Animal delivery early warning method based on near hypothalamic temperature

Abstract

The invention discloses an animal parturition early warning method based on near hypothalamus temperature, which comprises the following steps of: 1, wearing a wireless transmitter for continuously detecting the temperature in an ear canal on an animal in a gestation period, and wearing the wireless transmitter on the ear root part of a subject matter, a temperature probe of the wireless transmitter goes deep into the ear canal of a subject matter or is implanted into the tail root part of an animal or is implanted into the subcutaneous tissue of the subject matter; 2, filtering, processing and storing animal body temperature signals, collected by the wireless transmitter, of the near hypothalamus, and analyzing the signals by adopting a specific algorithm; 3, when the dynamically-collected body temperature signals conform to the body temperature characteristics of the animal during delivery. According to the invention, the collected temperature signals are filtered, processed and analyzed by adopting a specific algorithm, so that the system can extract a temperature change mode related to delivery, and the intelligent analysis not only reduces the need of human intervention, but also improves the reliability of prediction.

Description

Technical Field

[0001] The present invention relates to a technical field, and in particular to an animal delivery warning method based on near-hypothalamus temperature. Background Art

[0002] In modern animal husbandry and pet management, animal health monitoring and management are increasingly valued. Traditional delivery warning methods mainly rely on manual observation and empirical judgment, which often have problems such as long response time, low accuracy, and incomplete assessment of the impact on animal health. Especially during delivery, the change in animal body temperature is an important physiological indicator, but current monitoring methods generally lack real-time and accuracy.

[0003] In recent years, with the development of wireless sensor technology and the Internet of Things, devices that can monitor animal physiological parameters in real time have gradually emerged. Although existing technologies can provide some basic body temperature monitoring functions, they are often unable to provide accurate warnings for specific physiological states (such as delivery). Especially at the critical moment before delivery, how to quickly and accurately identify the physiological changes of animals and issue warnings is an important issue for improving breeding efficiency and animal welfare.

[0004] In addition, most existing monitoring systems lack intelligent analysis capabilities and are unable to adaptively adjust monitoring parameters according to the type and health status of different animals, resulting in a low degree of personalization of delivery warnings, which limits the widespread application of the system. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above-mentioned problems existing in the existing animal delivery warning method based on near-hypothalamic temperature, the present invention is proposed.

[0007] Therefore, the purpose of the present invention is to provide an animal delivery warning method based on near-hypothalamic temperature, which uses a specific algorithm to filter, process and analyze the collected temperature signals, so that the system can extract the temperature change patterns related to delivery. This intelligent analysis not only reduces the need for human intervention, but also improves the reliability of prediction.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: an animal delivery warning method based on near-hypothalamic temperature, comprising the following steps:

[0009] Step 1: Give the pregnant animal (target) a wireless transmitter that continuously detects the temperature in the ear canal. The wireless transmitter is worn at the base of the target's ear. The temperature probe of the wireless transmitter is inserted into the target's ear canal or implanted at the base of the animal's tail, or implanted into the subcutaneous tissue of the target.

[0010] Step 2: Filter, process, and store the animal's body temperature signal near the hypothalamus collected by the wireless transmitter, and use a specific algorithm to analyze the signal to extract the temperature change pattern related to animal delivery;

[0011] Step 3: When the dynamically collected body temperature signal meets the body temperature characteristics of the animal during childbirth, the wireless transmitter sends a specific signal to the external wireless receiving device to remind the animal that it is possible to give birth;

[0012] Step 4: The system records the temperature change data of each delivery and uploads it to the cloud computing center for data analysis to provide reference for future delivery warnings;

[0013] Step 5: Provide a user-friendly mobile phone or computer program that allows users to monitor temperature changes in real time, view historical data, and adjust feeding management measures based on analysis results.

[0014] As a preferred solution of the animal delivery warning method based on near-hypothalamic temperature described in the present invention, the wireless transmitter is composed of a temperature sensor, an MCU, a storage unit, a transmitting antenna, a battery and a packaging shell, and the wireless transmitter collects the body temperature of the target object once at regular intervals.

[0015] As a preferred solution of the animal delivery warning method based on near-hypothalamic temperature of the present invention, the temperature collected by the temperature sensor can be calculated and stored in the MCU of the wireless transmitter, and can also be wirelessly transmitted to an external computing unit.

[0016] As a preferred embodiment of the animal delivery warning method based on near-hypothalamic temperature of the present invention, the temperature is calculated and stored in the MCU, including the following steps:

[0017] S1, the collected temperature is written into the embedded program, which issues an instruction to collect temperature signals according to a specific time length, and filters the collected temperature signals according to the specific time length, filters out temperature signals greater than or less than a specific threshold, and averages the temperature signals that are not filtered out according to the specific time length to obtain the temperature representative value t1 of the specific time length;

[0018] S2, MCU averages the temperature representative values ​​t1 of the most recent n time lengths to obtain the average value aT1 of t1 in the past n time lengths. As time goes by, MCU continuously calculates aT1 of the past n time lengths and records it in its cache;

[0019] S3. The embedded program of MCU compares each newly collected and calculated t1 with aT1. When t1 is less than a specific value X of aT1, MCU assigns a specific value Flag1 to the value, and starts the transmission function of HMT. After Flag1 is identified, it is transmitted to the external wireless receiving device. At the same time, MCU stops calculating the new aT1 value, and continues to compare the newly generated t1 with aT1. When t1 is less than a specific value X of aT1, MCU assigns a specific value Flag1 to the value, and starts the transmission function of HMT. After Flag1 is identified, it is transmitted to the external wireless receiving device. This cycle continues until t1 is no longer less than a specific value X of aT1, and MCU stops transmitting the Flag1 value.

[0020] S4. The external wireless receiving device matches the manually input information of the alarm target object. When the alarm signal is sent out during the pregnancy period of the target object, the external wireless receiving device presents a labor alarm signal.

[0021] As a preferred solution of the animal delivery warning method based on near-hypothalamus temperature of the present invention, the steps when the temperature collected by the temperature sensor is wirelessly transmitted to the external computing unit are as follows:

[0022] A1, an embedded program is written into the MCU, which collects temperature signals regularly, identifies the temperature signals as t2, and transmits them to an external wireless receiving device;

[0023] A2, the external wireless receiving device receives the signal t2, and transmits t2 to the corresponding processing unit of the cloud computing center. The corresponding processing unit of the cloud computing center filters the received t2, screens out temperature signals greater than or less than a specific threshold, and averages the temperature signals that are not screened out according to a specific time length to obtain a temperature representative value t3 of the specific time length;

[0024] A3. The corresponding processing unit of the cloud computing center averages the temperature representative values ​​t3 of the past n time lengths to obtain the average value aT3 of t3 in the past n time lengths. As time goes by, the corresponding processing unit of the cloud computing center continuously calculates aT3 of the past n time lengths and records it in its storage unit, replacing the old aT3 with the latest aT3.

[0025] A4. The corresponding processing unit of the cloud computing center compares each newly collected and calculated t3 with aT3. When t3 is less than a specific value X of aT3, the corresponding processing unit of the cloud computing center assigns a specific value Flag3 to the value, starts the alarm function, and presents Flag3 in the corresponding program; at the same time, the corresponding processing unit of the cloud computing center stops calculating the new aT3 value, and continues to compare the newly generated t3 with aT3. When t3 is less than a specific value X of aT3, the corresponding processing unit of the cloud computing center assigns a specific value Flag3 to the value, starts the alarm function, and presents Flag3 in the corresponding program; this cycle is repeated until t3 is no longer less than a specific value X of aT3, and the corresponding processing unit of the cloud computing center stops the alarm function and no longer presents Flag3 in the corresponding program;

[0026] A5. The computer program of the corresponding processing unit of the cloud computing center matches the manually entered information of the object of the alarm. When the alarm signal is sent out after the gestation period of the object, the computer program presents a delivery alarm signal.

[0027] As a preferred embodiment of the animal delivery early warning method based on near-hypothalamic temperature of the present invention, the following specific algorithm and its process are used in step 2 to extract the temperature change pattern related to animal delivery:

[0028] 1. Signal preprocessing Noise Filtering

[0029] Algorithm: Use a low-pass filter to remove high-frequency noise;

[0030] formula:

[0031] in, is the filter transfer function, is the cutoff frequency, is the order of the filter;

[0032] Process: Design and apply a low-pass filter, input the original question signal into the filter, and output a smoothed signal;

[0033] 2. Feature extraction

[0034] Sliding window average

[0035] Algorithm: Calculate the sliding average of the signal to reduce noise interference;

[0036] formula:

[0037] in, is the sliding average, is the window size;

[0038] Process: Determine the sliding window size and calculate the average body temperature in each window;

[0039] Temperature change rate calculation

[0040] Algorithm: Calculates the rate of temperature change to identify significant changes before delivery;

[0041] formula:

[0042] in, is the temperature change, is the temperature at the current time point;

[0043] Process: For the smoothed signal, calculate the temperature changes at adjacent time points one by one.

[0044] As a preferred embodiment of the animal delivery warning method based on near-hypothalamic temperature of the present invention, the pattern recognition of the temperature change pattern includes:

[0045] Threshold Detection

[0046] Algorithm: Set thresholds based on the rate of temperature change to identify temperature patterns before delivery;

[0047] Formula: If

[0048] Process: Determine an appropriate rate-of-change threshold, detect if the temperature change exceeds the threshold, and trigger an alarm;

[0049] Machine Learning Models

[0050] Algorithm,classification using support vector machine;

[0051] Process: Collect labeled temperature data; split the data into training and test sets; train the model and input the extracted features; test the model and evaluate the prediction accuracy;

[0052] Data storage and update

[0053] Process: Store the processed temperature data and extracted features in a database; update the model regularly to incorporate the latest data to improve prediction accuracy.

[0054] As a preferred embodiment of the animal delivery warning method based on near-hypothalamic temperature of the present invention, the normal body temperature range and temperature change pattern before delivery of different animal species are different, and the initial threshold value can be set according to the animal species, specifically including:

[0055] a. Normal body temperature range

[0056] formula: ; and are the lower and upper limits of normal body temperature for a particular animal species;

[0057] b. Temperature change threshold before delivery

[0058] formula:

[0059] is the baseline value of normal body temperature;

[0060] is the adjustment factor (set according to the farrowing characteristics of the animal species and usually learned from historical data);

[0061] is the average temperature change under normal conditions;

[0062] For animals in poor health, the temperature changes before delivery are more significant and the threshold should be lowered appropriately, including:

[0063] c. Health status score

[0064] By scoring the health status of the animals, the direction of adjusting the threshold is determined;

[0065] formula:

[0066] is the health status score, Different health indicators. is the corresponding weight;

[0067] d. Dynamic adjustment of threshold

[0068] Adjust monitoring thresholds based on health status score:

[0069] formula:

[0070] is the adjustment factor, controlling the effect of health status on the threshold;

[0071] is the maximum value of the health score.

[0072] As a preferred solution of the animal delivery warning method based on near-hypothalamus temperature of the present invention, a dynamic update mechanism is set to monitor temperature and health status data in real time and adjust the threshold regularly;

[0073] 1) Moving mean and standard deviation

[0074] Use sliding mean and standard deviation to update baseline values

[0075] formula:

[0076] After updating, recalculate the threshold based on the current data;

[0077] Machine Learning Optimization

[0078] 2) Use machine learning algorithms to optimize and adjust strategies

[0079] Regression model, using a linear regression algorithm to predict the appropriate threshold

[0080] formula: .

[0081] Beneficial effects of the present invention:

[0082] 1. Improved real-time performance and accuracy: This method can achieve real-time monitoring of near-hypothalamic temperature through a wireless transmitter worn in the animal's ear canal, significantly improving the response speed and accuracy to the animal's delivery status.

[0083] 2. Intelligent data analysis: Using specific algorithms to filter, process and analyze the collected temperature signals, the system can extract the temperature change patterns related to childbirth. This intelligent analysis not only reduces the need for human intervention, but also improves the reliability of predictions.

[0084] 3. Personalized early warning mechanism: The system adaptively adjusts the temperature monitoring threshold and early warning strategy according to different animal species and health conditions, thereby providing personalized delivery warnings. This flexibility helps improve the adaptability and effectiveness of the system in different application scenarios.

[0085] 4. Data accumulation and learning ability: The system records the temperature change data of each delivery and uploads it to the cloud computing center for analysis. It can not only provide data support for future delivery warnings, but also continuously optimize the warning algorithm through big data analysis to form a benign self-improvement mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0087] Figure 1 The present invention is a flowchart of the method steps of the animal delivery warning method based on near-hypothalamic temperature. DETAILED DESCRIPTION

[0088] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0089] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0090] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0091] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0092] Reference Figure 1 , provides an animal delivery warning method based on near-hypothalamic temperature, comprising the following steps:

[0093] Step 1: Give the pregnant animal (target) a wireless transmitter that continuously detects the temperature in the ear canal. The wireless transmitter is worn at the base of the target's ear. The temperature probe of the wireless transmitter is inserted into the target's ear canal or implanted at the base of the animal's tail, or implanted into the subcutaneous tissue of the target.

[0094] Step 2: Filter, process, and store the animal's body temperature signal near the hypothalamus collected by the wireless transmitter, and use a specific algorithm to analyze the signal to extract the temperature change pattern related to animal delivery;

[0095] Step 3: When the dynamically collected body temperature signal meets the body temperature characteristics of the animal during childbirth, the wireless transmitter sends a specific signal to the external wireless receiving device to remind the animal that it is possible to give birth;

[0096] Step 4: The system records the temperature change data of each delivery and uploads it to the cloud computing center for data analysis to provide reference for future delivery warnings;

[0097] Step 5: Provide a user-friendly mobile phone or computer program that allows users to monitor temperature changes in real time, view historical data, and adjust feeding management measures based on analysis results.

[0098] Among them, the wireless transmitter is composed of a temperature sensor, an MCU, a storage unit, a transmitting antenna, a battery and a packaging shell. The wireless transmitter collects the body temperature of the target object once in a period of time. Specifically, the temperature collected by the temperature sensor can be calculated and stored in the MCU of the wireless transmitter, and can also be wirelessly transmitted to an external computing unit.

[0099] Furthermore, the temperature is calculated and stored in the MCU including the following steps:

[0100] S1, the collected temperature is written into the embedded program, which issues an instruction to collect temperature signals according to a specific time length, and filters the collected temperature signals according to the specific time length, filters out temperature signals greater than or less than a specific threshold, and averages the temperature signals that are not filtered out according to the specific time length to obtain the temperature representative value t1 of the specific time length;

[0101] S2, MCU averages the temperature representative values ​​t1 of the most recent n time lengths to obtain the average value aT1 of t1 in the past n time lengths. As time goes by, MCU continuously calculates aT1 of the past n time lengths and records it in its cache;

[0102] S3. The embedded program of MCU compares each newly collected and calculated t1 with aT1. When t1 is less than a specific value X of aT1, MCU assigns a specific value Flag1 to the value, and starts the transmission function of HMT. After Flag1 is identified, it is transmitted to the external wireless receiving device. At the same time, MCU stops calculating the new aT1 value, and continues to compare the newly generated t1 with aT1. When t1 is less than a specific value X of aT1, MCU assigns a specific value Flag1 to the value, and starts the transmission function of HMT. After Flag1 is identified, it is transmitted to the external wireless receiving device. This cycle continues until t1 is no longer less than a specific value X of aT1, and MCU stops transmitting the Flag1 value.

[0103] S4. The external wireless receiving device matches the manually input information of the alarm target object. When the alarm signal is sent out during the pregnancy period of the target object, the external wireless receiving device presents a labor alarm signal.

[0104] Furthermore, the steps when the temperature collected by the temperature sensor is wirelessly transmitted to the external computing unit are as follows:

[0105] A1, an embedded program is written into the MCU, which collects temperature signals regularly, identifies the temperature signals as t2, and transmits them to an external wireless receiving device;

[0106] A2, the external wireless receiving device receives the signal t2, and transmits t2 to the corresponding processing unit of the cloud computing center. The corresponding processing unit of the cloud computing center filters the received t2, screens out temperature signals greater than or less than a specific threshold, and averages the temperature signals that are not screened out according to a specific time length to obtain a temperature representative value t3 of the specific time length;

[0107] A3. The corresponding processing unit of the cloud computing center averages the temperature representative values ​​t3 of the past n time lengths to obtain the average value aT3 of t3 in the past n time lengths. As time goes by, the corresponding processing unit of the cloud computing center continuously calculates aT3 of the past n time lengths and records it in its storage unit, replacing the old aT3 with the latest aT3.

[0108] A4. The corresponding processing unit of the cloud computing center compares each newly collected and calculated t3 with aT3. When t3 is less than a specific value X of aT3, the corresponding processing unit of the cloud computing center assigns a specific value Flag3 to the value, starts the alarm function, and presents Flag3 in the corresponding program; at the same time, the corresponding processing unit of the cloud computing center stops calculating the new aT3 value, and continues to compare the newly generated t3 with aT3. When t3 is less than a specific value X of aT3, the corresponding processing unit of the cloud computing center assigns a specific value Flag3 to the value, starts the alarm function, and presents Flag3 in the corresponding program; this cycle is repeated until t3 is no longer less than a specific value X of aT3, and the corresponding processing unit of the cloud computing center stops the alarm function and no longer presents Flag3 in the corresponding program;

[0109] A5. The computer program of the corresponding processing unit of the cloud computing center matches the manually entered information of the object of the alarm. When the alarm signal is sent out after the gestation period of the object, the computer program presents a delivery alarm signal.

[0110] Among them, the following specific algorithms and processes are used in step 2 to extract the temperature change patterns associated with animal parturition:

[0111] 1. Signal preprocessing Noise Filtering

[0112] Algorithm: Use a low-pass filter to remove high-frequency noise;

[0113] formula:

[0114] in, is the filter transfer function, is the cutoff frequency, is the order of the filter;

[0115] Process: Design and apply a low-pass filter, input the original question signal into the filter, and output a smoothed signal;

[0116] 2. Feature extraction

[0117] Sliding window average

[0118] Algorithm: Calculate the sliding average of the signal to reduce noise interference;

[0119] formula:

[0120] in, is the sliding average, is the window size;

[0121] Process: Determine the sliding window size and calculate the average body temperature in each window;

[0122] Temperature change rate calculation

[0123] Algorithm: Calculates the rate of temperature change to identify significant changes before delivery;

[0124] formula:

[0125] in, is the temperature change, is the temperature at the current time point;

[0126] Process: For the smoothed signal, calculate the temperature changes at adjacent time points one by one.

[0127] Specifically, pattern recognition of temperature change patterns includes:

[0128] Threshold Detection

[0129] Algorithm: Set thresholds based on the rate of temperature change to identify temperature patterns before delivery;

[0130] Formula: If

[0131] Process: Determine an appropriate rate-of-change threshold, detect if the temperature change exceeds the threshold, and trigger an alarm;

[0132] Machine Learning Models

[0133] Algorithm,classification using support vector machine;

[0134] Process: Collect labeled temperature data; split the data into training and test sets; train the model and input the extracted features; test the model and evaluate the prediction accuracy;

[0135] Data storage and update

[0136] Process: Store the processed temperature data and extracted features in a database; update the model regularly to incorporate the latest data to improve prediction accuracy.

[0137] Furthermore, the normal body temperature range and temperature change pattern before delivery are different for different animal species, and the initial threshold can be set according to the animal species, including:

[0138] a. Normal body temperature range

[0139] formula:

[0140] and are the lower and upper limits of normal body temperature for a particular animal species;

[0141] b. Temperature change threshold before delivery

[0142] formula:

[0143] is the baseline value of normal body temperature;

[0144] is the adjustment factor (set according to the farrowing characteristics of the animal species and usually learned from historical data);

[0145] is the average temperature change under normal conditions;

[0146] For animals in poor health, the temperature changes before delivery are more significant and the threshold should be lowered appropriately, including:

[0147] c. Health status score

[0148] By scoring the health status of the animals, the direction of adjusting the threshold is determined;

[0149] formula:

[0150] is the health status score, Different health indicators. is the corresponding weight;

[0151] d. Dynamic adjustment of threshold

[0152] Adjust monitoring thresholds based on health status score: Formula:

[0153] is the adjustment factor, controlling the effect of health status on the threshold;

[0154] is the maximum value of the health score.

[0155] Among them, a dynamic update mechanism is set up to monitor temperature and health status data in real time and adjust thresholds regularly;

[0156] 1) Moving mean and standard deviation

[0157] Use sliding mean and standard deviation to update baseline values

[0158] formula:

[0159] After updating, recalculate the threshold based on the current data;

[0160] Machine Learning Optimization

[0161] 2) Use machine learning algorithms to optimize and adjust strategies

[0162] Regression model, using a linear regression algorithm to predict the appropriate threshold

[0163] formula: .

[0164] A computer device includes a memory and a processor. The computer device may be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner may be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covered on the display screen, or may be a key, trackball or touchpad provided on the housing of the computer device, or may be an external keyboard, touchpad or mouse.

[0165] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for early warning of animal delivery based on near-hypothalamic temperature, characterized in that: The following steps are involved: Step 1: A wireless transmitter for continuously detecting the temperature in the ear canal is worn on the pregnant animal. The wireless transmitter is worn at the base of the ear of the target animal. The temperature probe of the wireless transmitter is inserted into the ear canal of the target animal or implanted at the base of the tail of the animal or implanted in the subcutaneous tissue of the target animal. Step 2: The animal body temperature signal near the hypothalamus collected by the wireless transmitter is filtered, processed, and stored, and the signal is analyzed using a specific algorithm to extract the temperature change pattern related to animal delivery. Step 3: When the dynamically collected body temperature signal meets the body temperature characteristics of the animal during delivery, the wireless transmitter sends a specific signal to an external wireless receiving device to remind the animal that delivery is possible. Step 4: The system records the temperature change data of each delivery and uploads it to the cloud computing center for data analysis to provide a reference for future delivery warnings. Step 5: Provide a user-friendly mobile phone or computer program that enables users to monitor temperature changes in real time, view historical data, and adjust feeding management measures based on the analysis results.

2. The animal delivery warning method based on near-hypothalamic temperature according to claim 1, characterized in that: The wireless transmitter is composed of a temperature sensor, an MCU, a storage unit, a transmitting antenna, a battery and a packaging shell. The wireless transmitter collects the body temperature of the target object once every certain period of time.

3. The animal delivery warning method based on near-hypothalamic temperature according to claim 2, characterized in that: The temperature collected by the temperature sensor can be calculated and stored in the MCU of the wireless transmitter, and can also be wirelessly transmitted to an external computing unit.

4. The animal delivery warning method based on near-hypothalamic temperature according to claim 3, characterized in that: The temperature is calculated and stored in the MCU including the following steps: S1. The collected temperature is written into the embedded program, which issues instructions to collect temperature signals according to a specific time length, and filters the collected temperature signals according to the specific time length, screens out temperature signals greater than or less than a specific threshold, and averages the temperature signals that are not screened out according to the specific time length to obtain the temperature representative value t1 of the specific time length; S2. The MCU averages the temperature representative values ​​t1 of the most recent n time lengths to obtain the average value aT1 of t1 in the past n time lengths. As time goes by, the MCU continuously calculates aT1 of the past n time lengths and records it in its cache; S3. The embedded program of MCU compares each newly collected and calculated t1 with aT1. When t1 is less than a specific value X of aT1, MCU assigns a specific value Flag1 to the value, and starts the transmission function of HMT, identifies Flag1, and transmits it to the external wireless receiving device; at the same time, MCU stops calculating the new aT1 value, and continues to compare the newly generated t1 with aT1. When t1 is less than a specific value X of aT1, MCU assigns a specific value Flag1 to the value, and starts the transmission function of HMT, identifies Flag1, and transmits it to the external wireless receiving device, and this cycle continues until t1 is no longer less than a specific value X of aT1, and MCU stops transmitting the Flag1 value. S4. The external wireless receiving device matches the manually entered information of the target object of the alarm. When the alarm signal is sent at the time after the gestation period of the target object, the external wireless receiving device presents a labor alarm signal.

5. The animal delivery warning method based on near-hypothalamic temperature according to claim 3, characterized in that: The steps when the temperature collected by the temperature sensor is wirelessly transmitted to the external computing unit are as follows: A1, an embedded program is written into the MCU, the program collects temperature signals at regular intervals, identifies the temperature signals as t2, and transmits them to the external wireless receiving device; A2, the external wireless receiving device receives the signal t2, transmits t2 to the corresponding processing unit of the cloud computing center, the corresponding processing unit of the cloud computing center filters the received t2, screens out temperature signals greater than or less than a specific threshold, and averages the unscreened temperature signals according to a specific time length to obtain a temperature representative value t3 for the specific time length; A3, the corresponding processing unit of the cloud computing center averages the temperature representative values ​​t3 of the past n time lengths to obtain an average value aT3 of t3 within the past n time lengths. As time goes by, the corresponding processing unit of the cloud computing center continuously calculates aT3 of the past n time lengths, and records it in its storage unit, replacing the old aT3 with the latest aT3; A4, the corresponding processing unit of the cloud computing center The unit compares each newly collected and calculated t3 with aT3. When t3 is less than a specific value X of aT3, the corresponding processing unit of the cloud computing center assigns a specific value Flag3 to the value, starts the alarm function, and presents Flag3 in the corresponding program; at the same time, the corresponding processing unit of the cloud computing center stops calculating the new aT3 value, and continues to compare the newly generated t3 with aT3. When t3 is less than a specific value X of aT3, the corresponding processing unit of the cloud computing center assigns a specific value Flag3 to the value, and starts the alarm function, and presents Flag3 in the corresponding program; this cycle is repeated until t3 is no longer less than a specific value X of aT3, the corresponding processing unit of the cloud computing center stops the alarm function, and no longer presents Flag3 in the corresponding program; A5, the computer program of the corresponding processing unit of the cloud computing center matches the manually entered information of the subject matter of the alarm, and when the alarm signal is issued at the time after the gestation period of the subject matter, the computer program presents a delivery alarm signal.

6. The animal delivery warning method based on near-hypothalamic temperature according to claim 1, characterized in that: The following specific algorithms and processes are used in step 2 to extract the temperature change patterns associated with animal parturition:

1. Signal preprocessing Noise Filtering Algorithm: Use a low-pass filter to remove high-frequency noise; formula: ;in, is the filter transfer function, is the cutoff frequency, is the order of the filter; Process: Design and apply a low-pass filter, input the original question signal into the filter, and output a smoothed signal; 2. Feature extraction Sliding window average Algorithm: Calculate the sliding average of the signal to reduce noise interference; formula: ;in, is the sliding average, is the window size; process: determine the sliding window size and calculate the average body temperature in each window; Temperature change rate calculation Algorithm: Calculate the rate of temperature change to identify significant changes before delivery; Formula: ;in, is the temperature change, is the temperature at the current time point; Process: For the smoothed signal, calculate the temperature changes at adjacent time points one by one.

7. The animal delivery warning method based on near-hypothalamic temperature according to claim 6, characterized in that: The pattern recognition of the temperature change pattern includes: Threshold Detection Algorithm: Set thresholds based on the rate of temperature change to identify temperature patterns before delivery; Official: If ; Process: Determine an appropriate rate-of-change threshold, detect if the temperature change exceeds the threshold, and trigger an alarm; Machine Learning Models Algorithm,classification using support vector machine; Process: Collect labeled temperature data; split the data into training and test sets; train the model and input the extracted features; test the model and evaluate the prediction accuracy; Data storage and update Process: Store the processed temperature data and extracted features in a database; update the model regularly to incorporate the latest data to improve prediction accuracy.

8. The animal delivery warning method based on near-hypothalamic temperature according to claim 1, characterized in that: The normal body temperature range and temperature change pattern before delivery are different for different animal species. The initial threshold can be set according to the animal species, including: a. Normal body temperature range; formula: ; and is the lower and upper limits of normal body temperature for a specific animal species; b. the temperature change threshold before delivery; formula: ; is the baseline value of normal body temperature; is the adjustment factor (set according to the farrowing characteristics of the animal species and usually learned from historical data); It is the average temperature change under normal conditions; for animals with poor health, the temperature change before delivery is more significant, and the threshold should be appropriately lowered, including: c. Health status score; by scoring the health status of the animal, the direction of threshold adjustment is determined; formula: ; is the health status score, Different health indicators. is the corresponding weight; d. Dynamic adjustment of threshold; adjust the monitoring threshold according to the health status score: formula: ; is the adjustment factor, controlling the effect of health status on the threshold; is the maximum value of the health score.

9. The animal delivery warning method based on near-hypothalamic temperature according to claim 8, characterized in that: Set up a dynamic update mechanism to monitor temperature and health data in real time and adjust thresholds regularly; 1) Moving mean and standard deviation Use sliding mean and standard deviation to update baseline values formula: ;After updating, recalculate the threshold based on the current data; Machine Learning Optimization 2) Use machine learning algorithms to optimize and adjust strategies Regression model, using a linear regression algorithm to predict the appropriate threshold official: .

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the animal delivery warning method based on hypothalamic temperature as described in any one of claims 1 to 9 are implemented.

Images