Intelligent delivery room for pets

Abstract

The invention discloses an intelligent delivery room for pets, which comprises a medical kit for accommodating pets, and is characterized in that the medical kit carries a database, an acquisition module, a processing module and an early warning module; the risk assessment process of the intelligent delivery room for the pets comprises the following steps: screening, classifying and extracting pre-imported historical data of the delivery process of the pets in a database, and determining risk-related factors in the delivery process; carrying out assignment on the risk related factors to obtain corresponding quantitative data, carrying out preprocessing on the quantitative data, and carrying out multivariate ordered logistic regression analysis on the processed data to obtain a logistic regression model; carrying out generalized linear model analysis on the quantized data, and evaluating the advantages and disadvantages of a regression model; physiological indexes in the delivery process of the pet are collected in real time, and risk categories are predicted; and when the risk assessment reaches an early warning condition, alarm information is sent out through an early warning module. According to the invention, the risk in the delivery process of the pet can be effectively predicted and monitored.

Description

Technical Field

[0001] The invention relates to a smart delivery room for pets which can perform risk assessment on the delivery process of pets. Background Art

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

[0003] The pet delivery room in the prior art is usually a closed / semi-closed pet box, which mainly limits the pet's activity space to reduce risks. However, the pet delivery process can take a few hours or half a day or even longer, and there may be dystocia. The existing pet delivery room cannot know the relevant situation of the pet's delivery process, let alone conduct risk assessment of the pet's health status during delivery.

[0004] In addition, when there are risks during the pet's delivery process, timely assistance or sending the pet to a pet hospital for treatment is required, which requires timely and effective notifications to remind pet owners. Summary of the invention

[0005] In order to at least partially solve the deficiencies in the prior art, the main purpose of the present invention is to provide a pet smart delivery room that can perform risk assessment on the pet's delivery process.

[0006] In order to achieve the above main purpose, the present invention discloses a smart delivery room for pets, including a medical box for accommodating pets, the medical box is equipped with a database, a collection module, a processing module and an early warning module; the database is used to store historical data of the pet's delivery process pre-imported and store real-time data of the pet's delivery process, the collection module is used to collect relevant medical data of the current pet and its delivery process, the processing module is used to screen and process the aforementioned relevant medical data in the pet's delivery process to construct a risk assessment model, and 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 condition; wherein, the risk assessment process of the smart delivery room for pets includes:

[0007] Screen and classify the historical data of pet delivery process pre-imported in the database to determine the risk-related factors in the delivery process;

[0008] Assign values ​​to the aforementioned risk-related factors to obtain corresponding quantitative data, preprocess the quantitative data and perform multivariate ordered logistic regression analysis on the processed data to obtain a logistic regression model, which is a risk assessment model for the pet delivery process;

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

[0010] Real-time collection of physiological indicators of pet delivery process to predict risk categories; when the risk assessment reaches the warning conditions, the warning module will issue an alarm message, while increasing the collection frequency of the collection module and updating the risk assessment in real time.

[0011] In the above technical solution of the present invention, a database is set up in the pet smart delivery room to store historical data of the pet's delivery process. The data is processed by the processing module and a risk assessment model is constructed. The relevant medical data of the pet's delivery 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's delivery process.

[0012] Among them, a risk assessment model is established based on the key risk-related factors obtained from the data in the database, which can effectively predict and monitor the risks during the pet's delivery process. This helps pet owners to accurately understand the health status and delivery information of their pets during delivery, especially to notify them when risks occur, and then provide timely and effective assistance to pets in delivery, ultimately reducing the risks in the delivery process and protecting the health of pets.

[0013] Further, the risk-associated factors identified included pet breed, maternal postpartum blood loss, pup birth interval, 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 it into normal group and special group. The normal group is assigned a value of 1 and the special group is assigned a value of 2.

[0016] The amount of postpartum bleeding of the mother is assigned a value according to the interval. The amount of bleeding < 20% of the total blood volume of the mother is assigned a value of 1, 20% of the total blood volume of the mother ≤ the amount of bleeding ≤ 30% of the total blood volume of the mother is assigned a value of 2, and the amount of bleeding > 30% of the total blood volume of the mother is assigned a value of 3.

[0017] The time interval between the births of two cubs is also assigned a value according to the interval: a time interval of less than 60 minutes is assigned a value of 1, a time interval of 60 minutes ≤ time interval ≤ 120 minutes is assigned a value of 2, and a time interval of more than 120 minutes is assigned a value of 3;

[0018] Maternal body temperature is also assigned a value according to the interval: 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;

[0019] Maternal respiratory rate was also assigned a value according to the interval: 15 times / minute ≤ maternal respiratory rate ≤ 35 times / minute was assigned a value of 1, maternal respiratory rate <15 times / minute was assigned a value of 2, and maternal respiratory rate >35 times / minute was assigned a value of 3;

[0020] The maternal heart rate is also assigned a value according to the interval: 60 beats / minute ≤ maternal heart rate ≤ 100 beats / minute is assigned a value of 1, maternal heart rate < 60 beats / minute is assigned a value of 2, and maternal heart rate > 100 beats / minute is assigned a value of 3;

[0021] The risk level is divided into 3 levels, with no risk being 0, moderate risk being 1, and severe risk being 2.

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

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

[0024] Furthermore, the model evaluation indicators for evaluating the quality of the regression model are AIC and BIC, that is, when evaluating the quality of the regression model, AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion) are used to evaluate the quality of the obtained multivariate ordered logistic regression model.

[0025] Optionally, a parallel line test can be performed on the obtained logistic regression model, wherein the sig in the parallel line test needs to be greater than 0.05.

[0026] Furthermore, based on the statistical software SPSS, a multivariate ordered regression analysis was performed, and the multivariate ordered logistic regression equation was obtained as follows:

[0027] logit(p0)=8.782-3.191*a1+2.953*a2+3.152*a3+1.601*a5+2.002*a6;

[0028] logit(p0+p1)=13.405-3.191*a1+2.953*a2+3.152*a3+1.601*a5+2.002*a6;

[0029]

[0030] P2 = 1-P1;

[0031] Among them, a1 represents the pet breed, a2 represents the amount of postpartum bleeding of the mother, a3 represents the time interval between the birth of the pups, a5 represents the respiratory rate, a6 represents the mother's heart rate, P0 represents the probability of no risk, P1 represents the probability of moderate risk, and P3 represents the probability of severe risk.

[0032] Optionally, warning values ​​and alarm values ​​are set in the warning module, wherein when P1>P0 and P1>P2, a warning is issued, and when P2>P0 and P2>P1, an alarm is issued; an advance warning message is issued when the risk assessment reaches the warning condition, and an alarm message is issued when the risk assessment reaches the alarm condition.

[0033] In the above technical solution, by setting graded warnings and alarms, pet owners can be notified more promptly and accurately, so that pet owners can provide timely and effective assistance to pets in labor.

[0034] In order to more clearly illustrate the purpose, technical solutions and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a framework diagram of the pet smart delivery room of the present invention;

[0036] Figure 2 It is a risk assessment flow chart of the pet smart delivery room of the present invention. DETAILED DESCRIPTION

[0037] In the following description, many specific details are explained in conjunction with the embodiments to facilitate a full understanding of the present invention. However, it should be understood that the following embodiments and detailed descriptions are only for illustrative purposes and do not limit the scope of protection of the present invention.

[0038] The pet smart delivery room of the embodiment is as follows Figure 1 As shown, it includes a medical box and a data module, a collection module, a processing module and an early warning module mounted on the medical box.

[0039] The data module is used to provide a database, which stores pre-imported historical data of the pet's delivery process and real-time data of the pet's delivery process. The historical data in the initial state is shown in the following Appendix 1 (the assignment in the historical data is based on the assignment variable description in the following Table 2).

[0040] Appendix 1: Historical data of pet delivery process

[0041]

[0042]

[0043]

[0044] The collection module is used to collect relevant medical data of the current pet and its delivery process. After screening, the relevant medical data determined include pet breed, maternal postpartum bleeding, pup birth interval, maternal body temperature, maternal respiratory rate and maternal heart rate, and these six relevant medical data are used as risk-related factors. Among them, the collection of pet breeds depends on the input of pet owners. In some scenarios, such as when it is applied to pet hospitals, image recognition function can be added, that is, using cameras to identify and judge pet breeds.

[0045] The amount of postpartum bleeding can be obtained through a liquid detector. For example, a detection chamber is provided at the bottom of the medical box, and the liquid detector is arranged in the detection chamber; wherein the liquid detector can distinguish between amniotic fluid and urine by measuring the pH value of the liquid, and can distinguish between amniotic fluid, urine and blood by chromatographic analysis. Furthermore, the liquid detector can start to continuously detect blood after the first detection of blood to obtain the amount of bleeding, or introduce liquid into, for example, a blood storage box when blood is detected, and obtain the amount of bleeding by detecting the amount of liquid in the blood storage box.

[0046] The time interval between cub births can be sensed and obtained by, for example, an infrared sensor. The number of individuals whose body temperatures are detected by infrared sensors corresponds to the time when the cubs are born. For example, the time when the first body temperature is detected is T0, indicating that the mother has been sent in. The time when the second body temperature is detected is T1, indicating the first cub. And so on, until the last cub, the corresponding time is Tn, where n is the total number of cubs. The time interval between cub births can be obtained by calculating the difference between the above times.

[0047] At the same time, the mother's body temperature can also be detected by an infrared sensor. Correspondingly, the mother's respiratory rate and heart rate can be detected by a vital sign monitor, which can also detect body temperature. The vital sign monitor is, for example, a pedestal device (i.e., a monitoring table), which can be used as the bottom plate of the medical box when the pet is squatting or lying down. In other embodiments, the vital sign monitor can also be a wearable device.

[0048] The processing module is used to screen and process the aforementioned relevant medical data during the pet's delivery process to construct a risk assessment model; the early warning module is connected to the processing module. During the pet's delivery process, the collection module collects relevant data in real time, and transmits the collected data to the risk assessment model of the processing module. When the risk score of the risk assessment model exceeds the threshold, the early warning module will issue an early warning.

[0049] The risk assessment process of the pet smart delivery room in the embodiment includes:

[0050] First, the historical data of pet delivery process pre-imported into the database are screened and classified to determine the risk-related factors in the delivery process; among them, the determined risk-related factors include pet breed, maternal postpartum bleeding volume, time interval between puppies’ birth, maternal body temperature, maternal respiratory rate and maternal heart rate.

[0051] Then, the aforementioned risk-related factors are assigned values ​​to obtain corresponding quantitative data. The exemplary assignment rules for the aforementioned six risk-related factors are as follows (as shown in Table 2 below):

[0052] 1) Enter pet breed information and classify it into a normal group and a special group. The normal group is assigned a value of 1 and the special group is assigned a value of 2.

[0053] 2) The amount of postpartum bleeding of the mother is assigned a value according to an interval: a value of 1 is assigned if the amount of bleeding is less than 20% of the mother's total blood volume, a value of 2 is assigned if 20% ≤ the amount of bleeding ≤ 30%, and a value of 3 is assigned if the amount of bleeding is greater than 30%.

[0054] 3) The time interval between the births of two cubs is also assigned a value according to the interval: a time interval of less than 60 minutes is assigned a value of 1, a time interval of 60 minutes ≤ time interval ≤ 120 minutes is assigned a value of 2, and a time interval of more than 120 minutes is assigned a value of 3.

[0055] 4) Maternal body temperature is also assigned a value according to the interval: 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.

[0056] 5) Maternal respiratory rate is also assigned a value according to the interval: 15 times / minute ≤ maternal respiratory rate ≤ 15 times / minute is assigned a value of 1, maternal respiratory rate <15 times / minute is assigned a value of 2, and maternal respiratory rate >35 times / minute is assigned a value of 3.

[0057] 6) The maternal heart rate is also assigned a value according to the interval: 60 beats / minute ≤ maternal heart rate ≤ 100 beats / minute is assigned a value of 1, the maternal heart rate <60 beats / minute is assigned a value of 2, and the maternal heart rate >100 beats / minute is assigned a value of 3.

[0058] 7) The risk level is divided into 3 levels, with no risk assigned to 0, moderate risk to 1, and severe risk to 2. (Table 2)

[0059] Table 2: Description of assigned variables

[0060]

[0061] Next, the quantitative data is preprocessed. The preferred process of preprocessing includes: firstly, a chi-square test is performed on all variables after the assignment, and all variables with probability values ​​p less than a set threshold are screened out, wherein the set threshold in the chi-square test is 0.1.

[0062] Next, the processed data was subjected to multivariate ordered logistic regression analysis, and a parallel line test was performed to obtain a logistic regression model, which is a risk assessment model for pet delivery; in this embodiment, the parallel line test sig value is 0.096, and the parallel line test passed. In the logistic regression equation, whether there is a risk is the dependent variable, and the risk factor with p < 0.1 is the independent variable. Multivariate ordered regression logistic analysis is used, and multivariate ordered regression analysis is performed based on the statistical software SPSS to obtain the logistic regression equation and the regression result table (as shown in Table 3 below):

[0063] logit(p0)=8.782-3.191*a1+2.953*a2+3.152*a3+1.601*a5+2.002*a6

[0064] logit(p0+p1)=13.405-3.191*a1+2.953*a2+3.152*a3+1.601*a5+2.002*a6

[0065]

[0066] P2=1-P1

[0067] Among them, a1 represents the pet breed, a2 represents the amount of postpartum bleeding of the mother, a3 represents the time interval between the birth of the pups, a5 represents the respiratory rate, a6 represents the mother's heart rate, P0 represents the probability of no risk, P1 represents the probability of moderate risk, and P3 represents the probability of severe risk. After the above process, the maternal body temperature was not significant.

[0068] Table 3: Regression results of risk factors in pet delivery process

[0069]

[0070]

[0071] Finally, the quantitative data were analyzed by generalized linear model with risk value as dependent variable and risk factor with p<0.1 as independent variable, and the OR value, Omnibus test value, AIC and BIC values ​​of the logistic regression model were obtained as shown in Table 4:

[0072] Table 4: Model quality evaluation

[0073]

[0074] Note: Model I is a multivariate ordered regression model, and Model II is a linear model.

[0075] Among them, the OR value of the logistic regression model was used to analyze the contribution of each risk factor to the risk value, and the Omnibus test value, AIC, and BIC values ​​of the logistic regression model were used to analyze the advantages and disadvantages of the model.

[0076] Medical indicators of the pet's delivery process are monitored and collected in real time, and the indicators are brought into the regression equation for category prediction. When the risk assessment reaches the early warning level, an alarm is issued through the early warning module. At the same time, the collection frequency of the collection module is increased and the risk assessment is updated in real time.

[0077] Preferably, a warning value and an alarm value are set in the warning module, wherein when P1>P0 and P1>P2, a warning is issued, and when P2>P0 and P2>P1, an alarm is issued; when the risk assessment reaches the warning condition, an early warning message is issued, and when the risk assessment reaches the alarm condition, an alarm message is issued. In the embodiment, by setting graded warnings and alarms, 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.

[0078] In addition, when the pet smart delivery room in the embodiment is used in a pet hospital, the monitoring data and early warning alarm information can also be transmitted to the smart terminal or cloud server via wireless methods such as Bluetooth or Wi-Fi, so that pet owners or pet doctors can view and analyze them at any time.

[0079] Although the present invention has been described above through embodiments, the above embodiments are only used to exemplarily describe the feasible implementation schemes of the present invention, and are not used to limit the protection scope of the present invention. Any equivalent substitutions or changes made by those skilled in the art in accordance with the present invention should also be covered by the protection scope defined by the claims of the present invention.

Claims

1. A smart delivery room for pets, comprising a medical box for accommodating pets, the medical box being equipped with a database, a collection module, a processing module and an early warning module; the database being used to store historical data of the pet's delivery process pre-imported and to store real-time data of the pet's delivery process, the collection module being used to collect relevant medical data of the current pet and its delivery process, the processing module being used to screen and process the aforementioned relevant medical data in the pet's delivery process to construct a risk assessment model, and the early warning module being used to issue an early warning when the risk assessment of the aforementioned risk assessment model reaches an early warning condition; wherein, The risk assessment process of the pet smart delivery room includes: Screen and classify the historical data of pet delivery process pre-imported in the database to determine the risk-related factors in the delivery process; Assign values ​​to the aforementioned risk-related factors to obtain corresponding quantitative data, preprocess the quantitative data and perform multivariate ordered logistic regression analysis on the processed data to obtain a logistic regression model, which is a risk assessment model for the pet delivery process; With risk level as the dependent variable and risk factors with p < 0.1 as the independent variable, a generalized linear model analysis was performed on the quantitative data to evaluate the quality of the regression model; Real-time collection of physiological indicators of pet delivery process to predict risk categories; when the risk assessment reaches the warning conditions, the warning module will issue an alarm message, while increasing the collection frequency of the collection module and updating the risk assessment in real time.

2. The smart pet delivery room according to claim 1, characterized in that: Risk-associated factors identified included pet breed, maternal postpartum blood loss, time interval between pups, maternal body temperature, maternal respiratory rate, and maternal heart rate.

3. The smart pet delivery room according to claim 2, characterized in that: The rules for assigning values ​​to risk-related factors are as follows: Enter pet breed information and classify it into normal group and special group. The normal group is assigned a value of 1 and the special group is assigned a value of 2. The amount of postpartum bleeding of the mother is assigned a value according to the interval. The amount of bleeding < 20% of the total blood volume of the mother is assigned a value of 1, 20% of the total blood volume of the mother ≤ the amount of bleeding ≤ 30% of the total blood volume of the mother is assigned a value of 2, and the amount of bleeding > 30% of the total blood volume of the mother is assigned a value of 3. The time interval between the births of two cubs is also assigned a value according to the interval: a time interval of less than 60 minutes is assigned a value of 1, a time interval of 60 minutes ≤ time interval ≤ 120 minutes is assigned a value of 2, and a time interval of more than 120 minutes is assigned a value of 3; Maternal body temperature is also assigned a value according to the interval: 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; Maternal respiratory rate was also assigned a value according to the interval: 15 times / minute ≤ maternal respiratory rate ≤ 35 times / minute was assigned a value of 1, maternal respiratory rate <15 times / minute was assigned a value of 2, and maternal respiratory rate >35 times / minute was assigned a value of 3; The maternal heart rate is also assigned a value according to the interval: 60 beats / minute ≤ maternal heart rate ≤ 100 beats / minute is assigned a value of 1, maternal heart rate < 60 beats / minute is assigned a value of 2, and maternal heart rate > 100 beats / minute is assigned a value of 3; The risk level is divided into 3 levels, with no risk being 0, moderate risk being 1, and severe risk being 2.

4. The smart pet delivery room according to claim 3, characterized in that: The process of preprocessing quantitative data includes: firstly, performing a chi-square test on all variables after assignment, and screening out all variables with probability values ​​p less than the set threshold; performing a multivariate ordered logistic regression analysis on the remaining variables to obtain a logistic regression model, and performing a parallel line test on the obtained regression equation.

5. The smart pet delivery room according to claim 4, characterized in that: The threshold value in the chi-square test was set to 0.

1.

6. The smart pet delivery room according to claim 1, characterized in that: The model evaluation indicators for evaluating the quality of the regression model are AIC and BIC.

7. The smart pet delivery room according to claim 1, characterized in that: Based on the statistical software SPSS, a multivariate ordered regression analysis was performed and the multivariate ordered logistic regression equation was obtained as follows: logit(p0)=8.782-3.191*a1+2.953*a2+3.152*a3+1.601*a5+2.002*a6; logit(p0+p1)=13.405-3.191*a1+2.953*a2+3.152*a3+1.601*a5+2.002*a6; Among them, a1 represents the pet breed, a2 represents the amount of postpartum bleeding of the mother, a3 represents the time interval between the birth of the pups, a5 represents the respiratory rate, a6 represents the mother's heart rate, P0 represents the probability of no risk, P1 represents the probability of moderate risk, and P3 represents the probability of severe risk.

8. The smart pet delivery room according to claim 7, characterized in that: Warning values ​​and alarm values ​​are set in the warning module. When P1>P0 and P1>P2, a warning is issued, and when P2>P0 and P2>P1, an alarm is issued. When the risk assessment reaches the warning conditions, an early warning message is issued, and when the risk assessment reaches the alarm conditions, an alarm message is issued.

Images