, etc. of the target livestock. When the motion data is expressed by speed, a gyroscope can be set in the detection device, and the acceleration in the three-axis direction is detected by the gyroscope, and the speed of the target livestock can be obtained by summing the three accelerations detected in the three-axis direction.

[0082] It can be understood that when the vital sign data includes both temperature data and motion data, the vital sign data can be partially filtered out by combining the filtering conditions of the two, and then the remaining vital sign data can be recorded in a time series list with the transmission time.

[0083] In some embodiments, before outputting the prompt information of the target livestock leaving the pen, the method further includes:

[0084] When the status detection result indicates that the target livestock is in a state of leaving the pen, abnormal identification information of the target livestock or the detection device is obtained;

[0085] If the abnormal identification information indicates that the target livestock or the detection device has no abnormal identification, a prompt message indicating that the target livestock has left the pen is output.

[0086] In this embodiment, when the status detection result indicates that the target livestock is in a state of leaving the pen, abnormal identification information of the target livestock or the detection device can be further obtained to determine whether the target livestock or the detection device has an abnormal identification. When the target livestock or the detection device does not have an abnormal identification, a prompt information that the target livestock has left the pen is output, thereby improving the accuracy of determining whether the target livestock is in a state of leaving the pen.

[0087] When there is an abnormal mark on the target livestock or the detection device, a prompt message of the abnormal target livestock or the detection device can be output to remind relevant personnel to check the target livestock or the detection device, and then eliminate the abnormal situation and eliminate the abnormal mark on the target livestock or the detection device, so as to facilitate subsequent continuous remote monitoring of the status of the target livestock.

[0088] Exemplarily, the abnormality identification information includes: a life abnormality identification of the target livestock, a performance abnormality identification of the detection device, and a network abnormality identification of the base station used to transmit vital sign data.

[0089] Among them, the target livestock’s life abnormality mark may include the target livestock’s death mark, the mark of leaving the pen, etc. The detection device’s performance abnormality mark includes the detection device’s power exhaustion mark, the detection function abnormality mark, the network abnormality mark, etc. The base station’s network abnormality mark includes the network no signal mark, the network connection unstable mark, etc.

[0090] The abnormal identification of the target livestock or the detection device can be performed by relevant personnel according to the prompt information in the electronic device according to the target livestock, or the target livestock can be marked as abnormal when the electronic device detects the abnormality. The specific implementation method is not limited here, and those skilled in the art can set it according to actual needs.

[0091] It can be understood that when the electronic device loads the information of the target livestock, the abnormal identification information included in the information can be displayed. Relevant personnel can know that it is an abnormal identification by reading the abnormal identification information, and then manage the numbering and detection device of the target livestock in time, or check the base station, so as to ensure remote and unified monitoring of many livestock in the pen area, thereby saving the labor cost of supervising livestock, improving the effectiveness of livestock supervision, and ensuring the safety of livestock.

[0092] Exemplarily, the abnormal identification information can be stored in an electronic device or in a cloud server, and the specific storage method is not limited here.

[0093] In some embodiments, in a time series list for detecting target livestock, whether first historical data is recorded within a first historical time interval, before the time series list is used to record the vital sign data transmitted by the detection device carried by the target livestock, a step of obtaining abnormal identification information of the target livestock or the detection device can also be executed.

[0094] In this embodiment, that is, before detecting the status of the target livestock, it is also possible to first determine whether the target livestock or the detection device has an abnormal identification by obtaining abnormal identification information of the target livestock or the detection device. When there is no abnormal identification, the time series list of the target livestock is detected to determine whether the first historical data is recorded within the first historical time interval. The time series list is used to record the vital sign data transmitted by the detection device carried by the target livestock.

[0095] When an abnormal mark exists, the execution outputs a prompt message indicating that an abnormal mark exists.

[0096] Among them, by pre-detecting the abnormal life signs of the target livestock, the abnormal performance signs of the detection device, etc., it is possible to rule out abnormal situations of the target livestock or the detection device. When there is no abnormality in the target livestock or the detection device, it is continued to determine whether the target livestock is in a state of leaving the pen, thereby improving the accuracy of the determination that the target livestock is in a state of leaving the pen.

[0097] In order to better understand the solution provided by the embodiment of the present application, a specific embodiment is used here for explanation. Figure 4 , Figure 4 This is a logical judgment diagram of the livestock status monitoring method provided in the embodiment of the present application.

[0098] After the target livestock is determined, it is detected whether the first historical data is recorded in the first historical time interval in the time series list of the target livestock. If so, the step of processing the first historical data according to the preset state recognition model to obtain the state parameter is executed.

[0099] When the state parameter is the first preset value, the detection time series table is used to determine whether second historical data is recorded in the second historical time interval. If so, the step of determining whether the target livestock is in the pen is executed; if not, the detection time series table is used to determine whether third historical data is recorded in the third historical time interval. If so, the step of determining whether the target livestock is out of the pen is executed; if not, the step of determining whether the performance of the detection device is abnormal and outputting prompt information of the abnormal performance of the detection device is executed.

[0100] When the state parameter is a second preset value, the step of determining that the target livestock is in a pen state is performed.

[0101] In some embodiments, the livestock status monitoring method provided in the embodiments of the present application further includes a training method for a preset status recognition model, the method comprising:

[0102] Obtain a training set, where the training set includes multiple sample data, and each sample data has a corresponding state label;

[0103] Input each sample data into a preset state recognition model for state recognition processing to obtain a state detection result of each sample data;

[0104] According to the difference between the state label corresponding to each sample data and the state detection result, the preset state recognition model is iteratively trained until the model converges.

[0105] When training the preset state recognition model, the model training is performed by inputting the training set into the preset state recognition model. The training set includes a plurality of sample data, each sample data has a corresponding state label, when the state label is a first preset value, it indicates that the livestock is in the out-of-pen state, and when the state label is a second preset value, it indicates that the livestock is in the in-pen state.

[0106] In this embodiment, each sample data is either continuously distributed on the time axis or discretely distributed on the time axis. When the preset state recognition model is trained by the sample data, what is learned is the mapping relationship between the distribution of the sample data on the time axis and the state label. For example, when the distribution time of the sample data on the time axis is the total time, and the proportion of the time when the sample data is last distributed on the time axis in the total time is greater than the preset threshold, the state label of the sample data is the first preset value, otherwise it is the second preset value; when the sum of the time when the sample data is continuously distributed on the time axis in the total time is greater than the preset threshold, the state label of the sample data is the first preset value, otherwise it is the second preset value.

[0107] After the state recognition processing is performed on the sample data through the preset state recognition model, the state detection result can be output, wherein the model parameters can be adjusted according to the difference between the state detection result indication and the state label to realize iterative training of the model until the model converges.

[0108] In one embodiment, the sample data may also be the time series list mentioned in the embodiment of the present application. When the preset state recognition model is trained through the time series list, what is learned is the mapping relationship between the distribution of the vital sign data in the time series list and the state label.

[0109] Exemplarily, the vital sign data recorded in the first historical time interval can also be extracted from the time series list of each livestock for training a preset state recognition model to learn the mapping relationship between the first historical data distributed in the first historical time interval and the state label.

[0110] As can be seen from the above, the livestock status monitoring method proposed in the embodiment of the present invention establishes a time series list, and the time series list is used to record the vital sign data transmitted from the detection device carried by each livestock. When the status of the livestock is identified, it can be detected whether the first historical data is recorded in the first historical time interval in the time series list. When the first historical data is recorded, it means that the detection device can normally transmit the detected data. After that, the first historical data is input into the preset state recognition model for processing to obtain the state detection result. When the state detection result indicates that the livestock is in the out-of-pen state, it can also continue to detect whether the second historical data is recorded in the second historical time interval in the time series list. When the second historical data is not recorded in the second historical time interval, it means that the livestock may be in the out-of-pen state, and then continue to detect whether the third historical data is recorded in the third historical time interval in the time series list. When the third historical data is recorded, it is determined that the livestock has left the pen, and the prompt information of the livestock leaving the pen can be directly output to remind relevant personnel that the livestock has left the pen, so as to facilitate the relevant personnel to control the livestock that have left the pen, thereby improving the safety supervision of the livestock.

[0111] In one embodiment, a monitoring device 200 for livestock status is also provided. Figure 5 , Figure 5 The structure diagram of the monitoring device 200 for livestock status provided in the embodiment of the present application is shown in FIG. The monitoring device 200 for livestock status is applied to an electronic device, and the monitoring device 200 for livestock status includes:

[0112] A detection module 201 is used to detect whether first historical data is recorded in a time series list of a target livestock within a first historical time interval, and the time series list is used to record the vital sign data transmitted by the detection device carried by the target livestock;

[0113] A state recognition module 202 is used to process the first historical data according to a preset state recognition model to obtain a state detection result of the target livestock if the first historical data is recorded within the first historical time interval;

[0114] The information prompt module 203 is used to output prompt information of the target livestock leaving the pen when the status detection result indicates that the target livestock is in the state of leaving the pen.

[0115] In some embodiments, the state identification module 202 is further configured to:

[0116] Processing the first historical data according to a preset state recognition model to obtain a state parameter;

[0117] When the state parameter is a first preset value, the detection module 201 is further configured to:

[0118] In the detection time series table, whether second historical data is recorded in the second historical time interval, the second historical time interval is shorter than the first historical time interval, and the first preset value indicates that the target livestock is in a state of leaving the pen;

[0119] The state identification module 202 is also used for:

[0120] If not, it is determined that the target livestock is in a state of being out of the pen;

[0121] If yes, it is determined that the target livestock is in the pen;

[0122] When the state parameter is a second preset value, it is determined that the target livestock is in the pen state.

[0123] In some embodiments, before determining that the target livestock is in the out-of-pen state, the detection module 201 is further used to:

[0124] If not, then checking whether the time series table records third historical data in the third historical time interval, the third historical time interval is greater than the second historical time interval, and the third historical time interval is less than the first historical time interval;

[0125] The state identification module 202 is also used for:

[0126] If the third historical data is recorded in the third historical time interval, the step of determining that the target livestock is in a state of leaving the pen is executed.

[0127] In some embodiments, after detecting whether the third historical data is recorded in the third historical time interval in the time series list, the state identification module 202 is further used to:

[0128] If the third historical data is not recorded within the third historical time interval, it is determined that the performance of the detection device is abnormal;

[0129] The information prompt module 203 is also used for:

[0130] Outputs prompt information of abnormal performance of the detection device.

[0131] In some embodiments, before outputting the prompt information of the target livestock leaving the pen, the state identification module 202 is further used to:

[0132] When the status detection result indicates that the target livestock is in a state of leaving the pen, abnormal identification information of the target livestock or the detection device is obtained;

[0133] The information prompt module 203 is also used for:

[0134] If the abnormal identification information indicates that the target livestock or the detection device does not have an abnormal identification, a prompt message indicating that the target livestock has left the pen is output.

[0135] Exemplarily, the vital sign data includes temperature data and movement data obtained by the detection device detecting the target livestock; or,

[0136] The abnormal identification information includes: a life abnormality identification of the target livestock, a performance abnormality identification of the detection device, and a network abnormality identification of the base station used to transmit vital sign data.

[0137] It should be noted that the livestock status monitoring device 200 provided in the embodiment of the present application belongs to the same concept as the livestock status monitoring method in the above embodiment. Any method provided in the livestock status monitoring method embodiment can be implemented through the livestock status monitoring device 200. The specific implementation process is detailed in the livestock status monitoring method embodiment, which will not be repeated here.

[0138] As can be seen from the above, the livestock status monitoring device 200 proposed in the embodiment of the present application can establish a time series list, and the time series list is used to record the vital sign data transmitted from the detection device carried by each livestock. When the status of the livestock is identified, it can be detected in the time series list whether the first historical data is recorded in the first historical time interval. When the first historical data is recorded, it means that the detection device can normally transmit the detected data. After that, the first historical data is input into the preset state recognition model for processing to obtain the state detection result. When the state detection result indicates that the livestock is in the out-of-pen state, it can also continue to detect whether the second historical data is recorded in the second historical time interval in the time series list. When the second historical data is not recorded in the second historical time interval, it means that the livestock may be in the out-of-pen state, and then continue to detect whether the third historical data is recorded in the third historical time interval in the time series list. When the third historical data is recorded, it is determined that the livestock has left the pen, and the prompt information of the livestock leaving the pen can be directly output to remind relevant personnel that there is livestock leaving the pen, so as to facilitate the relevant personnel to control the livestock leaving the pen, thereby improving the safety supervision of the livestock.

[0139] The present application also provides an electronic device, which may be a smart phone, a tablet computer, a PDA, or a monitoring device. Figure 6 As shown, Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 300 includes a processor 301 having one or more processing cores, a memory 302 having one or more computer-readable storage media, and a computer program stored in the memory 302 and executable on the processor. The processor 301 is electrically connected to the memory 302. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or arrange components differently.

[0140] The processor 301 is the control center of the electronic device 300. It uses various interfaces and lines to connect various parts of the entire electronic device 300, executes various functions of the electronic device 300 and processes data by running or loading software programs and / or modules stored in the memory 302, and calling data stored in the memory 302, thereby monitoring the electronic device 300 as a whole.

[0141] In the embodiment of the present application, the processor 301 in the electronic device 300 will load instructions corresponding to the processes of one or more application programs into the memory 302 according to the following steps, and the processor 301 will run the application programs stored in the memory 302 to implement various functions:

[0142] In a time series list of detecting the target livestock, whether first historical data is recorded in a first historical time interval, the time series list being used to record vital sign data transmitted by a detection device carried by the target livestock;

[0143] If yes, the first historical data is processed according to a preset state recognition model to obtain a state detection result of the target livestock;

[0144] When the status detection result indicates that the target livestock is in a state of leaving the pen, a prompt message of the target livestock leaving the pen is output.

[0145] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0146] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] As can be seen from the above, the electronic device provided in this embodiment can establish a time series list, and the time series list is used to record the vital sign data transmitted from the detection device carried by each livestock. When the state of the livestock is identified, it can be detected in the time series list whether the first historical data is recorded in the first historical time interval. When the first historical data is recorded, it means that the detection device can normally transmit the detected data. After that, the first historical data is input into the preset state recognition model for processing to obtain the state detection result. When the state detection result indicates that the livestock is in the out-of-pen state, it can also continue to detect whether the second historical data is recorded in the second historical time interval in the time series list. When the second historical data is not recorded in the second historical time interval, it means that the livestock may be in the out-of-pen state, and then continue to detect whether the third historical data is recorded in the third historical time interval in the time series list. When the third historical data is recorded, it is determined that the livestock has left the pen, and the prompt information of the livestock leaving the pen can be directly output to remind relevant personnel that there is livestock leaving the pen, so as to facilitate the relevant personnel to control the livestock leaving the pen, thereby improving the safety supervision of the livestock.

[0148] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0149] To this end, the embodiment of the present application provides a computer-readable storage medium. A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps:

[0150] In a time series list of detecting the target livestock, whether first historical data is recorded in a first historical time interval, the time series list being used to record vital sign data transmitted by a detection device carried by the target livestock;

[0151] If yes, the first historical data is processed according to a preset state recognition model to obtain a state detection result of the target livestock;

[0152] When the status detection result indicates that the target livestock is in a state of leaving the pen, a prompt message of the target livestock leaving the pen is output.

[0153] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0154] The above-mentioned storage medium may be ROM / RAM, a magnetic disk, an optical disk, etc. Since the computer program stored in the storage medium can execute the steps in any livestock status monitoring method provided in the embodiments of the present application, the beneficial effects that can be achieved by any livestock status monitoring method provided in the embodiments of the present application can be achieved, as detailed in the previous embodiments, which will not be repeated here.

[0155] The above is a detailed introduction to a livestock status monitoring method, device, medium and electronic device provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for monitoring livestock status, characterized in that: The method comprises: Detecting whether first historical data is recorded in a first historical time interval in a time series list of the target livestock, the time series list being used to record the vital sign data transmitted by the detection device carried by the target livestock, wherein the first historical time interval is a first time period before the current moment; If yes, the first historical data is processed according to a preset state recognition model to obtain a state detection result of the target livestock; When the state detection result indicates that the target livestock is in a state of leaving the pen, outputting prompt information that the target livestock has left the pen; The processing of the first historical data according to the preset state recognition model to obtain the state detection result of the target livestock includes: Processing the first historical data according to a preset state recognition model to obtain state parameters; When the state parameter is a first preset value, detecting whether second historical data is recorded in a second historical time interval in the time series list, the second historical time interval being a second time period before the current moment, the second historical time interval being smaller than the first historical time interval, and the first preset value indicating that the target livestock is in a state of leaving the pen; If not, it is determined that the target livestock is in a state of leaving the pen; If yes, it is determined that the target livestock is in a pen; When the state parameter is a second preset value, it is determined that the target livestock is in a pen state.

2. The method according to claim 1, characterized in that Before determining that the target livestock is in a state of leaving the pen, the method further comprises: If not, then detecting whether third historical data is recorded in a third historical time interval in the time series table, the third historical time interval being a third time period before the current moment, the third historical time interval being greater than the second historical time interval, and the third historical time interval being less than the first historical time interval; If the third historical data is recorded within the third historical time interval, the step of determining that the target livestock is in a state of leaving the pen is executed.

3. The method according to claim 2, characterized in that After detecting whether third historical data is recorded in the third historical time interval in the time series list, the method further includes: If the third historical data is not recorded within the third historical time interval, it is determined that the performance of the detection device is abnormal, and prompt information of the abnormal performance of the detection device is output.

4. The method according to any one of claims 1 to 3, characterized in that: Before outputting the prompt information of the target livestock leaving the pen, the method further includes: When the state detection result indicates that the target livestock is in a state of leaving the pen, obtaining abnormal identification information of the target livestock or the detection device; If the abnormal identification information indicates that there is no abnormal identification on the target livestock or the detection device, a prompt message indicating that the target livestock has left the pen is output.

5. The method according to claim 4, characterized in that The vital sign data includes temperature data and movement data obtained by the detection device detecting the target livestock; or, The abnormal identification information includes: a life abnormality identification of the target livestock, a performance abnormality identification of the detection device, and a network abnormality identification of a base station used to transmit the vital sign data.

6. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtain a training set, wherein the training set includes a plurality of sample data, each sample data having a corresponding state label; Inputting each sample data into a preset state recognition model to perform state recognition processing, and obtaining a state detection result of each sample data; According to the difference between the state label corresponding to each sample data and the state detection result, the preset state recognition model is iteratively trained until the model converges.

7. A monitoring device for livestock status, characterized in that: include: A detection module, used to detect whether first historical data is recorded in a first historical time interval in a time series list of a target livestock, wherein the time series list is used to record the vital sign data transmitted by a detection device carried by the target livestock, wherein the first historical time interval is a first time period before the current moment; a state recognition module, configured to process the first historical data according to a preset state recognition model to obtain a state detection result of the target livestock if the first historical data is recorded within the first historical time interval; An information prompt module, configured to output prompt information indicating that the target livestock is leaving the pen when the status detection result indicates that the target livestock is in a state of leaving the pen; The state recognition module is further used to process the first historical data according to a preset state recognition model to obtain state parameters; The detection module is further used for detecting, when the state parameter is a first preset value, whether second historical data is recorded in a second historical time interval in the time series list, the second historical time interval being a second time period before the current moment, the second historical time interval being smaller than the first historical time interval, and the first preset value indicating that the target livestock is in a state of leaving the pen; The state identification module is further used to determine that the target livestock is in a state of leaving the pen if no; The state recognition module is further used to determine that the target livestock is in a pen state if yes; The state recognition module is also used to determine that the target livestock is in a pen state when the state parameter is a second preset value.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed on a computer, the computer is enabled to execute the method for monitoring livestock status according to any one of claims 1 to 6.

9. An electronic device comprising a processor and a memory, wherein the memory stores a computer program, characterized in that: The processor is used to execute the livestock status monitoring method according to any one of claims 1 to 6 by calling the computer program.

Images