Product quality tracing processing method and device, equipment and storage medium

Abstract

The invention provides a product quality tracing processing method and device, equipment and a storage medium. The method comprises the following steps: displaying a product quality tracing model of any product; generating a corresponding query condition in response to a query operation on any to-be-traced production link in the product quality traceability model; obtaining a tracing data preview table corresponding to the to-be-traced production link according to the query condition, wherein the tracing data preview table comprises a plurality of corresponding production batches; in response to any batch of click operation in the tracing data preview table, displaying a corresponding target data display chart, the target data display chart being generated according to the corresponding data display chart; if it is judged that no abnormal data exists in the production link to be traced according to the target data display chart, it is determined that the product quality is normal, and errors and omission of product quality tracing processing are avoided.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a product quality traceability processing method, device, equipment and storage medium. Background Art

[0002] With the continuous development of industrial level, the control of product quality management is becoming increasingly strict. In order to further improve the quality of product production and realize the whole process control of quality management, all-round monitoring is carried out from the entire production life cycle of the product, so as to timely carry out product quality traceability and subsequent quality management.

[0003] In the prior art, traditional product quality traceability processing methods usually collect and process production data of one or more production links through manual spot checks, so as to determine whether the production data is abnormal in order to facilitate subsequent product quality management.

[0004] However, in the prior art, traditional product quality traceability processing methods mainly rely on manual recording of production data of one or more production links, and manual judgment of whether the production data is abnormal, which is prone to errors and omissions in product quality traceability. Summary of the invention

[0005] The present application provides a product quality traceability processing method, device, equipment and storage medium to solve the problem that traditional product quality traceability processing methods manually record production data of one or more production links and manually determine whether the production data is abnormal, which is prone to errors and omissions in product quality traceability.

[0006] In a first aspect, the present application provides a product quality traceability processing method, which is applied to a computer device, comprising:

[0007] Display a product quality traceability model for any product, wherein the product quality traceability model includes multiple production links to be traced for the product; wherein each production link to be traced corresponds to a pre-created data display chart;

[0008] In response to a query operation on any production link to be traced in the product quality traceability model, generating a corresponding query condition;

[0009] Acquire a traceability data preview table corresponding to the production link to be traced according to the query condition, wherein the traceability data preview table includes corresponding multiple production batches;

[0010] In response to a click operation on any batch in the traceability data preview table, a corresponding target data display chart is displayed, wherein the target data display chart is generated according to the corresponding data display chart;

[0011] If it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, it is determined that the product quality is normal.

[0012] In a possible design, the target data display chart includes a target visualization chart and / or a target control chart; accordingly, if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, then the product quality is determined to be normal, including: if it is determined according to the target visualization chart that there is no abnormal data in the production link to be traced, then the product quality is determined to be normal; or, if it is determined according to the target control chart that there is no abnormal data in the production link to be traced, then the product quality is determined to be normal; or, if it is determined according to the target visualization chart and the target control chart that there is no abnormal data in the production link to be traced, then the product quality is determined to be normal.

[0013] In a possible design, if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, then the product quality is determined to be normal, including: calculating the difference rates between each actual value in the target visualization chart and each corresponding pre-generated expected value; if each difference rate is less than a preset difference threshold, it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

[0014] In a possible design, if it is determined according to the target visualization chart that there is no abnormal data in the production link to be traced, then the product quality is determined to be normal, including: in the target control chart, if there is no preset number of consecutive numerical points exceeding a preset center line, then it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

[0015] In a possible design, if it is determined according to the target visualization chart and the target control chart that there is no abnormal data in each production link to be traced, then the product quality is determined to be normal, including: calculating the difference rates between each actual value in the target visualization chart and each corresponding pre-generated expected value; if each difference rate is less than a preset difference threshold, and / or there is no preset number of consecutive numerical points exceeding a preset center line, then it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

[0016] In one possible design, the data display chart includes a visualization chart; accordingly, the process of creating the visualization chart includes: associating a preset table class component with a pre-generated data set to obtain an associated table class component; inputting each pre-generated expected value into the associated table class component, and corresponding them with the actual values ​​in the data set to obtain a final table class component; and determining the final table class component as the visualization chart.

[0017] In one possible design, the process of generating the data set includes: in response to the operation of filling in database information in the data source interface, obtaining the corresponding data source; and in response to the operation of filling in configuration information in the data set configuration interface, generating the corresponding data set configuration table; binding the data set configuration table to the data source to generate a data set; accordingly, the process of generating each expected value includes: obtaining each production data in the data set, and dividing the each production data into a training set and a calculation set according to a preset ratio; inputting the calculation set into a trained machine learning model for processing to obtain each expected value, wherein the trained machine learning model is trained based on the training set.

[0018] In a second aspect, the present application provides a product quality tracing processing device, which is applied to a computer device, including:

[0019] A first display module is used to display a product quality traceability model of any product, wherein the product quality traceability model includes a plurality of production links to be traced of the product; wherein each production link to be traced corresponds to a pre-created data display chart;

[0020] A first generating module, configured to generate corresponding query conditions in response to a query operation on any production link to be traced in the product quality traceability model;

[0021] A first acquisition module is used to acquire a traceability data preview table corresponding to the production link to be traced according to the query condition, wherein the traceability data preview table includes corresponding multiple production batches;

[0022] A second display module is used to display a corresponding target data display chart in response to a click operation on any batch in the traceability data preview table, wherein the target data display chart is generated according to the corresponding data display chart;

[0023] The first determination module is used to determine that the product quality is normal if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced.

[0024] In a third aspect, the present application provides a computer device, comprising: at least one processor and a memory;

[0025] The memory stores computer-executable instructions;

[0026] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the product quality traceability processing method described in the first aspect and various possible designs of the first aspect.

[0027] In a fourth aspect, the present application provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the product quality traceability processing method described in the first aspect and various possible designs of the first aspect is implemented.

[0028] The product quality tracing processing method, device, equipment and storage medium provided by the present application display a product quality tracing model of any product, wherein the product quality tracing model includes multiple production links to be traced of the product; wherein each production link to be traced corresponds to a pre-created data display chart; in response to a query operation on any production link to be traced in the product quality tracing model, generate a corresponding query condition; obtain a traceability data preview table corresponding to the production link to be traced according to the query condition, wherein the traceability data preview table includes corresponding multiple production batches; in response to a click operation on any batch in the traceability data preview table, display a corresponding target data display chart, wherein the target data display chart is generated according to the corresponding data display chart; if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, then it is determined that the product quality is normal, thereby reducing the manual workload and avoiding errors and omissions in product quality tracing processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0030] Figure 1 A schematic diagram of an application scenario of the product quality tracing processing method provided in an embodiment of the present application;

[0031] Figure 2 Schematic diagram of the product quality tracing method provided in the embodiment of the present application Figure 1 ;

[0032] Figure 3 A schematic diagram of a product quality traceability model provided in an embodiment of the present application;

[0033] Figure 4 Schematic diagram of the product quality tracing method provided in the embodiment of the present application Figure 2 ;

[0034] Figure 5 A schematic diagram of the structure of a product quality tracing processing device provided in an embodiment of the present application;

[0035] Figure 6A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] With the continuous development of industrial level, the control of product quality management is becoming increasingly strict. In order to further improve the quality of product production and realize the whole process control of quality management, all-round monitoring is carried out from the entire production life cycle of the product, and every production link from raw materials to final products is recorded and tracked to ensure the compliance, quality controllability and safety of the product. This method assigns a unique serial number or identifier to each product, records key information such as raw material supplier, production date, production process, etc., so as to trace back to a specific batch of products. In the prior art, the traditional product quality traceability processing method usually collects and processes the production data of one or more production links through manual spot checks, so as to determine whether the production data is abnormal, so as to facilitate the quality management of subsequent products. However, in the prior art, the traditional product quality traceability processing method mainly relies on manual recording of production data of one or more production links, and manual judgment of whether the production data is abnormal, which is prone to errors and omissions in product quality traceability.

[0038] In order to solve the above technical problems, the embodiments of the present application propose the following technical concepts: the inventors have taken into account the problem that errors and omissions are prone to occur in manual product quality tracing, and based on the product quality tracing model and query conditions, obtain a traceability data preview table corresponding to each production link to be traced, and use the query conditions and the data display charts created according to each production link to be traced to obtain each target data display chart, and call the corresponding target data display chart to determine whether there is abnormal data in the production link to be traced, so as to determine that the product quality is normal. The product quality is traced by the equipment, which reduces the manual workload and avoids errors and omissions in product quality tracing.

[0039] Figure 1 It is a schematic diagram of an application scenario of the product quality traceability processing method provided in an embodiment of the present application.

[0040] like Figure 1 As shown, the scene includes: a display terminal 101 and a computer device 102 .

[0041] The display terminal 101 may be a display screen or a terminal such as a personal computer.

[0042] The computer device 102 may be an independent device or a cluster consisting of multiple devices.

[0043] The display terminal 101 displays the product quality traceability model of any product and is interconnected with the computer device 102 through a wireless network. The computer device 102 generates corresponding query conditions in response to a query operation on any production link to be traced in the product quality traceability model; obtains a traceability data preview table corresponding to the production link to be traced according to the query conditions; displays the corresponding target data display chart on the display terminal 101 in response to a click operation on any batch in the traceability data preview table; if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, it is determined that the product quality is normal. The following is a detailed description using a detailed embodiment.

[0044] Figure 2 Schematic diagram of the product quality tracing method provided in the embodiment of the present application Figure 1 , the execution subject of this embodiment can be Figure 1 The computer device in the embodiment shown is not particularly limited in this embodiment. Figure 2 As shown, the method includes:

[0045] S201: Displaying a product quality traceability model of any product, wherein the product quality traceability model includes multiple production links to be traced of the product; wherein each production link to be traced corresponds to a pre-created data display chart.

[0046] In this embodiment, the product may be food, electronic product or other product; illustratively, the product may be milk.

[0047] In this embodiment, if Figure 3 The product quality traceability model is shown, which can be exemplified as a milk quality traceability model.

[0048] in, Figure 3 ① represents a query condition.

[0049] In addition, the creation process of the product quality traceability model specifically includes a~b:

[0050] Step a: Perform field configuration and parameter configuration for each production link to obtain a configured production link.

[0051] In this embodiment, the field is configured as the name of the production link, and the parameter is configured as the start time and end time of the production link.

[0052] Step b: Perform association configuration for each production link to obtain a complete product quality traceability model.

[0053] In this embodiment, the data display chart includes a visualization chart; accordingly, the process of creating the visualization chart in step S201 specifically includes:

[0054] S2011: Associating the preset table class component with the pre-generated data set to obtain an associated table class component.

[0055] Specifically, the process of generating the data set in step S2011 includes:

[0056] S20111: In response to the operation of filling in the database information in the data source interface, the corresponding data source is obtained.

[0057] In this embodiment, the database information may include name, database, address, port, account number and password, and may also include other information.

[0058] The database may be MySQL or other databases.

[0059] Exemplarily, the name is MI database.

[0060] S20112: In response to the filling operation of the configuration information in the data set configuration interface, a corresponding data set configuration table is generated.

[0061] In this embodiment, the configuration information may include a name, description, data source, type, statement, and parameter settings.

[0062] The type can be a SQL statement, or a data table, a view, a stored procedure, or other types; accordingly, the statement corresponds to an SQL statement.

[0063] Exemplarily, the data source is an MI database.

[0064] S20113: Bind the dataset configuration table to the data source to generate a dataset.

[0065] Exemplarily, the data set configuration table is bound to the data source through the name MI database in the data source and the data source MI database in the corresponding data set configuration table to generate a data set.

[0066] In addition, the data set also includes field information, where the field information is information such as the header name and type of each column of data in the data set.

[0067] S2012: Input the pre-generated expected value into the associated table class component, and correspond it with the actual value in the data set to obtain the final table class component.

[0068] In this embodiment, the pre-generated expected value and actual value are two columns of data and correspond to each other.

[0069] Specifically, the process of generating the expected value in step S2012 includes:

[0070] S20121: Acquire each production data in the data set, and divide each production data into a training set and a calculation set according to a preset ratio.

[0071] In this embodiment, the preset ratio may be any ratio of 7:3, 8:2 or 9:1, or other ratios.

[0072] S20122: Input the calculation set into a trained machine learning model for processing to obtain an expected value, wherein the trained machine learning model is trained based on the training set.

[0073] Specifically, the training process of the machine learning model in step S20122 specifically includes:

[0074] S201221: Perform data description processing on the training set to obtain first processed data.

[0075] In this embodiment, the data description process is to perform statistical analysis on each column of data in the table, and initially obtain basic data such as mean, variance, maximum, minimum, sum, and missing items to determine whether the training set data is classified as discrete or labeled.

[0076] S201222: Perform outlier analysis on the first processed data to obtain second processed data.

[0077] In this embodiment, the outlier analysis process uses a variance algorithm to determine whether the first processed data contains abnormal data; if the abnormal data is caused by noise or errors, it will have a significant impact on the stability of the data and the abnormal data needs to be recalculated and filled.

[0078] S201223: Perform missing value analysis on the second processed data to obtain third processed data.

[0079] In this embodiment, the missing value analysis process is used to fill in the empty values ​​of the second processed data, and the random forest algorithm is used to effectively make the data transition smoothly without affecting the overall fluctuation.

[0080] S201224: Perform feature analysis on the third processed data to obtain fourth processed data.

[0081] In this embodiment, the feature analysis process is used to analyze the features of all columns in the data table of the third processed data, which can be considered as a calculation of the weights affecting the overall data, and the weight calculation is performed according to the chi-square correlation algorithm and the Pearson correlation algorithm to obtain the weight norm.

[0082] S201225: Subject the fourth processed data to multiple machine learning model evaluations to determine scores of the multiple machine learning models.

[0083] Specifically, step S501225 is as follows: each machine learning model evaluation is configured with different algorithms, such as random forest, SVM, decision tree and dozens of other different algorithms, and then the fourth processed data is imported into each machine learning model in turn for calculation, and finally each machine learning model is evaluated according to the F1 score algorithm to determine the scores of multiple machine learning models.

[0084] S201226: Determine the machine learning model with the highest score as the trained machine learning model.

[0085] S2013: Determine the final table class component as a visual chart.

[0086] Exemplarily, the visualization chart includes parameters such as milk weight, temperature, batch, production time, and person in charge.

[0087] In this embodiment, the data display chart includes a control chart; accordingly, the process of creating the control chart in step S201 specifically includes:

[0088] S2014: Create an initial control chart, and associate the initial control chart with the pre-generated data set to obtain an associated initial control chart.

[0089] S2015: Performing multiple types of data configuration on the associated initial control chart to obtain a control chart.

[0090] In this embodiment, the multiple types of data configurations may include subgroup type, subgroup length, difference judgment rules, control indicator (specification line and control line) settings, query fields and X-axis scales, and may also include other data configurations.

[0091] The subgroup is a collection of one or more values ​​of each column value in the data set, the subgroup type is the corresponding data type, and the subgroup length is the corresponding data length.

[0092] The abnormality judgment rule may be that when tracing back the data preview table, if a preset number of consecutive points are all decreasing or all increasing, the tracing back data preview table is judged to be abnormal, wherein the range of the preset number is [5, 8]; or it may be that when tracing back the data preview table, if a preset number of consecutive points are staggered up and down, the tracing back data preview table is judged to be abnormal, wherein the range of the preset number is [12, 14].

[0093] Among them, the control indicators (specification lines and control lines) need to be set according to actual conditions.

[0094] Among them, the query field corresponds to the query condition.

[0095] The X-axis scale needs to be generated according to the query condition. When the query condition is a time period, the X-axis scale is the time of the time period.

[0096] Exemplarily, the control chart includes milk temperature, batch, and inspector, wherein the batch can be used as a corresponding point in the control chart.

[0097] S202: In response to a query operation on any production link to be traced in the product quality traceability model, a corresponding query condition is generated.

[0098] In this embodiment, the query condition may be a preset time period, batch or other conditions.

[0099] Exemplarily, the query condition is a preset time period.

[0100] Exemplarily, the production link to be traced can be determined as milk powder fat testing.

[0101] In addition, two Tab labels are created based on milk powder fat detection, where each Tab label is bound to a visualization chart and / or SPC control chart.

[0102] S203: Obtain a traceability data preview table corresponding to the production link to be traced according to the query conditions, wherein the traceability data preview table includes corresponding multiple production batches.

[0103] For example, taking milk powder fat testing as an example, the structure of the traceability data preview table includes: the start time and end time of the milk powder fat testing within the preset time period, the batch and batch number of the milk powder fat testing, the links of each batch, the amount of milk in each batch, and the test temperature.

[0104] S204: In response to a click operation on any batch in the traceability data preview table, a corresponding target data display chart is displayed, wherein the target data display chart is generated according to the corresponding data display chart.

[0105] S205: If it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, it is determined that the product quality is normal.

[0106] Exemplarily, if it is determined that there is no abnormal data in the milk powder fat test based on the target visualization chart and / or the target control chart, it is determined that the product quality is normal.

[0107] Among them, confirming that the product quality is normal can be done through pop-up windows or direct display.

[0108] In addition, if it is determined that there are abnormal data in the milk powder fat test, the abnormal part will be marked in red.

[0109] Exemplarily, based on S2012, if the difference ratio between the actual value of a point in the target visualization chart and the corresponding expected value exceeds a preset ratio, the traceability data preview table corresponding to the milk powder fat test is determined to be abnormal, and the abnormal part is marked in red.

[0110] The preset ratio may be a ratio trend or an actual value; if the preset ratio is an actual value, it may be any value among 5%, 10% or 15%, or other values.

[0111] In addition, based on step S202, a Tab label may be clicked to switch between the target visualization chart and the target control chart.

[0112] In summary, the product quality traceability processing method provided in the present embodiment displays a product quality traceability model of any product, wherein the product quality traceability model includes multiple production links to be traced of the product; wherein each production link to be traced corresponds to a pre-created data display chart; in response to a query operation on any production link to be traced in the product quality traceability model, a corresponding query condition is generated; according to the query condition, a traceability data preview table corresponding to the production link to be traced is obtained, wherein the traceability data preview table includes corresponding multiple production batches; in response to a click operation on any batch in the traceability data preview table, a corresponding target data display chart is displayed, wherein the target data display chart is generated based on the corresponding data display chart; if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, then it is determined that the product quality is normal, thereby reducing the manual workload and avoiding errors and omissions in product quality traceability processing.

[0113] In addition, the product quality tracing method provided in this embodiment can timely perform product quality tracing according to actual conditions, and take corrective measures in a timely manner to avoid the expansion of quality problems.

[0114] In addition, the product quality traceability processing method provided in this embodiment can reduce or increase the granularity of the comparison by comparing one or more data in a single or different batches through a target visualization chart, so that the product quality traceability processing can be flexibly adjusted according to different usage scenarios.

[0115] Figure 4 Schematic diagram of the product quality tracing method provided in the embodiment of the present application Figure 2 In the embodiment of the present application, Figure 2 Based on the provided embodiment, a specific implementation method for determining that the product quality is normal if the target data display chart determines that there is no abnormal data in the production link to be traced in S205 is described in detail, wherein the target data display chart includes a target visualization chart and / or a target control chart. Figure 4 As shown, the method includes:

[0116] S401: If it is determined according to the target visualization chart that there is no abnormal data in the production link to be traced, it is determined that the product quality is normal; or,

[0117] Specifically, step S401 includes:

[0118] S4011: Calculate the difference rates between each actual value in the target visualization chart and each corresponding pre-generated expected value.

[0119] In this embodiment, the calculation formula for calculating the difference rate between each actual value in the target visualization chart and each corresponding pre-generated expected value is:

[0120]

[0121] In the formula, DIF is the difference rate; X is the actual value; Y is the corresponding expected value.

[0122] S4012: If each difference rate is less than the preset difference threshold, it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

[0123] In this embodiment, the preset difference threshold may be any value among 20%, 30% or 50%, or other values.

[0124] S402: If it is determined according to the target control chart that there is no abnormal data in the production link to be traced, it is determined that the product quality is normal; or,

[0125] Specifically, step S402 specifically includes: in the target control chart, if there is no preset number of consecutive numerical points exceeding the preset center line, it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

[0126] In this embodiment, the preset number may be any number of 1, 2, or 3, or any other number.

[0127] In this embodiment, the preset center line may be automatically generated or manually set.

[0128] Specifically, step S402 includes the following situations:

[0129] In any target control chart of the traceability data preview table, determine whether there is a numerical point that exceeds the preset center line by K standard deviations, where the value range of K is [1, 6].

[0130] In any target control chart of the traceability data preview table, determine whether there are K consecutive numerical points on the same side of the preset center line, where the value range of K is [7, 11].

[0131] In any target control chart of the traceability data preview table, determine whether there are K+1 consecutive numerical points whose distance from the preset center line is greater than 2 standard deviations, where the value range of K is [2, 4].

[0132] In any target control chart of the traceability data preview table, determine whether there are K value points among K+1 consecutive value points whose distance from the preset center line is greater than 1 standard deviation, where the value range of K is [32, 6].

[0133] In any target control chart of the traceability data preview table, determine whether there are K consecutive numerical points within 1 standard deviation of the preset center line, where the value range of K is [12, 15].

[0134] In any target control chart of the traceability data preview table, determine whether there are K consecutive numerical points whose distance from the preset center line is greater than 1 standard deviation, where the value range of K is [6, 10].

[0135] S403: If it is determined that there is no abnormal data in the production link to be traced based on the target visualization chart and the target control chart, it is determined that the product quality is normal.

[0136] Specifically, step S403 includes:

[0137] S4031: Calculate the difference rates between each actual value in the target visualization chart and each corresponding pre-generated expected value.

[0138] In this embodiment, the discussion on the difference rate has been described in detail in step S4011 and will not be repeated here.

[0139] S4032: If each difference rate is less than a preset difference threshold, and / or there is no preset number of consecutive numerical points exceeding a preset center line, it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

[0140] Exemplarily, if each difference rate is less than 20%, and / or any of the situations in step S402 does not exist, it is determined that there is no abnormal data in the traceability data preview table.

[0141] In summary, the product quality traceability processing method provided in this embodiment determines that the product quality is normal if it is determined that there is no abnormal data in the production link to be traced according to the target visualization chart; or, if it is determined that there is no abnormal data in the production link to be traced according to the target control chart, the product quality is determined to be normal; or, if it is determined that there is no abnormal data in the production link to be traced according to the target visualization chart and the target control chart, the product quality is determined to be normal, making the product quality traceability processing more reasonable and accurate.

[0142] In addition, by using different methods in different scenarios to determine whether each traceability data preview table is abnormal, it can meet the complex quality control needs in the modern production environment and capture potential quality problems of the product in a timely manner.

[0143] It should be noted that this application proposes a B / S-side overall architecture based on quality traceability, including UI layer, service layer, cache layer and storage layer. The system supports data access in two ways: relational database and API. Through machine learning data analysis, visualization charts, SPC control charts, quality traceability and other processes, it provides data analysis and decision-making basis for product industrial production.

[0144] Among them, the UI layer is used to interact with the user. When the interaction is triggered, the interface request is made in a front-end and back-end separation manner, and the data is rendered after the back-end responds. By determining multiple production links to be traced for any product, and creating corresponding data display charts for each production link to be traced; in response to the query operation of multiple production links to be traced in the displayed product quality traceability model, corresponding query dialog boxes are generated; in response to the filling operation of each query dialog box, each query condition is generated; according to each query condition, the traceability data preview table corresponding to each production link to be traced is obtained; according to each query condition, the corresponding target data display charts are determined from each data display chart; in response to the call operation of any traceability data preview table, the corresponding target data display chart is called; according to each target data display chart, it is determined whether there is abnormal data in the corresponding traceability data preview table, so as to output an early warning prompt or a product quality traceability completion prompt.

[0145] Among them, the service layer is used to interact with the front-end UI layer, and provides all the interfaces required by the front-end UI layer, including configuration analysis, user permissions, data extraction, machine learning data processing, data discrimination, operation logs, and data source connection related services and interfaces. In the service layer, the core part is data processing. Basic data calculations such as aggregation and row and column conversion are completed by databases or spark, which are generally common in various visualization charts, while algorithms and data deep mining such as correlation analysis, discrete data analysis, and random forest filling data are completed by machine learning. Among them, the underlying set of machine learning is developed in combination with frameworks such as pandas, numpy, and sklean, covering dozens of model training algorithms.

[0146] The cache layer is used to store temporary system data and login passwords to avoid excessive database load pressure due to frequent database access. Since the cache layer has extremely fast read and write speeds, it is also used to store temporary data to improve system concurrency performance. The system supports three cache methods: JVM memory, Redis, and Spark. JVM memory stores temporary variables and constants generated by system operation, Redis stores temporary data and passwords, and Spark stores data in the DataFrame data format, combined with Spark's own computing engine for data computing and analysis.

[0147] The storage layer stores the operation information of the quality management system and the user's configuration information. The storage medium is a MySQL database, which ensures the permanent storage of information, prevents the loss of configuration information, and is also conducive to the subsequent migration of the system. At the same time, the expected value calculated by the machine learning model can also be inserted into the specified table of the database through the storage layer for data visualization.

[0148] Figure 5 This is a schematic diagram of the structure of the product quality tracing processing device provided in the embodiment of the present application. Figure 5 As shown, the product quality tracing processing device includes: a first display module 501 , a first generating module 502 , a first acquiring module 503 , a second display module 504 and a first determining module 505 .

[0149] The first display module 501 is used to display a product quality traceability model of any product, wherein the product quality traceability model includes multiple production links to be traced of the product; wherein each production link to be traced corresponds to a pre-created data display chart;

[0150] A first generating module 502, for generating corresponding query conditions in response to a query operation on any production link to be traced in the product quality traceability model;

[0151] A first acquisition module 503 is used to acquire a traceability data preview table corresponding to the production link to be traced according to the query condition, wherein the traceability data preview table includes corresponding multiple production batches;

[0152] A second display module 504 is used to display a corresponding target data display chart in response to a click operation on any batch in the traceability data preview table, wherein the target data display chart is generated according to the corresponding data display chart;

[0153] The first determination module 505 is used to determine that the product quality is normal if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced.

[0154] In a possible implementation, the target data display chart includes a target visualization chart and / or a target control chart; accordingly, the determination module 505 specifically includes:

[0155] The first determination unit 5051 is configured to determine that the product quality is normal if it is determined according to the target visualization chart that there is no abnormal data in the production link to be traced; or

[0156] The second determination unit 5052 is configured to determine that the product quality is normal if it is determined according to the target control chart that there is no abnormal data in the production link to be traced; or

[0157] The third determination unit 5053 is used to determine that the product quality is normal if it is determined that there is no abnormal data in the production link to be traced according to the target visualization chart and the target control chart.

[0158] In a possible implementation, the first determining unit 5051 specifically includes:

[0159] A calculation module 50511 is used to calculate the difference rates between the actual values ​​in the target visualization chart and the corresponding pre-generated expected values;

[0160] The determination module 50512 is used to determine that there is no abnormal data in the production link to be traced if the difference rates are less than a preset difference threshold, so as to determine that the product quality is normal.

[0161] In a possible implementation, the second determination unit 5052 is specifically used to: in the target control chart, if there are no preset number of consecutive numerical points exceeding a preset center line, determine that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

[0162] In a possible implementation, the third determining unit 5053 specifically includes:

[0163] A calculation unit 50531 is used to calculate the difference rates between the actual values ​​in the target visualization chart and the corresponding pre-generated expected values;

[0164] The determination unit 50532 is used to determine that there is no abnormal data in the production link to be traced if the difference rates are less than a preset difference threshold, and / or there is no preset number of consecutive numerical points exceeding a preset center line, so as to determine that the product quality is normal.

[0165] In a possible implementation, the data display chart includes a visualization chart; accordingly, the device further includes:

[0166] An association module 506 is used to associate the preset table class component with the pre-generated data set to obtain an associated table class component;

[0167] A first input module 507, used to input the pre-generated expected value into the associated table class component, and correspond it with the actual value in the data set to obtain a final table class component;

[0168] The second determining module 508 is configured to determine the final table component as the visual chart.

[0169] In a possible implementation manner, the device further includes:

[0170] The second acquisition module 509 is used to obtain the corresponding data source in response to the filling operation of the database information in the data source interface;

[0171] The second generating module 510 is used to generate a corresponding data set configuration table in response to the filling operation of the configuration information in the data set configuration interface;

[0172] A binding module 511, used to bind the data set configuration table with the data source to generate a data set;

[0173] A division module 512 is used to obtain each production data in the data set, and divide the each production data into a training set and a calculation set according to a preset ratio;

[0174] The second input module 513 is used to input the calculation set into a trained machine learning model for processing to obtain an expected value, wherein the trained machine learning model is trained based on the training set.

[0175] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0176] Figure 6Schematic diagram of the hardware structure of the computer device provided in the embodiment of the present application. Figure 6 As shown, the computer device of this embodiment includes: a processor 601 and a memory 602; the memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the above product quality traceability processing method.

[0177] Optionally, the memory 602 may be independent or integrated with the processor 601 .

[0178] When the memory 602 is independently provided, the computer device further includes a bus 603 for connecting the memory 602 and the processor 601 .

[0179] The embodiment of the present application further provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the product quality tracing processing method as described above is implemented.

[0180] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the product quality tracing processing method as described above is implemented.

[0181] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0182] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0183] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0184] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present application.

[0185] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0186] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0187] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0188] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0189] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0190] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0191] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A product quality tracing method, characterized in that: Applicable to computer equipment, including: Display a product quality traceability model for any product, wherein the product quality traceability model includes multiple production links to be traced for the product; wherein each production link to be traced corresponds to a pre-created data display chart; In response to a query operation on any production link to be traced in the product quality traceability model, a corresponding query condition is generated; Obtaining a traceability data preview table corresponding to the production link to be traced according to the query condition, wherein the traceability data preview table includes corresponding multiple production batches; In response to a click operation on any batch in the traceability data preview table, a corresponding target data display chart is displayed, wherein the target data display chart is generated according to the corresponding data display chart; If it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, it is determined that the product quality is normal.

2. The method according to claim 1, characterized in that Wherein the target data display chart includes a target visualization chart and / or a target control chart; Correspondingly, if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, then determining that the product quality is normal includes: If it is determined according to the target visualization chart that there is no abnormal data in the production link to be traced, then it is determined that the product quality is normal; or, If it is determined according to the target control chart that there is no abnormal data in the production link to be traced, then it is determined that the product quality is normal; or, If it is determined according to the target visualization chart and the target control chart that there is no abnormal data in the production link to be traced, it is determined that the product quality is normal.

3. The method according to claim 2, characterized in that If it is determined according to the target data display chart that there is no abnormal data in the production link to be traced, then it is determined that the product quality is normal, including: Calculate the difference between the actual value and the expected value in the target visualization chart; If the difference rates are less than the preset difference thresholds, it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

4. The method according to claim 2, characterized in that: If it is determined according to the target visualization chart that there is no abnormal data in the production link to be traced, then it is determined that the product quality is normal, including: In the target control chart, if there are no preset number of consecutive numerical points exceeding the preset center line, it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

5. The method according to any one of claims 2 to 4, characterized in that: If it is determined according to the target visualization chart and the target control chart that there is no abnormal data in each production link to be traced, then it is determined that the product quality is normal, including: Calculate the difference between the actual value and the expected value in the target visualization chart; If the difference rates are less than a preset difference threshold, and / or there are no preset number of consecutive numerical points exceeding a preset center line, it is determined that there is no abnormal data in the production link to be traced, so as to determine that the product quality is normal.

6. The method according to claim 1, characterized in that Wherein the data display chart includes a visual chart; Accordingly, the process of creating the visualization chart includes: Associating the preset table class component with the pre-generated data set to obtain the associated table class component; Inputting each pre-generated expected value into the associated table class component, and corresponding it with the actual value in the data set to obtain a final table class component; The final table component is determined as the visual chart.

7. The method according to claim 6, characterized in that The process of generating the data set includes: In response to the operation of filling in the database information in the data source interface, the corresponding data source is obtained; and, In response to the filling operation of the configuration information in the data set configuration interface, generating a corresponding data set configuration table; Binding the data set configuration table with the data source to generate a data set; Accordingly, the process of generating each expected value includes: Acquire each production data in the data set, and divide each production data into a training set and a calculation set according to a preset ratio; The calculation set is input into a trained machine learning model for processing to obtain each expected value, wherein the trained machine learning model is trained based on the training set.

8. A product quality tracing device, characterized in that: Applicable to computer equipment, including: A first display module is used to display a product quality traceability model of any product, wherein the product quality traceability model includes a plurality of production links to be traced of the product; wherein each production link to be traced corresponds to a pre-created data display chart; A first generating module, configured to generate corresponding query conditions in response to a query operation on any production link to be traced in the product quality traceability model; A first acquisition module is used to acquire a traceability data preview table corresponding to the production link to be traced according to the query condition, wherein the traceability data preview table includes corresponding multiple production batches; A second display module is used to display a corresponding target data display chart in response to a click operation on any batch in the traceability data preview table, wherein the target data display chart is generated according to the corresponding data display chart; The first determination module is used to determine that the product quality is normal if it is determined according to the target data display chart that there is no abnormal data in the production link to be traced.

9. A computer device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the product quality traceability processing method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions. When the processor executes the computer executable instructions, the product quality traceability processing method according to any one of claims 1 to 7 is implemented.

Images