Food safety service quality evaluation system

Abstract

The invention belongs to the technical field of food safety, and provides a food safety service quality evaluation system, comprising a data acquisition module which uses the Internet of Things technology to deploy a plurality of sensors to monitor each parameter of food in real time; the data storage module uses cloud computing service to store and manage the collected data; the data processing module preprocesses the collected data, analyzes the data, identifies a food safety risk mode and trend, analyzes consumer feedback by applying a natural language technology, and extracts emotions and opinions; the interaction module inputs feedback and scores of food safety by consumers and supervisors through mobile equipment and an online platform, and displays real-time data and historical trends; the alarm module automatically generates a food safety report, and immediately sends an alarm to a manager and a supervision mechanism when potential food safety problems and consumer feedback are detected; by improving the supervision efficiency and promoting information transparency, the food safety awareness of the public is enhanced.

Description

Technical Field

[0001] The invention belongs to the technical field of food safety, in particular to a food safety service quality evaluation system. Background Art

[0002] In today's society, food safety issues are increasingly attracting public attention. With the intensification of globalization and the complexity of supply chains, food safety incidents have occurred frequently, posing a serious threat to consumers' health, which in turn has caused social unrest and a crisis of trust in the food industry. In order to ensure the safety, traceability and quality stability of food, countries have strengthened food safety regulations and standards, and promoted the supervision of the entire chain of food production, processing, and circulation;

[0003] However, the existing food safety supervision system is often relatively simple and it is difficult to fully reflect the actual quality of food safety services. Traditional evaluation methods mostly rely on sampling inspection and post-event traceability, and lack real-time monitoring and evaluation of service processes and service quality. This makes it difficult to take effective preventive and response measures in a timely manner when facing potential food safety risks. At the same time, consumers' awareness and expectations of food safety are also constantly improving, and they hope to obtain more transparent and credible food safety information.

[0004] In the existing Chinese patent with publication number CN111626749A, the patent name is a food quality and safety traceability and safety level evaluation system, which aims to solve the problems existing in the existing food traceability system. The product includes a cloud server, a fresh food traceability module, an agricultural product traceability and safety level evaluation module, a current situation analysis module and a measure improvement module. The fresh food traceability module includes a fresh food traceability code generation module, a fresh food planting module, a fresh food detection module, a fresh food transportation management module, a fresh food sales module and a fresh food query module. The system records the information of growers, product types, product environment, etc. of fresh food and agricultural products at the beginning of planting and transmits the information to the cloud server. The cloud server records and evaluates the safety of the product, which is convenient for people to query and food consumption is safer. At the same time, the safety measures of the product are analyzed and improved to further ensure food safety. However, the system does not interact with consumers in real time during the food production process. Consumers can only query and trace the source, and cannot participate in the actual food production process. Consumers cannot express their emotional feedback and scores in real time, and lack the public's sense of participation in the food safety supervision process.

[0005] To this end, those skilled in the art have proposed a food safety service quality evaluation system. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a food safety service quality evaluation system, which collects feedback and scores from consumers and regulators in real time through mobile devices and online platforms, and combines objective data such as temperature parameter records, etc., uses natural language processing technology to perform sentiment analysis, extracts consumer opinions, and uses a weighted comprehensive scoring algorithm to derive a comprehensive score for food safety service quality to solve the problems raised in the background technology.

[0007] A food safety service quality evaluation system, comprising:

[0008] The data acquisition module uses IoT technology to deploy sensors in food production lines, warehousing, logistics and sales points to monitor food temperature, humidity and location parameters in real time;

[0009] Data storage module, which uses cloud computing services to store and manage collected data;

[0010] The data processing module cleans and preprocesses the collected data and uses machine learning algorithms to analyze the data, identify food safety risk patterns and trends, and apply natural language technology to analyze consumer feedback and extract sentiment and opinions;

[0011] An interactive module that allows consumers and regulators to input food safety feedback and ratings through mobile devices and online platforms, and displays real-time data and historical trends;

[0012] The alarm module automatically generates food safety reports and immediately sends alerts to managers and regulators when potential food safety issues and consumer feedback are detected.

[0013] Preferably, the sensors include temperature and humidity sensors, pressure and flow sensors, and grating and photoelectric sensors.

[0014] Preferably, the data processing module first preprocesses the collected data, including cleaning, normalization and missing value processing steps, and then performs feature selection from factors affecting food safety, including but not limited to temperature, humidity, pressure and appearance, expressed as: F = {f1, f2, ..., f n}, where F is the selected feature set, f i Represents the i-th feature; then use the linear regression model for training, expressed as: y = β0 + β1x1 + β2x2 + ... + β n x n , where y represents the target variable, x i Represents the characteristics, β i Represents the coefficient; then, by inputting new food safety data, rapid prediction and risk assessment are performed, and the prediction process is expressed as: pred =hθ (x), where y pred represents the predicted value, h θ (x) represents the hypothesis function obtained through training, and x is the new input data.

[0015] Preferably, the consumer feedback is analyzed by natural language technology to extract sentiment and opinions, which uses the TF-IDF method to represent the text as a collection of word frequencies and analyze the rarity of the words in the entire corpus, expressed as:

[0016]

[0017] Among them, TF(t,d) represents the frequency of occurrence of term t in document d, DF(t) represents the number of documents containing t, and N is the total number of documents;

[0018] Then, the classifier is trained by the labeled sentiment data set, and the support vector machine is used for sentiment classification. The process is expressed as:

[0019]

[0020] Among them, x i represents the support vector, α i represents the Lagrange multiplier, y i represents the label, K represents the kernel function, and b represents the bias term;

[0021] Then, a web application is built through F l ask. After the user enters text, the system outputs the sentiment analysis results.

[0022] Preferably, by combining parameter data and consumer feedback, a weight and scoring mechanism is introduced, and weighted calculation is performed according to the importance of different factors to obtain a comprehensive score of food safety service quality, which is expressed as:

[0023]

[0024] Where S represents the comprehensive score of food safety service quality, n represents the total number of evaluation indicators, and w i represents the weight of the i-th evaluation index, s i Represents the score of the i-th evaluation indicator.

[0025] Preferably, the interactive module allows consumers and regulators to input their feedback and ratings through a mobile application or an online platform, and the data submitted by the users is transmitted to the data processing module through the network, and then the data is stored in the data storage module. The analysis results are presented in the form of charts through data visualization tools, showing real-time data and historical trends, and the network transmission is encrypted using the HTTPS protocol.

[0026] Preferably, an API interface is also provided to enable a third-party system to interact with the system.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention collects feedback and scores from consumers and regulators in real time. Its timeliness not only speeds up the speed of information transmission, but also enables regulatory authorities to respond quickly to potential food safety issues, thereby improving overall regulatory efficiency.

[0029] 2. The present invention establishes an information platform for sharing and business collaboration, so that the data sharing mechanism not only reduces the phenomenon of information islands, but also increases the transparency of regulatory information, allowing the public to have a more comprehensive understanding of food safety conditions, while allowing consumers to directly input their feedback and ratings through mobile devices and online platforms. This interactive method enhances the public's sense of participation in the food safety regulatory process, while allowing regulatory authorities to hear the voice of the market more directly, further improving the transparency and fairness of information. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a block diagram of the food safety service quality evaluation system of the present invention. DETAILED DESCRIPTION

[0031] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0032] As attached Figure 1 As shown:

[0033] Embodiment 1: The present invention provides a food safety service quality evaluation system, comprising:

[0034] The data acquisition module uses IoT technology to deploy sensors in food production lines, warehousing, logistics and sales points to monitor food temperature, humidity and location parameters in real time;

[0035] Data storage module, which uses cloud computing services to store and manage collected data;

[0036] The data processing module cleans and preprocesses the collected data and uses machine learning algorithms to analyze the data, identify food safety risk patterns and trends, and apply natural language technology to analyze consumer feedback and extract sentiment and opinions;

[0037] An interactive module that allows consumers and regulators to input food safety feedback and ratings through mobile devices and online platforms, and displays real-time data and historical trends;

[0038] The alarm module automatically generates food safety reports and immediately sends alerts to managers and regulators when potential food safety issues and consumer feedback are detected.

[0039] By collecting feedback and ratings from consumers and regulators in real time, the timeliness not only speeds up the transmission of information, but also enables regulators to respond quickly to potential food safety issues, thereby improving overall regulatory efficiency.

[0040] Sensors include temperature and humidity sensors, pressure and flow sensors, as well as grating and photoelectric sensors. By deploying various sensors in various links of food production lines, warehousing, logistics and sales points, food safety and quality can be fully monitored.

[0041] The data processing module first preprocesses the collected data, including cleaning, normalization and missing value processing steps. The purpose of data preprocessing is to improve data quality and ensure the accuracy and reliability of subsequent analysis, which is expressed as: X clean =Clean(X raw ), where X clean represents the cleaned data, X raw represents the original data, and Clean() represents the data cleaning process; then feature selection is performed from factors that affect food safety, including but not limited to temperature, humidity, pressure, and appearance, expressed as: F = {f1, f2, ..., f n}, where F is the selected feature set, f i Represents the i-th feature; then use the linear regression model for training, expressed as: y = β0 + β1x1 + β2x2 + ... + β n x n , where y represents the target variable, x i Represents the characteristics, β i Represents the coefficient; then, by inputting new food safety data, rapid prediction and risk assessment are performed, and the prediction process is expressed as: pred =h θ (x), where y pred represents the predicted value, h θ (x) represents the hypothesis function obtained through training, and x is the new input data. The above steps can not only quickly identify food safety risks, but also provide decision support to ensure public food safety.

[0042] Analyze consumer feedback through natural language technology to extract emotions and opinions, including data preprocessing, feature extraction, model training and sentiment prediction steps. Data preprocessing includes word segmentation, stop word removal, and stem extraction operations. The original text is simplified and standardized through the above steps. The NLTK library can be used for word segmentation and stop word filtering. Feature extraction is to convert the preprocessed text into a format that can be understood and processed by the machine learning model. It uses the TF-IDF method to represent the text as a collection of word occurrence frequencies and analyze the rarity of the words in the entire corpus, which is expressed as:

[0043]

[0044] Among them, TF(t,d) represents the frequency of occurrence of term t in document d, DF(t) represents the number of documents containing t, and N is the total number of documents;

[0045] Then, the classifier is trained with the labeled sentiment data set to enable it to identify the sentiment tendency of new texts, and the support vector machine is used for sentiment classification. The process is expressed as:

[0046]

[0047] Among them, x i represents the support vector, α i represents the Lagrange multiplier, y i represents the label, K represents the kernel function, and b represents the bias term;

[0048] Then, a Web application is built through F l ask. After the user enters the text, the system outputs the sentiment analysis results. The trained model is applied to the actual system to provide users with real-time sentiment analysis services, thereby effectively extracting the emotions and opinions of the text and providing a scientific basis for the evaluation of food safety service quality.

[0049] By combining parameter data and consumer feedback, introducing a weight and scoring mechanism, and performing weighted calculations based on the importance of different factors, we can obtain a comprehensive score for food safety service quality, expressed as:

[0050]

[0051] Where S represents the comprehensive score of food safety service quality, n represents the total number of evaluation indicators, and w i represents the weight of the i-th evaluation index, s iRepresents the score of the i-th evaluation indicator. By considering multiple factors that affect the quality of food safety services and assigning different weights according to their importance, a comprehensive score is calculated. Each dimension can be scored according to the actual situation, and then weights are assigned according to their importance. Finally, the sum of these scores multiplied by their respective weights is the comprehensive score of food safety service quality, which can fully reflect the quality of food safety services.

[0052] The system adopts a three-tier architecture, including a front-end user interface, a back-end server, and a database. The front-end user interface provides a friendly interactive entrance for consumers and regulators, the back-end server processes business logic, and the database stores all collected data; the interactive module allows consumers and regulators to input their feedback and scores through mobile applications or online platforms, including filling out forms, selecting drop-down menu options, or scoring on a slider, etc. The data submitted by users is transmitted to the data processing module through the network. After receiving the data, the data processing module verifies and cleans it, and then stores the data in the data storage module. The data usually includes scores, comment text, timestamps, and user information, etc.; the system analyzes the data in the database regularly or as needed, and displays the analysis results in the form of charts through data visualization tools, showing real-time data and historical trends, including the distribution of food safety issues and trends over time; and uses the HTTPS protocol to encrypt network transmission, implement strict access control on the server side, ensure the privacy and security of user data, and the system can set up an automatic notification mechanism so that relevant personnel can receive timely notifications when food safety issues are reported; the system can effectively collect and process feedback from consumers and regulators, while displaying real-time data and historical trends, thereby helping to improve food safety levels.

[0053] Through the established information platform for sharing and business collaboration, the data sharing mechanism not only reduces the phenomenon of information islands, but also increases the transparency of regulatory information, enabling the public to have a more comprehensive understanding of food safety conditions, while allowing consumers to directly input their feedback and ratings through mobile devices and online platforms. This interactive method enhances the public's sense of participation in the food safety regulatory process, while allowing regulatory authorities to hear the voice of the market more directly, further improving the transparency and fairness of information.

[0054] Embodiment 2: This embodiment is basically the same as the previous embodiment, except that an API interface is also provided to enable a third-party system to interact with the system and to integrate with the existing enterprise resource planning system and supply chain management system.

[0055] Embodiment 3: This embodiment is basically the same as the previous embodiment, except that sentiment data annotation is to pre-process the collected text data, including removing irrelevant characters, stop word processing, stem extraction, etc., to reduce noise and highlight sentiment words. The text data collected for sentiment analysis comes from social media, product reviews, news articles, etc., and sentiment is divided into three types: positive, negative and neutral, and is manually annotated or automatically annotated through an existing sentiment dictionary.

[0056] The sentiment classifier is trained by selecting the BERT model based on Transformer. The core of Transformer is the self-attention mechanism, which is expressed as: Where Q, K, and V represent query, key, and value matrices, respectively, and d k Represents the scaling factor, and uses the attention mechanism to capture the global dependencies of the input data. Based on the Transformer architecture, BERT also introduces two pre-training tasks, namely Masked Language Model (MLM) and Next Sentence Prediction (NSP). The goal of MLM is to predict masked words, and its loss function can be expressed as: Among them, w i Represents masked words, and N is the total number of words in the sentence. BERT learns deep bidirectional representations from unlabeled text by jointly adjusting the left and right contexts in all layers and using a new masked l anguage mode l for pre-training. It also uses the Adam optimizer, which combines the advantages of the two optimization algorithms AdaGrad and RMSProp and can automatically adjust the learning rate. The model is trained using annotated datasets and the performance is evaluated on the validation set. Evaluation indicators include accuracy, recall, and F1 score. Cross-validation is used to improve the generalization ability of the model.

[0057] From the above, we can see that through mobile devices and online platforms, feedback and ratings from consumers and regulators are collected in real time. At the same time, combined with objective data such as temperature records, natural language processing technology is used for sentiment analysis, consumer opinions are extracted, and a weighted comprehensive scoring algorithm is used to obtain a comprehensive score for food safety service quality. This system can not only improve regulatory efficiency and information transparency, but also enhance consumer confidence, promote public participation, and provide scientific and comprehensive technical support for food safety supervision.

[0058] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, as well as parameter values ​​(e.g., temperature, pressure, etc.), mounting arrangements, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure described herein that performs the function, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0059] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0060] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0061] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A food safety service quality evaluation system, characterized in that: include: The data acquisition module uses IoT technology to deploy sensors in food production lines, warehousing, logistics and sales points to monitor food temperature, humidity and location parameters in real time; Data storage module, which uses cloud computing services to store and manage collected data; The data processing module cleans and preprocesses the collected data and uses machine learning algorithms to analyze the data, identify food safety risk patterns and trends, and apply natural language technology to analyze consumer feedback and extract sentiment and opinions; An interactive module that allows consumers and regulators to input food safety feedback and ratings through mobile devices and online platforms, and displays real-time data and historical trends; The alarm module automatically generates food safety reports and immediately sends alerts to managers and regulators when potential food safety issues and consumer feedback are detected.

2. A food safety service quality evaluation system as claimed in claim 1, characterized in that: The sensors include temperature and humidity sensors, pressure and flow sensors, as well as gratings and photoelectric sensors.

3. A food safety service quality evaluation system as claimed in claim 1, characterized in that: The data processing module first preprocesses the collected data, including cleaning, normalization and missing value processing steps, and then selects features from factors that affect food safety, including but not limited to temperature, humidity, pressure and appearance, expressed as: F = {f1, f2, ..., f n }, where F is the selected feature set, f i Represents the i-th feature; then use the linear regression model for training, expressed as: y = β0 + β1x1 + β2x2 + ... + β n x n , where y represents the target variable, x i Represents the characteristics, β i Represents the coefficient; then, by inputting new food safety data, rapid prediction and risk assessment are performed, and the prediction process is expressed as: pred =h θ (x), where y pred represents the predicted value, h θ (x) represents the hypothesis function obtained through training, and x is the new input data.

4. A food safety service quality evaluation system as claimed in claim 3, characterized in that: Consumer feedback is analyzed through natural language technology to extract sentiment and opinions. The TF-IDF method is used to represent the text as a collection of word frequencies and analyze the rarity of the words in the entire corpus, expressed as: Among them, TF(t,d) represents the frequency of occurrence of term t in document d, DF(t) represents the number of documents containing t, and N is the total number of documents; Then, the classifier is trained by the labeled sentiment data set, and the support vector machine is used for sentiment classification. The process is expressed as: Among them, x i represents the support vector, α i represents the Lagrange multiplier, y i represents the label, K represents the kernel function, and b represents the bias term; Then, a web application is built through Flask. After the user enters text, the system outputs the sentiment analysis results.

5. A food safety service quality evaluation system as claimed in claim 4, characterized in that: By combining parameter data and consumer feedback, introducing a weight and scoring mechanism, and performing weighted calculations based on the importance of different factors, we can obtain a comprehensive score for food safety service quality, expressed as: Where S represents the comprehensive score of food safety service quality, n represents the total number of evaluation indicators, and w i represents the weight of the i-th evaluation index, s i Represents the score of the i-th evaluation indicator.

6. A food safety service quality evaluation system as claimed in claim 1, characterized in that: The interactive module allows consumers and regulators to input their feedback and ratings through mobile applications or online platforms. The data submitted by users is transmitted to the data processing module through the network, and then the data is stored in the data storage module. The analysis results are presented in the form of charts through data visualization tools, showing real-time data and historical trends, and the network transmission is encrypted using the HTTPS protocol.

7. A food safety service quality evaluation system as claimed in claim 1, characterized in that: An API interface is also provided to enable third-party systems to interact with the system.

Images