Premade food risk management method and system

Abstract

The invention discloses a prefabricated prepared food risk management method and system, and relates to the technical field of food safety management, and the method comprises the steps: marking prefabricated prepared food, and generating a product digital identity label; collecting a first environment parameter of the prefabricated prepared food; associating the product digital identity label with the first environment parameter to obtain an association result; according to the association result, generating an individualized historical file of the prepared food; according to the individualized historical archive, performing state evaluation processing on the prefabricated prepared food to obtain a product state; generating a customized heating scheme according to the product state; and sending the customized heating scheme to a heating module, wherein the heating module is used for executing the customized heating scheme. According to the method, the product state can be evaluated in combination with the environmental parameters and the individualized historical archives, so that food risk management is realized, and the safety and the product quality are improved.

Description

Technical Field

[0001] This invention relates to the field of food safety management technology, and in particular to a method and system for risk management of pre-prepared prepared foods. Background Technology

[0002] In the production and distribution of pre-prepared foods, ensuring the safety and quality of every meal is crucial. However, traditional methods often focus on monitoring the overall environment, failing to capture the subtle and cumulative environmental changes experienced by individual food packages during their long journey. This lack of information makes it impossible to adjust the final heating method according to the actual conditions of each product, thus making it difficult to simultaneously guarantee food safety and delicious taste, resulting in low food management safety and low product quality.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this invention is to propose a risk management method and system for pre-prepared foods, which can assess product status by combining environmental parameters and individualized historical records to achieve food risk management and improve safety and product quality.

[0005] On one hand, embodiments of the present invention provide a method for risk management of pre-prepared prepared foods, including the following steps: During the distribution of pre-prepared foods, they are marked to generate digital product identification tags. Collect the first environmental parameters of the pre-prepared food; The product's digital identity is associated with the first environmental parameter to obtain the association result; Based on the association results, an individualized historical profile of the pre-prepared food is generated; During the heating process of pre-prepared prepared food, the state of the pre-prepared prepared food is evaluated based on the individualized historical records to obtain the product state. Based on the product status, a customized heating solution is generated; The customized heating scheme is sent to the heating module, which executes the customized heating scheme.

[0006] On the other hand, embodiments of the present invention provide a pre-prepared food risk management system, comprising: The identity tagging module is used to tag pre-prepared foods during their distribution process and generate digital product identities. An environmental data acquisition module is used to collect the first environmental parameters of the pre-prepared food. The association module is used to associate the product digital identity with the first environmental parameter to obtain the association result; The archive generation module is used to generate an individualized historical archive of the pre-prepared food based on the association results; The status assessment module is used to assess the status of the pre-prepared food based on the individualized historical records during the heating process of the pre-prepared food to obtain the product status. The solution generation module is used to generate a customized heating solution based on the product status. The scheme execution module is used to send the customized heating scheme to the heating module, and the heating module is used to execute the customized heating scheme.

[0007] The embodiments of this application include at least the following beneficial effects: First, the pre-prepared food is marked to generate a product digital identity. Then, the first environmental parameters of the pre-prepared food are collected, and the product digital identity is associated with the first environmental parameters to obtain the association result. Based on the association result, an individualized historical file of the pre-prepared food is generated. Based on the individualized historical file, the pre-prepared food is subjected to status assessment processing to obtain the product status. Finally, based on the product status, a customized heating plan is generated and executed through the heating module. This allows for the assessment of product status by combining environmental parameters and individualized historical files, thereby achieving food risk management and improving safety and product quality.

[0008] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description and the drawings. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0010] Figure 1 This is a flowchart illustrating a risk management method for pre-prepared prepared foods according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a pre-prepared food risk management system according to an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments.

[0012] In related technologies, ensuring the safety and quality of each meal is paramount during the production and distribution of pre-prepared foods. However, traditional methods often focus on monitoring the overall environment, failing to capture the subtle and cumulative environmental changes experienced by individual food packages during their long journey. This lack of information makes it impossible to adjust the final heating method according to the actual situation of each product, thus creating a dilemma between food safety and delicious taste.

[0013] For example, a large food processing company specializes in producing standardized meals like black pepper beef rice and curry chicken. From raw material selection, precise cooking, rapid cooling to aseptic packaging, the entire production process is strictly controlled to ensure that the products have good initial quality and safety when they leave the factory. The packaged food is immediately sent to a large cold storage warehouse, where the temperature is continuously monitored by multiple fixed probes to ensure that the ambient temperature remains stable within a safe range of 0 to 4 degrees Celsius. At this stage, risk management mainly relies on the control of macro-environmental parameters.

[0014] Subsequently, these pre-prepared foods are distributed to chain restaurants, convenience stores, and other sales terminals across the country via cold chain logistics. In the transportation phase, standard risk management practice involves installing temperature recorders in refrigerated truck compartments, typically near the refrigeration unit's air vents, to record the compartment temperature during transport. However, relying on temperature readings from only one or a few points cannot fully reflect the true temperature conditions of all goods within the compartment. In actual transportation, due to factors such as the way goods are stacked, the uneven flow of cold air within the compartment, and frequent opening and closing of doors during delivery, many micro-environments with varying temperatures can form inside the compartment. For example, goods near the doors are repeatedly exposed to warm outside air, while goods stacked in corners with poor ventilation may have surrounding temperatures significantly higher than those displayed by the temperature recorder. This means that some food packaging may experience undetected temperature anomalies during transport, while the overall transport temperature records show everything is normal.

[0015] The effects of temperature are cumulative. From the factory to the consumer, a food package undergoes multiple stages, including central warehouse, loading / unloading platform, trunk line transportation, city distribution, and store warehousing. At each stage, there may be brief periods of improper temperature control, such as prolonged exposure to room temperature during loading and unloading, or failure to immediately store in a refrigerated unit after receipt at the store. A single, brief temperature fluctuation may not pose a risk, but multiple, continuous small temperature increases can subtly alter the microbial state and physicochemical properties of the food. Existing risk management methods typically only conduct sampling temperature measurements at key points such as departure and arrival. This fragmented, point-like monitoring approach cannot depict the complete and continuous temperature change trajectory experienced by each food item. Therefore, the system cannot distinguish between two products produced in the same batch but with drastically different transportation experiences.

[0016] Finally, when these pre-prepared foods arrive at convenience stores and other retail outlets, they undergo a final heating process. Store staff operate according to the standardized instructions on the product packaging, such as "microwave on high for 3 minutes and 30 seconds." This standardized heating procedure is based on the premise that the product arrives at the retail level under ideal cold chain conditions. However, due to the aforementioned unrecorded cumulative temperature differences, two identical products delivered may actually have significantly different initial states before heating. Products that have experienced more temperature fluctuations may have a higher initial number of microorganisms. In this case, if the standard heating time is still used, it may not be possible to reduce the number of microorganisms to a safe level, thus posing a food safety hazard. Conversely, to ensure absolute safety, manufacturers often set a longer heating time as a uniform standard to cope with the worst-case scenario. However, such a setting constitutes overheating for products stored at ideal temperatures throughout the process, leading to moisture loss, deteriorated texture, destruction of flavor compounds, and loss of nutrients, severely impacting the consumer's eating experience.

[0017] In the industrialized production and distribution system of pre-packaged foods, existing risk management methods mainly rely on monitoring environmental parameters at each independent stage of the supply chain. This approach cannot acquire and record complete, continuous, and individualized historical information about the experiences of each individually packaged food item. This results in all products undergoing the same standardized reheating process at the final consumption stage, regardless of their conditions during logistics and storage. This approach may lead to safety issues due to insufficient heating for products with accumulated risks from inadequate cold chain systems; while for high-quality products that have been properly preserved throughout the process, overheating may sacrifice their intended taste and quality. Current technology struggles to correlate the environmental exposure data accumulated by individual food items throughout the distribution process with their final heating treatment, making it impossible to adjust the heating intensity and duration according to the actual state of each food item. This results in low food management safety and low product quality.

[0018] In light of this, this application achieves customized heating by implementing end-to-end digital tracking and individualized status assessment of pre-prepared foods. During the distribution of pre-prepared foods, each product is first assigned a unique digital identity, and the first environmental parameters of its surrounding environment are continuously collected. These environmental parameters are linked to the product's digital identity to jointly construct an individualized historical profile for each pre-prepared food. When the pre-prepared food enters the heating stage, the system no longer relies solely on a uniform heating standard but deeply analyzes its individualized historical profile, comprehensively assessing the quality changes and safety risks it may experience during distribution, thereby obtaining an accurate product status. Based on this product status, the system can intelligently generate a customized heating plan and send it to the heating module for execution. For example, for pre-prepared foods that have experienced slight temperature fluctuations during transportation, the system may suggest slightly extending the heating time to ensure microbial safety; while for pre-prepared foods that maintain ideal cold chain conditions throughout, a shorter or gentler heating method may be used to maximize the preservation of their flavor and nutrients. This method ensures that each pre-prepared food product receives optimal heating treatment, effectively mitigating food safety risks and avoiding quality deterioration caused by overheating, thereby significantly enhancing the consumer's eating experience.

[0019] The embodiments of this application will be explained in detail below with reference to the accompanying drawings: Figure 1 This is an optional flowchart of a risk management method for pre-prepared prepared foods provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S107.

[0020] Step S101: During the circulation of pre-prepared food, the pre-prepared food is marked to generate a digital product identity. Step S102: Collect the first environmental parameters of the pre-prepared food; Step S103: Associate the product digital identity with the first environmental parameter to obtain the association result; Step S104: Based on the association results, generate individualized historical profiles for pre-prepared prepared foods; Step S105: During the heating process of pre-prepared prepared food, the state of the pre-prepared prepared food is evaluated based on individualized historical records to obtain the product state. Step S106: Generate a customized heating solution based on the product status; Step S107: Send the customized heating plan to the heating module, which is used to execute the customized heating plan.

[0021] Steps S101 to S107 as illustrated in the embodiments of this application can combine environmental parameters and individualized historical records to assess product status, thereby achieving food risk management and improving safety and product quality.

[0022] In some embodiments, steps S101-S107 involve marking the pre-prepared foods during their distribution process to generate a digital product identity. This aims to assign a unique digital identity to each pre-prepared food item for end-to-end tracking. For example, a QR code can be printed on the packaging of each pre-prepared food item, or an RFID tag can be embedded. As the product moves through the supply chain, it can be identified by scanning the QR code or reading the RFID tag. Pre-prepared foods are foods that have undergone preliminary processing or cooking and are pre-packaged, requiring only simple heating or cooking after purchase. They are convenient and quick, but require higher risk management during storage and heating. A digital product identity is a unique digital code assigned to each pre-prepared food item, similar to a product's ID card, used to track and identify the product throughout its distribution process. This identifier can take various forms, such as QR codes, RFID tags, NFC chips, etc., and its core function is to achieve digital management and traceability of product information.

[0023] Then, the first environmental parameters of the pre-prepared food are collected. For example, environmental sensors can be deployed at key nodes such as cold chain transport vehicles, warehouses, and retail shelves to monitor parameters such as temperature and humidity in real time. These sensors can be standalone temperature recorders or multi-functional sensors integrated into the logistics box. The product's digital identity is then associated with the first environmental parameters to obtain the association results. The collected environmental data can be bound to the corresponding pre-prepared food. For example, when an environmental sensor records temperature data at a certain point in time, the system will simultaneously record the product digital identities of all pre-prepared foods in that environment at that time and associate the temperature data with these identities for storage. It can be understood that the first environmental parameters refer to the various physical or chemical indicators of the environment in which the pre-prepared food is located during the circulation process, such as temperature, humidity, light intensity, and gas composition. These parameters directly affect the quality and safety of the food.

[0024] Based on the correlation results, a personalized historical profile for each pre-prepared food is generated. All relevant environmental parameters associated with each pre-prepared food during its distribution process are aggregated to form a complete historical record. For example, the system can create a database entry for each product's digital identity, containing all environmental data such as temperature, humidity, time, and location experienced by the product from its production stage to the present moment. During the heating process of the pre-prepared food, a state assessment is performed based on the personalized historical profile to obtain the product status, aiming to evaluate its current quality and safety status based on the product's real historical data. For example, the system can analyze temperature fluctuation data in the personalized historical profile, combined with a degradation kinetic model of food components, to predict the growth of microorganisms or the degree of nutrient loss, thereby deriving the product's "product status," such as "mild degradation" or "moderate risk." In essence, a personalized historical profile refers to the summary of all key information about a single pre-prepared food from production to heating, including its digital identity, environmental parameters collected during distribution, and changes in food status derived from these parameters, forming a complete product lifecycle record. Product status is a comprehensive assessment of the internal quality and safety of pre-prepared foods before heating, including factors such as microbial growth, the degree of nutrient degradation, and changes in flavor compounds.

[0025] Finally, a customized heating plan is generated based on the product's condition. The system can tailor the most suitable heating method for each pre-prepared food item based on its assessed condition. For example, if the product condition assessment indicates a high risk of microbial contamination, the system may generate a plan to extend the heating time or increase the heating temperature; if the product condition indicates a slight decrease in quality but no safety concerns, the system may generate a plan to optimize the heating curve to restore the texture. The customized heating plan is then sent to the heating module for execution. The generated customized heating plan can also be transmitted to the device that actually performs the heating operation. For example, a smart microwave oven or oven can receive heating instructions from the system and automatically adjust the heating time, power, or mode accordingly to ensure precise heating of the pre-prepared food. In essence, a customized heating plan refers to heating instructions tailored to the product's condition, aiming to heat in the most optimized way, ensuring food safety while also considering taste and nutrition. The heating module refers to the device that executes the customized heating plan; it can be a smart oven, microwave oven, steam cabinet, etc., characterized by its ability to receive and accurately execute externally sent heating instructions.

[0026] Through the aforementioned technical solution, this embodiment achieves full lifecycle tracking and refined status assessment of each pre-prepared food product by introducing digital product identification and individualized historical records. This embodiment can accurately identify the unique environmental conditions experienced by each product and predict its internal quality and safety status accordingly. Furthermore, this embodiment generates customized heating solutions based on product status, enabling the heating process to precisely match the actual needs of the product. For example, if the individualized historical record of a pre-prepared food product shows that it experienced a brief temperature rise at a certain stage, the system can adjust its heating parameters accordingly to ensure effective killing of microorganisms while avoiding unnecessary overheating of other unaffected products. This customized risk management and heating strategy not only significantly improves food safety but also maximizes the preservation of the taste and nutritional value of pre-prepared foods, providing consumers with a superior eating experience.

[0027] In some embodiments, in step S106, generating a customized heating solution based on the product status may include, but is not limited to, the following steps: Step S201: Perform spectral scanning on the pre-prepared prepared food to obtain spectral data; Step S202: Identify the degradation state of pre-prepared prepared foods based on spectral data; Step S203: Generate a customized heating solution based on the product status and degradation status.

[0028] In some embodiments, relying solely on historical records and macroscopic product conditions may not fully and in real-time reflect the microscopic chemical changes and specific degradation pathways occurring within pre-prepared foods. This limitation may result in insufficient precision in the generated customized heating schemes, failing to address specific degradation issues that may arise during food distribution, thereby affecting food safety and quality.

[0029] To this end, pre-prepared foods can be first subjected to spectral scanning to obtain spectral data. The principle of electromagnetic wave-matter interaction can be utilized to perform non-contact or contact detection on pre-prepared foods to obtain physical or chemical information about their internal components. For example, near-infrared spectroscopy (NIR), Raman spectroscopy, and hyperspectral imaging techniques can be used to scan pre-prepared foods. The purpose is to obtain raw spectral data reflecting the internal chemical composition, structural changes, and degradation products of the food. Spectral data refers to the set of measurements of the absorption, reflection, scattering, or emission intensity of electromagnetic waves by pre-prepared foods within a specific wavelength range. This data contains information on the vibration and rotation of various molecular bonds in the food, indirectly reflecting the chemical composition and changes of the food.

[0030] Then, based on the spectral data, the degradation state of pre-prepared foods is identified. This can be achieved by analyzing and processing the acquired spectral data, for example using chemometric methods (such as principal component analysis, partial least squares, etc.), combined with a pre-established degradation model library or model, to determine the degree of degradation, degradation pathways, and the presence of harmful degradation products of specific components in pre-prepared foods. The aim is to obtain detailed, quantitative information about the internal degradation of the food.

[0031] Based on the product's condition and degradation status, a customized heating solution is generated. This can comprehensively consider the macroscopic product condition assessed from individual historical records (e.g., overall freshness, microbial risk level) and the microscopic degradation status identified through spectral data (e.g., degree of fat oxidation, degree of protein hydrolysis, degradation of specific flavor compounds). Using pre-defined decision logic or machine learning models, a combination of heating parameters that simultaneously optimizes food safety and quality is generated. This solution may include heating temperature, heating time, heating method (e.g., microwave, steam, convection), and humidity control during the heating process.

[0032] This embodiment introduces spectral scanning to obtain real-time spectral data of pre-prepared prepared foods and identifies their specific degradation states based on this data, thus overcoming the limitations of relying solely on individualized historical records and macroscopic product conditions for generating heating schemes. Since spectral data directly reflects changes in the internal chemical composition and structure of food, the identification of degradation states is more accurate and timely. By combining this real-time, microscopic degradation state information with macroscopic product conditions based on historical data, a more comprehensive assessment of the food's true condition can be achieved. This comprehensive assessment allows the generated customized heating schemes to more precisely target specific degradation issues in the food. For example, if spectral data shows severe fat oxidation, the heating scheme can be adjusted to reduce further oxidation; if protein degradation leads to changes in texture, the heating scheme can be optimized to improve taste. Therefore, this embodiment enables a deeper understanding of food deterioration mechanisms at the chemical level and allows for the development of more scientific and personalized heating strategies.

[0033] To illustrate this technical solution more clearly, a specific example is used below. Suppose there is a pre-prepared braised pork belly whose individual history shows it experienced a brief temperature fluctuation during distribution, leading to an assessment that its product status carries a slight risk of quality deterioration. Based solely on this product status, a conservative heating approach might be generated, such as extending the heating time to ensure safety, but this could result in the braised pork belly becoming overcooked. In this embodiment, before heating, the braised pork belly undergoes a spectral scan, for example, using a near-infrared spectrometer to acquire its spectral data. Analysis of the spectral data reveals that the characteristic peak intensity of fat oxidation products (such as malondialdehyde) is slightly higher than normal, indicating that the braised pork belly's degradation state is mild fat oxidation. At this point, the system comprehensively considers both the "product status" (slight risk of quality deterioration) and the "degradation state" (mild fat oxidation). Based on this, a customized heating solution is generated, which may include setting the heating temperature slightly lower than traditional solutions, but simultaneously adding a short high-temperature steam treatment stage to quickly kill potential microorganisms and improve the tenderness of the meat without further promoting fat oxidation. In addition, the heating module may be instructed to add a small amount of antioxidant vapor (such as rosemary extract) during the heating process to further inhibit fat oxidation. In this way, the resulting customized heating solution can more precisely address the specific degradation issues of braised pork, ensuring food safety while optimizing its taste and flavor.

[0034] Through the above technical solution, this embodiment can significantly improve the accuracy and effectiveness of pre-prepared food heating solutions. By introducing real-time, objective assessment of the food's degradation state, the resulting customized heating solutions can be optimized down to the level of internal chemical changes within the food. This not only helps to more accurately eliminate potential safety risks—such as by adjusting heating parameters to degrade specific harmful substances or inhibit microbial growth—but also maximizes the preservation of the food's nutrients, improves its texture and flavor, thereby enhancing the overall quality of the food. Furthermore, this refined management approach helps reduce food waste, improve resource utilization efficiency, and provide consumers with safer and more delicious pre-prepared foods.

[0035] In some embodiments, in step S202, identifying the degradation state of the pre-prepared food based on spectral data may include, but is not limited to, the following steps: The spectral data was compared with the spectral feature pattern library to obtain the comparison results. The spectral feature pattern library contains spectral feature patterns of various degradation products. Based on the comparison results, the contribution of multiple degradation pathways was calculated; Degradation status is identified based on the contribution levels of multiple degradation pathways.

[0036] In some embodiments, the spectral data can be compared with a spectral feature pattern library to obtain the comparison results. The collected spectral data of pre-prepared prepared foods can be compared with the spectral feature patterns of various degradation products in the spectral feature pattern library. This comparison can be achieved through various spectral analysis techniques, such as principal component analysis (PCA), partial least squares (PLS), support vector machine (SVM), or deep learning algorithms, to quantify the similarity or matching degree between the spectral data and the patterns in the library, thereby obtaining the comparison results. The spectral feature pattern library is a pre-established database containing spectral feature patterns of various degradation products. These patterns can be absorption peaks, peak shapes, peak intensities, or integral values ​​of spectral regions at specific wavelengths, used to characterize specific chemical substances produced by food under different degradation pathways. For example, protein degradation may produce amino acids or small peptides, which have unique fingerprint characteristics in specific infrared or Raman spectral regions; lipid oxidation may produce aldehydes, ketones, etc., which also have corresponding characteristic peaks in specific spectral regions. The spectral feature pattern library can be constructed by performing spectral analysis on known degradation products and combining it with chemometric methods for pattern recognition and storage. The comparison result can be a similarity score, a distance metric, or a probability value, used to indicate whether or not a certain degradation product is present in the food.

[0037] Then, based on the comparison results, the contribution of multiple degradation pathways is calculated. For example, if the comparison results show a high match between the food spectral data and the spectral characteristic patterns of protein degradation products, the contribution of the protein degradation pathway can be considered high. If it also matches the patterns of lipid oxidation products, a comprehensive evaluation is required. The calculation of contribution can be based on the quantitative values ​​of the comparison results, using weighted averages, regression analysis, or multivariate statistical methods.

[0038] The degradation state is then identified based on the contribution of various degradation pathways. The degradation state can be a comprehensive description, such as "mild oxidation," "moderate protein hydrolysis," or "severe microbial contamination," or it can be a quantitative indicator, such as the degradation index. Through a comprehensive analysis of the contribution of different degradation pathways, the overall degradation status of pre-prepared prepared foods can be determined comprehensively and accurately.

[0039] This embodiment compares the spectral data of pre-prepared prepared foods with a pre-defined spectral feature pattern library to identify degradation products at the molecular level. By quantifying the matching degree of the spectral feature patterns corresponding to different degradation products, the contribution of multiple degradation pathways can be calculated. This comparison and contribution calculation based on the spectral feature pattern library makes the identification of the degradation state of pre-prepared prepared foods no longer a single-dimensional judgment, but rather a comprehensive consideration of multiple potential degradation mechanisms, thus providing a more comprehensive and refined degradation state assessment. This allows for a more accurate understanding of the food deterioration process, providing a solid data foundation for subsequent risk assessment and heating scheme development.

[0040] Through the above technical solution, this embodiment establishes a spectral feature pattern library containing various degradation product spectral feature patterns, and performs comparisons and contribution calculations to identify multiple degradation pathways in food and their respective contributions, thereby providing a more accurate and comprehensive degradation status assessment result. This refined identification helps to more accurately assess the safety risk level and quality deterioration level of food, providing a more reliable basis for subsequent customized heating solutions, thus improving the overall risk management level of pre-prepared foods.

[0041] In some embodiments, in step S203, generating a customized heating scheme based on the product state and degradation state may include, but is not limited to, the following steps: Based on the degradation state, assess the safety risk level and quality deterioration level of pre-prepared foods; If the level of safety risk exceeds the preset safety threshold, a customized heating solution will be generated based on the safety enhancement strategy and product status. If the degree of quality deterioration exceeds the preset quality threshold, a customized heating solution will be generated based on the quality optimization strategy and product status. If the level of safety risk is less than the preset safety threshold and the level of quality degradation is less than the preset quality threshold, then a balance relationship is calculated based on the level of safety risk and the level of quality degradation, and a customized heating solution is generated based on the balance relationship and the product status.

[0042] In some embodiments, the failure to adequately distinguish the safety risks and quality degradation levels of pre-prepared foods may result in heating solutions that are not targeted at addressing different levels of problems, failing to achieve the best balance between safety and quality.

[0043] Therefore, the safety risk and quality degradation of pre-prepared foods can be assessed first based on their degradation state. The safety risk refers to the degree to which pre-prepared foods may pose a threat to consumer health, such as excessive microbial levels, toxin production, or accumulation of harmful substances. This assessment can be quantified based on data such as the toxicity of degradation products and growth models of pathogenic bacteria. The quality degradation refers to the degree of decline in the taste, flavor, nutritional value, and appearance of pre-prepared foods. This assessment can be quantified based on data such as the impact of degradation products on sensory characteristics and the rate of nutrient loss.

[0044] If the safety risk level exceeds the preset safety threshold, a customized heating solution is generated based on the safety enhancement strategy and product status. The preset safety threshold is set according to food safety standards and product characteristics, serving as a critical value to determine whether pre-prepared prepared foods are within an acceptable safety range. The safety enhancement strategy aims to eliminate or reduce food safety risks to the greatest extent possible by adjusting parameters such as heating temperature, heating time, and heating method; for example, using high-temperature short-time sterilization or extending heating time to ensure the elimination of pathogens.

[0045] If the quality degradation exceeds a preset quality threshold, a customized heating solution is generated based on the quality optimization strategy and the product's condition. The preset quality threshold, set according to product standards, consumer expectations, and market positioning, serves as a critical value for determining whether pre-prepared prepared foods still maintain good quality. The quality optimization strategy aims to restore or enhance the sensory quality and nutritional value of food as much as possible while ensuring food safety by adjusting heating parameters. Examples include using low-temperature slow cooking to maintain the tender texture of ingredients or activating flavor compounds through specific heating curves.

[0046] If the safety risk level is less than a preset safety threshold and the quality degradation level is less than a preset quality threshold, a balance is calculated based on these two factors. A customized heating solution is then generated based on this balance and the product's condition. The balance refers to how to achieve the optimal heating effect while ensuring both safety and quality remain within acceptable limits. For example, a multi-objective optimization model can be established, using the safety risk level and quality degradation level as inputs, and outputting a comprehensive weight or priority to guide the generation of the heating solution, maximizing the quality experience while ensuring safety.

[0047] This embodiment analyzes the degradation state of pre-prepared foods in detail, decomposing it into two dimensions for independent assessment: the degree of safety risk and the degree of quality deterioration. This refined assessment allows the system to adopt targeted heating strategies based on different levels of risk and deterioration. When the safety risk is high, safety enhancement strategies are prioritized to ensure food safety; when quality deterioration is significant, quality optimization strategies are emphasized to improve the consumer's eating experience. When both are within acceptable limits, the optimal balance between safety and quality can be achieved by calculating the equilibrium, avoiding overheating that leads to quality degradation or underheating that leads to potential risks. This hierarchical and graded decision-making mechanism makes the generation of customized heating solutions more scientific and reasonable.

[0048] To illustrate this technical solution more clearly, a specific example is used below. Suppose that a pre-prepared food (e.g., a serving of curry chicken rice) undergoes distribution, and its individualized history records show that it experienced a relatively high temperature at a certain stage, leading to its degradation state being identified as having a certain risk of microbial growth and oxidation of some flavor substances. First, based on this degradation state, the system assesses the safety risk level of the curry chicken rice as moderately high (e.g., microbial indicators are close to the preset safety threshold, but have not exceeded it), while the quality degradation level is slight (e.g., the flavor is slightly reduced, but the taste is still acceptable).

[0049] If the assessment results show that the level of safety risk exceeds the preset safety threshold (for example, microbial indicators have exceeded the standard), the system will immediately activate the safety enhancement strategy. At this time, the customized heating scheme may be set to increase the heating temperature to 120°C and extend the heating time to 10 minutes to ensure the complete elimination of potential pathogens, thereby prioritizing the safety of food consumption.

[0050] If the assessment results show that the safety risk level is less than the preset safety threshold, but the quality deterioration level is greater than the preset quality threshold (e.g., normal microbiological indicators, but severe oxidation of flavor substances, resulting in a significantly worse taste), the system will activate a quality optimization strategy. In this case, a customized heating scheme may be set to: use low-temperature slow cooking (e.g., heating at 80°C for 15 minutes), and may add steam or microwaves of a specific frequency during the heating process, in order to restore or improve the flavor and texture of the food as much as possible without further damaging the nutritional components.

[0051] If the assessment results show that the level of safety risk is less than the preset safety threshold, and the level of quality degradation is less than the preset quality threshold (e.g., microbiological indicators and flavor are within acceptable ranges, but with slight fluctuations), the system will calculate the balance between the level of safety risk and the level of quality degradation. For example, the system may use a preset optimization model to determine whether, under the current conditions, it is better to slightly increase the heating temperature to further reduce potential risks without excessively affecting the flavor, or to maintain standard heating parameters to preserve existing quality. A customized heating scheme may be set to use a standard heating temperature of 95°C for 8 minutes, and the heating curve may be fine-tuned according to the balance relationship to maximize the overall quality experience of the food while ensuring safety.

[0052] Through the above examples, this embodiment can intelligently generate the most suitable customized heating scheme based on the actual degradation of pre-prepared food, thereby maximizing the edible quality of food while ensuring food safety.

[0053] Through the above technical solution, this embodiment distinguishes between the degree of safety risk and the degree of quality deterioration, and adopts different heating strategies based on their relationship with preset thresholds. This ensures that when food safety is threatened, enhanced safety measures are prioritized, effectively reducing the risk of foodborne illnesses. Simultaneously, when quality deteriorates, targeted optimization can be implemented to maximize the preservation or restoration of the food's sensory characteristics and nutritional value. Furthermore, when both safety and quality are within acceptable ranges, unnecessary overheating is avoided through balancing calculations, saving energy and further improving the overall quality of the food. This provides consumers with safer, tastier, and more personalized pre-prepared prepared foods.

[0054] In some embodiments, in step S105, the pre-prepared food is subjected to a status assessment based on individualized historical records to obtain the product status, which may include, but is not limited to, the following steps: Step S301: Extract temperature, humidity, time, and location information of pre-prepared food products during the distribution process from individualized historical archives; Step S302: Extract the corresponding second environmental parameters from the individualized historical archives based on the location information; Step S303: Calculate the degradation rate of each component in the pre-prepared food based on temperature, humidity, time, second environmental parameters, and the sensitivity parameters of the food components to environmental parameters. Step S304: Calculate the cumulative degradation amount of each component in the pre-prepared prepared food based on the degradation rate of each component. Step S305: Based on the cumulative degradation amount of each component, conduct a composite degradation status assessment of the pre-prepared food to obtain the composite degradation status assessment results. Step S306: Based on the composite degradation status assessment results, generate the product status.

[0055] In some embodiments, temperature, humidity, time, and location information of pre-prepared foods during the distribution process can be extracted from individualized historical records. Key environmental data along the entire distribution chain of food, from production to heating, can be obtained using individualized historical records associated with the product's digital identity. This data forms the basis for assessing the food's condition; location information can be understood as the specific coordinates or area identifiers of the food in different geographical locations or storage environments.

[0056] Then, based on location information, corresponding secondary environmental parameters are extracted from individualized historical archives. For the specific environment in which the food is located, location-specific environmental parameters can be further obtained, such as light intensity, air pressure, and air composition. These parameters may have additional effects on the food degradation process. Based on temperature, humidity, time, secondary environmental parameters, and the sensitivity parameters of food components to these environmental parameters, the degradation rate of each component in the pre-prepared food is calculated. Known food chemistry kinetic models can be used, combined with actually monitored environmental parameters and the degree of response of different components in the food to these environmental parameters (i.e., sensitivity parameters), to quantify the degradation rate of each component under specific environmental conditions. For example, proteins may hydrolyze more rapidly under high temperature and humidity, while vitamin C is easily oxidized under light.

[0057] Then, based on the degradation rate of each component, the cumulative degradation amount of each component in the pre-prepared food is calculated. The degradation rates calculated over different time periods can be integrated or summed to obtain the total degradation degree of each component throughout the entire distribution process. This provides a quantitative indicator of the internal chemical changes in the food. Based on the cumulative degradation amount of each component, a composite degradation status assessment of the pre-prepared food is performed, yielding a composite degradation status assessment result. Considering the cumulative degradation amounts of multiple key components in the food, a comprehensive judgment of the overall degradation status of the food can be made using a pre-set assessment model (e.g., based on expert knowledge, machine learning models, or multi-index weighted algorithms). This assessment result can be a quantitative score, a classification, or a detailed degradation report.

[0058] Finally, based on the composite degradation status assessment results, the product status is generated. The composite degradation status assessment results can be transformed into an easy-to-understand and operational product status description, such as "fresh," "slightly degraded," "moderately degraded," or "not suitable for consumption," providing a direct basis for the subsequent generation of customized heating solutions.

[0059] To illustrate this technical solution more clearly, a specific example is used below. Suppose there is a pre-made prepared chicken rice dish whose individualized history record documenting complete distribution data from factory to consumer. First, the individualized history of the chicken rice dish is used to extract hourly temperature, humidity, timestamps, and GPS location information during transportation and storage. Second, based on this GPS location information, second environmental parameters corresponding to the time period and location are further extracted from external databases (e.g., local weather station data), such as the average light intensity and air quality index of the area. Next, using a pre-defined food component degradation kinetic model, combined with the sensitivity parameters of the main components of the chicken rice dish (such as protein, fat, carbohydrates, vitamins, etc.) to environmental parameters such as temperature, humidity, and light, the degradation rate of each component is calculated every hour. For example, the hydrolysis rate of protein at 25°C and 80% humidity is X; the oxidation rate of vitamin C under a specific light intensity is Y.

[0060] Then, these hourly degradation rates are summed to obtain the cumulative degradation amount of each component in the chicken rice throughout the entire distribution process. For example, protein cumulatively degrades by Z grams, and vitamin C cumulatively degrades by W milligrams. Subsequently, these cumulative degradation amounts are input into a pre-defined composite degradation state assessment model. This model may be a machine learning-trained classifier that comprehensively considers multiple degradation indicators such as protein hydrolysis, fat oxidation, and vitamin loss, outputting a composite degradation state assessment result, such as "mild fat oxidation, moderate vitamin C loss, good overall quality, low safety risk." Finally, based on this composite degradation state assessment result, the final product state of the chicken rice is generated, such as "Product State: Good, Normal Heating Recommended." This accurate product state will directly guide the heating module to generate the most suitable customized heating solution for this chicken rice, ensuring that it reaches its optimal eating state after heating.

[0061] Through the above technical solutions, this embodiment significantly improves the accuracy and reliability of product status assessment by introducing detailed tracking of environmental parameters throughout the entire food distribution chain, quantitative analysis of the degradation kinetics of various components within the food, and assessment of composite degradation states. This meticulous assessment method allows for a more precise matching of the actual degradation level of the food when generating customized heating solutions, thereby effectively ensuring the safety of pre-prepared prepared foods, maximizing the maintenance of their quality and flavor, avoiding overheating or underheating, and enhancing the user experience.

[0062] In some embodiments, in step S305, after assessing the composite degradation status of the pre-prepared food based on the cumulative degradation amount of each component and obtaining the composite degradation status assessment result, the method may further include, but is not limited to, the following steps: Step S401: Perform spectral residual analysis on the pre-prepared prepared food to obtain the residual spectrum; Step S402: Based on the characteristic peaks and characteristic regions of the residual spectrum, identify signs of degradation of trace components that are not present in the spectral feature pattern library; Step S403: Update the composite degradation status assessment results based on the degradation signs of trace components.

[0063] In some embodiments, relying solely on degradation models and spectral feature libraries of known components may not fully capture all potential degradation in pre-prepared foods, particularly for trace components, which could limit the assessment results and affect the accuracy of the final product status assessment and the effectiveness of customized heating schemes.

[0064] Therefore, a spectral residual analysis can be performed on pre-prepared foods to obtain residual spectra. By comparing the actual spectral data of the pre-prepared foods with the spectral data predicted based on a known component model, the residual spectra between the two can be obtained. These residual spectra reflect the portions of the actual spectra that are not fully explained by known components, which may originate from degradation products of trace components or unknown interactions.

[0065] Then, based on the characteristic peaks and regions of the residual spectrum, signs of degradation of trace components are identified. These trace components are not present in the spectral feature pattern library. The characteristic peaks and regions of the residual spectrum refer to absorption or emission peaks with specific wavelengths and intensities appearing in the residual spectrum, along with the specific wavelength ranges surrounding these peaks. These characteristic peaks and regions can serve as fingerprint information for identifying signs of trace component degradation. Trace components are substances present in extremely low amounts in pre-prepared foods but may have a significant impact on food safety or quality, such as certain flavor compounds, bioactive components, or potentially harmful byproducts. These trace components may not be included in the initial spectral feature pattern library due to their extremely low concentration or lack of standard spectral data. Identifying signs of trace component degradation can be achieved by analyzing the characteristic peaks and regions in the residual spectrum to infer whether these trace components have degraded, and the type and extent of degradation.

[0066] Then, based on the degradation indicators of trace components, the composite degradation status assessment results are updated. The information obtained through the analysis of trace component degradation indicators can be integrated into the original composite degradation status assessment results, thereby correcting and improving the assessment results to make them more comprehensive and accurate.

[0067] To illustrate this technical solution more clearly, a specific example is used below. Suppose a pre-prepared food product, during its distribution process, has an individualized history showing that it has experienced multiple temperature fluctuations. By analyzing the degradation rates and cumulative degradation amounts of known major components (such as proteins, fats, and carbohydrates) under these environmental conditions, a preliminary assessment of the complex degradation status is obtained. However, to further improve the accuracy of the assessment, the pre-prepared food product is subjected to spectral scanning, and residual analysis is performed between this and the spectra predicted based on a known component model. The results show characteristic peaks at specific wavelengths (e.g., 280 nm and 330 nm) in the residual spectrum; these characteristic peaks do not belong to the degradation products of any known major components in the spectral feature pattern library.

[0068] Further analysis revealed that these characteristic peaks might be associated with the oxidative degradation products of a trace antioxidant or a trace flavor precursor in the food. For example, the trace component might be a natural phenolic compound that degrades under high temperature or oxidative conditions, producing quinones with specific spectral absorption. Based on these degradation indicators, their impact on food safety risks (e.g., potential off-flavors or reduced nutritional value) and the degree of quality degradation (e.g., affecting taste or color) can be determined. For instance, if the degradation product of the trace component is confirmed to have a slight bitter taste, the original composite degradation status assessment can be revised, adjusting the degree of quality degradation upwards. Ultimately, based on the updated composite degradation status assessment, more precise customized heating protocols can be generated, such as adjusting heating temperature or time to minimize the negative impact of trace component degradation, or using specific heating profiles to passivate existing degradation products, thereby ensuring optimal quality and safety of the food after heating.

[0069] Through the above technical solution, this embodiment, by analyzing spectral residuals, can effectively identify and quantify even the degradation of trace components not included in traditional spectral feature mode libraries. This allows the assessment of the complex degradation state of pre-prepared foods to no longer be limited to known main components, but to cover a wider range of degradation pathways and products, thus more comprehensively reflecting the true safety risks and quality deterioration of the food. Consequently, potential safety hazards or quality decline caused by the degradation of trace components can be avoided, providing a more reliable basis for generating customized heating solutions, and ultimately ensuring food safety and the consumer's eating experience.

[0070] In some embodiments, in step S403, updating the composite degradation status assessment result based on trace component degradation indicators may include, but is not limited to, the following steps: Step S501: Determine the first influence weight of trace component degradation signs on the safety risk level and quality deterioration level of pre-prepared foods; Step S502: Determine the second influence weight of the degradation signs of known components on the safety risk level and quality deterioration level of pre-prepared prepared foods, wherein the known components exist in the spectral feature pattern library; Step S503: Determine the correction range of the state assessment result based on the first influence weight and the second influence weight; Step S504: Update the composite degradation status assessment results based on the correction range of the status assessment results.

[0071] In some embodiments, if the different weights of the influence of trace components and known components on food safety risks and the degree of quality deterioration are not fully considered, the accuracy of the assessment results may be insufficient, failing to accurately reflect the true state of pre-prepared foods, and thus affecting the effectiveness of customized heating solutions.

[0072] Therefore, we can first determine the primary influence weight of trace component degradation indicators on the safety risk and quality deterioration of prepared foods. The primary influence weight refers to the relative contribution or importance of trace component degradation indicators to the safety risk and quality deterioration of prepared foods. For example, some trace components, although present in extremely low amounts, may have degradation products that are significantly toxic or have a decisive impact on the flavor of the food; in such cases, their primary influence weight should be set to a higher value.

[0073] Then, the second influence weight of degradation signs of known components on the safety risk and quality deterioration of prepared foods is determined, whereby the known components exist in a spectral feature pattern library. The second influence weight refers to the relative contribution or importance of degradation signs of known components to the safety risk and quality deterioration of prepared foods. Known components are often major components of food, and their degradation may lead to widespread quality decline or safety hazards. Their second influence weight can be determined based on factors such as their content in the food and the nature of the degradation products.

[0074] Next, based on the first and second influence weights, the correction range for the state assessment results is determined. This correction range is a quantitative value calculated by combining the first and second influence weights, used to adjust the preliminary composite degradation state assessment results. This correction range aims to accurately reflect the combined impact of trace and known component degradation on the overall state of the food. Finally, based on the correction range, the composite degradation state assessment results are updated, resulting in a more comprehensive and accurate composite degradation state assessment result for pre-prepared foods.

[0075] To illustrate this technical solution more clearly, a specific example is used below. Suppose a pre-prepared food product is "Mushroom and Chicken," whose main ingredients include chicken, mushrooms, starch, and other known components, as well as trace amounts of B vitamins and specific flavor compounds. During distribution, spectral residual analysis identifies signs of degradation in a certain trace flavor compound. This degradation product may cause a slight off-odor, but has no significant impact on food safety. Simultaneously, slight oxidative degradation of chicken protein is also detected, which may affect taste and nutritional value. For accurate assessment, the first and second influence weights need to be determined. By reviewing relevant food science literature and conducting sensory evaluation experiments, the first influence weight of the trace flavor compound degradation on the degree of quality deterioration is determined to be 0.3, while the second influence weight of chicken protein oxidative degradation on the degree of quality deterioration is 0.6. Based on these weights, the correction margin for the status assessment result can be calculated. For example, if the preliminary composite degradation status assessment result shows a moderate degree of quality deterioration and a low level of safety risk... After considering the degradation indicators of trace and known components and their respective weights, a weighted average or other mathematical model was used to calculate that the quality degradation assessment result needs to be revised upwards by 0.1 units, and the safety risk assessment result by 0.02 units. Finally, based on this revision, the composite degradation status assessment result was updated, resulting in a revised quality degradation level of moderate to high, while the safety risk level remains low. Therefore, subsequent customized heating solutions may suggest using a gentler heating method to preserve as much of the remaining flavor as possible, or adding a small amount of seasoning after heating to mask any slight off-flavors while ensuring food safety.

[0076] Through the above technical solution, this embodiment can significantly improve the accuracy and comprehensiveness of the assessment of the composite degradation status of pre-prepared prepared foods. This embodiment not only considers the degradation impact of known components, but also effectively compensates for the shortcomings of traditional assessment methods that may overlook the degradation of trace but critical components by introducing the first influence weight of trace components. Therefore, it can more accurately identify the potential safety risks and quality deterioration degree of food, providing a solid foundation for generating more precise and personalized customized heating solutions, thereby effectively improving the overall risk management level of pre-prepared prepared foods and the consumer eating experience.

[0077] In some embodiments, after determining the correction magnitude of the state assessment result based on the first influence weight and the second influence weight in step S503, the method may further include, but is not limited to, the following steps: Step S601: Monitor the interaction data between trace component degradation indicators and known component degradation indicators; Step S602: Calculate the correction magnitude adjustment coefficient based on the interaction data and the synergistic antagonistic effect curve; Step S603: Adjust the correction magnitude of the state assessment result nonlinearly according to the correction magnitude adjustment coefficient.

[0078] In some embodiments, due to the complex interactions, such as synergistic or antagonistic effects, between trace components and known components during the actual degradation process of pre-prepared foods, these interactions can significantly alter their impact on the overall state of the food. Simply adjusting based on independent weights while ignoring these dynamic interactions between components may result in inaccurate corrections to the state assessment results, thus affecting the accuracy of the final product state assessment.

[0079] To this end, we can first monitor the interaction data between trace component degradation indicators and known component degradation indicators. Various analytical methods, such as spectral analysis, chromatographic analysis, or mass spectrometry, can be used to obtain real-time or periodic information on the changes in trace components and known components during the degradation process in pre-prepared foods. This information can include changes in their concentration, structure, activity, etc., as well as the time-series relationships and correlations between these changes. Interaction data aims to quantify the mutual influence of trace components and known components during the degradation process; for example, whether the degradation of one component accelerates or inhibits the degradation of another, or whether they jointly produce new degradation products.

[0080] Then, based on the interaction data and the synergistic-antagonistic curve, the correction magnitude adjustment coefficient is calculated. This can be based on the monitored interaction data combined with the synergistic-antagonistic curve. For example, if monitoring data shows a significant synergistic degradation effect between trace components and known components, and this synergistic effect accelerates food quality deterioration or increases safety risks, then the calculated correction magnitude adjustment coefficient will be a value greater than 1 to increase the original correction magnitude. Conversely, if an antagonistic effect exists, it may be a value less than 1. The synergistic-antagonistic curve refers to a pre-established mathematical model or empirical curve used to describe how the strength and type (synergistic or antagonistic) of interactions between different components affects their overall effect. This curve can be constructed using extensive experimental data, literature research, or based on chemical kinetic models. For example, when two components are present simultaneously, their degradation rate may be faster (synergistic effect) or slower (antagonistic effect) than when they are present alone. The synergistic-antagonistic curve maps the monitored interaction data to specific adjustments to the correction magnitude of the state assessment results.

[0081] Then, based on the adjustment coefficient, the correction magnitude of the state assessment result is nonlinearly adjusted. This allows for a more refined and realistic dynamic adjustment of the correction magnitude according to the actual interactions. This nonlinear adjustment can more accurately reflect the complex degradation mechanisms within the food, resulting in a more precise final state assessment result.

[0082] To illustrate this technical solution more clearly, a specific example is used below. Suppose a pre-prepared food contains vitamin C (a trace component) and a certain protein (a known component). During distribution, degradation signs of vitamin C (e.g., increased oxidation products) and protein (e.g., structural changes) are detected through methods such as spectral scanning. Differential analysis reveals that when vitamin C degrades to a certain extent, its oxidation products accelerate the oxidative degradation of the protein, exhibiting a synergistic effect. The system then monitors this synergistic effect data. A pre-established synergistic-antagonistic effect curve is used to calculate a correction adjustment coefficient greater than 1 based on the strength of this synergistic effect. For example, if the original correction calculated based on independent weights was 10%, after considering the synergistic effect and applying a non-linear adjustment with an adjustment coefficient of 1.2, the final correction might become 12%. Conversely, if the presence of a certain antioxidant (a trace component) significantly inhibits the oxidative degradation of fat (a known component), exhibiting an antagonistic effect, the calculated adjustment coefficient might be less than 1, thus reducing the original correction magnitude. In this way, the correction range of the state assessment results can dynamically and non-linearly adapt to the complex chemical changes inside the food, ensuring the accuracy of the assessment.

[0083] Through the above technical solution, this embodiment can more comprehensively and accurately consider the complex interactions between trace components and known components during the degradation process in pre-prepared foods, thereby significantly improving the accuracy of the correction range for the state assessment results. This embodiment can effectively avoid assessment bias caused by ignoring synergistic or antagonistic effects between components, making the final product state assessment closer to the actual condition of the food. This refined adjustment mechanism not only enhances the scientific nature and reliability of risk management, but also provides a solid foundation for generating more accurate and personalized customized heating solutions, thereby better ensuring the food safety and quality experience of pre-prepared foods.

[0084] In some embodiments, in step S601, monitoring the interaction data between degradation indicators of trace components and degradation indicators of known components may include, but is not limited to, the following steps: Spectral data were obtained by performing spectral scanning on pre-prepared prepared foods. Differential analysis was performed on the spectral data to identify the spectral variation trends of trace components and known components; By comparing and analyzing the spectral variation trends of trace components with those of known components, the differences and correlations in the variation trends were obtained. Based on the differences and correlations in the trends of change, the strength and type of the interaction between the degradation signs of trace components and the degradation signs of known components are analyzed to obtain interaction data.

[0085] In some embodiments, the pre-prepared prepared food can be first subjected to spectral scanning to obtain spectral data. Spectral analysis techniques can be used to measure the light absorption, reflection, or transmission characteristics of the pre-prepared prepared food within a specific wavelength range to obtain its chemical composition and structural information. Specifically, techniques such as near-infrared spectroscopy (NIR), Raman spectroscopy, or hyperspectral imaging can be used to perform non-contact scanning of the pre-prepared prepared food to obtain spectral data containing rich chemical information. This spectral data can reflect the characteristic absorption or scattering peaks of various components in the pre-prepared prepared food.

[0086] Then, differential analysis is performed on the spectral data to identify the spectral variation trends of trace components and known components. Mathematical processing methods can be used to highlight subtle but important changes in the spectral data and eliminate background interference. Specifically, differential analysis can be achieved by calculating the differences in spectral data at different time points or under different processing conditions, performing derivative calculations, or using multivariate curve resolution (MCR). By analyzing the changes in peak intensity or peak shape at specific wavelengths in the differential spectrum, the unique spectral variation patterns of trace components and known components during the degradation process can be identified, thereby revealing their degradation trends.

[0087] Then, a comparative analysis of the spectral change trends of trace components and known components is conducted to obtain differences and correlations in these trends. The relationships between two or more components can be revealed by comparing the similarities and differences in their spectral change patterns during degradation. For example, statistical methods such as correlation coefficients, Euclidean distance, principal component analysis (PCA), or partial least squares (PLS) can be used to quantify the similarity or difference between the spectral change trends of trace and known components. Differences in trends can reflect their independent degradation characteristics, while correlations may indicate synergistic or antagonistic effects between them.

[0088] Finally, based on the differences and correlations in the trends, the strength and type of interaction between the degradation signs of trace components and those of known components are analyzed to obtain interaction data. This allows us to explore the extent and manner in which trace and known components influence each other during degradation. For example, if the spectral trends of two components show a high positive correlation, it may indicate a synergistic degradation effect; if they show a negative correlation, it may indicate an antagonistic effect. By constructing corresponding mathematical models or expert systems, these interactions can be quantitatively evaluated, thus obtaining interaction data including interaction coefficients and interaction type identifiers.

[0089] This embodiment acquires real-time spectral information of pre-prepared food during its degradation process by performing spectral scanning. Subsequently, differential analysis effectively filters out background noise and amplifies subtle spectral changes in trace and known components, thereby accurately identifying their respective spectral trends. Furthermore, by comparing and analyzing these trends, the differences and correlations between them can be quantified, providing a data foundation for a deeper understanding of the interactions between trace and known components in the degradation process of complex food systems. This allows for accurate analysis of the intensity and type of interactions between these degradation indicators, resulting in more comprehensive and accurate interaction data, providing a reliable basis for subsequent calculation of correction magnitude adjustment coefficients.

[0090] Through the above technical solutions, this embodiment can more accurately identify the spectral characteristics and dynamic changes of different component degradation through spectral scanning, differential analysis, and comparative analysis, thereby revealing their synergistic or antagonistic effects. As a result, the obtained interaction data is more comprehensive and accurate, providing solid data support for subsequent nonlinear adjustments to the correction magnitude of the state assessment results, making the risk assessment and quality management of pre-prepared foods more precise and reliable.

[0091] The beneficial effects of implementing the embodiments of the present invention include: First, the pre-prepared food is marked to generate a digital product identity. Then, the first environmental parameters of the pre-prepared food are collected, and the digital product identity is associated with the first environmental parameters to obtain the association result. Based on the association result, an individualized historical file of the pre-prepared food is generated. Based on the individualized historical file, the pre-prepared food is subjected to a status assessment to obtain the product status. Finally, based on the product status, a customized heating scheme is generated and executed through the heating module. This allows for the assessment of the product status by combining environmental parameters and individualized historical files, thereby achieving food risk management and improving safety and product quality.

[0092] like Figure 2 As shown, this embodiment of the invention also provides a pre-prepared food risk management system, including: The identity tagging module 701 is used to tag pre-prepared foods during their distribution process and generate digital product identity tags. The environmental acquisition module 702 is used to collect the first environmental parameters of pre-prepared food. The association module 703 is used to associate the product's digital identity with the first environmental parameter to obtain the association result; The archive generation module 704 is used to generate individualized historical archives for pre-prepared foods based on the association results. The status assessment module 705 is used to assess the status of pre-prepared foods based on individualized historical records during the heating process of pre-prepared foods to obtain the product status. Solution generation module 706 is used to generate customized heating solutions based on product status; Solution execution module 707 is used to send customized heating solutions to the heating system. The content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0093] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

Claims

1. A method of pre-prepared, cooked food risk management, characterized by, The method comprises the following steps: marking the pre-prepared food during the flow process of the pre-prepared food, generating a product digital identity; collecting a first environmental parameter of the pre-prepared food; associating the product digital identity with the first environmental parameter to obtain an association result; generating an individualized historical archive of the pre-prepared food according to the association result; during the heating process of the pre-prepared food, performing state evaluation processing on the pre-prepared food according to the individualized historical archive to obtain a product state; generating a customized heating scheme according to the product state; sending the customized heating scheme to a heating module for executing the customized heating scheme.

2. The method of claim 1, wherein, The method of generating a customized heating scheme according to the product state comprises: performing spectral scanning on the pre-prepared food to obtain spectral data; identifying a degradation state of the pre-prepared food according to the spectral data; generating the customized heating scheme according to the product state and the degradation state.

3. The method of claim 2, wherein, The method of identifying a degradation state of the pre-prepared food according to the spectral data comprises: comparing the spectral data with a spectral feature mode library to obtain a comparison result, the spectral feature mode library containing spectral feature modes of multiple degradation products; calculating the contribution degree of multiple degradation pathways according to the comparison result; identifying the degradation state according to the contribution degree of multiple degradation pathways.

4. The method of claim 2, wherein, The method of generating the customized heating scheme according to the product state and the degradation state comprises: evaluating the safety risk degree and the quality deterioration degree of the pre-prepared food according to the degradation state; if the safety risk degree is greater than a preset safety threshold, generating the customized heating scheme according to a safety enhancement strategy and the product state; if the quality deterioration degree is greater than a preset quality threshold, generating the customized heating scheme according to a quality optimization strategy and the product state; if the safety risk degree is less than the preset safety threshold and the quality deterioration degree is less than the preset quality threshold, calculating a balance relationship according to the safety risk degree and the quality deterioration degree, and generating the customized heating scheme according to the balance relationship and the product state.

5. The method of claim 1, wherein, The method of performing state evaluation processing on the pre-prepared food according to the individualized historical archive to obtain a product state comprises: extracting temperature, humidity, time and location information of the pre-prepared food in the flow process from the individualized historical archive; extracting corresponding second environmental parameters from the individualized historical archive according to the location information; calculating the degradation rate of each ingredient in the pre-prepared food according to the temperature, the humidity, the time, the second environmental parameters and the sensitivity parameters of food ingredients to environmental parameters; calculating the cumulative degradation amount of each ingredient in the pre-prepared food according to the degradation rate of each ingredient; performing compound degradation state evaluation on the pre-prepared food according to the cumulative degradation amount of each ingredient to obtain a compound degradation state evaluation result; generating the product state according to the compound degradation state evaluation result.

6. The method of claim 5, wherein, After the composite degradation state evaluation result of the prepared and conditioned food is obtained by evaluating the prepared and conditioned food according to the cumulative degradation amount of each ingredient, the method further comprises: performing spectral residual analysis on the prepared and conditioned food to obtain a residual spectrum; identifying degradation signs of trace ingredients according to characteristic peaks and characteristic regions of the residual spectrum, the trace ingredients not existing in the spectral characteristic mode library; updating the composite degradation state evaluation result according to the degradation signs of the trace ingredients.

7. The method of claim 6, wherein, The updating of the composite degradation state evaluation result according to the degradation signs of the trace ingredients comprises: determining a first influence weight of the degradation signs of the trace ingredients on the safety risk degree and the quality deterioration degree of the prepared and conditioned food; determining a second influence weight of degradation signs of known ingredients on the safety risk degree and the quality deterioration degree of the prepared and conditioned food, the known ingredients existing in the spectral characteristic mode library; determining a state evaluation result correction amplitude according to the first influence weight and the second influence weight; updating the composite degradation state evaluation result according to the state evaluation result correction amplitude.

8. The method of claim 7, wherein, After the state evaluation result correction amplitude is determined according to the first influence weight and the second influence weight, the method further comprises: monitoring interaction data between the degradation signs of the trace ingredients and the degradation signs of the known ingredients; calculating a correction amplitude adjustment coefficient according to the interaction data and a synergistic antagonistic effect curve; nonlinearly adjusting the state evaluation result correction amplitude according to the correction amplitude adjustment coefficient.

9. The method of claim 8, wherein, The monitoring of the interaction data between the degradation signs of the trace ingredients and the degradation signs of the known ingredients comprises: performing spectral scanning on the prepared and conditioned food to obtain spectral data; performing differential analysis on the spectral data to identify spectral change trends of the trace ingredients and spectral change trends of the known ingredients; performing comparative analysis on the spectral change trends of the trace ingredients and the spectral change trends of the known ingredients to obtain change trend differences and change trend correlations; analyzing interaction intensity and types between the degradation signs of the trace ingredients and the degradation signs of the known ingredients according to the change trend differences and the change trend correlations to obtain the interaction data.

10. A pre-prepared, ready-to-eat food risk management system, characterized in that, comprises: an identity marking module configured to mark the prepared and conditioned food to generate a product digital identity in a flow process of the prepared and conditioned food; an environment acquisition module configured to acquire first environment parameters of the prepared and conditioned food; an association module configured to associate the product digital identity with the first environment parameters to obtain an association result; an archive generation module configured to generate an individualized historical archive of the prepared and conditioned food according to the association result; a state evaluation module configured to perform state evaluation processing on the prepared and conditioned food according to the individualized historical archive to obtain a product state in a heating process of the prepared and conditioned food; a scheme generation module configured to generate a customized heating scheme according to the product state. a protocol execution module to send the customized heating protocol to a heating module, the heating module to execute the customized heating protocol.

Images