An intelligent pet management system
Through the information acquisition, historical data processing, trajectory analysis and feature extraction module of the intelligent pet management system, the problem of low efficiency of pet management in the existing technology is solved, accurate judgment of pet behavior and real-time alarms are realized, and pet management is improved overall efficiency.
Patent Information
- Application Number
- CN202411237333.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-09-05
AI Technical Summary
In the prior art, pet management efficiency is inefficient, and there is a lack of integrated and intelligent pet management solutions, so it is impossible to provide comprehensive pet care services.
Provide an intelligent pet management system, including information acquisition module, historical data processing module, trajectory analysis module, feature extraction module and pet data management module, to obtain and analyze pet monitoring data, conduct behavioral characteristics judgment and real-time alarms to improve pets Management efficiency.
Through the use of intelligent pet management system, the accuracy and completeness of information acquisition are improved, the accuracy of analysis of pet observation characteristics and movement trajectories is enhanced, accurate judgment of pet characteristic behaviors and real-time alarms are achieved, and pets are improved Management efficiency.
Smart Images

Figure CN118761010B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of pet management, and in particular to an intelligent pet management system. Background Art
[0002] Due to work and life reasons, pet owners are often unable to accompany their pets at all times, resulting in the pet's health and psychological needs not being fully met. In the prior art, although there are some single-function pet monitoring or feeding devices, there is a lack of integrated and intelligent pet management solutions, and it is impossible to provide comprehensive pet care services.
[0003] Chinese patent publication number CN108874323A discloses a pet monitoring data processing method and system, which implants a health management chip in the pet, activates the health management chip monitoring function in the mobile terminal, and returns a variety of pet monitoring data to the mobile terminal. The cloud data center periodically sends a pet monitoring data collection request to the mobile terminal, and the data collection response is started. Through the improved task scheduling method and write merging, the concurrent execution of multiple pet monitoring data collection agents and the merged write method greatly improve the processing speed and transmission efficiency of the pet monitoring data, so that the pet monitoring data is no longer collected and obtained through the traditional polling method, and is no longer limited by the number of nodes; it can be seen that the invention does not conduct a detailed analysis of the processing process of the pet monitoring data, and there is a problem of low pet management efficiency. Summary of the invention
[0004] To this end, the present invention provides an intelligent pet management system to overcome the problem of low pet management efficiency in the prior art.
[0005] To achieve the above object, the present invention provides an intelligent pet management system, comprising:
[0006] An information acquisition module is used to acquire pet monitoring data within a monitoring period and also to acquire pet historical data;
[0007] A historical data processing module is used to analyze pet observation characteristics based on pet historical data;
[0008] A trajectory analysis module is used to analyze the pet's movement trajectory within the monitoring period based on the pet monitoring data within the monitoring period;
[0009] Adjustment and optimization module, used to adjust the analysis process of pet movement trajectory according to environmental data within the monitoring period;
[0010] A feature extraction module is used to extract features of pet actions according to the pet action trajectory analysis results during the monitoring period to obtain real-time feature trajectories;
[0011] A feature analysis module is used to judge the characteristic behavior of the pet within the monitoring period according to the real-time feature trajectory analysis results and the pet observation feature analysis results within the monitoring period;
[0012] The pet data management module is used to manage the real-time characteristic trajectory and the pet monitoring data within the monitoring period according to the judgment results of the pet's characteristic behavior within the monitoring period, and is also used to give real-time alarms to users according to the judgment results of the pet's characteristic behavior within the monitoring period.
[0013] Furthermore, the historical data processing module is provided with a historical trajectory analysis unit, and the historical trajectory analysis unit is used to analyze the historical action trajectory of the pet according to the historical action trajectory data of the pet;
[0014] The historical trajectory analysis unit calculates the trajectory vector α(i) between adjacent collected data according to each pet positioning data (x(i), y(i), z(i)), and sets α(i)=(x(i+1)-x(i), y(i+1)-y(i), z(i+1)-z(i));
[0015] The historical trajectory analysis unit calculates the speed weight β(i) of each trajectory vector α(i) according to each pet positioning data (x(i), y(i), z(i)), and sets β(i)=([x(i+1)-x(i)] / t, [y(i+1)-y(i)] / t, [z(i+1)-z(i)] / t);
[0016] The historical trajectory analysis unit uses each trajectory vector and the speed weight of each trajectory vector as the pet's historical action trajectory vector group Q, and sets Q={[α(1), β(1)], [α(2), β(2)], ..., [α(n-1), β(n-1)]};
[0017] Among them, x(i) represents the spatial horizontal coordinate of the i-th collected data in the historical monitoring period, y(i) represents the spatial longitudinal coordinate of the i-th collected data in the historical monitoring period, z(i) represents the spatial vertical coordinate of the i-th collected data in the historical monitoring period, x(i+1) represents the spatial horizontal coordinate of the i+1-th collected data in the historical monitoring period, y(i+1) represents the spatial longitudinal coordinate of the i+1-th collected data in the historical monitoring period, z(i+1) represents the spatial vertical coordinate of the i+1-th collected data in the historical monitoring period, α(1) is the first trajectory vector, α(2) is the second trajectory vector, α(n-1) is the n-1-th trajectory vector, β(1) is the first speed weight, β(2) is the second speed weight, β(n-1) is the n-1-th speed weight, t is the interval length of historical continuous collection, set i=1,2...n-1, n is the number of pet positioning data in the monitoring period.
[0018] Furthermore, the historical data processing module is further provided with a data screening unit, and the data screening unit is used to screen abnormal action trajectories according to the historical trajectory analysis results, wherein:
[0019] When β(i)≥K1 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is an abnormal action trajectory;
[0020] When β(i)<K1 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is a normal action trajectory;
[0021] When |α(i)|≥K2 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is an abnormal action trajectory;
[0022] When |α(i)|<K2 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is a normal action trajectory;
[0023] Among them, K1 is the preset pet abnormal speed, and K2 is the preset pet abnormal displacement length;
[0024] The data screening unit is further used to delete the historical action trajectory vector group of abnormal action trajectory.
[0025] Furthermore, the historical data processing module is further provided with an observation feature analysis unit, which is used to analyze the pet observation features according to the abnormal action trajectory screening results and historical health data, wherein:
[0026] When γ<B and |Q|<K3, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is a regular feature;
[0027] When γ<B and |Q|≥K3, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is a special feature;
[0028] When γ≥B, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is an abnormal pet action;
[0029] Among them, B is the threshold of the physical sign index, γ is the physical sign index in the historical monitoring period, and γ=(rR) / R is set, r is the historical pet heart rate, R is the preset pet heart rate, and K3 is the second preset pet abnormal displacement length;
[0030] The observation feature analysis unit is also used to store the pet observation features.
[0031] Furthermore, the trajectory analysis module is provided with a data processing unit, and the data processing unit is used to process the pet monitoring data within the monitoring period;
[0032] The data processing unit calculates the grouping vector a(j-1), and sets a(j-1)=(X(j)-X(j-1), Y(j)-Y(j-1), Z(j)-Z(j-1));
[0033] Wherein, X(j) is the X-axis coordinate of the j-th real-time positioning data, X(j-1) is the X-axis coordinate of the j-1-th real-time positioning data, Y(j) is the Y-axis coordinate of the j-th real-time positioning data, Y(j-1) is the Y-axis coordinate of the j-1-th real-time positioning data, Z(j) is the Z-axis coordinate of the j-th real-time positioning data, Z(j-1) is the Z-axis coordinate of the j-1-th real-time positioning data, j=2,3...J, J is the number of pet real-time positioning data acquired during the monitoring period;
[0034] The data processing unit performs abnormality judgment on the pet real-time positioning data within the monitoring period according to the grouping vector a(i), and performs data processing on the pet real-time positioning data within the monitoring period according to the judgment result, wherein:
[0035] When |a(j-1)|<K2, the data processing unit determines that the pet real-time positioning data of the grouping vector is normal;
[0036] When |a(j-1)|≥K2, the data processing unit determines that the pet real-time positioning data of the grouping vector is abnormal, and uses the pet real-time positioning data (X(j), Y(j), Z(j)) as abnormal positioning data;
[0037] The data processing unit is also used to delete the abnormal location data and the grouping vector a(j-1);
[0038] The trajectory analysis module is provided with a trajectory analysis unit, and the trajectory analysis unit is used to analyze the pet's movement trajectory within the monitoring period according to the data processing result of the pet monitoring data within the monitoring period;
[0039] The data processing unit generates a real-time action trajectory curve SQ within a monitoring period according to each grouping vector a(j-1), and sets SQ={[a(1), b(1)], [a(2), b(2)], ..., [a(J-1), b(J-1)]}; a(1) is the first real-time trajectory vector, a(2) is the second real-time trajectory vector, a(J-1) is the J-1th real-time trajectory vector, b(1) is the first real-time speed weight, b(2) is the second real-time speed weight, and b(J-1) is the J-1th real-time speed weight.
[0040] Furthermore, the adjustment and optimization module is provided with an adjustment unit, which is used to compare the ambient temperature c in the monitoring period with each preset ambient temperature, and adjust the analysis process of the pet's movement trajectory in the monitoring period according to the comparison result, wherein:
[0041] When c<C1, the adjustment unit determines that the ambient temperature is low during the monitoring period, and adjusts the preset abnormal displacement length of the pet to K2', setting K2'=K2×exp{(c-C1) / C1};
[0042] When C1≤c<C2, the adjustment unit determines that the ambient temperature within the monitoring period is normal and does not make any adjustment;
[0043] When c≥C2, the adjustment unit determines that the ambient temperature in the monitoring period is high, and adjusts the preset pet abnormal displacement length to K2", setting K2"=K2 / exp{(c-C2) / C1};
[0044] Wherein, C1 is the first preset pet temperature, C2 is the second preset pet temperature, and C1<C2.
[0045] Furthermore, the adjustment unit is further provided with an optimization unit, which is used to optimize the adjustment process of the pet's movement trajectory during the monitoring period according to the physical sign data during the monitoring period and the calculation results of the body mass index during the historical monitoring period, wherein:
[0046] When v / pγ<d, the optimization unit determines that the physical sign status of the pet is normal during the monitoring period and does not perform optimization;
[0047] When v / pγ≥d, the optimization unit determines that the physical state of the pet is abnormal during the monitoring period, and optimizes the second preset pet temperature to C2', setting C2'=C2×cos[(V / pγ-d) / d];
[0048] Among them, v is the real-time pet vital sign index, pγ is the average value of the pet's vital sign index during the historical monitoring period, and d is the preset offset index.
[0049] Furthermore, the feature extraction module extracts features of the pet's actions based on the pet's action trajectory analysis results during the monitoring period;
[0050] The feature extraction module calculates the real-time feature vector group η according to the real-time action trajectory curve SQ, and sets:
[0051] ;
[0052] ;
[0053] ;
[0054] ;
[0055] Wherein, M is the number of data in the group, set M=t / time interval for obtaining real-time spatial positioning data, SQ(m) is the mth item of data in the real-time action trajectory curve SQ, namely [a(m), b(m)], a(m) is the mth real-time trajectory vector, b(m) is the mth real-time speed weight, η1 is the first vector of the real-time feature vector group η, η2 is the second vector of the real-time feature vector group η, and ηn is the nth vector of the real-time feature vector group η;
[0056] The feature extraction module uses the real-time feature vector group n as a real-time feature trajectory.
[0057] Furthermore, the feature analysis module calculates the vector group fitting degree MSE according to the real-time feature vector group η and the historical action trajectory vector group Q;
[0058] The feature analysis module compares the vector group fit MSE with the preset fit W, and determines the pet's characteristic behavior within the monitoring period according to the comparison result, where:
[0059] When MSE≥W, the feature analysis module determines that the fit is abnormal, and determines that the characteristic behavior of the pet during the monitoring period is an abnormal characteristic behavior;
[0060] When MSE<W, the feature analysis module determines that the fit is normal, and determines that the characteristic behavior of the pet during the monitoring period is the pet observation feature corresponding to the historical action trajectory vector group Q.
[0061] Furthermore, the pet data management module manages the real-time characteristic trajectory and the pet monitoring data within the monitoring period according to the judgment result of the pet characteristic behavior within the monitoring period, wherein:
[0062] When the characteristic behavior of the pet in the monitoring period is abnormal, the pet data management module adds the real-time characteristic trajectory and the pet monitoring data in the monitoring period to the pet historical data of the next monitoring period, and issues a real-time risk alarm to the user;
[0063] When the characteristic behavior of the pet in the monitoring period is a regular characteristic, the pet data management module does not change the pet historical data of the next monitoring period and does not alarm the user;
[0064] When the pet's characteristic behavior in the monitoring period is a special characteristic, the pet data management module does not change the pet's historical data in the next monitoring period and issues a real-time risk alarm to the user;
[0065] When the characteristic behavior of the pet in the monitoring period is an abnormal action of the pet, the pet data management module does not change the historical data of the pet in the next monitoring period and issues a real-time danger alarm to the user.
[0066] Compared with the prior art, the beneficial effects of the present invention lie in that the information required by the present invention is acquired by the information acquisition module, thereby improving the accuracy and completeness of information acquisition, the pet observation characteristics are analyzed by the historical data processing module, thereby improving the accuracy of the observation characteristic analysis, the pet action trajectory is analyzed by the trajectory analysis module, thereby improving the accuracy of the pet trajectory analysis, the analysis process of the pet action trajectory is adjusted by the adjustment and optimization module, thereby improving the accuracy of the pet trajectory analysis, the feature extraction module extracts features of the pet action to obtain a real-time feature trajectory, thereby improving the accuracy of the real-time feature trajectory analysis, the feature analysis module judges the pet's characteristic behavior within the monitoring period, thereby improving the accuracy of the characteristic behavior judgment, the pet data management module manages the real-time characteristic trajectory and the pet monitoring data within the monitoring period, and issues a real-time alarm to the user based on the judgment result of the pet's characteristic behavior within the monitoring period, thereby improving the efficiency of pet management. BRIEF DESCRIPTION OF THE DRAWINGS
[0067] Figure 1 This is a schematic diagram of the structure of the intelligent pet management system of this embodiment.
[0068] Figure 2 Schematic diagram of the structure of the historical data processing module of this embodiment.
[0069] Figure 3 Schematic diagram of the structure of the trajectory analysis module of this embodiment.
[0070] Figure 4 This is a schematic diagram of the structure of the adjustment and optimization module in this embodiment. DETAILED DESCRIPTION
[0071] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0072] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.
[0073] It should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0074] See also Figure 1 As shown, it is a structural diagram of the intelligent pet management system of this embodiment, including:
[0075] The information acquisition module is used to obtain the pet monitoring data within the monitoring period, and is also used to obtain the pet historical data; the pet monitoring data includes the pet's real-time positioning data, vital sign data and environmental data within the monitoring period, the environmental data includes the ambient temperature, and the vital sign data includes the real-time pet heart rate; the present embodiment does not specifically limit the method for obtaining the pet's historical data, and those skilled in the art can set it freely, and only need to meet the requirements for obtaining the pet's historical data, such as obtaining it through a historical cloud database; the present embodiment does not specifically limit the method for obtaining the pet monitoring data, and those skilled in the art can set it freely, and only need to meet the requirements for obtaining the pet monitoring data, such as obtaining the pet monitoring data through a pet wearable device; the present embodiment does not specifically limit the value of the monitoring period, and those skilled in the art can set it freely, and only need to meet the requirements for the value of the monitoring period, such as the duration of the monitoring period can be set to 1 minute; the present embodiment obtains the pet's real-time positioning data within the monitoring period by continuously obtaining the real-time spatial positioning data within the monitoring period, and uses all the real-time spatial positioning data within the monitoring period as the pet's real-time positioning data; the present embodiment does not continuously obtain the real-time spatial positioning data The time interval of the data is specifically limited, and those skilled in the art can set it freely, and only need to meet the value requirements of the time interval for obtaining real-time spatial positioning data, such as the time interval for obtaining real-time spatial positioning data can be set to 1 second; the pet historical data includes pet historical health data and pet historical action trajectory data, and the pet historical health data includes historical pet heart rate; this embodiment does not specifically limit the number of pet historical data, and those skilled in the art can set it freely, and only need to meet the number requirements of pet historical data, such as the number of pet data can be set to 50 groups; the pet historical action trajectory data is a collection of pet positioning data continuously collected during the historical monitoring period, and the pet positioning data is spatial positioning data, and its data structure is represented in the form of a spatial rectangular coordinate system (x, y, z); this embodiment does not specifically limit the interval duration of continuous collection during the historical monitoring period, and those skilled in the art can set it freely, and only need to meet the value requirements of the interval duration of continuous collection during the historical monitoring period (interval duration of continuous collection during the historical monitoring period / time interval for obtaining real-time spatial positioning data ≥ 2), such as the interval duration of continuous collection can be set to 2 seconds;
[0076] It is worth noting that the duration of the historical monitoring axis is the same as the duration of the monitoring period;
[0077] It can be understood that the spatial rectangular coordinate system is established in this embodiment by taking the position of the pet when the pet monitoring data is first acquired during the monitoring period as the coordinate origin, the direction parallel to the latitude as the x-axis, the direction parallel to the longitude as the y-axis, and the direction perpendicular to the ground as the z-axis;
[0078] A historical data processing module, used for analyzing pet observation characteristics according to pet historical data, the historical data processing module is connected to the information acquisition module;
[0079] A trajectory analysis module, used for analyzing the pet's movement trajectory within the monitoring period according to the pet monitoring data within the monitoring period, and the trajectory analysis module is connected to the information acquisition module;
[0080] An adjustment and optimization module, used for adjusting the analysis process of the pet's movement trajectory according to the environmental data in the monitoring period, and the adjustment and optimization module is connected to the trajectory analysis module;
[0081] A feature extraction module, used to extract features of pet actions according to the pet action trajectory analysis results within the monitoring period to obtain real-time feature trajectories, the feature extraction module is connected to the adjustment and optimization module;
[0082] A feature analysis module, used to judge the characteristic behavior of the pet within the monitoring period according to the real-time feature trajectory analysis results and the pet observation feature analysis results within the monitoring period, and the feature analysis module is connected to the historical data processing module and the feature extraction module;
[0083] The pet data management module is used to manage the real-time characteristic trajectory and the pet monitoring data within the monitoring period according to the judgment results of the pet's characteristic behavior within the monitoring period, and is also used to make real-time alarms to the user according to the judgment results of the pet's characteristic behavior within the monitoring period. The pet data management module is connected to the characteristic analysis module.
[0084] Specifically, the intelligent pet management system described in this embodiment is applied to the intelligent management of pets in pet stores and pet shelters for free-range pets; the pet described in this embodiment is specifically a pet dog with the ability to move in a certain area; the pet described in this embodiment is equipped with a real-time positioning device and a signal transmitting device; this embodiment improves the efficiency of pet management by analyzing the pet's historical data and the real-time pet behavior characteristics.
[0085] See also Figure 2 As shown, it is a schematic diagram of the structure of the historical data processing module of this embodiment, including:
[0086] A historical trajectory analysis unit, used to analyze the pet's historical action trajectory based on the pet's historical action trajectory data;
[0087] A data screening unit, used for screening abnormal action trajectories according to the historical trajectory analysis results, the data screening unit is connected to the historical trajectory analysis unit;
[0088] The observation feature analysis unit is used to analyze the observation features of the pet according to the abnormal action trajectory screening results and the historical health data, and the observation feature analysis unit is connected to the data screening unit.
[0089] Specifically, the historical data processing module is provided with a historical trajectory analysis unit, and the historical trajectory analysis unit analyzes the historical action trajectory of the pet according to the historical action trajectory data of the pet;
[0090] The historical trajectory analysis unit calculates the trajectory vector α(i) between adjacent collected data according to each pet positioning data (x(i), y(i), z(i)), and sets α(i)=(x(i+1)-x(i), y(i+1)-y(i), z(i+1)-z(i));
[0091] The historical trajectory analysis unit calculates the speed weight β(i) of each trajectory vector α(i) according to each pet positioning data (x(i), y(i), z(i)), and sets β(i)=([x(i+1)-x(i)] / t, [y(i+1)-y(i)] / t, [z(i+1)-z(i)] / t);
[0092] The historical trajectory analysis unit uses each trajectory vector and the speed weight of each trajectory vector as the pet's historical action trajectory vector group Q, and sets Q={[α(1), β(1)], [α(2), β(2)], ..., [α(n-1), β(n-1)]};
[0093] Among them, x(i) represents the spatial horizontal coordinate of the i-th collected data in the historical monitoring period, y(i) represents the spatial longitudinal coordinate of the i-th collected data in the historical monitoring period, z(i) represents the spatial vertical coordinate of the i-th collected data in the historical monitoring period, x(i+1) represents the spatial horizontal coordinate of the i+1-th collected data in the historical monitoring period, y(i+1) represents the spatial longitudinal coordinate of the i+1-th collected data in the historical monitoring period, z(i+1) represents the spatial vertical coordinate of the i+1-th collected data in the historical monitoring period, α(1) is the first trajectory vector, α(2) is the second trajectory vector, α(n-1) is the n-1-th trajectory vector, β(1) is the first speed weight, β(2) is the second speed weight, β(n-1) is the n-1-th speed weight, t is the interval length of historical continuous collection, set i=1,2...n-1, n is the number of pet positioning data in the monitoring period.
[0094] Specifically, the historical trajectory analysis unit analyzes the pet's historical action trajectory based on the pet's historical action trajectory data, thereby improving the accuracy of the historical action trajectory analysis, and further improving the accuracy of the pet's observation trajectory analysis, thereby improving the accuracy of the pet's characteristic behavior judgment, and ultimately improving the efficiency of pet management.
[0095] Specifically, the historical data processing module is further provided with a data screening unit, which screens abnormal action trajectories according to the historical trajectory analysis results, wherein:
[0096] When β(i)≥K1 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is an abnormal action trajectory;
[0097] When β(i)<K1 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is a normal action trajectory;
[0098] When |α(i)|≥K2 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is an abnormal action trajectory;
[0099] When |α(i)|<K2 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is a normal action trajectory;
[0100] Among them, K1 is the preset pet abnormal speed, and K2 is the preset pet abnormal displacement length;
[0101] The data screening unit is further used to delete the historical action trajectory vector group of abnormal action trajectory.
[0102] It can be understood that in this embodiment, “|α(i)|” is a modular operation on the trajectory vector α(i).
[0103] Specifically, the data screening unit screens the abnormal action trajectory according to the historical trajectory analysis results, thereby improving the accuracy of the abnormal action trajectory screening, and further improving the accuracy of the pet observation trajectory analysis, thereby improving the accuracy of the pet characteristic behavior judgment, and ultimately improving the efficiency of pet management; it can be understood that this embodiment does not specifically limit the values of the preset pet abnormal speed K1 and the preset pet abnormal displacement length K2. Those skilled in the art can set them freely, and only need to meet the value requirements of the preset pet abnormal speed K1 and the preset pet abnormal displacement length K2. For example, the preset pet abnormal speed K1 can be set to 5m / s, and the preset pet abnormal displacement length K2 can be set to 15m.
[0104] Specifically, the historical data processing module is further provided with an observation feature analysis unit, which analyzes the pet observation features according to the abnormal action trajectory screening results and historical health data, wherein:
[0105] When γ<B and |Q|<K3, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is a regular feature;
[0106] When γ<B and |Q|≥K3, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is a special feature;
[0107] When γ≥B, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is an abnormal pet action;
[0108] Among them, B is the threshold of the physical sign index, γ is the physical sign index in the historical monitoring period, and γ=(rR) / R is set, r is the historical pet heart rate, R is the preset pet heart rate, and K3 is the second preset pet abnormal displacement length;
[0109] The observation feature analysis unit is also used to store the pet observation features.
[0110] Specifically, the observation feature analysis unit analyzes the pet observation features according to the abnormal action trajectory screening results and historical health data, thereby improving the accuracy of the pet observation trajectory analysis, thereby improving the accuracy of the pet characteristic behavior judgment, and ultimately improving the efficiency of pet management; it can be understood that this embodiment does not make specific limitations on the value of the second preset pet abnormal displacement length K3, and technical personnel in this field can set it freely, as long as the value requirement of the second preset pet abnormal displacement length K3 is met, such as the second preset pet abnormal displacement length K3 can be set to 10m.
[0111] See also Figure 3 As shown, it is a schematic diagram of the structure of the trajectory analysis module of this embodiment, including:
[0112] A data processing unit, used for processing the pet monitoring data within the monitoring period;
[0113] The trajectory analysis unit is used to analyze the pet's movement trajectory within the monitoring period according to the data processing result of the pet monitoring data within the monitoring period, and the trajectory analysis unit is connected to the data processing unit.
[0114] Specifically, the trajectory analysis module is provided with a data processing unit, and the data processing unit is used to process the pet monitoring data within the monitoring period;
[0115] The data processing unit calculates the grouping vector a(j-1), and sets a(j-1)=(X(j)-X(j-1), Y(j)-Y(j-1), Z(j)-Z(j-1));
[0116] Wherein, X(j) is the X-axis coordinate of the j-th real-time positioning data, X(j-1) is the X-axis coordinate of the j-1-th real-time positioning data, Y(j) is the Y-axis coordinate of the j-th real-time positioning data, Y(j-1) is the Y-axis coordinate of the j-1-th real-time positioning data, Z(j) is the Z-axis coordinate of the j-th real-time positioning data, Z(j-1) is the Z-axis coordinate of the j-1-th real-time positioning data, j=2,3...J, J is the number of pet real-time positioning data acquired during the monitoring period;
[0117] The data processing unit performs abnormality judgment on the pet real-time positioning data within the monitoring period according to the grouping vector a(i), and performs data processing on the pet real-time positioning data within the monitoring period according to the judgment result, wherein:
[0118] When |a(j-1)|<K2, the data processing unit determines that the pet real-time positioning data of the grouping vector is normal;
[0119] When |a(j-1)|≥K2, the data processing unit determines that the pet real-time positioning data of the grouping vector is abnormal, and uses the pet real-time positioning data (X(j), Y(j), Z(j)) as abnormal positioning data;
[0120] The data processing unit is further used to delete the abnormal location data and the grouping vector a(j-1).
[0121] It can be understood that the calculation process of “|a(j-1)|” in this embodiment is “|a(j-1)|={[X(j)-X(j-1)] 2 +[Y(j)-Y(j-1)] 2 +[Z(j)-Z(j-1)] 2} 1 / 2 "; At the same time, in this embodiment, after deleting the grouping vector a(j-1), the subsequent grouping vectors are moved forward in sequence, that is, the original a(j) is moved forward to the new a(j-1).
[0122] Specifically, the data processing unit improves the accuracy of pet movement trajectory analysis within the monitoring period by processing the pet monitoring data within the monitoring period, thereby improving the accuracy of judging the pet's characteristic behavior, and ultimately improving the efficiency of pet management.
[0123] Specifically, the trajectory analysis module is provided with a trajectory analysis unit, and the trajectory analysis unit analyzes the pet's movement trajectory within the monitoring period according to the data processing result of the pet monitoring data within the monitoring period;
[0124] The data processing unit generates a real-time action trajectory curve SQ within the monitoring period according to each grouping vector a(j-1), and sets SQ={[a(1), b(1)], [a(2), b(2)], ..., [a(J-1), b(J-1)]}; a(1) is the first real-time trajectory vector, a(2) is the second real-time trajectory vector, a(J-1) is the J-1th real-time trajectory vector, b(1) is the first real-time speed weight, b(2) is the second real-time speed weight, and b(J-1) is the J-1th real-time speed weight (the process of generating the real-time action trajectory curve within the monitoring period in this embodiment is the same as the process of generating the historical action trajectory vector group within the historical monitoring period and the calculation process of b(j-1) is the same as β(i), which will not be repeated here).
[0125] Specifically, the trajectory analysis unit analyzes the pet's movement trajectory within the monitoring period according to the data processing results of the pet monitoring data within the monitoring period, thereby improving the accuracy of the pet's movement trajectory analysis within the monitoring period, thereby improving the accuracy of the pet's characteristic behavior judgment, and ultimately improving the efficiency of pet management.
[0126] See also Figure 4 As shown, it is a schematic diagram of the structure of the adjustment and optimization module of this embodiment, including:
[0127] An adjustment unit, for adjusting the analysis process of the pet's movement trajectory during the monitoring period according to the ambient temperature during the monitoring period;
[0128] The optimization unit is used to optimize the adjustment process of the pet's movement trajectory during the monitoring period according to the physical sign data during the monitoring period and the calculation results of the body mass index during the historical monitoring period, and the optimization unit is connected to the adjustment unit. Specifically, the adjustment optimization module is provided with an adjustment unit, and the adjustment unit compares the ambient temperature c during the monitoring period with each preset ambient temperature, and adjusts the analysis process of the pet's movement trajectory during the monitoring period according to the comparison results, wherein:
[0129] When c<C1, the adjustment unit determines that the ambient temperature is low during the monitoring period, and adjusts the preset abnormal displacement length of the pet to K2', setting K2'=K2×exp{(c-C1) / C1};
[0130] When C1≤c<C2, the adjustment unit determines that the ambient temperature within the monitoring period is normal and does not make any adjustment;
[0131] When c≥C2, the adjustment unit determines that the ambient temperature in the monitoring period is high, and adjusts the preset pet abnormal displacement length to K2", setting K2"=K2 / exp{(c-C2) / C1};
[0132] Wherein, C1 is the first preset pet temperature, C2 is the second preset pet temperature, and C1<C2.
[0133] Specifically, the adjustment unit improves the accuracy of the pet's action trajectory analysis within the monitoring period by adjusting the analysis process of the pet's action trajectory within the monitoring period, thereby improving the accuracy of the pet's characteristic behavior judgment, and ultimately improving the efficiency of pet management; it can be understood that this embodiment does not specifically limit the values of the first preset pet temperature C1 and the second preset pet temperature C2, and those skilled in the art can set them freely, as long as the value requirements of the first preset pet temperature C1 and the second preset pet temperature C2 are met, such as the first preset pet temperature C1 can be set as the left value of the pet's suitable temperature range, and the second preset pet temperature C2 can be set as the right value of the pet's suitable temperature range; the pet's suitable temperature range can be obtained through a pet introduction website, or obtained by user interactive input.
[0134] Specifically, the adjustment unit is further provided with an optimization unit, which optimizes the adjustment process of the pet's movement trajectory during the monitoring period according to the physical sign data during the monitoring period and the calculation results of the body mass index during the historical monitoring period, wherein:
[0135] When v / pγ<d, the optimization unit determines that the physical sign status of the pet is normal during the monitoring period and does not perform optimization;
[0136] When v / pγ≥d, the optimization unit determines that the physical state of the pet is abnormal during the monitoring period, and optimizes the second preset pet temperature to C2', setting C2'=C2×cos[(V / pγ-d) / d];
[0137] Wherein, v is the real-time pet vital sign index, pγ is the average vital sign index of the pet in the historical monitoring period, and pγ=[γ(1)+γ(2)+...+γ(N)] / N is set, γ(1) is the vital sign index of the pet in the first historical monitoring period, γ(2) is the vital sign index of the pet in the second historical monitoring period, γ(N) is the vital sign index of the pet in the Nth historical monitoring period, N is the number of historical monitoring periods, and d is the preset offset index;
[0138] Specifically, the present embodiment does not make the calculation process of the real-time pet vital sign index v the same as the calculation process of the vital sign index γ in the historical monitoring period, and will not be elaborated here.
[0139] Specifically, the optimization unit improves the accuracy of the pet's movement trajectory analysis within the monitoring period by optimizing the adjustment process of the pet's movement trajectory within the monitoring period, thereby improving the accuracy of the pet's characteristic behavior judgment, and ultimately improving the efficiency of pet management; it can be understood that this embodiment does not make a specific limitation on the value of the preset offset index d, and technical personnel in this field can set it freely, as long as the value requirement of the preset offset index d is met, such as the preset offset index d can be set to 1.2.
[0140] Specifically, the feature extraction module extracts features of the pet's actions based on the pet's action trajectory analysis results during the monitoring period;
[0141] The feature extraction module calculates the real-time feature vector group η according to the real-time action trajectory curve SQ, and sets:
[0142] ;
[0143] ;
[0144] ;
[0145] ;
[0146] Wherein, M is the number of data in the group, set M=t / time interval for obtaining real-time spatial positioning data, SQ(m) is the mth item of data in the real-time action trajectory curve SQ, namely [a(m), b(m)], a(m) is the mth real-time trajectory vector, b(m) is the mth real-time speed weight, η1 is the first vector of the real-time feature vector group η, η2 is the second vector of the real-time feature vector group η, and ηn is the nth vector of the real-time feature vector group η;
[0147] The feature extraction module uses the real-time feature vector group n as a real-time feature trajectory.
[0148] It is understandable that this embodiment =[(a(1)+a(2)+...+a(M)) / M, (b(1)+b(2)+...+b(M)) / M]; where a(M) is the Mth trajectory vector, and b(M) is the Mth velocity weight vector;
[0149] Specifically, the feature extraction module extracts features of the pet's actions based on the pet's action trajectory analysis results during the monitoring period, thereby improving the accuracy of judging the pet's characteristic behaviors and ultimately improving the efficiency of pet management.
[0150] Specifically, the feature analysis module calculates the vector group fitting degree MSE according to the real-time feature vector group η and the historical action trajectory vector group Q. The calculation formula of the vector group fitting degree MSE is as follows:
[0151] ;
[0152] Among them, ηh represents the hth vector of the real-time feature vector group η, α(h) represents the hth trajectory vector, and β(h) represents the hth speed weight;
[0153] The feature analysis module compares the vector group fit MSE with the preset fit W, and determines the pet's characteristic behavior within the monitoring period according to the comparison result, where:
[0154] When MSE≥W, the feature analysis module determines that the fit is abnormal, and determines that the characteristic behavior of the pet during the monitoring period is an abnormal characteristic behavior;
[0155] When MSE<W, the feature analysis module determines that the fit is normal, and determines that the characteristic behavior of the pet during the monitoring period is the pet observation feature corresponding to the historical action trajectory vector group Q.
[0156] Specifically, the characteristic analysis module improves the accuracy of judging the characteristic behavior of the pet by judging the characteristic behavior of the pet within the monitoring period, thereby ultimately improving the efficiency of pet management; it can be understood that this embodiment does not specifically limit the value of the preset fitness degree W, and technicians in this field can set it freely, as long as the value requirement of the preset fitness degree W is met, such as the preset fitness degree W can be set to 1.
[0157] Specifically, the pet data management module manages the real-time characteristic trajectory and the pet monitoring data within the monitoring period according to the judgment result of the pet characteristic behavior within the monitoring period, wherein:
[0158] When the characteristic behavior of the pet in the monitoring period is abnormal, the pet data management module adds the real-time characteristic trajectory and the pet monitoring data in the monitoring period to the pet historical data of the next monitoring period, and issues a real-time risk alarm to the user;
[0159] When the characteristic behavior of the pet in the monitoring period is a regular characteristic, the pet data management module does not change the pet historical data of the next monitoring period and does not alarm the user;
[0160] When the pet's characteristic behavior in the monitoring period is a special characteristic, the pet data management module does not change the pet's historical data in the next monitoring period and issues a real-time risk alarm to the user;
[0161] When the characteristic behavior of the pet in the monitoring period is an abnormal action of the pet, the pet data management module does not change the historical data of the pet in the next monitoring period and issues a real-time danger alarm to the user.
[0162] Specifically, the pet data management module manages the real-time characteristic trajectory and pet monitoring data within the monitoring period according to the judgment results of the pet's characteristic behavior within the monitoring period, and is also used to provide real-time alarms to users according to the judgment results of the pet's characteristic behavior within the monitoring period, thereby improving the accuracy of the judgment of the pet's characteristic behavior and ultimately improving the efficiency of pet management.
[0163] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.
Claims
1. An intelligent pet management system, characterized in that: include: An information acquisition module is used to acquire pet monitoring data within a monitoring period and also to acquire pet historical data; A historical data processing module is used to analyze pet observation characteristics based on pet historical data; A trajectory analysis module is used to analyze the pet's movement trajectory within the monitoring period based on the pet monitoring data within the monitoring period; Adjustment and optimization module, used to adjust the analysis process of pet movement trajectory according to environmental data within the monitoring period; A feature extraction module is used to extract features of pet actions according to the pet action trajectory analysis results during the monitoring period to obtain real-time feature trajectories; A feature analysis module is used to judge the characteristic behavior of the pet within the monitoring period according to the real-time feature trajectory analysis results and the pet observation feature analysis results within the monitoring period; A pet data management module is used to manage the real-time characteristic trajectory and the pet monitoring data within the monitoring period according to the judgment results of the pet's characteristic behavior within the monitoring period, and is also used to issue a real-time alarm to the user according to the judgment results of the pet's characteristic behavior within the monitoring period; The historical data processing module is provided with a historical trajectory analysis unit, and the historical trajectory analysis unit is used to analyze the historical action trajectory of the pet according to the historical action trajectory data of the pet; The historical trajectory analysis unit calculates the trajectory vector α(i) between adjacent collected data according to each pet positioning data (x(i), y(i), z(i)), and sets α(i)=(x(i+1)-x(i), y(i+1)-y(i), z(i+1)-z(i)); The historical trajectory analysis unit calculates the speed weight β(i) of each trajectory vector α(i) according to each pet positioning data (x(i), y(i), z(i)), and sets β(i)=([x(i+1)-x(i)] / t, [y(i+1)-y(i)] / t, [z(i+1)-z(i)] / t); The historical trajectory analysis unit uses each trajectory vector and the speed weight of each trajectory vector as the pet's historical action trajectory vector group Q, and sets Q={[α(1), β(1)], [α(2), β(2)], ..., [α(n-1), β(n-1)]}; Among them, x(i) represents the spatial horizontal coordinate of the i-th collected data in the historical monitoring period, y(i) represents the spatial longitudinal coordinate of the i-th collected data in the historical monitoring period, z(i) represents the spatial vertical coordinate of the i-th collected data in the historical monitoring period, x(i+1) represents the spatial horizontal coordinate of the i+1-th collected data in the historical monitoring period, y(i+1) represents the spatial longitudinal coordinate of the i+1-th collected data in the historical monitoring period, z(i+1) represents the spatial vertical coordinate of the i+1-th collected data in the historical monitoring period, α(1) is the first trajectory vector, α(2) is the second trajectory vector, α(n-1) is the n-1-th trajectory vector, β(1) is the first speed weight, β(2) is the second speed weight, β(n-1) is the n-1-th speed weight, t is the interval length of historical continuous collection, set i=1,2...n-1, n is the number of pet positioning data in the monitoring period.
2. The intelligent pet management system according to claim 1, characterized in that: The historical data processing module is further provided with a data screening unit, which is used to screen abnormal action trajectories according to the historical trajectory analysis results, wherein: When β(i)≥K1 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is an abnormal action trajectory; When β(i)<K1 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is a normal action trajectory; When |α(i)|≥K2 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is an abnormal action trajectory; When |α(i)|<K2 exists in the historical action trajectory vector group Q, the data screening unit determines that the historical action trajectory vector group is a normal action trajectory; Among them, K1 is the preset pet abnormal speed, and K2 is the preset pet abnormal displacement length; The data screening unit is further used to delete the historical action trajectory vector group of abnormal action trajectory.
3. The intelligent pet management system according to claim 2, characterized in that: The historical data processing module is further provided with an observation feature analysis unit, which is used to analyze the pet observation features according to the abnormal action trajectory screening results and historical health data, wherein: When γ<B and |Q|<K3, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is a regular feature; When γ<B and |Q|≥K3, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is a special feature; When γ≥B, the observation feature analysis unit determines that the pet observation feature of the historical action trajectory is an abnormal pet action; Among them, B is the threshold of the physical sign index, γ is the physical sign index in the historical monitoring period, and γ=(rR) / R is set, r is the historical pet heart rate, R is the preset pet heart rate, and K3 is the second preset pet abnormal displacement length; The observation feature analysis unit is also used to store the pet observation features.
4. The intelligent pet management system according to claim 3, characterized in that: The trajectory analysis module is provided with a data processing unit, and the data processing unit is used to process the pet monitoring data within the monitoring period; The data processing unit calculates the grouping vector a(j-1), and sets a(j-1)=(X(j)-X(j-1), Y(j)-Y(j-1), Z(j)-Z(j-1)); Wherein, X(j) is the X-axis coordinate of the j-th real-time positioning data, X(j-1) is the X-axis coordinate of the j-1-th real-time positioning data, Y(j) is the Y-axis coordinate of the j-th real-time positioning data, Y(j-1) is the Y-axis coordinate of the j-1-th real-time positioning data, Z(j) is the Z-axis coordinate of the j-th real-time positioning data, Z(j-1) is the Z-axis coordinate of the j-1-th real-time positioning data, j=2,3...J, J is the number of pet real-time positioning data acquired during the monitoring period; The data processing unit performs abnormality judgment on the pet real-time positioning data within the monitoring period according to the grouping vector a(i), and performs data processing on the pet real-time positioning data within the monitoring period according to the judgment result, wherein: When |a(j-1)|<K2, the data processing unit determines that the pet real-time positioning data of the grouping vector is normal; When |a(j-1)|≥K2, the data processing unit determines that the pet real-time positioning data of the grouping vector is abnormal, and uses the pet real-time positioning data (X(j), Y(j), Z(j)) as abnormal positioning data; The data processing unit is also used to delete the abnormal location data and the grouping vector a(j-1); The trajectory analysis module is provided with a trajectory analysis unit, and the trajectory analysis unit is used to analyze the pet's movement trajectory within the monitoring period according to the data processing result of the pet monitoring data within the monitoring period; The data processing unit generates a real-time action trajectory curve SQ within a monitoring period according to each grouping vector a(j-1), and sets SQ={[a(1), b(1)], [a(2), b(2)], ..., [a(J-1), b(J-1)]}; a(1) is the first real-time trajectory vector, a(2) is the second real-time trajectory vector, a(J-1) is the J-1th real-time trajectory vector, b(1) is the first real-time speed weight, b(2) is the second real-time speed weight, and b(J-1) is the J-1th real-time speed weight.
5. The intelligent pet management system according to claim 4, characterized in that: The adjustment and optimization module is provided with an adjustment unit, which is used to compare the ambient temperature c in the monitoring period with each preset ambient temperature, and adjust the analysis process of the pet's movement trajectory in the monitoring period according to the comparison result, wherein: When c<C1, the adjustment unit determines that the ambient temperature is low during the monitoring period, and adjusts the preset abnormal displacement length of the pet to K2', setting K2'=K2×exp{(c-C1) / C1}; When C1≤c<C2, the adjustment unit determines that the ambient temperature within the monitoring period is normal and does not make any adjustment; When c≥C2, the adjustment unit determines that the ambient temperature in the monitoring period is high, and adjusts the preset pet abnormal displacement length to K2", setting K2"=K2 / exp{(c-C2) / C1}; Wherein, C1 is the first preset pet temperature, C2 is the second preset pet temperature, and C1<C2.
6. The intelligent pet management system according to claim 5, characterized in that: The adjustment unit is further provided with an optimization unit, which is used to optimize the adjustment process of the pet's movement trajectory during the monitoring period according to the physical sign data during the monitoring period and the weight index calculation results during the historical monitoring period, wherein: When v / pγ<d, the optimization unit determines that the physical sign status of the pet is normal during the monitoring period and does not perform optimization; When v / pγ≥d, the optimization unit determines that the physical state of the pet is abnormal during the monitoring period, and optimizes the second preset pet temperature to C2', setting C2'=C2×cos[(V / pγ-d) / d]; Among them, v is the real-time pet vital sign index, pγ is the average value of the pet's vital sign index during the historical monitoring period, and d is the preset offset index.
7. The intelligent pet management system according to claim 6, characterized in that: The feature extraction module extracts features of the pet's actions based on the pet's action trajectory analysis results during the monitoring period; The feature extraction module calculates the real-time feature vector group η according to the real-time action trajectory curve SQ, and sets: ; ; ; ; Wherein, M is the number of data in the group, set M=t / time interval for obtaining real-time spatial positioning data, SQ(m) is the mth item of data in the real-time action trajectory curve SQ, namely [a(m), b(m)], a(m) is the mth real-time trajectory vector, b(m) is the mth real-time speed weight, η1 is the first vector of the real-time feature vector group η, η2 is the second vector of the real-time feature vector group η, and ηn is the nth vector of the real-time feature vector group η; The feature extraction module uses the real-time feature vector group n as a real-time feature trajectory.
8. The intelligent pet management system according to claim 7, characterized in that: The feature analysis module calculates the vector group fitting degree MSE according to the real-time feature vector group η and the historical action trajectory vector group Q; The feature analysis module compares the vector group fit MSE with the preset fit W, and determines the pet's characteristic behavior within the monitoring period according to the comparison result, where: When MSE≥W, the feature analysis module determines that the fit is abnormal, and determines that the characteristic behavior of the pet during the monitoring period is an abnormal characteristic behavior; When MSE<W, the feature analysis module determines that the fit is normal, and determines that the characteristic behavior of the pet during the monitoring period is the pet observation feature corresponding to the historical action trajectory vector group Q.
9. The intelligent pet management system according to claim 8, characterized in that: The pet data management module manages the real-time characteristic trajectory and the pet monitoring data within the monitoring period according to the judgment result of the pet characteristic behavior within the monitoring period, wherein: When the characteristic behavior of the pet in the monitoring period is abnormal, the pet data management module adds the real-time characteristic trajectory and the pet monitoring data in the monitoring period to the pet historical data of the next monitoring period, and issues a real-time risk alarm to the user; When the characteristic behavior of the pet in the monitoring period is a regular characteristic, the pet data management module does not change the pet historical data of the next monitoring period and does not alarm the user; When the pet's characteristic behavior in the monitoring period is a special characteristic, the pet data management module does not change the pet's historical data in the next monitoring period and issues a real-time risk alarm to the user; When the characteristic behavior of the pet in the monitoring period is an abnormal action of the pet, the pet data management module does not change the historical data of the pet in the next monitoring period and issues a real-time danger alarm to the user.
