Computer-based feed formula data optimization processing system and method

Abstract

The invention discloses a computer-based feed formula data optimization processing system and method, and relates to the technical field of computer software informationization, and the method comprises the following steps: preprocessing feed formula data obtained through various ways, and transmitting the preprocessed feed formula data to a receiving device through a network; multiple items of transmission information, including network transmission quality information and transmission signal interference information, during transmission of the preprocessed feed formula data through the network are collected in real time, and after collection, the network transmission quality information and the transmission signal interference information are processed; and establishing a data analysis model according to the processed network transmission quality information and transmission signal interference information when the preprocessed feed formula data is transmitted through the network, and generating a data damage hidden danger evaluation coefficient. By monitoring the network transmission quality and the signal interference in real time, whether the feed formula data is damaged or not in the transmission process can be judged, and the stability and the safety of data transmission are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer software information technology, and in particular to a computer-based feed formula data optimization processing system and method. Background Art

[0002] The computer-based feed formula data optimization processing system and method is an innovative application based on modern computer technology and mathematical optimization algorithms. Its core goal is to process a large amount of feed raw material data through computers, and automatically generate the optimal feed formula according to user needs and constraints to improve the efficiency, quality and cost-effectiveness of feed production. The basic architecture of this system includes a front-end user interface, a back-end algorithm engine and a database. Users input relevant data and set parameters through the front-end interface, and the back-end algorithm engine uses the feed raw material information and optimization algorithm stored in the database for calculation and optimization, and finally generates the best feed formula results. The implementation steps of the method mainly include data collection and collation, data preprocessing, formula optimization calculation, and result display and feedback. In the data collection stage, it is necessary to collect feed raw material data and user needs, and then clean, integrate and standardize the data. Subsequently, a mathematical model is established, and an appropriate optimization algorithm is selected for calculation and optimization. Finally, the optimization results are presented to the user in an intuitive way, and adjusted and optimized according to user feedback. To realize this system and method, various programming languages ​​and technologies need to be applied, including Python, Matlab, R and other programming languages, as well as related optimization algorithm libraries, databases and front-end development frameworks. Once development is completed, the system needs to be deployed to the server for continuous maintenance and updates to ensure that its performance and functions are continuously optimized and improved.

[0003] This computer-based feed formula optimization processing system and method has broad application prospects. It can help feed production companies improve production efficiency and product quality and reduce costs. It also helps to promote the digitalization and intelligent development of the feed production industry. However, the existing technology still has some shortcomings.

[0004] The existing technology has the following deficiencies: the existing technology requires a large amount of data transmission during the data collection and collation stage, and when the data passes through the network transmission medium during the transmission process, it will be affected by the environment, especially it is very susceptible to electromagnetic interference, which will cause data corruption, but the existing technology cannot detect this part of the damaged data in time. The damaged data will lead to errors in the data analysis results, thereby causing misleading data statistics and quality control problems, and further affecting product quality and safety. In addition, if the damaged data is mistakenly used for model training, it will lead to large deviations in the prediction, which will reduce the accuracy of the model and even lead to waste of resources. This will reduce the trust in the optimization method and affect its reliability and effectiveness in practical applications.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a computer-based feed formula data optimization processing system and method to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] A computer-based optimization processing method for feed formula data comprises the following steps:

[0009] S1. Preprocess the feed formula data obtained through various channels and transmit it to the receiving device through the network;

[0010] S2. Real-time collection of a plurality of transmission information when the pre-processed feed formula data is transmitted through the network, including network transmission quality information and transmission signal interference information. After collection, the network transmission quality information and transmission signal interference information are processed;

[0011] S3, establishing a data analysis model for the processed network transmission quality information and transmission signal interference information when the pre-processed feed formula data is transmitted through the network, and generating a data damage hidden danger assessment coefficient;

[0012] S4, comparing and analyzing the data damage hidden danger assessment coefficient generated when the pre-processed feed formula data is transmitted through the network with a preset data damage hidden danger assessment coefficient reference threshold, and generating a normal signal and an abnormal signal;

[0013] S5. After receiving an abnormal signal generated when the pre-processed feed formula data is transmitted through the network, a number of data damage hidden danger assessment coefficients generated during subsequent data transmission are obtained for comprehensive analysis, and the abnormal hidden danger type of the feed formula data when it is transmitted through the network is determined, and output through the mobile terminal;

[0014] S6. After receiving the pre-processed feed formula data transmitted through the network, the receiving device restores the pre-processed feed formula data to the original feed formula data.

[0015] Preferably, the network transmission quality information when the pre-processed feed formula data is transmitted through the network includes a data transmission delay stability coefficient and a bandwidth utilization dynamic coefficient. After collection, the data transmission delay stability coefficient and the bandwidth utilization dynamic coefficient are calibrated as SJSY ～ and BUDC θ ;

[0016] The transmission signal interference information when transmitting the pre-processed feed formula data through the network includes the signal-to-noise power ratio smoothing coefficient. After collection, the signal-to-noise power ratio smoothing coefficient is calibrated as SNR ≡ .

[0017] Preferably, the logic for obtaining the data transmission delay stability coefficient is as follows:

[0018] S211, obtaining the sending timestamps and receiving timestamps of a plurality of feed formula data packets when they are sent and received within a time period T when data is transmitted through the network, and marking the sending timestamps and receiving timestamps of a plurality of feed formula data packets when they are sent and received within a time period T as and m represents the number of the sending timestamp and receiving timestamp of a number of feed formula data packets during sending and receiving within the time T, m = 1, 2, 3, 4, ..., a, a is a positive integer;

[0019] S212, calculate the transmission delay of each data packet, and mark the transmission delay of each data packet as The specific calculation formula is as follows: m represents the sending timestamp and receiving timestamp of a number of feed formula data packets during sending and receiving within time T, and the number of the transmission delay of each data packet, m=1, 2, 3, 4, ..., a, where a is a positive integer;

[0020] S213. Calculate the data delay stability coefficient. The specific calculation formula is as follows:

[0021]

[0022] Among them, SJSY ～ is the data delay stability coefficient.

[0023] Preferably, the logic for obtaining the bandwidth utilization dynamic coefficient is as follows:

[0024] S221, when data is transmitted through the network, the amount of data transmitted on the network link within the time T and the transmission time are obtained, and the amount of data transmitted on the network link within the time T and the transmission time are respectively calibrated as and n represents the amount of data transmitted on the network link within time T and the number of the transmission time, n = 1, 2, 3, 4, ..., b, b is a positive integer;

[0025] S222, calibrate the bandwidth utilization rate of each sampling time point within T time as The specific calculation formula is as follows: n represents the number of bandwidth utilization at each sampling time point within time T, n=1, 2, 3, 4, ..., b, b is a positive integer;

[0026] S223, obtaining a weight smoothing coefficient of data transmission, calibrating the weight smoothing coefficient of data transmission as θ, and calculating a dynamic coefficient of bandwidth utilization. The specific calculation formula is as follows:

[0027]

[0028] Wherein, θ represents the weight smoothing coefficient of data transmission, and 0<θ<1.

[0029] Preferably, it is characterized in that the logic of obtaining the signal-to-noise power ratio smoothing coefficient is as follows:

[0030] S231, obtaining the time domain waveform data of the transmission signal within the time T when data is transmitted through the network, and obtaining the time domain waveform data of each time point t within the time T. i The signal amplitude X of the time domain waveform data of the transmission signal i , i represents the number of each time point of the time domain waveform data within the time T and the signal amplitude of the time domain waveform data corresponding to each time point, i=1, 2, 3, 4, ..., c, c is a positive integer;

[0031] S232. Calculate signal power. The specific calculation formula is:

[0032] S233, obtaining the time domain waveform data of the noise signal within the time T when data is transmitted through the network, and obtaining the time domain waveform data of each time point t within the time T. i The signal amplitude N of the time domain waveform data of the noise signal i , i represents the number of each time point of the time domain waveform data within the time T and the signal amplitude of the time domain waveform data corresponding to each time point, i=1, 2, 3, 4, ..., c, c is a positive integer;

[0033] S234. Calculate the noise power. The specific calculation formula is:

[0034] S235: Calculate the signal-to-noise power ratio. The specific calculation formula is:

[0035] S236: Calculate the signal-to-noise power ratio smoothing coefficient. The specific calculation formula is:

[0036]

[0037] In the formula, is the smoothing coefficient of the signal interference, and

[0038] Preferably, the transmission delay stability coefficient SJSY ～ , Bandwidth utilization dynamic coefficient BUDC θ And the signal-to-noise power ratio smoothing coefficient SNR ≡ Establish a data analysis model to generate a data corruption risk assessment coefficient Q SHPG , according to the formula:

[0039]

[0040] Where r1, r2 and r3 are the data transmission delay stability coefficients SJSY ～ , Bandwidth utilization dynamic coefficient BUDC θ And the signal-to-noise power ratio smoothing coefficient SNR ≡ The preset proportional coefficient, and r1, r2 and r3 are all greater than 0.

[0041] Preferably, the data damage hidden danger assessment coefficient generated when the pre-processed feed formula data is transmitted through the network is compared and analyzed with a preset data damage hidden danger assessment coefficient reference threshold, and the result of the comparison and analysis is as follows:

[0042] If the data corruption hidden danger assessment coefficient is less than the preset data corruption hidden danger assessment coefficient reference threshold, a normal signal is generated; if the data corruption hidden danger assessment coefficient is greater than or equal to the preset data corruption hidden danger assessment coefficient reference threshold, an abnormal signal is generated.

[0043] Preferably, a plurality of data damage hidden danger assessment coefficients generated when the pre-processed feed formula data is transmitted through a network are received, and the plurality of data damage hidden danger assessment coefficients are recalibrated as z represents the serial number of a number of data corruption risk assessment coefficients, z=1, 2, 3, 4, ..., d, d is a positive integer;

[0044] The average value of several data corruption risk assessment coefficients is calibrated as Q - , the specific calculation formula is:

[0045] The standard deviation of several data corruption risk assessment coefficients is calibrated as Q σ , the specific calculation formula is:

[0046] Preferably, a preset mean value and a preset standard deviation of a plurality of data damage hidden danger assessment coefficients generated when the pre-processed feed formula data is transmitted through a network are obtained, and the preset mean values ​​and the preset standard deviations of the plurality of data damage hidden danger assessment coefficients are calibrated as and The average value of several data corruption risk assessment coefficients Q -and the standard deviation Q of several data corruption risk assessment coefficients σ The preset average values ​​of several data damage risk assessment coefficients are and preset standard deviation A comparative analysis is conducted, and the specific analysis is as follows:

[0047] like A continuous safety hazard signal is generated and transmitted to the mobile terminal for prompting;

[0048] like and An intermittent safety hazard signal is generated and transmitted to the mobile terminal for prompting;

[0049] like and An accidental safety hazard signal is generated and transmitted to the mobile terminal, through which a prompt is given.

[0050] A computer-based feed formula data optimization processing system, including a data acquisition and processing module, a model building module, a data analysis module, and a prompt module;

[0051] A data acquisition and processing module collects a plurality of transmission information when the pre-processed feed formula data is transmitted through the network, including network transmission quality information and transmission signal interference information. After the collection, the network transmission quality information and the transmission signal interference information are processed, and the processed network transmission quality information and the transmission signal interference information are transmitted to the model building module;

[0052] The model building module receives the network transmission quality information and transmission signal interference information processed by the data acquisition and processing module, establishes a data analysis model, and generates a data damage hidden danger assessment coefficient;

[0053] The data analysis module compares and analyzes the data damage hidden danger assessment coefficient generated by the model building module with the pre-set data damage hidden danger assessment coefficient reference threshold, generates normal signals and abnormal signals, and at the same time, when generating abnormal signals, obtains several data damage hidden danger assessment coefficients generated during subsequent data transmission for comprehensive analysis, determines the abnormal hidden danger type of the feed formula data when it is transmitted through the network, and outputs it through the prompt module;

[0054] The prompt module prompts the analysis results of the data analysis module through the mobile terminal.

[0055] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0056] The present invention collects network transmission quality information and transmission signal interference information in real time during the data transmission process, performs corresponding processing, and establishes a data analysis model for the processed network transmission quality information and transmission signal interference information, which helps to timely discover and solve problems that may cause data damage in transmission, can help identify bottlenecks and anomalies in the transmission process, take timely measures to adjust and optimize, ensure the stability and reliability of data transmission, can discover changes in the transmission environment and interference factors in advance, take corresponding measures to reduce the impact of interference on data transmission, ensure the quality of data transmission, can further improve the security and stability of data transmission, and help to detect in real time whether feed formula data will be damaged during transmission.

[0057] After the abnormal signal is generated when the pre-processed feed formula data is transmitted through the network, the present invention obtains several data damage hidden danger assessment coefficients generated during subsequent data transmission for comprehensive analysis, and determines the abnormal hidden danger type of the feed formula data when it is transmitted through the network, which can improve the reliability and stability of data transmission, ensure the integrity and accuracy of the data, and help avoid erroneous data analysis and statistical results, thereby ensuring product quality and safety; secondly, timely detection of data damage can reduce the misuse of damaged data, avoid misleading effects on model training and decision-making, and improve the accuracy and reliability of data processing; in addition, through accidental judgment, it can also help to timely discover abnormal situations and problems in network transmission, which is beneficial to the optimization of network performance and the troubleshooting of problems, further improve the efficiency and quality of data transmission, and enhance the stability and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0059] Figure 1 The present invention is a method flow chart of a computer-based feed formula data optimization processing system and method.

[0060] Figure 2 The present invention is a module schematic diagram of a computer-based feed formula data optimization processing system and method. DETAILED DESCRIPTION

[0061] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0062] The present invention provides Figure 1 A computer-based feed formula data optimization processing method is shown, comprising the following steps:

[0063] S1. Preprocess the feed formula data obtained through various channels and transmit it to the receiving device through the network;

[0064] It should be noted that the feed formula data can be obtained by obtaining raw material cost and nutritional value data from suppliers, or by obtaining purchase records from the internal procurement system. The feed formula data acquisition method is not specifically limited here and can be determined according to actual conditions.

[0065] The preprocessing of feed formula data includes data format conversion, data compression, data encryption and other steps. Data format conversion can ensure that the data can be correctly parsed and processed by the receiving device during transmission; data compression can reduce the amount of transmitted data and improve transmission efficiency; data encryption can protect the privacy and confidentiality of the data and prevent unauthorized access or tampering during transmission. Preprocessing can improve the reliability and security of data transmission and help ensure the integrity and confidentiality of data during transmission.

[0066] S2. Real-time collection of a plurality of transmission information when the pre-processed feed formula data is transmitted through the network, including network transmission quality information and transmission signal interference information. After collection, the network transmission quality information and transmission signal interference information are processed;

[0067] The network transmission quality information when transmitting the pre-processed feed formula data through the network includes the data transmission delay stability coefficient and the bandwidth utilization dynamic coefficient. After collection, the data transmission delay stability coefficient and the bandwidth utilization dynamic coefficient are calibrated as SJSY ～ and BUDC θ .

[0068] When the pre-processed feed formula data is transmitted through the network, the transmission delay refers to the time delay required for the data to travel from the sender to the receiver. It can also be understood as the time it takes for the data to travel in the network. It is an important indicator for describing the delay of data in the network transmission process, which directly affects the speed, efficiency and real-time performance of data transmission. The transmission delay includes the time consumed by the data in the process of caching, transmission, routing, propagation and caching at the receiver. The transmission delay usually consists of four parts:

[0069] Transmission delay: the time data is buffered at the sender waiting for transmission;

[0070] Transmission delay: the time it takes for data to propagate in the transmission medium, which depends on the transmission distance and transmission rate;

[0071] Processing latency: the time it takes for data to be processed on network devices such as routers and switches;

[0072] Queuing delay: the time data waits in the queue of a network device for transmission;

[0073] The reasons for transmission delay when preprocessed feed formula data is transmitted through the network are:

[0074] Network congestion: When there is a large amount of data traffic in the network, it exceeds the capacity of the network bandwidth, causing data packets to queue up for transmission during the transmission process, causing transmission delays;

[0075] Transmission distance: The longer the data transmission distance, the longer the data propagation time, thus increasing the transmission delay;

[0076] Equipment processing capacity: The time required for network equipment such as routers and switches to process data packets will increase transmission delay;

[0077] Packet size: Larger packets take longer to transmit, thus increasing transmission latency;

[0078] The size of the transmission delay is affected by many factors, including network bandwidth, network congestion, transmission distance, data packet size, network equipment processing capabilities, etc. The size of the transmission delay depends on many factors such as network environment, network equipment, data packet size, etc. Generally, the smaller the transmission delay, the better, because a smaller transmission delay means faster data transmission and higher real-time performance. However, too large a transmission delay will cause data transmission delays, affecting the timeliness and real-time performance of data, thereby reducing network performance. A smaller transmission delay helps to improve the speed and real-time performance of data transmission, thereby improving user experience, especially for applications that require real-time interaction and high real-time requirements (such as video conferencing, online games, etc.). On the contrary, a larger transmission delay will cause data transmission delays, which may cause data loss, excessive delay or poor real-time performance, affecting user experience and data transmission reliability.

[0079] The data delay stability coefficient describes the stability of the transmission delay of several data packets from the sending end to the receiving end, that is, whether the time required for data transmission fluctuates within a relatively stable range. Better delay stability means that the delay variation of data transmission is smaller. When the data transmission delay stability coefficient is higher, it means that the data transmission delay varies more and the delay fluctuation is more drastic; when the data transmission delay stability coefficient is lower, it means that the data transmission delay varies less and the delay fluctuation is more stable.

[0080] Relationship with data corruption: The data transmission delay stability coefficient can indirectly reflect the stability and reliability of the data transmission process. If the data transmission delay stability coefficient is high and the delay fluctuates greatly, this may cause the data packet to be subject to greater interference and fluctuations during the transmission process, increasing the risk of data corruption. On the contrary, if the data transmission delay stability coefficient is low, the delay fluctuation is small, the stability during the transmission process is high, and the possibility of data corruption is relatively small.

[0081] Therefore, there is a certain relationship between the data transmission delay stability coefficient and data corruption: a higher transmission delay stability coefficient may increase the risk of data corruption, while a lower transmission delay stability coefficient may reduce the risk of data corruption. By monitoring and analyzing the data transmission delay stability coefficient, it can help evaluate the stability of data transmission and take corresponding measures to reduce the occurrence of data corruption.

[0082] The logic for obtaining the data transmission delay stability coefficient is as follows:

[0083] S211, obtaining the sending timestamps and receiving timestamps of a plurality of feed formula data packets when they are sent and received within a time period T when data is transmitted through the network, and marking the sending timestamps and receiving timestamps of a plurality of feed formula data packets when they are sent and received within a time period T as and m represents the number of the sending timestamp and receiving timestamp of a number of feed formula data packets during sending and receiving within the time T, m = 1, 2, 3, 4, ..., a, a is a positive integer;

[0084] It should be noted that when data is transmitted through the network, the sending timestamp and receiving timestamp of several feed formula data packets during the sending and receiving within the time T are obtained in the following manner: first, at the sending end, the time when each data packet is sent is recorded, which can be achieved through the timestamp function provided by the operating system or the timestamp option of the application layer protocol; then, at the receiving end, the time when each data packet is received is recorded, which can also be obtained through the timestamp function provided by the operating system or the timestamp option of the application layer protocol; the specific acquisition method is not specifically limited here and can be determined according to actual conditions;

[0085] S212, calculate the transmission delay of each data packet, and mark the transmission delay of each data packet as The specific calculation formula is as follows: m represents the sending timestamp and receiving timestamp of a number of feed formula data packets during sending and receiving within time T, and the number of the transmission delay of each data packet, m=1, 2, 3, 4, ..., a, where a is a positive integer;

[0086] S213. Calculate the data delay stability coefficient. The specific calculation formula is as follows:

[0087]

[0088] Among them, SJSY ～ is the data delay stability coefficient. A smaller data delay stability coefficient indicates that the delay variation of data transmission is relatively small and the transmission process is relatively stable; while a larger data delay stability coefficient indicates that the delay variation is large and the transmission process is not very stable.

[0089] Calculating the data transmission delay stability coefficient is of great significance for determining whether data corruption occurs when the pre-processed feed formula data is transmitted through the network. The transmission delay stability coefficient reflects the degree of fluctuation of the delay during data transmission. When the transmission delay stability coefficient is high, it means that the data transmission delay varies greatly, which may increase the risk of interference and fluctuation of the data packet during transmission, which may lead to data corruption. Therefore, by monitoring and analyzing the transmission delay stability coefficient, stability problems in the data transmission process can be discovered in time, and possible data corruption can be warned in advance, so that corresponding measures can be taken to ensure the reliability and integrity of data transmission. This helps to optimize the network transmission environment, reduce the risk of data corruption, improve the quality and reliability of data transmission, and thus ensure the accuracy and security of feed formula data.

[0090] When the pre-processed feed formula data is transmitted through the network, bandwidth utilization refers to the ratio of the bandwidth actually used on the network link to the total bandwidth. It represents the usage of the network at a certain moment, or it can be the ratio of the amount of data transmitted to the transmission time. In network transmission, bandwidth utilization is an important indicator to measure the usage of network links. It reflects the data transmission load on the current network link. High bandwidth utilization indicates that the network link is being fully utilized, which may increase the delay of data transmission, reduce the transmission speed, and even cause data loss or damage.

[0091] When feed formula data is transmitted over the network, it also needs to occupy the network's bandwidth resources. If the network bandwidth resources are insufficient or the bandwidth utilization rate is too high, it may affect the transmission speed and stability of the feed formula data, leading to problems such as increased data transmission delays, increased packet loss rates, and data corruption.

[0092] The bandwidth utilization dynamic coefficient refers to the rate of change of bandwidth utilization over a period of time. It reflects the dynamic changes in network link bandwidth utilization, that is, the speed of change of network transmission load. By monitoring the bandwidth utilization dynamic coefficient, you can more timely detect the change trend of network load and judge the stability and performance of the network.

[0093] In the process of feed formula data transmission through the network, the change of the dynamic coefficient of bandwidth utilization will directly affect the quality and stability of data transmission, and thus indirectly affect whether the data will be damaged. Specifically: if the dynamic coefficient of bandwidth utilization is small, it means that the bandwidth utilization on the network link changes slowly and the network load is relatively stable. In this case, the stability of data transmission is high, and the transmission delay and packet loss rate of data packets are relatively low, so the data is unlikely to be damaged; on the contrary, if the dynamic coefficient of bandwidth utilization is large, it means that the bandwidth utilization on the network link changes rapidly and the network load fluctuates greatly. In this case, data transmission may be affected, resulting in increased transmission delay, increased packet loss rate and other problems, which increases the possibility of data damage.

[0094] Therefore, by monitoring the bandwidth utilization dynamic coefficient, we can timely detect the changes in bandwidth utilization on the network link, predict the stability of data transmission, and then determine whether the data will be damaged during the transmission process. A larger bandwidth utilization dynamic coefficient may mean an increase in the instability of the network load, indicating the risk of data damage.

[0095] The logic for obtaining the dynamic coefficient of bandwidth utilization is as follows:

[0096] S221, when data is transmitted through the network, the amount of data transmitted on the network link within the time T and the transmission time are obtained, and the amount of data transmitted on the network link within the time T and the transmission time are respectively calibrated as and n represents the amount of data transmitted on the network link within time T and the number of the transmission time, n = 1, 2, 3, 4, ..., b, b is a positive integer;

[0097] It should be noted that the amount of data transmitted on the network link within the time T and the time of transmission can be obtained by: first, recording the timestamps of the start and end of data transmission within the time T to calculate the transmission time; second, monitoring the number of data packets on the network link or using the traffic statistics function of the network device to obtain the amount of data transmitted within the time T. The specific acquisition method is not specifically limited here and can be selected according to actual needs;

[0098] S222, calibrate the bandwidth utilization rate of each sampling time point within T time as The specific calculation formula is as follows: n represents the number of bandwidth utilization at each sampling time point within time T, n=1, 2, 3, 4, ..., b, b is a positive integer;

[0099] S223, obtaining a weight smoothing coefficient of data transmission, calibrating the weight smoothing coefficient of data transmission as θ, and calculating a dynamic coefficient of bandwidth utilization. The specific calculation formula is as follows:

[0100]

[0101] Where θ represents the weight smoothing coefficient of data transmission, and 0<θ<1;

[0102] It should be noted that the weight smoothing coefficient θ of data transmission is a parameter used to specify the degree of influence of new data on the smoothing process. It indicates the weight ratio of new data in calculating the average or predicted value during smoothing. Usually, the value range of the weight smoothing coefficient θ is between 0 and 1, because this range can ensure that the weight of new data gradually decreases throughout the process, thereby better reflecting the trend of the data. When θ is close to 0, the smoothing effect will be weak and more dependent on historical data; and when θ is close to 1, the impact of new data will be more significant, reflecting more recent changes. Therefore, θ, which usually ranges from 0 to 1, can balance the weights of historical data and new data, so that the smoothing process can better adapt to data changes; the specific value of the weight smoothing coefficient θ of data transmission is not specifically limited here, and is usually determined according to the application scenario and requirements. The most appropriate θ value can be determined through experiments and adjustments. It is usually evaluated and selected in combination with the characteristics of the data and the requirements for the smoothing results. At the same time, the selection of θ value can also be guided by experience or domain knowledge to achieve the best smoothing effect.

[0103] The transmission signal interference information when transmitting the pre-processed feed formula data through the network includes the signal-to-noise power ratio smoothing coefficient. After collection, the signal-to-noise power ratio smoothing coefficient is calibrated as SNR ≡ .

[0104] When the pre-processed feed formula data is transmitted through the network, the signal-to-noise power ratio (SNR) refers to the ratio of signal power to noise power, which is usually used to quantify the ratio between useful information and noise in the signal. In data transmission, the signal represents valid information, while the noise represents interference or error. Therefore, the signal-to-noise power ratio describes the strength or clarity of the signal relative to the noise.

[0105] For the data transmission process, a good signal-to-noise power ratio means that the signal power is relatively high and the noise power is relatively low, which effectively protects the data from interference. However, when the signal-to-noise power ratio is low, the noise power dominates, which may cause errors or losses in data transmission.

[0106] Therefore, there is a close relationship between the signal-to-noise power ratio and the data corruption that occurs when the feed formula data is transmitted through the network. When the signal-to-noise power ratio is low, the interference of noise on the signal will increase, thereby reducing the quality of data transmission, which may lead to problems such as packet loss, data corruption or transmission errors. Therefore, by monitoring and evaluating the signal-to-noise power ratio, it is possible to effectively determine whether data corruption will occur during data transmission, and take corresponding measures to improve the reliability and quality of data transmission.

[0107] The signal-to-noise power ratio smoothing coefficient refers to the value after the signal-to-noise power ratio is smoothed. It is of great significance in evaluating whether data corruption occurs when feed formula data is transmitted through the network. By reducing data volatility, improving evaluation accuracy, enhancing understanding of data changes, and improving system stability, smoothing helps reduce the impact of noise and interference on evaluation results, making them more reliable and stable. In this way, abnormal situations in the data transmission process can be better monitored, and timely measures can be taken to ensure the quality and reliability of data transmission.

[0108] The logic for obtaining the signal-to-noise power ratio smoothing coefficient is as follows:

[0109] S231, obtaining the time domain waveform data of the transmission signal within the time T when data is transmitted through the network, and obtaining the time domain waveform data of each time point t within the time T. i The signal amplitude X of the time domain waveform data of the transmission signal i , i represents the number of each time point of the time domain waveform data within the time T and the signal amplitude of the time domain waveform data corresponding to each time point, i=1, 2, 3, 4, ..., c, c is a positive integer;

[0110] It should be noted that the time domain waveform data of the signal transmitted within the time T when data is transmitted through the network can be obtained through sensors, instruments or signal acquisition equipment. The specific acquisition method is not specifically limited here and can be selected according to actual needs;

[0111] S232. Calculate signal power. The specific calculation formula is:

[0112] S233, obtaining the time domain waveform data of the noise signal within the time T when data is transmitted through the network, and obtaining the time domain waveform data of each time point t within the time T. i The signal amplitude N of the time domain waveform data of the noise signal i , i represents the number of each time point of the time domain waveform data within the time T and the signal amplitude of the time domain waveform data corresponding to each time point, i=1, 2, 3, 4, ..., c, c is a positive integer;

[0113] It should be noted that the time domain waveform data of the noise signal within the time T when data is transmitted through the network can be obtained by separating the noise component from the signal containing the noise through a suitable filter, which includes the time domain waveform data. The specific acquisition method is not limited here and can be selected according to actual needs;

[0114] S234. Calculate the noise power. The specific calculation formula is:

[0115] S235: Calculate the signal-to-noise power ratio. The specific calculation formula is:

[0116] S236: Calculate the signal-to-noise power ratio smoothing coefficient. The specific calculation formula is:

[0117]

[0118] In the formula, is the smoothing coefficient of the signal interference, and

[0119] It should be noted that the smoothing coefficient It controls the weight of new data in the smoothing process, that is, it determines the relative contribution of new and old data. Specifically, the smoothing coefficient determines the response speed of the smoothed data and the degree of noise suppression. When the smoothing coefficient is close to 1, the weight of new data is large, and the smoothed data is more sensitive to the most recent observations, which makes the smoothed data closer to the original data, but also more susceptible to noise; when the smoothing coefficient is close to 0, the weight of old data is large, and the smoothed data is more stable, but the response speed is slow, and it is not sensitive enough to data changes. Therefore, by adjusting the smoothing coefficient, the stability and response speed of the smoothed data can be balanced to meet the needs of different scenarios; the smoothing coefficient The specific value of is not limited here. It is usually determined according to the application scenario and requirements. The most appropriate value can be determined through experiments and adjustments. The value is usually evaluated and selected based on the characteristics of the data and the requirements for smoothing results. It can also be guided by experience or domain knowledge. The value is chosen to achieve the best smoothing effect.

[0120] S3, establishing a data analysis model for the processed network transmission quality information and transmission signal interference information when the pre-processed feed formula data is transmitted through the network, and generating a data damage hidden danger assessment coefficient;

[0121] Obtain the data transmission delay stability coefficient SJSY after processing when the pre-processed feed formula data is transmitted through the network ～ , Bandwidth utilization dynamic coefficient BUDC θ And the signal-to-noise power ratio smoothing coefficient SNR ≡ , the transmission delay stability coefficient SJSY ～ , Bandwidth utilization dynamic coefficient BUDC θ And the signal-to-noise power ratio smoothing coefficient SNR ≡ Establish a data analysis model to generate a data corruption risk assessment coefficient Q SHPG , according to the formula:

[0122]

[0123] Where r1, r2 and r3 are the data transmission delay stability coefficients SJSY ～ , Bandwidth utilization dynamic coefficient BUDC θ And the signal-to-noise power ratio smoothing coefficient SNR ≡ The preset proportional coefficient, and r1, r2 and r3 are all greater than 0;

[0124] From the calculation formula, we can know that the data transmission delay stability coefficient SJSY generated within T time when the pre-processed feed formula data is transmitted through the network is ～ and bandwidth utilization dynamic coefficient BUDC θ The smaller the signal-to-noise power ratio, the smoothing coefficient SNR ≡ The larger the data corruption risk assessment coefficient Q is, the SHPG The smaller it is, the smaller the risk of data corruption in the process of feeding formula data transmission through the network is. On the contrary, the larger the risk of data corruption in the process of feeding formula data transmission through the network is.

[0125] It should be noted that the above-mentioned T time is selected as a relatively short time period. The time within the time period is not specifically limited here and can be set according to actual conditions. Its purpose is to monitor the hidden dangers of data corruption during the T time when the feed formula data is transmitted through the network, so as to monitor the data transmission security risks in different time periods (T time) during data transmission over the data line in real time.

[0126] S4. Compare and analyze the data damage hidden danger assessment coefficient generated when the pre-processed feed formula data is transmitted through the network with the pre-set data damage hidden danger assessment coefficient reference threshold to generate normal signals and abnormal signals:

[0127] The data corruption risk assessment coefficient generated when the pre-processed feed formula data is transmitted through the network is compared with the pre-set data corruption risk assessment coefficient reference threshold. The results of the comparison analysis are as follows:

[0128] If the data corruption hidden danger assessment coefficient is less than the preset data corruption hidden danger assessment coefficient reference threshold, a normal signal is generated; if the data corruption hidden danger assessment coefficient is greater than or equal to the preset data corruption hidden danger assessment coefficient reference threshold, an abnormal signal is generated.

[0129] S5. After receiving an abnormal signal generated when the pre-processed feed formula data is transmitted through the network, a number of data damage hidden danger assessment coefficients generated during subsequent data transmission are obtained for comprehensive analysis, and the abnormal hidden danger type of the feed formula data when it is transmitted through the network is determined, and output through the mobile terminal;

[0130] Receiving a number of data damage potential risk assessment coefficients generated when the pre-processed feed formula data is transmitted through the network, recalibrating the data damage potential risk assessment coefficients to z represents the serial number of a number of data corruption risk assessment coefficients, z=1, 2, 3, 4, ..., d, d is a positive integer;

[0131] The average value of several data corruption risk assessment coefficients is calibrated as Q - , the specific calculation formula is:

[0132] The standard deviation of several data corruption risk assessment coefficients is calibrated as Q σ , the specific calculation formula is:

[0133] The preset average values ​​and the preset standard deviations of several data damage hidden danger assessment coefficients generated when the preprocessed feed formula data is transmitted through the network are obtained, and the preset average values ​​and the preset standard deviations of several data damage hidden danger assessment coefficients are calibrated as and The average value Q of several data damage risk assessment coefficients - and the standard deviation Q of several data corruption risk assessment coefficients σ The preset average values ​​of several data damage risk assessment coefficients are and preset standard deviation A comparative analysis is conducted, and the specific analysis is as follows:

[0134] like A continuous safety hazard signal is generated and transmitted to the mobile terminal for prompting. When the continuous safety hazard signal is generated when the feed formula data is transmitted through the network, it indicates that there is a great safety hazard when the feed formula data is transmitted through the network.

[0135] like and An intermittent safety hazard signal is generated and transmitted to the mobile terminal, and a prompt is given through the mobile terminal. When the intermittent safety hazard signal is generated when the feed formula data is transmitted through the network, a greater safety hazard occurs when the feed formula data is transmitted through the network, and the degree of the safety hazard is less than the degree of the safety hazard under the continuous safety hazard signal;

[0136] like and An accidental safety hazard signal is generated and transmitted to the mobile terminal, and a prompt is given through the mobile terminal. When a safety hazard signal is generated when the feed formula data is transmitted through the network, it indicates that an accidental safety hazard has occurred when the feed formula data is transmitted through the network, and no attention is required at this time.

[0137] When feed formula data is transmitted over the network, performing accidental judgment can help to promptly discover and identify data corruption so that appropriate countermeasures can be taken. First, it can improve the reliability and stability of data transmission, ensure the integrity and accuracy of data, and help avoid erroneous data analysis and statistical results, thereby ensuring product quality and safety. Secondly, timely detection of data corruption can reduce the misuse of damaged data, avoid misleading effects on model training and decision-making, and improve the accuracy and reliability of data processing. In addition, accidental judgment can also help to promptly discover abnormal situations and problems in network transmission, which is conducive to optimizing network performance and troubleshooting, further improving the efficiency and quality of data transmission, and enhancing the stability and reliability of the system. In summary, accidental judgment is of great significance and value in ensuring the smoothness and accuracy of data transmission and improving the effectiveness and reliability of data processing.

[0138] S6. After receiving the pre-processed feed formula data transmitted through the network, the receiving device restores the pre-processed feed formula data to the original feed formula data;

[0139] It should be noted that there are several ways to restore:

[0140] Decryption and decompression: If the data is encrypted and compressed during transmission, the receiving device needs to decrypt and decompress the data first to restore it to the original unprocessed data.

[0141] Data format conversion: Depending on the format used during data transmission, the receiving device may need to perform format conversion to convert the data into the format used by the original feed formula data to ensure that the data can be correctly identified and processed.

[0142] Error detection and repair: Data corruption may occur during the transmission process. The receiving device can use some error detection and repair technologies, such as using redundant check codes or forward error correction codes, to detect and repair damaged data to restore the original data as much as possible.

[0143] Data reassembly and sorting: If the data is split into multiple packets for transmission during the transmission process, the receiving device needs to reassemble and sort these data packets in order to restore the original feed formula data.

[0144] The significance of this method is to ensure that the receiving device can accurately obtain the original feed formula data, ensure the integrity and accuracy of the data, and thus ensure that the subsequent data analysis and processing work can proceed smoothly. Only through effective data restoration methods can the receiving device obtain reliable data and provide a correct basis for subsequent decision-making and production.

[0145] like Figure 2 A computer-based feed formula data optimization processing system is shown, comprising a data acquisition and processing module, a model building module, a data analysis module, and a prompt module;

[0146] A data acquisition and processing module collects a plurality of transmission information when the pre-processed feed formula data is transmitted through the network, including network transmission quality information and transmission signal interference information. After the collection, the network transmission quality information and the transmission signal interference information are processed, and the processed network transmission quality information and the transmission signal interference information are transmitted to the model building module;

[0147] The model building module receives the network transmission quality information and transmission signal interference information processed by the data acquisition and processing module, establishes a data analysis model, and generates a data damage hidden danger assessment coefficient;

[0148] The data analysis module compares and analyzes the data damage hidden danger assessment coefficient generated by the model building module with the pre-set data damage hidden danger assessment coefficient reference threshold, generates normal signals and abnormal signals, and when generating abnormal signals, obtains several data damage hidden danger assessment coefficients generated during subsequent data transmission for comprehensive analysis, determines the abnormal hidden danger type of the feed formula data when it is transmitted through the network, and transmits the determination result to the prompt module;

[0149] The prompt module prompts the analysis results of the data analysis module through the mobile terminal.

[0150] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0151] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0152] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0153] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0154] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0157] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A computer-based feed formula data optimization processing method, characterized in that: The following steps are involved: S1. Preprocess the feed formula data obtained through various channels and transmit it to the receiving device through the network; S2. Real-time collection of a plurality of transmission information when the pre-processed feed formula data is transmitted through the network, including network transmission quality information and transmission signal interference information. After collection, the network transmission quality information and transmission signal interference information are processed; The network transmission quality information when transmitting the pre-processed feed formula data through the network includes the data transmission delay stability coefficient and the bandwidth utilization dynamic coefficient. After collection, the data transmission delay stability coefficient and the bandwidth utilization dynamic coefficient are calibrated as SJSY ～ and The transmission signal interference information when transmitting the pre-processed feed formula data through the network includes the signal-to-noise power ratio smoothing coefficient. After collection, the signal-to-noise power ratio smoothing coefficient is calibrated as SNR ≡ ; S3, establishing a data analysis model for the processed network transmission quality information and transmission signal interference information when the pre-processed feed formula data is transmitted through the network, and generating a data damage hidden danger assessment coefficient; The transmission delay stability coefficient SJSY ～ , Bandwidth utilization dynamic coefficient And the signal-to-noise power ratio smoothing coefficient SNR ≡ Establish a data analysis model to generate a data corruption risk assessment coefficient Q SHPG , according to the formula: Where r1, r2 and r3 are the data transmission delay stability coefficients SJSY ～ , Bandwidth utilization dynamic coefficient And the signal-to-noise power ratio smoothing coefficient SNR ≡ The preset proportional coefficient, and r1, r2 and r3 are all greater than 0; wherein, the acquisition logic of the data transmission delay stability coefficient is as follows: Obtain the sending timestamps and receiving timestamps of several feed formula data packets when they are sent and received within T time when data is transmitted through the network, and mark the sending timestamps and receiving timestamps of several feed formula data packets when they are sent and received within T time as and m represents the number of the sending timestamp and receiving timestamp of a number of feed formula data packets during sending and receiving within the time T, m = 1, 2, 3, 4, ..., a, a is a positive integer; Calculate the transmission delay of each data packet and calibrate the transmission delay of each data packet as The specific calculation formula is as follows: m represents the sending timestamp and receiving timestamp of a number of feed formula data packets during sending and receiving within time T, and the number of the transmission delay of each data packet, m=1, 2, 3, 4, ..., a, where a is a positive integer; Calculate the data delay stability coefficient. The specific calculation formula is as follows: Among them, SJSY ～ is the data delay stability coefficient; The logic for obtaining the dynamic coefficient of bandwidth utilization is as follows: Obtain the amount of data transmitted on the network link within T time and the transmission time when data is transmitted through the network, and mark the amount of data transmitted on the network link within T time and the transmission time as and n represents the amount of data transmitted on the network link within time T and the number of the transmission time, n = 1, 2, 3, 4, ..., b, b is a positive integer; The bandwidth utilization rate of each sampling time point within T time is calibrated as The specific calculation formula is as follows: n represents the number of bandwidth utilization at each sampling time point within time T, n=1, 2, 3, 4, ..., b, b is a positive integer; Obtain the weight smoothing coefficient of data transmission and calibrate the weight smoothing coefficient of data transmission as Calculate the dynamic coefficient of bandwidth utilization. The specific calculation formula is as follows: In the formula, represents the weight smoothing coefficient of data transmission, and The logic for obtaining the signal-to-noise power ratio smoothing coefficient is as follows: Get the time domain waveform data of the transmitted signal within T time when data is transmitted through the network, and get the time domain waveform data of each time point t within T time. i The signal amplitude X of the time domain waveform data of the transmission signal i , i represents the number of each time point of the time domain waveform data within the time T and the signal amplitude of the time domain waveform data corresponding to each time point, i=1, 2, 3, 4, ..., c, c is a positive integer; Calculate the signal power. The specific calculation formula is: Obtain the time domain waveform data of the noise signal within T time when data is transmitted through the network, and obtain the time domain waveform data of each time point t within T time. i The signal amplitude N of the time domain waveform data of the noise signal i , i represents the number of each time point of the time domain waveform data within the time T and the signal amplitude of the time domain waveform data corresponding to each time point, i=1, 2, 3, 4, ..., c, c is a positive integer; Calculate the noise power. The specific calculation formula is: Calculate the signal-to-noise power ratio. The specific calculation formula is: Calculate the signal-to-noise power ratio smoothing coefficient. The specific calculation formula is: In the formula, is the smoothing coefficient of the signal interference, and S4, comparing and analyzing the data damage hidden danger assessment coefficient generated when the pre-processed feed formula data is transmitted through the network with a preset data damage hidden danger assessment coefficient reference threshold, and generating a normal signal and an abnormal signal; S5. After receiving an abnormal signal generated when the pre-processed feed formula data is transmitted through the network, a number of data damage hidden danger assessment coefficients generated during subsequent data transmission are obtained for comprehensive analysis, and the abnormal hidden danger type of the feed formula data when it is transmitted through the network is determined, and output through the mobile terminal; S6. After receiving the pre-processed feed formula data transmitted through the network, the receiving device restores the pre-processed feed formula data to the original feed formula data.

2. A computer-based feed formula data optimization processing method according to claim 1, characterized in that: The data corruption risk assessment coefficient generated when the pre-processed feed formula data is transmitted through the network is compared with the pre-set data corruption risk assessment coefficient reference threshold. The results of the comparison analysis are as follows: If the data corruption hidden danger assessment coefficient is less than the preset data corruption hidden danger assessment coefficient reference threshold, a normal signal is generated; if the data corruption hidden danger assessment coefficient is greater than or equal to the preset data corruption hidden danger assessment coefficient reference threshold, an abnormal signal is generated.

3. A computer-based feed formula data optimization processing method according to claim 2, characterized in that: Receiving a number of data damage potential risk assessment coefficients generated when the pre-processed feed formula data is transmitted through the network, recalibrating the data damage potential risk assessment coefficients to z represents the number of several data corruption risk assessment coefficients, z = 1, 2, 3, 4, ..., d, d is a positive integer; The average value of several data corruption risk assessment coefficients is calibrated as Q - , the specific calculation formula is: The standard deviation of several data corruption risk assessment coefficients is calibrated as Q σ , the specific calculation formula is:

4. A computer-based feed formula data optimization processing method according to claim 3, characterized in that: Obtain the preset mean values ​​and preset standard deviations of several data damage hidden danger assessment coefficients generated when the preprocessed feed formula data is transmitted through the network, and calibrate the preset mean values ​​and preset standard deviations of several data damage hidden danger assessment coefficients as and The average value Q of several data damage risk assessment coefficients - and the standard deviation Q of several data corruption risk assessment coefficients σ The preset average values ​​of several data damage risk assessment coefficients are and preset standard deviation A comparative analysis is conducted, and the specific analysis is as follows: like A continuous safety hazard signal is generated and transmitted to the mobile terminal for prompting; like and An intermittent safety hazard signal is generated and transmitted to the mobile terminal for prompting; like and An accidental safety hazard signal is generated and transmitted to the mobile terminal, through which a prompt is given.

5. A computer-based feed formula data optimization processing system, used to implement the computer-based feed formula data optimization processing method according to any one of claims 1 to 4, characterized in that: It includes data collection and processing module, model building module, data analysis module and prompt module; A data acquisition and processing module collects a plurality of transmission information when the pre-processed feed formula data is transmitted through the network, including network transmission quality information and transmission signal interference information. After the collection, the network transmission quality information and the transmission signal interference information are processed, and the processed network transmission quality information and the transmission signal interference information are transmitted to the model building module; The model building module receives the network transmission quality information and transmission signal interference information processed by the data acquisition and processing module, establishes a data analysis model, and generates a data damage hidden danger assessment coefficient; The data analysis module compares and analyzes the data damage hidden danger assessment coefficient generated by the model building module with the pre-set data damage hidden danger assessment coefficient reference threshold, generates normal signals and abnormal signals, and at the same time, when generating abnormal signals, obtains several data damage hidden danger assessment coefficients generated during subsequent data transmission for comprehensive analysis, determines the abnormal hidden danger type of the feed formula data when it is transmitted through the network, and outputs it through the prompt module; The prompt module prompts the analysis results of the data analysis module through the mobile terminal.

Images