Food waste whole-process monitoring analysis method and system based on multiple scenes

Abstract

The invention provides a multi-scene-based food waste whole-process monitoring analysis method and system, and the method comprises the steps: constructing a multi-scene monitoring system, and employing a layered three-stage probability sampling design for each food waste scene, and the three-stage probability sampling design comprises investigation object selection, investigation region coverage and food material classification; based on a multi-scene monitoring system, food waste data collection is carried out on food waste scenes to which catering canteens, take-out food and families belong through a five-barrel classification method, a quaternary separation method and a three-step classification method; the collected food waste data are sequentially subjected to preprocessing and classified data coding, and the preprocessing step comprises data format unification, data cleaning, data classification, missing value processing and numerical value standardization; and for the data after preprocessing and classification data coding, food waste quantitative analysis is carried out by adopting a descriptive statistical method and a quantitative analysis method, and comprehensive monitoring of the food waste condition is completed.

Description

Technical Field

[0001] The present application relates to the technical field of food waste monitoring and analysis, and in particular to a method and system for full-process monitoring and analysis of food waste based on multiple scenarios. Background Art

[0002] In today's society, the problem of food waste is becoming increasingly serious, which not only causes a large amount of waste of resources, but also has a negative impact on the environment. In order to effectively solve this problem, it is necessary to accurately monitor and analyze the food waste situation. At present, although there are some food waste monitoring methods for specific scenarios, such as weighing food waste after meals in restaurants, these methods have many limitations. First, they usually only focus on a single scenario and cannot fully cover multiple scenarios such as restaurants, takeaways, and families, resulting in one-sidedness and incompleteness of the data. Secondly, the existing monitoring methods lack standardized processes and operating specifications, and the accuracy and comparability of data collection are difficult to guarantee. In addition, the analysis of waste situations mostly stays on the surface, lacks in-depth quantitative analysis and research on influencing factors, and cannot provide a strong basis for formulating effective measures to reduce food waste.

[0003] In general, there are several major problems with existing food waste monitoring technologies: First, the monitoring scenario is single. Most existing technologies only monitor traditional scenarios such as restaurants, homes, and canteens, while ignoring the waste in emerging industries such as takeout. This limitation makes it impossible for existing methods to fully reflect the overall situation of food waste and cover all key consumption scenarios.

[0004] Secondly, there is a lack of standardized processes. Existing monitoring methods lack unified standardized processes and operating specifications. Different researchers or institutions use different technologies and methods in the data collection process, resulting in inconsistent data collection. This inconsistency makes it difficult to compare and integrate different data, which seriously affects the reliability and availability of the data.

[0005] Thirdly, data analysis is insufficient. Existing technologies lack in-depth quantitative analysis of monitored food waste data and research on influencing factors, and are unable to fully identify the key factors that lead to food waste. This deficiency limits the role of existing technologies in proposing scientific and effective measures to reduce food waste.

[0006] Finally, the practicality is poor. Some existing technologies have problems such as complex operation, expensive monitoring equipment, and low data collection efficiency in practical applications. These defects significantly increase the cost and difficulty of using the technology, limiting its promotion and popularization in large-scale applications. Summary of the invention

[0007] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0008] To this end, the first objective of this application is to propose a full-process monitoring and analysis method for food waste based on multiple scenarios.

[0009] The second objective of this application is to propose a full-process monitoring and analysis system for food waste based on multiple scenarios.

[0010] The third objective of the present application is to provide an electronic device.

[0011] A fourth objective of the present application is to provide a computer-readable storage medium.

[0012] A fifth object of the present application is to provide a computer program product.

[0013] To achieve the above objectives, the first embodiment of the present application proposes a full-process monitoring and analysis method for food waste based on multiple scenarios, including: Construct a multi-scenario monitoring system and adopt a stratified three-stage probability sampling design for each food waste scenario, which includes survey subject selection, survey area coverage and food classification; Based on the multi-scenario monitoring system, food waste data is collected for food waste scenarios in catering canteens, takeaways, and households through the five-barrel classification method, the four-element separation method, and the three-step classification method; The collected food waste data is preprocessed and classified into data encoding, wherein the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and numerical standardization; Based on the data after preprocessing and classification data coding, descriptive statistical methods and quantitative analysis methods are used to conduct quantitative analysis of food waste and complete comprehensive monitoring of food waste.

[0014] Optionally, the multi-scenario monitoring system is constructed, and a stratified three-stage probability sampling design is adopted for each food waste scenario, including: In the research object selection stage, catering operators were selected based on market share, including Chinese formal meals, global cuisine, fast food, hot pot, and snacks. Consumers were selected based on demographic characteristics, consumption behavior characteristics, waste monitoring indicators, and waste management systems. The research boundary covered the entire process from procurement and transportation, storage and cooking, consumption and dining to garbage disposal. In-depth research was conducted in the entire process of various dining scenarios through a variety of research methods, including at least one of direct weighing method, garbage diary method, questionnaire / interview method, digital photography and recognition method, volume method, and garbage composition analysis method. During the regional coverage phase of the survey, several cities with typical characteristics were selected for field research, and the sample size was allocated using a quota sampling method based on their economic development levels and population sizes. The selected cities are geographically distributed widely, and each has its own characteristics in terms of economic development level, population size, and cultural background, ensuring that the research results can fully reflect the regional differences in food waste in China; During the food classification stage, a standardized food classification method is adopted to divide food into multiple basic categories and twelve subcategories to ensure comprehensive monitoring of food waste, and pay attention to the waste of food during storage, processing and consumption. According to the degree of classification portability in different scenarios, a personalized food waste monitoring standardized classification basis is created; the basic categories include staple foods, meat, and fruits and vegetables, and the subcategories include pork, eggs, and beans.

[0015] Optionally, also include: In the survey of catering operators, the garbage diary method was used to record food waste in daily operations, questionnaires and interviews were used to obtain operational data, and the volume method was used to assess food loss and garbage generation; In terms of consumer surveys, direct weighing methods are used to measure individual or family food consumption, storage waste, processing loss and post-meal waste. The garbage diary method is used to record daily diet and waste processes. Questionnaires and interviews are used to collect basic consumer information, consumption habits and waste reasons. Digital photography and recognition methods are used to record and verify the accuracy of the reported information.

[0016] Optionally, food waste data can be collected for food waste scenarios in catering canteens using the five-bucket classification method, including: Sort the leftover food after meals into five categories: staple food, vegetables, meat, inedible parts and soup, and put them into the corresponding trash cans; During the post-meal cleanup phase in restaurants and cafeterias, each type of food waste is weighed using standardized weighing equipment, and its weight is recorded and counted.

[0017] Optionally, the food waste data of takeout food waste scenarios can be collected through the four-element separation method, including: Weigh the food before takeaway meals, and choose to weigh it separately or as a whole according to the takeaway packaging, and record the weight of the staple food and the total weight of the dishes separately; Classify the leftover food after takeout meals into staple food, dishes, soup and packaging, and put them into the corresponding trash cans respectively; when processing after the meal, drain the soup from the leftover food to ensure that there is no obvious liquid flow; For each type of food waste, weigh it using standardized weighing equipment, record its weight and make statistics.

[0018] Optionally, food waste data can be collected by using a three-step classification method to classify the food waste scenarios that a household belongs to, including: Food waste in the household is divided into raw material waste, post-meal waste and inedible parts, and they are classified in different trash cans. The raw material waste refers to the raw kitchen waste generated before and during cooking, and the post-meal waste refers to the remaining food after a meal. For each type of food waste, weigh it using standardized weighing equipment, record its weight and make statistics.

[0019] Optionally, the collected food waste data is preprocessed and classified into data encoding in sequence, wherein the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and numerical standardization, including: For the collected food waste data, convert all numerical data into a unified unit, convert all date and time data into a standard format, and convert all categorical data into a unified coding format; Perform data cleaning on the unified data, including removing duplicate records, correcting outliers, deleting data with negative weights, abnormally high values, and logical contradictions, and unifying the data formats of the same variable in different records; According to the preset classification criteria, the cleaned data is divided into different analogies; Process missing values ​​for classified data, directly delete data records with missing key variables, and mark missing values ​​of non-key variables as null values; The data with missing values ​​were numerically standardized by using Z-score standardization, Min-Max normalization or logarithmic transformation methods to convert data of different dimensions into comparable unified scales; Perform categorical data encoding on the standardized data, using one-hot encoding or label encoding methods to convert categorical variables into binary format or integer representation.

[0020] Optionally, the data after preprocessing and classification data coding is subjected to quantitative analysis of food waste using descriptive statistics and quantitative analysis methods to complete comprehensive monitoring of food waste, including: The average level of food waste of each category was calculated using descriptive statistical methods, including mean, median, standard deviation, and quartile; Based on the average level of food waste of various types, the fluctuation range of waste in different scenarios is evaluated from the degree of dispersion, and the skewness and peak characteristics of waste data are studied from the distribution characteristics to comprehensively reveal the laws and characteristics of food waste; Quantitative analysis methods were applied to conduct in-depth exploration of descriptive statistical results in order to identify key influencing factors, sensitive groups and evaluate the effectiveness of intervention measures. The quantitative analysis methods included multivariate linear regression analysis, heterogeneity analysis and double difference model analysis.

[0021] To achieve the above objectives, the second embodiment of the present application proposes a food waste full-process monitoring and analysis system based on multiple scenarios, including: A monitoring system construction unit, which is used to construct a multi-scenario monitoring system and adopt a stratified three-stage probability sampling design for each food waste scenario. The three-stage probability sampling design includes survey subject selection, survey area coverage and food classification; A data collection unit is used to collect food waste data for food waste scenarios such as catering canteens, takeaways, and families through a five-barrel classification method, a four-element separation method, and a three-step classification method based on the multi-scenario monitoring system; A preprocessing and coding unit, used to sequentially preprocess and classify the collected food waste data, wherein the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and numerical standardization; The analysis unit is used to conduct quantitative analysis of food waste using descriptive statistical methods and quantitative analysis methods for the data after preprocessing and classification data coding, so as to complete comprehensive monitoring of food waste.

[0022] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.

[0023] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, in which computer-readable storage medium is stored computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.

[0024] To achieve the above-mentioned purpose, the fifth aspect of the present application proposes a computer program product, which implements any method in the first aspect when executed by a processor.

[0025] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects: 1. Comprehensive monitoring scenarios: It can fully cover various scenarios such as restaurants, take-outs, and homes, provide more comprehensive food waste data, and provide a more accurate basis for formulating comprehensive measures to reduce food waste.

[0026] 2. Accurate and reliable data collection: Through standardized monitoring processes and operating specifications, as well as strict volunteer training and on-site monitoring procedures, the accuracy and comparability of data collection are ensured, and the reliability and availability of data are improved.

[0027] 3. In-depth analysis results: The use of advanced statistical analysis methods such as multivariate linear regression analysis, heterogeneity analysis and double difference model can deeply reveal the laws and influencing factors of food waste, and provide a scientific basis for formulating effective measures to reduce food waste.

[0028] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which: Figure 1 A schematic diagram of a process flow of a method for monitoring and analyzing the entire process of food waste based on multiple scenarios provided in an embodiment of the present application; Figure 2 A schematic diagram of monitoring solutions and data flows in different scenarios provided by the embodiments of the present application; Figure 3 A schematic diagram of the flow chart of the quantitative analysis method provided in the embodiment of the present application; Figure 4 A schematic diagram of the structure of a full-process monitoring and analysis device for food waste based on multiple scenarios provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] In order to solve the problems of existing food waste monitoring technology in terms of single monitoring scenario, lack of standardized process, insufficient data analysis and poor practicality, the embodiment of the present application provides a full-process monitoring and analysis method for food waste based on multiple scenarios, which can comprehensively cover various scenarios such as restaurants, take-outs, and families, establish standardized monitoring processes and operating specifications, and conduct accurate data collection and in-depth quantitative analysis of food waste, thereby providing a strong basis for formulating effective measures to reduce food waste, and has good practicality and scalability.

[0032] Figure 1A flowchart of a method for monitoring and analyzing the whole process of food waste based on multiple scenarios provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps: Step 101, build a multi-scenario monitoring system and adopt a stratified three-stage probability sampling design for each food waste scenario. The three-stage probability sampling design includes survey subject selection, survey area coverage and food classification.

[0033] In order to ensure the breadth and diversity of the samples and the universal applicability of the research results, the embodiment of the present application adopted a stratified three-stage probability sampling design, namely, survey subjects, sampling area coverage and food classification.

[0034] In the embodiments of the present application, Figure 2 As shown, the selection of research subjects comprehensively considered two key perspectives: catering operators and consumers.

[0035] In terms of catering operators, according to market share, it covers a variety of catering types such as Chinese formal meals, global cuisine, fast food, snacks and hot pot, which almost covers the entire picture of the Chinese catering market. In terms of consumers, the survey subjects are distributed in a wide range of groups with different age distributions, gender distributions, family sizes, geographical distributions, income stratifications and education levels. Taking into account the parameters of multiple aspects such as demographic characteristics (such as age distribution, gender distribution, family size, etc.), consumer behavior characteristics (such as dining scenes, food classification statistics, consumer decision-making factors, etc.), waste monitoring indicators (such as storage links, consumption links, processing links, etc.) and waste management systems (such as source reduction, classified collection, resource utilization, terminal disposal, etc.), the data collection form was designed in detail, as shown in Table 1.

[0036] Table 1

[0037] In addition, in the embodiments of this application, the research boundary mainly covers the whole process from procurement and transportation, storage and cooking, consumption and dining to garbage disposal. The monitoring of food waste is a comprehensive study using multiple methods in the sales, consumption and garbage disposal links. This application uses the most comprehensive research methods, including direct weighing method, garbage diary method, questionnaire / interview method, digital photography and recognition method, volume method and garbage composition analysis method, and conducts in-depth research in the whole process (procurement and transportation, storage and cooking, sales and consumption, garbage disposal) of various dining scenarios (catering, take-out, canteen, family) to obtain the most comprehensive and accurate data.

[0038] Specifically, catering operators mainly use three methods to conduct surveys: using the garbage diary method to record food waste in daily operations; filling out operational data through questionnaires / interviews; and using the volume method to assess food loss and garbage generation. Consumers participate in the survey mainly in four ways: using direct weighing to measure personal or family food consumption, storage waste, processing loss, and post-meal waste; using the garbage diary method to record daily diet and waste processes; participating in questionnaires and interviews to share their basic information, consumption habits, and reasons for waste; using digital photography and recognition to record and prove the accuracy of reported information.

[0039] Secondly, in the survey area coverage stage, the survey scope designed by this application is wide, and the coverage varies according to the personalized survey methods adopted by different survey objects, and the coverage is for administrative regions at all levels across the country through questionnaires / interviews and volumetric assessments from the perspectives of catering operators and consumers. In addition, in order to further enhance the representativeness of the sample and the accuracy of the data, the embodiments of this application specially selected a number of cities with typical characteristics for field surveys. These cities need to meet the requirements of not only being widely distributed geographically, but also having their own characteristics in terms of economic development level, population size and cultural background, so that the research can fully capture the regional differences in food waste in China. In terms of small business surveys, different types of restaurants are covered, including Chinese meals, global cuisine, fast food, snacks and hot pot. Each city uses a quota sampling method to allocate sample size according to its level of economic development and population size.

[0040] In a possible embodiment, for Chinese meals and hot pot restaurants, sampling is conducted once at lunch and once at dinner, ensuring a sample size of 50 people each time; for fast food and small businesses, sampling is conducted 30 minutes before the meal or after the peak dining time, also ensuring a sample size of 50 people, to ensure the scientificity and reliability of the data.

[0041] Finally, the standardization of food classification is another important aspect of the study of the embodiments of this application. This application adopts a standardized food classification method to divide food into multiple basic categories and twelve subcategories to ensure comprehensive monitoring of food waste, including not only basic categories such as staple food, meat, fruits and vegetables, but also twelve subcategories such as pork, eggs, and beans. In addition, the embodiments of this application also pay special attention to the waste of food during storage, processing, and consumption, and create a personalized food waste monitoring standardization classification basis based on the portability of classification in different scenarios.

[0042] Step 102, based on the multi-scenario monitoring system, collect food waste data for food waste scenarios in catering canteens, take-outs, and households through the five-bucket classification method, the four-element separation method, and the three-step classification method.

[0043] (1) In the restaurant and canteen scenarios, the embodiment of this application adopts the five-barrel classification method. According to its operating characteristics and turnover rate, the catering stores take samples during the lunch and dinner peak hours to ensure that the sample size reaches 50 people to improve the representativeness of the data. The canteens establish cooperative relationships with local garbage classification authorities, urban management committees and other government departments to share data and resources. Government departments can provide data such as canteen terminal food waste, local food waste collection and disposal methods.

[0044] Specifically, the embodiment of the present application accurately divides the leftover food after a meal into five categories and puts them into corresponding trash cans: (1) Meat trash can: collects all animal food, including livestock and poultry meat, offal, aquatic products, eggs and milk, etc.; (2) Vegetable trash can: collects plant food, including vegetables, beans, bean products, tubers, etc.; (3) Staple food trash can: specially collects staple food such as rice, noodles, cakes, dumplings, etc.; (4) Inedible trash can: collects inedible parts such as peels, cores, bones, shells, etc.; (5) Soup trash can: used to collect liquid waste such as soup, tea, and beverages. For mixed food, such as rice bowls, they are classified according to the main ingredients.

[0045] In the actual application stage, during the post-meal cleanup phase in restaurants and canteens, staff or volunteers can put food scraps into corresponding trash cans according to classification standards and weigh them using standardized weighing equipment. The judgment rule is to classify food according to its nature and edibility, such as: meat barrels are used to collect all animal foods, such as livestock and poultry meat, offal, aquatic products, eggs and milk, etc.; vegetable barrels are used to collect plant foods, including vegetables, beans, bean products, tubers, etc.; staple food barrels are specially used to collect staple foods such as rice, noodles, cakes, dumplings, etc.; inedible barrels collect inedible parts such as peels, bones, shells, etc.; soup barrels are specially used to collect liquid waste such as vegetable soup, tea, and beverages.

[0046] (2) In the takeaway scenario, the embodiment of the present application adopts a four-element separation method to divide the post-meal food residue into four categories: staple food separation barrel, dish separation barrel, soup separation barrel and packaging separation bag: (1) Staple food separation barrel: specially collects the staple food part of takeaway, such as rice, noodles, etc. (2) Dish separation barrel: used to collect the remaining parts of various dishes, including non-vegetarian dishes with more meat, non-vegetarian dishes with more vegetables, etc. (3) Soup separation barrel: specially collects liquid waste such as soups and beverages. (4) Packaging separation bag: used to collect takeaway packaging, such as lunch boxes, plastic bags and other materials.

[0047] In the actual application stage, the present application weighs the food before the meal, and can choose to weigh it separately or as a whole according to the takeaway packaging, and record the weight of the staple food and the total weight of the dishes separately. During post-meal processing, the soup in the remaining food needs to be drained to ensure that there is no obvious liquid flow, and then the staple food and dishes are weighed separately, and the inedible parts are weighed separately. Considering the impact of takeaway packaging on the weight of food, the weight of the packaging is also weighed and recorded separately in the embodiment of the present application to ensure the accuracy of the data. Based on the quaternary separation method, the recommended parameters for the types of ingredients that are also monitored in detail include rice and its products, wheat and pasta made from it, cereals and their products, vegetables and fruits, potatoes, roots and tubers, pork, beef and mutton, poultry, fish meat, eggs, milk, etc.

[0048] (3) Similarly, in a family dining scenario, the embodiment of the present application adopts a three-step classification method to divide food waste in the family into raw material waste, post-meal waste and inedible parts, and uses different trash cans for classification: (1) Raw material classification bin, also known as raw kitchen waste, collects raw kitchen waste generated before and during cooking, such as vegetable peels, fruit cores, etc.; (2) Waste classification bin: used to collect leftover food after meals, that is, post-meal waste; (3) Inedible classification bin: specially collects inedible parts such as bones, shells, and fruit cores.

[0049] It is understandable that the source consumption classification standard divides kitchen waste into three categories: raw material waste, post-meal waste, and inedible waste. Raw material waste includes waste generated by operations such as picking vegetables and peeling, post-meal waste is the weighing of remaining food after meals, and the inedible category collects all inedible parts. Similarly, based on the source consumption classification standard, the recommended parameters for the types of ingredients monitored in detail after family meals are consistent with the takeaway scenario. The difference is that the parameters for the pre-meal cooking stage have been increased on this basis, including the use of sugars, salt, oils, fungus and other dry goods, and the waste generated in the storage stage is recorded in detail.

[0050] It should be noted that for different scenarios, standardized weighing equipment is ultimately required to weigh, record the weight and make statistics.

[0051] In addition, to ensure the standardization and accuracy of data collection, the embodiment of the present application has also established a strict data collection control system, which mainly consists of four steps: recruitment management, training assessment, data supervision, and multiple verification.

[0052] First, with the help of the Internet's natural dissemination mechanism and organized distribution channels, volunteers are recruited nationwide to participate in data collection. By setting up a reward mechanism, such as giving corresponding rewards based on the number of scenarios in which volunteers participate, the accuracy and completeness of data collection, etc., the enthusiasm and initiative of volunteers can be fully mobilized. This prevents passive and perfunctory reporting of data. By analyzing the gender, age, family structure, income level and food-saving habits of volunteers in multiple dimensions, we evaluate whether the sample size is sufficient and whether the degree of sample distribution dispersion is reasonable. Then, we manage the samples in a targeted manner until they show a trend of approximately normal distribution.

[0053] At the same time, systematic online training and education are provided for volunteers, catering companies and canteen data reporting managers, including the definitions of various types of garbage and related operating procedures of the embodiments of this application to ensure that volunteers can accurately classify food waste; at the same time, easy-to-understand weighing videos and standardized operating guidance materials are provided to help volunteers / volunteer merchants better master the weighing process and precautions. During the training process, it is important to emphasize minimizing interference with the lives of the interviewees and ensuring that the interviewees can weigh the data without disrupting their daily lifestyle. In addition, the purpose, significance, steps and methods of the survey are clarified, and the interviewees also need to fully understand the background and objectives of the survey, the assessment mechanism and rewards after the project is completed.

[0054] In terms of incentive mechanism, the embodiment of the present application combines the structure of the acquired data and specifically designs a scientific working time calculation method to flexibly adjust the survey data structure.

[0055] In a possible embodiment, in a family scenario, a single weight measurement of raw or cooked inedible food is recorded as 0.5 hours, and a group meal with multiple people is recorded as 0.75 hours; in a takeaway scenario, a single weight measurement of food before and after a meal is recorded as 0.5 hours, a small portion of takeaway food is recorded as 1 hour, and a group meal with multiple people is recorded as 0.5 hours; in a restaurant scenario, a single weight measurement of food after a meal is recorded as 1 hour, the measurement of leftover food after meals of large and small portions is recorded as 1 hour, and a group meal with multiple people is recorded as 1.5 hours.

[0056] In addition, it is necessary to regularly organize volunteer experience exchange meetings to continuously improve and perfect the operating procedures. At the same time, establish cooperative relationships with local garbage classification authorities, urban management committees and other government departments, as well as catering companies and food delivery platforms, share interim research results and best practices, and cooperate with companies to carry out pilot projects to verify and optimize supervision and reduction measures.

[0057] Secondly, in the specific implementation process of data collection, this application also establishes strict on-site monitoring operation specifications. When volunteers are monitoring on site, they must strictly follow the standardized operation process, including calibrating the weighing equipment, operating in accordance with the prescribed garbage classification and collection specifications, and recording data immediately after each weighing operation. At the same time, for each weighing operation, volunteers are required to take real-time photos and records, and the shooting angle must be able to clearly display the weighing value and the measured object, providing strong support for the authenticity of the data and subsequent verification. In addition, the embodiment of the present application also establishes a two-person on-site review mechanism, which further ensures the accuracy of the data by one person operating and one person reviewing. For abnormal data found during the monitoring process, such as the value displayed by the weighing equipment is obviously abnormal or the measured object is obviously inconsistent with the weighing result, the volunteers must immediately mark it as abnormal data and record its relevant information in detail, including the specific value of the abnormal data, the time, place, scene, and food type involved. Subsequently, through telephone return visits or online communication, the situation is verified with relevant personnel, and possible reasons are recorded for identification and processing in subsequent data processing. If the abnormal data cannot be reasonably explained, it will be marked as invalid data and excluded from the analysis.

[0058] Finally, the embodiment of the present application also uses a multi-dimensional cross-validation mechanism to further ensure data quality. This includes verifying the rationality of the number of diners, judging the credibility of the data based on behavioral economic factors such as restaurant size, dining time, and consumption amount; conducting a range review of weight data, setting reasonable upper and lower limits, and focusing on checking data that exceeds the range; requiring image proof of the CD situation to ensure the authenticity of the data, etc. This application does not make specific restrictions on this. And through the cross-validation mechanism, the data at different times and in different scenarios are compared and analyzed to identify possible outliers, thereby improving the accuracy and reliability of the data.

[0059] Step 103, preprocessing and classification data coding are performed on the collected food waste data in sequence, and the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and numerical standardization.

[0060] In order to ensure the systematic and scientific nature of data processing, this application also designs a detailed data processing method framework, which covers multiple links such as data preprocessing, missing value processing, numerical standardization, categorical data coding, and data analysis.

[0061] Data preprocessing is the first step in data processing, which aims to convert raw data into a format suitable for analysis. The specific steps include: First, for the collected food waste data, all numerical data (such as weight, quantity, amount) are converted into unified units (such as grams, kilograms, yuan, ten thousand yuan, etc.), all date and time data are converted into a standard format (such as YYYY-MM-DD HH:MM:SS), and all categorical data (such as gender, age group, restaurant type) are converted into a unified coding format.

[0062] Then, data cleaning is performed on the data with unified format, including removing duplicate records, correcting outliers, deleting data with negative weights, abnormally high values, and logical contradictions, and unifying the data format of the same variable in different records.

[0063] Next, according to the preset classification criteria, the data is divided into different categories, such as restaurants, take-outs, canteens, families and other scenarios, as well as food categories such as meat, vegetables, and staple foods.

[0064] Next, the classified data is processed for missing values, which aims to ensure the integrity of the data and the convenience of processing. For records containing missing values, especially those with missing key variables (such as weight, number of meals, dining scenes, etc.), the entire data is deleted directly to avoid misleading the analysis results. For missing values ​​of non-key variables, the records can be retained, but marked as "null" values ​​during analysis so that special processing can be performed in subsequent analysis.

[0065] Finally, the data with missing values ​​processed are numerically standardized, and data from different sources and dimensions are converted into a unified scale for comparison and analysis.

[0066] In the embodiments of the present application, Z-score standardization, Min-Max normalization or logarithmic transformation method can be used to convert data of different dimensions into a comparable unified scale, as follows: Z-score standardization: Convert the data to a standard normal distribution, the formula is:

[0067] in, is the original data, is the mean, is the standard deviation. This method is applicable when the data is normally distributed, and it can eliminate the influence of dimension, making the data have zero mean and unit variance.

[0068] Min-Max normalization: linearly map the data to the [0,1] interval. The formula is:

[0069] in, and are the minimum and maximum values ​​of the data respectively. This method is suitable for situations where the data range is wide, and can compress the data range so that all data are within the same dimensional range.

[0070] Logarithmic transformation: Process the right-skewed distribution data. The formula is:

[0071] in, It can be the natural logarithm ( ) or the common logarithm ( ), plus 1 is to deal with the 0 value in the data, because the logarithmic function is undefined at 0. Logarithmic transformation can reduce the skewness of the data and make the data closer to normal distribution, especially when dealing with data with great differences, it can make the data distribution more uniform.

[0072] These standardization methods can effectively eliminate the differences between different data sources and dimensions, allowing various types of data to be compared and analyzed on the same scale, ensuring data consistency and scientificity in subsequent processing and modeling.

[0073] After preprocessing the data, the embodiment of the present application performs categorical data encoding on the standardized data. Categorical data encoding is to convert categorical variables into numerical form for statistical analysis.

[0074] In one embodiment of the present application, one-hot encoding can be used to convert categorical variables into binary format, with each category corresponding to a binary column; or label encoding can be used to convert categorical variables into integer form, with each category corresponding to an integer.

[0075] Step 104, for the data after preprocessing and classification data coding, use descriptive statistical methods and quantitative analysis methods to conduct quantitative analysis of food waste, and complete comprehensive monitoring of food waste.

[0076] In the present embodiment, the average level of food waste of each category is first calculated by descriptive statistical methods. Descriptive statistical methods include: Mean: Calculate the arithmetic mean of all data points to reflect the overall level of food waste; Median: Calculates the middle value of the data, providing another measure of the central trend of food waste data, especially useful when there are extreme values; Standard deviation: measures the degree of deviation of data points from the mean and describes the degree of dispersion of food waste; Quartiles: Provides details of data distribution by dividing the dataset into four parts, helping to understand the distribution characteristics of food waste data.

[0077] This application further evaluates the fluctuation range of waste in different scenarios from the degree of discreteness based on the average level of various types of food waste, and quantifies the volatility of waste in different scenarios (such as catering, takeout, and family), by calculating the standard deviation and interquartile range, thereby revealing the changing patterns of food waste in different environments.

[0078] And from the distribution characteristics, the skewness and kurtosis characteristics of waste data are studied. Skewness describes the symmetry of data distribution, and kurtosis describes the sharpness of data distribution. By analyzing these characteristics, it can be revealed whether food waste data has a long-tail distribution, extreme waste trends, and waste concentration, and comprehensively reveal the laws and characteristics of food waste.

[0079] In addition, the quantitative analysis method is also applied in the embodiments of the present application to conduct in-depth mining of the descriptive statistical results to identify key influencing factors, identify sensitive groups and evaluate the effects of intervention measures. The quantitative analysis method includes the following parts: Multiple linear regression analysis: By building a regression model, we analyze the impact of multiple independent variables on food waste, identify the key factors that affect waste behavior, and reveal the differences between different scenarios and groups; Heterogeneity analysis: By analyzing the differences in food waste among different groups or scenarios, we can identify the behavioral characteristics of different groups and help accurately identify sensitive groups for targeted interventions. Double difference model analysis: By setting up intervention groups and control groups, the effects of different intervention measures are evaluated, and the changes before and after the intervention are compared to quantify the impact of different measures.

[0080] The specific flow chart is as follows Figure 3 As shown in the figure, the specific steps and logical relationships of the above quantitative analysis methods are demonstrated, including the operational procedures of multiple linear regression analysis, heterogeneity analysis and double difference model analysis.

[0081] In general, through the above-mentioned systematic data processing method framework, this application can ensure the scientificity and systematicness of data processing, thereby comprehensively understanding the food waste situation in different scenarios, helping to identify the main waste patterns and influencing factors, and providing a scientific basis for formulating effective waste reduction strategies.

[0082] In order to implement the above embodiments, the present application also proposes a full-process food waste monitoring and analysis system based on multiple scenarios. Figure 4 This is a schematic diagram of the structure of a food waste full-process monitoring and analysis system based on multiple scenarios provided in an embodiment of the present application. Figure 4 As shown, the system includes: A monitoring system construction unit 100 is used to construct a multi-scenario monitoring system, and a stratified three-stage probability sampling design is used for each food waste scenario. The three-stage probability sampling design includes survey object selection, survey area coverage, and food classification; The data collection unit 200 is used to collect food waste data for food waste scenarios such as catering canteens, takeaways, and families through the five-barrel classification method, the four-element separation method, and the three-step classification method based on the multi-scenario monitoring system; A preprocessing and encoding unit 300 is used to preprocess and classify the collected food waste data in sequence, wherein the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and value standardization; The analysis unit 400 is used to conduct quantitative analysis of food waste using descriptive statistical methods and quantitative analysis methods for the data after preprocessing and classification data encoding, so as to complete comprehensive monitoring of food waste.

[0083] Regarding the system in the above embodiment, the specific manner in which each unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0084] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0085] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0086] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0087] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0088] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0089] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0090] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they contradict each other.

[0091] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0092] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0093] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0094] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0095] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0096] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0097] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

[0098] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0099] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-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 this application should be included in the protection scope of this application.

Claims

1. A food waste full-process monitoring and analysis method based on multiple scenarios, characterized in that: The following steps are involved: Construct a multi-scenario monitoring system and adopt a stratified three-stage probability sampling design for each food waste scenario, which includes survey subject selection, survey area coverage and food classification; Based on the multi-scenario monitoring system, food waste data is collected for food waste scenarios in catering canteens, takeaways, and households through the five-barrel classification method, the four-element separation method, and the three-step classification method; The collected food waste data is preprocessed and classified into data encoding, wherein the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and numerical standardization; Based on the data after preprocessing and classification data coding, descriptive statistical methods and quantitative analysis methods are used to conduct quantitative analysis of food waste and complete comprehensive monitoring of food waste.

2. The method according to claim 1, characterized in that The multi-scenario monitoring system is constructed, and a stratified three-stage probability sampling design is adopted for each food waste scenario, including: In the research object selection stage, catering operators were selected based on market share, including Chinese formal meals, global cuisine, fast food, hot pot, and snacks. Consumers were selected based on demographic characteristics, consumption behavior characteristics, waste monitoring indicators, and waste management systems. The research boundary covered the entire process from procurement and transportation, storage and cooking, consumption and dining to garbage disposal. In-depth research was conducted in the entire process of various dining scenarios through a variety of research methods, including at least one of direct weighing method, garbage diary method, questionnaire / interview method, digital photography and recognition method, volume method, and garbage composition analysis method. During the regional coverage phase of the survey, several cities with typical characteristics were selected for field research, and the sample size was allocated using a quota sampling method based on their economic development levels and population sizes. The selected cities are geographically distributed widely, and each has its own characteristics in terms of economic development level, population size, and cultural background, ensuring that the research results can fully reflect the regional differences in food waste in China; During the food classification stage, a standardized food classification method is adopted to divide food into multiple basic categories and twelve subcategories to ensure comprehensive monitoring of food waste, and pay attention to the waste of food during storage, processing and consumption. According to the degree of classification portability in different scenarios, a personalized food waste monitoring standardized classification basis is created; the basic categories include staple foods, meat, and fruits and vegetables, and the subcategories include pork, eggs, and beans.

3. The method according to claim 2, characterized in that Also includes: In the survey of catering operators, the garbage diary method was used to record food waste in daily operations, questionnaires and interviews were used to obtain operational data, and the volume method was used to assess food loss and garbage generation; In terms of consumer surveys, direct weighing methods are used to measure individual or family food consumption, storage waste, processing loss and post-meal waste. The garbage diary method is used to record daily diet and waste processes. Questionnaires and interviews are used to collect basic consumer information, consumption habits and waste reasons. Digital photography and recognition methods are used to record and verify the accuracy of the reported information.

4. The method according to claim 3, characterized in that The five-bucket classification method is used to collect food waste data for food waste scenarios in catering canteens, including: Sort the leftover food after meals into five categories: staple food, vegetables, meat, inedible parts and soup, and put them into the corresponding trash cans; During the post-meal cleanup phase in restaurants and cafeterias, each type of food waste is weighed using standardized weighing equipment, and its weight is recorded and counted.

5. The method according to claim 4, characterized in that The food waste data of takeout food waste scenarios are collected through the four-element separation method, including: Weigh the food before takeaway meals, and choose to weigh it separately or as a whole according to the takeaway packaging, and record the weight of the staple food and the total weight of the dishes separately; Classify the leftover food after takeout meals into staple food, dishes, soup and packaging, and put them into the corresponding trash cans respectively; when processing after the meal, drain the soup from the leftover food to ensure that there is no obvious liquid flow; For each type of food waste, weigh it using standardized weighing equipment, record its weight and make statistics.

6. The method according to claim 5, characterized in that Food waste data is collected based on the food waste scenarios of each household through a three-step classification method, including: Food waste in the household is divided into raw material waste, post-meal waste and inedible parts, and they are classified in different trash cans. The raw material waste refers to the raw kitchen waste generated before and during cooking, and the post-meal waste refers to the remaining food after a meal. For each type of food waste, weigh it using standardized weighing equipment, record its weight and make statistics.

7. The method according to claim 6, characterized in that The collected food waste data is preprocessed and classified into data encoding in sequence, wherein the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and numerical standardization, including: For the collected food waste data, convert all numerical data into a unified unit, convert all date and time data into a standard format, and convert all categorical data into a unified coding format; Perform data cleaning on the unified data, including removing duplicate records, correcting outliers, deleting data with negative weights, abnormally high values, and logical contradictions, and unifying the data formats of the same variable in different records; According to the preset classification criteria, the cleaned data is divided into different analogies; Process missing values ​​for classified data, directly delete data records with missing key variables, and mark missing values ​​of non-key variables as null values; The data with missing values ​​were numerically standardized by using Z-score standardization, Min-Max normalization or logarithmic transformation methods to convert data of different dimensions into comparable unified scales; Perform categorical data encoding on the standardized data, using one-hot encoding or label encoding methods to convert categorical variables into binary format or integer representation.

8. The method according to claim 7, characterized in that The data after preprocessing and classification data coding are used to conduct quantitative analysis of food waste using descriptive statistical methods and quantitative analysis methods to complete comprehensive monitoring of food waste, including: The average level of food waste of each category was calculated using descriptive statistical methods, including mean, median, standard deviation, and quartile; Based on the average level of food waste, the fluctuation range of waste in different scenarios is evaluated from the degree of dispersion, and the skewness and peak characteristics of waste data are studied from the distribution characteristics to comprehensively reveal the laws and characteristics of food waste. Quantitative analysis methods were applied to conduct in-depth exploration of descriptive statistical results in order to identify key influencing factors, sensitive groups and evaluate the effectiveness of intervention measures. The quantitative analysis methods included multivariate linear regression analysis, heterogeneity analysis and double difference model analysis.

9. A food waste full-process monitoring and analysis system based on multiple scenarios, characterized in that: include: A monitoring system construction unit, which is used to construct a multi-scenario monitoring system and adopt a stratified three-stage probability sampling design for each food waste scenario. The three-stage probability sampling design includes survey subject selection, survey area coverage and food classification; A data collection unit is used to collect food waste data for food waste scenarios such as catering canteens, takeaways, and families through a five-barrel classification method, a four-element separation method, and a three-step classification method based on the multi-scenario monitoring system; A preprocessing and coding unit, used to sequentially preprocess and classify the collected food waste data, wherein the preprocessing steps include data format unification, data cleaning, data classification, missing value processing and numerical standardization; The analysis unit is used to conduct quantitative analysis of food waste using descriptive statistical methods and quantitative analysis methods for the data after preprocessing and classification data coding, so as to complete comprehensive monitoring of food waste.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

Images