Livestock state monitoring method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a livestock state monitoring method and device, electronic equipment and a storage medium, and relates to the technical field of intelligent breeding. Acquiring a plurality of physiological indexes respectively corresponding to the livestock to be monitored in a plurality of preset time periods, wherein each preset time period corresponds to one or more physiological indexes; and determining at least one first target physiological state of the to-be-monitored livestock according to the plurality of physiological indexes corresponding to the plurality of preset time periods. By adopting the above technical scheme, the at least one first target physiological state of the to-be-monitored livestock can be determined according to the plurality of physiological indexes corresponding to the plurality of preset time periods, the conditions of oestrus, illness, scare and the like of the livestock can be automatically and accurately predicted, intervention measures can be conveniently taken in time, the livestock breeding cost is reduced, and the livestock breeding efficiency is improved. The livestock breeding yield is improved.

Description

Technical Field

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

[0002] In livestock farming, timely understanding of the current status of livestock (such as livestock in estrus, illness or fright) and taking corresponding measures are of great significance for improving livestock production. For example, if livestock in estrus is monitored in time, livestock conception can be completed as soon as possible, and if livestock illness is monitored in time, corresponding treatment measures can be taken.

[0003] In the related art, the physiological state of livestock is usually determined through manual monitoring, which has high labor costs and is not timely. Taking the monitoring of livestock estrus as an example, manual estrus detection is usually adopted in the related art, such as determining whether the livestock is in estrus by observing the appearance of the physiological parts of the livestock. Since the frequency of manual estrus detection is limited, the estrus time of livestock is short, and the estrus time of multiple livestock is not uniform, manual estrus detection cannot detect livestock estrus in time, and manual estrus detection is costly and has certain risks. Summary of the invention

[0004] The purpose of the embodiments of the present disclosure is to provide a method, device, electronic device and storage medium for monitoring livestock status.

[0005] To solve the above technical problems, the embodiments of the present disclosure are implemented through the following aspects.

[0006] According to a first aspect of an embodiment of the present disclosure, a method for monitoring livestock status is provided, the method comprising: Acquire multiple physiological indicators corresponding to the livestock to be monitored in multiple preset time periods, each preset time period corresponds to one or more physiological indicators; determine at least one first target physiological state of the livestock to be monitored based on the multiple physiological indicators corresponding to the multiple preset time periods.

[0007] According to a second aspect of an embodiment of the present disclosure, there is provided a device for monitoring livestock status, the device comprising: The acquisition module is used to obtain multiple physiological indicators corresponding to the livestock to be monitored in multiple preset time periods, each preset time period corresponds to one or more physiological indicators; the determination module is used to determine at least one first target physiological state of the livestock to be monitored based on the multiple physiological indicators corresponding to the multiple preset time periods.

[0008] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is used to execute the steps of the livestock status monitoring method described in the first aspect above.

[0009] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the steps of the livestock status monitoring method described in the first aspect.

[0010] One of the above technical solutions has the following advantages or beneficial effects: it can determine at least one first target physiological state of the livestock to be monitored through multiple physiological indicators corresponding to multiple preset time periods, automatically and accurately predict the estrus, illness, fright, etc. of the livestock, so as to facilitate timely intervention measures, reduce the cost of livestock breeding, and increase the output of livestock breeding.

[0011] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0012] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 A schematic diagram showing a flow chart of a method for monitoring livestock status provided by an embodiment of the present disclosure; Figure 2 Another schematic flow chart of the livestock status monitoring method provided by the embodiment of the present disclosure is shown; Figure 3 Another schematic flow chart of the livestock status monitoring method provided by the embodiment of the present disclosure is shown; Figure 4 Another schematic flow chart of the livestock status monitoring method provided by the embodiment of the present disclosure is shown; Figure 5 Another schematic flow chart of the livestock status monitoring method provided by the embodiment of the present disclosure is shown; Figure 6A block diagram showing a device for monitoring livestock status provided by an embodiment of the present application; Figure 7 A schematic diagram of the hardware structure of an electronic device for executing the livestock status monitoring method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the technical solutions in the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present disclosure.

[0016] Figure 1 A schematic diagram showing a flow chart of a method for monitoring livestock status provided by an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the method may include the following steps: In step S101, a plurality of physiological indicators corresponding to the livestock to be monitored in a plurality of preset time periods are obtained.

[0017] Each preset time period corresponds to one or more physiological indicators.

[0018] The livestock to be monitored can be pigs, cattle, sheep, horses, donkeys, etc. raised in a stable. This application does not limit the type of livestock to be monitored.

[0019] In some embodiments, the preset time period may be a continuous time period of multiple hours, or may be a plurality of discontinuous time periods of hours set at preset intervals, such as 0-1 o'clock, 3-4 o'clock, 5-6 o'clock, 7-8 o'clock, and so on every day. The preset time period may also be a time period excluding some special time periods such as livestock sleeping time periods and feeding time periods. It is understandable that due to their different physiological laws, the preset time periods corresponding to different types of livestock may be different, and of course may be partially or completely the same, and the length of the time period may also be half an hour or two hours, and this application does not limit this.

[0020] In some embodiments, the physiological indicator may include at least one of a respiratory physiological indicator, a heartbeat physiological indicator, and a behavioral physiological indicator.

[0021] Among them, respiratory physiological indicators are related indicators used to characterize the respiratory characteristics of livestock, such as respiratory frequency, rate of change of respiratory frequency, duration of respiratory frequency exceeding or falling below a threshold, proportion of time when respiratory frequency exceeds or falls below a threshold, etc. The rate of change of respiratory frequency can be the rate of change of respiratory frequency in the current time period relative to the respiratory frequency in any previous time period, or the rate of change of respiratory frequency in the current time period relative to a preset standard respiratory frequency (such as the daily average respiratory frequency of livestock). In some embodiments, in order to obtain accurate respiratory physiological indicators, the respiratory physiological indicators of the livestock to be monitored when lying still can be obtained.

[0022] Heartbeat physiological indicators are related indicators used to characterize the heartbeat characteristics of livestock, such as heartbeat frequency (also called heart rate), heartbeat frequency change rate (also called heart rate change rate), the duration of heartbeat exceeding or falling below a threshold, the proportion of time when heartbeat exceeds or falls below a threshold, etc. The heartbeat frequency change rate can be the heartbeat frequency change rate in the current time period relative to the heartbeat frequency of any previous time period, or the heartbeat frequency change rate in the current time period relative to a preset standard heartbeat frequency (such as the daily average heartbeat frequency of livestock). In some embodiments, in order to obtain accurate heartbeat physiological indicators, the heartbeat physiological indicators of the livestock to be monitored when they are lying still can be obtained.

[0023] Behavioral physiological indicators are related indicators used to characterize the behavioral characteristics of livestock in non-lying positions, such as the proportion of non-lying time, the proportion of time in different postures (standing, walking or running), the number of posture changes (such as the number of changes between lying, standing, and walking), the longest time to maintain the same posture, etc. Of course, more behavioral indicators can be set as needed, and this application does not limit this.

[0024] It is understandable that due to the differences in populations of different types of livestock, the physiological indicators corresponding to different types of livestock may be different. Of course, they may also be partially or completely the same.

[0025] In step S102, at least one first target physiological state of the livestock to be monitored is determined according to a plurality of physiological indicators corresponding to a plurality of preset time periods.

[0026] After obtaining multiple physiological indicators corresponding to the livestock to be monitored in multiple preset time periods, at least one first target physiological state of the livestock to be monitored can be determined based on the timing characteristics between the multiple physiological indicators corresponding to the multiple preset time periods.

[0027] Among them, the first target physiological state can be the physiological state of the individual livestock to be monitored, such as whether the livestock to be monitored is in estrus, the intensity of estrus, whether the livestock to be monitored is sick, the predicted ovulation date (that is, the time interval from the current time to ovulation, which can be accurate to the hour level), and the type of illness of the livestock to be monitored (such as cold or diarrhea). At least one of them.

[0028] Figure 2 A schematic diagram showing a flow chart of a method for monitoring livestock status provided by an embodiment of the present disclosure is shown as follows: Figure 2 As shown in (a), step S102 may include the following steps: In step S1021, the physiological indicators corresponding to a plurality of preset time periods are input into a pre-trained livestock state prediction model to obtain at least one first target physiological state of the livestock to be monitored. The livestock state prediction model is a deep learning model for time series prediction.

[0029] The livestock status prediction model may be a deep learning model for time series prediction, including but not limited to a model based on MLP (Multilayer Perceptron), a model based on RNN (Recurrent Neural Network), a model based on CNN (Convolutional Neural Network), and a model based on Transformer. This application does not specifically limit the type of livestock status prediction model.

[0030] The livestock state prediction model can be trained by a training data set. The training data set can include training physiological indicators and corresponding physiological state labels. The training physiological indicators can also include at least one of respiratory physiological indicators, heartbeat physiological indicators, and behavioral physiological indicators. The physiological state label can be, for example, the target physiological state corresponding to the training physiological indicator, such as whether it is estrus, whether it is sick, the time interval from the current time to ovulation, and the type of illness of the livestock to be monitored. The acquisition of the physiological state label can refer to the records in the relevant technology, and this application will not elaborate on this.

[0031] When training the livestock state prediction model, the training physiological indicators in the training data set can be input into the livestock state prediction model to be trained, and the loss value is calculated according to the output result of the livestock state prediction model (i.e., the predicted physiological state) and the physiological state label. When multiple physiological state labels are included, the loss value can be the weighted cumulative value of the loss values ​​corresponding to the multiple predicted physiological states and the corresponding physiological state labels. Then, with the goal of minimizing the loss value, the model parameters of the livestock state prediction model to be trained are iteratively optimized until the preset iteration termination condition is reached, and a trained livestock state prediction model is obtained.

[0032] It is understandable that although examples of multiple physiological indicators are listed in this application, for a certain type of livestock, it does not mean that all physiological indicators are input into the livestock state prediction model to predict the first target physiological state. In some embodiments, part or all of the multiple physiological indicators can be input into the livestock state prediction model to predict the first target physiological state. In some embodiments, the input of the livestock state prediction model can also include the type of livestock. It is understandable that for different types of livestock, the types of physiological indicators input into the livestock state prediction model can be the same or different.

[0033] In some embodiments, different first target physiological states can be obtained by inputting physiological indicators of different granularities into corresponding livestock state prediction models. For example, the predicted ovulation date (the time interval from the current time to ovulation) is obtained by inputting physiological indicators of hourly level into the first livestock state prediction model, and the intensity of estrus is obtained by inputting physiological indicators of daily level into the second livestock state prediction model.

[0034] like Figure 2 As shown in (b), step S102 may further include the following steps: In step S1022, at least one first target physiological state of the livestock to be monitored is determined according to the physiological indicators corresponding to the plurality of preset time periods.

[0035] In some embodiments, at least one first target physiological state of the livestock to be monitored may also be determined by corresponding physiological indicators and / or the changing patterns of physiological indicators in a plurality of preset time periods.

[0036] Specifically, step S1022 may be implemented by at least one of the following implementations: Method 1: determining whether the livestock to be monitored is in estrus based on at least one of whether the increase in the proportion of the non-lying time of the livestock to be monitored exceeds the first threshold, whether the time when the respiratory rate of the livestock to be monitored exceeds the second threshold exceeds the third threshold, and whether the time when the heart rate of the livestock to be monitored exceeds the fourth threshold exceeds the fifth threshold.

[0037] For example, the livestock to be monitored is a pig, for example, the first threshold value may be 100%, the second threshold value may be 30 times per minute, the third threshold value may be 200 minutes, the fourth threshold value may be 100 times per minute, and the fifth threshold value may be 100 minutes. When the proportion of non-resting time of the pig in a certain time period increases by a ratio greater than or equal to 100% compared with the proportion of non-resting time in any previous time period, the duration of the respiratory rate greater than 30 times per minute exceeds 200 minutes, and the duration of the heart rate greater than 100 times per minute exceeds 100 minutes, it can be determined that the first target physiological state of the pig is the estrus state. Of course, estrus judgment can also be performed based on one or more of the above three conditions as needed.

[0038] Method 2: determining whether the monitored livestock is sick based on at least one of the following: whether the time during which the respiratory rate exceeds the sixth threshold exceeds the seventh threshold, whether the frequency of posture changes exceeds the eighth threshold, and whether the proportion of lying still time exceeds the ninth threshold.

[0039] For example, the livestock to be monitored is a pig, for example, the sixth threshold value may be 60 times per minute, the seventh threshold value may be 30 minutes, and the eighth and ninth threshold values ​​may be set according to the statistical values ​​of the daily posture changes of the pigs (for example, the eighth and ninth threshold values ​​may be different in different seasons).

[0040] In some possible implementations, the first target physiological state of the livestock to be monitored can be determined to be a sick state when at least one of the respiratory frequency of the livestock to be monitored exceeds the sixth threshold, the time exceeds the seventh threshold (characterized by shortness of breath), the frequency of posture changes exceeds the eighth threshold (characterized by restlessness), and the proportion of lying time exceeds the ninth threshold (characterized by listlessness).

[0041] Those skilled in the art may also refer to the above embodiments to make appropriate changes to the conditions and thresholds for determining whether a person is in estrus or sick. They may also refer to the physiological laws of the corresponding types of livestock in the art to set more methods, conditions and thresholds for determining the first target physiological state, which will not be elaborated in this application.

[0042] In some embodiments, the methods of steps S1021 and S1022 can also be combined, and when the first target physiological states corresponding to both are the first target physiological state of the livestock to be monitored being a sick state, the first target physiological state of the livestock to be monitored is determined to be a sick state, which can further improve the accuracy. The target physiological state A of the livestock to be monitored can also be monitored by step S1021, and the target physiological state B of the livestock to be monitored can be monitored by step S1022.

[0043] By adopting the above-mentioned technical scheme, at least one first target physiological state of the livestock to be monitored can be determined through multiple physiological indicators corresponding to multiple preset time periods, and the estrus, illness, fright, etc. of the livestock can be automatically and accurately predicted, so as to facilitate timely intervention measures, reduce the cost of livestock breeding, and increase the output of livestock breeding.

[0044] In some embodiments, a variety of possible ways can be adopted to obtain the physiological indicators of the livestock to be monitored. For example, the physiological indicators of the livestock to be monitored can be obtained by monitoring the ups and downs of the body parts of the livestock to be monitored when lying still and the behavior of the livestock to be monitored when not lying still through millimeter wave radar. The behavior of the livestock to be monitored when not lying still can also be monitored by millimeter wave radar to obtain the behavioral physiological indicators of the livestock to be monitored, and at the same time, the respiratory physiological indicators and / or heartbeat physiological indicators can be obtained in combination with sensors set on the surface of the livestock to be monitored or buried in the body. Other possible ways can also be adopted to obtain other physiological indicators of the livestock to be monitored, and this application does not limit this.

[0045] Figure 3 Another flow chart of the method for monitoring livestock status provided by the embodiment of the present disclosure is shown as follows: Figure 3 As shown, step S101 may include the following steps: In step S1011, at least one of a first respiratory physiological signal, a first heartbeat physiological signal, and behavioral data of the livestock to be monitored is acquired through a millimeter wave radar.

[0046] In some embodiments, the millimeter wave radar can be set at a preset position above the livestock pen to be monitored (for example, 1.5 meters above), the detection direction of the millimeter wave radar is vertically downward, and the detection range of the millimeter wave radar is greater than the height of the preset position from the ground.

[0047] In some possible implementations, the millimeter wave radar may be a multi-channel millimeter wave radar, and the first respiratory physiological signal, the first heartbeat physiological signal, and the behavior data may be respectively acquired in the following manners.

[0048] Method 1: acquiring first data of the livestock to be monitored when lying still through the first target channel of the millimeter wave radar, and separating the first respiratory physiological signal from the first data through a bandpass filter.

[0049] Method 2: obtaining second data of the livestock to be monitored while lying still through the second target channel of the millimeter wave radar, and separating the first heartbeat physiological signal from the second data through a bandpass filter.

[0050] It is understandable that the first data and the second data of the livestock to be monitored when monitored by the millimeter wave radar when the livestock is lying still include respiratory physiological signals and cardiac physiological signals, but the respiratory physiological signals and the cardiac physiological signals have obvious differences in frequency and amplitude.

[0051] Taking the monitored livestock as pigs as an example, the respiratory physiological signal is a low-frequency signal, generally 0.1-0.5Hz, with an amplitude of 5-20mm, while the cardiac physiological signal is a high-frequency signal, generally 0.67-2Hz, with an amplitude of 0.2mm-0.8mm. Based on the above obvious differences, the first respiratory physiological signal can be separated from the first data according to the frequency range of the respiratory physiological signal by a bandpass filter. Similarly, the first cardiac physiological signal can also be separated from the second data according to the frequency range of the cardiac physiological signal by a bandpass filter.

[0052] When the monitored livestock is sick, it may have rapid breathing, that is, the breathing rate is close to the heart rate, which makes it impossible to successfully separate the first respiratory physiological signal from the first data. At this time, the first respiratory physiological signal can be set to a preset fixed value, such as 0 or 255, to facilitate the processing of subsequent steps.

[0053] It is understandable that different channels of the millimeter wave radar can monitor corresponding signals based on different detection depths, and the first target channel and the second target channel can be the same or different. Using independent channels to monitor respiratory and heartbeat physiological signals can further improve the accuracy of monitoring.

[0054] Method three: obtaining third data of the livestock to be monitored when it is not lying still through millimeter wave radar, and using the third data as behavior data.

[0055] In some embodiments, corresponding behavior data, such as standing, walking, running, etc., can be identified through third data, namely, the distance and changes of the monitored livestock from the millimeter wave radar.

[0056] In step S1012, statistics are collected on at least one of the first respiratory physiological signal, the first heartbeat physiological signal and the behavioral data of the monitored livestock according to a preset statistical cycle to obtain a physiological index.

[0057] In some embodiments, the preset statistical period can be, for example, at the hourly or daily level. The first respiratory physiological signal can be statistically analyzed according to the preset statistical period to obtain respiratory physiological indicators, the first heartbeat physiological signal can be statistically analyzed according to the preset statistical period to obtain heartbeat physiological indicators, and the behavioral data can be statistically analyzed according to the preset statistical period to obtain behavioral physiological indicators.

[0058] By adopting the above-mentioned technical solution, a multi-channel millimeter-wave radar can be used, and the first respiratory physiological signal and / or the first heartbeat physiological signal can be accurately obtained based on the target channel of the corresponding millimeter-wave radar, and the behavioral data can be accurately obtained through the millimeter-wave radar, which can further improve the accuracy of the acquisition of physiological indicators.

[0059] Figure 4 Another flow chart of the method for monitoring livestock status provided by the embodiment of the present disclosure is shown as follows: Figure 4 As shown, the method may further include the following steps.

[0060] In step S103, fourth data corresponding to the livestock to be monitored when lying still are obtained through multiple channels of the millimeter wave radar, and each channel corresponds to one fourth data.

[0061] For example, the millimeter wave radar includes n channels, and n fourth data corresponding to the livestock to be monitored when lying still can be obtained through the n channels, and each fourth data includes a respiratory physiological signal and a heartbeat physiological signal.

[0062] In step S104, the plurality of fourth data are divided into a corresponding plurality of second respiratory physiological signals and a plurality of second heartbeat physiological signals by using a bandpass filter.

[0063] For example, the n fourth data may be separated by a bandpass filter to obtain n second respiratory physiological signals and n second heartbeat physiological signals.

[0064] In step S105, the first target channel of the millimeter wave radar is determined by at least one of the peak position, amplitude and autocorrelation of multiple second respiratory physiological signals, and the second target channel of the millimeter wave radar is determined by at least one of the peak position, amplitude and autocorrelation of multiple second heartbeat physiological signals.

[0065] For example, n second respiratory physiological signals may be obtained, and the variance values ​​of the intervals of the peak positions corresponding to the n second respiratory physiological signals may be obtained, and the channel corresponding to the second respiratory physiological signal with the smallest variance value (i.e., the smallest fluctuation in the intervals of the peak positions) may be taken as the first target channel.

[0066] Alternatively, the average amplitudes corresponding to the n second respiratory physiological signals may be obtained, and the channel corresponding to the second respiratory physiological signal with the largest amplitude may be used as the first target channel.

[0067] The autocorrelations corresponding to the n second respiratory physiological signals may also be obtained, and the channel corresponding to the second respiratory physiological signal with the largest autocorrelation is used as the first target channel.

[0068] It is also possible to obtain multiple indicators of the three indicators, namely, the variance value, amplitude and autocorrelation of the interval of the peak position, and appropriately transform the corresponding indicators (for example, transform all three indicators to the larger the better, and normalize them), and determine the channel corresponding to the second respiratory physiological signal as the first target channel through the comprehensive evaluation indicators of multiple indicators (for example, weighted values).

[0069] Similarly, a similar method to the first target channel may be used to determine the second target channel of the millimeter wave radar through at least one of the peak positions, amplitudes, and autocorrelations of multiple second heartbeat physiological signals.

[0070] By adopting the above technical solution, the target channels corresponding to the heartbeat physiological signals and the respiratory physiological signals can be determined, thereby further improving the accuracy of obtaining the heartbeat physiological signals and the respiratory physiological signals.

[0071] Figure 5 Another flow chart of the livestock status monitoring method provided by the embodiment of the present disclosure is shown, wherein the livestock to be monitored are multiple livestock, such as Figure 5 As shown, the method may further include the following steps.

[0072] In step S103, at least one second target physiological state of the plurality of livestock is determined according to the plurality of physiological indicators respectively corresponding to the plurality of livestock within one or more preset time periods.

[0073] In some embodiments, the time periods corresponding to different livestock may be the same time period, or different time periods whose difference does not exceed a threshold (ie, adjacent time periods).

[0074] For example, the second target physiological state may be that the livestock group is frightened. The second target physiological state may be determined as the livestock group being frightened if the following conditions are met: The current corresponding time period is the livestock sleeping time period; and, The standing time percentage of multiple livestock in a certain target time period increases by more than the preset threshold compared with the previous time period.

[0075] For example, the second target physiological state may also be livestock group illness, and the second target physiological state may be determined to be livestock group illness when multiple livestock meet at least one of the following conditions within the same target time period or within a time period adjacent to the target time period: The respiratory rate exceeds the tenth threshold for a period longer than the eleventh threshold; The frequency of posture changes exceeds the twelfth threshold; The proportion of time spent lying still exceeds the thirteenth threshold.

[0076] It is understandable that more judgment conditions and corresponding second target physiological states can be set based on livestock breeding experience and with reference to the above embodiment. Of course, multiple livestock physiological indicators can also be input into the third livestock state prediction model to predict at least one second target physiological state.

[0077] By adopting the above technical solution, it is possible to further timely perceive the target physiological state of the livestock group, further reduce the cost of livestock breeding, and increase the output of livestock breeding.

[0078] Figure 6 A block diagram of a livestock status monitoring device provided by an embodiment of the present application is shown, such as Figure 6 As shown, the monitoring device 100 for livestock status comprises: An acquisition module 110 is used to acquire a plurality of physiological indicators corresponding to the livestock to be monitored in a plurality of preset time periods, each preset time period corresponding to one or more physiological indicators; The determination module 120 is used to determine at least one first target physiological state of the livestock to be monitored according to a plurality of physiological indicators corresponding to a plurality of preset time periods.

[0079] Optionally, the determination module 120 is further configured to: Inputting physiological indicators corresponding to a plurality of preset time periods into a pre-trained livestock state prediction model to obtain at least one first target physiological state of the livestock to be monitored, wherein the livestock state prediction model is a deep learning model for time series prediction; or At least one first target physiological state of the livestock to be monitored is determined according to the physiological indicators corresponding to each other in a plurality of preset time periods.

[0080] Optionally, the physiological index includes at least one of a respiratory physiological index, a heartbeat physiological index, and a behavioral physiological index. The acquisition module 110 is further used to: Acquire at least one of a first respiratory physiological signal, a first heartbeat physiological signal, and behavioral data of the livestock to be monitored by a millimeter wave radar; At least one of the first respiratory physiological signal, the first heartbeat physiological signal and the behavioral data of the monitored livestock is statistically analyzed according to a preset statistical cycle to obtain a physiological index.

[0081] Optionally, the millimeter wave radar is a multi-channel millimeter wave radar, and the acquisition module 110 is further used for: Acquire first data of the livestock to be monitored when lying still through the first target channel of the millimeter wave radar, and separate the first respiratory physiological signal from the first data through a bandpass filter; Acquire second data of the livestock to be monitored when lying still through the second target channel of the millimeter wave radar, and separate the first heartbeat physiological signal from the second data through a bandpass filter; The millimeter wave radar is used to obtain third data of the livestock to be monitored when it is not lying still, and the third data is used as behavior data.

[0082] Optionally, the acquisition module 110 is further configured to: Acquire fourth data respectively corresponding to the livestock to be monitored when they are lying still through multiple channels of the millimeter wave radar, wherein each channel corresponds to one fourth data; Separating the plurality of fourth data into a corresponding plurality of second respiratory physiological signals and a plurality of second heartbeat physiological signals through a bandpass filter; The first target channel of the millimeter wave radar is determined by at least one of the peak positions, amplitudes and autocorrelations of multiple second respiratory physiological signals, and the second target channel of the millimeter wave radar is determined by at least one of the peak positions, amplitudes and autocorrelations of multiple second heartbeat physiological signals.

[0083] Optionally, the determination module 120 is further configured to: Determine whether the livestock is in estrus according to at least one of whether the increase ratio of the non-lying time of the livestock to be monitored exceeds a first threshold, whether the time during which the respiratory rate of the livestock to be monitored exceeds a second threshold exceeds a third threshold, and whether the time during which the heart rate of the livestock to be monitored exceeds a fourth threshold exceeds a fifth threshold; Whether the monitored livestock is sick is determined based on at least one of the following: whether the time of its respiratory rate exceeding the sixth threshold exceeds the seventh threshold, whether the frequency of posture changes exceeds the eighth threshold, and whether the proportion of its lying time exceeds the ninth threshold.

[0084] Optionally, the determination module 120 is further configured to: At least one second target physiological state of the plurality of livestock is determined according to the plurality of physiological indicators respectively corresponding to the plurality of livestock within one or more preset time periods.

[0085] The device 100 provided in the embodiment of the present application can execute each method in the foregoing method embodiment and realize the functions and beneficial effects of each method in the foregoing method embodiment, which will not be described in detail here.

[0086] Figure 7 A schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present disclosure is shown. Figure 7 As shown, at the hardware level, the electronic device includes at least one processor, and optionally includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0087] The processor, network interface and memory can be interconnected through an internal bus, which can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0088] The memory stores the program. Specifically, the program may include a program code, and the program code includes at least one computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0089] At least one processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a device for locating the target user at the logical level. At least one processor executes the program stored in the memory and specifically performs: the method disclosed in the embodiment shown in the first aspect and realizes the functions and beneficial effects of each method described in the method embodiment above, which will not be repeated here.

[0090] The method disclosed in the embodiment shown in the first aspect of the present disclosure can be applied to at least one processor or implemented by at least one processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware or software instructions in at least one processor. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0091] The electronic device can also execute the methods described in the foregoing method embodiments, and realize the functions and beneficial effects of the methods described in the foregoing method embodiments, which will not be repeated here.

[0092] Of course, in addition to software implementation, the electronic device disclosed in the present invention does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0093] The embodiments of the present disclosure also propose a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by at least one processor, they implement the method disclosed in the embodiment shown in the first aspect and realize the functions and beneficial effects of the various methods described in the previous method embodiments, which will not be repeated here.

[0094] The computer-readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0095] Furthermore, the embodiments of the present disclosure also provide a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the following process is implemented: the method disclosed in the embodiment shown in the first aspect and the functions and beneficial effects of the various methods described in the previous method embodiments are implemented, which will not be repeated here.

[0096] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the various processes of the method disclosed in the embodiment shown in the first aspect and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0097] In short, the above is only a preferred embodiment of the present disclosure and does not limit the protection scope of the present disclosure. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

[0098] The systems, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0099] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0100] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0101] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

Claims

1. A method for monitoring livestock status, characterized in that: The method comprises: Acquire multiple physiological indicators corresponding to the livestock to be monitored in multiple preset time periods, each preset time period corresponds to one or more physiological indicators; At least one first target physiological state of the livestock to be monitored is determined according to the multiple physiological indicators corresponding to the multiple preset time periods.

2. The method according to claim 1, characterized in that: The step of determining at least one first target physiological state of the livestock to be monitored according to the multiple physiological indicators corresponding to the multiple preset time periods respectively includes: Inputting the physiological indicators corresponding to the plurality of preset time periods into a pre-trained livestock state prediction model to obtain at least one first target physiological state of the livestock to be monitored, wherein the livestock state prediction model is a deep learning model for time series prediction; or At least one first target physiological state of the livestock to be monitored is determined according to the physiological indicators corresponding to the multiple preset time periods.

3. The method according to claim 1, characterized in that: The physiological index includes at least one of a respiratory physiological index, a heartbeat physiological index, and a behavioral physiological index. The step of obtaining the multiple physiological indexes corresponding to the livestock to be monitored in multiple preset time periods includes: Acquire at least one of a first respiratory physiological signal, a first heartbeat physiological signal, and behavioral data of the livestock to be monitored by a millimeter wave radar; The physiological index is obtained by performing statistics on at least one of the first respiratory physiological signal, the first heartbeat physiological signal and the behavioral data of the livestock to be monitored according to a preset statistical period.

4. The method according to claim 3, characterized in that The millimeter wave radar is a multi-channel millimeter wave radar, and obtaining at least one of the first respiratory physiological signal, the first heartbeat physiological signal, and the behavior data of the livestock to be monitored by the millimeter wave radar includes at least one of the following: Acquire first data of the livestock to be monitored when lying still through a first target channel of the millimeter wave radar, and separate the first respiratory physiological signal from the first data through a bandpass filter; Acquire second data of the livestock to be monitored when lying still through a second target channel of the millimeter wave radar, and separate the first heartbeat physiological signal from the second data through a bandpass filter; The third data of the livestock to be monitored when it is not lying still is obtained by using the millimeter wave radar, and the third data is used as the behavior data.

5. The method according to claim 4, characterized in that The method further comprises: Acquire, through the multiple channels of the millimeter wave radar, fourth data respectively corresponding to the livestock to be monitored when lying still, wherein each channel corresponds to one fourth data; Separating the plurality of fourth data into a corresponding plurality of second respiratory physiological signals and a plurality of second heartbeat physiological signals through a bandpass filter; The first target channel of the millimeter-wave radar is determined by at least one of the peak positions, amplitudes and autocorrelations of the multiple second respiratory physiological signals, and the second target channel of the millimeter-wave radar is determined by at least one of the peak positions, amplitudes and autocorrelations of the multiple second heartbeat physiological signals.

6. The method according to claim 2, characterized in that Determining at least one first target physiological state of the livestock to be monitored according to the multiple physiological indicators corresponding to the multiple preset time periods respectively includes at least one of the following: Determine whether the livestock is in estrus according to at least one of whether the increase ratio of the non-lying time of the livestock to be monitored exceeds a first threshold, whether the time during which the respiratory rate of the livestock to be monitored exceeds a second threshold exceeds a third threshold, and whether the time during which the heart rate of the livestock to be monitored exceeds a fourth threshold exceeds a fifth threshold; Whether the monitored livestock is sick is determined based on at least one of whether the respiratory frequency of the monitored livestock exceeds the sixth threshold for a time period exceeding the seventh threshold, whether the frequency of posture changes exceeds the eighth threshold, and whether the proportion of lying time exceeds the ninth threshold.

7. The method according to any one of claims 1 to 6, characterized in that The livestock to be monitored is a plurality of livestock, and the method further comprises: At least one second target physiological state of the plurality of livestock is determined according to a plurality of physiological indicators respectively corresponding to the plurality of livestock within one or more preset time periods.

8. A device for monitoring livestock status, characterized in that: The device comprises: An acquisition module, used to acquire a plurality of physiological indicators corresponding to the livestock to be monitored in a plurality of preset time periods, each preset time period corresponding to one or more physiological indicators; The determination module is used to determine at least one first target physiological state of the livestock to be monitored according to the multiple physiological indicators corresponding to the multiple preset time periods.

9. An electronic device, characterized in that: include: Memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method for monitoring the status of livestock as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for monitoring the status of livestock according to any one of claims 1 to 7 is implemented.

Images