CN119204835A - Quality traceability system of traditional Chinese medicine granules based on data fusion - Google Patents
Quality traceability system of traditional Chinese medicine granules based on data fusion Download PDFInfo
- Publication number
- CN119204835A CN119204835A CN202411675974.XA CN202411675974A CN119204835A CN 119204835 A CN119204835 A CN 119204835A CN 202411675974 A CN202411675974 A CN 202411675974A CN 119204835 A CN119204835 A CN 119204835A
- Authority
- CN
- China
- Prior art keywords
- quality
- data
- key
- weighted
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 74
- 230000004927 fusion Effects 0.000 title claims abstract description 19
- 239000008187 granular material Substances 0.000 title claims description 25
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000004519 manufacturing process Methods 0.000 claims description 103
- 238000000034 method Methods 0.000 claims description 69
- 230000002159 abnormal effect Effects 0.000 claims description 37
- 230000008569 process Effects 0.000 claims description 30
- 239000002994 raw material Substances 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims 1
- 230000007423 decrease Effects 0.000 claims 1
- 238000001303 quality assessment method Methods 0.000 claims 1
- 239000002245 particle Substances 0.000 abstract description 55
- 239000002131 composite material Substances 0.000 description 8
- 230000006872 improvement Effects 0.000 description 8
- 238000013441 quality evaluation Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010606 normalization Methods 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000006731 degradation reaction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005206 flow analysis Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 230000006978 adaptation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000012535 impurity Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000003326 Quality management system Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 239000004480 active ingredient Substances 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004090 dissolution Methods 0.000 description 1
- 239000013583 drug formulation Substances 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Factory Administration (AREA)
Abstract
The invention provides a traditional Chinese medicine formula particle quality tracing system based on data fusion, which relates to the technical field of data processing and comprises the steps of defining a dynamic adjustment factor according to actual conditions, multiplying an actual value of each key feature with a weight corresponding to the actual value and the dynamic adjustment factor to obtain weighted key feature values, summing all weighted key feature values to obtain a comprehensive quality index, comparing the comprehensive quality index with a corresponding quality standard to obtain a comparison result, judging the quality of new traditional Chinese medicine formula particle data according to the comparison result, judging that quality problems exist in traditional Chinese medicine formula particles in corresponding batches if the comprehensive quality index is lower than the quality standard, and analyzing the weighted key feature values to obtain key features negatively affecting the comprehensive quality index. The invention improves the efficiency and accuracy of quality problem processing.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a traditional Chinese medicine formula particle quality tracing system based on data fusion.
Background
The traditional Chinese medicine formula particle quality traceability system has the following defects:
For example, some data of only partial links can be collected, and the whole process from production to sales of the traditional Chinese medicine formula particles cannot be covered completely, which leads to data incompleteness and reduced traceability accuracy.
Secondly, in traditional quality tracing, the extraction of key quality features is mostly dependent on manual experience and simple statistical analysis, so that it is difficult to accurately capture key factors affecting the quality of traditional Chinese medicine formula particles.
For another example, in the conventional method, when calculating the quality index, a fixed weight and a static evaluation standard are adopted, so that the dynamic change of the actual situation is ignored. Such an evaluation method may not be suitable for the continuously changing production environment and market demands, resulting in insufficient accuracy and real-time of the quality evaluation result.
Disclosure of Invention
The invention aims to solve the technical problem of providing a traditional Chinese medicine formula particle quality tracing system based on data fusion, so that the efficiency and accuracy of quality problem processing are improved.
In order to solve the technical problems, the technical scheme of the invention is as follows:
in a first aspect, a method for tracing quality of traditional Chinese medicine formula particles based on data fusion includes:
The data acquisition module is used for collecting parameter data of the traditional Chinese medicine formula particles in various links of production, processing, transportation, storage and sales;
the data preprocessing module is used for preprocessing the parameter data to obtain preprocessed data;
the extraction module is used for extracting key characteristics related to the quality of the traditional Chinese medicine formula particles from the pretreatment data;
The quality evaluation calculation module is used for distributing a weight to each key feature according to the historical data, defining a dynamic adjustment factor according to the actual situation, multiplying the actual value of each key feature by the corresponding weight and the dynamic adjustment factor to obtain a weighted key feature value, summing all the weighted key feature values to obtain a comprehensive quality index, and comparing the comprehensive quality index with the corresponding quality standard to obtain a comparison result;
The quality tracing module is used for judging the quality of the new traditional Chinese medicine formula granule data according to the comparison result, judging that the traditional Chinese medicine formula granule in the corresponding batch has quality problems if the comprehensive quality index is lower than the quality standard, analyzing the weighted key characteristic value to obtain the key characteristic negatively influencing the comprehensive quality index, and positioning the key node with the problem according to the production batch information, the weight of the key characteristic and the dynamic adjustment factor;
The prediction module is used for connecting the key nodes with the production information of each link in series through the established quality tracing model to form a quality tracing chain, and obtaining a tracing result according to the quality tracing chain.
Further, extracting key features related to the quality of the traditional Chinese medicine formula particles from the pretreatment data comprises the following steps:
Receiving the data related to the pretreated traditional Chinese medicine formula particles, and referring to a pre-established feature library, wherein the feature library comprises all features related to the quality of the traditional Chinese medicine formula particles, including chemical component content, processing temperature, humidity and time stamp;
Screening out corresponding characteristic fields from the preprocessing data according to a pre-established characteristic library;
and calculating a correlation coefficient between the characteristic field and the quality index to obtain the key characteristic.
Further, calculating a correlation coefficient between the feature field and the quality index to obtain the key feature includes:
By passing through Calculating a correlation coefficient between the characteristic field and the quality index;
screening according to the correlation coefficient to obtain key features;
Wherein, The correlation coefficient is represented by a correlation coefficient,Representing the total number of observations, representing the number of samples in the dataset; And Representing the first of two variablesThe observed values; From 1 to Traversing all samples; Representing the sum symbols, representing from 1 to Summation operations of all sample points; Representing variables Is the average value of (2); Representing variables Is the average value of (2); Representing variables Is the first of (2)The difference between the individual values and their mean; Representing variables Is the first of (2)The difference between the individual values and their mean; index representing sample point currently being processed for traversing from 1 to Is a sample of all points of the sample; And Is a subscript in the summation for calculating the variableAndIn the mean value calculation, respectively go through from 1 toAll of (3)AndValues.
Further, assigning a weight to each key feature based on the historical data, comprising:
based on historical data, by Assigning a weight to each key feature;
Wherein, Is the firstCorrelation coefficients between the key features and the quality index; And Is an adjustment coefficient; Is the total number of key features; Is the first Get the first key featureProbability of the individual value; Is the first The number of values of the key features; Is the first Correlation coefficients between the key features and the quality index; Is the first The number of values of the key features; Is the first Get the first key featureProbability of the individual value; Is an index of key features; Is in the calculation of Index used when information entropy of each key feature; is an index used when calculating the information entropy of each key feature in the denominator; Is an index used in the denominator to traverse all key features.
Further, the calculation formula of the dynamic adjustment factor is:
;
Wherein, AndIs a weight coefficient; And Weights of temperature and humidity, respectively; And Ideal temperature and humidity values, respectively; And The actual measured temperature and humidity values, respectively; And The maximum possible ranges of variation of temperature and humidity, respectively; Is the number of key process parameters; Is the first Actual values of the individual process parameters; Is the first Target values of the individual process parameters; is the maximum range of possible variation of the process parameters.
Further, analyzing the weighted key feature values to obtain key features that negatively affect the composite quality index, including:
Carrying out data standardization processing on the weighted characteristic values to obtain standardized data;
Calculating statistics of each weighted characteristic value in the standardized data, wherein the statistics comprise a mean value, a standard deviation, a median and a quartile, so as to know the distribution condition of the standardized data and the variation range of the characteristic values;
setting a threshold based on the statistics, and judging whether the weighted characteristic value is abnormal or not;
Traversing all the weighted characteristic values, comparing each weighted characteristic value with a threshold value, and marking out an abnormal weighted characteristic value;
For each weighted feature value marked as abnormal, removing the corresponding weighted feature value from the standardized data, and recalculating the comprehensive quality index based on the remaining weighted feature values;
comparing the difference between the original comprehensive quality index and the comprehensive quality index after the abnormal characteristics are removed;
The method comprises the steps of sorting all the weight characteristic values of the anomalies according to the influence degree of the comprehensive quality indexes, setting a negative influence threshold, when the influence degree of the weight characteristic values of the anomalies on the comprehensive quality indexes exceeds the negative influence threshold, regarding the weight characteristic values of the anomalies as key characteristics which negatively influence the whole quality, and screening key characteristics which exceed the negative influence threshold from a sorted weight characteristic value list of the anomalies.
Further, locating problematic key nodes according to the production lot information and the weights and dynamic adjustment factors of key features, comprising:
Multiplying the actual measured values of the respective key features by their corresponding weights for each production lot to obtain weighted scores;
multiplying the weighted value by a corresponding dynamic adjustment factor to reflect the actual situation in the current production environment;
Comparing weighted scores of different production batches to obtain batches with abnormal scores;
According to the batches with abnormal scores, analyzing each link in the production flow, including the quality of raw materials and the state of equipment, so as to obtain a production flow analysis result;
Based on the production flow analysis and the weighted scores, key nodes that lead to product quality degradation are located.
In a second aspect, a method for tracing the quality of traditional Chinese medicine formula particles based on data fusion comprises the following steps:
Collecting parameter data of traditional Chinese medicine formula particles in various links of production, processing, transportation, storage and sales;
preprocessing the parameter data to obtain preprocessed data;
extracting key characteristics related to the quality of the traditional Chinese medicine formula particles from the pretreatment data;
The method comprises the steps of obtaining historical data, distributing a weight for each key feature, defining a dynamic adjustment factor according to actual conditions, multiplying the actual value of each key feature with the weight corresponding to the actual value and the dynamic adjustment factor to obtain a weighted key feature value, summing all weighted key feature values to obtain a comprehensive quality index, and comparing the comprehensive quality index with a corresponding quality standard to obtain a comparison result;
According to the comparison result, carrying out quality judgment on new traditional Chinese medicine formula particle data, if the comprehensive quality index is lower than a quality standard, judging that the traditional Chinese medicine formula particle of the corresponding batch has quality problems;
And connecting the key nodes with the production information of each link in series through the established quality tracing model to form a quality tracing chain, and obtaining a tracing result according to the quality tracing chain.
In a third aspect, a computing device includes:
one or more processors;
And a storage means for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the method.
In a fourth aspect, a computer readable storage medium has a program stored therein, which when executed by a processor, implements the method.
The above scheme of the invention at least comprises the following beneficial effects.
Through the data acquisition module, the system can comprehensively and automatically collect parameter data of the traditional Chinese medicine formula particles in various links of production, processing, transportation, storage and sales, and the comprehensive data acquisition ensures the integrity and the accuracy of the data. The data preprocessing module can effectively clean, convert and standardize the collected parameter data, so that high-quality preprocessed data is obtained, the quality of the data is improved, and the complexity and error rate of subsequent processing are reduced.
The extraction module can accurately extract key characteristics related to the quality of the traditional Chinese medicine formula particles from the preprocessed data by utilizing a data analysis technology. The quality evaluation calculation module combines historical data and actual conditions, and realizes dynamic evaluation of the quality of the traditional Chinese medicine formula particles through dynamic adjustment factors and weight distribution. The quality tracing module can rapidly judge the quality problem of the traditional Chinese medicine formula particles according to the comparison result of the comprehensive quality index and the quality standard, and accurately locate the key nodes with problems by analyzing the weighted key characteristic values, thereby improving the efficiency and accuracy of quality problem processing.
The prediction module can predict potential quality problems through the established quality traceability model, and connects the key nodes with production information of each link in series to form a complete quality traceability chain.
Drawings
Fig. 1 is a schematic diagram of a system for tracing the quality of traditional Chinese medicine formula particles based on data fusion according to an embodiment of the invention.
Fig. 2 is a flow chart of a method for tracing the quality of traditional Chinese medicine formula particles based on data fusion according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides a data fusion-based quality traceability system for a traditional Chinese medicine granule, which includes:
The data acquisition module is used for collecting parameter data of the traditional Chinese medicine formula particles in various links of production, processing, transportation, storage and sales;
the data preprocessing module is used for preprocessing the parameter data to obtain preprocessed data;
the extraction module is used for extracting key characteristics related to the quality of the traditional Chinese medicine formula particles from the pretreatment data;
The quality evaluation calculation module is used for distributing a weight to each key feature according to the historical data, defining a dynamic adjustment factor according to the actual situation, multiplying the actual value of each key feature by the corresponding weight and the dynamic adjustment factor to obtain a weighted key feature value, summing all the weighted key feature values to obtain a comprehensive quality index, and comparing the comprehensive quality index with the corresponding quality standard to obtain a comparison result;
The quality tracing module is used for judging the quality of the new traditional Chinese medicine formula granule data according to the comparison result, judging that the traditional Chinese medicine formula granule in the corresponding batch has quality problems if the comprehensive quality index is lower than the quality standard, analyzing the weighted key characteristic value to obtain the key characteristic negatively influencing the comprehensive quality index, and positioning the key node with the problem according to the production batch information, the weight of the key characteristic and the dynamic adjustment factor;
The prediction module is used for connecting the key nodes with the production information of each link in series through the established quality tracing model to form a quality tracing chain, and obtaining a tracing result according to the quality tracing chain.
In the embodiment of the invention, the comprehensive and automatic collection of the full life cycle (production, processing, transportation, storage and sales) data of the traditional Chinese medicine formula particles is realized, the timeliness and the accuracy of the data are ensured, and a rich data source is provided for the subsequent quality tracing. By performing preprocessing operations such as cleaning, conversion, standardization and the like on the collected original data, noise and abnormal values in the data are effectively eliminated, and the quality and usability of the data are improved. By utilizing a data mining technology, key characteristics closely related to the quality of the traditional Chinese medicine formula particles are accurately extracted from the preprocessed data, and the characteristics can directly reflect the quality condition of the product.
By combining historical data and dynamic adjustment factors, reasonable weights are distributed for each key feature, dynamic and quantitative evaluation of the quality of the traditional Chinese medicine formula particles is achieved, the evaluation method is high in flexibility, the actual quality level of the product can be reflected more truly, and accuracy and reliability of quality evaluation are improved.
According to the comparison result of the comprehensive quality index and the quality standard, whether the traditional Chinese medicine formula particles have quality problems or not can be rapidly and accurately judged, and specific links and factors affecting the quality of products can be accurately positioned through analyzing the weighted key characteristic values.
And the production information of each link is connected with the key nodes in series through the established quality tracing model, so that a complete quality tracing chain is formed. The method is beneficial to the enterprises to comprehensively understand the formation process of the product quality, and can also predict potential quality risks, and meanwhile, the quality traceability model can be continuously perfected and optimized through the feedback of traceability results, so that the accuracy and the effectiveness of prediction are improved.
In another preferred embodiment of the invention, data such as raw material information, production process parameters, equipment running state and the like are collected in a production link, key data such as a processing method, a processing environment, processing time and the like are collected in a processing link, a transportation link focuses on a transportation mode, transportation time and temperature and humidity change and the like during transportation, a storage link collects warehouse environment data (such as temperature and humidity, illumination), inventory states, inventory time and the like, and a sales link records information such as sales time, places and customer feedback.
The method comprises the steps of monitoring key environmental parameters such as temperature, humidity and pressure in real time by utilizing a sensor technology, tracking the moving paths of materials and products by utilizing an RFID (radio frequency identification) or two-dimensional code technology, integrating an Enterprise Resource Planning (ERP), a Manufacturing Execution System (MES) and other informationized systems, automatically grabbing data in the production and processing processes, transmitting the acquired data to a data center in real time through a wired or wireless network, and establishing a safe and reliable database in the data center for storing and managing the data.
The data preprocessing module is in charge of cleaning, converting and standardizing the collected original data to improve the quality and usability of the data, identifying and removing repeated records to ensure the uniqueness of the data, detecting and processing missing values, complementing the data by adopting methods of deleting, mean filling, interpolating and the like according to data characteristics and service rules, identifying abnormal values by using statistical methods (such as Z-score, IQR and the like), carrying out corresponding processing (such as replacing, deleting or reserving but marking), carrying out type conversion on the data, such as converting text data into numerical data, facilitating subsequent analysis and calculation, carrying out data normalization or standardization processing to eliminate dimension differences, enabling different characteristics to have comparability, encoding the classified data (such as independent thermal encoding), formulating data standards according to service requirements, carrying out formatting processing on the data, extracting key characteristics related to the quality of traditional Chinese medicine formula particles, such as raw material quality indexes, production process stability indexes and the like.
For example, taking a home drug formulation particle manufacturing enterprise as an example, the data acquisition and preprocessing flow is as follows:
The method comprises the steps of installing temperature and humidity sensors on a production line, monitoring and recording temperature and humidity changes of a production environment in real time, tracking a moving path of raw materials from warehouse entry to the production line by using RFID labels, ensuring traceability of raw material sources, and collecting key process parameters in the production process, such as mixing time, drying temperature and the like through an MES system. And (3) installing GPS and temperature and humidity monitoring equipment on the transport vehicle, and recording transport track and environmental change. And cleaning the collected temperature and humidity data, and removing abnormal values caused by sensor faults. And correlating the RFID tag data with the raw material quality information to form a complete raw material traceability data set. And carrying out normalization processing on the technological parameter data in the MES system, and analyzing the influence of environmental stability on the product quality in the transportation process by combining the GPS data and the temperature and humidity monitoring data.
In another preferred embodiment of the present invention, extracting key features related to the quality of the traditional Chinese medicine formula particles from the pre-processed data comprises:
The method comprises the steps of receiving the related data of the preprocessed traditional Chinese medicine formula particles, referring to a pre-established feature library, wherein the feature library comprises all features related to the quality of the traditional Chinese medicine formula particles, including chemical component content, processing temperature, humidity and time stamp, and screening corresponding feature fields from the preprocessed data according to the pre-established feature library, wherein the method specifically comprises the following steps:
The method comprises the steps of establishing a safe data interface for receiving related data of traditional Chinese medicine formula particles transmitted from a data preprocessing module, triggering data receiving operation after the data preprocessing module finishes data preprocessing, receiving and storing the preprocessed data into a designated data warehouse or database through the data interface to ensure the integrity and safety of the data, and establishing a perfect feature library before feature screening. The feature library should contain all the features related to the quality of the traditional Chinese medicine formula particles, such as chemical component content (such as effective components, impurity components and the like), processing temperature, humidity, time stamp and the like, each feature should be clearly defined and described in the feature library, each field is traversed from the preprocessed data, each field is matched with the features in the feature library, whether the field belongs to the features related to the quality of the traditional Chinese medicine formula particles or not is judged, if the field is successfully matched with a certain feature in the feature library, the field is marked as a key feature field, if the field is not matched with all the features in the feature library, the field is regarded as a non-key feature field, and the field can be selectively reserved or discarded according to service requirements and data redundancy conditions. And sorting the screened key characteristic fields to form a new data set or data table.
And calculating a correlation coefficient between the characteristic field and the quality index to obtain the key characteristic.
In the embodiment of the invention, the system can accurately screen out the characteristic fields directly related to the quality of the traditional Chinese medicine formula particles from massive pretreatment data by referring to the pre-established characteristic library. The targeted data extraction mode greatly reduces the calculation amount of subsequent analysis and improves the data processing efficiency. And calculating a correlation coefficient between the characteristic field and the quality index, and helping to identify key characteristics which have the greatest influence on the quality of the traditional Chinese medicine formula particles. Based on the key characteristics, the quality evaluation is carried out, so that the actual quality condition of the product can be reflected more accurately, and the reliability of the quality evaluation is improved. After knowing which features are critical to quality, the enterprise can allocate resources more reasonably, and pay attention to and improve the production links and process parameters with obvious influence on quality preferentially, so that the optimized resource allocation strategy is beneficial to the enterprise to improve the production efficiency and reduce the quality risk. The extracted key characteristics and the correlation information of the key characteristics and the quality index provide powerful data support for enterprises to formulate quality management strategies and optimize production processes. In the quality tracing process, the extraction of key features is helpful for rapidly positioning specific links and factors which possibly influence the quality of products, and the tracing efficiency is improved.
In another preferred embodiment of the present invention, calculating a correlation coefficient between the feature field and the quality index to obtain the key feature includes:
By passing through Calculating a correlation coefficient between the characteristic field and the quality index;
screening according to the correlation coefficient to obtain key features;
Wherein, The correlation coefficient is represented by a correlation coefficient,Representing the total number of observations, representing the number of samples in the dataset; And Representing the first of two variablesThe observed values; From 1 to Traversing all samples; Representing the sum symbols, representing from 1 to Summation operations of all sample points; Representing variables Is the average value of (2); Representing variables Is the average value of (2); Representing variables Is the first of (2)The difference between the individual values and their mean; Representing variables Is the first of (2)The difference between the individual values and their mean; index representing sample point currently being processed for traversing from 1 to Is a sample of all points of the sample; And Is a subscript in the summation for calculating the variableAndIn the mean value calculation, respectively go through from 1 toAll of (3)AndValues.
In the embodiment of the invention, by calculating the correlation coefficient, which characteristic fields have obvious influence on the quality of the traditional Chinese medicine formula particles can be accurately identified, and the method is beneficial for enterprises to concentrate on improving key production links. After knowing the key characteristics, enterprises can pertinently optimize the production flow, and the quality of products is improved by adjusting the key characteristics, so that more accurate quality control is realized. By reducing excessive attention to non-critical links, the enterprise can allocate resources more efficiently, thereby improving overall production efficiency. Accurate identification of key features helps enterprises avoid excessive resources being put into unnecessary links, thereby reducing production cost.
In another preferred embodiment of the present invention, assigning a weight to each key feature based on historical data comprises:
based on historical data, by Assigning a weight to each key feature;
Wherein, Is the firstCorrelation coefficients between the key features and the quality index; And Is an adjustment coefficient; Is the total number of key features; Is the first Get the first key featureProbability of the individual value; Is the first The number of values of the key features; Is the first Correlation coefficients between the key features and the quality index; Is the first The number of values of the key features; Is the first Get the first key featureProbability of the individual value; Is an index of key features; Is in the calculation of Index used when information entropy of each key feature; is an index used when calculating the information entropy of each key feature in the denominator; Is an index used in the denominator to traverse all key features.
In the embodiment of the invention, by combining the correlation coefficient and the information entropy, the weight distribution not only considers the direct correlation of the characteristics and the quality index, but also considers the value diversity of the characteristics, thereby more comprehensively evaluating the importance of the characteristics. The assignment of weights is based on historical data, which makes the assessment more objective and accurate. By quantifying the impact of each key feature, an enterprise can more specifically optimize the production flow. After knowing the weight of each key feature, the enterprise can more reasonably allocate resources to preferentially improve the features with larger weights and more obvious influence on quality. The weight assignment process is based on explicit mathematical formulas and historical data, which enhances the transparency and credibility of the decision.
In another preferred embodiment of the present invention, the dynamic adjustment factor is calculated as:
;
Wherein, AndIs a weight coefficient; And Weights of temperature and humidity, respectively; And Ideal temperature and humidity values, respectively; And The actual measured temperature and humidity values, respectively; And The maximum possible ranges of variation of temperature and humidity, respectively; Is the number of key process parameters; Is the first Actual values of the individual process parameters; Is the first Target values of the individual process parameters; is the maximum range of possible variation of the process parameters.
In the embodiment of the invention, the formula comprehensively considers a plurality of influencing factors including temperature, humidity and key process parameters, and provides comprehensive evaluation indexes for dynamic adjustment of the production environment. By weight coefficientAndAnd weight of temperature and humidityAndThe formula can flexibly adapt to different production requirements and environmental conditions. The enterprise can adjust the weights according to actual conditions so as to reflect different influences of factors on the product quality. The difference between the ideal value and the actual measured value and the ratio of the values to the maximum possible variation range are introduced into the formula, so that the accurate control of the production environment is realized. This helps to reduce fluctuations in the production process and improve the stability of product quality. By comparing the actual value with the target value of the technological parameter, the formula helps enterprises to determine the deviation in the production process, thereby improving the production efficiency and the product quality. The change of the dynamic adjustment factors is calculated and monitored regularly, problems in the production process are found in time and improved, and the method is beneficial to continuous improvement of enterprises, and production efficiency and product quality are continuously improved.
In another preferred embodiment of the present invention, multiplying the actual value of each key feature with its corresponding weight and dynamic adjustment factor to obtain weighted key feature values, summing all weighted key feature values to obtain a composite quality index, comparing the composite quality index with a corresponding quality standard to obtain a comparison result, including:
The actual values of all key features are collected to ensure that the values are up-to-date and accurate, the weights corresponding to each key feature are obtained, the weights have been determined by previous analysis, and the current dynamic adjustment factors are calculated or obtained, which should be calculated based on real-time environmental conditions (such as temperature, humidity) and process parameters. For each key feature, multiplying the actual value thereof by the corresponding weight to obtain a preliminary weighted value. And multiplying each preliminary weighting value by a dynamic adjustment factor to obtain a final weighted key characteristic value. This step is to adjust the feature values in real time in order to take into account the current environmental and process conditions.
And summing all weighted key characteristic values to obtain a total numerical value, namely the comprehensive quality index. This index reflects the performance of all key features in the current environment and process conditions in combination. Corresponding quality standards are set or obtained, and the standards can be common standards in the industry or standards formulated in the enterprise according to actual requirements. The calculated integrated quality index is compared with a quality standard. The result of the comparison may be a specific numerical difference or a ranking (e.g., "pass", "fail", "excellent", etc.). And the comparison result is output in a proper form, so that the comparison result is convenient for relevant personnel to look and understand. The output may be in the form of a report, chart, or other visualization tool. Interpretation of the comparison results, definition of the quality of the current product or service, and aspects that may require improvement or optimization. And according to the comparison result, making a corresponding improvement measure or optimization plan. Such measures may include adjusting process parameters, improving production environment, enhancing quality control, etc., which are repeated periodically to continuously monitor and improve the quality of the product or service.
In another preferred embodiment of the present invention, the quality determination is performed on the new data of the traditional Chinese medicine formula particles according to the comparison result, and if the integrated quality index is lower than the quality standard, the quality problem of the traditional Chinese medicine formula particles in the corresponding batch is determined, including:
And collecting relevant data of the new traditional Chinese medicine formula particles, including actual detection values of various key characteristics such as active ingredient content, dissolution speed, impurity content and the like, ensuring the accuracy and the integrity of the data, and carrying out necessary pretreatment such as cleaning, formatting and the like on the data. And calculating weighted key characteristic values by applying a previously determined weight and dynamic adjustment factor calculation formula and combining the newly collected data, and summing all the weighted key characteristic values to obtain the comprehensive quality index of the traditional Chinese medicine formula particles in the batch.
And consulting the related quality standard file or database to obtain the quality standard value of the traditional Chinese medicine formula particles. This criterion may be set according to historical data requirements and the calculated integrated quality index is compared with the acquired quality criterion. If the comprehensive quality index is lower than the quality standard, judging that the quality problem exists in the batch of traditional Chinese medicine formula particles, and if the comprehensive quality index meets or exceeds the quality standard, the quality of the batch of traditional Chinese medicine formula particles is qualified. Recording the judging result in a quality management system or a related document, and if a quality problem exists, immediately generating a quality report, and specifying the problem and possible reasons. For batches with quality problems, corresponding corrective measures, such as reworking, adjusting formulations, improving production processes, etc., are taken based on analysis in the quality report, the effect of the corrective measures is monitored, and necessary adjustments are made to ensure the quality of the subsequent production batches. Analyzing the reasons of quality problems, identifying weak links in the production process, and continuously improving the links, such as optimizing the production flow, improving the staff skills, updating equipment and the like.
In another preferred embodiment of the present invention, analyzing the weighted key feature values to obtain key features that negatively impact the composite quality index includes:
the method comprises the steps of carrying out data standardization processing on weighted eigenvalues to obtain standardized data, calculating statistics of each weighted eigenvalue in the standardized data, wherein the statistics comprise a mean value, a standard deviation, a median and a quartile, so as to know distribution conditions of the standardized data and change ranges of the eigenvalues, setting a threshold value based on the statistics and judging whether the weighted eigenvalues are abnormal, traversing all the weighted eigenvalues, comparing each weighted eigenvalue with the threshold value and marking abnormal weighted eigenvalues, removing the corresponding weighted eigenvalue from the standardized data for each weighted eigenvalue marked as abnormal, recalculating the comprehensive quality index based on the rest weighted eigenvalues, and comparing differences between original comprehensive quality indexes and the comprehensive quality indexes after abnormal characteristics are removed, wherein the method specifically comprises the following steps:
For each weighted eigenvalue, the overall mean and standard deviation are calculated first, and the z-score normalization method is used to subtract the mean from each weighted eigenvalue and then divide the mean by the standard deviation to obtain normalized data. For each weighted eigenvalue after normalization, calculating the mean and standard deviation to confirm whether the normalization process is correct (the mean should be close to 0 and the standard deviation should be close to 1 after normalization), calculating the median to know the central trend of the data, and calculating the quartiles (Q1, Q2, Q3) to identify the distribution range and potential outliers of the data. Based on the calculated statistics, particularly the quartiles, a threshold for outlier detection is set. For example, 1.5 times or 3 times of IQR (quarter bit distance, i.e., Q3-Q1) may be used as a criterion for outliers. Any weighted feature values below (Q1-1.5 xIQR) or above (Q3+1.5 xIQR) are considered anomalies. And traversing all the standardized weighted characteristic values, comparing each value with the set threshold value, and marking a certain weighted characteristic value as abnormal if the certain weighted characteristic value exceeds the threshold value range. And comparing the original comprehensive quality index with the comprehensive quality index calculated after removing the abnormal characteristics, analyzing the difference between the original comprehensive quality index and the comprehensive quality index, and knowing the influence degree of the abnormal characteristic value on the comprehensive quality index.
The method comprises the steps of sorting all the weighted feature values of the anomalies according to the influence degree of the comprehensive quality indexes, setting a negative influence threshold, wherein when the influence degree of the weighted feature values of the anomalies on the comprehensive quality indexes exceeds the negative influence threshold, the weighted feature values of the anomalies are regarded as key features which negatively influence the whole quality, and screening key features which exceed the negative influence threshold from a sorted weighted feature value list, wherein the key features comprise the following steps:
Ensuring that the anomaly detection of the weighted feature values has been completed and having a list recording all anomaly weighted feature values; for each anomaly weighted feature value in the list, calculating its degree of influence on the composite quality index by comparing the difference between the composite quality index containing the feature value and the composite quality index after removal of the feature value, and storing the degree of influence (difference) as an important attribute of the anomaly feature value. Each anomaly weighted feature value is ranked according to its degree of impact on the composite quality index, and the feature values are ranked in order of magnitude of impact using a suitable ranking algorithm (e.g., fast ranking, merge ranking, etc.). Based on historical data, industry specifications, or expert advice, a negative impact threshold is set that is used to determine whether the anomaly weighted feature value has a significant negative impact on overall body mass. Traversing the ordered abnormal weighted feature value list, comparing the influence degree of each feature value with a negative influence threshold, and if the influence degree of a certain feature value exceeds the negative influence threshold, considering the feature value as a key feature which negatively influences the overall quality, and independently listing the key features to form a new list or set.
In the embodiment of the invention, the method can accurately identify the key features which have negative influence on the comprehensive quality index by deeply analyzing the weighted key feature values. By carrying out data standardization processing on the weighted characteristic values, the influence of dimension and magnitude between different characteristic values is eliminated, so that comparability between the characteristic values is realized, and the accuracy and reliability of data analysis are improved. And calculating statistics (such as mean, standard deviation, median and quartile) of each weighted characteristic value in the standardized data, so as to be helpful for comprehensively understanding the distribution condition of the data and the variation range of the characteristic value. The threshold is set based on the statistics, and the abnormal weighted feature value can be automatically detected. This greatly improves the efficiency of data processing and reduces the likelihood of human error. By comparing the difference between the original comprehensive quality index and the comprehensive quality index after removing the abnormal features, the method can quantitatively evaluate the specific influence degree of each abnormal feature on the comprehensive quality. And ordering the weighted eigenvalues of all the anomalies according to the influence degree on the comprehensive quality index, thereby being beneficial to the enterprises to definitely improve the working priority. Enterprises can preferentially process key features with the greatest influence on the comprehensive quality index so as to realize the rapid improvement of the product quality. By setting the negative influence threshold, the screened key features can be ensured to have obvious negative influence on the whole quality. This avoids unnecessary improvement work and improves the efficiency of use of enterprise resources.
In another preferred embodiment of the present invention, locating problematic key nodes according to the weights and dynamic adjustment factors of the production lot information and key features includes:
for each production batch, multiplying the actual measured value of each key feature by the corresponding weight to obtain a weighted score, multiplying the weighted value by the corresponding dynamic adjustment factor to reflect the actual situation in the current production environment, comparing the weighted scores of different production batches to obtain a batch with abnormal score, analyzing each link in the production process of the batch including the quality of raw materials and the state of equipment according to the batch with abnormal score to obtain a production process analysis result, and positioning key nodes which lead to the reduction of the product quality according to the production process analysis and the weighted score, wherein the method comprises the following steps:
Collecting the actual measurement values of each key feature in each production batch to ensure that each key feature has a corresponding weight value, wherein the weight values reflect the importance of the feature to the product quality, acquiring or calculating a dynamic adjustment factor under the current production environment, multiplying the actual measurement value of each key feature by the corresponding weight for each production batch, adding the products to obtain a weighted score of the batch, multiplying the weighted score of each production batch by the corresponding dynamic adjustment factor to reflect the actual condition under the current production environment, comparing the adjusted weighted scores of all production batches to identify batches with abnormally high or abnormally low scores, and setting the threshold value of the abnormal score by using a statistical method (such as standard deviation, quartile and the like). For the batches with abnormal scores, various links in the production flow of the batches are deeply analyzed, including quality inspection records of raw materials, running state logs of equipment, skill level of operators and the like, and different points which possibly cause product quality degradation are found out by comparing production flow data of normal batches and abnormal batches.
And for the production process analysis, the key data such as raw material quality inspection reports, equipment maintenance records, operator logs and the like are particularly concerned. And (3) comparing the weighted scores of different batches, marking the batches with abnormally low scores or large fluctuation, wherein the batches possibly comprise quality problems, and preliminarily screening links with problematic production flow analysis results in the abnormal batches, such as raw material quality fluctuation, equipment fault records and the like.
For the problem links which are primarily screened, the relevance between the problem links and the weight score abnormality is further analyzed, for example, if a lot finds unstable quality in the raw material quality inspection link and the weight score of the lot is also abnormally low, the unstable quality of the raw material can be considered as a key node.
Through statistical analysis and expert evaluation, links which have obvious influence on the weighted score and do have problems in the production flow analysis are identified as key nodes, and possible key nodes include, but are not limited to, unstable quality of raw materials, performance degradation caused by equipment aging, improper operation, unreasonable process parameter setting and the like.
In the embodiment of the invention, the method can more accurately position the key nodes influencing the product quality by comprehensively considering the weight and the dynamic adjustment factor of the key features. This helps the enterprise to find and solve the problem rapidly, improves production efficiency and product quality. By comparing the weighted scores of different production batches, enterprises can more intelligently allocate resources, and more attention and resources are put into batches with abnormal scores and more problems, so that the utilization efficiency of the resources is improved. According to the method, through deep analysis of each link in the production flow, enterprises can know the influence of each link in the production process on the product quality more clearly, and the production flow is optimized. By locating key nodes that lead to product quality degradation, enterprises can more effectively conduct risk management and prevent potential product quality problems. The method not only helps the enterprise locate the existing problems, but also provides a framework for continuous improvement for the enterprise. By continuously collecting and analyzing production data, enterprises can continuously optimize the weights and dynamic adjustment factors of key features, thereby continuously improving the product quality and the production efficiency.
In another preferred embodiment of the present invention, the key nodes are connected in series with the production information of each link by the established quality tracing model to form a quality tracing chain, and the tracing result is obtained according to the quality tracing chain, including:
The production process is acquired and analyzed, the whole production process is known in detail, links such as raw material purchase, processing, quality inspection, packaging, storage, logistics and the like are included, input and output of each link and key control points are determined, and the key control points are recorded in a flow chart.
And identifying key nodes, and identifying and recording key nodes with great influence on the product quality, such as raw material acceptance, key process steps, important quality inspection links and the like, so as to ensure that each key node has clear definition and identification. The data structure is designed and associated, and according to key nodes and business processes, reasonable data structures are designed to store related information such as raw material batches, production dates, process parameters, quality inspection results and the like, and data of all links are associated by utilizing unique identifiers (such as batch numbers and serial numbers) of products, so that consistency and traceability of the data are ensured.
A data acquisition and transmission system is established, data acquisition points are arranged at each key node, and data are accurately acquired in real time by utilizing an automatic means (such as bar code technology, RFID labels, sensors and the like), so that the high efficiency and accuracy of data acquisition are ensured, and human errors are reduced. And constructing a database and a traceability system, constructing a safe and reliable database to store and manage traceability data, developing a user-friendly query interface and interface, and supporting quick query of traceability information through a product identifier. According to actual requirements, accurate traceable query conditions, such as product batch numbers, production dates, quality problem types and the like, are set, so that the query conditions can be accurately matched with products or production links needing traceability.
Executing a traceback query:
The method comprises the steps of inputting a set query condition in a quality tracing system, rapidly positioning related key nodes and production information in a quality tracing chain according to the query condition, displaying a tracing result in an intuitive mode (such as a table, a chart or a report) by the system, wherein the tracing result comprises detailed data of the key nodes and associated information of production links, and analyzing the tracing result by a user to determine the root cause and the influence range of a product quality problem. And (3) according to the analysis result, making corresponding improvement measures and prevention plans so as to improve the product quality and the production efficiency, feeding the improvement measures back to the production flow, and continuously perfecting and optimizing a quality traceability model.
The quality tracing system is evaluated and optimized regularly, the change of the production flow and new tracing requirements are guaranteed to be adapted, the data acquisition and transmission conditions of key nodes are monitored, the real-time performance and accuracy of the data are guaranteed, staff are trained regularly, and the proficiency and efficiency of the quality tracing system are improved.
As shown in fig. 2, the embodiment of the invention further provides a method for tracing the quality of the traditional Chinese medicine formula particles based on data fusion, which comprises the following steps:
Collecting parameter data of traditional Chinese medicine formula particles in various links of production, processing, transportation, storage and sales;
preprocessing the parameter data to obtain preprocessed data;
extracting key characteristics related to the quality of the traditional Chinese medicine formula particles from the pretreatment data;
The method comprises the steps of obtaining historical data, distributing a weight for each key feature, defining a dynamic adjustment factor according to actual conditions, multiplying the actual value of each key feature with the weight corresponding to the actual value and the dynamic adjustment factor to obtain a weighted key feature value, summing all weighted key feature values to obtain a comprehensive quality index, and comparing the comprehensive quality index with a corresponding quality standard to obtain a comparison result;
According to the comparison result, carrying out quality judgment on new traditional Chinese medicine formula particle data, if the comprehensive quality index is lower than a quality standard, judging that the traditional Chinese medicine formula particle of the corresponding batch has quality problems;
And connecting the key nodes with the production information of each link in series through the established quality tracing model to form a quality tracing chain, and obtaining a tracing result according to the quality tracing chain.
It is noted that the system is a system corresponding to the above method, and all implementation manners in the above method embodiment are applicable to the embodiment, so that the same technical effect can be achieved.
Embodiments of the invention also provide a computing device comprising a processor, a memory storing a computer program which, when executed by the processor, performs a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411675974.XA CN119204835A (en) | 2024-11-22 | 2024-11-22 | Quality traceability system of traditional Chinese medicine granules based on data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411675974.XA CN119204835A (en) | 2024-11-22 | 2024-11-22 | Quality traceability system of traditional Chinese medicine granules based on data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119204835A true CN119204835A (en) | 2024-12-27 |
Family
ID=94061005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411675974.XA Pending CN119204835A (en) | 2024-11-22 | 2024-11-22 | Quality traceability system of traditional Chinese medicine granules based on data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119204835A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119557779A (en) * | 2025-01-24 | 2025-03-04 | 珠海飞企耀点科技有限公司 | A pharmaceutical quality management method and system based on big data and artificial intelligence |
| CN119863096A (en) * | 2025-03-21 | 2025-04-22 | 深圳市雄毅华绝缘材料有限公司 | Epoxy plate batch traceable management method and system for lithium battery packaging |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082394A1 (en) * | 2019-10-30 | 2021-05-06 | 南京智慧航空研究院有限公司 | Layout-variable taxiing-out time prediction system based on big data deep learning |
| CN117899163A (en) * | 2024-01-15 | 2024-04-19 | 沈阳药科大学 | Extraction method of effective ingredients of traditional Chinese medicine composition for treating knee osteoarthritis based on entropy weight method and response surface methodology |
| CN117993933A (en) * | 2024-01-25 | 2024-05-07 | 浙江大学 | Evaluation method based on tobacco leaf logistics full life cycle traceability system |
| CN118446096A (en) * | 2024-05-09 | 2024-08-06 | 安徽理工大学 | Adaptive mine fan mesh operation ventilation system optimization adjustment method and device |
| CN118462508A (en) * | 2024-07-11 | 2024-08-09 | 威海朗盛新能源科技有限公司 | Fatigue life prediction method and system for wind turbine blade |
| CN118803906A (en) * | 2024-01-02 | 2024-10-18 | 中国移动通信集团湖南有限公司 | Data processing method, device and electronic equipment |
-
2024
- 2024-11-22 CN CN202411675974.XA patent/CN119204835A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082394A1 (en) * | 2019-10-30 | 2021-05-06 | 南京智慧航空研究院有限公司 | Layout-variable taxiing-out time prediction system based on big data deep learning |
| CN118803906A (en) * | 2024-01-02 | 2024-10-18 | 中国移动通信集团湖南有限公司 | Data processing method, device and electronic equipment |
| CN117899163A (en) * | 2024-01-15 | 2024-04-19 | 沈阳药科大学 | Extraction method of effective ingredients of traditional Chinese medicine composition for treating knee osteoarthritis based on entropy weight method and response surface methodology |
| CN117993933A (en) * | 2024-01-25 | 2024-05-07 | 浙江大学 | Evaluation method based on tobacco leaf logistics full life cycle traceability system |
| CN118446096A (en) * | 2024-05-09 | 2024-08-06 | 安徽理工大学 | Adaptive mine fan mesh operation ventilation system optimization adjustment method and device |
| CN118462508A (en) * | 2024-07-11 | 2024-08-09 | 威海朗盛新能源科技有限公司 | Fatigue life prediction method and system for wind turbine blade |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119557779A (en) * | 2025-01-24 | 2025-03-04 | 珠海飞企耀点科技有限公司 | A pharmaceutical quality management method and system based on big data and artificial intelligence |
| CN119863096A (en) * | 2025-03-21 | 2025-04-22 | 深圳市雄毅华绝缘材料有限公司 | Epoxy plate batch traceable management method and system for lithium battery packaging |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119204835A (en) | Quality traceability system of traditional Chinese medicine granules based on data fusion | |
| CN118011990B (en) | Industrial data quality monitoring and improving system based on artificial intelligence | |
| CN116308211A (en) | Enterprise intelligent management system and method based on big data | |
| CN118469405B (en) | Processing method, device, equipment and storage medium for household supply chain data | |
| CN116523442B (en) | Production process digital management system and method for paint | |
| CN118761745B (en) | OA collaborative workflow optimization method applied to enterprise | |
| CN119151297B (en) | A project execution risk assessment system and method based on data mining | |
| CN112884212A (en) | Cigarette single gram weight deviation analysis and prediction method | |
| CN117541057A (en) | Enterprise operation early warning monitoring method and system based on data analysis | |
| CN118586765A (en) | A quality management risk control method and system based on big data | |
| CN118114023A (en) | Pharmaceutical production line state monitoring and alarming method and system based on Internet of things | |
| CN118485465A (en) | Agricultural wholesale market product sales forecasting and analysis system and method based on artificial intelligence | |
| CN118863552B (en) | A risk early warning method and system based on food business risk information database | |
| CN118917390B (en) | Service knowledge base management system and method based on knowledge big model | |
| CN119273296A (en) | Safety inspection method and system applied to project management | |
| CN119228397A (en) | Organic fertilizer quality and safety traceability management method based on multi-source data | |
| CN119476697A (en) | An innovation achievement evaluation system based on big data | |
| CN117893019A (en) | Launch enterprise information management and control system and operational risk management methods | |
| CN117290183A (en) | ETL-based cross-system exception monitoring processing method and device | |
| CN117172721A (en) | Data flow supervision early warning method and system for financing service | |
| JP4853373B2 (en) | Inspection product selection method and inspection product selection program | |
| CN118400396B (en) | Industrial Internet security monitoring method and system based on big data | |
| CN120278727A (en) | Food safety traceability method and system based on multi-source monitoring | |
| CN120297910A (en) | A full-process traceability management system for work order audit based on big data | |
| CN120106811A (en) | Method and system based on efficient nuclear power plant work order processing algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |