A pet monitoring data processing system
By analyzing pet historical data and network performance in the pet monitoring data processing system and optimizing the data transmission solution, the problems of low processing speed and low transmission efficiency of pet monitoring data are solved, and more efficient data processing and transmission are achieved.
Patent Information
- Application Number
- CN202411194681.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-08-29
AI Technical Summary
The existing pet monitoring data processing system cannot meet the needs of quickly processing pet monitoring data, and there are packet loss and delay problems, which affects the integrity and timeliness of the data.
A pet monitoring data processing system was designed, including data acquisition module, priority analysis module, data monitoring module, performance evaluation module, evaluation optimization module and data processing module. By analyzing pet historical data, network performance and transmission abnormalities, data is optimized. Transfer schemes to improve processing speed and efficiency.
By setting preset thresholds, weights and abnormal coefficients, the accuracy of data processing schemes and abnormality analysis of pet data transmission are improved, the speed and transmission efficiency of pet monitoring data processing are improved, and the performance evaluation and optimization of cloud server network is improved.
Smart Images

Figure CN118714042B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of computer data processing, and in particular to a pet monitoring data processing system. Background Art
[0002] With the rapid development of the pet market, more and more people are beginning to pay attention to the health and safety of their pets. To this end, a variety of pet monitoring devices have appeared on the market to collect pet activity data, health indicators and other information. However, a large amount of monitoring data needs to be processed quickly, but the existing processing system often cannot meet this demand. During the wireless transmission process, data packet loss and delay are serious, affecting the integrity and timeliness of the data.
[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 on 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 writing 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 acquired through the traditional polling method, and is no longer limited by the number of nodes; it can be seen that when the scheme is combing the pet monitoring data, it only analyzes the concurrent execution and merged writing methods of the pet monitoring data collection agents, and there are problems of low processing speed and low transmission efficiency of the pet monitoring data. Summary of the invention
[0004] To this end, the present invention provides a pet monitoring data processing system to overcome the problems of low pet monitoring data processing speed and low transmission efficiency in the prior art.
[0005] To achieve the above-mentioned object, the present invention provides a pet monitoring data processing system, the system comprising: a data acquisition module for acquiring historical data of various categories of pets, data of various categories of pets and cloud server data;
[0006] A priority analysis module is used to analyze the priority of each category of pet data based on the acquired historical data of each category of pets;
[0007] A data monitoring module is used to analyze each category of transmission data according to the analysis results of each category of pet data and each category of pet data priority obtained during the monitoring period, and to analyze the abnormality of pet data transmission according to the analysis results of each category of transmission data during the monitoring period;
[0008] A performance evaluation module is used to evaluate the network performance of the cloud server based on the network delay and network packet loss rate of the cloud server obtained during the management period;
[0009] An evaluation and optimization module is used to optimize the evaluation process of the cloud server network performance according to the response time and error rate of the cloud server obtained during the management cycle;
[0010] The data processing module is used to analyze the processing plan for pet data in the next management period based on the analysis results of the abnormality of pet data transmission in the management period and the evaluation results of the cloud server network performance, and output the processing plan to the user.
[0011] Further, the priority analysis module is provided with a fluctuation analysis unit, an abnormality analysis unit and a priority analysis unit, the fluctuation analysis unit is used to analyze the fluctuation coefficient of the pet historical data according to the acquired pet historical data, and set the fluctuation coefficient of the m-th category pet historical data as Em, the fluctuation analysis unit compares the fluctuation coefficient Em of the m-th category pet historical data with a preset fluctuation threshold E, and analyzes the abnormality of the fluctuation of the m-th category pet historical data according to the comparison result, wherein:
[0012] When Em≤E, the fluctuation analysis unit determines that the fluctuation of the historical data of the m-th category pet is normal;
[0013] When Em>E, the fluctuation analysis unit determines that the volatility of the historical data of the m-th category pet is abnormal;
[0014] Where, m=1,2,3, mi is the ith data in the mth category pet historical data, km is the number of mth category pet historical data, m 均 is the mean of the historical data of the mth category of pets. When m=1, the data category is pet body temperature; when m=2, the data category is pet heart rate; when m=3, the data category is pet respiratory rate.
[0015] Furthermore, the abnormality analysis unit is used to analyze the abnormality of each category of pet historical data according to the acquired pet historical data of each category, wherein:
[0016] When mi≤ym1 or mi≥ym2, the abnormality analysis unit determines that the i-th data in the m-th category of pet historical data is the m-th category of abnormal data;
[0017] When ym1<mi<ym2, the abnormality analysis unit determines that the i-th data in the m-th category of pet historical data is the m-th category of normal data;
[0018] The abnormality analysis unit analyzes the abnormality of each category of pet historical data according to the analysis results of the abnormal data in each category of pet historical data, wherein:
[0019] When my / km≤α, the abnormality analysis unit determines that the historical data of the pet of the mth category is normal;
[0020] When my / km>α, the abnormality analysis unit determines that the historical data of the pet of the mth category is abnormal;
[0021] Among them, ym1 is the first preset threshold of m-category pet data, ym2 is the second preset threshold of m-category pet data, my is the number of abnormal data in the m-category pet historical data, and α is the preset abnormal proportion.
[0022] Furthermore, the priority analysis unit divides the priority of each category of pet data according to the analysis results of the fluctuation abnormality of each category of pet historical data and the analysis results of the abnormality of each category of pet historical data, wherein:
[0023] When the m-th category pet historical data is normal and has normal volatility, the priority analysis unit determines that the priority of the m-th category pet data is level one;
[0024] When the historical data of the m-th category pet is normal and the volatility is abnormal, if x2×(Em-E) / E≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x2×(Em-E) / E>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3;
[0025] When the historical data of the m-th category pet is abnormal and the volatility is normal, if x1×ln(1+my / km-α)≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x1×ln(1+my / km-α)>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3;
[0026] When the historical data of the m-th category pet is abnormal and has abnormal volatility, if x1×ln(1+my / km-α)+x2×(Em-E) / E≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x1×ln(1+my / km-α)+x2×(Em-E) / E>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3;
[0027] Among them, x1 is the volatility weight, x2 is the anomaly weight, and u is the preset anomaly coefficient.
[0028] Furthermore, the data monitoring module analyzes the abnormality of each category of pet data based on each category of pet data acquired during the monitoring period, wherein:
[0029] When 2×(ym1-mj) / (ym1+ym2)≥Pmz or 2×(mj-ym2) / (ym1+ym2)≥Pmz, the data monitoring module determines that the jth data in the mth category pet data of the current monitoring period is abnormal, and transmits it as the mth category data;
[0030] When 2×(ym1-mj) / (ym1+ym2)≤Pmz and 2×(mj-ym2) / (ym1+ym2)≤Pmz, the data monitoring module determines that the jth data in the mth category pet data of the current monitoring period is normal and does not regard it as the mth category transmission data;
[0031] Wherein, mj is the jth data in the mth category pet data in the current monitoring period, Pmz is the preset abnormal proportion of the mth category pet data, z=1,2,3; when the priority of the mth category pet data is level one, z=1, when the priority of the mth category pet data is level two, z=2, Pm2=Pm1×(1-β), when the priority of the mth category pet data is level three, z=3, Pm3=pm2×(1-β), β is the preset adjustment coefficient, 0<β<0.2;
[0032] The data monitoring module analyzes the abnormality of pet data transmission according to the analysis results of each category of transmission data within the monitoring period, wherein:
[0033] when When the data monitoring module determines that the pet data transmission in the current monitoring period is normal;
[0034] when When the data monitoring module determines that the pet data transmission in the current monitoring period is abnormal;
[0035] Among them, Rm is the number of m-category transmission data within the monitoring period, Tm is the number of m-category pet data within the monitoring period, W is the number of pet data categories, and yc is the preset transmission anomaly coefficient.
[0036] Furthermore, the performance evaluation module compares the cloud server network delay s0 obtained during the management period with the preset delay s1, and analyzes the network delay index according to the comparison result, wherein:
[0037] When s0≤s1, the performance evaluation module determines that the network delay in the current management period is normal, and sets the network delay index to N1, setting N1=0;
[0038] When s0>s1, the performance evaluation module determines that the network delay in the current management period is abnormal, and sets the network delay index to N2, setting N2=sin[(s0-s1) / (s0+s1)];
[0039] The performance evaluation module compares the network packet loss rate d0 obtained during the management period with the preset packet loss rate d1, and analyzes the network packet loss index according to the comparison result, wherein:
[0040] When d0≤d1, the performance evaluation module determines that the network packet loss rate of the current management period is normal, and sets the network packet loss index to L1, setting L1=0;
[0041] When d0>d1, the performance evaluation module determines that the network packet loss rate of the current management period is abnormal, and sets the network packet loss index to L2, setting L2=arctan[(d0-d1) / (d0+d1)×(π / 4)];
[0042] The performance evaluation module evaluates the network performance of the cloud server according to the analysis results of the network delay index and the network packet loss index within the management period, wherein:
[0043] When w1×Nn+w2×Lt≤M, the performance evaluation module determines that the network performance of the cloud server in the current management period is normal;
[0044] When w1×Nn+w2×Lt>M, the performance evaluation module determines that the network performance of the cloud server in the current management period is abnormal;
[0045] Among them, Nn is the analysis result of the network delay index, n=1,2; Lt is the analysis result of the network packet loss index, t=1,2; M is the preset performance coefficient, w1 is the delay weight, and w2 is the packet loss weight.
[0046] Furthermore, the evaluation and optimization module is provided with a first optimization unit and a second optimization unit, wherein the first optimization unit is used to compare the cloud server response time xy0 obtained during the management period with the preset response time xy1, and optimize the evaluation process of the cloud server network performance once according to the comparison result, wherein:
[0047] When xy0≤xy1, the first optimization unit determines that the response time of the cloud server in the current management period is normal and does not perform optimization;
[0048] When xy0>xy1, the first optimization unit determines that the response time of the cloud server in the current management period is abnormal, and optimizes the evaluation process of the cloud server network performance, and sets the optimized preset performance coefficient to M', setting:
[0049] M'=M×exp[-(xy0-xy1) / (xy0+xy1)].
[0050] Furthermore, the second optimization unit compares the cloud server error rate cw0 obtained during the management period with the preset error rate cw1, and performs secondary optimization on the evaluation process of the cloud server network performance according to the comparison result, wherein:
[0051] When cw0≤cw1, the second optimization unit determines that the cloud server error rate in the current management period is normal and does not perform optimization;
[0052] When cw0>cw1, the second optimization unit determines that the cloud server error rate in the current management period is abnormal, and performs secondary optimization on the evaluation process of the cloud server network performance, and sets the optimized preset response time as xy1', setting:
[0053] xy1'=xy1×{1+exp[3×(cw0-cw1) / (cw0+cw1)-3]}.
[0054] Furthermore, the data processing module is provided with a cache processing unit and a transmission processing unit, and the cache processing unit is used to analyze the local cache size of the pet data in the next management period according to the evaluation result of the cloud server network performance in the management period, wherein:
[0055] If the network performance of the cloud server in the current management period is normal, the cache processing unit sets the local cache size of the pet data in the next management period to G1, and sets G1=g0;
[0056] If the network performance of the cloud server in the current management period is abnormal, the cache processing unit sets the local cache size of the pet data in the next management period to G2, and sets G2=g0×{1+{{exp[sin(w1×Nn+w2×Lt-M)]}-1} / 3};
[0057] Among them, g0 is the preset cache size.
[0058] Furthermore, the transmission processing unit analyzes the transmission interval of the data transmitted in the next management period according to the analysis results of the abnormality of pet data transmission in the management period and the evaluation results of the cloud server network performance, wherein:
[0059] If the network performance of the cloud server in the current management period is normal, the transmission processing unit sets the transmission interval of the data to be transmitted in the next management period to F1, and sets F1=f0;
[0060] If the network performance of the cloud server in the current management period is abnormal, when h0 / h1≤q1, the transmission processing unit sets the transmission interval of the data transmitted in the next management period to F2, and sets F2=f0×[1+γ×(w1×Nn+w2×Lt-M)]; when h0 / h1>q1, the transmission processing unit sets the transmission interval of the data transmitted in the next management period to F3, and sets F3=f0×{1+γ×[1-(h0 / h1-q1) / (q1+h0 / h1)]×(w1×Nn+w2×Lt-M)};
[0061] Among them, f0 is the preset transmission interval, h0 is the number of monitoring periods of abnormal pet data transmission within the management period, h1 is the number of monitoring periods within the management period, q1 is the preset transmission anomaly ratio, and γ is the preset correction coefficient.
[0062] Compared with the prior art, the beneficial effects of the present invention are that the priority analysis module improves the accuracy of abnormality analysis of pet historical data fluctuations by setting a preset fluctuation threshold, improves the accuracy of abnormality analysis of pet historical data by setting a preset abnormality ratio, a first preset threshold and a second preset threshold, and improves the accuracy of priority analysis of each category of pet data by setting fluctuation weights, abnormality weights and preset abnormality coefficients. The data monitoring module improves the accuracy of abnormality analysis of pet data transmission by setting a preset abnormality ratio, a preset adjustment coefficient and a preset transmission abnormality coefficient, thereby improving the accuracy of pet data processing solution analysis. The performance evaluation module improves the accuracy of abnormality analysis of pet historical data fluctuations by setting a preset abnormality ratio, a preset adjustment coefficient and a preset transmission abnormality coefficient. The packet loss rate, delay weight, packet loss weight and preset performance coefficient are used to improve the accuracy of the cloud server network performance evaluation. The evaluation optimization module sets a preset response time to reduce the impact of the cloud server response time on the cloud server network performance evaluation process, and sets a preset error rate to reduce the impact of excessive cloud server error rate on the cloud server network performance evaluation process, thereby improving the accuracy of the cloud server network performance evaluation. The data processing module sets a preset cache size to improve the accuracy of the pet data processing solution analysis, and sets a preset transmission interval and a preset correction coefficient to improve the accuracy of the pet data processing solution analysis, thereby improving the pet monitoring data processing speed and transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] Figure 1 Schematic diagram of the pet monitoring data processing system of this embodiment.
[0064] Figure 2 Schematic diagram of the structure of the priority analysis module in this embodiment.
[0065] Figure 3 This is a schematic diagram of the structure of the evaluation and optimization module of this embodiment.
[0066] Figure 4 Schematic diagram of the structure of the data processing module of this embodiment. DETAILED DESCRIPTION
[0067] 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.
[0068] 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.
[0069] 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.
[0070] See also Figure 1 As shown, it is a structural diagram of the pet monitoring data processing system of this embodiment, and the system includes:
[0071] A data acquisition module is used to acquire various categories of pet historical data, various categories of pet data and cloud server data, wherein the various categories of pet historical data include pet heart rate historical data, pet body temperature historical data and pet respiratory rate historical data, and the various categories of pet data include pet heart rate data, pet temperature data and pet respiratory rate data; the cloud server data includes cloud server network delay, cloud server error rate, cloud server response time and cloud server network packet loss rate, wherein the cloud server error rate is the proportion of errors or anomalies that occur in the cloud server during the request processing process, and the cloud server network packet loss rate is the number of data packets that fail to be successfully transmitted in the network data packets sent or received by the cloud server within a certain period of time. ratio; In this embodiment, no specific limitation is made on the acquisition method of each category of pet historical data, each category of pet data and cloud server data, and those skilled in the art can freely set it, as long as the acquisition requirements of each category of pet historical data, each category of pet data and cloud server data are met, wherein each category of pet historical data can be obtained through interaction, and each category of pet data can be obtained through the built-in sensor of the pet wearable device, such as body temperature can be obtained through the temperature sensor, heart rate and respiratory rate can be obtained through the piezoelectric sensor, and the cloud server data can be obtained through the LoadRunner performance testing software; In this embodiment, no specific limitation is made on the setting of the pet data category, and those skilled in the art can also add other factors such as location, etc.;
[0072] A priority analysis module, used for analyzing the priority of each category of pet data according to the acquired historical data of each category of pets, the priority analysis module being connected to the data acquisition module;
[0073] The data monitoring module is used to analyze the transmission data of each category according to the analysis results of the pet data of each category and the priority of each category of pet data obtained during the monitoring period, and analyze the abnormality of the pet data transmission according to the analysis results of the transmission data of each category during the monitoring period. The data monitoring module is connected to the priority analysis module. In this embodiment, the setting of the monitoring period is not specifically limited, and those skilled in the art can freely set it as long as the setting requirements of the monitoring period are met. Among them, the monitoring period can be set to 30 minutes, 40 minutes, etc.
[0074] A performance evaluation module is used to evaluate the network performance of the cloud server according to the network delay and network packet loss rate of the cloud server obtained within the management period, and the performance evaluation module is connected to the data acquisition module; the network delay of the cloud server obtained within the management period in this embodiment is the average value of the network delay of the cloud server within the management period; in this embodiment, the setting of the management period is not specifically limited, and those skilled in the art can freely set it, as long as the setting requirements of the management period are met, wherein the management period can be set to 15 days, 20 days, etc.;
[0075] An evaluation and optimization module, used to optimize the evaluation process of the cloud server network performance according to the response time and error rate of the cloud server obtained during the management period, and the evaluation and optimization module is connected to the performance evaluation module; in this embodiment, the response time of the cloud server obtained during the management period is the average value of the response time of the cloud server during the management period;
[0076] The data processing module is used to analyze the processing plan for pet data in the next management period based on the analysis results of the abnormality of pet data transmission within the management period and the evaluation results of the cloud server network performance, and output the processing plan to the user. The data processing module is connected to the data monitoring module and the evaluation and optimization module.
[0077] Specifically, the pet monitoring data processing system described in this embodiment is applied to the cloud server of the pet data monitoring system. It analyzes the priority of each category of pet data and incrementally transmits the data based on the analysis results. It analyzes the pet data processing scheme in combination with the abnormalities of pet data transmission and the cloud server performance evaluation results, thereby improving the processing speed and transmission efficiency of pet monitoring data.
[0078] Specifically, the data monitoring module analyzes the abnormality of each category of pet data based on each category of pet data acquired during the monitoring period, wherein:
[0079] When 2×(ym1-mj) / (ym1+ym2)≥Pmz or 2×(mj-ym2) / (ym1+ym2)≥Pmz, the data monitoring module determines that the jth data in the mth category pet data of the current monitoring period is abnormal, and transmits it as the mth category data;
[0080] When 2×(ym1-mj) / (ym1+ym2)≤Pmz and 2×(mj-ym2) / (ym1+ym2)≤Pmz, the data monitoring module determines that the jth data in the mth category pet data of the current monitoring period is normal and does not regard it as the mth category transmission data;
[0081] Wherein, mj is the jth data in the mth category pet data in the current monitoring period, Pmz is the preset abnormal proportion of the mth category pet data, z=1,2,3; when the priority of the mth category pet data is level one, z=1, when the priority of the mth category pet data is level two, z=2, Pm2=Pm1×(1-β), when the priority of the mth category pet data is level three, z=3, Pm3=pm2×(1-β), β is the preset adjustment coefficient, 0<β<0.2;
[0082] The data monitoring module analyzes the abnormality of pet data transmission according to the analysis results of each category of transmission data within the monitoring period, wherein:
[0083] when When the data monitoring module determines that the pet data transmission in the current monitoring period is normal;
[0084] when When the data monitoring module determines that the pet data transmission in the current monitoring period is abnormal;
[0085] Among them, Rm is the number of m-category transmission data within the monitoring period, Tm is the number of m-category pet data within the monitoring period, W is the number of pet data categories, and yc is the preset transmission anomaly coefficient.
[0086] Specifically, the data monitoring module improves the accuracy of pet data transmission abnormality analysis by setting a preset abnormality ratio, a preset adjustment coefficient and a preset transmission abnormality coefficient, thereby improving the accuracy of pet data processing scheme analysis, and ultimately improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of the preset abnormality ratio, the preset adjustment coefficient and the preset transmission abnormality coefficient, and those skilled in the art can set them freely, as long as the setting requirements of the preset abnormality ratio, the preset adjustment coefficient and the preset transmission abnormality coefficient are met, among which the optimal value of β is 0.12, the optimal value of yc is 0.36, when m=1, the optimal value of the preset abnormality ratio is 0.022, when m=2, the optimal value of the preset abnormality ratio is 0.08, and when m=3, the optimal value of the preset abnormality coefficient is 0.05.
[0087] Specifically, the performance evaluation module compares the cloud server network delay s0 obtained during the management period with the preset delay s1, and analyzes the network delay index according to the comparison result, where:
[0088] When s0≤s1, the performance evaluation module determines that the network delay in the current management period is normal, and sets the network delay index to N1, setting N1=0;
[0089] When s0>s1, the performance evaluation module determines that the network delay in the current management period is abnormal, and sets the network delay index to N2, setting N2=sin[(s0-s1) / (s0+s1)];
[0090] The performance evaluation module compares the network packet loss rate d0 obtained during the management period with the preset packet loss rate d1, and analyzes the network packet loss index according to the comparison result, wherein:
[0091] When d0≤d1, the performance evaluation module determines that the network packet loss rate of the current management period is normal, and sets the network packet loss index to L1, setting L1=0;
[0092] When d0>d1, the performance evaluation module determines that the network packet loss rate of the current management period is abnormal, and sets the network packet loss index to L2, setting L2=arctan[(d0-d1) / (d0+d1)×(π / 4)];
[0093] The performance evaluation module evaluates the network performance of the cloud server according to the analysis results of the network delay index and the network packet loss index within the management period, wherein:
[0094] When w1×Nn+w2×Lt≤M, the performance evaluation module determines that the network performance of the cloud server in the current management period is normal;
[0095] When w1×Nn+w2×Lt>M, the performance evaluation module determines that the network performance of the cloud server in the current management period is abnormal;
[0096] Among them, Nn is the analysis result of the network delay index, n=1,2; Lt is the analysis result of the network packet loss index, t=1,2; M is the preset performance coefficient, w1 is the delay weight, w2 is the packet loss weight, w1+w2=1, w1<w2.
[0097] Specifically, the performance evaluation module improves the accuracy of the cloud server network performance evaluation by setting a preset delay, a preset packet loss rate, a delay weight, a packet loss weight and a preset performance coefficient, thereby improving the accuracy of the pet data processing solution analysis, and ultimately improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of the preset delay, the preset packet loss rate, the delay weight, the packet loss weight and the preset performance coefficient, and technical personnel in this field can set them freely, as long as they meet the setting requirements of the preset delay, the preset packet loss rate, the delay weight, the packet loss weight and the preset performance coefficient, among which the optimal value of s1 is 50 milliseconds, the optimal value of d1 is 0.02, the optimal value of w1 is 0.36, the optimal value of w2 is 0.64, and the optimal value of M is 0.2.
[0098] See also Figure 2 As shown, it is a schematic diagram of the structure of the priority analysis module of this embodiment, and the priority analysis module includes:
[0099] A fluctuation analysis unit, used to analyze the fluctuation abnormality of the pet historical data based on the acquired pet historical data of each category;
[0100] An abnormality analysis unit, used for analyzing abnormal data of each category of pet historical data according to the acquired historical data of each category of pets;
[0101] The priority analysis unit is used to prioritize the pet data of each category according to the analysis results of the fluctuation anomaly of each category of pet historical data and the analysis results of the anomaly of each category of pet historical data. The priority analysis unit is connected to the fluctuation analysis unit and the anomaly analysis unit.
[0102] Specifically, the fluctuation analysis unit analyzes the fluctuation coefficient of the pet historical data according to the acquired pet historical data, and the fluctuation analysis unit sets the fluctuation coefficient of the m-th category pet historical data as Em, and sets ,
[0103] The fluctuation analysis unit compares the fluctuation coefficient Em of the m-th category pet historical data with the preset fluctuation threshold E, and analyzes the abnormality of the fluctuation of the m-th category pet historical data according to the comparison result, wherein:
[0104] When Em≤E, the fluctuation analysis unit determines that the fluctuation of the historical data of the m-th category pet is normal;
[0105] When Em>E, the fluctuation analysis unit determines that the volatility of the historical data of the m-th category pet is abnormal;
[0106] Where, m=1,2,3, mi is the ith data in the mth category pet historical data, km is the number of mth category pet historical data, m 均 is the mean of the historical data of the mth category of pets, When m=1, the data category is pet body temperature; when m=2, the data category is pet heart rate; when m=3, the data category is pet respiratory rate.
[0107] Specifically, the fluctuation analysis unit improves the accuracy of the fluctuation abnormality analysis of the pet historical data by setting a preset fluctuation threshold, thereby improving the accuracy of the priority analysis of each category of pet data, thereby improving the accuracy of the pet data processing scheme analysis, and ultimately improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of the preset fluctuation threshold, and technical personnel in this field can set it freely, as long as the setting requirements of the preset fluctuation threshold are met, where the optimal value of E is 0.2.
[0108] Specifically, the abnormality analysis unit analyzes the abnormality of each category of pet historical data based on the acquired pet historical data of each category, wherein:
[0109] When mi≤ym1 or mi≥ym2, the abnormality analysis unit determines that the i-th data in the m-th category of pet historical data is the m-th category of abnormal data;
[0110] When ym1<mi<ym2, the abnormality analysis unit determines that the i-th data in the m-th category of pet historical data is the m-th category of normal data;
[0111] The abnormality analysis unit analyzes the abnormality of each category of pet historical data according to the analysis results of the abnormal data in each category of pet historical data, wherein:
[0112] When my / km≤α, the abnormality analysis unit determines that the historical data of the pet of the mth category is normal;
[0113] When my / km>α, the abnormality analysis unit determines that the historical data of the pet of the mth category is abnormal;
[0114] Among them, ym1 is the first preset threshold of m-category pet data, ym2 is the second preset threshold of m-category pet data, my is the number of abnormal data in the m-category pet historical data, and α is the preset abnormal proportion.
[0115] Specifically, the abnormality analysis unit improves the accuracy of abnormality analysis of pet historical data by setting a preset abnormality ratio, a first preset threshold and a second preset threshold, thereby improving the accuracy of priority analysis of each category of pet data, thereby improving the accuracy of pet data processing scheme analysis, and ultimately improving the processing speed and transmission efficiency of pet monitoring data; in this embodiment, there is no specific limitation on the setting of the preset abnormality ratio, the first preset threshold and the second preset threshold, and technical personnel in this field can set them freely, as long as the setting requirements of the preset abnormality ratio, the first preset threshold and the second preset threshold are met. Among them, when the pet type is dog, when m=1, the optimal value of the first preset threshold is 38.0℃, and the optimal value of the second preset threshold is 39℃. When m=2, the optimal value of the first preset threshold is 80 times / minute, and the optimal value of the second preset threshold is 120 times / minute. When m=3, the optimal value of the first preset threshold is 12 times / minute, and the optimal value of the second preset threshold is 30 times / minute. The optimal value of α is 0.16.
[0116] Specifically, the priority analysis unit divides the priority of each category of pet data according to the analysis results of the fluctuation abnormality of each category of pet historical data and the analysis results of the abnormality of each category of pet historical data, wherein:
[0117] When the m-th category pet historical data is normal and has normal volatility, the priority analysis unit determines that the priority of the m-th category pet data is level one;
[0118] When the historical data of the m-th category pet is normal and the volatility is abnormal, if x2×(Em-E) / E≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x2×(Em-E) / E>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3;
[0119] When the historical data of the m-th category pet is abnormal and the volatility is normal, if x1×ln(1+my / km-α)≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x1×ln(1+my / km-α)>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3;
[0120] When the historical data of the m-th category pet is abnormal and has abnormal volatility, if x1×ln(1+my / km-α)+x2×(Em-E) / E≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x1×ln(1+my / km-α)+x2×(Em-E) / E>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3;
[0121] Among them, x1 is the volatility weight, x2 is the anomaly weight, u is the preset anomaly coefficient, x1+x2=1, x1>x2.
[0122] Specifically, the priority analysis unit improves the accuracy of priority analysis of each category of pet data by setting fluctuation weights, abnormal weights and preset abnormal coefficients, thereby improving the accuracy of pet data processing solution analysis, and ultimately improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of fluctuation weights, abnormal weights and preset abnormal coefficients, and technical personnel in this field can set them freely, as long as the setting requirements of fluctuation weights, abnormal weights and preset abnormal coefficients are met, among which the optimal value of x1 is 0.6, the optimal value of x2 is 0.4, and the optimal value of u is 0.23; the priority of pet data described in this embodiment is a level of transmission data analysis, and the higher the priority, the higher the threshold for incremental data transmission.
[0123] See also Figure 3 As shown, it is a schematic diagram of the structure of the evaluation and optimization module of this embodiment, and the evaluation and optimization module includes:
[0124] A first optimization unit is used to optimize the evaluation process of the cloud server network performance according to the cloud server response time obtained during the management period;
[0125] The second optimization unit is used to perform secondary optimization on the evaluation process of the cloud server network performance according to the cloud server error rate obtained during the management period, and the second optimization unit is connected to the first optimization unit.
[0126] Specifically, the first optimization unit compares the cloud server response time xy0 obtained during the management period with the preset response time xy1, and optimizes the evaluation process of the cloud server network performance according to the comparison result, wherein:
[0127] When xy0≤xy1, the first optimization unit determines that the response time of the cloud server in the current management period is normal and does not perform optimization;
[0128] When xy0>xy1, the first optimization unit determines that the response time of the cloud server in the current management period is abnormal, and optimizes the evaluation process of the cloud server network performance, and sets the optimized preset performance coefficient to M', setting:
[0129] M'=M×exp[-(xy0-xy1) / (xy0+xy1)].
[0130] Specifically, the first optimization unit reduces the impact of the cloud server response time on the cloud server network performance evaluation process by setting a preset response time, thereby improving the accuracy of the cloud server network performance evaluation, thereby improving the accuracy of the pet data processing solution analysis, and ultimately improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of the preset response time, and technical personnel in this field can set it freely as long as the setting requirements of the preset response time are met, where the optimal value of xy1 is 100 milliseconds.
[0131] Specifically, the second optimization unit compares the cloud server error rate cw0 obtained during the management period with the preset error rate cw1, and performs secondary optimization on the evaluation process of the cloud server network performance according to the comparison result, wherein:
[0132] When cw0≤cw1, the second optimization unit determines that the cloud server error rate in the current management period is normal and does not perform optimization;
[0133] When cw0>cw1, the second optimization unit determines that the cloud server error rate in the current management period is abnormal, and performs secondary optimization on the evaluation process of the cloud server network performance, and sets the optimized preset response time as xy1', setting:
[0134] xy1'=xy1×{1+exp[3×(cw0-cw1) / (cw0+cw1)-3]}.
[0135] Specifically, the second optimization unit reduces the impact of the excessively high error rate of the cloud server on the cloud server network performance evaluation process by setting a preset error rate, thereby improving the accuracy of the cloud server network performance evaluation, thereby improving the accuracy of the pet data processing solution analysis, and ultimately improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of the preset error rate, and technical personnel in this field can set it freely, as long as the setting requirements of the preset error rate are met, where the optimal value of cw1 is 0.01.
[0136] See also Figure 4 As shown, it is a schematic diagram of the structure of the data processing module of this embodiment, and the data processing module includes:
[0137] A cache processing unit, used to analyze the local cache size of pet data in the next management period according to the evaluation result of the cloud server network performance in the management period;
[0138] A transmission processing unit, used for analyzing the transmission interval of the data to be transmitted in the next management period according to the analysis result of the abnormality of the pet data transmission in the management period and the evaluation result of the network performance of the cloud server, and the transmission processing unit is connected to the cache processing unit;
[0139] The output unit is used to output the analysis result of the local cache size of the pet data in the next management period and the analysis result of the transmission interval as a processing solution for the pet data to the user, and the output unit is connected to the transmission processing unit.
[0140] Specifically, the cache processing unit analyzes the local cache size of the pet data in the next management period according to the evaluation result of the cloud server network performance in the management period, wherein:
[0141] If the network performance of the cloud server in the current management period is normal, the cache processing unit sets the local cache size of the pet data in the next management period to G1, and sets G1=g0;
[0142] If the network performance of the cloud server in the current management period is abnormal, the cache processing unit sets the local cache size of the pet data in the next management period to G2, and sets G2=g0×{1+{{exp[sin(w1×Nn+w2×Lt-M)]}-1} / 3};
[0143] Among them, g0 is the preset cache size.
[0144] Specifically, the cache processing unit improves the accuracy of the pet data processing solution analysis by setting a preset cache size, thereby ultimately improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of the preset cache size, and technical personnel in this field can set it freely, as long as the setting requirements of the preset cache size are met, where the optimal value of g0 is 100MB; the local cache described in this embodiment is to temporarily store the most recently collected data on the local device (i.e., the pet data collection device). When the user needs to query the most recent data, the system can obtain it directly from the cache without having to request it from the server again.
[0145] Specifically, the transmission processing unit analyzes the transmission interval of the data to be transmitted in the next management period according to the analysis results of the abnormality of pet data transmission in the management period and the evaluation results of the cloud server network performance, wherein:
[0146] If the network performance of the cloud server in the current management period is normal, the transmission processing unit sets the transmission interval of the data to be transmitted in the next management period to F1, and sets F1=f0;
[0147] If the network performance of the cloud server in the current management period is abnormal, when h0 / h1≤q1, the transmission processing unit sets the transmission interval of the data transmitted in the next management period to F2, and sets F2=f0×[1+γ×(w1×Nn+w2×Lt-M)]; when h0 / h1>q1, the transmission processing unit sets the transmission interval of the data transmitted in the next management period to F3, and sets F3=f0×{1+γ×[1-(h0 / h1-q1) / (q1+h0 / h1)]×(w1×Nn+w2×Lt-M)};
[0148] Among them, f0 is the preset transmission interval, h0 is the number of monitoring cycles with abnormal pet data transmission within the management period, h1 is the number of monitoring cycles within the management period, q1 is the preset transmission anomaly ratio, γ is the preset correction coefficient, 0.1<γ<0.35.
[0149] Specifically, the transmission processing unit improves the accuracy of the pet data processing scheme analysis by setting a preset transmission interval and a preset correction coefficient, thereby improving the pet monitoring data processing speed and transmission efficiency; in this embodiment, there is no specific limitation on the setting of the preset transmission interval and the preset correction coefficient, and technical personnel in this field can set them freely, as long as the setting requirements of the preset transmission interval and the preset correction coefficient are met, among which the optimal value of f0 is 60s, the optimal value of γ is 0.26, and the optimal value of q1 is 0.32.
[0150] Specifically, the output unit outputs the analysis result of the local cache size of the pet data in the next management period and the analysis result of the transmission interval to the user as a processing solution for the pet data.
[0151] 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 monitoring data processing system, characterized in that: include, A data acquisition module is used to obtain historical data of various categories of pets, data of various categories of pets and cloud server data; A priority analysis module is used to analyze the priority of each category of pet data based on the acquired historical data of each category of pets; A data monitoring module is used to analyze each category of transmission data according to the analysis results of each category of pet data and each category of pet data priority obtained during the monitoring period, and to analyze the abnormality of pet data transmission according to the analysis results of each category of transmission data during the monitoring period; A performance evaluation module is used to evaluate the network performance of the cloud server based on the network delay and network packet loss rate of the cloud server obtained during the management period; An evaluation and optimization module is used to optimize the evaluation process of the cloud server network performance according to the response time and error rate of the cloud server obtained during the management cycle; A data processing module is used to analyze the processing scheme of pet data in the next management period according to the analysis results of the abnormality of pet data transmission in the management period and the evaluation results of the network performance of the cloud server, and output the processing scheme to the user; The priority analysis module is provided with a fluctuation analysis unit, an abnormality analysis unit and a priority analysis unit. The fluctuation analysis unit is used to analyze the fluctuation coefficient of the pet historical data according to the acquired pet historical data, and set the fluctuation coefficient of the m-th category pet historical data to Em. The fluctuation analysis unit compares the fluctuation coefficient Em of the m-th category pet historical data with a preset fluctuation threshold E, and analyzes the abnormality of the fluctuation of the m-th category pet historical data according to the comparison result, wherein: When Em≤E, the fluctuation analysis unit determines that the fluctuation of the historical data of the m-th category pet is normal; When Em>E, the fluctuation analysis unit determines that the volatility of the historical data of the m-th category pet is abnormal; Wherein, m=1,2,3, mi is the i-th data in the m-th category of pet historical data, km is the number of m-th category of pet historical data, m is the mean of the m-th category of pet historical data, when m=1, the data category is pet body temperature, when m=2, the data category is pet heart rate, when m=3, the data category is pet respiratory rate; The abnormality analysis unit is used to analyze the abnormality of each category of pet historical data according to the acquired pet historical data of each category, wherein: When mi≤ym1 or mi≥ym2, the abnormality analysis unit determines that the i-th data in the m-th category of pet historical data is the m-th category of abnormal data; When ym1<mi<ym2, the abnormality analysis unit determines that the i-th data in the m-th category of pet historical data is the m-th category of normal data; The abnormality analysis unit analyzes the abnormality of each category of pet historical data according to the analysis results of the abnormal data in each category of pet historical data, wherein: When my / km≤α, the abnormality analysis unit determines that the historical data of the pet of the mth category is normal; When my / km>α, the abnormality analysis unit determines that the historical data of the pet of the mth category is abnormal; Among them, ym1 is the first preset threshold of m-category pet data, ym2 is the second preset threshold of m-category pet data, my is the number of abnormal data in the m-category pet historical data, and α is the preset abnormal proportion.
2. The pet monitoring data processing system according to claim 1, characterized in that: The priority analysis unit divides the priority of each category of pet data according to the analysis results of the fluctuation abnormality of each category of pet historical data and the analysis results of the abnormality of each category of pet historical data, wherein: When the m-th category pet historical data is normal and has normal volatility, the priority analysis unit determines that the priority of the m-th category pet data is level one; When the historical data of the m-th category pet is normal and the volatility is abnormal, if x2×(Em-E) / E≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x2×(Em-E) / E>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3; When the historical data of the m-th category pet is abnormal and the volatility is normal, if x1×ln(1+my / km-α)≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; If x1×ln(1+my / km-α)>u, the priority analysis unit determines that the priority of the m-th category pet data is level three; When the historical data of the m-th category pet is abnormal and has abnormal volatility, if x1×ln(1+my / km-α)+x2×(Em-E) / E≤u, the priority analysis unit determines that the priority of the m-th category pet data is level 2; if x1×ln(1+my / km-α)+x2×(Em-E) / E>u, the priority analysis unit determines that the priority of the m-th category pet data is level 3; Among them, x1 is the volatility weight, x2 is the anomaly weight, and u is the preset anomaly coefficient.
3. The pet monitoring data processing system according to claim 2, characterized in that: The data monitoring module analyzes the abnormality of each category of pet data based on each category of pet data acquired during the monitoring period, wherein: When 2×(ym1-mj) / (ym1+ym2)≥Pmz or 2×(mj-ym2) / (ym1+ym2)≥Pmz, the data monitoring module determines that the jth data in the mth category pet data of the current monitoring period is abnormal, and transmits it as the mth category data; When 2×(ym1-mj) / (ym1+ym2)≤Pmz and 2×(mj-ym2) / (ym1+ym2)≤Pmz, the data monitoring module determines that the jth data in the mth category pet data of the current monitoring period is normal and does not regard it as the mth category transmission data; Wherein, mj is the jth data in the mth category pet data in the current monitoring period, Pmz is the preset abnormal proportion of the mth category pet data, z=1,2,3; when the priority of the mth category pet data is level one, z=1, when the priority of the mth category pet data is level two, z=2, Pm2=Pm1×(1-β), when the priority of the mth category pet data is level three, z=3, Pm3=pm2×(1-β), β is the preset adjustment coefficient, 0<β<0.2; The data monitoring module analyzes the abnormality of pet data transmission according to the analysis results of each category of transmission data within the monitoring period, wherein: when When the data monitoring module determines that the pet data transmission in the current monitoring period is normal; when When the data monitoring module determines that the pet data transmission in the current monitoring period is abnormal; Among them, Rm is the number of m-category transmission data within the monitoring period, Tm is the number of m-category pet data within the monitoring period, W is the number of pet data categories, and yc is the preset transmission anomaly coefficient.
4. The pet monitoring data processing system according to claim 3, characterized in that: The performance evaluation module compares the cloud server network delay s0 obtained during the management period with the preset delay s1, and analyzes the network delay index according to the comparison result, where: When s0≤s1, the performance evaluation module determines that the network delay in the current management period is normal, and sets the network delay index to N1, setting N1=0; When s0>s1, the performance evaluation module determines that the network delay in the current management period is abnormal, and sets the network delay index to N2, setting N2=sin[(s0-s1) / (s0+s1)]; The performance evaluation module compares the network packet loss rate d0 obtained during the management period with the preset packet loss rate d1, and analyzes the network packet loss index according to the comparison result, wherein: When d0≤d1, the performance evaluation module determines that the network packet loss rate of the current management period is normal, and sets the network packet loss index to L1, setting L1=0; When d0>d1, the performance evaluation module determines that the network packet loss rate of the current management period is abnormal, and sets the network packet loss index to L2, setting L2=arctan[(d0-d1) / (d0+d1)×(π / 4)]; The performance evaluation module evaluates the network performance of the cloud server according to the analysis results of the network delay index and the network packet loss index within the management period, wherein: When w1×Nn+w2×Lt≤M, the performance evaluation module determines that the network performance of the cloud server in the current management period is normal; When w1×Nn+w2×Lt>M, the performance evaluation module determines that the network performance of the cloud server in the current management period is abnormal; Among them, Nn is the analysis result of the network delay index, n=1,2; Lt is the analysis result of the network packet loss index, t=1,2; M is the preset performance coefficient, w1 is the delay weight, and w2 is the packet loss weight.
5. The pet monitoring data processing system according to claim 4, characterized in that: The evaluation and optimization module is provided with a first optimization unit and a second optimization unit. The first optimization unit is used to compare the cloud server response time xy0 obtained in the management period with the preset response time xy1, and optimize the evaluation process of the cloud server network performance according to the comparison result, wherein: When xy0≤xy1, the first optimization unit determines that the response time of the cloud server in the current management period is normal and does not perform optimization; When xy0>xy1, the first optimization unit determines that the response time of the cloud server in the current management period is abnormal, and optimizes the evaluation process of the cloud server network performance, and sets the optimized preset performance coefficient to M', setting: M'=M×exp[-(xy0-xy1) / (xy0+xy1)].
6. The pet monitoring data processing system according to claim 5, characterized in that: The second optimization unit compares the cloud server error rate cw0 obtained during the management period with the preset error rate cw1, and performs secondary optimization on the evaluation process of the cloud server network performance according to the comparison result, wherein: When cw0≤cw1, the second optimization unit determines that the cloud server error rate in the current management period is normal and does not perform optimization; When cw0>cw1, the second optimization unit determines that the cloud server error rate in the current management period is abnormal, and performs secondary optimization on the evaluation process of the cloud server network performance, and sets the optimized preset response time as xy1', setting: xy1'=xy1×{1+exp[3×(cw0-cw1) / (cw0+cw1)-3]}.
7. The pet monitoring data processing system according to claim 6, characterized in that: The data processing module is provided with a cache processing unit and a transmission processing unit, and the cache processing unit is used to analyze the local cache size of the pet data in the next management period according to the evaluation result of the cloud server network performance in the management period, wherein: If the network performance of the cloud server in the current management period is normal, the cache processing unit sets the local cache size of the pet data in the next management period to G1, and sets G1=g0; If the network performance of the cloud server in the current management period is abnormal, the cache processing unit sets the local cache size of the pet data in the next management period to G2, and sets G2=g0×{1+{{exp[sin(w1×Nn+w2×Lt-M)]}-1} / 3}; Among them, g0 is the preset cache size.
8. The pet monitoring data processing system according to claim 7, characterized in that: The transmission processing unit analyzes the transmission interval of the data to be transmitted in the next management period according to the analysis results of the abnormality of pet data transmission in the management period and the evaluation results of the network performance of the cloud server, wherein: If the network performance of the cloud server in the current management period is normal, the transmission processing unit sets the transmission interval of the data to be transmitted in the next management period to F1, and sets F1=f0; If the network performance of the cloud server in the current management period is abnormal, when h0 / h1≤q1, the transmission processing unit sets the transmission interval of the data transmitted in the next management period to F2, and sets F2=f0×[1+γ×(w1×Nn+w2×Lt-M)]; when h0 / h1>q1, the transmission processing unit sets the transmission interval of the data transmitted in the next management period to F3, and sets F3=f0×{1+γ×[1-(h0 / h1-q1) / (q1+h0 / h1)]×(w1×Nn+w2×Lt-M)}; Among them, f0 is the preset transmission interval, h0 is the number of monitoring periods of abnormal pet data transmission within the management period, h1 is the number of monitoring periods within the management period, q1 is the preset transmission anomaly ratio, and γ is the preset correction coefficient.
Citation Information
Patent Citations
Pet monitoring data processing method and system
CN108874323A
Health maintenance system
US20080162352A1
Opportunistic Syncing Methods for Wearable Devices
US20160174099A1
Pet health and wellness system
WO2023026212A1
KR20190101002A
