Real-time monitoring and analyzing method and system for food color change

Abstract

The invention provides a food color change real-time monitoring and analysis method and system. The method comprises the following steps: capturing a color change image of food, and constructing a multi-modal food color data set; based on the multi-modal food color data set, performing dynamic correction processing on food color change to obtain a color change trend analysis report; according to the color change trend analysis report, performing prediction processing on the attenuation speed and possible deterioration points of the food freshness, and generating a food shelf life evaluation result; and by utilizing the food shelf life evaluation result, through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, carrying out automatic planning processing on a whole flow path from production to consumption of food, dynamically adjusting storage conditions and a transportation time window, and generating a logistics scheme. According to the technical scheme provided by the invention, more accurate food color change dynamic correction processing is realized, so that the accuracy of food freshness prediction is remarkably improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of real-time monitoring technology, and in particular to a method and system for real-time monitoring and analysis of food color changes. Background Art

[0002] As consumers' demands for food safety and freshness continue to increase, real-time monitoring and analysis technologies in the food supply chain have become particularly important.

[0003] Currently, some food industries use traditional visual inspection systems combined with manual inspection to perform preliminary assessments of food color changes. These methods typically rely on photos or video streams taken at fixed angles, simple environmental sensor data collection, and then basic data processing algorithms to identify potential problem areas.

[0004] Traditional methods are difficult to fully capture all the details of food color changes, especially when light source conditions change, which can easily lead to misjudgment; the ability to predict food color change trends is limited, and it is impossible to accurately assess the rate of food freshness decay and its possible deterioration points. Summary of the invention

[0005] The embodiments of the present application provide a method and system for real-time monitoring and analysis of food color changes, so as to solve the problem of limited ability to predict food color change trends in the prior art.

[0006] In a first aspect, the present application provides a method for real-time monitoring and analysis of food color changes, comprising:

[0007] Use high-sensitivity imaging equipment from multiple angles and different spectral ranges to capture food color change images in real time, use environmental sensing devices to collect temperature, humidity, and light intensity parameters of the environment in which the food is located, and build a multimodal food color dataset;

[0008] Based on the multimodal food color dataset, the random forest algorithm under the integrated learning framework is combined with the adaptive color space mapping technology to dynamically correct the food color changes and obtain a color change trend analysis report;

[0009] According to the color change trend analysis report, a long short-term memory network based on time series analysis is used in combination with food component analysis technology and a grey prediction model to predict the decay rate of food freshness and possible deterioration points, and generate a food shelf life assessment result;

[0010] Utilizing the food shelf life assessment results, an intelligent logistics scheduling system driven by a multi-objective optimization algorithm is used to automatically plan and process the entire process path of food from production to consumption, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

[0011] Optionally, based on the multimodal food color dataset, the random forest algorithm under the integrated learning framework is combined with the adaptive color space mapping technology to dynamically correct the food color change and obtain a color change trend analysis report, including:

[0012] Using the multimodal food color dataset, adaptive color space mapping is performed on color information in different spectral ranges to eliminate color deviation caused by light source changes and obtain standardized color data;

[0013] Based on the standardized color data, a random forest algorithm is used to combine the color change patterns of foods under different environmental conditions to perform predictive modeling on the color changes of foods, thereby generating a food color change prediction model;

[0014] According to the food color change prediction model, the time series data of food color change is analyzed for trend and periodic characteristics, the color stability of food under different environmental conditions is evaluated, and the color change characteristic evaluation result is obtained;

[0015] Utilizing the color change characteristic evaluation results, the main trends, periodic characteristics, and color change rate and amplitude information of food color changes are integrated through data visualization technology and statistical analysis methods to generate a color change trend analysis report.

[0016] Optionally, based on the standardized color data, a random forest algorithm is used in combination with the color change patterns of the food under different environmental conditions to perform a predictive modeling process on the food color change to generate a food color change prediction model, including:

[0017] In calculating C pred (t) Before, the multimodal food color dataset needs to be preprocessed to eliminate the color deviation caused by light source changes through adaptive color space mapping technology to obtain standardized color data in preparation for building a random forest model for predicting food color changes;

[0018]

[0019] Among them, C pred (t) represents the predicted food color change value at time t, w i is the weight of the i-th tree in the random forest, reflecting the contribution of each tree to the final prediction result; C i (t) represents the standardized color data of the i-th sample at time t; E i(t) represents the environmental condition data of the i-th sample at time t; N is the number of samples; α is the adjustment coefficient related to the ambient temperature, which is used to adjust the effect of temperature on color change; β is the adjustment coefficient related to the ambient humidity, which is used to adjust the effect of humidity on color change; T(t) represents the ambient temperature at time t; H(t) represents the ambient humidity at time t; δ is the adjustment coefficient related to the ratio of temperature and humidity, which is used to reflect the combined effect of temperature and humidity on color change;

[0020] Calculate C pred (t), to generate f(C i (t), E i (t)) It is necessary to analyze the time series data of food color change, combine food component analysis technology, consider the influence of environmental conditions such as temperature and humidity, and correct the predicted value of color change to ensure the accuracy of the prediction;

[0021] f(C i (t), E i (t)) = C i (t)·(1+γ·sin(2π·F(E i (t)))+η·cos(2π·G(E i (t))))

[0022] Among them, C i (t) represents the standardized color data of the i-th sample at time t; E i (t) represents the environmental condition data of the i-th sample at time t; γ is a coefficient related to the periodic change of environmental conditions, which is used to adjust the effect of periodic changes in environmental conditions on color change; η is a coefficient related to another periodic change in environmental conditions, which is used to adjust the effect of different periodic changes on color change; F(E i (t)) represents the environmental condition E i The frequency function of (t) is used to capture the periodic effect of environmental condition changes on food color changes; G(E i (t)) represents the environmental condition E i Another frequency function of (t) is used to capture the different periodic effects of changes in environmental conditions on food color changes;

[0023] After calculating f(C i (t), E i (t)), in order to generate a food color change prediction model, it is necessary to comprehensively consider the main trends, periodic characteristics and environmental conditions of food color changes, use time series analysis methods and food component analysis technology to optimize model parameters, and finally generate a model that accurately predicts food color changes.

[0024] Optionally, the food color change prediction model is used to perform trend and periodic feature analysis on the time series data of the food color change, evaluate the color stability of the food under different environmental conditions, and obtain a color change feature evaluation result, including:

[0025] Based on the food color change prediction model, trend analysis is performed on the time series data of food color changes to identify the main trend direction and change rate of color changes and obtain color change trend information;

[0026] Using the color change trend information and combining it with Fourier transform technology, the time series data of food color change is analyzed and processed based on periodic characteristics, the periodic pattern of color change is extracted, and the periodic characteristic information of color change is obtained;

[0027] According to the color change trend information and the color change periodic characteristic information, by comparing the color changes of the food under different environmental conditions, the color stability of the food under different environmental conditions is evaluated, and a color stability evaluation index is generated;

[0028] The color stability evaluation index is used in combination with the correlation analysis of food ingredients and environmental conditions to comprehensively evaluate the color change characteristics of food under different environmental conditions and obtain a color change characteristic evaluation result.

[0029] Optionally, the color change characteristic evaluation result is used to integrate the main trend, periodic characteristics, and color change rate and amplitude information of food color changes through data visualization technology and statistical analysis methods to generate a color change trend analysis report, including:

[0030] Using the color change characteristic evaluation results, a visualization chart of food color change is generated through data visualization technology to intuitively display the main trends and periodic characteristics of food color change, thereby obtaining a color change trend chart;

[0031] Based on the color change trend graph, combined with statistical analysis methods, the rate and amplitude of food color change are quantitatively analyzed to evaluate the severity and change rules of food color change, and obtain color change rate and amplitude analysis results;

[0032] Based on the color change rate and amplitude analysis results, a comprehensive evaluation is performed on the color stability of the food under different environmental conditions, key factors affecting the color change of the food are extracted, and a comprehensive evaluation report on the color stability is obtained;

[0033] The color stability comprehensive evaluation report is used to integrate the main trends, periodic characteristics, and color change rate and amplitude information of food color changes to generate a color change trend analysis report.

[0034] Optionally, according to the color change trend analysis report, a long short-term memory network based on time series analysis is used in combination with food component analysis technology and a grey prediction model to predict the decay rate of food freshness and possible deterioration points, and generate a food shelf life assessment result, including:

[0035] According to the color change trend analysis report, extract the main trend, periodic characteristics, change rate and amplitude information of food color change, and construct a time series data set of food color change;

[0036] Using the time series data set of food color changes, combined with food component analysis technology, the decay rate of food freshness is modeled through a long short-term memory network to generate a food freshness decay rate prediction model;

[0037] Based on the food freshness decay rate prediction model, a grey prediction model is applied to supplement the prediction of the time series data of food color change, so as to enhance the accuracy and robustness of the prediction and obtain a comprehensive prediction result of food freshness;

[0038] Using the comprehensive prediction results of the food freshness, identifying key nodes in the food color change process that may indicate spoilage, assessing the risk of food spoilage under different conditions, and generating a food spoilage point prediction report;

[0039] Based on the food spoilage point prediction report, combined with food ingredient characteristics and historical data, a comprehensive assessment of the food's shelf life is conducted to generate a food shelf life assessment result.

[0040] Optionally, based on the food freshness decay rate prediction model, a grey prediction model is applied to supplement the prediction of the time series data of food color change to enhance the accuracy and robustness of the prediction, and obtain a comprehensive prediction result of food freshness, including:

[0041] In calculating F gray Before (t), it is necessary to preprocess the time series data of food color change, extract environmental condition data, and combine it with the food freshness decay rate prediction model C pred (t) and food composition analysis techniques to provide input for supplementary prediction of grey prediction models;

[0042]

[0043] Among them, F gray(t) represents the food freshness supplement prediction value obtained by applying the grey prediction model at time t, α is the weight coefficient of the grey prediction model, GM(1,1)(t) represents the prediction value of the grey prediction model GM(1,1) based on time t, β is the adjustment coefficient related to the food freshness prediction value, γ is the sensitivity coefficient related to the food color change prediction value, C pred (t) represents the predicted food color change value at time t, δ is the reference value of food color change, which is used to adjust the sensitivity of prediction, λ is the coefficient related to the periodic change of ambient temperature, ω is the angular frequency of ambient temperature change, T(t) represents the ambient temperature at time t, φ is the phase angle of ambient temperature change;

[0044] After calculating F gray (t), to generate C comp (t), we need to change F gray (t) and the predicted value of food color change C pred (t) Fusion, adjustment of the weight coefficients of the two, and introduction of the influence of environmental humidity and food packaging characteristics to generate a more accurate prediction value of food freshness;

[0045]

[0046] Among them, C comp (t) represents the food freshness value obtained by comprehensive prediction at time t, θ is the weight coefficient of the food color change prediction value, C pred (t) represents the predicted food color change value at time t, F gray (t) represents the supplementary prediction value of food freshness obtained by applying the grey prediction model at time t, μ is the adjustment coefficient related to the ambient humidity and food packaging characteristics, H(t) represents the ambient humidity at time t, and P(t) represents the food packaging characteristic parameter at time t, which is used to reflect the impact of packaging on food freshness;

[0047] Calculate C comp (t), in order to obtain a comprehensive prediction result of food freshness, it is necessary to combine the food ingredient characteristics and historical data, evaluate the decay rate of food freshness and possible spoilage points, identify key spoilage nodes, evaluate spoilage risks, and finally generate a comprehensive prediction result of food freshness.

[0048] Optionally, the time series data set of the food color change is used in combination with food component analysis technology to model the decay rate of food freshness through a long short-term memory network to generate a food freshness decay rate prediction model, including:

[0049] Based on the time series data set of food color changes, combined with the food composition information provided by food composition analysis technology, the data is preprocessed, including missing value filling, outlier processing and data standardization, to ensure that the data quality meets the modeling requirements;

[0050] Using the preprocessed food color change time series data, a long short-term memory network model is constructed. This long short-term memory network model can capture the long-term dependencies in the time series and effectively reflect the change of food freshness over time.

[0051] In the long short-term memory network model, food ingredient information is used as an auxiliary input and acts together with time series data in the model training process to enhance the model's ability to understand the changing characteristics of food freshness and improve prediction accuracy;

[0052] The long short-term memory network model is trained iteratively and cross-validation technology is used to evaluate the model performance to ensure the generalization ability of the model under different time periods and different food composition conditions. Finally, a food freshness decay rate prediction model is generated. The food freshness decay rate prediction model can accurately predict the food freshness decay rate.

[0053] Optionally, the food shelf life evaluation result is used to automatically plan the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan, including:

[0054] Using the food shelf life evaluation results, a multi-objective optimization problem for food logistics path planning is constructed to obtain an optimization target set;

[0055] Based on the optimization target set, a multi-objective optimization algorithm is used to automatically plan the entire process path of food from production to consumption, and a preliminary logistics path planning solution is obtained;

[0056] According to the preliminary logistics route planning scheme, combined with the food shelf life evaluation results, dynamically adjust the storage conditions of each storage point, wherein the storage conditions at least include temperature and humidity, and generate optimized storage condition settings;

[0057] The optimized storage condition settings are used to further optimize the transportation time window and generate a final logistics plan.

[0058] In a second aspect, the present application provides a real-time monitoring and analysis system for food color changes, including:

[0059] A construction module is used to capture the color change images of food in real time using high-sensitivity imaging devices from multiple angles and different spectral ranges, and to collect the temperature, humidity, and light intensity parameters of the environment in which the food is located using an environmental sensing device to construct a multimodal food color dataset;

[0060] A correction module is used to dynamically correct the color change of food based on the multimodal food color dataset by combining the random forest algorithm under the integrated learning framework with the adaptive color space mapping technology to obtain a color change trend analysis report;

[0061] A prediction module is used to predict the decay rate of food freshness and possible deterioration points according to the color change trend analysis report, using a long short-term memory network based on time series analysis combined with food component analysis technology and a grey prediction model, and generate a food shelf life assessment result;

[0062] The adjustment module is used to utilize the food shelf life evaluation results to automatically plan and process the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

[0063] In an embodiment of the present application, a high-sensitivity imaging device is used to capture color change images of food in real time from multiple angles and different spectral ranges, and an environmental sensing device is used to collect temperature, humidity, and light intensity parameters of the environment in which the food is located to construct a multimodal food color data set; based on the multimodal food color data set, a random forest algorithm under an integrated learning framework is combined with an adaptive color space mapping technology to dynamically correct the color changes of the food and obtain a color change trend analysis report; based on the color change trend analysis report, a long short-term memory network based on time series analysis is combined with food component analysis technology and a gray prediction model to predict the decay rate of food freshness and possible deterioration points, and generate a food shelf life assessment result; using the food shelf life assessment result, an intelligent logistics scheduling system driven by a multi-objective optimization algorithm is used to automatically plan the entire process path of food from production to consumption, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

[0064] The technical solution of this application has the following beneficial effects:

[0065] The present invention uses high-sensitivity imaging devices from multiple angles and different spectral ranges to capture food color change images in real time, and combines the temperature, humidity and light intensity parameters collected by the environmental sensing device to construct a comprehensive multimodal food color data set. This method can not only capture the details of food color changes more accurately, but also effectively eliminate the color deviation caused by light source changes, thereby providing a more reliable color change trend analysis report. Based on this report, a method combining the random forest algorithm under the ensemble learning framework with the adaptive color space mapping technology is used to dynamically correct the food color changes, further improving the accuracy of color change prediction. In addition, by combining the long short-term memory network (LSTM) of time series analysis, food component analysis technology and gray prediction model, the present invention can accurately predict the decay rate of food freshness and its possible deterioration point, and generate scientific food shelf life evaluation results. This comprehensive prediction method overcomes the limitations of traditional methods that rely only on visual inspection and basic environmental parameter monitoring, and greatly improves the accuracy and reliability of food freshness prediction. Finally, using the food shelf life evaluation results, the present invention realizes the automatic planning and processing of the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm. The system can dynamically adjust storage conditions and transportation time windows to ensure that food is stored and transported under optimal conditions, thereby effectively extending the shelf life of food, reducing waste, and improving the overall efficiency of the supply chain. This method solves the problem of the lack of dynamic adjustment capabilities and the inability to effectively extend the shelf life of food in existing solutions, providing a more intelligent and efficient solution for the food industry.

[0066] Furthermore, based on the multimodal food color dataset, this method first processes the color information in different spectral ranges through adaptive color space mapping to eliminate the influence caused by light source changes, and then uses the random forest algorithm to combine the color change pattern of food under specific environmental conditions to establish a prediction model. Then, the trend and periodicity analysis of the time series color change data is performed to evaluate the color stability, and finally the main trend, periodic characteristics and change rate are integrated to generate a comprehensive color change trend analysis report. This method effectively improves the accuracy and reliability of food color change monitoring by finely processing food color data and using advanced machine learning technology to construct a prediction model. It can not only more accurately identify subtle color changes caused by environmental factors, but also help to deeply understand the law of food color evolution over time, providing strong data support for food quality control. In addition, by generating a detailed color change trend analysis report, relevant personnel can more intuitively understand the state changes of food, so as to take timely measures to prevent food deterioration, ensure food safety, and optimize inventory management and logistics scheduling processes.

[0067] Furthermore, according to the color change trend analysis report, this method extracts the main trend, periodic characteristics, change rate and amplitude information of food color change, and constructs a time series data set. The data set is combined with food component analysis technology to model the decay rate of food freshness through long short-term memory network, and the gray prediction model is applied for supplementary prediction to enhance the accuracy and robustness of the prediction, thereby generating a comprehensive prediction result of food freshness. Based on these prediction results, the key nodes of deterioration are identified, the deterioration risk under different conditions is evaluated, and finally the food shelf life evaluation results are generated. By combining advanced machine learning technology and food component analysis, this method can more accurately predict the decay rate of food freshness and possible deterioration points, thereby providing a more scientific and reliable food shelf life evaluation. This not only helps to timely discover and deal with potential quality problems and reduce food waste, but also provides strong support for supply chain management to ensure the safety and quality of food in the entire circulation process. In addition, by identifying key deterioration nodes, targeted measures can be taken to extend the shelf life of food, optimize inventory management and logistics scheduling, and improve overall operational efficiency.

[0068] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0070] Figure 1 A flowchart of a method for real-time monitoring and analysis of food color changes provided in an embodiment of the present application;

[0071] Figure 2 A schematic diagram of the structure of a real-time monitoring and analysis system for food color changes provided in an embodiment of the present application;

[0072] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0074] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0075] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0076] Figure 1 A flowchart of a method for real-time monitoring and analysis of food color changes is provided for the present application embodiment, such as Figure 1 As shown, the method includes:

[0077] 101. Use high-sensitivity imaging equipment from multiple angles and different spectral ranges to capture food color change images in real time, use environmental sensing devices to collect temperature, humidity, and light intensity parameters of the environment in which the food is located, and construct a multimodal food color dataset;

[0078] The multimodal food color dataset includes food color change images captured from multiple angles and different spectral ranges (such as visible light, near infrared, etc.) by high-sensitivity imaging equipment, as well as parameters such as temperature, humidity, and light intensity collected by environmental sensing devices. These data are used to comprehensively monitor the color changes of food and the environmental conditions in which they are located.

[0079] In the embodiment of the present application, during the production, storage or transportation of food, a high-sensitivity imaging device is used to capture the color change images of the food in real time from different angles and spectral ranges, and the environment sensing device is used to simultaneously record the temperature, humidity and light intensity of the environment in which the food is located. These images and environmental parameters together constitute a multimodal data set, which provides basic data for subsequent color change analysis.

[0080] Suppose a food processing company needs to monitor the color changes of a batch of fresh fruits. First, multiple high-sensitivity cameras are installed at key locations of the fruit production line. Each camera is equipped with multiple spectral filters that can capture visible light and near-infrared images at the same time. In addition, environmental sensors are deployed in the same area to monitor and record the temperature, humidity, and light intensity of the area in real time. Whenever the fruit passes by the camera, the system automatically triggers the shooting and stores the image together with the corresponding environmental data in the database, forming a multimodal food color dataset containing timestamps, images, and environmental parameters.

[0081] 102. Based on the multimodal food color dataset, a random forest algorithm under an integrated learning framework is combined with an adaptive color space mapping technology to dynamically correct the color change of the food and obtain a color change trend analysis report;

[0082] Dynamic correction processing is based on a multimodal food color dataset. It uses a combination of the random forest algorithm under an integrated learning framework and adaptive color space mapping technology to eliminate color deviations caused by light source changes, obtain standardized color data, and then perform predictive modeling on food color changes, ultimately generating a color change trend analysis report.

[0083] In this step, adaptive color space mapping technology is applied to images in the multimodal food color dataset to eliminate color deviation caused by light source changes, and then a prediction model is established by combining the color change patterns of food under different environmental conditions using a random forest algorithm. Based on this model, trend and periodic feature analysis is performed on the time series data of food color changes to evaluate food color stability, and finally integrated to generate a color change trend analysis report.

[0084] Optionally, in step 102, based on the multimodal food color dataset, a random forest algorithm under an integrated learning framework is combined with an adaptive color space mapping technology to dynamically correct the food color change, thereby obtaining a color change trend analysis report, including:

[0085] The multimodal food color data set is used to perform adaptive color space mapping processing on color information in different spectral ranges to eliminate color deviations caused by light source changes and obtain standardized color data; based on the standardized color data, a random forest algorithm is used in combination with the color change patterns of foods under different environmental conditions to perform predictive modeling processing on food color changes and generate a food color change prediction model; according to the food color change prediction model, trend and periodic feature analysis and processing are performed on time series data of food color changes to evaluate the color stability of foods under different environmental conditions and obtain color change feature evaluation results; using the color change feature evaluation results, the main trends, periodic features, and color change rate and amplitude information of food color changes are integrated through data visualization technology and statistical analysis methods to generate a color change trend analysis report.

[0086] Wherein, the trend and periodicity characteristic analysis and processing of the time series data of the food color change are performed according to the food color change prediction model, the color stability of the food under different environmental conditions is evaluated, and the color change characteristic evaluation results are obtained, including:

[0087] Based on the food color change prediction model, trend analysis and processing are performed on the time series data of food color changes to identify the main trend direction and change rate of color changes and obtain color change trend information; using the color change trend information and combining it with Fourier transform technology, periodic feature analysis and processing are performed on the time series data of food color changes to extract the periodic pattern of color changes and obtain color change periodic feature information; based on the color change trend information and the color change periodic feature information, by comparing the color changes of food under different environmental conditions, the color stability of food under different environmental conditions is evaluated to generate a color stability evaluation index; using the color stability evaluation index and combining it with the correlation analysis of food ingredients and environmental conditions, the color change characteristics of food under different environmental conditions are comprehensively evaluated to obtain a color change feature evaluation result.

[0088] Wherein, the color change characteristic evaluation results are used to integrate the main trends, periodic characteristics, and color change rate and amplitude information of food color changes through data visualization technology and statistical analysis methods to generate a color change trend analysis report, including:

[0089] Using the color change characteristic evaluation results, a visualization chart of food color changes is generated through data visualization technology, which intuitively displays the main trends and periodic characteristics of food color changes, and obtains a color change trend chart; based on the color change trend chart, combined with statistical analysis methods, the rate and amplitude of food color changes are quantitatively analyzed, the severity and change rules of food color changes are evaluated, and the color change rate and amplitude analysis results are obtained; based on the color change rate and amplitude analysis results, the color stability of food under different environmental conditions is comprehensively evaluated, the key factors affecting food color changes are extracted, and a color stability comprehensive evaluation report is obtained; using the color stability comprehensive evaluation report, the main trends, periodic characteristics, and color change rate and amplitude information of food color changes are integrated to generate a color change trend analysis report.

[0090] In the embodiments of the present application, first, the multimodal food color data set is adaptively mapped to the color space to eliminate the color deviation caused by the change of the light source and obtain standardized color data; secondly, based on the standardized color data, a food color change prediction model is established by combining the color change patterns under different environmental conditions with the random forest algorithm; thirdly, the model is used to perform trend analysis on the time series data of food color changes to identify the main trend direction and change rate, and at the same time, the Fourier transform technology is combined to extract periodic features and evaluate color stability; finally, through data visualization technology and statistical analysis methods, the main trends, periodic features, change rate and amplitude information are integrated to generate a color change trend analysis report.

[0091] Suppose a food processing company needs to monitor the color changes of a batch of fresh strawberries. First, capture the color change images of strawberries from multiple angles and different spectral ranges, and record parameters such as ambient temperature, humidity, and light intensity to construct a multimodal food color dataset; secondly, apply adaptive color space mapping technology to the images in the dataset to eliminate the color deviation caused by different light sources and obtain standardized color data; then, use the random forest algorithm to combine the color change pattern of strawberries under different temperature, humidity, and light conditions to establish a food color change prediction model; then, based on the model, perform trend analysis on the time series data of strawberry color change, identify the main trend direction and change rate of color change, and combine Fourier transform technology to extract the periodic pattern of color change and evaluate the color stability of strawberries under different environmental conditions; finally, generate a visualization chart of strawberry color change through data visualization technology to intuitively display the main trends and periodic characteristics, and combine statistical analysis methods to quantify the rate and amplitude of color change, evaluate the change law, and finally generate a detailed color change trend analysis report to provide a scientific basis for subsequent freshness prediction and logistics scheduling; through the above steps, companies can more accurately monitor and manage the color changes of strawberries to ensure product quality and supply chain efficiency.

[0092] This application considers that the construction of a food color change prediction model is to accurately predict the color change trend of food under different environmental conditions, so as to evaluate the freshness and shelf life of food. The model combines standardized color data, environmental condition data, and food component analysis technology, and is comprehensively modeled through random forest algorithm and adaptive color space mapping technology.

[0093] Optionally, based on the standardized color data, a random forest algorithm is used in combination with the color change patterns of the food under different environmental conditions to perform a predictive modeling process on the food color change to generate a food color change prediction model, including:

[0094] In calculating C pred (t) Before, the multimodal food color dataset needs to be preprocessed to eliminate the color deviation caused by light source changes through adaptive color space mapping technology to obtain standardized color data in preparation for building a random forest model for predicting food color changes;

[0095]

[0096] Among them, C pred (t) represents the predicted food color change value at time t, w i is the weight of the i-th tree in the random forest, reflecting the contribution of each tree to the final prediction result; C i (t) represents the standardized color data of the i-th sample at time t; E i (t) represents the environmental condition data of the i-th sample at time t; N is the number of samples; α is the adjustment coefficient related to the ambient temperature, which is used to adjust the effect of temperature on color change; β is the adjustment coefficient related to the ambient humidity, which is used to adjust the effect of humidity on color change; T(t) represents the ambient temperature at time t; H(t) represents the ambient humidity at time t; δ is the adjustment coefficient related to the ratio of temperature and humidity, which is used to reflect the combined effect of temperature and humidity on color change;

[0097] Calculate C pred (t), to generate f(C i (t), E i (t)) It is necessary to analyze the time series data of food color change, combine food component analysis technology, consider the influence of environmental conditions such as temperature and humidity, and correct the predicted value of color change to ensure the accuracy of the prediction;

[0098] f(C i (t), E i (t)) = C i (t)·(1+γ·sin(2π·F(E i(t)))+η·cos(2π·G(E i (t))))

[0099] Among them, C i (t) represents the standardized color data of the i-th sample at time t; E i (t) represents the environmental condition data of the i-th sample at time t; γ is a coefficient related to the periodic change of environmental conditions, which is used to adjust the effect of periodic changes in environmental conditions on color change; η is a coefficient related to another periodic change in environmental conditions, which is used to adjust the effect of different periodic changes on color change; F(E i (t)) represents the environmental condition E i The frequency function of (t) is used to capture the periodic effect of environmental condition changes on food color changes; G(E i (t)) represents the environmental condition E i Another frequency function of (t) is used to capture the different periodic effects of changes in environmental conditions on food color changes;

[0100] After calculating f(C i (t), E i (t)), in order to generate a food color change prediction model, it is necessary to comprehensively consider the main trends, periodic characteristics and environmental conditions of food color changes, use time series analysis methods and food component analysis technology to optimize model parameters, and finally generate a model that accurately predicts food color changes.

[0101] The formula aims to accurately predict the color change of food by combining environmental conditions (such as temperature, humidity and their periodic changes) through ensemble learning methods (such as random forests). pred (t) Improve the stability and accuracy of prediction by integrating the prediction results of multiple trees and adjusting the influence of temperature and humidity; f(C i (t), E i (t) captures the complex pattern of color change by considering the periodic changes of standardized color data and environmental conditions. These designs ensure that the model can fully reflect the color change trend of food under different environmental conditions.

[0102] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0103]

[0104] Random Forest Contribution This item represents the contribution of each tree in the random forest to the final prediction result, and improves the stability and accuracy of the prediction through ensemble learning methods;

[0105] Temperature influence This term takes into account the effect of temperature on color change, where an exponential function is used to adjust the nonlinear effect of temperature change on color change;

[0106] Humidity and temperature ratio influence This term takes into account the effect of the relative relationship between humidity and temperature on color change, and a logarithmic function is used to capture changes in this ratio relationship;

[0107] The following is a brief introduction to how to obtain the parameters of the formula:

[0108] w i The weight of each tree is obtained through the random forest training process; f(C i (t), E i (t)): According to the formula f(C i (t), E i (t)) = C i (t)·(1+γ·sin(2π·F(E i (t)))+η·cos(2π.G(E i (t)))) calculation; α, β, δ are set by historical data fitting or expert experience; T(t) and H(t) are the temperature and humidity data collected in real time by the environmental sensing device:

[0109] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0110] f(C i (t), E i (t)) = C i (t)·(1+γ·sin(2π·F(E i (t)))+η·cos(2π·G(E i (t))))

[0111] Basic color data item: C i (t): This term represents the standardized color data of the i-th sample at time t, which is the basis for prediction;

[0112] Environmental periodic impact term γ·sin(2π·F(E i (t))): This term takes into account the effect of periodic changes in environmental conditions on color change, and the sine function is used to capture the periodic changes;

[0113] Environmental periodic impact term η·cos(2π·G(E i (t))): This term considers the effect of another periodic change on color change, and the cosine function is used to capture different periodic changes;

[0114] The following is a brief introduction to how to obtain the parameters of the formula:

[0115] C i (t) Standardized color data after processing by adaptive color space mapping; E i (t) Environmental condition data collected in real time by environmental sensing devices; γ, η are set by historical data fitting or expert experience; F(E i (t)) and G(E i (t)) Frequency function extracted from environmental condition data by Fourier transform or other methods;

[0116] Suppose a food processing company needs to predict the color change of a batch of fresh fruits. First, the color change images of the fruits and the environmental temperature and humidity data are collected through high-sensitivity imaging equipment and environmental sensing devices; secondly, the data is preprocessed to eliminate the deviation caused by light source changes and obtain standardized color data; then, the random forest algorithm is used to combine the environmental condition data to build a prediction model.

[0117] Example Calculation

[0118] Assume N = 5, the weight of each tree is w 1 =0.2, w 2 =0.3, w 3 =0.1, w 4 =0.2, w 5 =0.2;

[0119] Standardized color data C i (t) are 0.8, 0.7, 0.9, 0.6, and 0.8 respectively;

[0120] Environmental Condition Data i (t) includes temperature T(t) = 25°C and humidity H(t) = 60%;

[0121] Parameter settings: α=0.1, β=0.01, δ=0.2, γ=0.05, η=0.03;

[0122] Frequency function F(E i (t))=0.01,G(E i (t)) = 0.02;

[0123]

[0124] C pred (t)=0.71+0.00006+(-0.05)≈0.66006;

[0125] Through the above calculation, it is predicted that under the current environmental conditions, the color change value of the fruit is 0.66006. Assuming that the threshold of color change is set to 0.7, since the result 0.6606 is less than the set threshold, it shows that under the given temperature and humidity conditions, the color of the fruit changes slowly and maintains a good freshness. Based on this prediction result, the company can optimize the storage and transportation conditions to ensure that the fruit is delivered to consumers in the best condition.

[0126] By combining multimodal food color datasets and environmental conditions, using random forest algorithms and adaptive color space mapping technology, this method can more accurately predict the color change trend of food. This not only improves the accuracy of food freshness prediction, but also helps companies optimize environmental conditions during storage and transportation to ensure that food is delivered to consumers in the best condition, thereby reducing the risk of food spoilage, extending shelf life, and improving overall supply chain efficiency.

[0127] 103. According to the color change trend analysis report, a long short-term memory network based on time series analysis is used in combination with food component analysis technology and a grey prediction model to predict the decay rate of food freshness and possible deterioration points, and generate a food shelf life assessment result;

[0128] Based on the color change trend analysis report, the long short-term memory network (LSTM) is used in combination with food composition analysis technology and grey prediction model to predict the freshness decay rate and possible deterioration points of food, and generate food shelf life assessment results.

[0129] In this step, the main trends, periodic characteristics, change rates and amplitude information in the color change trend analysis report are extracted to construct a time series data set. The decay rate of food freshness is modeled using LSTM, and then the gray prediction model is applied to supplement the prediction to enhance the accuracy and robustness of the prediction. Based on the comprehensive prediction results, the key nodes of deterioration are identified, the deterioration risk is assessed, and finally the food shelf life assessment results are generated.

[0130] Optionally, in step 103, based on the color change trend analysis report, a long short-term memory network based on time series analysis is used in combination with food component analysis technology and a grey prediction model to predict the decay rate of food freshness and possible deterioration points, and generate a food shelf life assessment result, including:

[0131] According to the color change trend analysis report, the main trend, periodic characteristics, change rate and amplitude information of food color change are extracted to construct a time series data set of food color change; using the time series data set of food color change, combined with food component analysis technology, the decay rate of food freshness is modeled and processed through a long short-term memory network to generate a food freshness decay rate prediction model; based on the food freshness decay rate prediction model, a gray prediction model is applied to supplement the prediction of the time series data of food color change, enhance the accuracy and robustness of the prediction, and obtain a comprehensive prediction result of food freshness; using the comprehensive prediction result of food freshness, key nodes that may indicate deterioration in the process of food color change are identified, the deterioration risk of food under different conditions is evaluated, and a food deterioration point prediction report is generated; according to the food deterioration point prediction report, combined with food component characteristics and historical data, the shelf life of the food is comprehensively evaluated to generate a food shelf life evaluation result.

[0132] The method of using the time series data set of food color changes, combined with food component analysis technology, to model the decay rate of food freshness through a long short-term memory network to generate a food freshness decay rate prediction model includes:

[0133] Based on the time series data set of food color changes, combined with the food ingredient information provided by food ingredient analysis technology, the data is preprocessed, including missing value filling, outlier processing and data standardization, to ensure that the data quality meets the modeling requirements; using the preprocessed food color change time series data, a long short-term memory network model is constructed, and the long short-term memory network model can capture the long-term dependencies in the time series and effectively reflect the changing pattern of food freshness over time; in the long short-term memory network model, the food ingredient information is used as an auxiliary input and acts together with the time series data in the model training process to enhance the model's understanding of the characteristics of food freshness changes and improve prediction accuracy; by continuously iteratively training the long short-term memory network model, the cross-validation technology is used to evaluate the model performance to ensure the generalization ability of the model under different time periods and different food ingredient conditions, and finally a food freshness decay rate prediction model is generated, and the food freshness decay rate prediction model can accurately predict the food freshness decay rate.

[0134] In the embodiments of the present application, first, according to the color change trend analysis report, the main trends, periodic characteristics, change rates and amplitude information of food color changes are extracted to construct a time series data set; secondly, in combination with the food ingredient information provided by the food ingredient analysis technology, the data is preprocessed, including missing value filling, outlier processing and data standardization, to ensure that the data quality meets the modeling requirements; thirdly, the preprocessed data is used to construct a long short-term memory network model, which can capture the long-term dependencies in the time series, effectively reflect the change pattern of food freshness over time, and use food ingredient information as auxiliary input to improve the prediction accuracy of the model; finally, by continuously iteratively training the model and using cross-validation technology to evaluate the performance, the generalization ability of the model under different time periods and different food ingredient conditions is ensured, and a food freshness decay rate prediction model is generated.

[0135] Suppose a food processing company needs to monitor the freshness of a batch of fresh milk. First, extract the main trends, periodic characteristics, change rates and amplitudes of milk color changes from the color change trend analysis report to construct a time series data set; second, combine the milk composition information provided by food ingredient analysis technology to preprocess the data, including missing value filling, outlier processing and data standardization to ensure that the data quality meets the modeling requirements; third, use the preprocessed data to build a long short-term memory network model, which can capture the long-term dependencies in the time series and effectively reflect the changes in milk freshness over time. It also uses milk composition information (such as fat content, protein content, etc.) as auxiliary inputs, and works together with time series data in the model training process to improve the prediction accuracy of the model; then, train the model through continuous iterations and use cross-validation technology to evaluate model performance to ensure that the model The generalization ability under different time periods and different milk composition conditions finally generates a prediction model that can accurately predict the decay rate of milk freshness; then, based on this model, the gray prediction model is applied to supplement the prediction of the time series data of milk color change, enhance the accuracy and robustness of the prediction, and obtain a comprehensive prediction result of milk freshness; the comprehensive prediction results are used to identify the key nodes that may indicate spoilage in the process of milk color change, evaluate the spoilage risk of milk under different conditions, and generate a milk spoilage point prediction report; finally, combined with the milk component characteristics and historical data, a comprehensive evaluation of the shelf life of milk is conducted to generate a shelf life evaluation result; through the above steps, enterprises can more accurately predict the decay rate of milk freshness and spoilage points, thereby optimizing inventory management and logistics scheduling, and ensuring product quality and consumer safety.

[0136] This application considers that in the prediction of food freshness, combining the gray prediction model with the time series data of food color changes can enhance the accuracy and robustness of the prediction. By introducing environmental condition data, food ingredient analysis technology and packaging characteristic parameters, it is possible to more comprehensively evaluate the trend of food freshness changes, thereby generating a comprehensive prediction result.

[0137] Optionally, based on the food freshness decay rate prediction model, a grey prediction model is applied to supplement the prediction of the time series data of food color change to enhance the accuracy and robustness of the prediction, and obtain a comprehensive prediction result of food freshness, including:

[0138] In calculating F gray Before (t), it is necessary to preprocess the time series data of food color change, extract environmental condition data, and combine it with the food freshness decay rate prediction model C pred (t) and food composition analysis techniques to provide input for supplementary prediction of grey prediction models;

[0139]

[0140] Among them, F gray (t) represents the food freshness supplement prediction value obtained by applying the grey prediction model at time t, α is the weight coefficient of the grey prediction model, GM(1,1)(t) represents the prediction value of the grey prediction model GM(1,1) based on time t, β is the adjustment coefficient related to the food freshness prediction value, γ is the sensitivity coefficient related to the food color change prediction value, C pred (t) represents the predicted food color change value at time t, δ is the reference value of food color change, which is used to adjust the sensitivity of prediction, λ is the coefficient related to the periodic change of ambient temperature, ω is the angular frequency of ambient temperature change, T(t) represents the ambient temperature at time t, φ is the phase angle of ambient temperature change;

[0141] After calculating F gray (t), to generate C comp (t), F gray (t) and the predicted value of food color change C pred (t) Fusion, adjustment of the weight coefficients of the two, and introduction of the influence of environmental humidity and food packaging characteristics to generate a more accurate prediction value of food freshness;

[0142]

[0143] Among them, C comp (t) represents the food freshness value obtained by comprehensive prediction at time t, θ is the weight coefficient of the food color change prediction value, C pred (t) represents the predicted food color change value at time t, Fgray (t) represents the supplementary prediction value of food freshness obtained by applying the grey prediction model at time t, μ is the adjustment coefficient related to the ambient humidity and food packaging characteristics, H(t) represents the ambient humidity at time t, and P(t) represents the food packaging characteristic parameter at time t, which is used to reflect the impact of packaging on food freshness;

[0144] Calculate C comp (t), in order to obtain a comprehensive prediction result of food freshness, it is necessary to combine the food ingredient characteristics and historical data, evaluate the decay rate of food freshness and possible spoilage points, identify key spoilage nodes, evaluate spoilage risks, and finally generate a comprehensive prediction result of food freshness.

[0145] The formula aims to enhance the accuracy and robustness of food freshness prediction by combining the grey prediction model and the time series data of food color changes. Specifically, the formula aims to comprehensively consider the impact of environmental conditions, food ingredient analysis technology and packaging characteristics on food freshness, thereby generating more comprehensive and reliable comprehensive prediction results to help companies make more accurate decisions in supply chain management.

[0146] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0147]

[0148] Grey prediction model term α·GM(1,1)(t): Use the grey prediction model GM(1,1) to make supplementary predictions on time series data to improve the accuracy of predictions;

[0149] Food freshness forecast adjustment The predicted value of food freshness is adjusted through the Sigmoid function to make it smoother and have nonlinear characteristics;

[0150] Ambient temperature periodic influence term λ·sin(ω·T(t)+φ): Considering the impact of periodic changes in ambient temperature on food freshness, a sine function is used to capture this periodic change;

[0151] The following is a brief introduction to how to obtain the parameters of the formula:

[0152] α is set by fitting historical data or expert experience; GM(1,1)(t) is calculated by the grey prediction model GM(1,1); β is set by fitting historical data or expert experience; γ is set by fitting historical data or expert experience; Cpre d (t) is calculated by the food color change prediction model; δ is set by historical data fitting or expert experience; λ is set by historical data fitting or expert experience; ωAngular frequency extracted from ambient temperature data by Fourier transform or other methods; T(t) is ambient temperature data collected in real time by the environmental sensing device; φ is the phase angle extracted from ambient temperature data by Fourier transform or other methods;

[0153] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0154]

[0155] Food color change prediction term θ·C pred (t): retain the main contribution of the food color change prediction value to ensure the accuracy of the basic prediction;

[0156] Grey prediction model supplementary term (1-θ)·F gray (t): The results of the grey prediction model are integrated with the predicted value of food color change to further improve the robustness of the prediction;

[0157] Environmental humidity and packaging characteristics Considering the effects of ambient humidity and food packaging characteristics on freshness, a logarithmic function is used to capture the changes in these factors;

[0158] The following is a brief introduction to how to obtain the parameters of the formula:

[0159] θ is set by fitting historical data or expert experience; Cpred(t) is calculated by the food color change prediction model; Fgra y (t) is calculated by the above formula; μ Through historical data fitting or expert experience setting; H(t) is the environmental humidity data collected in real time by the environmental sensing device; P(t) is obtained through food packaging characteristic data;

[0160] Suppose a food processing company needs to predict the freshness of a batch of fresh fruits. First, the color change images of the fruits and the environmental temperature and humidity data are collected through high-sensitivity imaging equipment and environmental sensing devices; secondly, the data is preprocessed to eliminate the deviation caused by light source changes and obtain standardized color data; then, a comprehensive prediction model is constructed using the food freshness decay rate prediction model and the gray prediction model.

[0161] Assume α=0.5, β=0.3, γ=0.05, δ=0.7, λ=0.2, ω=0.1, φ=0.2;

[0162] Prediction value Cpred(t)=0.66006;

[0163] Ambient temperature T(t) = 25°C;

[0164] Grey prediction model value GM(1,1)(t)=0.7;

[0165] θ = 0.6, μ = 0.1;

[0166] Ambient humidity H(t) = 60%;

[0167] Packaging characteristic parameter P(t) = 0.8;

[0168] Substitute data for calculation

[0169]

[0170] Fgray(t)=0.35+0.3·0.475+0.2·0.999≈0.6425;

[0171]

[0172] C comp (t)=0.396036+0.257+0.1·2.041≈0.657146;

[0173] Through the above calculation, it is predicted that under the current environmental conditions, the freshness value of the fruit is 0.657146. Assuming that the threshold of freshness is set to 0.7, since the result 0.657146 is less than the set threshold, it shows that under the given temperature, humidity and packaging conditions, the freshness of the fruit is well maintained. Based on this prediction result, the company can optimize the storage and transportation conditions to ensure that the fruit is delivered to consumers in the best condition.

[0174] By combining the grey prediction model with the time series data of food color changes, this method can significantly improve the accuracy and robustness of food freshness prediction. This not only helps companies more accurately assess the rate of food freshness decay and possible spoilage points, but also optimizes storage and transportation conditions to ensure that food is delivered to consumers in the best condition, thereby reducing the risk of food spoilage, extending the shelf life, and improving overall supply chain efficiency.

[0175] 104. Utilizing the food shelf life assessment results, an intelligent logistics scheduling system driven by a multi-objective optimization algorithm is used to automatically plan and process the entire process path of food from production to consumption, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

[0176] Based on the food shelf life assessment results, an intelligent logistics scheduling system driven by a multi-objective optimization algorithm automatically plans the entire process path of food from production to consumption, and dynamically adjusts storage conditions and transportation time windows to ensure that food is circulated under optimal conditions and extends its shelf life.

[0177] In this step, the food shelf life evaluation results are used to construct a multi-objective optimization problem for logistics path planning. A multi-objective optimization algorithm is used to automatically plan the entire process path from production to consumption. Based on the planning results, the temperature and humidity conditions of each storage point are dynamically adjusted, and the transportation time window is optimized to generate the optimal logistics solution.

[0178] Optionally, the food shelf life evaluation result is used in step 104 to automatically plan the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan, including:

[0179] Using the food shelf life evaluation results, a multi-objective optimization problem for food logistics path planning is constructed to obtain an optimization target set; based on the optimization target set, a multi-objective optimization algorithm is used to automatically plan and process the entire process path from food production to consumption to obtain a preliminary logistics path planning scheme; based on the preliminary logistics path planning scheme and in combination with the food shelf life evaluation results, the storage conditions of each storage point are dynamically adjusted, the storage conditions at least including temperature and humidity, to generate optimized storage condition settings; using the optimized storage condition settings, the transportation time window is further optimized to generate a final logistics plan.

[0180] In the embodiments of the present application, firstly, a multi-objective optimization problem of food logistics path planning is constructed using the food shelf life evaluation results to obtain an optimization target set; secondly, based on the optimization target set, a multi-objective optimization algorithm is used to automatically plan and process the entire process path of food from production to consumption to obtain a preliminary logistics path planning scheme; thirdly, based on the preliminary logistics path planning scheme and in combination with the food shelf life evaluation results, the storage conditions of each storage point are dynamically adjusted, and the storage conditions include at least temperature and humidity, to generate an optimized storage condition setting; finally, the optimized storage condition setting is used to further optimize the transportation time window to generate a final logistics plan.

[0181] Suppose a food processing company needs to transport a batch of fresh fruits from the place of origin to multiple retail outlets. First, using the results of food shelf life evaluation, a multi-objective optimization problem for food logistics path planning is constructed, and the optimization goal is set to minimize transportation time and cost while maximizing the freshness of food; secondly, based on these optimization goals, a genetic algorithm is used to automatically plan the logistics path from the place of origin to each retail outlet, considering the transportation time, cost and possible deterioration risk of different paths, and a preliminary logistics path planning scheme is obtained; thirdly, based on the preliminary logistics path planning scheme, combined with the results of food shelf life evaluation, the storage conditions such as temperature and humidity of each storage point are dynamically adjusted, for example, in warehouses with a longer expected storage time, a lower temperature and appropriate humidity are set to slow down the deterioration rate of the fruit, and the optimized storage condition settings are generated; finally, using the optimized storage condition settings, the transportation time window is further optimized to ensure that the fruit is transported under the best conditions, avoid transportation during high temperature periods, reduce the risk of deterioration, and generate the final logistics plan; through the above steps, the company can ensure that the fruit is kept in the best condition throughout the supply chain, while optimizing logistics costs and efficiency and improving overall operational benefits.

[0182] Figure 2 A structural diagram of a real-time monitoring and analysis system for food color changes is provided for the present application embodiment. Figure 2 As shown, the device comprises:

[0183] Building module 21, for capturing color change images of food in real time using high-sensitivity imaging equipment from multiple angles and different spectral ranges, collecting temperature, humidity, and light intensity parameters of the environment in which the food is located using an environmental sensing device, and building a multimodal food color dataset;

[0184] A correction module 22 is used to dynamically correct the color change of food based on the multimodal food color data set by combining the random forest algorithm under the integrated learning framework with the adaptive color space mapping technology to obtain a color change trend analysis report;

[0185] Prediction module 23, used to predict the decay rate of food freshness and possible deterioration points according to the color change trend analysis report, using a long short-term memory network based on time series analysis combined with food component analysis technology and a grey prediction model, and generate a food shelf life assessment result;

[0186] The adjustment module 24 is used to utilize the food shelf life evaluation results to automatically plan and process the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

[0187] Figure 2The real-time monitoring and analysis system for food color changes can be performed Figure 1 The implementation principle and technical effect of the method for real-time monitoring and analysis of food color changes described in the embodiment shown are not described in detail. The specific manner in which each module and unit performs operations in the real-time monitoring and analysis system for food color changes in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0188] In one possible design, Figure 2 A real-time monitoring and analysis system for food color change in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0189] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0190] The processing component 32 is used to: use high-sensitivity imaging equipment from multiple angles and different spectral ranges to capture color change images of food in real time, use environmental sensing devices to collect temperature, humidity, and light intensity parameters of the environment in which the food is located, and construct a multimodal food color data set; based on the multimodal food color data set, dynamically correct the color change of food by combining the random forest algorithm under the integrated learning framework with the adaptive color space mapping technology to obtain a color change trend analysis report; based on the color change trend analysis report, use a long short-term memory network based on time series analysis combined with food component analysis technology and a gray prediction model to predict the decay rate of food freshness and possible deterioration points, and generate a food shelf life evaluation result; use the food shelf life evaluation result to automatically plan the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

[0191] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0192] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0193] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0194] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0195] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0196] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0197] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The embodiment shown is a method for real-time monitoring and analysis of food color changes.

[0198] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0199] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0200] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0201] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for real-time monitoring and analysis of food color changes, characterized in that: include: Use high-sensitivity imaging equipment from multiple angles and different spectral ranges to capture food color change images in real time, use environmental sensing devices to collect temperature, humidity, and light intensity parameters of the environment in which the food is located, and build a multimodal food color dataset; Based on the multimodal food color dataset, the random forest algorithm under the integrated learning framework is combined with the adaptive color space mapping technology to dynamically correct the food color changes and obtain a color change trend analysis report; According to the color change trend analysis report, a long short-term memory network based on time series analysis is used in combination with food component analysis technology and a grey prediction model to predict the decay rate of food freshness and possible deterioration points, and generate a food shelf life assessment result; Utilizing the food shelf life assessment results, an intelligent logistics scheduling system driven by a multi-objective optimization algorithm is used to automatically plan and process the entire process path of food from production to consumption, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

2. The method according to claim 1, characterized in that: Based on the multimodal food color data set, the random forest algorithm under the integrated learning framework is combined with the adaptive color space mapping technology to dynamically correct the food color change and obtain a color change trend analysis report, including: Using the multimodal food color dataset, adaptive color space mapping is performed on color information in different spectral ranges to eliminate color deviation caused by light source changes and obtain standardized color data; Based on the standardized color data, a random forest algorithm is used to combine the color change patterns of foods under different environmental conditions to perform predictive modeling on food color changes, thereby generating a food color change prediction model; According to the food color change prediction model, the time series data of food color change is analyzed for trend and periodic characteristics, the color stability of food under different environmental conditions is evaluated, and the color change characteristic evaluation result is obtained; Utilizing the color change characteristic evaluation results, the main trends, periodic characteristics, and color change rate and amplitude information of food color changes are integrated through data visualization technology and statistical analysis methods to generate a color change trend analysis report.

3. The method according to claim 2, characterized in that Based on the standardized color data, the food color change is predicted and modeled by a random forest algorithm in combination with the color change pattern of the food under different environmental conditions to generate a food color change prediction model, including: In calculating C pred (t) Before, the multimodal food color dataset needs to be preprocessed to eliminate the color deviation caused by light source changes through adaptive color space mapping technology to obtain standardized color data in preparation for building a random forest model for predicting food color changes; Among them, C pred (t) represents the predicted food color change value at time t, w i is the weight of the i-th tree in the random forest, reflecting the contribution of each tree to the final prediction result; C i (t) represents the standardized color data of the i-th sample at time t; E i (t) represents the environmental condition data of the i-th sample at time t; N is the number of samples; α is the adjustment coefficient related to the ambient temperature, which is used to adjust the effect of temperature on color change; β is the adjustment coefficient related to the ambient humidity, which is used to adjust the effect of humidity on color change; T(t) represents the ambient temperature at time t; H(t) represents the ambient humidity at time t; δ is the adjustment coefficient related to the ratio of temperature and humidity, which is used to reflect the combined effect of temperature and humidity on color change; Calculate C pred (t), to generate f(C i (t), E i (t)) It is necessary to analyze the time series data of food color change, combine food component analysis technology, consider the influence of environmental conditions such as temperature and humidity, and correct the predicted value of color change to ensure the accuracy of the prediction; f(C i (t),E i (t))=C i (t)·(1+γ·sin(2π·F(E i (t)))+η·cos(2π·G(E i (t)))) Among them, C i (t) represents the standardized color data of the i-th sample at time t; E i (t) represents the environmental condition data of the i-th sample at time t; γ is a coefficient related to the periodic change of environmental conditions, which is used to adjust the effect of periodic changes in environmental conditions on color change; η is a coefficient related to another periodic change in environmental conditions, which is used to adjust the effect of different periodic changes on color change; F(E i (t)) represents the environmental condition E i The frequency function of (t) is used to capture the periodic effect of environmental condition changes on food color changes; G(E i (t)) represents the environmental condition E i Another frequency function of (t) is used to capture the different periodic effects of changes in environmental conditions on food color changes; After calculating f(C i (t), E i (t)), in order to generate a food color change prediction model, it is necessary to comprehensively consider the main trends, periodic characteristics and environmental conditions of food color changes, use time series analysis methods and food component analysis technology to optimize model parameters, and finally generate a model that accurately predicts food color changes.

4. The method according to claim 2, characterized in that: According to the food color change prediction model, the time series data of food color change is analyzed and processed for trend and periodic characteristics, the color stability of food under different environmental conditions is evaluated, and the color change characteristic evaluation result is obtained, including: Based on the food color change prediction model, trend analysis is performed on the time series data of food color changes to identify the main trend direction and change rate of color changes and obtain color change trend information; Using the color change trend information and combining it with Fourier transform technology, the time series data of food color change is analyzed and processed based on periodic characteristics, the periodic pattern of color change is extracted, and the periodic characteristic information of color change is obtained; According to the color change trend information and the color change periodic characteristic information, by comparing the color changes of the food under different environmental conditions, the color stability of the food under different environmental conditions is evaluated, and a color stability evaluation index is generated; The color stability evaluation index is used in combination with the correlation analysis of food ingredients and environmental conditions to comprehensively evaluate the color change characteristics of food under different environmental conditions and obtain a color change characteristic evaluation result.

5. The method according to claim 2, characterized in that: The color change characteristic evaluation results are used to integrate the main trends, periodic characteristics, and color change rate and amplitude information of food color changes through data visualization technology and statistical analysis methods to generate a color change trend analysis report, including: Using the color change characteristic evaluation results, a visualization chart of food color change is generated through data visualization technology to intuitively display the main trends and periodic characteristics of food color change, thereby obtaining a color change trend chart; Based on the color change trend graph, combined with statistical analysis methods, the rate and amplitude of food color change are quantitatively analyzed to evaluate the severity and change rules of food color change, and obtain color change rate and amplitude analysis results; Based on the color change rate and amplitude analysis results, a comprehensive evaluation is performed on the color stability of the food under different environmental conditions, key factors affecting the color change of the food are extracted, and a comprehensive evaluation report on the color stability is obtained; The color stability comprehensive evaluation report is used to integrate the main trends, periodic characteristics, and color change rate and amplitude information of food color changes to generate a color change trend analysis report.

6. The method according to claim 1, characterized in that According to the color change trend analysis report, the long short-term memory network based on time series analysis is combined with food component analysis technology and gray prediction model to predict the decay rate of food freshness and possible deterioration points, and generate food shelf life assessment results, including: According to the color change trend analysis report, extract the main trend, periodic characteristics, change rate and amplitude information of food color change, and construct a time series data set of food color change; Using the time series data set of food color changes, combined with food component analysis technology, the decay rate of food freshness is modeled through a long short-term memory network to generate a food freshness decay rate prediction model; Based on the food freshness decay rate prediction model, a grey prediction model is applied to supplement the prediction of the time series data of food color change, so as to enhance the accuracy and robustness of the prediction and obtain a comprehensive prediction result of food freshness; Using the comprehensive prediction results of the food freshness, identifying key nodes in the food color change process that may indicate spoilage, assessing the risk of food spoilage under different conditions, and generating a food spoilage point prediction report; Based on the food spoilage point prediction report, combined with food ingredient characteristics and historical data, a comprehensive assessment of the food's shelf life is conducted to generate a food shelf life assessment result.

7. The method according to claim 6, characterized in that Based on the food freshness decay rate prediction model, the grey prediction model is applied to supplement the prediction of the time series data of food color change, so as to enhance the accuracy and robustness of the prediction and obtain the comprehensive prediction result of food freshness, including: In calculating F gray Before (t), it is necessary to preprocess the time series data of food color change, extract environmental condition data, and combine it with the food freshness decay rate prediction model C pred (t) and food composition analysis techniques to provide input for supplementary prediction of grey prediction models; Among them, F gray (t) represents the food freshness supplement prediction value obtained by applying the grey prediction model at time t, α is the weight coefficient of the grey prediction model, GM(1,1)(t) represents the prediction value of the grey prediction model GM(1,1) based on time t, β is the adjustment coefficient related to the food freshness prediction value, γ is the sensitivity coefficient related to the food color change prediction value, C pred (t) represents the predicted food color change value at time t, δ is the reference value of food color change, which is used to adjust the sensitivity of prediction, λ is the coefficient related to the periodic change of ambient temperature, ω is the angular frequency of ambient temperature change, T(t) represents the ambient temperature at time t, φ is the phase angle of ambient temperature change; After calculating F gray (t), to generate C comp (t), we need to change F gray (t) is fused with the food color change prediction value Cpred(t), the weight coefficients of the two are adjusted, and the influence of environmental humidity and food packaging characteristics are introduced to generate a more accurate food freshness prediction value; Among them, C comp (t) represents the food freshness value obtained by comprehensive prediction at time t, θ is the weight coefficient of the food color change prediction value, C pred (t) represents the predicted food color change value at time t, F gray (t) represents the supplementary prediction value of food freshness obtained by applying the grey prediction model at time t, μ is the adjustment coefficient related to the ambient humidity and food packaging characteristics, H(t) represents the ambient humidity at time t, and P(t) represents the food packaging characteristic parameter at time t, which is used to reflect the impact of packaging on food freshness; Calculate C comp (t), in order to obtain a comprehensive prediction result of food freshness, it is necessary to combine the food ingredient characteristics and historical data, evaluate the decay rate of food freshness and possible spoilage points, identify key spoilage nodes, evaluate spoilage risks, and finally generate a comprehensive prediction result of food freshness.

8. The method according to claim 6, characterized in that The method utilizes the time series data set of food color changes, combines food component analysis technology, and models the decay rate of food freshness through a long short-term memory network to generate a food freshness decay rate prediction model, including: Based on the time series data set of food color changes, combined with the food composition information provided by food composition analysis technology, the data is preprocessed, including missing value filling, outlier processing and data standardization, to ensure that the data quality meets the modeling requirements; Using the preprocessed food color change time series data, a long short-term memory network model is constructed. This long short-term memory network model can capture the long-term dependencies in the time series and effectively reflect the change of food freshness over time. In the long short-term memory network model, food ingredient information is used as an auxiliary input and acts together with time series data in the model training process to enhance the model's ability to understand the changing characteristics of food freshness and improve prediction accuracy; The long short-term memory network model is trained iteratively and cross-validation technology is used to evaluate the model performance to ensure the generalization ability of the model under different time periods and different food composition conditions. Finally, a food freshness decay rate prediction model is generated. The food freshness decay rate prediction model can accurately predict the food freshness decay rate.

9. The method according to claim 1, characterized in that: The food shelf life evaluation results are used to automatically plan the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan, including: Using the food shelf life evaluation results, a multi-objective optimization problem for food logistics path planning is constructed to obtain an optimization target set; Based on the optimization target set, a multi-objective optimization algorithm is used to automatically plan the entire process path of food from production to consumption, and a preliminary logistics path planning solution is obtained; According to the preliminary logistics route planning scheme, combined with the food shelf life evaluation results, dynamically adjust the storage conditions of each storage point, wherein the storage conditions at least include temperature and humidity, and generate optimized storage condition settings; The optimized storage condition settings are used to further optimize the transportation time window and generate a final logistics plan.

10. A real-time monitoring and analysis system for food color changes, characterized in that: include: A construction module is used to capture the color change images of food in real time using high-sensitivity imaging devices from multiple angles and different spectral ranges, and to collect the temperature, humidity, and light intensity parameters of the environment in which the food is located using an environmental sensing device to construct a multimodal food color dataset; A correction module is used to dynamically correct the color change of food based on the multimodal food color dataset by combining the random forest algorithm under the integrated learning framework with the adaptive color space mapping technology to obtain a color change trend analysis report; A prediction module is used to predict the decay rate of food freshness and possible deterioration points according to the color change trend analysis report, using a long short-term memory network based on time series analysis combined with food component analysis technology and a grey prediction model, and generate a food shelf life assessment result; The adjustment module is used to utilize the food shelf life evaluation results to automatically plan and process the entire process path of food from production to consumption through an intelligent logistics scheduling system driven by a multi-objective optimization algorithm, dynamically adjust storage conditions and transportation time windows, and generate a logistics plan.

Images