A pet information processing system based on the Internet of Things
Through the pet information processing system based on the Internet of Things, the problems of low efficiency of pet information analysis and inaccurate classification and storage are solved, efficient clustering feature analysis and accurate storage of pet information are realized, and management efficiency is improved.
Patent Information
- Application Number
- CN202411248400.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-09-06
AI Technical Summary
In the prior art, pet information analysis is inefficient and inaccurate classification storage is problematic.
A pet information processing system based on the Internet of Things was designed, including information acquisition module, node marking module, node analysis module, periodic analysis module, cluster analysis module and storage management module. By periodically obtaining pet information, time nodes and Coordinates, analyze differences nodes and correlation characteristics, calculate clustering characteristics and similarity, and realize clustering and accurate storage of information.
It improves the analysis efficiency of pet information and the accuracy of classification storage, and realizes efficient clustering feature analysis and merged storage of information.
Smart Images

Figure CN118760727B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of pet data processing, and in particular to a pet information processing system based on the Internet of Things. Background Art
[0002] With the development of information technology, pet information storage and management is gradually transforming from traditional manual recording to digital and intelligent. The traditional pet information management model has problems such as inconvenient information acquisition, cumbersome processes, and inaccurate management. In order to improve management efficiency and service quality, it has become an industry trend to use cloud computing, big data, database and other technologies to achieve centralized and automated management of pet information.
[0003] China Patent Publication No.: CN114185997A discloses a trusted storage system for pet information based on blockchain, including an underlying data storage system, an intermediate data processing system and an upper blockchain system. The underlying data storage system includes multiple data nodes, each of which is used to store different types of data, which can reduce the storage resource consumption of pet multimedia files and reduce the data storage capacity of the upper blockchain system; the intermediate data processing system is a bridge for data interaction between the underlying data storage system and the upper blockchain system; the upper blockchain system includes multiple blockchain nodes, which only store the characteristic value information of pet multimedia files, and can also perform secondary verification on the underlying data storage system through the mapping relationship between the upper blockchain nodes and the underlying data nodes. This invention realizes the hierarchical storage of pet information, but does not realize the digital classification processing of pet information content. There are problems such as low efficiency in pet information analysis and inaccurate classification storage processing of pet information. Summary of the invention
[0004] To this end, the present invention provides a pet information processing system based on the Internet of Things to overcome the problems of low efficiency in pet information analysis and inaccurate classification, storage and processing of pet information in the prior art.
[0005] To achieve the above object, the present invention provides a pet information processing system based on the Internet of Things, comprising:
[0006] An information acquisition module, used to periodically acquire pet information;
[0007] A node marking module is used to construct a time node according to the pet information, and is also used to analyze the node pet information according to the time node and the pet information;
[0008] A node analysis module, used to analyze the number of different nodes according to the node pet information, and also used to analyze the node association characteristics according to the number of different nodes and the node pet information;
[0009] A cycle analysis module is used to analyze motion-related parameters, cycle-related characteristics, and cycle fluctuation parameters based on pet information;
[0010] A coordinate construction module, used to construct node coordinates according to node pet information, and also used to construct periodic coordinates according to pet information and motion-related parameters;
[0011] A cluster analysis module, for analyzing cluster comparison parameters according to node association characteristics, period association characteristics and period fluctuation parameters, and for analyzing cluster characteristics according to node coordinates, period coordinates and cluster comparison parameters;
[0012] Cluster comparison module, used to analyze cluster similarity based on cluster characteristics;
[0013] The storage management module is used to manage the storage of pet information according to clustering characteristics and clustering similarities.
[0014] Furthermore, the node analysis module is provided with a difference analysis unit, which is used to calculate the node information difference parameter according to the node pet information through a difference analysis formula, and the difference analysis unit is provided with a difference analysis formula as follows:
[0015] W1(i,j)=[|A(i,j)-A(i,j-1)|+|A(i,j)-A(i,j+1)|] / 2;
[0016] W2(i,j)=[|B(i,j)-B(i,j-1)|+|B(i,j)-B(i,j+1)|] / 2;
[0017] Among them, A(i,j) represents the node pet body temperature, B(i,j) represents the node pet heart rate, W1(i,j) represents the node temperature difference parameter, W2(i) represents the node heart rate difference parameter, A(i,j-1) represents the node pet body temperature at the previous time node of the current analysis time node, A(i,j+1) represents the node pet body temperature at the next time node of the current analysis time node, B(i,j-1) represents the node pet heart rate at the previous time node of the current analysis time node, B(i,j+1) represents the node pet heart rate at the next time node of the current analysis time node, i represents the analysis period number, i∈N + , j represents the time node number, j∈N + And j≤Nj, Nj represents the number of nodes, Nj=T×60 / t+1, Nj is rounded down, and T represents the duration of the preset analysis cycle.
[0018] Furthermore, the node analysis module is further provided with a difference statistics unit, which is used to analyze the number of difference nodes according to the node information difference parameter and the node information fluctuation parameter, wherein:
[0019] When W1(i,j)>Q1(i) and W2(i,j)>Q2(i), the difference counting unit takes the current analysis time node as the difference time node, and counts the number of difference time nodes in the current analysis period as the number of difference nodes;
[0020] When W1(i,j)≤Q1(i) or W2(i,j)≤Q2(i), the difference statistics unit does not analyze the number of difference nodes;
[0021] Among them, Q1(i) represents the node temperature fluctuation parameter, and Q2(i) represents the node heart rate fluctuation parameter.
[0022] Furthermore, the node analysis module is further provided with a node analysis unit, which is used to calculate the node association feature through a node analysis formula according to the node information fluctuation parameter, the node information difference parameter and the number of difference nodes. The node analysis unit is provided with a node analysis formula as follows:
[0023] ,
[0024] ,
[0025] ,
[0026] Where D(i) represents the node association feature, w1(i,j) represents the first body temperature parameter, and W1(i,j) min Represents the minimum value of the node temperature difference parameter, W1(i,j) max represents the maximum value of the node temperature difference parameter, w2(i,j) represents the first heart rate parameter, W2(i,j) min Represents the minimum value of the node heart rate difference parameter, W2(i,j) max It represents the maximum value of the node heart rate difference parameter, and NQ(i) represents the number of difference nodes.
[0027] Furthermore, the cycle analysis module is provided with a change analysis unit, which is used to calculate the motion-related parameters according to the cycle motion steps and the pet information through a change analysis formula, and the change analysis unit is provided with a change analysis formula as follows:
[0028] R(i)=[a(i)+b(i)]×lg[S(i)+1];
[0029] Among them, R(i) represents the motion association parameter, S(i) represents the number of periodic motion steps;
[0030] The cycle analysis module is further provided with a first cycle analysis unit, which is used to calculate the cycle correlation feature according to the pet information through a first cycle analysis formula. The first cycle analysis unit is provided with a first cycle analysis formula as follows:
[0031] ,
[0032] Among them, F1(i) represents the period correlation parameter, c(i) represents the pet information mean parameter, c(i)=a(i)+b(i), c(i-1) represents the pet information mean parameter of the previous analysis period, and imax represents the maximum value of the analysis period number.
[0033] Furthermore, the cycle analysis module is further provided with a second cycle analysis unit, which is used to calculate the cycle fluctuation parameter according to the pet information through a second cycle analysis formula, and the second cycle analysis unit is provided with a second cycle analysis formula as follows:
[0034] ,
[0035] Among them, F2 represents the periodic fluctuation parameter.
[0036] Furthermore, the cluster analysis module is provided with a period clustering unit, which is used to analyze the period clustering according to the adjacent period distance and the period fluctuation parameter, wherein:
[0037] When X2(i)≤F2, the period clustering unit groups the period clusters of the current analysis period and the previous analysis period into the same period cluster, and sets the period cluster to U k ;
[0038] When X2(i)>F2, the period clustering unit sets the period cluster of the current analysis period to U k+1 ;
[0039] Among them, U k represents the periodic cluster, k represents the periodic cluster number, U k+1 represents a newly created cycle cluster that is different from the previous analysis cycle, and X2(i) represents the distance between adjacent cycles.
[0040] Furthermore, the cluster analysis module is further provided with a cluster analysis unit, which is used to calculate cluster comparison parameters according to node association characteristics, pet information mean parameters and node information fluctuation parameters through a cluster analysis formula, and the cluster analysis unit is provided with a cluster comparison formula as follows:
[0041] G(i)=[Q1(i)+Q2(i)]×c(i) / D(i);
[0042] Where G(i) represents the cluster alignment parameter;
[0043] The cluster analysis module is further provided with a cluster adjustment unit, which is used to adjust the analysis process of cluster comparison parameters according to periodic clustering, wherein;
[0044] When NUk(i)>Nj, the cluster adjustment unit adjusts the analysis process of the cluster alignment parameter, and the adjusted cluster alignment parameter is G1(i), and G1(i)=G(i)×g is set;
[0045] When NUk(i)≤Nj, the cluster adjustment unit does not adjust the analysis process of the cluster comparison parameters;
[0046] Among them, NUk(i) represents the number of time nodes in the period cluster corresponding to the current analysis period, g represents the period adjustment parameter, and setting ;
[0047] The cluster analysis module is also provided with a cluster optimization unit, which is used to optimize the adjustment process of cluster comparison parameters according to the periodic correlation characteristics, wherein:
[0048] When F1(i)≤f, the cluster optimization unit determines that the periodic correlation feature meets the threshold value and does not optimize the adjustment process of the cluster comparison parameters;
[0049] When F1(i)>f, the cluster optimization unit determines that the periodic correlation feature does not meet the threshold, optimizes the adjustment process of the cluster comparison parameter, and the optimized cluster comparison parameter is G2(i);
[0050] Wherein, f represents the periodic correlation comparison threshold;
[0051] The cluster analysis module is further provided with a node clustering unit, which is used to analyze node clustering according to the adjacent node distance and cluster comparison parameters, wherein:
[0052] When any X1(i,j)≤G(i), the node clustering unit sets the pet information of each node in the current analysis period to the same node cluster, and sets the node cluster to V;
[0053] When X1(i,j)>G(i), the node clustering unit increases the clustering comparison parameter, the increased clustering comparison parameter is G(i)', G(i)'=G(i)×α, and the node clustering analysis process is iterated;
[0054] Among them, α represents the clustering increase parameter, and X1(i,j) represents the distance between adjacent nodes;
[0055] The cluster analysis module is also provided with a feature analysis unit, which is used to analyze cluster features according to node clustering and period clustering, set the cluster features to H(i), and set H(i)=[c(i),G(i)].
[0056] Furthermore, the cluster comparison module calculates cluster similarity according to cluster features through a similarity analysis formula, and the cluster comparison module is provided with a similarity analysis formula as follows:
[0057] Z(i,n)=[c(i) / c(n)+G(i) / G(n)] / 2;
[0058] Among them, Z(i,n) represents the cluster similarity, n represents the number of the non-current analysis period, and n∈N + And n≠i, H(n)=[c(n),G(n)], H(n) represents the clustering features of the non-current analysis period.
[0059] Furthermore, the storage management module manages the storage of pet information according to clustering characteristics and clustering similarity, wherein:
[0060] When Z(i,n)≥z exists, the storage management module merges and stores the pet information of the current analysis period with the pet information of the analysis period numbered n;
[0061] When any Z(i,n)<z, the storage management module independently stores the pet information of the current analysis period;
[0062] Where z represents the similarity threshold.
[0063] Compared with the prior art, the beneficial effect of the present invention lies in that, through the periodic acquisition of pet information by the information acquisition module and the processing and analysis of pet information by other modules, clustering feature analysis of pet information can be realized, and pet information can be merged and stored according to the clustering features of the pet information, thereby improving the system's analysis efficiency of pet information and improving the accuracy of the system's classified storage of pet information. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] Figure 1 Schematic diagram of the structure of the pet information processing system based on the Internet of Things in this embodiment.
[0065] Figure 2 Schematic diagram of the structure of the node analysis module of this embodiment.
[0066] Figure 3 Schematic diagram of the structure of the periodic analysis module of this embodiment.
[0067] Figure 4 Schematic diagram of the structure of the cluster analysis module of this embodiment. DETAILED DESCRIPTION
[0068] 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.
[0069] 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.
[0070] In addition, 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 it can be indirectly connected 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.
[0071] See also Figure 1 As shown, this is a pet information processing system based on the Internet of Things in this embodiment, including:
[0072] An information acquisition module is used to periodically acquire pet information, wherein the pet information includes pet body temperature, pet heart rate, and exercise steps, etc. In this embodiment, the setting of the pet information is not specifically limited, and those skilled in the art can freely set it, such as pet blood sugar and pet blood oxygen saturation, etc. The pet information should be set to health data information about the pet. The pet information is acquired by uploading data from a pet monitoring device composed of multiple sensors and a smart chip. The pet information is acquired once per a preset analysis period. In this embodiment, the preset analysis period is 5 minutes. In this embodiment, the setting of the preset analysis period is not specifically limited, and those skilled in the art can freely set it, such as 1 minute, 3 minutes, and 10 minutes, etc. The setting of the preset analysis period should be less than or equal to 30 minutes;
[0073] A node marking module, used to construct a time node according to the pet information, and also used to analyze the node pet information according to the time node and the pet information, wherein the node pet information includes the node pet heart rate and the node pet body temperature, and the node marking module is connected to the information acquisition module;
[0074] A node analysis module, used to analyze the number of different nodes according to the node pet information, and also used to analyze the node association characteristics according to the number of different nodes and the node pet information, the node analysis module is connected to the node marking module;
[0075] A cycle analysis module, used for analyzing the motion-related parameters, cycle-related characteristics and cycle fluctuation parameters according to the pet information, the cycle analysis module being connected to the node marking module;
[0076] A coordinate construction module, used to construct node coordinates according to node pet information, and also used to construct period coordinates according to pet information and motion-related parameters, the coordinate construction module being connected to the period analysis module and the node analysis module;
[0077] A cluster analysis module, used for analyzing cluster comparison parameters according to node association characteristics, period association characteristics and period fluctuation parameters, and for analyzing cluster characteristics according to node coordinates, period coordinates and cluster comparison parameters, the cluster analysis module being connected to the coordinate construction module;
[0078] A cluster comparison module, used for analyzing cluster similarity according to cluster characteristics, the cluster comparison module is connected to the cluster analysis module;
[0079] The storage management module is used to manage the storage of pet information according to cluster characteristics and cluster similarity, and the storage management module is connected to the cluster comparison module.
[0080] Specifically, this embodiment is applied to the cloud data management of pet daily activity information, and the collected pet information is analyzed to achieve cluster analysis of the pet information and optimize the storage of the pet information.
[0081] Specifically, the node marking module in this embodiment marks a time node every t time in each analysis period of the pet information, and corresponds the time node to the pet information in each analysis period one by one to obtain the node pet information, where t represents the node marking parameter, 10≤t≤20. The unit of the node marking parameter is seconds. It can be understood that the value of the node marking parameter is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as the marking of the time node is satisfied. The optimal value of the node marking parameter is: t=15.
[0082] Specifically, in this embodiment, the node marking module is used to analyze the pet information to mark the time nodes, and the time nodes are used to represent the pet data at each time in each analysis cycle, thereby increasing the diversity of the system analysis, thereby improving the system's analysis efficiency of the pet information and improving the accuracy of the system's classification and storage of pet information.
[0083] See also Figure 2 As shown, the node analysis module includes:
[0084] A fluctuation analysis unit, used to analyze node information fluctuation parameters according to node pet information;
[0085] A difference analysis unit, used for analyzing the node information difference parameters according to the node pet information, the difference analysis unit is connected to the fluctuation analysis unit;
[0086] A difference statistics unit, used for analyzing the number of difference nodes according to the node information difference parameter and the node information fluctuation parameter, the difference statistics unit is connected to the difference analysis unit;
[0087] The node analysis unit is used to analyze the node association characteristics according to the node information fluctuation parameter, the node information difference parameter and the number of difference nodes. The node analysis unit is connected to the difference statistics unit.
[0088] Specifically, in this embodiment, the fluctuation analysis unit calculates the node information fluctuation parameter according to the node pet information through the first fluctuation analysis formula. The fluctuation analysis unit is provided with the first fluctuation analysis formula as follows:
[0089] ,
[0090] ,
[0091] ,
[0092] ,
[0093] Among them, Q1(i) represents the node temperature fluctuation parameter, A(i,j) represents the node pet temperature, a(i) represents the node temperature mean, i represents the analysis period number, i∈N + , j represents the time node number, j∈N + And j≤Nj, Nj represents the number of nodes, Nj=T×60 / t+1, Nj is rounded down, T represents the duration of the preset analysis period, Q2(i) represents the node heart rate fluctuation parameter, B(i,j) represents the node pet heart rate, and b(i) represents the node mean heart rate.
[0094] Specifically, in this embodiment, the node pet information is analyzed by the fluctuation analysis unit to analyze the node information fluctuation parameters, and the node information fluctuation parameters are used to represent the fluctuation of the pet information of each node in each analysis cycle, thereby improving the system's analysis efficiency of the pet information and improving the accuracy of the system's classification and storage of pet information.
[0095] Specifically, the difference analysis unit in this embodiment calculates the node information difference parameter according to the node pet information through the difference analysis formula, and the difference analysis unit is provided with the difference analysis formula as follows:
[0096] W1(i,j)=[|A(i,j)-A(i,j-1)|+|A(i,j)-A(i,j+1)|] / 2;
[0097] W2(i,j)=[|B(i,j)-B(i,j-1)|+|B(i,j)-B(i,j+1)|] / 2;
[0098] Among them, W1(i,j) represents the node body temperature difference parameter, W2(i) represents the node heart rate difference parameter, A(i,j-1) represents the node pet body temperature at the time node before the current analysis time node, A(i,j+1) represents the node pet body temperature at the time node after the current analysis time node, B(i,j-1) represents the node pet heart rate at the time node before the current analysis time node, and B(i,j+1) represents the node pet heart rate at the time node after the current analysis time node.
[0099] Specifically, in this embodiment, the difference analysis unit analyzes the node pet information to analyze the node information difference parameters, and the node information difference parameters are used to represent the difference between the data of each time node and the adjacent time nodes within the analysis period, thereby improving the system's analysis efficiency of pet information and improving the accuracy of the system's classification and storage of pet information.
[0100] Specifically, when the difference statistics unit in this embodiment analyzes the node information difference parameter, the value range of the node time number should satisfy 1<j<Nj-1.
[0101] Specifically, the difference statistics unit in this embodiment analyzes the number of difference nodes according to the node information difference parameter and the node information fluctuation parameter, wherein:
[0102] When W1(i,j)>Q1(i) and W2(i,j)>Q2(i), the difference counting unit takes the current analysis time node as the difference time node, and counts the number of difference time nodes in the current analysis period as the number of difference nodes;
[0103] When W1(i,j)≤Q1(i) or W2(i,j)≤Q2(i), the difference statistics unit does not analyze the number of difference nodes.
[0104] Specifically, the node analysis unit in this embodiment calculates the node association feature through a node analysis formula according to the node information fluctuation parameter, the node information difference parameter and the number of difference nodes. The node analysis unit is provided with a node analysis formula as follows:
[0105] ,
[0106] ,
[0107] ,
[0108] Where D(i) represents the node association feature, w1(i,j) represents the first body temperature parameter, and W1(i,j) min Represents the minimum value of the node temperature difference parameter, W1(i,j) max represents the maximum value of the node temperature difference parameter, w2(i,j) represents the first heart rate parameter, W2(i,j) min Represents the minimum value of the node heart rate difference parameter, W2(i,j) max It represents the maximum value of the node heart rate difference parameter, and NQ(i) represents the number of difference nodes.
[0109] Specifically, in this embodiment, the node analysis unit analyzes the node information fluctuation parameters, node information difference parameters and the number of difference nodes to analyze the node association characteristics, and uses the node association characteristics to represent the association characteristics of the pet information of each node within the analysis period, thereby improving the system's analysis efficiency of pet information and improving the accuracy of the system's classification and storage of pet information.
[0110] See also Figure 3 As shown, the cycle analysis module includes:
[0111] A step counting unit is used to analyze the number of periodic motion steps according to the number of motion steps;
[0112] a change analysis unit, used for analyzing the motion-related parameters according to the periodic motion steps and the pet information, the change analysis unit being connected to the step counting unit;
[0113] A first cycle analysis unit, used for analyzing the cycle correlation characteristics according to the pet information, the first cycle analysis unit being connected to the change analysis unit;
[0114] The second cycle analysis unit is used to analyze the cycle fluctuation parameters according to the pet information, and the second cycle analysis unit is connected to the first cycle analysis unit.
[0115] Specifically, the step counting unit described in this embodiment analyzes the periodic motion steps according to the motion steps, sets the periodic motion steps to S(i), and sets S(i)=s(i)-s(i-1); wherein S(i) represents the periodic motion steps, s(i) represents the motion steps, and s(i-1) represents the motion steps in the previous analysis period.
[0116] Specifically, the change analysis unit in this embodiment calculates the motion-related parameters according to the periodic motion steps and the pet information through a change analysis formula, and the change analysis unit is provided with a change analysis formula as follows:
[0117] R(i)=[a(i)+b(i)]×lg[S(i)+1];
[0118] Wherein, R(i) represents the motion association parameter.
[0119] Specifically, in this embodiment, the change analysis unit analyzes the periodic exercise steps and pet information to analyze the motion associated parameters, and uses the motion associated parameters to represent the relationship between the pet's exercise volume and physical condition during the analysis period, thereby improving the system's analysis efficiency of pet information and improving the accuracy of the system's classification and storage of pet information.
[0120] Specifically, in this embodiment, the first cycle analysis unit calculates the cycle correlation feature according to the pet information through the first cycle analysis formula. The first cycle analysis unit is provided with the first cycle analysis formula as follows:
[0121] ,
[0122] Among them, F1(i) represents the period correlation parameter, c(i) represents the pet information mean parameter, c(i)=a(i)+b(i), c(i-1) represents the pet information mean parameter of the previous analysis period, and imax represents the maximum value of the analysis period number.
[0123] Specifically, in this embodiment, the first cycle analysis unit analyzes the pet information to analyze the periodic correlation characteristics, and uses the periodic correlation characteristics to represent the correlation between the pet information in adjacent analysis periods, thereby improving the system's analysis efficiency of the pet information and improving the accuracy of the system's classification and storage of the pet information.
[0124] Specifically, in this embodiment, the second cycle analysis unit calculates the periodic fluctuation parameter according to the pet information through the second cycle analysis formula, and the second cycle analysis unit is provided with the second cycle analysis formula as follows:
[0125] ,
[0126] Among them, F2 represents the periodic fluctuation parameter.
[0127] Specifically, in this embodiment, the pet information is analyzed by the second periodic analysis unit to analyze the periodic fluctuation parameters, and the periodic fluctuation parameters are used to represent the fluctuation of the pet information in each analysis period, thereby improving the system's analysis efficiency of the pet information and improving the accuracy of the system's classification and storage of the pet information.
[0128] Specifically, the coordinate construction module described in this embodiment constructs node coordinates according to the node pet information, and sets the node coordinates to (j, C(i, j)), C(i, j) = A(i, j) + B(i, j), and the coordinate construction module constructs periodic coordinates according to the pet information and motion association parameters, and sets the periodic coordinates to (i, R(i)).
[0129] See also Figure 4 As shown, the cluster analysis module includes:
[0130] A distance analysis unit, used to analyze the distances between adjacent nodes according to the node coordinates, and also used to analyze the distances between adjacent cycles according to the cycle coordinates;
[0131] A cycle clustering unit, used for analyzing the cycle clustering according to the adjacent cycle distance and the cycle fluctuation parameter, the cycle clustering unit is connected to the distance analysis unit;
[0132] A cluster analysis unit, used for analyzing cluster comparison parameters according to node association characteristics, pet information mean parameters and node information fluctuation parameters, the cluster analysis unit being connected to the periodic clustering unit;
[0133] A cluster adjustment unit, used to adjust the analysis process of cluster comparison parameters according to periodic clustering, and the cluster adjustment unit is connected to the cluster analysis unit;
[0134] A cluster optimization unit, used for optimizing the adjustment process of cluster comparison parameters according to periodic correlation characteristics, and the cluster optimization unit is connected to the cluster adjustment unit;
[0135] A node clustering unit, used for analyzing node clustering according to adjacent node distances and cluster comparison parameters, and the node clustering unit is connected to the clustering optimization unit;
[0136] The feature analysis unit is used to analyze clustering features according to node clustering and period clustering, and the feature analysis unit is connected to the node clustering unit.
[0137] Specifically, in this embodiment, the distance analysis unit calculates the distance between adjacent nodes according to the node coordinates through a first distance analysis formula. The distance analysis unit is provided with a first distance analysis formula as follows:
[0138] ,
[0139] Among them, X1(i,j) represents the distance between adjacent nodes.
[0140] Specifically, in this embodiment, the distance analysis unit calculates the adjacent period distances according to the period coordinates by using a second distance analysis formula. The distance analysis unit is provided with a second distance analysis formula as follows:
[0141] ,
[0142] Among them, X2(i) represents the distance between adjacent cycles.
[0143] Specifically, in this embodiment, the distance analysis unit analyzes the node coordinates and period coordinates to analyze the adjacent node distances and adjacent period distances, which respectively represent the coordinate distances of each adjacent numbered data, thereby improving the system's analysis efficiency of pet information and improving the system's accuracy in classifying and storing pet information.
[0144] Specifically, the cycle clustering unit in this embodiment analyzes the cycle clustering according to the adjacent cycle distance and the cycle fluctuation parameter, wherein:
[0145] When X2(i)≤F2, the period clustering unit groups the period clusters of the current analysis period and the previous analysis period into the same period cluster, and sets the period cluster to U k ;
[0146] When X2(i)>F2, the period clustering unit sets the period cluster of the current analysis period to U k+1 ;
[0147] Among them, U k represents the periodic cluster, k represents the periodic cluster number, U k+1 Indicates a newly created period cluster that is different from the previous analysis period.
[0148] Specifically, in this embodiment, the periodic clustering unit analyzes the adjacent periodic distances and periodic fluctuation parameters to analyze the periodic clusters, implement cluster analysis of the pet information of each analysis period, and set adjacent pet information with small differences as the same cluster, thereby improving the system's analysis efficiency of the pet information and improving the accuracy of the system's classification and storage of pet information.
[0149] Specifically, the cluster analysis unit in this embodiment calculates the cluster comparison parameter according to the node association feature, the pet information mean parameter and the node information fluctuation parameter through the cluster analysis formula. The cluster analysis unit is provided with the cluster comparison formula as follows:
[0150] G(i)=[Q1(i)+Q2(i)]×c(i) / D(i);
[0151] Where G(i) represents the cluster alignment parameter.
[0152] Specifically, in this embodiment, the cluster analysis unit analyzes the node association characteristics, pet information mean parameters and node information fluctuation parameters to analyze the cluster comparison parameters, and uses the cluster comparison parameters to represent the maximum fluctuation error of each adjacent time node to limit the cluster analysis of the node pet information, thereby improving the system's analysis efficiency of pet information and improving the accuracy of the system's classification and storage of pet information.
[0153] Specifically, the cluster adjustment unit in this embodiment adjusts the analysis process of the cluster comparison parameters according to periodic clustering, wherein;
[0154] When NUk(i)>Nj, the cluster adjustment unit adjusts the analysis process of the cluster alignment parameter, and the adjusted cluster alignment parameter is G1(i), and G1(i)=G(i)×g is set;
[0155] When NUk(i)≤Nj, the cluster adjustment unit does not adjust the analysis process of the cluster comparison parameters;
[0156] Among them, NUk(i) represents the number of time nodes in the period cluster corresponding to the current analysis period, g represents the period adjustment parameter, and setting .
[0157] Specifically, in this embodiment, the cluster adjustment unit analyzes the periodic clustering to adjust the analysis process of the cluster comparison parameters so that the cluster comparison parameters are related to the cluster to which the current analysis period belongs, thereby increasing the diversity of the system analysis, thereby improving the system's analysis efficiency of pet information and improving the accuracy of the system's classification and storage of pet information.
[0158] Specifically, the cluster optimization unit in this embodiment optimizes the adjustment process of the cluster comparison parameters according to the periodic correlation characteristics, wherein:
[0159] When F1(i)≤f, the cluster optimization unit determines that the periodic correlation feature meets the threshold value and does not optimize the adjustment process of the cluster comparison parameters;
[0160] When F1(i)>f, the cluster optimization unit determines that the periodic correlation feature does not meet the threshold, optimizes the adjustment process of the cluster comparison parameter, and the optimized cluster comparison parameter is G2(i), and G2(i)=G1(i)×F1(i);
[0161] Wherein, f represents the periodic correlation comparison threshold, 1<f≤1.2. It can be understood that the value of the periodic correlation comparison threshold is not specifically limited in this embodiment, and those skilled in the art can freely set it, as long as the clustering comparison parameter adjustment process is optimized. The optimal value of the periodic correlation comparison threshold is: f=1.1.
[0162] Specifically, in this embodiment, the cluster optimization unit analyzes the periodic correlation characteristics to optimize the adjustment process of the cluster comparison parameters, so that the optimized cluster comparison parameters are related to the correlation characteristics of each adjacent period, thereby improving the system's analysis efficiency of pet information and improving the accuracy of the system's classification and storage of pet information.
[0163] Specifically, the node clustering unit in this embodiment analyzes node clustering according to the adjacent node distance and cluster comparison parameters, wherein:
[0164] When any X1(i,j)≤G(i), the node clustering unit sets the pet information of each node in the current analysis period to the same node cluster, and sets the node cluster to V;
[0165] When X1(i,j)>G(i), the node clustering unit increases the clustering comparison parameter, the increased clustering comparison parameter is G(i)', G(i)'=G(i)×α, and the node clustering analysis process is iterated;
[0166] Wherein, α represents the clustering increase parameter, 1<α≤1.1. It is understandable that the value of the clustering increase parameter is not specifically limited in this embodiment, and those skilled in the art can freely set it as long as it satisfies the analysis of node clustering. The optimal value of the clustering increase parameter is: α=1.05.
[0167] Specifically, in this embodiment, the node clustering unit analyzes the distance between adjacent nodes and the clustering comparison parameters to achieve node clustering, thereby improving the system's efficiency in analyzing pet information and improving the accuracy of the system's classification and storage of pet information.
[0168] Specifically, the feature analysis unit in this embodiment analyzes the clustering feature according to the node clustering and the period clustering, sets the clustering feature to H(i), and sets H(i)=[c(i),G(i)].
[0169] Specifically, the cluster comparison module in this embodiment calculates cluster similarity according to cluster features through a similarity analysis formula. The cluster comparison module is provided with a similarity analysis formula as follows:
[0170] Z(i,n)=[c(i) / c(n)+G(i) / G(n)] / 2;
[0171] Among them, Z(i,n) represents the cluster similarity, n represents the number of the non-current analysis period, and n∈N + And n≠i, H(n)=[c(n),G(n)], H(n) represents the clustering features of the non-current analysis period.
[0172] Specifically, the storage management module in this embodiment manages the storage of pet information according to clustering features and clustering similarities, wherein:
[0173] When Z(i,n)≥z exists, the storage management module merges and stores the pet information of the current analysis period with the pet information of the analysis period numbered n;
[0174] When any Z(i,n)<z, the storage management module independently stores the pet information of the current analysis period;
[0175] Wherein, z represents the similarity threshold, 0.95≤z<1. It can be understood that the present embodiment does not specifically limit the value of the similarity threshold, and those skilled in the art can freely set it as long as it satisfies the storage management of pet information. The best value of the similarity threshold is: z=0.98.
[0176] 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. A pet information processing system based on the Internet of Things, It is characterized in that include: An information acquisition module, used to periodically acquire pet information; A node marking module is used to construct a time node according to the pet information, and is also used to analyze the node pet information according to the time node and the pet information; A node analysis module, used to analyze the number of different nodes according to the node pet information, and also used to analyze the node association characteristics according to the number of different nodes and the node pet information; A cycle analysis module is used to analyze motion-related parameters, cycle-related characteristics, and cycle fluctuation parameters based on pet information; A coordinate construction module, used to construct node coordinates according to node pet information, and also used to construct periodic coordinates according to pet information and motion-related parameters; A cluster analysis module, for analyzing cluster comparison parameters according to node association characteristics, period association characteristics and period fluctuation parameters, and for analyzing cluster characteristics according to node coordinates, period coordinates and cluster comparison parameters; Cluster comparison module, used to analyze cluster similarity based on cluster characteristics; A storage management module, used to manage the storage of pet information according to clustering characteristics and clustering similarity; The node analysis module is provided with a difference analysis unit, which is used to calculate the node information difference parameter according to the node pet information through a difference analysis formula. The difference analysis unit is provided with a difference analysis formula as follows: W1(i,j)=[|A(i,j)-A(i,j-1)|+|A(i,j)-A(i,j+1)|] / 2; W2(i,j)=[|B(i,j)-B(i,j-1)|+|B(i,j)-B(i,j+1)|] / 2; Among them, A(i,j) represents the node pet body temperature, B(i,j) represents the node pet heart rate, W1(i,j) represents the node temperature difference parameter, W2(i) represents the node heart rate difference parameter, A(i,j-1) represents the node pet body temperature at the previous time node of the current analysis time node, A(i,j+1) represents the node pet body temperature at the next time node of the current analysis time node, B(i,j-1) represents the node pet heart rate at the previous time node of the current analysis time node, B(i,j+1) represents the node pet heart rate at the next time node of the current analysis time node, i represents the analysis period number, i∈N + , j represents the time node number, j∈N + And j≤Nj, Nj represents the number of nodes, Nj=T×60 / t+1, Nj is rounded down, and T represents the duration of the preset analysis cycle; The node analysis module is also provided with a difference statistics unit, which is used to analyze the number of difference nodes according to the node information difference parameter and the node information fluctuation parameter, wherein: When W1(i,j)>Q1(i) and W2(i,j)>Q2(i), the difference counting unit takes the current analysis time node as the difference time node, and counts the number of difference time nodes in the current analysis period as the number of difference nodes; When W1(i,j)≤Q1(i) or W2(i,j)≤Q2(i), the difference statistics unit does not analyze the number of difference nodes; Among them, Q1(i) represents the node temperature fluctuation parameter, Q2(i) represents the node heart rate fluctuation parameter; The node analysis module is further provided with a node analysis unit, which is used to calculate the node association feature through a node analysis formula according to the node information fluctuation parameter, the node information difference parameter and the number of difference nodes. The node analysis unit is provided with a node analysis formula as follows: , , , Where D(i) represents the node association feature, w1(i,j) represents the first body temperature parameter, and W1(i,j) min Represents the minimum value of the node temperature difference parameter, W1(i,j) max represents the maximum value of the node temperature difference parameter, w2(i,j) represents the first heart rate parameter, W2(i,j) min Represents the minimum value of the node heart rate difference parameter, W2(i,j) max It represents the maximum value of the node heart rate difference parameter, and NQ(i) represents the number of difference nodes.
2. The pet information processing system based on the Internet of Things according to claim 1, It is characterized in that The periodic analysis module is provided with a change analysis unit, which is used to calculate the motion-related parameters according to the periodic motion steps and the pet information through a change analysis formula. The change analysis unit is provided with a change analysis formula as follows: R(i)=[a(i)+b(i)]×lg[S(i)+1]; Among them, R(i) represents the motion association parameter, S(i) represents the number of periodic motion steps; The cycle analysis module is further provided with a first cycle analysis unit, which is used to calculate the cycle correlation feature according to the pet information through a first cycle analysis formula. The first cycle analysis unit is provided with a first cycle analysis formula as follows: , Among them, F1(i) represents the period correlation parameter, c(i) represents the pet information mean parameter, c(i)=a(i)+b(i), c(i-1) represents the pet information mean parameter of the previous analysis period, and imax represents the maximum value of the analysis period number.
3. The pet information processing system based on the Internet of Things according to claim 2, It is characterized in that The cycle analysis module is further provided with a second cycle analysis unit, which is used to calculate the cycle fluctuation parameter according to the pet information through a second cycle analysis formula, and the second cycle analysis unit is provided with a second cycle analysis formula as follows: , Among them, F2 represents the periodic fluctuation parameter.
4. The pet information processing system based on the Internet of Things according to claim 3, It is characterized in that The cluster analysis module is provided with a period clustering unit, which is used to analyze period clustering according to adjacent period distances and period fluctuation parameters, wherein: When X2(i)≤F2, the period clustering unit groups the period clusters of the current analysis period and the previous analysis period into the same period cluster, and sets the period cluster to U k ; When X2(i)>F2, the period clustering unit sets the period cluster of the current analysis period to U k+1 ; Among them, U k represents the periodic cluster, k represents the periodic cluster number, U k+1 represents a newly created cycle cluster that is different from the previous analysis cycle, and X2(i) represents the distance between adjacent cycles.
5. The pet information processing system based on the Internet of Things according to claim 4, It is characterized in that The cluster analysis module is further provided with a cluster analysis unit, which is used to calculate cluster comparison parameters according to node association characteristics, pet information mean parameters and node information fluctuation parameters through a cluster analysis formula. The cluster analysis unit is provided with a cluster comparison formula as follows: G(i)=[Q1(i)+Q2(i)]×c(i) / D(i); Where G(i) represents the cluster alignment parameter; The cluster analysis module is further provided with a cluster adjustment unit, which is used to adjust the analysis process of cluster comparison parameters according to periodic clustering, wherein; When NUk(i)>Nj, the cluster adjustment unit adjusts the analysis process of the cluster alignment parameter, and the adjusted cluster alignment parameter is G1(i), and G1(i)=G(i)×g is set; When NUk(i)≤Nj, the cluster adjustment unit does not adjust the analysis process of the cluster comparison parameters; Among them, NUk(i) represents the number of time nodes in the period cluster corresponding to the current analysis period, g represents the period adjustment parameter, and setting ; The cluster analysis module is also provided with a cluster optimization unit, which is used to optimize the adjustment process of cluster comparison parameters according to the periodic correlation characteristics, wherein: When F1(i)≤f, the cluster optimization unit determines that the periodic correlation feature meets the threshold value and does not optimize the adjustment process of the cluster comparison parameters; When F1(i)>f, the cluster optimization unit determines that the periodic correlation feature does not meet the threshold, optimizes the adjustment process of the cluster comparison parameter, and the optimized cluster comparison parameter is G2(i); Wherein, f represents the periodic correlation comparison threshold; The cluster analysis module is further provided with a node clustering unit, which is used to analyze node clustering according to the adjacent node distance and cluster comparison parameters, wherein: When any X1(i,j)≤G(i), the node clustering unit sets the pet information of each node in the current analysis period to the same node cluster, and sets the node cluster to V; When X1(i,j)>G(i), the node clustering unit increases the clustering comparison parameter, the increased clustering comparison parameter is G(i)', G(i)'=G(i)×α, and the node clustering analysis process is iterated; Among them, α represents the clustering increase parameter, and X1(i,j) represents the distance between adjacent nodes; The cluster analysis module is also provided with a feature analysis unit, which is used to analyze cluster features according to node clustering and period clustering, set the cluster features to H(i), and set H(i)=[c(i),G(i)].
6. The pet information processing system based on the Internet of Things according to claim 5, It is characterized in that The cluster comparison module calculates cluster similarity according to cluster features through a similarity analysis formula. The cluster comparison module is provided with a similarity analysis formula as follows: Z(i,n)=[c(i) / c(n)+G(i) / G(n)] / 2; Among them, Z(i,n) represents the cluster similarity, n represents the number of the non-current analysis period, and n∈N + And n≠i, H(n)=[c(n),G(n)], H(n) represents the clustering features of the non-current analysis period.
7. The pet information processing system based on the Internet of Things according to claim 6, It is characterized in that The storage management module manages the storage of pet information according to clustering features and clustering similarities, wherein: When Z(i,n)≥z exists, the storage management module merges and stores the pet information of the current analysis period with the pet information of the analysis period numbered n; When any Z(i,n)<z, the storage management module independently stores the pet information of the current analysis period; Where z represents the similarity threshold.
Citation Information
Patent Citations
Pet information trusted storage system based on block chain
CN114185997A
Energy management method and platform of integrated energy system
CN117478678A
Systems, apparatus, articles of manufacture, and methods for cross-training and collaborative artificial intelligence for active data management and analysis
CN117642737A
Financial user data security protection method based on block chain
CN117788174A
Data processing system based on edge data center
CN118228186A
