Method, device, storage medium and electronic device for determining livestock estrus

Abstract

This application discloses a method, device, storage medium, and electronic device for determining livestock estrus, comprising: obtaining a motion feature sequence of a livestock to be identified within a preset time interval, the motion feature sequence comprising motion features at different moments, each motion feature obtained by performing feature analysis on the motion data of the livestock to be identified at the corresponding moment; determining target motion features belonging to a preset feature category from the motion features at different moments; analyzing the quantitative distribution of the target motion features in the motion feature sequence to obtain motion reference parameters of the livestock to be identified; obtaining motion measurement parameters corresponding to the motion reference parameters, the motion measurement parameters being used to determine the estrus state of the livestock to be identified; and determining that the livestock to be identified is in estrus if the motion reference parameters are within the parameter range of the motion measurement parameters. This application can improve the accuracy of determining the estrus state of livestock.

Description

Technical Field

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

[0002] Improving livestock production can significantly boost the development of the animal husbandry industry. Accurately timing estrus is crucial for increasing livestock production. For example, for livestock like cows, sows, and hens, electronic devices can detect their movement data and determine if they are in estrus, allowing them to be bred when they are in estrus.

[0003] Existing technology determines whether livestock are in estrus by comparing and analyzing movement data with preset estrus data. Because movement data is greatly affected by interference factors, this analysis method has the disadvantage of large errors. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, storage medium, and electronic device for determining estrus in livestock, which can improve the accuracy of determining estrus in livestock.

[0005] In a first aspect, an embodiment of the present application provides a method for determining estrus in livestock, the method comprising:

[0006] Obtaining a motion feature sequence of the livestock to be identified within a preset time interval, the motion feature sequence including motion features at different moments, each motion feature being obtained by performing feature analysis on the motion data of the livestock to be identified at the corresponding moment;

[0007] Determining target motion features belonging to a preset feature category from motion features at different moments;

[0008] Analyze the quantitative distribution of target motion features in the motion feature sequence to obtain motion reference parameters of the livestock to be identified;

[0009] Obtaining a motion measurement parameter corresponding to the motion reference parameter, the motion measurement parameter being used to determine the estrus state of the livestock to be identified;

[0010] If the motion reference parameter is within the parameter range of the motion measurement parameter, it is determined that the livestock to be identified is in estrus.

[0011] In a second aspect, an embodiment of the present application further provides a device for determining livestock estrus, comprising:

[0012] A livestock data acquisition module is used to acquire a motion feature sequence of the livestock to be identified within a preset time interval. The motion feature sequence includes motion features at different moments, and each motion feature is obtained by performing feature analysis on the motion data of the livestock to be identified at the corresponding moment.

[0013] A feature identification module is used to determine the target motion features belonging to a preset feature category from the motion features at different times;

[0014] A reference parameter determination module is used to analyze the quantity distribution of the target motion characteristics in the motion characteristic sequence to obtain the motion reference parameters of the livestock to be identified;

[0015] a measurement parameter acquisition module, for acquiring movement measurement parameters corresponding to the movement reference parameters, the movement measurement parameters being used to determine the estrus state of the livestock to be identified;

[0016] The estrus determination module is used to determine that the livestock to be identified is in estrus if the movement reference parameter is within the parameter range of the movement measurement parameter.

[0017] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program runs on a computer, the computer executes a method for determining livestock estrus as provided in any embodiment of the present application.

[0018] In a fourth aspect, an embodiment of the present application further provides an electronic device comprising a processor and a memory, wherein the memory contains a computer program, and the processor calls the computer program to execute a method for determining livestock estrus as provided in any embodiment of the present application.

[0019] The technical solution provided by the embodiment of the present application performs motion feature analysis on the motion data of the livestock to be identified, and determines the target motion features belonging to the preset feature category from the various motion features obtained by the analysis. Based on the quantitative distribution of the target motion features in the motion feature sequence, the motion reference parameters of the livestock to be identified are determined, and then the motion reference parameters are compared with the motion measurement parameters to determine that the livestock to be identified is in estrus when the motion reference parameters are within the parameter range of the motion measurement parameters. Compared to the existing technology, the present application accurately obtains the motion reference parameters of the livestock to be identified by performing feature analysis on the motion data of the livestock to be identified, and then analyzes the motion reference parameters based on the motion measurement parameters to accurately determine whether the livestock to be identified is in estrus. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A schematic flow chart of a method for determining livestock estrus provided in an embodiment of the present application.

[0022] Figure 2 This is a schematic diagram of determining the estrus state of livestock to be identified based on the first reference component and the second reference component in the method provided in an embodiment of the present application.

[0023] Figure 3a This is a schematic diagram of the visualization results of the paired T test on livestock No. 1 in the method provided in the embodiment of the present application.

[0024] Figure 3b This is a schematic diagram of the visualization results of the paired T test on livestock number 2 in the method provided in the embodiment of the present application.

[0025] Figure 3c This is a schematic diagram of the visualization results of the paired T test on livestock number 3 in the method provided in the embodiment of the present application.

[0026] Figure 3d This is a schematic diagram of the visualization results of the paired T test on livestock No. 4 in the method provided in the embodiment of the present application.

[0027] Figure 4 This is a flow chart of determining motion measurement parameters in the method provided in an embodiment of the present application.

[0028] Figure 5 This is a schematic diagram of the structure of the device for determining estrus in livestock provided in an embodiment of the present application.

[0029] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0031] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The present invention provides a method for determining livestock estrus. The method can be performed by the livestock estrus determination device provided in the present invention, or an electronic device incorporating the livestock estrus determination device. The livestock estrus determination device can be implemented in hardware or software, and the electronic device can be a smartphone, tablet computer, desktop computer, or other device.

[0033] See also Figure 1 , Figure 1 This is a flow chart of the method for determining estrus in livestock provided in an embodiment of the present application. The specific flow of the method for determining estrus in livestock provided in an embodiment of the present application can be as follows:

[0034] 110. Obtain a motion feature sequence of the livestock to be identified within a preset time interval. The motion feature sequence includes motion features at different moments. Each motion feature is obtained by performing feature analysis on motion data of the livestock to be identified at a corresponding moment.

[0035] The livestock to be identified can be any livestock on a farm, such as a cow, sow, hen, etc. A farm may have only one type of livestock or at least two. Each livestock on the farm can carry a motion detection device to record its motion data in real time. This motion detection device can include at least one of various motion sensors, such as an accelerometer, a gyroscope, a heart rate sensor, an angular velocity sensor, etc. In addition, each livestock can also carry at least one of a temperature sensor, an infrared sensor, and a heart rate sensor to comprehensively analyze its motion and physiological conditions.

[0036] For example, the motion detection device can be integrated into an ear tag carried by livestock to record the livestock's motion data at every moment in real time. In this embodiment, the motion data can be motion acceleration, and the motion acceleration recorded at consecutive moments can be represented as time-series motion data.

[0037] The preset time interval can be set based on a sampling period, which can be a day, week, month, or the like. For example, 00:00-12:00 every day can be set as the preset time interval. Another example is 00:00-24:00 every day can be set as the preset time interval. Another example is 00:00-17:00 every day can be set as the preset time interval. Alternatively, the entire Monday can be set as the preset time interval. Since there are many possible implementation methods, they will not be listed here one by one.

[0038] For example, feature analysis can be performed on motion data at each moment in a preset time period to obtain motion features at each moment, and the motion features at each moment constitute a motion feature sequence for a preset time interval. Methods for feature analysis of motion data include, but are not limited to, classifying the motion data into corresponding motion features based on their numerical values, or extracting features from the motion data using a neural network model to obtain corresponding motion features.

[0039] 120. Determine target motion features belonging to a preset feature category from the motion features at different moments.

[0040] The motion features at different moments are arranged in chronological order into a motion feature sequence. For the motion features corresponding to different moments in the motion feature sequence, a target motion feature belonging to a preset feature category can be determined from the motion feature sequence. The preset feature category may indicate that the livestock to be identified has a large movement amplitude and a long movement duration.

[0041] Exemplarily, the motion features in the motion feature sequence may be classified into categories according to preset feature categories to obtain target motion features belonging to the preset feature categories and other motion features that do not belong to the preset feature categories.

[0042] 130. The quantitative distribution of the target motion features in the motion feature sequence is analyzed to obtain the motion reference parameters of the livestock to be identified.

[0043] There are multiple ways to analyze the distribution of quantities. For example, the number of target motion features in a motion feature sequence can be analyzed, and the motion reference parameter can be expressed as the number, or as the percentage of the number. Another example is analyzing the distribution of target motion features in a motion feature sequence, and the motion reference parameter can be expressed as the distribution, or as the distribution trend. The distribution can include concentrated distribution, sparse distribution, etc., and the distribution trend can include distribution tending to be concentrated, distribution tending to be sparse, etc.

[0044] 140. Obtain a motion measurement parameter corresponding to the motion reference parameter, where the motion measurement parameter is used to determine the estrus state of the livestock to be identified.

[0045] The motion measurement parameter may be a pre-set value. After obtaining the motion reference parameter, the motion reference parameter may be analyzed based on the motion measurement parameter. If the motion reference parameter is within the parameter range of the motion measurement parameter, it is determined that the livestock to be identified is in estrus. If the motion reference parameter is not within the parameter range of the motion measurement parameter, it is determined that the livestock to be identified is not in estrus.

[0046] If the motion reference parameter is within the parameter range of the motion measurement parameter, it is determined that the livestock to be identified is in estrus.

[0047] After determining that the livestock to be identified is in estrus, the livestock herder can be reminded through information prompts to promptly breed the livestock to increase livestock production. In addition, after determining that the livestock to be identified is not in estrus, the above steps can be continued until the livestock to be identified is determined to be in estrus.

[0048] For example, information prompts include, but are not limited to, controlling the ear tags carried by the livestock to be identified to flash or emit sounds, or sending text messages, voice prompts, notification messages, etc. to the livestock owner to remind the livestock to be identified that the livestock is in estrus, etc. Since there are many optional methods, they are not listed here one by one.

[0049] During specific implementation, the present application is not limited by the execution order of the various steps described. If no conflict occurs, some steps can be performed in other orders or simultaneously.

[0050] Through the livestock estrus determination method in the embodiment of the present application, it is possible to perform feature analysis on the time-series motion data of the livestock to be identified, and generate motion reference parameters related to the motion amount based on the motion characteristics, thereby accurately and intuitively describing the motion status of the livestock to be identified. When the motion reference parameters are within the parameter range of the motion measurement parameters, it is determined that the livestock to be identified is in estrus, thereby being able to timely and accurately analyze whether the livestock to be identified is in estrus, while reducing the amount of calculation and improving the accuracy of identifying the estrus status of the livestock.

[0051] The method described in the above embodiments will be further described in detail below with examples.

[0052] In some embodiments, the corresponding motion features can be obtained by performing feature analysis on the motion data at different times. For example, step 110 includes:

[0053] 111. Acquire time-series motion data of the livestock to be identified within a preset time interval, where the time-series motion data includes time-series sub-motion data in different preset directions.

[0054] The preset time interval is, for example, every half day (0:00-12:00), and the time series motion data is composed of motion data at each moment. Each motion data also includes sub-motion data in different preset directions, and the sub-motion data at different moments constitute the time series sub-motion data. For example, when the motion data is motion acceleration, the motion acceleration can also include three-axis sub-motion acceleration, and the three-axis sub-motion acceleration at different moments respectively constitute the time series sub-motion acceleration of different axes. Among them, the moment can refer to every 1 second, every 5 seconds, every 10 seconds, etc.

[0055] Among them, the movement data of the livestock to be identified can be expressed as D t , where t represents the moment, t∈T, T represents the preset time interval, and the temporal motion data of the livestock to be identified can be expressed as X∈(T, D).

[0056] 112. Perform vector synthesis on the time-series sub-motion data in each preset direction to obtain time-series vector data.

[0057] Among them, the motion data D at each moment t t They all include sub-motion data in each preset direction. For example, the acceleration of the three-axis sub-motion can be expressed as d tx , d ty , d tz The vector synthesis of the three sub-motion accelerations at time t can be expressed by the following formula:

[0058]

[0059] Among them, G t Indicates D t The time series vector data of the livestock to be identified can be expressed as (T, G).

[0060] 113. Perform mean aggregation processing on the time series vector data at a preset sampling rate to obtain a motion feature sequence.

[0061] In this embodiment, the preset sampling rate can be set to 5t, 10t, 15t, 20t, etc. For example, mean aggregation processing is performed on 10 vector data at every 10 time points t to obtain motion features corresponding to the 10 time points t, and the motion features corresponding to each 10t time point form a motion feature sequence in chronological order.

[0062] The method of performing mean aggregation processing on the time series vector data at a preset sampling rate is, for example, to first divide the time series vector data into multiple sets according to the preset sampling rate, each set including a corresponding number of vector data. For example, if the preset sampling rate is 10t, then a set contains 10 vector data. Then, the average value of all vector data in each set is used as the return value of the set to obtain the motion features corresponding to each set. The motion features corresponding to all sets form a motion feature sequence in chronological order.

[0063] For example, f represents the preset sampling rate, and by setting f, the preset time interval T is divided into M time periods, each time period is represented by m, M = T / f, and the set of vector data included in each time period is represented as {D i , D i+1 ...D i+f}, where D i Represents the i-th vector data, i=n*f+1, n=0,1...(M-1). For each set, the average value of the f vector data in the set is represented as the motion feature corresponding to the set, with M D Represents the motion characteristics, and the motion feature sequence of the livestock to be identified can be expressed as (M, M D ).

[0064] In this embodiment, by performing vector synthesis on the time-series sub-motion data in different preset directions, the time-series motion data of the livestock to be identified can be comprehensively represented by the time-series vector data, and then the time-series vector data is subjected to mean aggregation processing at a preset sampling rate, which can effectively avoid the disadvantage of missing motion data affecting the calculation results, thereby improving the accuracy of subsequent estrus status determination.

[0065] In some embodiments, step 120 includes:

[0066] 121. For each motion feature in the motion feature sequence, calculate the feature mean of the historical motion features within a preset time period before the motion feature.

[0067] For example, h represents the preset duration, for the mth j Motion feature M Dmj , j=1,2...M, the Mth Dmj The set of historical motion features within a preset time period before the motion feature is expressed as {M Dmj-h , M Dmj-h+ 1...M Dmj-1}, by taking the average value of h motion features in the set as the feature mean A of the set mj .

[0068] 122. If the motion feature is greater than the feature mean, the motion feature is determined as a target motion feature belonging to a preset feature category.

[0069] By putting M Dmj With A mj For comparison, if M Dmj >A mj , then M Dmj Determined as target motion feature. On the contrary, if M Dmj ≤A mj , then determine M Dmj Does not belong to the preset feature category. The preset feature category indicates that the current motion feature is showing an increasing trend compared to the historical motion feature.

[0070] Among them, when obtaining the motion reference parameters of the livestock to be identified, it is also possible to perform a multi-dimensional analysis of the target motion characteristics to obtain multi-dimensional motion reference parameters, wherein the motion reference parameters can also include at least two motion components, which can be respectively expressed as a first motion reference component and a second motion reference component. Accordingly, when using the motion measurement parameters to analyze the motion reference parameters, it is also possible to obtain a first motion measurement component corresponding to the first motion reference component and a second motion measurement component corresponding to the second motion reference component, that is, the motion measurement parameters include the first motion measurement component and the second motion measurement component. In the following embodiment, a scheme for determining whether the livestock to be identified is in estrus based on the first motion reference component and the second motion reference component is described.

[0071] In some embodiments, step 130 includes:

[0072] 131. Assign a first feature identifier to the target motion feature, and assign a second feature identifier to the motion features other than the target motion feature in the motion feature sequence, to obtain a feature identifier sequence.

[0073] For example, a feature identifier is assigned to each motion feature in the motion feature sequence. Specifically, a first feature identifier can be assigned to target motion features in the motion feature sequence that belong to a preset feature category, and a second feature identifier can be assigned to motion features in the motion feature sequence that do not belong to the preset feature category. The feature identifiers corresponding to each motion feature are sorted in chronological order to obtain a feature identifier sequence, and the feature identifier sequence only includes two types of feature identifiers, namely, the first feature identifier and the second feature identifier.

[0074] The first feature identifier and the second feature identifier may also be represented by binary numerical values, for example, "1" is used to represent the first feature identifier, and "0" is used to represent the second feature identifier, and the total number of "1" and "0" is M.

[0075] Combined with the above step 122, the feature identification sequence is represented by the following table 1, Table 1:

[0076]

[0077]

[0078] Table 1 only captures the motion features corresponding to the first 10 time periods in the motion feature sequence, and the duration of each time period m is 10s, t represents the time, A b Indicates a feature identifier.

[0079] 132. Determine a first motion reference component of the livestock to be identified based on a quantitative proportion of the first characteristic identifier in the characteristic identifier sequence.

[0080] The number of first feature identifiers can be counted, and the relationship between the number of first feature identifiers and the number of feature identifiers in the feature identifier sequence can be analyzed to represent the first motion reference component. For example, the ratio of the number of first feature identifiers to the number of all feature identifiers can be used as the first motion reference component. The feature identifier sequence can also be segmented to obtain the proportion of the number of first feature identifiers in each segment to the number of all feature identifiers in that segment. Since there are many optional methods, they are not listed here one by one.

[0081] 133. Determine a second motion reference component of the livestock to be identified based on the number of first feature identifiers continuously distributed in the feature identifier sequence.

[0082] For example, the number of consecutive occurrences of the first feature identifier in the feature identifier sequence can be counted. That is, a sequence segment in which at least two first feature identifiers appear consecutively can be intercepted, and the number of first feature identifiers in the sequence segment can be counted, thereby determining the second motion reference component based on the number of identifiers of the first feature identifier in each sequence segment. When there are at least two sequence segments, one can also be selected from the number of identifiers corresponding to each sequence segment as the second motion reference component. Methods for selecting the second motion reference component include, but are not limited to, selecting the maximum value, selecting the median value, selecting the average value, etc. In this embodiment, the maximum value selected from the number of identifiers corresponding to each sequence segment is used as the second motion reference component.

[0083] As described above, step 140 includes:

[0084] A first motion measurement component corresponding to the first motion reference component is obtained, and a second motion measurement component corresponding to the second motion reference component is obtained.

[0085] As above, step 150 includes:

[0086] If the first motion reference component is within the component range of the first motion measurement component, or the second motion reference component is within the component range of the second motion measurement component, it is determined that the livestock to be identified is in estrus.

[0087] The first motion measurement component and the second motion measurement component may indicate a parameter range and may also indicate a maximum value of the parameter.

[0088] In this embodiment, on the one hand, the first motion reference component is analyzed based on the first motion measurement component to determine whether the first motion reference component is within the component range of the first motion measurement component. If so, the livestock to be identified is determined to be in estrus. If not, the livestock to be identified may be determined not to be in estrus, or other methods may be combined to continue determining the estrus status of the livestock to be identified. On the other hand, the second motion reference component is also analyzed based on the second motion measurement component to determine whether the second motion reference component is within the component range of the second motion measurement component. If so, the livestock to be identified is determined to be in estrus. If not, the livestock to be identified may be determined not to be in estrus, or other methods may be combined to continue determining the estrus status of the livestock to be identified.

[0089] Other methods include capturing images of the livestock to be identified using a camera, and then determining whether the livestock exhibits target behaviors consistent with estrus. If not, the livestock is determined to be not in estrus. Another example is capturing the body temperature of the livestock to be identified using a temperature sensor. If the body temperature does not exceed a preset temperature threshold for a preset period of time, the livestock is determined to be not in estrus.

[0090] See also Figure 2 , Figure 2 A schematic diagram of determining the estrus state of livestock to be identified based on the first reference component and the second reference component in the method provided in an embodiment of the present application. Particularly, by analyzing the quantitative distribution of the first feature identifier in the feature identifier sequence from two aspects, on the one hand, the quantitative proportion of the first feature identifier in the feature identifier sequence is analyzed to obtain the first motion reference component. On the other hand, the number of continuously distributed first feature identifiers is analyzed to obtain the second motion reference component. Two judgment conditions are then set, namely, condition 1: determining whether the first motion reference component is within the component range of the first motion measurement component, and condition 2: determining whether the second motion reference component is within the component range of the second motion measurement component. If the result of satisfying one of the two conditions is "yes", it is determined that the livestock to be identified is in estrus.

[0091] In some embodiments, the first motion reference component may be obtained by segmenting the feature identification sequence. Specifically, the preset time interval includes at least two time units. Step 132 includes:

[0092] 1321. Determine a sub-identification sequence corresponding to each time unit from the feature identification sequence.

[0093] The time unit is represented by r, r>m, and is an integer multiple of m. For example, taking one hour as the time unit, r=1 is the first time period, which can indicate the time period of 00:00-01:00. The first feature identifier and / or the second feature identifier included in the time period constitute a sub-identifier sequence. The sub-identifier sequence is represented by a b , A b ∈(r,a b ), each sub-identifier sequence a b It includes r feature identifiers.

[0094] 1322. Determine the proportion of the first characteristic identifiers in each sub-identifier sequence as the unit motion amount of each sub-identifier sequence.

[0095] The unit motion is represented by p, and the unit motion is represented by c r Indicates the number of the first feature identifier in the sub-identifier sequence. For the sub-identifier sequence a corresponding to the e-th time unit be The corresponding unit motion is expressed as p e =c re / r,e=1,2...r.

[0096] 1323. Obtain at least one of the standard deviation of multiple unit motion amounts, the maximum fluctuation rate among the fluctuation rates of the multiple unit motion amounts, and the standard deviation of the multiple fluctuation rates as a first motion reference component of the livestock to be identified.

[0097] The standard deviation of r unit motion is calculated by the following formula (1):

[0098]

[0099] Where x represents the average value of r unit motion quantities p.

[0100] Exemplarily, obtaining the fluctuation rate of each unit of motion includes:

[0101] For each unit motion amount, the maximum historical motion amount is determined from the historical unit motion amounts preceding the unit motion amount;

[0102] Calculate the absolute value of the difference between the unit motion and the maximum historical motion;

[0103] The ratio of the absolute value of the difference to the unit motion is determined as the fluctuation rate of the unit motion.

[0104] The volatility V of the e-th unit motion is calculated by the following formula (2):e :

[0105]

[0106] Among them, the historical unit movement before the e-th unit movement is composed of the set max{p1, p1…p e-1} means that by selecting the maximum value from this set, e Calculate the e-th volatility Ve.

[0107] Afterwards, the maximum fluctuation rate may be selected from the fluctuation rates V of the r unit motion quantities as the first motion reference component.

[0108] The standard deviation of r volatility V is calculated by the following formula (3):

[0109]

[0110] Where y represents the average of r volatility V.

[0111] In some embodiments, the preset time interval may be segmented according to the above-mentioned time units to obtain the second reference component. Step 133 includes:

[0112] 1331. Determine a sub-identification sequence corresponding to each time unit from the feature identification sequence.

[0113] 1332. Determine the maximum number of first characteristic identifiers that are continuously distributed in each sub-identifier sequence.

[0114] By counting each sub-identification sequence a b The number of first feature identifiers c in the continuous distribution k , to select from at least one c k Determine the maximum value M k , M k =max{c k It is understandable that each sub-identifier sequence may have a continuously distributed first feature identifier or may not have a continuously distributed first feature identifier. By counting the number of first feature identifiers in each continuously distributed segment, the largest number is selected as the maximum number corresponding to the sub-identifier sequence. For example, for the sub-identifier sequence a corresponding to the e-th time unit, be For example, if the first feature identifier of the corresponding continuous distribution has three segments with the number of 3, 5, and 2 respectively, then the largest number of 5 is selected from the three segments as the sub-identifier sequence a be The corresponding maximum number M ke .

[0115] 1333. Obtain at least one of a standard deviation of a plurality of maximum values, a maximum fluctuation rate among fluctuation rates of a plurality of maximum values, and a standard deviation of a plurality of fluctuation rates as a second motion reference component of the livestock to be identified.

[0116] The standard deviation of the r maximum values is calculated using the following formula (4):

[0117]

[0118] Among them, z represents the maximum value of r numbers M k The average value of .

[0119] Exemplarily, obtaining the volatility of each maximum quantity includes:

[0120] For each maximum quantity, determine the maximum historical maximum quantity from the historical maximum quantities before the maximum quantity;

[0121] Calculate the absolute value of the difference between the maximum quantity and the maximum historical quantity;

[0122] The ratio of the absolute value of the difference to the maximum quantity is determined as the volatility of the maximum quantity.

[0123] The volatility Q of the maximum value of the e-th quantity is calculated by the following formula (5): e :

[0124]

[0125] Among them, the historical maximum value before the maximum value of the e-th quantity is represented by the set max{M k1 , M k2 …M ke-1} means that by selecting the maximum value from this set, ke Calculate the e-th volatility Q e .

[0126] Afterwards, the maximum fluctuation rate may be selected from the fluctuation rates Q of the r unit motion quantities as the first motion reference component.

[0127] The standard deviation of r volatility Q is calculated by the following formula (6):

[0128]

[0129] Where s represents the average of r volatility Q.

[0130] A paired T-test (also known as a dependent or dependent T-test) is a statistical test that compares the means / averages and standard deviations of two related groups to determine whether there is a significant difference between the two groups. A significant difference occurs when the difference between the groups is unlikely to be due to sampling error or chance; the groups may be related by being the same group of people, the same project, or being affected by the same conditions. In this embodiment, the difference between the first motion reference component and the second motion reference component is also tested using a paired T-test, as follows:

[0131] Python is an interpreted, object-oriented, high-level programming language with dynamic data types. In the embodiment of the present application, the first motion reference parameters and the second motion reference parameters of multiple livestock in the farm are also used to perform a paired T test. The multiple livestock include the livestock to be identified as described above. Specifically, the levene function and the ttest_ind function in Python can be used to perform a paired T test on the unit motion amount of each livestock and the fluctuation rate of each unit motion amount, as well as the maximum number of each livestock and the fluctuation rate of each maximum number. Taking the preset time interval of 00:00 to 17:00 as an example, the data of the paired T test are provided in Table 2 below.

[0132] Table 2:

[0133]

[0134]

[0135] Paired T-test results show that the significance of different movement reference parameters varies across livestock, but the fluctuation rate of unit movement volume and the fluctuation rate of maximum movement volume are the two most significant characteristics. Therefore, using T-test results or a single movement characteristic as a criterion for estrus is not sufficient. It is necessary to consider the distribution of different characteristics and use multiple characteristics to complement each other.

[0136] In addition, the T-test results of livestock can be visualized using Tableau (a data analysis and visualization tool) to observe whether the livestock's movement on the day of estrus differs from that at other times in absolute values or continuity. Please refer to the schematic diagram of the visualization results of the paired T-test of livestock in the method provided in the Examples of this application.

[0137] Among them, the visualization result of livestock number 1 is as follows Figure 3a shown.

[0138] The horizontal axis of the graph represents time, showing data for five days from February 8, 2023 to February 12, 2023, where February 12, 2023 is the day the livestock are in estrus. The vertical axis represents the unit movement (p) and the fluctuation rate of each unit movement (V e ), and the maximum number (M k ) and the volatility of the maximum value of each quantity (Q e ).

[0139] The visualization result of livestock number 4 is as follows Figure 3b The figure shows data for six days, from February 28, 2023, to February 13, 2023, with February 12, 2023, being the day the livestock were in estrus.

[0140] The visualization result of livestock number 5 is as follows Figure 3c The figure shows data for five days, from 2023.28 to 2023.2.12, where 2023.2.12 is the day when livestock are in estrus.

[0141] The visualization result of livestock number 6 is as follows Figure 3d The figure shows data for six days, from February 28, 2023, to February 13, 2023, with February 12, 2023, being the day the livestock were in estrus.

[0142] It can be seen from the visualization results that the movement state of livestock on the day of estrus is significantly different from that at other times, but the degree of significance of different characteristics varies among different livestock. First, the overall trend of the unit movement curve of livestock on the day of estrus is flatter, and the volatility is lower than at other times, but the overall value is higher, which means that the movement state of livestock lasts longer, showing a long period of restlessness. Secondly, the maximum number of livestock on the day of estrus is lower than at other times, the volatility is lower, the overall value is more concentrated, and the peak is not obvious; while the continuous movement on other days shows more obvious stage fluctuations over time, and the absolute value is also higher, with the peak usually occurring at 10-12 o'clock in the morning. Based on the conclusions of the visualization, this application determines the estrus state of livestock from two aspects: continuity and absolute value. Therefore, the absolute values of the unit movement volume and the maximum number are further statistically analyzed to determine the corresponding movement measurement parameters.

[0143] In the following embodiments, the focus is on describing how to determine the motion measurement parameters. The details are as follows.

[0144] See also Figure 4 , Figure 4 This is a flow chart of determining motion measurement parameters in the method provided in an embodiment of the present application. Before obtaining the motion measurement parameters corresponding to the motion reference parameters, the method further includes:

[0145] 210. Obtain multiple sample standard deviations of each sample livestock within a preset time interval of different sampling periods, where the sample standard deviation is the standard deviation of multiple unit sample exercise amounts within the preset time interval.

[0146] The sample livestock may be a plurality of livestock in a farm. For each sample livestock, the method mentioned in the above embodiment can be used to obtain the unit exercise volume of each sample livestock, also referred to as the unit sample exercise volume. The standard deviation of the multiple unit sample exercise volumes can also be obtained using the formula mentioned above. The preset time interval is consistent with the preset time interval mentioned above. For example, when the preset time interval indicates 0.00-17:00, the sampling period can be measured in days, weeks, or months, such as obtaining the standard deviation of the unit sample exercise volume corresponding to all time units between 0.00-17:00 for each livestock every day.

[0147] 220. Determine target livestock in estrus from the sample livestock, and determine estrus time intervals from preset time intervals corresponding to different sampling periods of the target livestock.

[0148] The standard deviation of each livestock in different sampling periods constitutes a standard deviation set, and one standard deviation in the set corresponds to one sampling period, which is expressed as {σ d11 , σ d21 ...σ dn1 For example, different sampling periods can indicate 6 from 2023.2.8 to 2023.2.13. If a certain sample livestock is in estrus on 2023.2.13, 2023.2.13 can be regarded as the estrus time interval, while 2023.2.8 to 2023.2.12 does not belong to the estrus time interval.

[0149] 230. Determine a candidate time interval that is not an estrus time interval from a plurality of preset time intervals corresponding to each sample livestock.

[0150] After identifying target livestock in estrus from a plurality of sample livestock, the estrus time interval of each target livestock can also be determined. It is understood that the preset time interval corresponding to the date of estrus for each target livestock is referred to as the estrus time interval, while the preset time intervals corresponding to other dates can be referred to as candidate time intervals.

[0151] 240. Determine the maximum sample standard deviation from the sample standard deviations corresponding to the estrus time interval.

[0152] Among them, the standard deviations corresponding to the estrus time intervals of all target livestock are combined into an estrus standard deviation set, and then the maximum value of the standard deviation is screened out from the estrus standard deviation set, which is called the maximum sample standard deviation.

[0153] 250. If the sample standard deviations corresponding to the candidate time intervals are all greater than the maximum sample standard deviation, the maximum sample standard deviation is determined as the upper limit of the motion measurement parameter.

[0154] In addition, the standard deviations corresponding to the candidate time intervals of all sample livestock can also be combined into a non-estrus standard deviation set. It can be understood that for sample livestock that do not belong to the target livestock, the preset time intervals corresponding to all their sampling periods are called candidate time intervals.

[0155] The maximum value from the set of non-estrus standard deviations is selected as a threshold value for comparison with the maximum sample standard deviation. If the threshold value is greater than the maximum sample standard deviation, the maximum sample standard deviation is used as the upper limit of the exercise measurement parameter. Specifically, it can be used as the first upper limit of the standard deviation of multiple unit exercise amounts included in the first exercise measurement parameter.

[0156] It is understandable that there may be at least two preset time intervals corresponding to different sampling periods, for example, one preset time interval is 0:00-12:00 and the other preset time interval is 0:00-17:00. The motion measurement parameter includes a first motion measurement component and a second motion measurement component. The first motion measurement component includes a first upper limit value corresponding to the standard deviation of multiple unit motion quantities, a second upper limit value corresponding to the maximum volatility among the volatility of the multiple unit motion quantities, and a third upper limit value corresponding to the standard deviation of the volatility of the multiple unit motion quantities. The second motion measurement component includes a fourth upper limit value corresponding to the standard deviation of the multiple maximum values, a fifth upper limit value corresponding to the maximum volatility among the volatility of the multiple maximum values, and a sixth upper limit value corresponding to the standard deviation of the volatility of the multiple maximum values.

[0157] The method of obtaining the first upper limit value, the second upper limit value, the third upper limit value, the fourth upper limit value and the fifth upper limit value can refer to the above steps 210-250, which will not be repeated here.

[0158] Table 3 below also provides examples of different preset time intervals and upper limit values.

[0159] Table 3:

[0160]

[0161] In some embodiments, before obtaining the motion feature sequence of the livestock to be identified within a preset time interval, the method further includes:

[0162] Determine the motion measurement parameters corresponding to the motion reference parameters in different preset time intervals;

[0163] Obtaining a sequence of motion features of the livestock to be identified within a preset time interval, including:

[0164] For a preset time interval that reaches a cutoff moment, a motion feature sequence of the livestock to be identified within the preset time interval is obtained.

[0165] As described above, there can be multiple preset time intervals. If there are multiple preset time intervals, the estrus state of the livestock to be identified can be determined based on the motion reference parameters within the preset time interval at each preset time interval. For example, when the current time reaches 12:00, the motion feature sequence of the livestock to be identified within the preset time interval (0:00-12:00) is obtained, and then the standard deviation of multiple unit motion quantities, the maximum fluctuation rate among the fluctuation rates of multiple unit motion quantities, and the standard deviation of multiple fluctuation rates are obtained based on the motion feature sequence. At least one of the standard deviation of multiple maximum values, the maximum fluctuation rate among the fluctuation rates of multiple maximum values, and the standard deviation of multiple fluctuation rates is obtained as the second motion reference component of the livestock to be identified.

[0166] Then, the standard deviation of the multiple unit exercise amounts is compared with a first upper limit value corresponding to the preset time interval (0:00-12:00), the maximum fluctuation rate among the fluctuation rates of the multiple unit exercise amounts is compared with a second upper limit value corresponding to the preset time interval (0:00-12:00), and the standard deviation of the fluctuation rates of the multiple unit exercise amounts is compared with a third upper limit value corresponding to the preset time interval (0:00-12:00). If each standard deviation or maximum fluctuation rate is less than the corresponding first upper limit value, second upper limit value, and third upper limit value, it is determined that the livestock to be identified was in estrus between 0:00 and 12:00 on the same day. For example, if the standard deviation of the multiple unit exercise amounts is less than 0.14, the maximum fluctuation rate among the fluctuation rates of the multiple unit exercise amounts is less than 2.2, and the standard deviation of the fluctuation rates of the multiple unit exercise amounts is less than 0.62, then the livestock to be identified is determined to be in estrus between 0:00 and 12:00 on the same day.

[0167] In addition, the standard deviation of the plurality of maximum quantity values may be compared with a fourth upper limit value corresponding to the preset time interval (0:00-12:00), the maximum fluctuation rate among the fluctuation rates of the plurality of maximum quantity values may be compared with a fifth upper limit value corresponding to the preset time interval (0:00-12:00), and the standard deviation of the fluctuation rates of the plurality of maximum quantity values may be compared with a sixth upper limit value corresponding to the preset time interval (0:00-12:00). If each standard deviation or maximum fluctuation rate value is less than the corresponding fourth, fifth, and sixth upper limits, it is determined that the livestock to be identified was in estrus between 0:00 and 12:00 on the same day. For example, if the standard deviation of the plurality of maximum quantity values is less than 2.9, the maximum fluctuation rate among the fluctuation rates of the plurality of maximum quantity values is less than 2, and the standard deviation of the fluctuation rates of the plurality of maximum quantity values is less than 0.79, it is determined that the livestock to be identified was in estrus between 0:00 and 12:00 on the same day.

[0168] For example, when the current time reaches 17:00, a motion feature sequence of the livestock to be identified within a preset time interval (0:00-17:00) is obtained, and then, based on the motion feature sequence, at least one of the standard deviation of multiple unit motion quantities, the maximum fluctuation rate among the fluctuation rates of the multiple unit motion quantities, and the standard deviation of the multiple fluctuation rates is obtained. Furthermore, at least one of the standard deviation of multiple maximum values, the maximum fluctuation rate among the fluctuation rates of the multiple maximum values, and the standard deviation of the multiple fluctuation rates is obtained as the second motion reference component of the livestock to be identified.

[0169] Then, the standard deviation of the multiple unit exercise amounts is compared with a first upper limit value corresponding to the preset time interval (0:00-17:00), the maximum fluctuation rate among the fluctuation rates of the multiple unit exercise amounts is compared with a second upper limit value corresponding to the preset time interval (0:00-17:00), and the standard deviation of the fluctuation rates of the multiple unit exercise amounts is compared with a third upper limit value corresponding to the preset time interval (0:00-17:00). If each standard deviation or maximum fluctuation rate is less than the corresponding first upper limit value, second upper limit value, and third upper limit value, it is determined that the livestock to be identified was in estrus between 0:00 and 17:00 on the same day. For example, if the standard deviation of the multiple unit exercise amounts is less than 0.12, the maximum fluctuation rate among the fluctuation rates of the multiple unit exercise amounts is less than 2.2, and the standard deviation of the fluctuation rates of the multiple unit exercise amounts is less than 0.52, then the livestock to be identified is determined to be in estrus between 0:00 and 17:00 on the same day.

[0170] In addition, the standard deviation of the plurality of maximum quantity values may be compared with a fourth upper limit value corresponding to the preset time interval (0:00-17:00), the maximum fluctuation rate among the fluctuation rates of the plurality of maximum quantity values may be compared with a fifth upper limit value corresponding to the preset time interval (0:00-17:00), and the standard deviation of the fluctuation rates of the plurality of maximum quantity values may be compared with a sixth upper limit value corresponding to the preset time interval (0:00-17:00). If each standard deviation or maximum fluctuation rate value is less than the corresponding fourth, fifth, and sixth upper limits, it is determined that the livestock to be identified was in estrus between 0:00 and 17:00 on the same day. For example, if the standard deviation of the plurality of maximum quantity values is less than 3.4, the maximum fluctuation rate among the fluctuation rates of the plurality of maximum quantity values is less than 2, and the standard deviation of the fluctuation rates of the plurality of maximum quantity values is less than 0.82, it is determined that the livestock to be identified was in estrus between 0:00 and 17:00 on the same day.

[0171] It is understandable that the preset time interval can also be selected according to actual needs, and the corresponding motion measurement parameters are updated according to the changes in the preset time interval. The specific implementation method is as described above and will not be repeated here.

[0172] As can be seen from the above, the livestock estrus determination method proposed in the embodiments of the present invention can significantly improve the reproductive rate and quality of livestock on farms, and can effectively improve the inaccuracy and inefficiency caused by traditional methods. In addition, the required equipment is simple, which also reduces breeding costs.

[0173] In one embodiment, a device for determining whether livestock is in estrus is also provided. Figure 5 , Figure 5 This is a schematic diagram of the structure of a livestock estrus determination device 300 provided in an embodiment of the present application. The livestock estrus determination device 300 is applied to an electronic device and includes the following:

[0174] The livestock data acquisition module 301 is used to obtain a motion feature sequence of the livestock to be identified within a preset time interval. The motion feature sequence includes motion features at different moments. Each motion feature is obtained by performing feature analysis on the motion data of the livestock to be identified at the corresponding moment.

[0175] A feature identification module 302 is used to determine target motion features belonging to a preset feature category from motion features at different moments;

[0176] The reference parameter determination module 303 is used to analyze the quantity distribution of the target motion features in the motion feature sequence to obtain the motion reference parameters of the livestock to be identified;

[0177] A measurement parameter acquisition module 304 is used to obtain a motion measurement parameter corresponding to the motion reference parameter, the motion measurement parameter being used to determine the estrus state of the livestock to be identified;

[0178] The estrus determination module 305 is configured to determine that the livestock to be identified is in estrus if the motion reference parameter is within the parameter range of the motion measurement parameter.

[0179] In some embodiments, the motion reference parameter includes a first motion reference component and a second motion reference component, and the motion metric parameter includes a first motion metric component corresponding to the first motion reference component, and a second motion metric component corresponding to the second motion reference component;

[0180] The reference parameter determination module 303 is further configured to:

[0181] Assigning a first feature identifier to the target motion feature, and assigning a second feature identifier to the motion features other than the target motion feature in the motion feature sequence, to obtain a feature identifier sequence;

[0182] determining a first motion reference component of the livestock to be identified according to a proportion of the first characteristic identifier in the characteristic identifier sequence;

[0183] determining a second motion reference component of the livestock to be identified based on the number of first feature identifiers distributed continuously in the feature identifier sequence;

[0184] The estrus determination module 305 is further used for:

[0185] If the first motion reference component is within the component range of the first motion measurement component, or the second motion reference component is within the component range of the second motion measurement component, it is determined that the livestock to be identified is in estrus.

[0186] In some embodiments, the preset time interval includes at least two time units;

[0187] The reference parameter determination module 303 is further configured to:

[0188] Determine a sub-identification sequence corresponding to each time unit from the feature identification sequence;

[0189] The proportion of the first characteristic identifier in each sub-identifier sequence is determined as the unit motion amount of each sub-identifier sequence;

[0190] At least one of the standard deviation of the plurality of unit motion amounts, the maximum fluctuation rate among the fluctuation rates of the plurality of unit motion amounts, and the standard deviation of the plurality of fluctuation rates is obtained as a first motion reference component of the livestock to be identified.

[0191] In some embodiments, the reference parameter determination module 303 is further configured to:

[0192] For each unit motion amount, the maximum historical motion amount is determined from the historical unit motion amounts preceding the unit motion amount;

[0193] Calculate the absolute value of the difference between the unit motion and the maximum historical motion;

[0194] The ratio of the absolute value of the difference to the unit motion is determined as the fluctuation rate of the unit motion.

[0195] In some embodiments, the livestock estrus determination device 300 further includes a measurement parameter determination module, if the first motion reference component includes a standard deviation of a plurality of unit motion quantities;

[0196] Before obtaining the motion measurement parameters corresponding to the motion reference parameters, the measurement parameter determination module is used to:

[0197] Obtaining multiple sample standard deviations of each sample livestock within a preset time interval of different sampling periods, where the sample standard deviation is the standard deviation of the movement amount of multiple unit samples within the preset time interval;

[0198] Determining target livestock in estrus from among the sample livestock, and determining estrus time intervals from preset time intervals corresponding to different sampling periods of the target livestock;

[0199] Determining a candidate time interval that is not an estrus time interval from a plurality of preset time intervals corresponding to each sample livestock;

[0200] Determine the maximum sample standard deviation from the sample standard deviations corresponding to the estrus time interval;

[0201] If the sample standard deviations corresponding to the candidate time intervals are all greater than the maximum sample standard deviation, the maximum sample standard deviation is determined as the upper limit of the motion measurement parameter.

[0202] In some embodiments, the preset time interval includes at least two time units; the reference parameter determination module 303 is further configured to:

[0203] Determine a sub-identification sequence corresponding to each time unit from the feature identification sequence;

[0204] Determine the maximum number of first characteristic identifiers distributed continuously in each sub-identifier sequence;

[0205] At least one of a standard deviation of a plurality of maximum values, a maximum fluctuation rate among fluctuation rates of the plurality of maximum values, and a standard deviation of a plurality of fluctuation rates is obtained as a second motion reference component of the livestock to be identified.

[0206] In some embodiments, the feature identification module 302 is further configured to:

[0207] For each motion feature in the motion feature sequence, the feature mean of the historical motion features within a preset time period before the motion feature is obtained;

[0208] If the motion feature is greater than the feature mean, the motion feature is determined as a target motion feature belonging to a preset feature category.

[0209] In some embodiments, the livestock data acquisition module 301 is further configured to:

[0210] Acquiring time-series motion data of the livestock to be identified within a preset time interval, the time-series motion data including time-series sub-motion data in different preset directions;

[0211] Performing vector synthesis on the time-series sub-motion data in each preset direction to obtain time-series vector data;

[0212] The time series vector data is averaged and aggregated at a preset sampling rate to obtain a motion feature sequence.

[0213] In some embodiments, before obtaining the motion feature sequence of the livestock to be identified within a preset time interval, the livestock data acquisition module 301 is further configured to:

[0214] Determine the motion measurement parameters corresponding to the motion reference parameters in different preset time intervals;

[0215] For a preset time interval that reaches a cutoff moment, a motion feature sequence of the livestock to be identified within the preset time interval is obtained.

[0216] It should be noted that the livestock estrus determination device 300 provided in the embodiment of the present application and the livestock estrus determination method in the above embodiment belong to the same concept. Any method provided in the livestock estrus determination method embodiment can be implemented through the livestock estrus determination device 300. The specific implementation process is detailed in the livestock estrus determination method embodiment, which will not be repeated here.

[0217] The present application also provides an electronic device, which may be a smart phone, tablet computer, desktop computer, etc. Figure 6 As shown, Figure 6 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 400 includes a processor 401 having one or more processing cores, a memory 402 having one or more computer-readable storage media, and a computer program stored in the memory 402 and executable on the processor. The processor 401 is electrically connected to the memory 402. It will be understood by those skilled in the art that the electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0218] The processor 401 is the control center of the electronic device 400. It uses various interfaces and lines to connect various parts of the entire electronic device 400. By running or loading software programs and / or modules stored in the memory 402 and calling data stored in the memory 402, it executes various functions of the electronic device 400 and processes data, thereby monitoring the electronic device 400 as a whole.

[0219] In the embodiment of the present application, the processor 401 in the electronic device 400 loads instructions corresponding to one or more application processes into the memory 402 according to the following steps, and the processor 401 runs the application stored in the memory 402 to implement various functions:

[0220] Obtaining a motion feature sequence of the livestock to be identified within a preset time interval, the motion feature sequence including motion features at different moments, each motion feature being obtained by performing feature analysis on the motion data of the livestock to be identified at the corresponding moment;

[0221] Determining target motion features belonging to a preset feature category from motion features at different moments;

[0222] Analyze the quantitative distribution of target motion features in the motion feature sequence to obtain motion reference parameters of the livestock to be identified;

[0223] Obtaining a motion measurement parameter corresponding to the motion reference parameter, the motion measurement parameter being used to determine the estrus state of the livestock to be identified;

[0224] If the motion reference parameter is within the parameter range of the motion measurement parameter, it is determined that the livestock to be identified is in estrus.

[0225] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0226] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0227] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0228] To this end, the embodiments of the present application provide a computer-readable storage medium. Persons skilled in the art will appreciate that all or part of the steps in the above-described embodiment methods can be implemented by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. When executed, the program includes the following steps:

[0229] Obtaining a motion feature sequence of the livestock to be identified within a preset time interval, the motion feature sequence including motion features at different moments, each motion feature being obtained by performing feature analysis on the motion data of the livestock to be identified at the corresponding moment;

[0230] Determining target motion features belonging to a preset feature category from motion features at different moments;

[0231] Analyze the quantitative distribution of target motion features in the motion feature sequence to obtain motion reference parameters of the livestock to be identified;

[0232] Obtaining a motion measurement parameter corresponding to the motion reference parameter, the motion measurement parameter being used to determine the estrus state of the livestock to be identified;

[0233] If the motion reference parameter is within the parameter range of the motion measurement parameter, it is determined that the livestock to be identified is in estrus.

[0234] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0235] The aforementioned storage medium may be ROM / RAM, a magnetic disk, an optical disk, or the like. Since the computer program stored in the storage medium can execute the steps of any of the methods for determining livestock estrus provided in the embodiments of the present application, the beneficial effects achievable by any of the methods for determining livestock estrus provided in the embodiments of the present application can be achieved. For details, please refer to the previous embodiments and will not be repeated here.

[0236] The above is a detailed introduction to a method, device, storage medium and electronic device for determining estrus in livestock provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core ideas of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A method for determining estrus in livestock, characterized in that: The method comprises: Obtaining a motion feature sequence of a to-be-identified livestock within a preset time interval includes: obtaining time-series motion data of the to-be-identified livestock within the preset time interval, the time-series motion data including time-series sub-motion data in different preset directions; performing vector synthesis on the time-series sub-motion data in each preset direction to obtain time-series vector data; performing mean aggregation processing on the time-series vector data at a preset sampling rate to obtain the motion feature sequence; the motion feature sequence includes motion features at different moments, each motion feature being obtained by performing feature analysis on the motion data of the to-be-identified livestock at a corresponding moment; wherein the preset time interval includes time units; Determining a target motion feature belonging to a preset feature category from the motion features at different moments, including: for each motion feature in the motion feature sequence, calculating a feature mean of historical motion features within a preset time period before the motion feature; if the motion feature is greater than the feature mean, determining the motion feature as a target motion feature belonging to the preset feature category; Analyzing the quantitative distribution of the target motion features in the motion feature sequence to obtain motion reference parameters of the livestock to be identified, including: assigning a first feature identifier to the target motion feature, and assigning a second feature identifier to motion features other than the target motion feature in the motion feature sequence to obtain a feature identifier sequence; determining a sub-identification sequence corresponding to each of the time units from the feature identifier sequence; determining the quantitative proportion of the first feature identifier in each of the sub-identification sequences as the unit motion amount of each of the sub-identification sequences; obtaining at least one of a standard deviation of a plurality of the unit motion amounts, a maximum volatility among the volatility rates of a plurality of the unit motion amounts, and a standard deviation of a plurality of the volatility rates as a first motion reference component of the livestock to be identified; and determining a second motion reference component of the livestock to be identified based on the number of first feature identifiers continuously distributed in the feature identifier sequence; Obtaining multiple sample standard deviations of each sample livestock within preset time intervals of different sampling cycles; determining a target livestock in estrus from each of the sample livestock, and determining an estrus time interval from the preset time intervals of the target livestock corresponding to different sampling cycles; determining candidate time intervals that do not belong to the estrus time interval from the multiple preset time intervals corresponding to each of the sample livestock; determining a maximum sample standard deviation from the sample standard deviations corresponding to the estrus time intervals; if the sample standard deviations corresponding to each of the candidate time intervals are all greater than the maximum sample standard deviation, determining the maximum sample standard deviation as the upper limit value of the movement measurement parameter; Obtaining a motion measurement parameter corresponding to the motion reference parameter, the motion measurement parameter being used to determine the estrus state of the livestock to be identified; wherein the motion reference parameter includes a first motion reference component and a second motion reference component, and the motion measurement parameter includes a first motion measurement component corresponding to the first motion reference component, and a second motion measurement component corresponding to the second motion reference component; If the motion reference parameter is within the parameter range of the motion measurement parameter, then the livestock to be identified is determined to be in estrus, including: if the first motion reference component is within the component range of the first motion measurement component, or the second motion reference component is within the component range of the second motion measurement component, then the livestock to be identified is determined to be in estrus.

2. The method according to claim 1, characterized in that The preset time interval includes at least two time units.

3. The method according to claim 2, characterized in that The obtaining of the fluctuation rate of each unit motion amount includes: For each unit movement amount, determining a maximum historical movement amount from historical unit movement amounts preceding the unit movement amount; Calculating the absolute value of the difference between the unit motion amount and the maximum historical motion amount; The ratio of the absolute value of the difference to the unit motion amount is determined as the fluctuation rate of the unit motion amount.

4. The method according to claim 2, characterized in that The first motion reference component includes a plurality of standard deviations of the unit motion quantities; the sample standard deviation is a standard deviation of a plurality of unit sample motion quantities within a preset time interval.

5. The method according to claim 1, wherein The preset time interval includes at least two time units; and determining the second motion reference component of the livestock to be identified based on the number of first feature identifiers continuously distributed in the feature identifier sequence includes: Determining a sub-identification sequence corresponding to each of the time units from the feature identification sequence; Determining the maximum number of first characteristic identifiers distributed continuously in each of the sub-identifier sequences; At least one of a standard deviation of a plurality of the maximum values of the number, a maximum fluctuation rate among the fluctuation rates of the plurality of the maximum values of the number, and a standard deviation of the plurality of the fluctuation rates is obtained as a second motion reference component of the livestock to be identified.

6. The method according to any one of claims 1 to 5, characterized in that Before obtaining the motion feature sequence of the livestock to be identified within a preset time interval, the method further includes: Determine the motion measurement parameters corresponding to the motion reference parameters in different preset time intervals; The step of obtaining a motion feature sequence of the livestock to be identified within a preset time interval includes: For a preset time interval that reaches a cutoff moment, a motion feature sequence of the livestock to be identified within the preset time interval is obtained.

7. A device for determining estrus in livestock, characterized in that: include: The livestock data acquisition module is used to obtain a motion feature sequence of the livestock to be identified within a preset time interval, comprising: obtaining time-series motion data of the livestock to be identified within the preset time interval, the time-series motion data including time-series sub-motion data in different preset directions; performing vector synthesis on the time-series sub-motion data in each preset direction to obtain time-series vector data; performing mean aggregation processing on the time-series vector data at a preset sampling rate to obtain the motion feature sequence; the motion feature sequence includes motion features at different moments, each motion feature being obtained by performing feature analysis on the motion data of the livestock to be identified at the corresponding moment; wherein the preset time interval includes time units; a feature identification module configured to determine, from the motion features at different moments, a target motion feature belonging to a preset feature category, including: for each motion feature in the motion feature sequence, obtaining a feature mean of historical motion features within a preset time period preceding the motion feature; and if the motion feature is greater than the feature mean, determining the motion feature as a target motion feature belonging to the preset feature category; The reference parameter determination module is used to analyze the quantitative distribution of the target motion characteristics in the motion characteristic sequence to obtain the motion reference parameters of the livestock to be identified, including: assigning a first characteristic identifier to the target motion characteristics, assigning a second characteristic identifier to the motion characteristics other than the target motion characteristics in the motion characteristic sequence, to obtain a characteristic identifier sequence; determining a sub-identification sequence corresponding to each of the time units from the characteristic identifier sequence; determining the quantitative proportion of the first characteristic identifier in each of the sub-identification sequences as the unit motion amount of each of the sub-identification sequences; obtaining at least one of the standard deviation of multiple unit motion amounts, the maximum volatility among the volatility of multiple unit motion amounts, and the standard deviation of multiple volatility as the first motion reference parameter of the livestock to be identified. component; determining a second motion reference component of the livestock to be identified based on the number of first feature identifiers continuously distributed in the feature identifier sequence; obtaining multiple sample standard deviations of each sample livestock within a preset time interval of different sampling cycles; determining a target livestock in estrus from each of the sample livestock, and determining an estrus time interval from the preset time intervals of the target livestock corresponding to different sampling cycles; determining a candidate time interval that does not belong to the estrus time interval from the multiple preset time intervals corresponding to each of the sample livestock; determining a maximum sample standard deviation from the sample standard deviations corresponding to the estrus time intervals; if the sample standard deviations corresponding to each of the candidate time intervals are all greater than the maximum sample standard deviation, determining the maximum sample standard deviation as the upper limit value of the motion measurement parameter; a measurement parameter acquisition module, configured to acquire a motion measurement parameter corresponding to the motion reference parameter, wherein the motion measurement parameter is used to determine the estrus state of the livestock to be identified; wherein the motion reference parameter includes a first motion reference component and a second motion reference component, and the motion measurement parameter includes a first motion measurement component corresponding to the first motion reference component, and a second motion measurement component corresponding to the second motion reference component; An estrus determination module is used to determine that the livestock to be identified is in estrus if the motion reference parameter is within the parameter range of the motion measurement parameter, including: if the first motion reference component is within the component range of the first motion measurement component, or the second motion reference component is within the component range of the second motion measurement component, then determine that the livestock to be identified is in estrus.

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

9. An electronic device comprising a processor and a memory, wherein the memory stores a computer program, wherein: The processor is configured to execute the livestock estrus determination method according to any one of claims 1 to 6 by calling the computer program.

Images