A mutton quality risk perception big data management system

Abstract

This invention discloses a big data management system for mutton quality risk perception, belonging to the field of mutton quality assessment technology, including a cloud platform and a user terminal. The user terminal includes a mutton information module; the cloud platform includes a mutton data module and a quality analysis module. The mutton information module is used by users to upload mutton information to be analyzed and send the mutton information to the mutton data module in the cloud. The mutton data module is used to collect mutton quality data based on the received mutton information, perform consistency assessment on the mutton quality data, obtain the traceability credibility of the mutton quality data, supplement the traceability credibility into the mutton quality data, and send the mutton quality data to the quality analysis module. The quality analysis module is used to perform quality assessment on the mutton quality data, obtain the corresponding quality assessment results, and perform corresponding processing based on the quality assessment results.

Description

Technical Field

[0001] This invention belongs to the field of mutton quality assessment technology, specifically a mutton quality risk perception big data management system. Background Technology

[0002] In the meat consumption market, mutton is highly favored by consumers due to its high nutritional value and unique flavor. However, mutton quality and safety issues occur frequently, such as excessive veterinary drug residues caused by inadequate disease control in the breeding process, the accumulation of harmful substances caused by feed contamination, microbial contamination or adulteration caused by irregular operations in the processing process, and the risk of spoilage caused by cold chain disruptions in the logistics process. These issues not only seriously threaten consumer health but also pose a challenge to the sustainable development of the mutton industry.

[0003] Therefore, how to conduct quality analysis of mutton has become a technical problem that needs to be solved. Based on this, the present invention provides a mutton quality risk perception big data management system. Summary of the Invention

[0004] To address the problems existing in the above solutions, the present invention provides a big data management system for mutton quality risk perception.

[0005] The objective of this invention can be achieved through the following technical solutions: A big data management system for perceiving mutton quality risks, including cloud and user terminals; Furthermore, there is a communication connection between the cloud and each user terminal.

[0006] The user terminal includes a mutton information module; The mutton information module is used by users to upload mutton information to be analyzed and send the mutton information to the mutton data module in the cloud.

[0007] The cloud platform includes a mutton data module and a quality analysis module. The mutton data module is used to collect mutton quality data based on the received mutton information and send the mutton quality data to the quality analysis module.

[0008] Furthermore, when the mutton information is a traceability code, mutton quality data is collected based on the traceability code.

[0009] Furthermore, the mutton quality data also includes supplementary quality data added by the user.

[0010] Furthermore, a consistency assessment is conducted on the mutton quality data to obtain the traceability credibility of the mutton quality data, and the traceability credibility is then added to the mutton quality data.

[0011] Furthermore, a consistency assessment of the mutton quality data was conducted, including: The platform provider sets up an association library, which is used to store the associated data items corresponding to various quality data items; Identify the various quality data items corresponding to the mutton quality data, input the quality data items into the association database for matching, obtain each associated data item, extract features from the mutton quality data based on the quality data items and their corresponding associated data items, and obtain the corresponding single quality data and associated material data; Based on the associated material data, a consistency assessment is performed on the corresponding individual quality data to obtain the corresponding consistency assessment results, which include consistency qualified and consistency unqualified. The true coefficient of each individual quality data point is determined based on the consistency evaluation results corresponding to each individual quality data point. The true coefficient is 1 or 0. The traceability credibility of the mutton quality data is calculated based on the true coefficient of each individual quality data item.

[0012] Furthermore, the matched associated data items are filtered based on each quality data item, and associated data items that are not within the scope of the quality data items are removed.

[0013] Furthermore, a consistency assessment is conducted on the corresponding individual quality data based on the associated material data, including: Establish a consistency model, the expression of which is: ; In the formula: (q, p) are the input data, where q and p represent individual quality data and related material data, respectively; q→p indicates that the corresponding individual quality data meets the consistency of the related material data; the output data is the consistency evaluation value YP(q, p), and the consistency evaluation value is 1 or 0. By integrating relevant individual quality data and related material data into input data, the data is input into the consistency model for analysis, and the corresponding consistency evaluation value is obtained. When the consistency assessment value is 1, the consistency assessment result includes "consistency qualified". When the consistency assessment value is 0, the consistency assessment result includes non-compliance.

[0014] Furthermore, the traceability credibility of mutton quality data is calculated based on the authenticity coefficient of each individual quality data point, including: Each true coefficient is labeled as μ. i , i represents the corresponding quality data item, i=1,2,...,n, where n is the number of quality data items; The corresponding source tracing credibility is calculated according to the source tracing credibility formula, which is: ; In the formula: k represents the source tracing credibility.

[0015] Furthermore, the traceability credibility of mutton quality data is calculated based on the authenticity coefficient of each individual quality data point, including: Preset the baseline values ​​for each quality data item; Each true coefficient is labeled as μ. i , i represents the corresponding quality data item, i=1,2,...,n, where n is the number of quality data items; The corresponding source tracing credibility is calculated according to the source tracing credibility formula, which is: ; In the formula: k is the source tracing credibility, CA i This represents the baseline value for the corresponding quality data item.

[0016] Furthermore, when mutton information cannot be traced, the mutton information is divided into collected information and filtered information; Based on the collected information, relevant mutton quality reference data is collected. Based on the filtering information, the mutton quality reference data is filtered, and the mutton quality reference data with the highest similarity is regarded as the mutton quality data of the corresponding mutton. A credibility analysis is conducted based on mutton information and mutton quality data to obtain the reference credibility of the mutton quality data.

[0017] The quality analysis module is used to assess the quality data of mutton, obtain the corresponding quality assessment results, and perform appropriate processing based on the quality assessment results.

[0018] Compared with the prior art, the beneficial effects of the present invention are: The mutton quality risk perception big data management system of this invention provides a comprehensive and efficient solution to the serious quality and safety problems in the current mutton consumption market, bringing many significant benefits. This system integrates data from the entire mutton industry chain, from breeding and processing to logistics, enabling comprehensive and accurate perception of potential quality risks at each stage. These risks include excessive veterinary drug residues due to inadequate disease control in the breeding stage, the accumulation of harmful substances caused by feed contamination, microbial contamination or adulteration due to improper processing, and spoilage risks caused by cold chain disruptions in the logistics stage. This effectively overcomes the shortcomings of traditional quality analysis methods, which often suffer from incomplete information and missed risk assessments. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0021] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0022] like Figure 1 As shown, a big data management system for perceiving mutton quality risks includes a cloud platform and a user terminal. The communication connection between the cloud and each user terminal.

[0023] The user terminal includes a mutton information module; The mutton information module is used by users to upload mutton information to be analyzed, which refers to information data related to mutton quality data; and to send the mutton information to the mutton data module in the cloud.

[0024] In one embodiment, the mutton information includes traceability codes, QR codes, mutton codes, and other information that can indicate the mutton's source, cut, etc.; it can also be a method for collecting mutton quality data from other mutton participants, such as methods for farmers, slaughterhouses, merchants, and transporters to obtain mutton quality data from other preceding stages; that is, this embodiment is for mutton with data traceability.

[0025] In one embodiment, for individual consumers who do not have traceability codes or other means to trace the origin of mutton, the mutton information may include mutton photos, cuts, sellers, and information about the source of the mutton advertised by the sellers. This facilitates the use of big data and other related technologies in the cloud to collect mutton quality data that can represent the quality of the mutton.

[0026] The cloud platform includes a mutton data module and a quality analysis module. The mutton data module is used to collect corresponding mutton quality data based on the received mutton information and send the mutton quality data to the quality analysis module.

[0027] In one embodiment, when the mutton information is a traceability code, QR code, or other related information, it indicates that the mutton has pre-collected mutton quality data, which can be accessed and collected simply by using the mutton information. For example, current data systems applied to the entire industry chain monitor mutton quality-related data throughout the entire industry chain, including breeding, slaughtering, transportation, and sales, to form corresponding monitoring data, which is then stored using blockchain or similar methods. In this case, the present invention collects data based on the mutton information through the mutton data module.

[0028] In one embodiment, if there is no channel for pre-stored mutton quality data such as traceability codes or QR codes, mutton quality data that can be used to assess the quality of the mutton can be obtained based on existing big data technologies.

[0029] In one embodiment, when traceability cannot be performed based on mutton information, i.e., when mutton quality data provided by the corresponding mutton link cannot be obtained according to the above embodiments, similarity data is collected based on mutton information to obtain the corresponding mutton quality data and corresponding credibility.

[0030] This involves collecting information such as photos of mutton, cuts of mutton, sellers, and the source of mutton advertised by sellers. For example, historical mutton quality data with the same source, seller, and cut of mutton can be collected based on the seller, the source of mutton advertised by sellers, and the mutton. Then, similarity matching is performed based on mutton images to determine the closest historical mutton quality data, which is used as the mutton quality data for that mutton. This is equivalent to dividing mutton information into collection information and filtering information according to information such as source, seller, cut, and mutton photos. Historical mutton quality data is collected through collection information and marked as mutton quality reference data. The closest mutton quality data is selected from the mutton quality reference data through filtering information. Based on user feedback accumulated on the platform and other data sources, credibility analysis is conducted on mutton information and mutton quality data to obtain corresponding reference credibility. Credibility assessment can be performed using various current credibility assessment algorithms and models to obtain corresponding credibility, which is marked as reference credibility to distinguish it from traceability credibility.

[0031] In one embodiment, for cases where traceability is possible based on mutton information, individual consumers can supplement quality data such as mutton pictures and descriptions as needed to improve the accuracy of subsequent quality assessments.

[0032] In one embodiment, to avoid situations such as falsification of traceability data, a consistency assessment is performed on mutton quality data to obtain the traceability credibility of the mutton quality data.

[0033] This means judging the consistency of mutton quality data based on its correlation, and then assessing the data credibility and marking it as traceability credibility. For example, if the data provided by the breeder and the transportation data cannot match the data from the slaughterhouse, it does not meet the consistency requirements.

[0034] For example, intelligent models can be built based on machine learning, deep learning algorithms, etc., to conduct consistency assessments of mutton quality data and obtain traceability credibility.

[0035] In one embodiment, a consistency assessment of mutton quality data includes: The platform pre-marks the correlations between various mutton quality data based on the available data. For example, the correlations between feed input and sheep weight gain, vaccination time and antibody test results, breeding environment parameters and sheep health status, slaughter time and meat pH value, and processing temperature and microbial test results are all recorded by the platform. The platform summarizes and compiles these correlations into a database, which stores the quality data items associated with each quality data item and marks the associated quality data items as related data items. Identify the various quality data items corresponding to the mutton quality data. Identify the quality data items based on the various data included in the mutton quality data. Input the quality data items into the association database for matching to obtain each associated data item. Filter the matched associated data items based on each quality data item and remove associated data items that are not within the scope of the quality data items. Since the mutton quality data does not contain such data, it can be removed. Feature extraction is performed on the mutton quality data based on the quality data items and their corresponding related data items to obtain the corresponding individual quality data and related material data. The related material data is the data corresponding to the corresponding related data item, and the individual quality data is the data corresponding to the quality data item. Consistency assessment is performed on the corresponding individual quality data based on the related material data to obtain the corresponding consistency assessment results, which include consistency qualified and consistency unqualified. The true coefficient of each individual quality data point is determined based on the consistency evaluation results corresponding to each individual quality data point. The true coefficient is 1 or 0. The traceability credibility of mutton quality data is calculated based on the true coefficient of each individual quality data item.

[0036] In one embodiment, consistency assessment of corresponding individual quality data is performed based on associated material data. This can be done using existing methods to assess the consistency of individual quality data based on associated material data, determine whether the individual quality data is abnormal or conflicting, and obtain a consistency assessment result; for example, assessment and judgment can be performed based on machine learning, deep learning algorithms, etc.

[0037] In one embodiment, a consistency assessment of the corresponding individual quality data based on associated material data includes: Establish a consistency model, the expression of which is: ; In the formula: (q, p) are the input data, where q and p represent individual quality data and related material data, respectively; q→p indicates that the corresponding individual quality data meets the consistency of the related material data; the output data is the consistency evaluation value YP(q, p), which is 1 or 0; the staff will train the corresponding training set based on the association library and historical data to determine which situations are normal and abnormal, and then make identification judgments. By integrating relevant individual quality data and related material data into input data, the data is input into the consistency model for analysis, and the corresponding consistency evaluation value is obtained. When the consistency assessment value is 1, the consistency assessment result includes "consistency qualified". When the consistency assessment value is 0, the consistency assessment result includes non-compliance.

[0038] In one embodiment, the true coefficient of each individual quality data is determined based on the consistency evaluation results corresponding to each individual quality data. That is, based on the consistency evaluation results corresponding to each individual quality data, it is first determined which individual quality data are distorted and which data are true. Then, based on the data that is inconsistent with the clearly true data, the distorted data is determined. The forward and backward reasoning is used to determine whether each individual quality data is true. The true coefficient of true data is 1, and the true coefficient of false data is 0.

[0039] Alternatively, other methods can be used for summary analysis to determine whether each individual quality data item is authentic. For example, based on historical data, pre-determine which combinations of consistency assessment results can determine whether a particular quality data item is authentic or distorted. Then, direct matching can be performed to identify authentic and distorted individual quality data items. Based on the clearly identified authentic and distorted individual quality data items, other individual quality data items can be inferred. If they are inconsistent with the authentic data, their distortion can be assessed.

[0040] If there are situations where the authenticity cannot be proven, settings can be configured according to user needs, such as treating them as untrue or true.

[0041] It can also add a true coefficient for data whose authenticity cannot be proven.

[0042] In one embodiment, the traceability credibility of mutton quality data is calculated based on the authenticity coefficient of each individual quality data item. Once it is clear whether each individual quality data item is authentic (authenticity coefficient), the credibility of the mutton quality data can be determined based on existing technology and marked as traceability credibility.

[0043] In one embodiment, calculating the traceability credibility of mutton quality data based on the authenticity coefficient of each individual quality data point includes: Each true coefficient is labeled as μ. i , i represents the corresponding quality data item, i=1,2,...,n, where n is the number of quality data items; The corresponding source tracing credibility is calculated according to the source tracing credibility formula, which is: ; In the formula: k represents the source tracing credibility.

[0044] In one embodiment, calculating the traceability credibility of mutton quality data based on the authenticity coefficient of each individual quality data point includes: Considering the differences in importance of different quality data items, corresponding weight coefficients, base values, and other values ​​that can represent the differences in importance can be set for each quality data item and marked as the baseline value of the data item. Each true coefficient is labeled as μ. i , i represents the corresponding quality data item, i=1,2,...,n, where n is the number of quality data items; The corresponding source tracing credibility is calculated according to the source tracing credibility formula, which is: ; In the formula: k is the source tracing credibility, CA i This represents the baseline value for the corresponding quality data item.

[0045] The quality analysis module is used to assess the quality data of mutton, obtain the corresponding quality assessment results, and perform appropriate processing based on the quality assessment results.

[0046] In a real-time example, when mutton quality data is obtained, quality assessment can be performed based on existing mutton quality assessment methods, such as building a quality assessment model based on machine learning and deep learning algorithms, and then using the quality assessment model to perform quality assessment.

[0047] In one embodiment, the quality assessment results are processed accordingly, and the processing is carried out according to user needs. For example, the quality assessment results are displayed to the relevant users, and a non-compliance warning is issued. The inventory of mutton can also be processed according to the quality assessment results, and the specific management is carried out according to the actual user's management needs.

[0048] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0049] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A big data management system for perceiving mutton quality risks, characterized in that, Including both cloud and client-side applications; The user terminal includes a mutton information module; the cloud terminal includes a mutton data module and a quality analysis module. The mutton information module is used by users to upload mutton information to be analyzed and send the mutton information to the mutton data module in the cloud. The mutton data module is used to collect mutton quality data based on the received mutton information, perform consistency assessment on the mutton quality data, obtain the traceability credibility of the mutton quality data, supplement the traceability credibility into the mutton quality data, and send the mutton quality data to the quality analysis module. The quality analysis module is used to assess the quality data of mutton, obtain the corresponding quality assessment results, and perform appropriate processing based on the quality assessment results.

2. The mutton quality risk perception big data management system according to claim 1, characterized in that, The communication connection between the cloud and each user terminal.

3. The mutton quality risk perception big data management system according to claim 1, characterized in that, When the mutton information is a traceability code, mutton quality data is collected based on the traceability code.

4. The mutton quality risk perception big data management system according to claim 1, characterized in that, A consistency assessment of mutton quality data was conducted, including: The platform provider sets up an association library, which is used to store the associated data items corresponding to various quality data items; Identify the various quality data items corresponding to the mutton quality data, input the quality data items into the association database for matching, obtain each associated data item, extract features from the mutton quality data based on the quality data items and their corresponding associated data items, and obtain the corresponding single quality data and associated material data; Based on the associated material data, a consistency assessment is performed on the corresponding individual quality data to obtain the corresponding consistency assessment results, which include consistency qualified and consistency unqualified. The true coefficient of each individual quality data point is determined based on the consistency evaluation results corresponding to each individual quality data point. The true coefficient is 1 or 0. The traceability credibility of the mutton quality data is calculated based on the true coefficient of each individual quality data item.

5. The mutton quality risk perception big data management system according to claim 4, characterized in that, Based on each quality data item, the matched related data items are filtered, and related data items that are not within the scope of the quality data items are removed.

6. The mutton quality risk perception big data management system according to claim 4, characterized in that, A consistency assessment of the corresponding individual quality data is performed based on the associated material data, including: Establish a consistency model, the expression of which is: ； In the formula: (q, p) are the input data, where q and p represent individual quality data and related material data, respectively; q→p indicates that the corresponding individual quality data meets the consistency of the related material data; the output data is the consistency evaluation value YP(q, p), and the consistency evaluation value is 1 or 0. By integrating relevant individual quality data and related material data into input data, the data is input into the consistency model for analysis, and the corresponding consistency evaluation value is obtained. When the consistency assessment value is 1, the consistency assessment result includes "consistency qualified". When the consistency assessment value is 0, the consistency assessment result includes non-compliance.

7. The mutton quality risk perception big data management system according to claim 4, characterized in that, The traceability credibility of mutton quality data is calculated based on the true coefficient of each individual quality data point, including: Each true coefficient is labeled as μ. i , i represents the corresponding quality data item, i=1,2,...,n, where n is the number of quality data items; The corresponding source tracing credibility is calculated according to the source tracing credibility formula, which is: ； In the formula: k represents the source tracing credibility.

8. The mutton quality risk perception big data management system according to claim 4, characterized in that, The traceability credibility of mutton quality data is calculated based on the true coefficient of each individual quality data point, including: Preset the baseline values ​​for each quality data item; Each true coefficient is labeled as μ. i , i represents the corresponding quality data item, i=1,2,...,n, where n is the number of quality data items; The corresponding source tracing credibility is calculated according to the source tracing credibility formula, which is: ； In the formula: k is the source tracing credibility, CA i This represents the baseline value for the corresponding quality data item.

9. The mutton quality risk perception big data management system according to claim 1, characterized in that, When mutton information cannot be traced back to its source, the mutton information is divided into collected information and filtered information. Based on the collected information, relevant mutton quality reference data is collected. Based on the filtering information, the mutton quality reference data is filtered, and the mutton quality reference data with the highest similarity is regarded as the mutton quality data of the corresponding mutton. A credibility analysis is conducted based on mutton information and mutton quality data to obtain the reference credibility of the mutton quality data.

Images