Production data analysis method and device, computer device, and storage medium

Abstract

The application provides a production data analysis method and device, equipment and a storage medium. The analysis method comprises the following steps: grouping the obtained first production data according to product types to obtain multiple groups of second production data; the first production data represents the production data of multiple types of products in a production process in a last continuous production time period; the straight-through rate of the products is determined according to the second production data; the second production data is grouped according to production processes to obtain at least one group of third production data; the production capacity and the defective rate of the production process are determined according to the third production data; and whether to perform early warning is determined according to the straight-through rate, the production capacity and the defective rate. The application can achieve the purposes of automatically and regularly analyzing and counting production data and actively warning abnormal production data by analyzing the production data in the last continuous production time period and determining whether to perform early warning according to the straight-through rate, the production capacity and the defective rate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a production data analysis method and device, computer equipment and storage medium. BACKGROUND

[0002] Intelligent production is an important part of intelligent factory construction, and the analysis and utilization of production data are extremely important for realizing intelligent production. How to efficiently process a large amount of production data generated in the production process, analyze the problems existing in production from the data, and achieve the purpose of guiding production is an urgent problem to be solved in the current intelligent production construction. Reasonable analysis and utilization of real-time production data can effectively improve product quality and production efficiency.

[0003] Through the research on the current data utilization, the current utilization of production data mainly embodies various production data related reports. Management personnel understand the production situation by viewing the reports, and adjust the production strategy according to the reports. However, the report generation process has hysteresis and passivity. First, the generated report can only represent the summary of the production situation in the past period (such as several days, several months), and cannot reflect the current real-time production situation. Secondly, the report cannot directly reflect the problem, and still needs the management personnel to view the report and analyze the existing problem from the report, which leads to that the actual role of the report still depends on the work attitude and business level of the management personnel.

[0004] In view of the technical problems in the above related art that the report generation scheme cannot directly reflect the real-time production situation and production problems, no effective solution has been proposed at present. SUMMARY

[0005] The embodiments of the present application provide a production data analysis method and device, computer equipment and storage medium, to overcome the technical problem that the report generation scheme in the related art cannot directly reflect the real-time production situation and production problems.

[0006] In order to achieve the above purpose, the first aspect of the embodiments of the present application provides a production data analysis method, comprising:

[0007] grouping the obtained first production data according to product types to obtain a plurality of groups of second production data; the first production data represents the production data of a plurality of types of products in a production process in a last continuous production time period, and the second production data represents the production data of a single type of product in the production process in the last continuous production time period;

[0008] determining a straight-through rate of the product according to the second production data;

[0009] grouping the second production data according to production procedures to obtain at least one group of third production data, wherein the third production data represents production data of a single type of product in a single production procedure;

[0010] determining the capacity and the defective rate of the production procedure according to the third production data;

[0011] judging whether to perform early warning according to the straight-through rate, the capacity and the defective rate.

[0012] The production data analysis method provided by the application can automatically analyze and count production data at a regular time without manual operation, and can actively warn and push abnormal or possibly abnormal production data without requiring a manager to actively check a report to find problems.

[0013] Optionally, in a possible implementation manner of the first aspect, the determining the straight-through rate of the product according to the second production data comprises:

[0014] preprocessing production data in the second production data, wherein the preprocessing is to remove second production data corresponding to a bar code of an unfinished packaging procedure;

[0015] grouping the preprocessed second production data according to bar codes to obtain a plurality of groups of fourth production data, and determining a grouping number of the fourth production data, wherein each group of fourth production data represents all production data of each product in a production process;

[0016] judging whether all production data of each group in the fourth production data are qualified one by one, if all production data of each group are qualified, determining a group to which the corresponding fourth production data belongs as a straight-through group, and counting a number of straight-through groups in the fourth production data;

[0017] determining the straight-through rate of the product according to the grouping number of the fourth production data and the number of straight-through groups.

[0018] The production data analysis method provided by the application can accurately determine the probability that a single type of product is qualified from a first procedure to a last procedure at one time, and can accurately reflect the ability of a product to be straight through to a finished product in all procedures in a production process.

[0019] Optionally, in a possible implementation manner of the first aspect, the determining the production capacity and the defective rate of the production process according to the third production data comprises:

[0020] sorting production data in at least one group of the third production data according to production completion time;

[0021] determining a continuous production time period according to a data sorting result;

[0022] counting a quantity of qualified production data in the at least one group of the third production data;

[0023] determining the production capacity of the production process according to the continuous production time period and the quantity of the qualified production data;

[0024] determining the defective rate of the production process according to the quantity of the qualified production data in the third production data and a total quantity of the third production data.

[0025] The production data analysis method provided by the application can determine the production capacity of the production process through the continuous production time period and the quantity of the qualified production data, can truly and accurately reflect the current production capacity of the enterprise, so as to accurately determine whether the current production capacity of the enterprise can adapt to the market demand; and can determine the defective rate of the production process through the quantity of the qualified production data in the third production data and the total quantity of the third production data, can accurately determine the current production quality of the product, so as to adaptively adjust the production process according to the current production quality, thereby achieving the purpose of improving the production quality.

[0026] Optionally, in a possible implementation manner of the first aspect, the determining the continuous production time period according to the data arrangement result comprises:

[0027] performing deduplication processing on third production data produced at the same time in the data arrangement result to generate a data set, the deduplication processing indicating that a plurality of third production data produced at the same time retains any one of the third production data;

[0028] performing clustering on the data set according to production completion time by using a standard time interval to obtain an earliest production time and a latest production time;

[0029] determining the continuous production time period according to the earliest production time and the latest production time.

[0030] Optionally, in a possible implementation manner of the first aspect, the method further comprises:

[0031] obtaining temperature data in a preset time, grouping the temperature data according to collection devices, and sorting the grouped temperature data according to time sequence.

[0032] input the grouped temperature data and the time data of the temperature data into a temperature prediction model to obtain a temperature prediction curve in a preset future time;

[0033] if the temperature prediction curve exceeds a normal temperature range, an early warning information is sent out.

[0034] The production data analysis method provided by the application can accurately predict the environmental temperature in a future period of time, so as to achieve the purpose of real-time regulation of the temperature of the production environment according to the predicted temperature, thereby ensuring the normal production of products.

[0035] Optionally, in a possible implementation manner of the first aspect, the determining whether to perform early warning according to the pass rate, the production capacity and the defective rate comprises:

[0036] preset threshold values corresponding to the pass rate, the production capacity and the defective rate are set respectively, and the preset threshold values comprise a first threshold value, a second threshold value and a third threshold value; wherein the first threshold value represents a preset threshold value of the pass rate, the second threshold value represents a preset threshold value of the production capacity, and the third threshold value represents a preset threshold value of the defective rate.

[0037] comparing the pass rate with the first threshold value, and determining whether to send an early warning prompt about the pass rate according to a first comparison result;

[0038] comparing the production capacity with the second threshold value, and determining whether to send an early warning prompt about the production capacity according to a second comparison result;

[0039] comparing the defective rate with the third threshold value, and determining whether to send an early warning prompt about the defective rate according to a third comparison result.

[0040] Optionally, in a possible implementation manner of the first aspect,

[0041] the determining whether to send an early warning prompt about the pass rate according to the first comparison result comprises: when the pass rate is less than the first threshold value, sending first early warning information through an early warning module;

[0042] the determining whether to send an early warning prompt about the production capacity according to the second comparison result comprises: when the production capacity is less than the second threshold value, sending second early warning information through the early warning module;

[0043] The third comparison result is used to determine whether to send a warning prompt about the defective rate, and the warning prompt includes sending third warning information by the warning module when the defective rate is greater than the third threshold.

[0044] The method for analyzing production data provided by the application can actively warn and push abnormal and possibly abnormal production data by comparing the pass rate, production capacity and defective rate with corresponding thresholds and sending corresponding warning prompts according to the comparison results, without the need for managers to check reports to find problems, which can help save labor consumption.

[0045] In a second aspect, the application provides a device for analyzing production data, comprising:

[0046] A first grouping module is configured to group the obtained first production data according to product types to obtain a plurality of groups of second production data, wherein the first production data represents production data of a plurality of types of products in a production process in a last continuous production period, and the second production data represents production data of a single type of product in the production process in the last continuous production period.

[0047] A first determining module is configured to determine a pass rate of the product according to the second production data.

[0048] A second grouping module is configured to group the second production data according to production processes to obtain at least one group of third production data, wherein the third production data represents production data of a single type of product in a single production process.

[0049] A second determining module is configured to determine a production capacity and a defective rate of the production process according to the third production data.

[0050] A warning module is configured to determine whether to send a warning according to the pass rate, the production capacity and the defective rate.

[0051] In a third aspect, the application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor implements the steps in each method embodiment of the application when executing the computer program.

[0052] In a fourth aspect, the application provides a readable storage medium, wherein the readable storage medium stores a computer program, and the computer program is used to implement the steps of the method in the first aspect and various possible designs of the first aspect when executed by a processor. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and the ordinary skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0054] Figure 1 The flowchart of the analysis method for the production data of the embodiment 1 of the present application.

[0055] Figure 2 The principle block diagram of the analysis device for the production data of the embodiment 2 of the present application.

[0056] Figure 3 The structural schematic diagram of the computer device in the embodiment 3 of the present application. EMBODIMENT

[0057] The technical solutions of the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by the ordinary skilled in the art without any creative effort belong to the protection scope of the present application.

[0058] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0059] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication between two elements, or it can be wireless connection, or it can be wired connection. For the ordinary skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0060] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as there is no conflict between them.

[0061] Embodiment 1

[0062] The embodiment provides an analysis method of production data, as shown in the following table, the analysis method comprises the following steps: Figure 1

[0063] S100: grouping the obtained first production data according to product types to obtain a plurality of groups of second production data.

[0064] Specifically, the first production data represents all production data of products of a plurality of types in a production process in a last continuous production time period, and can be understood as automatically collecting production data (for example, production data of all products in each production process) newly generated in the last time period after each working time period (for example, morning shift, noon shift and night shift) ends, wherein the production data can include whether the product in each production process is qualified. The second production data represents all production data of products of a single type in the production process in the last continuous production time period. The first production data is production data generated by a production system and stored in a data warehouse, and then all production data (that is, the first production data) in the data warehouse is grouped according to product types to obtain a plurality of groups of second production data; each group of second production data can be understood as production data of a product of a certain type in each production process.

[0065] More specifically, the production process, also known as the process flow or the processing flow, refers to a process of continuously processing through certain production equipment according to certain production processes from raw material input to finished product output. For example, from the whole production process, it can include a transportation process, a process process and a quality inspection process, wherein the transportation process has a transportation machine specially used for transporting materials, the process process has production equipment specially used for product production, and the quality inspection process has a machine specially used for quality inspection of the produced products. From the process process, it can include one or more process sub-processes, for example, a pretreatment sub-process responsible for pretreatment of raw materials, and a plurality of product processing sub-processes responsible for processing of the pretreated materials.

[0066] S200: determining a straight-through rate of the product according to the second production data.

[0067] Specifically, the straight-through rate of the product is a parameter for the product to be qualified once from the first process to the last process, and can understand the ability of the product to be straight to the finished product in all processes in the product production process.

[0068] Step S200 comprises the following steps:

[0069] ​S210: preprocessing the production data in the second production data, the preprocessing being eliminating the second production data corresponding to the bar code of the unfinished packaging process.

[0070] Specifically, the production data corresponding to the bar code of the unfinished packaging process in each group of the second production data is eliminated, and the purpose is to retain the production data corresponding to the bar code of the product that has completed all production processes.

[0071] S220: grouping the preprocessed second production data according to the bar code to obtain a plurality of groups of fourth production data, and determining the number of groups of the fourth production data; each group of the fourth production data represents all production data of each product in the production process.

[0072] Specifically, the bar code represents identification information unique to each product, and the preprocessed second production data is grouped according to the bar code, and the purpose is to group all production data of the same product in the entire production process according to the bar code, so as to obtain the total production quantity of a certain type of product by counting the number of groups.

[0073] S230: judging whether all production data in each group of the fourth production data is qualified, if all production data is qualified, determining the group corresponding to the fourth production data as a straight-through group, and counting the number of straight-through groups in the fourth production data.

[0074] Specifically, by judging whether each group of the fourth production data (i.e. all production data in each group) is qualified, the group in which all production data is qualified can be determined as a straight-through group, i.e. it can be determined that the product is qualified from the first process to the last process at one time. By counting the number of straight-through groups, the number of products that are qualified from the first process to the last process at one time can be determined.

[0075] S240: determining the straight-through rate of the product according to the number of groups of the fourth production data and the number of straight-through groups.

[0076] Specifically, after determining the number of groups and the number of straight-through groups, the straight-through rate of a single type of product can be determined by the following formula:

[0077] FPY=(A1 / A)*100%

[0078] Wherein, FPY represents the straight-through rate, A1 represents the number of straight-through groups, and A represents the number of groups.

[0079] S300: grouping the second production data according to the production process to obtain at least one group of third production data; the third production data represents the production data of a single type of product in a single production process.

[0080] Specifically, the second production data is grouped according to the production process, and one or more groups of third production data can be obtained. It can be understood that the production data of all products of a single product type is grouped according to the production process, that is, the production data of one group represents the production data of all products of the same product type in one production process, and the number of groups can represent the number of production processes that the product needs to go through in the production process.

[0081] S400: determining the capacity and the defective rate of the production process according to the third production data.

[0082] Specifically, the capacity can be understood as the maximum qualified production quantity that a production unit can produce in a fixed time, and the defective rate refers to the ratio of defective products to all products in a certain time period, which is a key indicator for measuring production quality.

[0083] Step S400 includes steps S410 to S430 as follows:

[0084] S410: sorting the production data in at least one group of third production data according to the production completion time; and determining a continuous production time period according to the data sorting result.

[0085] Specifically, the continuous production time period can be determined according to the data sorting result of sorting the production data according to the production completion time. For example, when the production completion time of the production data is generally from 8:00 am to 12:00 pm and from 1:00 pm to 6:00 pm, the continuous production time period can be determined as from 8:00 am to 12:00 pm and from 2:00 pm to 6:00 pm. Alternatively, the production work can be divided into morning shift, afternoon shift and night shift, and the production time period corresponding to each shift can be regarded as a continuous production time period.

[0086] Preferably, step S410 includes but is not limited to steps S411 to S413, including:

[0087] S411: performing a deduplication process on the third production data produced at the same time in the data arrangement result to generate a data set, and the deduplication process means that multiple third production data produced at the same time are retained arbitrarily.

[0088] Specifically, the third production data in the data arrangement result is merged according to the production completion time, and the merging basis is that the third production data produced at the same time is retained arbitrarily, thereby generating a data set of the continuous production time period.

[0089] S412: clustering the data set according to the production completion time by using a standard time interval to obtain the earliest production time and the latest production time.

[0090] Specifically, for each production device, the production time interval between all time-adjacent data is calculated; the median of all the obtained production time intervals is taken as the standard time interval; the standard time interval is used as the density, and the data set of the continuous production time period is clustered according to the production time using a clustering algorithm (for example, DBSCAN algorithm, Density-Based Spatial Clustering of Applications with Noise); for each cluster obtained by clustering, the earliest and latest production times are taken as the start and end times of each continuous production period.

[0091] S413: determining the continuous production time period according to the earliest production time and the latest production time.

[0092] Specifically, the continuous production time period can be determined according to the standard time interval, the earliest production time and the latest production time by the following formula:

[0093] T = T1-T2+T0

[0094] Wherein, T represents the continuous production time period, T1 represents the latest production time, T2 represents the earliest production time, and T0 represents the standard time interval.

[0095] S420: counting the number of qualified production data in at least one group of third production data.

[0096] Specifically, the capacity of the present application refers to the maximum output of qualified production data that can be produced in a fixed time, so it is necessary to count the number of qualified production data produced in a continuous production time period.

[0097] S430: determining the capacity of the production process according to the continuous production time period and the number of qualified production data.

[0098] Specifically, after determining the continuous production time period and the number of qualified production data, the capacity of a single type of product in a certain production process can be determined by the following formula:

[0099] Q = (B1 / T)*100%

[0100] Wherein, Q represents the capacity, B1 represents the number of qualified production data in the third production data, and T represents the continuous production time period.

[0101] Step S400 includes a step S440 of determining the failure rate of the production process, which is specifically as follows:

[0102] S440: determining the failure rate of the production process according to the number of qualified production data in the third production data and the total amount of the third production data.

[0103] Specifically, on the basis of counting the total number of the third production data of each group and the number of qualified production data in the third production data of each group, the yield of each group is determined by using the following formula:

[0104] PPM = (1 - B1 / B) * 100%

[0105] PPM represents the yield, B represents the total number of the third production data, and B1 represents the number of qualified production data in the third production data.

[0106] S500: Determine whether to issue a warning according to the yield, capacity and yield.

[0107] Specifically, the yield of the product is monitored in real time, which can determine which type of product is not prone to unqualified data in the production process, and can understand the ability of the product to reach the finished product under all processes in the production process. By monitoring the capacity of each production process, the current product processing capacity of each production process can be truly reflected. By monitoring the yield of each production process, the production process that needs to be improved can be determined according to the yield, thereby improving the product production capacity.

[0108] Step S500 includes but is not limited to the following steps:

[0109] S510: Set corresponding preset thresholds for the yield, capacity and yield, respectively, and the preset thresholds include first, second and third thresholds; wherein the first threshold represents the preset threshold of the yield, the second threshold represents the preset threshold of the capacity, and the third threshold represents the preset threshold of the yield.

[0110] Specifically, the first, second and third thresholds can be set according to actual production needs, which are not limited here.

[0111] S520: Compare the yield with the first threshold, and determine whether to issue a warning prompt about the yield according to the first comparison result.

[0112] S530: Compare the capacity with the second threshold, and determine whether to issue a warning prompt about the capacity according to the second comparison result.

[0113] S540: Compare the yield with the third threshold, and determine whether to issue a warning prompt about the yield according to the third comparison result.

[0114] In steps S520 to S540, when the pass rate is less than the first threshold value, the first early warning information is issued by the early warning module; when the production capacity is less than the second threshold value, the second early warning information is issued by the early warning module; and when the defective rate is greater than the third threshold value, the third early warning information is issued by the early warning module. For example, after each working time period (morning shift, afternoon shift, night shift) ends, the production data analysis system constructed based on the method of the application automatically analyzes the newly generated production data in the last time period (the time period just ended) and generates early warning information and pushes it according to the analysis result; for example, after the morning work ends, the system analyzes the data and finds that the defective rate of product A in the pressure test in the morning is out of standard, and sends an early warning email to the corresponding process personnel; the process personnel see the early warning email after lunch and come to the workshop to troubleshoot the problem and record it to the system to form an experience database.

[0115] Preferably, the method further comprises: acquiring temperature data within a preset time, grouping the temperature data according to the collection equipment, and sorting the grouped temperature data in chronological order; inputting the grouped temperature data and the time data of the temperature data into a temperature prediction model to obtain a temperature prediction curve in a future preset time; and issuing a warning information if the temperature prediction curve exceeds a normal temperature range.

[0116] Specifically, the application can also use environmental temperature data to calculate the environmental temperature trend, generate a temperature prediction curve, and warn about the environmental temperature overrun that has occurred and may occur, specifically as follows:

[0117] The temperature information of the thermometer of the production environment is acquired every first preset time and uploaded to the server; the server acquires all temperature data in the last 1 hour of the current time every second preset time (the second preset time is greater than the first preset time), arranges them in chronological order from early to late, and groups them according to the collection equipment (different temperature sensors), and for the temperature data of each group, the following steps are performed; input the temperature and time data into an autoregressive integrated moving average model (ARIMA model), train the model, and obtain the temperature prediction curve of the model for a future period of time; obtain the normal temperature range (manually set) of the sensor; if the measured data or the predicted data exceeds the normal temperature range, a warning information is issued through the early warning management module. The humidity data of the production environment is monitored, and the specific embodiments of the temperature monitoring are implemented accordingly.

[0118] Preferably, by establishing an early warning model, the relationship between the behavior of personnel or equipment and the production quality is analyzed based on the personnel information or equipment information and the production information in the production data, and the possible production quality risk is warned.

[0119] The method for establishing the equipment operation early warning model (the personnel operation early warning model is established and used in the same way) is as follows:

[0120] For all production data in the data warehouse, group by device type, and use all production data of each group of devices to calculate the device production time period; arrange all production data of this group by production time from early to late; merge production data by production time, and for production data generated at the same time, only keep any one of the data to generate a continuous production time period calculation data set; for each production device, calculate the production time interval between all time adjacent data; take the median of all production time intervals obtained as the standard time interval; use the standard time interval as the density, and use the clustering algorithm (such as DBSCAN algorithm, Density-Based Spatial Clustering of Applications with Noise) to cluster the continuous production time period calculation data set by production time; for each class obtained by clustering, take its earliest and latest production time, which is the start and end time of each continuous production; divide the continuous production time period into three categories: morning, afternoon, and evening; for each category of morning, afternoon, and evening, take the median of the start time and end time of all time periods (ignore date, only keep time) as the standard production time period of morning, afternoon, and evening, respectively; for all production data, group by barcode, and take out the group with unqualified data for the following analysis: for all production data of a single barcode, take the operating device of each process, the operator, each device as a parameter, and each operator as a parameter; take the unqualified process name, each process name as a parameter; obtain a parameter for each barcode to form a data set, train using the frequent pattern tree (FP tree) algorithm to obtain an FP tree; save each device morning, afternoon, and evening production time period and FP tree generated to serve as a device operation analysis model.

[0121] The device operation is warned by the following method: group the production data by barcode, and take out the production data corresponding to the barcode in the historical data; for all production data of a single barcode, take the operating device of each process, the operator, each device as a parameter, and each operator as a parameter; take the unqualified process name, each process name as a parameter; read the saved FP tree, and use the parameters in the previous step as input to search for association rules in the FP tree; if an association rule is found, send a warning message through the warning module.

[0122] Preferably, the present application also provides a production data real-time analysis system comprising a production data acquisition module, a report viewing module, a service management module, a data analysis model management module, and an early warning management module. The production data acquisition module acquires production data produced by a production system and stores the production data into a data warehouse. The report viewing module provides display functions for various production reports. The service management module provides the results of statistical analysis of production data to other modules in the form of a web application program interface (web api). The data analysis model management module provides management functions for various data analysis models and can update the models using new data. The early warning management module provides early warning push functions for production abnormalities. Details are as follows:

[0123] The production data acquisition module is used to provide production data acquisition services to the server background, automatically acquires newly produced production data every certain period of time, and stores the preprocessed production data into a data warehouse. The system sends warning information through the early warning module for non-standard data encountered during processing.

[0124] The report viewing module provides users with daily, weekly, and monthly statistical reports of production. In addition, users can also view temperature and humidity curves and prediction curves of temperature and humidity sensors, real-time production information (current products in production, production capacity, defect rate, etc.), and other real-time reports.

[0125] The service management module is used to provide data analysis results to the production system and other business systems. The production system requests data through a service interface, allowing users to view reports generated by the data analysis system without switching systems.

[0126] The data analysis model management module is used to automatically analyze production data at regular intervals to generate corresponding data analysis models, uniformly store and manage generated model files, and back up the model files. The model pool is used to manage model loading and updating when the service uses the model.

[0127] The early warning management module is used to call the early warning management interface to add early warning information to the early warning queue when the automatic timing analysis service in the system background generates information that needs to be warned. The system background service automatically sends messages in the early warning queue, supporting reminder methods such as email, short message, WeChat public number message, etc.

[0128] Through the cooperation between the above-mentioned multiple modules, production data is automatically collected and analyzed, production data that may have problems is early warned and pushed to remind relevant personnel to confirm and handle, and traditional report viewing functions are provided through the interface, effectively improving data utilization and production quality.

[0129] The technical solution of the present application also has the following technical effects:

[0130] The automatic timing analyzes and counts the real-time production data without manual operation. The abnormal and possible abnormal production data are actively warned and pushed without waiting for the manager to check the report to find the problem.

[0131] Embodiment 2

[0132] The embodiment provides an analysis device for production data, which comprises, as shown in the figure, a first grouping module, a first determining module, a second grouping module, a second determining module and a warning module. Figure 2

[0133] The first grouping module is used for grouping the obtained first production data according to product types to obtain a plurality of groups of second production data; the first production data represents production data of a plurality of types of products in a production process in a last continuous production time period, and the second production data represents production data of a single type of product in the production process in the last continuous production time period.

[0134] The first determining module is used for determining a straight-through rate of the product according to the second production data.

[0135] The second grouping module is used for grouping the second production data according to production processes to obtain at least one group of third production data; the third production data represents production data of the single type of product in a single production process.

[0136] The second determining module is used for determining a capacity and a defective rate of the production process according to the third production data.

[0137] The warning module is used for judging whether to perform a warning according to the straight-through rate, the capacity and the defective rate.

[0138] Preferably, the first determining module comprises a preprocessing unit, a barcode grouping unit, a straight-through grouping determining unit and a straight-through rate determining unit.

[0139] The preprocessing unit is used for preprocessing production data in the second production data, and the preprocessing is to eliminate the second production data corresponding to a barcode of an unfinished packaging process.

[0140] The barcode grouping unit is used for grouping the preprocessed second production data according to the barcode to obtain a plurality of groups of fourth production data, and determining a grouping number of the fourth production data; each group of the fourth production data represents all production data of each product in the production process.

[0141] The straight-through grouping determining unit is used for judging whether all production data in each group of the fourth production data are all qualified, and if yes, determining a group corresponding to the fourth production data as a straight-through group, and counting a number of the straight-through groups in the fourth production data.

[0142] The straight-through rate determining unit is used for determining the straight-through rate of the product according to the grouping number of the fourth production data and the number of the straight-through groups. ​

[0143] Preferably, the second determining module comprises:

[0144] The continuous production time period determining unit is configured to sort the production data in the at least one set of third production data according to the production completion time, and determine the continuous production time period according to the data sorting result.

[0145] The quantity counting unit is configured to count the quantity of qualified production data in the at least one set of third production data.

[0146] The capacity determining unit is configured to determine the capacity of the production process according to the continuous production time period and the quantity of qualified production data.

[0147] The defective rate determining unit is configured to determine the defective rate of the production process according to the quantity of qualified production data in the third production data and the total quantity of the third production data.

[0148] Preferably, the continuous production time period determining unit comprises:

[0149] The deduplication sub-unit is configured to perform deduplication processing on the third production data produced at the same time in the data arrangement result to generate a data set, and the deduplication processing indicates that multiple third production data produced at the same time are retained at random.

[0150] The clustering sub-unit is configured to cluster the data set according to the production completion time by using a standard time interval to obtain the earliest production time and the latest production time.

[0151] The continuous production time period determining sub-unit is configured to determine the continuous production time period according to the earliest production time and the latest production time.

[0152] Preferably, the production data analysis device further comprises:

[0153] The temperature sorting module is configured to obtain temperature data within a preset time, group the temperature data according to the collection equipment, and sort the grouped temperature data according to the time sequence.

[0154] The prediction curve determining module is configured to input the grouped temperature data and the time data of the temperature data into a temperature prediction model to obtain a temperature prediction curve within a future preset time.

[0155] The temperature judging module is configured to issue a warning information if the temperature prediction curve exceeds a normal temperature range.

[0156] Preferably, the warning module comprises:

[0157] The threshold setting unit is configured to set corresponding preset thresholds for the pass rate, the production capacity and the defective rate, respectively, wherein the preset thresholds include a first threshold, a second threshold and a third threshold; the first threshold represents the preset threshold of the pass rate, the second threshold represents the preset threshold of the production capacity, and the third threshold represents the preset threshold of the defective rate.

[0158] The first comparison unit is configured to compare the pass rate with the first threshold, and determine whether to send a warning prompt about the pass rate according to a first comparison result.

[0159] The second comparison unit is configured to compare the production capacity with the second threshold, and determine whether to send a warning prompt about the production capacity according to a second comparison result.

[0160] The third comparison unit is configured to compare the defective rate with the third threshold, and determine whether to send a warning prompt about the defective rate according to a third comparison result.

[0161] Preferably, the first comparison unit includes a first warning subunit configured to send first warning information through the warning module when the pass rate is less than the first threshold.

[0162] Preferably, the second comparison unit includes a second warning subunit configured to send second warning information through the warning module when the production capacity is less than the second threshold.

[0163] Preferably, the third comparison unit includes a third warning subunit configured to send third warning information through the warning module when the defective rate is greater than the third threshold.

[0164] Embodiment 3

[0165] The present application also provides a computer device, as shown in the accompanying drawings, comprising a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements the production data analysis method provided by the various embodiments when executing the computer program. Figure 3 The present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to implement the production data analysis method provided by the various embodiments.

[0166] The present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to implement the production data analysis method provided by the various embodiments.

[0167] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0168] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0169] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0170] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0171] Obviously, the above-described embodiments are only examples for clarity and are not intended to limit the implementation. Based on the above description, other different forms of changes or variations can also be made by those skilled in the art. All the embodiments are not required to be exhaustive. The obvious changes or variations derived therefrom are still within the protection scope of the present application.

Claims

1. A method of analyzing production data, characterized by, The method comprises the following steps: grouping the obtained first production data according to product types to obtain multiple groups of second production data; the first production data represents production data of multiple types of products in a production process in a last continuous production time period, and the second production data represents production data of a single type of product in the production process in the last continuous production time period; determining a straight-through rate of the product according to the second production data, comprising: pre-processing production data in the second production data, wherein the pre-processing is to eliminate second production data corresponding to a barcode of an unfinished packaging process; grouping the pre-processed second production data according to the barcode to obtain multiple groups of fourth production data, and determining a grouping number of the fourth production data; each group of the fourth production data represents all production data of each product in the production process; judging whether all production data in each group of the fourth production data are qualified one by one, if all the production data are qualified, determining a group corresponding to the fourth production data as a straight-through group, and counting a number of the straight-through groups in the fourth production data; determining the straight-through rate of the product according to the grouping number of the fourth production data and the number of the straight-through groups; grouping the second production data according to production processes to obtain at least one group of third production data; the third production data represents production data of a single type of product in a single production process; determining a capacity and a defective rate of the production process according to the third production data, comprising: sorting production data in at least one group of the third production data according to production completion time; determining a continuous production time period according to a data sorting result; counting a number of qualified production data in the at least one group of the third production data; determining the capacity of the production process according to the continuous production time period and the number of the qualified production data; determining the defective rate of the production process according to a number of the qualified production data in the third production data and a total amount of the third production data; judging whether to perform early warning according to the straight-through rate, the capacity and the defective rate.

2. The analysis method of production data according to claim 1, characterized in that, the determining of the continuous production time period according to the data sorting result comprises: performing a deduplication processing on third production data produced at the same time in the data sorting result to generate a data set, wherein the deduplication processing means that multiple third production data produced at the same time retain any one of them; performing clustering on the data set according to production completion time by using a standard time interval to obtain an earliest production time and a latest production time; determining the continuous production time period according to the earliest production time and the latest production time.

3. The analysis method of production data according to claim 1, characterized in that, The method further comprises: obtaining temperature data in a preset time, grouping the temperature data according to collection devices, and sorting the grouped temperature data according to time sequence; inputting the grouped temperature data and time data of the temperature data into a temperature prediction model to obtain a temperature prediction curve in a future preset time; if the temperature prediction curve exceeds a normal temperature range, an early warning information is sent out.

4. The analysis method of production data according to claim 1, characterized in that, The method further comprises: setting a corresponding preset threshold for the pass rate, the production capacity and the defective rate, wherein the preset threshold comprises a first threshold, a second threshold and a third threshold; the first threshold represents the preset threshold of the pass rate, the second threshold represents the preset threshold of the production capacity, and the third threshold represents the preset threshold of the defective rate; comparing the pass rate with the first threshold, and determining whether to issue a warning prompt about the pass rate according to a first comparison result; comparing the production capacity with the second threshold, and determining whether to issue a warning prompt about the production capacity according to a second comparison result; comparing the defective rate with the third threshold, and determining whether to issue a warning prompt about the defective rate according to a third comparison result.

5. The production data analysis method of claim 4, wherein the determining whether to issue the warning prompt about the pass rate according to the first comparison result comprises: when the pass rate is less than the first threshold, issuing first warning information through a warning module; the determining whether to issue the warning prompt about the production capacity according to the second comparison result comprises: when the production capacity is less than the second threshold, issuing second warning information through the warning module; the determining whether to issue the warning prompt about the defective rate according to the third comparison result comprises: when the defective rate is greater than the third threshold, issuing third warning information through the warning module.

6. An analysis device of production data, characterized by, The method further comprises: a first grouping module configured to group the obtained first production data according to product types to obtain a plurality of groups of second production data; the first production data represents production data of a plurality of types of products in a production process in a last continuous production period, and the second production data represents production data of a single type of product in the production process in the last continuous production period; a first determination module configured to determine a pass rate of the product according to the second production data, comprising: a preprocessing unit configured to preprocess the production data in the second production data, the preprocessing being to eliminate second production data corresponding to a bar code of an unfinished packaging process; a bar code grouping unit configured to group the preprocessed second production data according to bar codes to obtain a plurality of groups of fourth production data, and determine a grouping number of the fourth production data; each group of the fourth production data representing all production data of each product in the production process; a pass grouping determination unit configured to determine, one by one, whether all production data of each group in the fourth production data are all qualified, and if so, determine a group corresponding to the fourth production data as a pass group, and count a number of the pass groups in the fourth production data; and a pass rate determination unit configured to determine the pass rate of the product according to the grouping number of the fourth production data and the number of the pass groups; a second grouping module configured to group the second production data according to production processes to obtain at least one group of third production data; the third production data representing production data of a single type of product in a single production process. The second determining module is configured to determine the capacity and the defective rate of the production process according to the third production data, and includes: a continuous production time period determining unit configured to sort the production data in at least one group of third production data according to production completion time, determine a continuous production time period according to the data sorting result, a quantity counting unit configured to count the quantity of qualified production data in at least one group of third production data, a capacity determining unit configured to determine the capacity of the production process according to the continuous production time period and the quantity of qualified production data, and a defective rate determining unit configured to determine the defective rate of the production process according to the quantity of qualified production data in the third production data and the total quantity of the third production data. The early warning module is configured to determine whether to perform early warning according to the straight-through rate, the capacity and the defective rate. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the computer device is characterized in that, The computer program is executed by the processor to implement the steps of the production data analysis method in any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the production data analysis method in any one of claims 1 to 5.

Images