Health food processing control optimization method and device based on production prediction

Abstract

The invention discloses a health food processing control optimization method and device based on production prediction, and relates to the technical field of processing prediction management, and the method comprises the steps: deploying monitoring equipment at a health food production line, and obtaining real-time monitoring data; a model is constructed through data, and key control points and production deviations of health care and food processing are mined. And predicting the production trend based on the deviation by using a medicine and food homology strategy to obtain an adjustment index set. And extracting key control indexes according to the adjustment index set contrast deviation. And establishing a feedback mechanism based on the key control indexes, and setting a dynamic threshold range to optimize and adjust the production line in real time. The technical problem that comprehensive and accurate monitoring, scientific adjustment basis, clear key control indexes and dynamic adjustment mechanisms are lacked in existing health food production is solved, and the technical effects of comprehensively optimizing the health food production process, improving the product quality and the production efficiency and providing safer and more effective health food are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of processing prediction management, and in particular to a method and device for optimizing health food processing control based on production prediction. Background Art

[0002] In the production scenario of health food, the guarantee of product quality and production efficiency is particularly prominent, and the contradiction between the demand for scientific and reasonable processing control methods is relatively more prominent. Achieving efficient processing control to improve product quality has become a crucial link in the production of health food. Traditional health food production is often extensive and lacks specificity. It relies solely on experience for production control, lacks comprehensive monitoring of the production process, lacks in-depth mining and analysis of health-related and food-related data, and is difficult to accurately identify key control points and production deviations. In terms of production adjustments, there is a lack of scientific basis, resulting in inappropriate adjustment plans, unclear key control indicators, and inability to respond well to different production conditions and product requirements.

[0003] At the current stage, relevant technologies exist in the lack of comprehensive and accurate monitoring, scientific adjustment basis, clear key control indicators and dynamic adjustment mechanism in the production of health food. Summary of the invention

[0004] This application provides a health food processing control optimization method and device based on production prediction, and adopts monitoring equipment deployed in the health food production line to obtain real-time monitoring data, including health and food related data. Through these data, a model is constructed to dig out key control points and production deviations in health and food processing. Based on the deviation, the production trend is predicted with the medicine and food homology strategy, and the adjustment index set corresponding to the content of the first and second class homology raw materials is obtained. At the same time, the key control indicators, including the retention rate of the active ingredient and the stability of the product, are extracted according to the deviation of the adjustment index set. Finally, a feedback mechanism is established based on the key control indicators, and the dynamic threshold range is set to optimize and adjust the production line in real time, which realizes comprehensive real-time monitoring, accurate identification of key control points and production deviations, scientific adjustment with the medicine and food homology strategy, clear key control indicators, establishment of feedback mechanism and setting of dynamic threshold range, and achieves the comprehensive optimization of the health food production process, improves product quality and production efficiency, and provides a safer and more effective technical effect of health food.

[0005] This application provides a health food processing control optimization method based on production prediction, including: Deploy monitoring equipment on a health food production line to obtain real-time monitoring data, wherein the real-time monitoring data includes health-related monitoring data and food-related monitoring data; construct a data analysis model through the real-time monitoring data, and conduct in-depth mining on the health-related monitoring data and the food-related monitoring data, respectively, to identify health-related processing key control points and health-related production deviations, food processing key control points and food production deviations; based on the health-related processing key control points and health-related production deviations, predict production trends with the strategy of medicine and food homology, and obtain a first adjustment indicator set, wherein the first adjustment indicator set corresponds to a class of homologous raw material content marked with health attributes; based on the food processing key control points and health-related production deviations, predict production trends with the strategy of medicine and food homology, and obtain a first adjustment indicator set, wherein the content of a class of homologous raw materials marked with health attributes is The key control points of the processing industry and the deviations of food production are used to predict the production trend with the strategy of medicine and food homology, and a second adjustment indicator set is obtained. The second adjustment indicator set corresponds to the content of the second type of homologous raw materials marked with nutritional attributes; at the same time, according to the first adjustment indicator set and the second adjustment indicator set, the health food production line is connected, and the key control points of health processing and health production deviations, food processing key control points and food production deviations are compared to extract key control indicators, which include effective ingredient retention rate and product stability; based on the key control indicators, a feedback mechanism is established, and a dynamic threshold range is set to optimize and adjust the health food production line in real time.

[0006] The present application also provides a health food processing control optimization device based on production prediction, comprising: A real-time monitoring data acquisition module, the real-time monitoring data acquisition module is used to deploy monitoring equipment on the health food production line to acquire real-time monitoring data, the real-time monitoring data including health-related monitoring data and food-related monitoring data; a data analysis model construction module, the data analysis model construction module is used to construct a data analysis model through the real-time monitoring data, and conduct in-depth mining of the health-related monitoring data and the food-related monitoring data, respectively, to identify health-related processing key control points and health-related production deviations, food processing key control points and food production deviations; a production trend prediction module, the production trend prediction module is used to predict production trends based on the health-related processing key control points and health-related production deviations, using the medicine-food homology strategy, to acquire a first adjustment indicator set, the first adjustment indicator set corresponds to the content of a class of homologous raw materials marked with health attributes; a second adjustment indicator set is obtained The acquisition module is used for predicting the production trend based on the food processing key control points and food production deviations, using the medicine and food homology strategy to obtain the second adjustment indicator set, and the second adjustment indicator set corresponds to the content of the second type of homologous raw materials marked with nutritional attributes; the key control indicator extraction module is used for simultaneously, according to the first adjustment indicator set and the second adjustment indicator set, connecting the health food production line, comparing the health processing key control points and health production deviations, food processing key control points and food production deviations, extracting key control indicators, the key control indicators include effective ingredient retention rate, product stability; feedback mechanism establishment module, the feedback mechanism establishment module is used to establish a feedback mechanism based on the key control indicators, and set a dynamic threshold range to optimize and adjust the health food production line in real time.

[0007] The method and device for optimizing the processing control of health food based on production prediction proposed in this application are first deployed on the health food production line to obtain real-time monitoring data, including health and food related data. The model is constructed through these data to dig out the key control points and production deviations of health and food processing. Based on the deviation, the production trend is predicted with the strategy of medicine and food homology, and the adjustment index set corresponding to the content of Class I and Class II homology raw materials is obtained. At the same time, the key control indicators, including the retention rate of active ingredients and product stability, are extracted according to the deviation of the adjustment index set. Finally, a feedback mechanism is established based on the key control indicators, and the dynamic threshold range is set to optimize and adjust the production line in real time. Through comprehensive real-time monitoring, accurate identification of key control points and production deviations, scientific adjustment with the strategy of medicine and food homology, clear key control indicators, establishment of feedback mechanism and setting of dynamic threshold range, the comprehensive optimization of the production process of health food is achieved, the product quality and production efficiency are improved, and the technical effect of providing safer and more effective health food is provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic diagram of a process flow of a health food processing control optimization method based on production prediction provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a health food processing control optimization device based on production prediction provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: real-time monitoring data acquisition module 10, data analysis model construction module 20, production trend prediction module 30, second adjustment indicator set acquisition module 40, key control indicator extraction module 50, feedback mechanism establishment module 60. DETAILED DESCRIPTION

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0012] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0013] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0014] The present application embodiment provides a method for optimizing health food processing control based on production prediction, such as Figure 1 As shown, the method includes: Step S100, deploy monitoring equipment on the health food production line to obtain real-time monitoring data, and the real-time monitoring data includes health-related monitoring data and food-related monitoring data. Specifically, in the process of deploying monitoring equipment on the health food production line to obtain real-time monitoring data, the specific monitoring requirements of health-related monitoring data (such as the content of active ingredients in raw materials, efficacy indicators, the impact of the processing process on health-related ingredients, etc.) and food-related monitoring data (such as production environment parameters, production process parameters, product quality parameters, etc.) are clarified, and appropriate monitoring equipment is selected according to the requirements, such as high-performance liquid chromatographs for health-related monitoring, temperature sensors for food-related monitoring, etc., the installation location is determined, and the equipment is installed and debugged according to the equipment manual, and the equipment is connected to the data transmission system to ensure that the real-time monitoring data can be transmitted to the data center in time for storage and analysis. After the equipment is running, the data is collected in real time, and the data center processes and analyzes it. If an abnormal situation occurs, the early warning mechanism is activated to notify relevant personnel to take measures to ensure the stability of the production process and the safety of product quality.

[0015] Step S200, construct a data analysis model through the real-time monitoring data, and conduct in-depth mining on the health-related monitoring data and the food-related monitoring data, respectively, to identify health-related processing key control points and health-related production deviations, food processing key control points and food production deviations. Specifically, collect and organize the real-time monitoring data from the health food production line, including health-related monitoring data and food-related monitoring data, and classify them according to different aspects, select a suitable analysis method to build a data analysis model, clarify that the input of the model is the two types of organized monitoring data, and the output is the identification results of health-related processing key control points and health-related production deviations, food processing key control points and food production deviations, use historical data to train the model, and continuously adjust the model parameters and structure so that it can accurately identify key control points and production deviations. At the same time, use part of the data as a validation set to verify and optimize the trained model to ensure its accuracy and reliability. For health-related monitoring data, deeply analyze the changes in the content of active ingredients, and observe its changing trends in different production links through time series analysis and other methods. If the content of active ingredients in a certain link is If the quality of the product decreases or fluctuates significantly, this link may be the key control point of health-care processing; at the same time, evaluate the stability of efficacy indicators, analyze their changes in the production process, and determine whether there is a production deviation. For food-related monitoring data, analyze the impact of production environment parameters such as temperature, humidity, and air pressure on food quality, and determine the appropriate parameter range. Exceeding the range may lead to food production deviations; optimize production process parameters, and study the impact of different process parameter combinations on product quality through experimental design and other methods, and determine the best parameters to avoid production deviations; monitor product quality parameters such as appearance, color, odor, taste, as well as microbial indicators, heavy metal content and other safety indicators in real time. If they do not meet the standards, there may be food production deviations. Comprehensively analyze and deeply mine the results of the two types of monitoring data, combine professional knowledge and experience, and judge the key control points of health-care processing and food processing as well as the existence of production deviations.

[0016] Step S300, based on the health care processing key control points and health care production deviations, the production trend is predicted with the medicine and food homology strategy, and the first adjustment index set is obtained, and the content of a class of homologous raw materials marked with health attributes corresponding to the first adjustment index set. Specifically, the health care processing key control points and health care production deviations are determined by analyzing the real-time monitoring data of the health food production line, and the medicine and food homology strategy is understood. A class of homologous raw materials such as wolfberry, yam, and Poria cocos have both health and nutritional attributes. Historical data related to key control points and production deviations are collected, and a prediction model is established. The current situation is input into the model to obtain future production trends. The prediction content includes changes in active ingredient content and efficacy indicators. The adjustment target is determined according to the prediction results, and the effect of a class of homologous raw materials on the target is analyzed. The first adjustment index set, that is, the content of a class of homologous raw materials marked with health attributes, is determined through experimental design and other methods, providing a scientific basis for the adjustment of health food production.

[0017] Step S400, based on the food processing key control points and food production deviations, the production trend is predicted with the medicine and food homology strategy, and the second adjustment index set is obtained. The second adjustment index set corresponds to the content of the second type of homologous raw materials with nutritional attributes. Specifically, by analyzing the real-time monitoring data of the health food production line, the food processing key control points and food production deviations are clarified. The key control points may involve specific production links. The production deviation is manifested as the product quality parameters not meeting the standards, etc., and the application of the medicine and food homology strategy in food processing is understood. The second type of homologous raw materials have nutritional attribute marks, can provide nutrients for food and may have health effects, collect relevant data, establish a prediction model, input the current key control points and production deviations into the model, and obtain future food production trends, including the changing trends of food quality parameters and nutrient content. According to the prediction results, the adjustment target is determined, the role of the second type of homologous raw materials is analyzed, and the second adjustment index set, that is, the content of the second type of homologous raw materials with nutritional attributes is determined, so as to provide a scientific adjustment basis for the food processing of health foods.

[0018] Step S500, at the same time, according to the first adjustment index set and the second adjustment index set, the health food production line is connected, and the health processing key control points and health production deviations, food processing key control points and food production deviations are compared to extract key control indicators, and the key control indicators include active ingredient retention rate and product stability. Specifically, the data analysis system is connected to the health food production line, and the first and second adjustment index sets are prepared. The parameters related to health efficacy on the production line are analyzed by comparing the health processing key control points and health production deviations, and the influence of the content adjustment of a class of homologous raw materials is analyzed in combination with the first adjustment index set; the food quality-related parameters are evaluated by comparing the food processing key control points and food production deviations, and the effect of the content adjustment of the second class of homologous raw materials is studied in combination with the second adjustment index set, and the key control indicator of the effective ingredient retention rate is determined. By analyzing each link on the production line, the influencing factors are determined and control measures are formulated, and the changes in the active ingredient content are monitored to calculate the effective ingredient retention rate; at the same time, the product stability is evaluated, including physical and chemical stability, and the corresponding control indicators are determined by using accelerated stability tests and other methods, and the key control indicators such as the effective ingredient retention rate and product stability are extracted according to the adjustment index set in comparison with the key control points and production deviations, so as to provide support for the production control and quality optimization of health foods.

[0019] Step S600, based on the key control indicators, a feedback mechanism is established, and a dynamic threshold range is set to optimize and adjust the health food production line in real time. Specifically, in the production of health foods, the two key control indicators of effective ingredient retention rate and product stability are crucial. First, relevant data is collected by continuously monitoring the production line in real time, and compared and analyzed with preset indicators. If there is a deviation, a feedback signal is generated, and then adjustment measures are formulated. For example, if the effective ingredient retention rate is low, the process parameters can be adjusted or the content of a class of homologous raw materials can be increased. If there is a problem with product stability, the storage conditions can be optimized, etc. The dynamic threshold range is determined by analyzing historical data and considering various factors, and it is adjusted in real time with production changes. Once the feedback mechanism is triggered, the production line is adjusted quickly, and the key control indicator changes are continuously monitored after the adjustment. If the effect is not ideal, the measures are re-analyzed and formulated for continuous optimization, so as to ensure the production of high-quality health foods.

[0020] In a possible implementation, a feedback mechanism is established based on the key control indicators, and a dynamic threshold range is set to perform real-time optimization and adjustment on the health food production line. Step S600 further includes step S610, collecting basic information of consumer groups associated with the health food production line, wherein the basic information of consumer groups includes group health data and consumption preference information. Specifically, determine the scope of the consumer group, determine the target consumer group of health food through market research, sales data analysis, etc., and use multiple channels to collect basic information for the determined consumer group. For group health data, cooperate with medical institutions, conduct questionnaires, or use big data analysis and other means to collect information on consumers' common health problems, the prevalence of specific diseases, and demand for different nutrients. For example, if the target consumer group is mainly middle-aged and elderly people, you may collect information about their high attention to cardiovascular health, bone health, etc., and the possibility of chronic diseases such as hypertension and hyperlipidemia. For consumer preference information, collect it through online surveys, social media analysis, consumer feedback, etc., including consumers' preferences for product taste, dosage form (such as tablets, capsules, oral liquids, etc.), packaging design, and preference or avoidance of specific ingredients (such as vegetarians' avoidance of animal-derived ingredients). For example, through surveys, it is found that consumers prefer natural ingredients and are more sensitive to artificial additives.

[0021] Step S620, introduce the needs of the consumer group, and synchronously trim the dynamic threshold range against the basic information of the consumer group. The adaptability of the directional trimming segment corresponding to the synchronous trimming does not meet the limitations of the consumer group needs. Specifically, analyze the specific needs of consumers based on the collected basic information of the consumer group. For example, if the group health data shows that consumers are generally concerned about cardiovascular health, then there may be a high demand for specific ingredients in health foods. If consumer preference information shows that consumers like low-sugar products, then the sugar content needs to be reduced during the production process. The dynamic threshold range is synchronously trimmed against the basic information of the consumer group. The dynamic threshold range was originally set based on various technical indicators and quality control requirements in the production process, but in order to better meet the needs of the consumer group, it needs to be adjusted according to the health data and preference information of the consumer. For example, if the original sugar content threshold range is certain, but because consumers prefer low-sugar products, this threshold range needs to be adjusted downward to ensure that the health foods produced meet the needs of consumers. During synchronization, When cutting, each cutting segment needs to be evaluated to ensure that its fitness meets the requirements of the consumer group. For example, if the sugar content threshold is lowered, it is necessary to evaluate whether this adjustment will affect the taste, stability and other aspects of the product. If the taste of the product becomes poor or the stability is affected after the adjustment, then the fitness of this cutting segment does not meet the requirements of the consumer group. If it is found that the fitness of a certain cutting segment does not meet the requirements, it needs to be readjusted. Through further experiments, consumer testing, etc., a more appropriate threshold range can be found to ensure that while meeting consumer needs, the quality and safety of the product are guaranteed. Collecting basic information on consumer groups and introducing consumer group needs to synchronously cut the dynamic threshold range can make the production of health foods closer to the actual needs of consumers and improve the market competitiveness of products.

[0022] In a possible implementation, the demand of the consumer group is introduced, and the dynamic threshold range is synchronously trimmed in accordance with the basic information of the consumer group. The fitness of the directional trimming segment corresponding to the synchronous trimming does not meet the limitation of the demand of the consumer group. Step S620 further includes step S621, connecting the health food production line, marking the starting point coordinates, and the starting point coordinates are raw material procurement nodes. Specifically, a data connection channel with the health food production line is established, and each link of the production line is connected to the data processing system by installing sensors, data acquisition equipment, etc., so as to obtain various data in the production process in real time, ensure the stability and reliability of the data connection, and be able to transmit production data in a timely and accurate manner, providing a basis for subsequent analysis and adjustment. Determining the starting point of health food production, that is, the raw material procurement node, is the beginning of the entire production process and plays a vital role in subsequent production links. The starting point coordinates are clearly marked in the data processing system so that the production process can be clearly tracked and managed in the subsequent process. For example, a specific identifier or number can be used to mark the raw material procurement node.

[0023] Step S622, starting from the starting point coordinates, in accordance with the health food production line, along the direction of the health food production process, the key control indicators are marked in sequence. Specifically, starting from the raw material procurement node, in accordance with the actual health food production line, each production link is analyzed one by one, and the specific operation and function of each link are understood to prepare for marking key control indicators. Through on-site observation, reviewing the production flow chart, communicating with production personnel, etc., the operation of the production line is deeply understood. According to the production process of health food, from raw material procurement, processing, packaging and other links, in each link, the key control indicators related to the retention rate of active ingredients and product stability are determined. For example, in the raw material procurement link, the key control indicators may include the quality, purity, active ingredient content of the raw materials, etc.; in the processing link, it may include process parameters such as temperature, pressure, time, etc.; in the packaging link, it may include the sealing and moisture resistance of the packaging materials, etc., and each key control indicator is clearly marked so that it can be accurately identified and operated in the subsequent adjustment process.

[0024] Step S623, in the key control indicators, multi-point parallel adjustment is performed according to the dynamic threshold range after cutting. Specifically, the marked key control indicators are adjusted using the dynamic threshold range that was previously cut according to the needs of the consumer group. Multi-point parallel adjustment means that adjustments are made on multiple key control indicators at the same time to achieve overall optimization. For example, if a key control indicator exceeds the dynamic threshold range after cutting, it can be returned to a reasonable range by adjusting the relevant production parameters or taking other measures. Different adjustment methods can be used for different key control indicators. For example, for raw material quality issues, suppliers can be replaced or quality inspections can be strengthened; for process parameter issues, equipment settings can be adjusted or production processes can be optimized. During the adjustment process, changes in key control indicators need to be monitored in real time to ensure that the effect of the adjustment meets expectations. If the requirements are still not met after the adjustment, it is necessary to further analyze the reasons and make adjustments again, and comprehensively manage and optimize the health food production line to ensure that the quality and stability of the products meet the needs of consumers.

[0025] In a possible implementation, the key control indicators are adjusted in parallel at multiple points according to the clipped dynamic threshold range, and step S623 further includes step S6231, setting the quality standard of health food according to the health food industry standard. Specifically, the relevant standards and regulations of the health food industry are studied in depth, and the standards include national and local laws and regulations, specifications formulated by industry associations, and internationally used health food standards. Combined with the company's own production capacity, technical level and market positioning, the quality standard of health food suitable for the company is determined. The quality standard should cover all aspects of the product, such as active ingredient content, microbial indicators, heavy metal content, product stability, etc. A documented management system for quality standards is established to ensure the clarity and operability of the standards, and the quality standards are reviewed and updated regularly to adapt to the development and changes of the industry.

[0026] Step S6232, according to the health food quality standard, according to the clipped dynamic threshold range, multi-point parallel extraction is performed in the health food production program to obtain a multi-point parallel set, and the multi-point parallel set includes multiple parallel subsets. Specifically, based on the set health food quality standard, and considering the clipped dynamic threshold range, the dynamic threshold range is adjusted according to the needs of the consumer group, which is more in line with the actual market situation. In the health food production program, multiple key control points are determined. These key control points can be raw material procurement, production and processing, quality inspection, packaging and storage, etc. Data collection and analysis are performed on each key control point to extract information related to the quality standard. For example, in the raw material procurement link, the quality inspection data of the raw materials is extracted; in the production and processing link, the process parameters and the intermediate quality data of the product are extracted; in the quality inspection link, the data of various inspection indicators are extracted, and the data extracted from each key control point are integrated to form a multi-point parallel set, which includes multiple parallel subsets, and each subset corresponds to a data set of a key control point.

[0027] Step S6233, based on the multi-point parallel set, multi-point parallel adjustment is performed according to the dynamic threshold range after clipping. Specifically, based on the multi-point parallel set, a comprehensive analysis and evaluation of the health food production process is performed, and by comparing the data in each parallel subset with the dynamic threshold range after clipping, it is determined which key control points need to be adjusted. For the key control points that need to be adjusted, specific adjustment measures are formulated, and the adjustment measures include optimizing the raw material procurement channels, adjusting the production process parameters, strengthening the quality inspection efforts, improving the packaging and storage conditions, etc., and implementing multi-point parallel adjustment, that is, adjusting multiple key control points at the same time to achieve an overall optimization effect. During the adjustment process, the data changes of each key control point are monitored in real time to ensure the effectiveness of the adjustment measures. If the quality standards and dynamic threshold range requirements are still not met after the adjustment, it is necessary to re-evaluate the production process, find the root cause of the problem, and make further adjustments and optimizations.

[0028] In a possible implementation, based on the multi-point parallel set, multi-point parallel adjustment is performed according to the clipped dynamic threshold range, and step S6233 further includes step S62331, and the multi-point parallel adjustment formula is: ;in, is the weighted average of the multi-point parallel adjustments at time t, , , are the proportional, integral, and derivative control gains, is the error function at time t, which is used to characterize the difference corresponding to the expected output. Specifically, first understand the meaning of each part in the multi-point parallel adjustment formula, The weighted average value of the multi-point parallel adjustment at time t is the final adjustment value to be obtained, which is used to adjust the key control points in the production process of health food; is the error function at time t, representing the difference from the expected output; , , They are proportional, integral, and differential control gains. Determine the expected output and actual output, determine the expected output value of the key control point according to the quality standard and production target, obtain the actual output value through real-time monitoring, and calculate the error function That is, the difference between the actual and expected output values. The control gain parameters are determined through experiments, etc. , , , substitute the error function and control gain parameters into the formula to calculate the multi-point parallel adjustment value , including the addition of proportional terms, integral terms and differential terms. Finally, according to the adjustment value, the critical control point is adjusted and the effect is monitored in real time. If the error does not improve, the control gain parameter needs to be re-evaluated or other measures need to be taken. This formula can be used to accurately control and optimize the production of health food, ensure that the product quality meets the standards and improve production efficiency and stability.

[0029] In a possible implementation, the key control indicators are adjusted in parallel at multiple points according to the clipped dynamic threshold range, and step S623 further includes step S6234, using time series information as a constraint to predict the demand change trend. Specifically, collect time series information related to the demand for health food, which may include historical sales data, market research data, industry trend reports, etc., covering the consumer demand for health food in different time periods, analyze the key factors in the time series information, such as seasonal changes, holidays, socio-economic conditions, etc., on the demand for health food, for example, in winter, the demand for health food that enhances immunity may increase, and during holidays, the demand for health food with gift attributes may increase, and use data analysis methods, such as time series analysis, machine learning algorithms, etc., with time series information as a constraint, to predict the demand change trend of health food in the future period of time, for example, by establishing a time series model, predict the sales volume and demand growth of different types of health food in the next few months.

[0030] Step S623 further includes step S6235, adjusting the health food production plan of the health food production line and the raw material procurement strategy of the starting point coordinates according to the demand change trend. Specifically, according to the predicted demand change trend, the production plan of the health food production line is adjusted. If it is predicted that the demand for a certain health food will increase significantly, the production quantity of the product can be increased accordingly, the production schedule can be adjusted, and the production capacity of the production line can be improved, for example, the production shifts can be increased, the working hours can be extended, or the equipment investment can be increased, etc. The raw material procurement strategy of the starting point coordinates is adjusted. According to the demand change trend, the types and quantities of the required raw materials are predicted, and the supplier is communicated with in time to adjust the purchase order. For example, if the demand for a certain raw material will increase, the supplier is negotiated in advance to increase the supply and ensure the timeliness and stability of the supply to avoid affecting production due to shortage of raw materials.

[0031] Step S623 further includes step S6236, adjusting the key control indicators through the production plan of the health food production line, the raw material procurement strategy of the starting point coordinates, and the adaptive window. Specifically, after adjusting the production plan and raw material procurement strategy, the key control indicators are adjusted in combination with the adaptive window. The adaptive window is a time range or parameter range that is dynamically adjusted according to the production situation, and is used to monitor and adjust the key control indicators in real time. For different key control indicators, such as active ingredient retention rate, product stability, etc., they are monitored and analyzed within the adaptive window according to changes in the production plan and raw material procurement. For example, if the increase in the production plan leads to faster production, it may be necessary to pay more attention to the active ingredient retention rate and adjust the production process parameters to ensure that the product quality can be maintained at high output. If the adjustment of the raw material procurement strategy leads to changes in the quality or source of the raw materials, the key control indicators also need to be adjusted accordingly. For example, the raw materials provided by the new supplier may require different processing conditions to ensure product stability. By conducting experiments and adjustments within the adaptive window, the optimal control parameters are found, and the demand change trend is predicted with timing information as a constraint, and then the production plan and raw material procurement strategy are adjusted. In addition, the key control indicators are adjusted in combination with the adaptive window, which can enable the health food production line to respond more flexibly to changes in market demand and improve production efficiency and product quality.

[0032] In a possible implementation, the key control indicators are adjusted by combining the production plan of the health food production line, the raw material procurement strategy of the starting point coordinates, and the adaptive window. Step S6236 further includes step S62361, building a supply chain collaboration platform, which is used for information communication and sharing between suppliers, manufacturers and distributors. Specifically, the needs and functional goals of the supply chain collaboration platform are determined, the purpose is to promote information flow and collaboration between suppliers, manufacturers and distributors to improve the efficiency and responsiveness of the entire supply chain, design the architecture and technical solutions of the platform, and use cloud computing, big data, Internet of Things and other technologies to build a safe, reliable and efficient information sharing platform. For example, a platform based on a web page or mobile application is established to facilitate all parties to access and exchange information anytime and anywhere, determine the information content that needs to be shared on the platform, including raw material supply, production progress, inventory level, sales data, etc., to ensure that all parties can timely understand the dynamics of the entire supply chain in order to make accurate decisions, implement platform construction and deployment, carry out software development, testing and optimization, ensure the stability and performance of the platform, and train suppliers, manufacturers and distributors to make them familiar with the platform's usage and operation procedures.

[0033] Step S62362, add an initial window to the supply chain collaboration platform, and the initial window is used to adapt to the temporal changes in the health food production plan and the raw material procurement strategy. Specifically, on the constructed supply chain collaboration platform, add an initial window function, and the initial window is set to adapt to the temporal changes in the health food production plan and the raw material procurement strategy, and determine the parameters and settings of the initial window. For example, the time range of the window, the update frequency, etc., according to historical data and experience, preliminarily set a reasonable initial window, so that when the production plan and procurement strategy change, the operation of the supply chain can be adjusted in time, and the initial window can be integrated with the supply chain collaboration platform to ensure that all parties can easily view and use the initial window on the platform, and understand the impact of changes in production plans and procurement strategies on the supply chain.

[0034] Step S62363, evaluate the inventory and overstock risk of health food, and adaptively optimize the initial window to obtain the adaptive window. Specifically, the inventory of health food is monitored and analyzed in real time. Through the supply chain collaboration platform, inventory data of each link is collected, including raw material inventory, work-in-progress inventory and finished product inventory, and the risk of inventory backlog and expiration is evaluated. Considering factors such as the shelf life of the product, sales speed, and changes in market demand, it is analyzed whether the inventory has the risk of backlog and expiration. For example, if the sales speed of a certain product decreases and the inventory level is high, there may be a risk of backlog and expiration. According to the inventory evaluation results, the initial window is adaptively optimized. If it is found that the inventory risk is high, it is necessary to adjust the parameters of the initial window to speed up the response speed of the supply chain and reduce inventory backlog. For example, the time range of the window can be shortened and the update frequency can be increased so that the production plan and procurement strategy can be adjusted more timely. The adaptive window is continuously monitored and optimized. As market demand and supply chain conditions change, inventory risks are continuously evaluated. The adaptive window is adjusted and optimized to ensure the efficient operation of the supply chain and the reasonable control of inventory. The supply chain collaboration platform is constructed, the initial window is added and adaptively optimized, which can improve the collaborative ability of the supply chain, reduce inventory risks, and adapt to changes in health food production plans and raw material procurement strategies.

[0035] The embodiment of the present application adopts the deployment of monitoring equipment in the health food production line to obtain real-time monitoring data, including health and food related data. The model is constructed through these data to dig out the key control points and production deviations of health care and food processing. Based on the deviation, the production trend is predicted with the medicine and food homology strategy, and the adjustment index set corresponding to the content of the first and second class homology raw materials is obtained. At the same time, the key control indicators, including the retention rate of active ingredients and product stability, are extracted according to the deviation of the adjustment index set. Finally, a feedback mechanism is established based on the key control indicators, and the dynamic threshold range is set to optimize and adjust the production line in real time, achieving comprehensive real-time monitoring, accurate identification of key control points and production deviations, scientific adjustment with the medicine and food homology strategy, clarifying key control indicators, establishing a feedback mechanism and setting a dynamic threshold range, achieving the comprehensive optimization of the health food production process, improving product quality and production efficiency, and providing a safer and more effective technical effect of health food.

[0036] In the above, refer to Figure 1 The method for optimizing the processing control of health food based on production prediction according to an embodiment of the present invention is described in detail. Figure 2 A health food processing control optimization device based on production prediction according to an embodiment of the present invention is described.

[0037] The health food processing control optimization device based on production prediction according to the embodiment of the present invention is used to solve the technical problems of lack of comprehensive and accurate monitoring, scientific adjustment basis, clear key control indicators and dynamic adjustment mechanism in the existing health food production, so as to achieve the comprehensive optimization of the health food production process, improve product quality and production efficiency, and provide a safer and more effective health food. The health food processing control optimization device based on production prediction includes: a real-time monitoring data acquisition module 10, a data analysis model construction module 20, a production trend prediction module 30, a second adjustment indicator set acquisition module 40, a key control indicator extraction module 50, and a feedback mechanism establishment module 60.

[0038] The real-time monitoring data acquisition module 10 is used to deploy monitoring equipment in the health food production line to acquire real-time monitoring data, wherein the real-time monitoring data includes health-related monitoring data and food-related monitoring data; The data analysis model building module 20 is used to build a data analysis model through the real-time monitoring data, and to perform in-depth mining on the health-related monitoring data and the food-related monitoring data, respectively, to identify health-related processing key control points and health-related production deviations, food processing key control points and food production deviations; The production trend prediction module 30 is used to predict the production trend based on the health-care processing critical control points and health-care production deviations using the medicine-food homology strategy, and obtain a first adjustment index set, wherein the first adjustment index set corresponds to the content of a class of homologous raw materials marked with health attributes; The second adjustment index set acquisition module 40 is used to predict the production trend based on the food processing key control points and food production deviations using the medicine and food homology strategy to acquire the second adjustment index set, and the second adjustment index set corresponds to the content of the second homologous raw materials marked by the nutritional attributes; The key control index extraction module 50 is used to simultaneously connect the health food production line according to the first adjustment index set and the second adjustment index set, and extract key control indicators by comparing the health processing key control points and health production deviations, food processing key control points and food production deviations, wherein the key control indicators include active ingredient retention rate and product stability; The feedback mechanism establishment module 60 is used to establish a feedback mechanism based on the key control indicators and set a dynamic threshold range to perform real-time optimization and adjustment on the health food production line.

[0039] The specific configuration of the feedback mechanism establishment module 60 will be described in detail below. As described above, based on the key control indicators, a feedback mechanism is established, and a dynamic threshold range is set to optimize and adjust the health food production line in real time. The feedback mechanism establishment module 60 further includes: a basic information collection unit, the basic information collection unit is used to collect basic information of consumer groups associated with the health food production line, and the basic information of consumer groups includes group health data and consumption preference information; a dynamic threshold range synchronization unit, the dynamic threshold range synchronization unit is used to introduce consumer group needs, and synchronously cut the dynamic threshold range against the basic information of the consumer group, and the fitness of the directional cutting segment corresponding to the synchronous cutting does not meet the limitation of the consumer group needs.

[0040] Among them, the consumer group demand is introduced, and the dynamic threshold range is synchronously trimmed according to the basic information of the consumer group. The adaptability of the directional trimming segment corresponding to the synchronous trimming does not meet the limitation of the consumer group demand. The dynamic threshold range synchronization unit further includes: a starting point coordinate marking subunit, the starting point coordinate marking subunit is used to connect the health food production line and mark the starting point coordinates, and the starting point coordinates are the raw material procurement nodes; a key control indicator marking subunit, the key control indicator marking subunit is used to start from the starting point coordinates, compare with the health food production line, and mark the key control indicators in sequence along the direction of the health food production process; a multi-point parallel adjustment subunit, the multi-point parallel adjustment subunit is used to perform multi-point parallel adjustment on the key control indicators according to the dynamic threshold range after trimming.

[0041] Among them, in the key control indicators, multi-point parallel adjustment is performed according to the dynamic threshold range after trimming, and the multi-point parallel adjustment subunit further includes: a quality standard setting microunit, the quality standard setting microunit is used to set the health food quality standard according to the health food industry standard; a multi-point parallel set acquisition microunit, the multi-point parallel set acquisition microunit is used to perform multi-point parallel extraction in the health food production process according to the health food quality standard and the dynamic threshold range after trimming, and obtain a multi-point parallel set, the multi-point parallel set includes multiple parallel subsets; a multi-point parallel adjustment microunit, the multi-point parallel adjustment microunit is used to perform multi-point parallel adjustment based on the multi-point parallel set according to the dynamic threshold range after trimming.

[0042] Wherein, based on the multi-point parallel set, multi-point parallel adjustment is performed according to the clipped dynamic threshold range, and the multi-point parallel adjustment micro-unit further includes: a parallel adjustment formula determines a nano-unit, and the parallel adjustment formula determines a nano-unit for a multi-point parallel adjustment formula: ;in, is the weighted average of the multi-point parallel adjustments at time t, , , are the proportional, integral, and derivative control gains, is the error function at time t, representing the difference from the expected output.

[0043] Among them, in the key control indicators, multi-point parallel adjustment is performed according to the dynamic threshold range after trimming, and the multi-point parallel adjustment sub-unit further includes: a demand change trend prediction micro-unit, the demand change trend prediction micro-unit is used to predict the demand change trend with timing information as a constraint; a raw material procurement strategy micro-unit, the raw material procurement strategy micro-unit is used to adjust the health food production plan of the health food production line and the raw material procurement strategy of the starting point coordinates through the demand change trend; an adaptive window combination micro-unit, the adaptive window combination micro-unit is used to adjust the key control indicators through the production plan of the health food production line and the raw material procurement strategy of the starting point coordinates in combination with the adaptive window.

[0044] Among them, the key control indicators are adjusted through the production plan of the health food production line, the raw material procurement strategy of the starting point coordinates, and the adaptive window. The adaptive window combined with the micro unit further includes: a communication sharing nano unit, the communication sharing nano unit is used to build a supply chain collaboration platform, and the supply chain collaboration platform is used for information communication and sharing between suppliers, manufacturers and distributors; an initial window adding nano unit, the initial window adding nano unit is used to add an initial window to the supply chain collaboration platform, and the initial window is used to adapt to the temporal changes of the health food production plan and the raw material procurement strategy; an adaptive optimization nano unit, the adaptive optimization nano unit is used to evaluate the inventory and backlog expiration risk of health food, and adaptively optimize the initial window to obtain the adaptive window.

[0045] The health food processing control optimization device based on production prediction provided in the embodiment of the present invention can execute the health food processing control optimization method based on production prediction provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0046] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0047] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A health food processing control optimization method based on production prediction, characterized in that: The method comprises: Deploy monitoring equipment on a health food production line to obtain real-time monitoring data, wherein the real-time monitoring data includes health-related monitoring data and food-related monitoring data; By using the real-time monitoring data, a data analysis model is constructed to perform in-depth mining on the health-related monitoring data and the food-related monitoring data, respectively, to identify health-related processing critical control points and health-related production deviations, food processing critical control points and food production deviations; Based on the health-care processing critical control points and health-care production deviations, a production trend forecast is performed using a medicine-food homology strategy to obtain a first adjustment indicator set, wherein the first adjustment indicator set corresponds to a homologous raw material content of a health attribute marker; Based on the food processing critical control points and food production deviations, a production trend forecast is performed using the medicine-food homology strategy to obtain a second adjustment index set, and the second adjustment index set corresponds to the content of the second homologous raw materials marked with nutritional attributes; At the same time, according to the first adjustment index set and the second adjustment index set, the health food production line is connected, and the key control indicators are extracted by comparing the health processing key control points and health production deviations, food processing key control points and food production deviations. The key control indicators include active ingredient retention rate and product stability; Based on the key control indicators, a feedback mechanism is established, and a dynamic threshold range is set to perform real-time optimization and adjustment on the health food production line.

2. The method for optimizing health food processing control based on production prediction according to claim 1, characterized in that: Setting a dynamic threshold range, the method further includes: Collecting basic information of consumer groups associated with the health food production line, wherein the basic information of consumer groups includes group health data and consumption preference information; The consumer group demand is introduced, and the dynamic threshold range is synchronously trimmed according to the basic information of the consumer group. The adaptability of the directional trimming segment corresponding to the synchronous trimming does not meet the limitation of the consumer group demand.

3. The method for optimizing health food processing control based on production prediction according to claim 2, characterized in that: The dynamic threshold range is synchronously tailored in accordance with the basic information of the consumer group, and then the method includes: Connect the health food production line and mark the starting point coordinates, where the starting point coordinates are the raw material procurement nodes; Starting from the starting point coordinates, in accordance with the health food production line, along the direction of the health food production process, the key control indicators are marked in sequence; In the key control indicators, multi-point parallel adjustment is performed according to the clipped dynamic threshold range.

4. The method for optimizing health food processing control based on production prediction according to claim 3, characterized in that: Performing multi-point parallel adjustment according to the clipped dynamic threshold range, the method comprising: Set up quality standards for health foods according to health food industry standards; According to the health food quality standard and the clipped dynamic threshold range, multi-point parallel extraction is performed in the health food production process to obtain a multi-point parallel set, wherein the multi-point parallel set includes a plurality of parallel subsets; Based on the multi-point parallel set, multi-point parallel adjustment is performed according to the clipped dynamic threshold range.

5. The method for optimizing health food processing control based on production prediction according to claim 4, characterized in that: Performing multi-point parallel adjustment according to the clipped dynamic threshold range, the method comprising: Multi-point parallel adjustment formula: ； in, is the weighted average of the multi-point parallel adjustments at time t, , , are the proportional, integral, and derivative control gains, The error function at time t is used to characterize the difference corresponding to the expected output.

6. The method for optimizing health food processing control based on production prediction according to claim 3, characterized in that: Performing multi-point parallel adjustment according to the clipped dynamic threshold range, the method further includes: Using time series information as a constraint, predict demand change trends; According to the demand change trend, the health food production plan of the health food production line and the raw material procurement strategy of the starting point coordinates are adjusted; The key control indicators are adjusted through the production plan of the health food production line, the raw material procurement strategy of the starting point coordinates, and the adaptive window.

7. The method for optimizing health food processing control based on production prediction according to claim 6, characterized in that: The key control index is adjusted by combining the production plan of the health food production line, the raw material procurement strategy of the starting point coordinates, and the adaptive window. The method includes: Building a supply chain collaboration platform, which is used for information communication and sharing among suppliers, manufacturers and distributors; In the supply chain collaboration platform, an initial window is added, and the initial window is used to adapt to the temporal changes of the health food production plan and the raw material procurement strategy; The inventory and overstocking risk of health food are evaluated, and the initial window is adaptively optimized to obtain the adaptive window.

8. A health food processing control optimization device based on production prediction, characterized in that: The device is used to implement the health food processing control optimization method based on production prediction according to any one of claims 1 to 7, and the device comprises: A real-time monitoring data acquisition module, which is used to deploy monitoring equipment on a health food production line to acquire real-time monitoring data, including health-related monitoring data and food-related monitoring data; A data analysis model building module, wherein the data analysis model building module is used to build a data analysis model through the real-time monitoring data, and to perform in-depth mining on the health-related monitoring data and the food-related monitoring data, respectively, to identify health-related processing critical control points and health-related production deviations, food processing critical control points and food production deviations; A production trend prediction module, the production trend prediction module is used to predict the production trend based on the health care processing key control points and health care production deviations with the medicine and food homology strategy, and obtain a first adjustment indicator set, and the content of a class of homologous raw materials marked with health attributes corresponding to the first adjustment indicator set; A second adjustment index set acquisition module, the second adjustment index set acquisition module is used to predict the production trend based on the food processing key control points and food production deviations with the medicine and food homology strategy, and acquire the second adjustment index set, and the second adjustment index set corresponds to the content of the second homologous raw materials marked with nutritional attributes; A key control index extraction module, the key control index extraction module is used to simultaneously connect the health food production line according to the first adjustment index set and the second adjustment index set, and extract key control indicators by comparing the health processing key control points and health production deviations, food processing key control points and food production deviations, wherein the key control indicators include active ingredient retention rate and product stability; A feedback mechanism establishment module is used to establish a feedback mechanism based on the key control indicators and set a dynamic threshold range to optimize and adjust the health food production line in real time.

Images