Pet intelligence production room

Abstract

The application discloses a pet intelligent delivery room, which comprises a medical box for accommodating pets, and the medical box is provided with a database, a collection module, a processing module and a warning module; the risk assessment process of the pet intelligent delivery room comprises the following steps: screening and classifying extraction of historical data of pet delivery processes previously imported into the database to determine risk related factors in the delivery process; the risk related factors are valued to obtain corresponding quantitative data, the quantitative data are preprocessed, and multiple ordered logistic regression analysis is performed on the processed data to obtain a logistic regression model; generalized linear model analysis is performed on the quantitative data, and the regression model is evaluated; physiological indexes of the pet delivery process are collected in real time, and a risk category is predicted; and when the risk assessment reaches a warning condition, an alarm information is sent through the warning module. The application can effectively predict and monitor the risk in the pet delivery process.

Description

TECHNICAL FIELD

[0001] The present application relates to a pet intelligent delivery room capable of assessing the risk of pet delivery process. BACKGROUND

[0002] More and more pets are kept in modern families, especially pet cats and dogs. Pet cats and dogs not only entertain our lives, but also accompany us to eliminate the loneliness of our lives. Usually, when pets give birth, such as cats and dogs, they will give birth in their own nests. For many white-collar pet owners, pet delivery is a time-consuming and important event.

[0003] The existing pet delivery room is usually a closed / semi-closed pet box, which mainly limits the activity space of the pet to reduce the risk. However, the pet delivery process is short for several hours, long for half a day or even longer, and may also appear difficult delivery. The existing pet delivery room cannot know the relevant situation of the pet delivery process, and cannot assess the risk of the health status of the pet delivery process.

[0004] In addition, when the pet delivery process appears risk, it needs to be assisted or sent to the pet hospital for treatment in time, which requires timely and effective notification to remind the pet owner. SUMMARY

[0005] In order to at least partially solve the deficiencies in the prior art, the main purpose of the present application is to provide a pet intelligent delivery room capable of assessing the risk of pet delivery process.

[0006] In order to achieve the above main purpose, the present application discloses a pet intelligent delivery room, comprising a medical box for accommodating pets, the medical box being provided with a database, a collection module, a processing module and a warning module; the database is used to store historical data of pet delivery process imported in advance and real-time data in pet delivery process, the collection module is used to collect relevant medical data of the pet and its delivery process at the moment, the processing module is used to screen and process the relevant medical data in the pet delivery process to construct a risk assessment model, and the warning module is used to warn when the risk assessment of the risk assessment model reaches the warning condition; wherein, the risk assessment process of the pet intelligent delivery room comprises:

[0007] screening and classifying the historical data of pet delivery process imported in advance in the database to determine the risk related factors in the delivery process;

[0008] The aforementioned risk-related factors are assigned values ​​to obtain corresponding quantitative data. The quantitative data is preprocessed and multivariate ordered logistic regression analysis is performed on the processed data to obtain a logistic regression model. This logistic regression model is the risk assessment model for pet parturition.

[0009] Using risk level as the dependent variable and risk factors with p < 0.1 as independent variables, a generalized linear model analysis was performed on the quantitative data to evaluate the merits of the regression model.

[0010] Real-time collection of physiological indicators during pet birthing to predict risk categories; when the risk assessment reaches the warning conditions, an alarm message is issued through the warning module, while the collection frequency of the collection module is increased and the risk assessment is updated in real time.

[0011] In the above technical solution of the present invention, a database is set up in the smart pet birthing room to store historical data of the pet birthing process. The data is processed by the processing module and a risk assessment model is constructed. The relevant medical data of the pet birthing process collected by the acquisition module is imported into the risk assessment model to realize real-time online monitoring and alarm control, thereby understanding the health status of the pet during the birthing process.

[0012] Among them, key risk-related factors obtained from the database are used to establish a risk assessment model, which can effectively predict and monitor the risks during pet birthing. This helps pet owners accurately understand the health status and birthing information of their pets, especially to notify them when risks occur, and provide timely and effective assistance to the pets in labor, ultimately reducing the risks during the birthing process and ensuring the health of the pets.

[0013] Furthermore, the identified risk-related factors included pet breed, maternal postpartum hemorrhage, interval between pup births, maternal body temperature, maternal respiratory rate, and maternal heart rate.

[0014] Optionally, the rules for assigning values ​​to risk-related factors are as follows:

[0015] Enter pet breed information and classify them into normal group and special group, assigning a value of 1 to normal group and 2 to special group;

[0016] The amount of postpartum hemorrhage in the mother is assigned a value according to the range: 1 for hemorrhage < 20% of the mother's total blood volume, 2 for hemorrhage ≤ 30% of the mother's total blood volume, and 3 for hemorrhage > 30% of the mother's total blood volume.

[0017] The time interval between the birth of two cubs is also assigned according to intervals, and the time interval <60 minutes is assigned as 1, 60 minutes≤time interval≤120 minutes is assigned as 2, and the time interval >120 minutes is assigned as 3.

[0018] The maternal body temperature is also assigned according to intervals, and 36℃≤maternal body temperature≤39℃ is assigned as 1, maternal body temperature <36℃ is assigned as 2, and maternal body temperature >39℃ is assigned as 3.

[0019] The maternal respiratory rate is also assigned according to intervals, and 15 times / minute≤maternal respiratory rate≤35 times / minute is assigned as 1, maternal respiratory rate <15 times / minute is assigned as 2, and maternal respiratory rate >35 times / minute is assigned as 3.

[0020] The maternal heart rate is also assigned according to intervals, and 60 times / minute≤maternal heart rate≤100 times / minute is assigned as 1, maternal heart rate <60 times / minute is assigned as 2, and maternal heart rate >100 times / minute is assigned as 3.

[0021] The risk level is divided into three levels, and no risk is assigned as 0, moderate risk is assigned as 1, and severe risk is assigned as 2.

[0022] Optionally, the process of preprocessing the quantitative data includes: first, performing chi-square test on all variables after assignment, and screening out all variables with a probability value p less than a set threshold; performing multivariate ordinal logistic regression analysis on the remaining variables to obtain a logistic regression model, and performing parallel line test on the obtained regression equation.

[0023] Specifically, the set threshold in the chi-square test is 0.1.

[0024] Further, the model evaluation index for evaluating the pros and cons of the regression model is AIC and BIC, that is, when evaluating the pros and cons of the regression model, AIC (Akaike information criterion) and BIC (Bayesian information criterion) are used to evaluate the pros and cons of the obtained multivariate ordinal logistic regression model.

[0025] Optionally, the obtained logistic regression model can also be subjected to parallel line test, and in the parallel line test, sig needs to be greater than 0.05.

[0026] Further, based on the statistical software SPSS, multivariate ordinal regression analysis is performed to obtain a multivariate ordinal logistic regression equation as follows:

[0027] Wherein, a1 represents the assignment of pet species, a2 represents the assignment of postpartum hemorrhage of the mother, a3 represents the assignment of the birth interval of the offspring, a5 represents the assignment of respiratory frequency, a6 represents the assignment of the heart rate of the mother, P is the probability, j is the category, Pj is the probability corresponding to the category j, x is the independent variable, Y is the dependent variable, β is the regression coefficient of the independent variable x, exp is the exponential function of e, P0 represents the probability of no risk, P1 represents the probability of moderate risk, and P2 represents the probability of severe risk.

[0028] Optionally, the warning value and the alarm value are set in the warning module, wherein, when P1>P0 and P1>P2, the warning is performed, and when P2>P0 and P2>P1, the alarm is performed; the early warning information is sent when the risk assessment reaches the warning condition, and the alarm information is sent when the risk assessment reaches the alarm condition.

[0029] In the above technical solution, by setting the graded warning and alarm, the pet owner can be notified more timely and accurately, so that the pet owner can provide timely and effective help to the pet in labor.

[0030] In order to more clearly illustrate the purpose, technical scheme and advantages of the present application, the present application will be further described in detail below with reference to the drawings and specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 is the framework diagram of the pet intelligent delivery room of the present application;

[0032] Figure 2 is the risk assessment flowchart of the pet intelligent delivery room of the present application. DETAILED DESCRIPTION

[0033] In the following description, many specific details are set forth in connection with the implementation in order to fully understand the present application, but it should be understood that the following implementation and detailed description are only for the purpose of illustration and do not limit the protection scope of the present application.

[0034] The pet intelligent delivery room of the embodiment is shown as Figure 1 , which includes a medical kit and a data module, a collection module, a processing module and a warning module carried on the medical kit.

[0035] The data module is used to provide a database, in which pre-imported historical data of pet delivery process and real-time data in pet delivery process are stored, and the historical data in the initial state is shown in the following Table 1 (wherein the assignment in the historical data is made according to the assignment variable description in Table 2 below).

[0036] Table 1: Historical data of pet delivery process

[0037] Breed Amount of bleeding Interval time Body temperature Respiration Heartbeat Risk level 1 1 1 1 1 1 0 1 1 1 1 2 1 1 1 1 1 1 3 1 1 2 2 2 2 2 2 2 2 3 3 3 3 3 2 2 2 1 1 1 3 2 2 1 3 1 1 1 2 1 1 2 1 1 1 0 1 3 1 1 1 1 2 1 2 1 3 1 1 1 1 1 3 2 1 1 2 1 1 2 1 1 1 0 2 1 2 2 1 1 2 2 1 2 3 1 1 1 2 1 2 2 2 1 2 1 1 2 2 2 2 2 1 1 2 2 3 1 2 1 1 2 2 2 3 2 2 1 2 2 3 2 2 2 1 2 2 3 3 2 1 2 1 1 2 2 1 1 2 1 1 2 1 1 2 2 1 2 2 2 2 2 2 1 2 2 2 2 2 2 1 3 2 2 2 1 2 1 3 3 1 1 1 2 1 3 2 1 1 2 3 1 3 1 1 2 2 3 3 3 3 1 2 2 3 3 3 1 1 2 1 2 3 1 1 1 2 1 1 1 3 1 1 1 2 2 3 2 2 2 2 1 1 1 1 1 1 0 1 1 1 1 2 1 1 1 1 1 1 3 1 1 2 2 2 2 2 2 2 2 3 3 3 3 3 2 2 2 1 1 1 3 2 2 1 3 1 1 1 2 1 1 2 1 1 1 0 1 3 1 1 1 1 2 1 2 1 3 1 1 1 1 1 3 2 1 1 2 1 1 2 1 1 1 0 2 1 2 2 1 1 2 2 1 2 3 1 1 1 2 1 2 2 2 1 2 1 1 2 2 2 2 2 1 1 2 2 3 1 2 1 1 2 2 2 3 2 2 1 2 2 3 2 2 2 1 2 2 3 3 2 1 2 1 1 2 2 1 1 2 1 1 2 1 1 2 2 1 2 2 2 2 2 2 1 2 2 2 2 2 2 1 3 2 2 2 1 2 1 3 3 1 1 1 2 1 3 2 1 1 2 3 1 3 1 1 2 2 3 3 3 3 1 2 2 3 3 3 1 1 2 1 2 3 1 1 1 2 1 1 1 3 1 1 1 2 2 3 2 2 2 2 2 3 3 3 3 3 2 2 3 3 3 1 3 2 2 3 1 1 1 1 2 1 2 3 2 2 2 2

[0038] The collection module is used to collect the relevant medical data of the pet and its delivery process. After screening, the determined relevant medical data includes six items, i.e., pet breed, maternal postpartum bleeding volume, birth interval of the pups, maternal body temperature, maternal respiratory rate, and maternal heart rate, and the six relevant medical data are taken as risk-related factors. The collection of the pet breed is specifically based on the input of the pet owner. In some scenarios, for example, when applied to a pet hospital, an image recognition function can be added, i.e., a camera is used to identify and determine the pet breed.

[0039] The postpartum bleeding volume can be obtained by a liquid detector. For example, the bottom of the medical kit is provided with a detection bin, and the liquid detector is arranged in the detection bin. The liquid detector can distinguish amniotic fluid and urine by measuring the pH value of the liquid, and distinguish amniotic fluid, urine and blood by chromatographic analysis. Further, the liquid detector can start continuous detection of blood after detecting blood for the first time to obtain the bleeding volume, or introduce the liquid into a blood storage box when blood is detected to obtain the bleeding volume by detecting the amount of liquid in the blood storage box.

[0040] The birth interval of the pups can be sensed and obtained by, for example, an infrared sensor. The number of individuals detected by the infrared sensor corresponds to the time of birth of the pups. For example, the time of detecting the first body temperature is T0, which indicates that the mother is sent in. The time of detecting the second body temperature is T1, which indicates the birth of the first pup. Similarly, the time of detecting the last pup is Tn, where n is the total number of pups. The birth interval of the pups can be obtained by calculating the difference between the above-mentioned times.

[0041] Meanwhile, the maternal body temperature can also be detected by the infrared sensor. Correspondingly, the maternal respiratory rate and the maternal heart rate can be detected by a vital sign monitor. The vital sign monitor can also detect the body temperature. The vital sign monitor is, for example, a pedestal device (i.e., a monitoring pedestal) that can monitor the pet when it is squatting. The pedestal device is used as the bottom plate of the medical kit. In other embodiments, the vital sign monitor can also be a wearable device.

[0042] The processing module is used to screen and process the aforementioned relevant medical data during the delivery process of the pet to construct a risk assessment model. The warning module is connected to the processing module. During the delivery process of the pet, the relevant data is collected in real time by the collection module, and the collected data is transmitted to the risk assessment model of the processing module. When the risk score of the risk assessment model exceeds the threshold value, the warning module is used for warning.

[0043] The risk assessment process of the pet smart delivery room in the embodiment includes:

[0044] First, the historical data of the pet delivery process pre-imported in the database is screened and classified to determine the risk-related factors in the delivery process; wherein the determined risk-related factors include pet breed, postpartum bleeding volume of the mother, birth time interval of the offspring, body temperature of the mother, respiratory rate of the mother and heart rate of the mother.

[0045] Then, the aforementioned risk-related factors are assigned to obtain corresponding quantitative data, and the exemplary assignment rules of the aforementioned six risk-related factors are as follows (as shown in Table 2 below):

[0046] 1) Enter the pet breed information and classify it into normal group and special group, the normal group is assigned as 1 and the special group is assigned as 2.

[0047] 2) The postpartum bleeding volume of the mother is assigned according to the interval, the bleeding volume < 20% of the whole body blood volume of the mother is assigned as 1, 20% ≤ bleeding volume ≤ 30% is assigned as 2, and bleeding volume > 30% is assigned as 3.

[0048] 3) The time interval of the birth of two offspring is also assigned according to the interval, the time interval < 60 minutes is assigned as 1, 60 minutes ≤ time interval ≤ 120 minutes is assigned as 2, and the time interval > 120 minutes is assigned as 3.

[0049] 4) The body temperature of the mother is also assigned according to the interval, 36℃ ≤ body temperature of the mother ≤ 39℃ is assigned as 1, body temperature of the mother < 36℃ is assigned as 2, and body temperature of the mother > 39℃ is assigned as 3.

[0050] 5) The respiratory rate of the mother is also assigned according to the interval, 15 times / minute ≤ respiratory rate of the mother ≤ 15 times / minute is assigned as 1, respiratory rate of the mother < 15 times / minute is assigned as 2, and respiratory rate of the mother > 35 times / minute is assigned as 3.

[0051] 6) The heart rate of the mother is also assigned according to the interval, 60 times / minute ≤ heart rate of the mother ≤ 100 times / minute is assigned as 1, heart rate of the mother < 60 times / minute is assigned as 2, and heart rate of the mother > 100 times / minute is assigned as 3.

[0052] 7) The risk level is divided into three levels, no risk is assigned as 0, moderate risk is assigned as 1, and severe risk is assigned as 2. (Table 2)

[0053] Table 2: Assignment variable explanation

[0054] Variable name Variable code Variable definition Mean Standard deviation Breed of pet a1 Normal group assigned as 1, special group assigned as 2 1.5000 0.504 Amount of postpartum bleeding of mother a2 Amount of bleeding < 20% of total blood volume of mother assigned as 1, 20% ≤ amount of bleeding ≤ 30% assigned as 2, amount of bleeding > 30% assigned as 3 1.7286 0.760 Interval time of birth of pups a3 Interval time < 60 minutes assigned as 1, 60 minutes ≤ interval time ≤ 120 minutes assigned as 2, interval time > 120 minutes assigned as 3 1.8000 0.809 Body temperature of mother a4 36℃ ≤ body temperature of mother ≤ 39℃ assigned as 1, body temperature of mother < 36℃ assigned as 2, body temperature of mother > 39℃ assigned as 3 1.9857 0.807 Respiration frequency of mother a5 15 times / minute ≤ respiration frequency of mother ≤ 35 times / minute assigned as 1, respiration frequency of mother < 15 times / minute assigned as 2, respiration frequency of mother > 35 times / minute assigned as 3 1.7857 0.778 Heart rate of mother a6 60 times / minute ≤ heart rate of mother ≤ 100 times / minute assigned as 1, heart rate of mother < 60 times / minute assigned as 2, heart rate of mother > 100 times / minute assigned as 3 1.5286 0.737 Risk level - No risk assigned as 0, moderate risk assigned as 1, severe risk assigned as 2 - -

[0055] Next, the quantitative data is preprocessed. The preferred process of preprocessing includes: first, performing chi-square test on all variables after assignment, and screening out all variables with probability value p less than the set threshold, wherein the set threshold in chi-square test is 0.1.

[0056] Following that, the processed data is subjected to multivariate ordered logistic regression analysis, and a parallel line test is performed to obtain a logistic regression model, which is the risk assessment model in the pet delivery process; in this embodiment, the parallel line test sig value is 0.096, and the parallel line test passes. In the logistic regression equation, whether there is a risk is the dependent variable, the risk factor with p<0.1 is the independent variable, multivariate ordered regression logistic analysis is adopted, multivariate ordered regression analysis is performed based on the statistical software SPSS, and a logistic regression equation and a regression result table (as shown in Table 3 below) are obtained:

[0057] wherein a1 represents the value of the pet breed, a2 represents the value of the postpartum hemorrhage amount of the mother, a3 represents the value of the birth time interval of the pups, a5 represents the value of the respiratory frequency, a6 represents the value of the heart rate of the mother, P is the probability, j is the category, Pj is the probability corresponding to the category j, x is the independent variable, Y is the dependent variable, β is the regression coefficient of the independent variable x, exp is the exponential function of e, is the constant term of the category j, P0 represents the probability of no risk, P1 represents the probability of moderate risk, and P2 represents the probability of severe risk. Through the above process, the body temperature of the mother is not significant.

[0058] Table 3: Regression results of risk factors in pet delivery process

[0059] Variable name Coefficient Standard error Wald value Exp(B) OR value sig Breed of pet 1 -3.191 1.098 8.454 0.041 0.004 Breed of pet 2 0 a ]] - - 1 - Amount of postpartum bleeding of mother 2.953 0.919 10.331 19.172 0.001 Interval time of birth of pups 3.152 0.904 12.161 23.393 0.000 Body temperature of mother 0.477 0.474 1.012 1.611 0.314 Respiration frequency of mother 1.601 0.606 6.969 4.956 0.008 Heart rate of mother 2.002 0.908 4.857 7.403 0.028

[0060] Finally, the risk value is taken as the dependent variable, and the risk factor with p<0.1 is taken as the independent variable to perform generalized linear model analysis on the quantitative data, and the OR value, Omnibus test value, AIC, and BIC value of the logistic regression model are obtained as shown in Table 4:

[0061] Table 4: Model evaluation

[0062] Model -2 Log likelihood Pearson chi-square AIC BIC Omnibus test sig Parallel line test sig Model I 53.049 22.995 67.499 85.487 0.000 0.096 Model II - - 109.380 111.741 0.000 -

[0063] Note: Model I is a multivariate ordered regression model, and Model II is a linear model.

[0064] Among them, the OR value of the logistic regression model is used to analyze the contribution of each risk factor to the risk value, and the Omnibus test value, AIC, and BIC value of the logistic regression model are used to analyze the advantages and disadvantages of the model.

[0065] Real-time monitoring of medical indicators of the pet delivery process is collected, a regression equation is used for category prediction, when the risk assessment reaches the early warning information, an alarm information is sent through the early warning module, and the collection frequency of the collection module is improved and the risk assessment is updated in real time.

[0066] Preferably, the early warning value and the alarm value are set in the early warning module, wherein P1>P0 and P1>P2, early warning is performed, and P2>P0 and P2>P1, alarm is performed; early warning information is sent when the risk assessment reaches the early warning condition, and alarm information is sent when the risk assessment reaches the alarm condition. In the embodiment, by setting the graded early warning and alarm, the pet owner can be notified more timely and accurately, so that the pet owner can provide timely and effective help to the pet during delivery.

[0067] In addition, when the pet smart delivery room of the embodiment is used in a pet hospital, the monitoring data and early warning and alarm information can also be transmitted to a smart terminal or a cloud server through wireless methods such as Bluetooth or Wi-Fi, so that the pet owner or the pet doctor can check and analyze at any time.

[0068] Although the above describes the present application through embodiments, the above embodiments are only used to exemplarily describe the implementable solutions of the present application, and are not used to limit the protection scope of the present application, and any equivalent replacement or change made by those skilled in the art according to the present application should also be covered by the protection scope defined by the claims of the present application.

Claims

1. A smart pet birthing room, comprising a medical box for accommodating pets, the medical box being equipped with a database, a data acquisition module, a processing module, and an early warning module; the database is used to store pre-imported historical data of the pet's birthing process and to store real-time data of the pet's birthing process; the data acquisition module is used to collect relevant medical data of the pet at present and during its birthing process; the processing module is used to filter and process the aforementioned relevant medical data during the pet's birthing process to construct a risk assessment model; the early warning module is used to issue an early warning when the risk assessment of the aforementioned risk assessment model reaches the early warning conditions; wherein, The risk assessment process for the smart pet birthing room includes: Historical data on pet birthing processes imported into the database were screened, categorized, and extracted to identify risk-related factors during the birthing process. These risk-related factors included pet breed, maternal postpartum hemorrhage, interval between pup births, maternal body temperature, maternal respiratory rate, and maternal heart rate. The aforementioned risk-related factors were assigned values ​​to obtain corresponding quantitative data. This quantitative data was preprocessed, and a multivariate ordered logistic regression analysis was performed on the processed data to obtain a logistic regression model. This logistic regression model serves as the risk assessment model for pet parturition. The multivariate ordered logistic regression equation was obtained using SPSS statistical software, as follows: Where a1 represents the pet breed, a2 represents the maternal postpartum hemorrhage, a3 represents the time interval between pup births, a5 represents the respiratory rate, a6 represents the maternal heart rate, P is the probability, j is the category, Pj is the probability corresponding to category j, x is the independent variable, Y is the dependent variable, β is the regression coefficient of the independent variable x, and exp is the exponential function of e. Let P0 be a constant term for category j, where P0 represents the probability of no risk, P1 represents the probability of moderate risk, and P2 represents the probability of severe risk. Using risk level as the dependent variable and risk factors with p < 0.1 as independent variables, a generalized linear model analysis was performed on the quantitative data to evaluate the merits of the regression model. Real-time collection of physiological indicators during pet birthing to predict risk categories; when the risk assessment reaches the warning conditions, an alarm message is issued through the warning module, while the collection frequency of the collection module is increased and the risk assessment is updated in real time.

2. The smart pet birthing room according to claim 1, characterized in that: The rules for assigning values ​​to risk-related factors are as follows: Enter pet breed information and classify them into normal group and special group, assigning a value of 1 to normal group and 2 to special group; The amount of postpartum hemorrhage in the mother is assigned a value according to the range: 1 for hemorrhage < 20% of the mother's total blood volume, 2 for hemorrhage ≤ 30% of the mother's total blood volume, and 3 for hemorrhage > 30% of the mother's total blood volume. The time interval between the births of the two cubs is also assigned a value according to the interval: the time interval < 60 minutes is assigned a value of 1, 60 minutes ≤ time interval ≤ 120 minutes is assigned a value of 2, and the time interval > 120 minutes is assigned a value of 3. Maternal body temperature is also assigned values ​​according to ranges: 36℃≤maternal body temperature≤39℃ is assigned a value of 1, maternal body temperature<36℃ is assigned a value of 2, and maternal body temperature>39℃ is assigned a value of 3. The maternal respiratory rate is also assigned a value according to the interval: 15 breaths / minute ≤ maternal respiratory rate ≤ 35 breaths / minute is assigned a value of 1, maternal respiratory rate < 15 breaths / minute is assigned a value of 2, and maternal respiratory rate > 35 breaths / minute is assigned a value of 3. The maternal heart rate is also assigned values ​​according to intervals: 60 beats / minute ≤ maternal heart rate ≤ 100 beats / minute is assigned 1, maternal heart rate < 60 beats / minute is assigned 2, and maternal heart rate > 100 beats / minute is assigned 3. The risk level is divided into 3 levels: no risk is assigned a value of 0, moderate risk is assigned a value of 1, and severe risk is assigned a value of 2.

3. The smart pet birthing room according to claim 2, characterized in that: The preprocessing of quantitative data includes: first, performing a chi-square test on all variables after assignment, and filtering out all variables whose probability value p is less than a set threshold; then, performing multivariate ordered logistic regression analysis on the remaining variables to obtain a logistic regression model, and finally performing a parallel line test on the obtained regression equation.

4. The smart pet birthing room according to claim 3, characterized in that: The threshold value for the chi-square test is set at 0.

1.

5. The smart pet birthing room according to claim 1, characterized in that: The model evaluation metrics used to assess the quality of regression models are AIC and BIC.

6. The smart pet birthing room according to claim 1, characterized in that: The early warning module sets early warning and alarm values. When P1 > P0 and P1 > P2, an early warning is issued; when P2 > P0 and P2 > P1, an alarm is issued. An early warning message is issued when the risk assessment meets the early warning conditions, and an alarm message is issued when the risk assessment meets the alarm conditions.

Images