CN113592043B - Carton classification method - Google Patents
Carton classification method Download PDFInfo
- Publication number
- CN113592043B CN113592043B CN202111167098.6A CN202111167098A CN113592043B CN 113592043 B CN113592043 B CN 113592043B CN 202111167098 A CN202111167098 A CN 202111167098A CN 113592043 B CN113592043 B CN 113592043B
- Authority
- CN
- China
- Prior art keywords
- capacity
- data
- classified
- carton
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a carton classification method, which comprises the steps of obtaining real-time classified capacity data and judging whether each current carton classified production line is in a normal capacity working state or not; if the judgment result is yes, generating a current capacity state identifier, acquiring basic information of an actual output paper box, and acquiring a complete degree value of a box body of the paper box to be classified; respectively generating basic data identifiers of paper boxes to be classified, and judging whether the characteristic matching degree value of each basic data identifier of the paper boxes to be classified and each standard classification reference value in a preset standard classification reference set meets a preset matching threshold value or not; if the classification information is judged to be yes, the initial classification information of the paper boxes is generated, and the updated classification information of the paper boxes is generated. The invention realizes that the carton classification information is updated as a result of integrating information in multiple aspects, improves the accuracy and reliability of carton classification, does not need to repeat multiple classification, and indirectly improves the carton classification efficiency.
Description
Technical Field
The application relates to the technical field of carton data identification, in particular to a carton classification method.
Background
At present, there are various methods for classifying paper products such as paper boxes, for example, an apparatus and a method for establishing a used paper image classifier disclosed in patent application No. CN201810344496.2, and an automatic used paper classifying system and a method for classifying the same. The method for establishing the waste paper image classifier comprises the following steps: s1: establishing a sample library, wherein a plurality of waste paper sample images and classification grades corresponding to the waste paper sample images are stored in the sample library, and the waste paper sample images comprise sample images corresponding to different types of waste paper; s2, constructing a CNN image classification model; and S3, randomly extracting waste paper sample images from the sample library to train the CNN image classification model to obtain a waste paper classification model, namely a waste paper image classifier.
Although the technical scheme can realize a certain classification effect, the paper box classification method is applied to paper box classification, and has the problems of large time consumption and low efficiency like other classification technologies.
Disclosure of Invention
In view of the above, it is necessary to provide a carton sorting method capable of improving the carton sorting efficiency in view of the above-mentioned technical problems.
The technical scheme of the invention is as follows:
a carton sorting method, the method comprising:
acquiring preset real-time classified capacity data of each current carton classified production line, and judging whether each current carton classified production line is in a normal capacity working state or not according to the real-time classified capacity data; if so, respectively generating current capacity state identifiers according to each current carton classifying production line, acquiring basic information of actual output cartons of each current carton classifying production line, and respectively acquiring complete degree values of cartons to be classified according to the basic information of the actual output cartons; generating basic data identifiers of the paper boxes to be classified according to actual output paper box basic information corresponding to each current paper box classification production line and the integrity degree value of the paper boxes to be classified, and judging whether the characteristic matching degree value of each basic data identifier of the paper boxes to be classified and each standard classification reference value in a preset standard classification reference set meets a preset matching threshold value or not, wherein one standard classification reference set corresponds to one standard classification category; if the classification information is judged to be the initial classification information, generating initial classification information of the paper boxes, and generating updated classification information of the paper boxes according to the initial classification information of the paper boxes, the current capacity state identification, the complete degree value of the paper boxes to be classified and the basic data identification of the paper boxes to be classified.
Specifically, if the current production capacity state identifier is determined to be the current production capacity state identifier, the actual output carton basic information of each current carton classification production line is obtained, and meanwhile, the complete degree value of the carton body of the carton to be classified is obtained according to each actual output carton basic information; then also comprises the following steps:
acquiring a numerical value set of which the box body integrity degree value of the paper boxes to be classified corresponding to each current paper box classification production line is smaller than a preset paper box minimum damage degree value, wherein the set formed by the paper boxes to be classified corresponding to the numerical value set is a non-receiving paper box set; acquiring special carton product information matched with the minimum damage degree value of the carton; analyzing the breakage degree of the special carton product information to generate carton breakage degree data; generating paper box repair measure data according to the paper box damage degree data; and generating a repair information index value according to the paper box repair measure data, and adding the repair information index value to the paper box update classification information.
Specifically, the method includes the steps of obtaining preset real-time classified capacity data of each current carton classified production line, and judging whether each current carton classified production line is in a normal capacity working state according to the real-time classified capacity data, and specifically includes the following steps:
acquiring theoretical classified yield data of each current carton classified production line; carrying out actual capacity statistics on each preset current carton classified production line, and acquiring real-time classified capacity data after the actual capacity statistics; carrying out capacity data screening on the capacity in the high-capacity monitoring time period in the real-time classified capacity data, and acquiring high-capacity state screening data; performing capacity state analysis and comparison according to the theoretical classified yield data and the high-capacity state screening data, and generating a capacity comparison and analysis result; and judging whether each current carton classification production line is in a normal capacity working state or not according to the capacity comparison analysis result.
Specifically, capacity data screening is carried out on capacity within a high-capacity monitoring time period in the real-time classified capacity data, and high-capacity state screening data is obtained; the method specifically comprises the following steps:
presetting a high-productivity monitoring time period; performing data screening on the real-time classified capacity data according to the high-yield monitoring time period, and generating a high-yield state data change table; high-yield data bump collection is carried out according to the high-yield state data change table, high-difference energy data bumps are obtained, high-efficiency data collection is carried out on the high-yield state data change table, and high-efficiency data points are obtained; and generating high-yield state screening data according to the high-difference energy data salient points and the high-efficiency data points.
Specifically, the method comprises the following steps of judging whether each current carton classification production line is in a normal capacity working state according to the capacity comparison analysis result, and then:
when the high-capacity state screening data exceeds the theoretical classified yield data, namely, when the current carton classified production line is judged not to be in a normal capacity working state according to the capacity comparison analysis result, generating a capacity adjusting instruction; acquiring adjustment parameters of the productivity comparison and analysis result according to the productivity adjustment instruction, and generating a productivity adjustment vector; performing simulation adjustment on the high-yield state screening data according to the productivity adjustment vector, generating a simulation adjustment result value, and generating an adjustable instruction when the simulation adjustment result value is greater than or equal to a preset qualified adjustment value; and carrying out capacity adjustment on each current carton classification production line according to the adjustable instruction and the capacity adjustment vector.
The invention has the following technical effects:
according to the carton classifying method, the preset real-time classified capacity data of each current carton classified production line is obtained in sequence, and whether each current carton classified production line is in a normal capacity working state or not is judged according to the real-time classified capacity data; if so, respectively generating current capacity state identifiers according to each current carton classifying production line, acquiring basic information of actual output cartons of each current carton classifying production line, and respectively acquiring complete degree values of cartons to be classified according to the basic information of the actual output cartons; generating basic data identification of the paper box to be classified according to actual output paper box basic information corresponding to each current paper box classification production line and the integrity value of the box body of the paper box to be classified, and judging whether the characteristic matching degree value of each basic data identification of the paper box to be classified and each standard classification reference value in a preset standard classification reference set meets a preset matching threshold value or not; if the current production capacity data is judged to be in the normal production capacity working state, the current carton classification production line is judged to be in the normal production capacity working state by obtaining the preset real-time classification production capacity data of each current carton classification production line, and when the current carton classification production line is judged to be in the normal production capacity working state, in order to realize tracing of the subsequent classification data, namely tracing of which assembly line each paper box to be classified is output from, current capacity state identification is respectively generated according to each current paper box classification production assembly line, wherein the current capacity state identification comprises capacity data of the current paper box classification production assembly line and assembly line identification data of the current paper box classification production assembly line, the assembly line identification data corresponds to the current paper box classification production assembly line and is used for representing the current paper box classification production assembly line, in order to further classify the paper boxes, actual output paper box basic information of each current paper box classification production assembly line is required to be obtained, and according to each actual output paper box basic information, the complete degree value of the paper box body of the paper box to be classified is respectively obtained, and the complete degree value of the paper box body of the paper box to be classified is used for representing the complete degree of the paper box to be classified, the method is characterized in that the method is expanded in a numerical value mode, so that the data display is realized, the subsequent classification efficiency is improved, and in order to further classify the paper boxes, basic data identification of the paper boxes to be classified is generated according to actual output paper box basic information corresponding to each current paper box classification production line and the integrity value of the paper box bodies to be classified, the basic data identification of the paper boxes to be classified is identification associated with the integrity value of the paper box bodies to be classified, meanwhile, a standard classification reference set is preset, a standard classification reference set is set in the standard classification reference set, so that whether the characteristic matching degree value of each basic data identification of the paper boxes to be classified and each standard classification reference value meets a preset matching threshold value is judged, and when the judgment is met, the paper boxes to be classified meeting the preset matching threshold value belong to the corresponding standard classification category, then, the initial classification information of the paper boxes is generated, and in order to achieve the rigor of classification and the comprehensiveness of classification consideration, the updated classification information of the paper boxes is generated according to the initial classification information of the paper boxes, the current capacity state identification, the integrity degree value of the paper boxes to be classified and the basic data identification of the paper boxes to be classified, so that the updated classification information of the paper boxes is a result achieved after multi-aspect information is integrated, the accuracy and the reliability of classification of the paper boxes are improved, repeated classification is not needed, and the classification efficiency of the paper boxes is indirectly improved.
Drawings
FIG. 1 is a schematic flow diagram of a carton sorting method in one embodiment;
FIG. 2 is a block diagram of the structure of a carton sorting system in one embodiment;
FIG. 3 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, there is provided a carton sorting method comprising:
step S100: acquiring preset real-time classified capacity data of each current carton classified production line, and judging whether each current carton classified production line is in a normal capacity working state or not according to the real-time classified capacity data;
specifically, the carton classification method is applied to a plurality of carton classification production lines, the cartons to be classified are the cartons needing to be recycled, and the types and the damage degrees of the cartons are different, so that the cartons need to be classified according to parameters such as the types, the damage degrees and the like.
Further, in order to ensure the normal operation of the classification work, firstly, before classifying the paper boxes to be classified output by each current paper box classification production line, whether each current paper box classification production line is in a normal working state is judged, that is, the preset real-time classification capacity data of each current paper box classification production line is obtained, and whether each current paper box classification production line is in a normal capacity working state is judged according to the real-time classification capacity data.
Step S200: if so, respectively generating current capacity state identifiers according to each current carton classifying production line, acquiring basic information of actual output cartons of each current carton classifying production line, and respectively acquiring complete degree values of cartons to be classified according to the basic information of the actual output cartons;
specifically, when each current carton classifying production line is judged to be in a normal capacity working state, in order to realize tracing of the subsequent classifying data, namely tracing of which production line each carton to be classified is output from, current capacity state identification is respectively generated according to each current carton classifying production line, wherein the current capacity state identification comprises capacity data of the current carton classifying production line and production line identification data of the current carton classifying production line, the production line identification data corresponds to the current carton classifying production line and is used for representing the current carton classifying production line, in order to further classify the cartons, actual output carton basic information of each current carton classifying production line needs to be obtained, and a carton body integrity degree value of the carton to be classified is respectively obtained according to each actual output carton basic information, the integrity degree value of the box body of the paper box to be classified is used for representing the integrity degree of the paper box to be classified, and the data display is realized by expanding the integrity degree value in a numerical value mode, so that the subsequent classification efficiency is improved.
The basic information of the actual output paper box comprises material information, shape information and knife edge data of the actual output paper box. The material information is preferably acquired by spectral analysis, the shape information is acquired by a CCD camera, the knife edge data is cutting position data, or the material information may be acquired by image acquisition by a CCD camera.
It should be understood that the integrity degree value of the carton body to be classified is only intermediate data, and the integrity degree value is used for selecting and storing records according to actual requirements and is used as the intermediate data to facilitate subsequent convenient comparison.
Step S300: generating basic data identifiers of the paper boxes to be classified according to actual output paper box basic information corresponding to each current paper box classification production line and the integrity degree value of the paper boxes to be classified, and judging whether the characteristic matching degree value of each basic data identifier of the paper boxes to be classified and each standard classification reference value in a preset standard classification reference set meets a preset matching threshold value or not, wherein one standard classification reference set corresponds to one standard classification category;
specifically, in order to further classify the paper boxes, basic data identifiers of the paper boxes to be classified are generated according to actual output paper box basic information corresponding to each current paper box classification production line and integrity values of the paper boxes to be classified, the basic data identifiers of the paper boxes to be classified are identifiers associated with the integrity values of the paper boxes to be classified, meanwhile, a standard classification reference set is preset, and a standard classification reference set is set in the standard classification reference set, so that whether a preset matching threshold value is met or not is judged by judging whether a feature matching degree value of each basic data identifier of the paper boxes to be classified and each standard classification reference value meets the preset matching threshold value, and when the preset matching threshold value is met, the paper boxes to be classified which meet the preset matching threshold value belong to the corresponding standard classification category.
Further, in this embodiment, the basic data identifier of the paper box to be classified is implemented by using a two-dimensional code, and the two-dimensional codes representing the integrity degree values of the paper box body to be classified are different, that is, different integrity degrees correspond to different two-dimensional codes, and the integrity degree values appearing after different two-dimensional codes are scanned are also different, for example, when the integrity degree of the paper box body to be classified is 100%, the displayed information is a-100 after scanning the corresponding two-dimensional codes, wherein 100 represents that the integrity degree value is 100, when the integrity degree of the paper box body to be classified is 95% intact due to damage, the displayed integrity degree value is a-95 after scanning the corresponding two-dimensional codes, and wherein 95 represents that the integrity degree value is 95. A contains the basic information of the actual output paper box.
Of course, the above information representation is only an example and is not particularly limited.
Furthermore, the paper box basic data identification to be classified is not only associated with the paper box body integrity degree value to be classified, but also associated with the actual output paper box basic information, and it is understood that the paper box basic data identification to be classified is comprehensive marking information generated after the actual output paper box basic information and the paper box body integrity degree value to be classified are integrated, and the paper box basic data identification to be classified mainly has the main function of facilitating subsequent classification of the paper box, namely, classification is carried out by using one comprehensive marking information, so that twice classification is avoided respectively carried out by the actual output paper box basic information and the paper box body integrity degree value to be classified, and the classification efficiency is improved.
The method comprises the steps that a preset standard classification reference set is used for storing a standard classification reference value, wherein each standard classification reference value in the preset standard classification reference set is a string of English codes and digital codes with reference information, such as B-96, B-32, C-84 and the like, wherein the English codes represent basic information of an actual output paper box, preferably material information representing the actual output paper box, and then, in the process of judging whether feature matching degree values of basic data identification of each paper box to be classified and each standard classification reference value in the preset standard classification reference set meet preset matching threshold values or not, a similarity algorithm is adopted to judge whether matching is achieved through similarity values.
Step S400: if the classification information is judged to be the initial classification information, generating initial classification information of the paper boxes, and generating updated classification information of the paper boxes according to the initial classification information of the paper boxes, the current capacity state identification, the complete degree value of the paper boxes to be classified and the basic data identification of the paper boxes to be classified.
Specifically, for the purpose of the rigor of classification and the comprehensiveness of classification consideration, the carton updating classification information is generated according to the initial carton classification information, the current capacity state identifier, the integrity degree value of the carton body of the carton to be classified and the basic data identifier of the carton to be classified, so that the carton updating classification information is a result obtained after multi-aspect information is integrated, the accuracy and the reliability of carton classification are improved, repeated multiple classification is not needed, and the carton classification efficiency is indirectly improved.
Specifically, the initial carton classification information further comprises the generation time of the initial carton classification information, and when the updated carton classification information is generated according to the initial carton classification information, the current capacity state identifier, the complete degree value of the carton body of the carton to be classified and the basic data identifier of the carton to be classified, the traceability of each time information in the subsequent updated carton classification information is improved by adding the generation time information.
In one embodiment, step S200: if so, respectively generating current capacity state identifiers according to each current carton classifying production line, acquiring basic information of actual output cartons of each current carton classifying production line, and respectively acquiring complete degree values of cartons to be classified according to the basic information of the actual output cartons; then also comprises the following steps:
step S210: acquiring a numerical value set of which the box body integrity degree value of the paper boxes to be classified corresponding to each current paper box classification production line is smaller than a preset paper box minimum damage degree value, wherein the set formed by the paper boxes to be classified corresponding to the numerical value set is a non-receiving paper box set;
step S220: acquiring special carton product information matched with the minimum damage degree value of the carton;
step S230: analyzing the breakage degree of the special carton product information to generate carton breakage degree data;
step S240: generating paper box repair measure data according to the paper box damage degree data;
step S250: and generating a repair information index value according to the paper box repair measure data, and adding the repair information index value to the paper box update classification information.
Specifically, the minimum damage degree value of the carton is preset, the carton to be classified corresponding to the minimum damage degree value of the carton is damaged to the extent that the carton cannot be directly recycled and needs to be repaired, therefore, special carton product information matched with the minimum damage degree value of the carton is obtained, the special carton product information is actual information of the carton in the unreceived carton set and comprises the damage degree grade, damage reason analysis and damage area statistics, then, carton repair measure data is generated according to the carton damage degree data, the carton repair measure data is data formed by integrating corresponding repair measures according to the data of the damage degree grade, the damage reason analysis and the damage area statistics, and the generated repair information index value represents the steps spent in the repair process, And the repair information index value is added to the carton updating classification information, so that cost statistics processing can be conveniently carried out on the sorted data of the carton in the follow-up process.
In one embodiment, step S100: the method comprises the steps of obtaining preset real-time classified capacity data of each current carton classified production line, and judging whether each current carton classified production line is in a normal capacity working state according to the real-time classified capacity data, and specifically comprises the following steps:
step S110: acquiring theoretical classified yield data of each current carton classified production line;
step S120: carrying out actual capacity statistics on each preset current carton classified production line, and acquiring real-time classified capacity data after the actual capacity statistics;
step S130: carrying out capacity data screening on the capacity in the high-capacity monitoring time period in the real-time classified capacity data, and acquiring high-capacity state screening data;
step S140: performing capacity state analysis and comparison according to the theoretical classified yield data and the high-capacity state screening data, and generating a capacity comparison and analysis result;
step S150: and judging whether each current carton classification production line is in a normal capacity working state or not according to the capacity comparison analysis result.
Specifically, each theoretical classified yield data corresponds to each current carton classified production line one to one and is used for representing theoretically achievable capacity of each current carton classified production line, then capacity data screening is performed on capacity within a high-capacity monitoring time period in the real-time classified capacity data, and high-capacity state screening data is obtained, the high-capacity monitoring time period is divided in advance according to actual capacity, specifically, 10% of the data of capacity arrangement in different capacity data is extracted according to different capacity data, and capacity state analysis and comparison are performed according to the theoretical classified yield data and the high-capacity state screening data, and a generated capacity comparison analysis result is used for judging whether each current carton classified production line is in a normal capacity working state or not.
Further, the high-throughput screening data represents throughput data of the current carton sorting production line in a relatively optimized working state, preferably measured by the throughput of the production line in this embodiment. If the yield obtained after extracting the data of 10% of the first capacity arrangement in the different capacity data is 10000 pieces/hour, and the theoretical classified yield data is 9800 pieces/hour-12000 pieces/hour, the capacity state analysis and comparison are carried out according to the theoretical classified yield data and the high-capacity state screening data, namely 10000 pieces/hour and 9800 pieces/hour-12000 pieces/hour are obtained, and the generated capacity comparison and analysis result is that: the actual capacity is within the theoretical capacity data range, and the result of the capacity comparison analysis shows that the capacity is normal, namely, the capacity is in a normal capacity working state, otherwise, the capacity is abnormal.
And then the capacity state analysis and comparison are carried out according to the theoretical classified yield data and the high-capacity state screening data, and the generated capacity comparison and analysis result is used for judging whether each current carton classified production line is in a normal capacity working state or not.
In one embodiment, step S130: carrying out capacity data screening on the capacity in the high-capacity monitoring time period in the real-time classified capacity data, and acquiring high-capacity state screening data; the method specifically comprises the following steps:
step S131: presetting a high-productivity monitoring time period;
step S132: performing data screening on the real-time classified capacity data according to the high-yield monitoring time period, and generating a high-yield state data change table;
step S133: high-yield data bump collection is carried out according to the high-yield state data change table, high-difference energy data bumps are obtained, high-efficiency data collection is carried out on the high-yield state data change table, and high-efficiency data points are obtained;
step S134: and generating high-yield state screening data according to the high-difference energy data salient points and the high-efficiency data points.
Specifically, a high-capacity monitoring time period is set, then data screening is performed on the real-time classified capacity data, a high-capacity state data change table is generated, capacity visual statistics is performed through the high-capacity state data change table, then high-capacity data bump collection is performed according to the high-capacity state data change table, high-differential-energy data bumps are obtained, high-efficiency data collection is performed on the high-capacity state data change table, high-efficiency data points are obtained, the high-differential-energy data bumps are peak points of capacity data in a certain time period, the high-efficiency data points are starting points of the capacity data, the capacity rate of the capacity data is larger than a preset standard rate, and further, high-capacity state screening data are generated according to the high-differential-energy data bumps and the high-efficiency data points.
In one embodiment, step S150: judging whether each current carton classification production line is in a normal capacity working state or not according to the capacity comparison analysis result, and then, the method further comprises the following steps:
step S151: when the high-capacity state screening data exceeds the theoretical classified yield data, namely, when the current carton classified production line is judged not to be in a normal capacity working state according to the capacity comparison analysis result, generating a capacity adjusting instruction;
step S152: acquiring adjustment parameters of the productivity comparison and analysis result according to the productivity adjustment instruction, and generating a productivity adjustment vector;
step S153: performing simulation adjustment on the high-yield state screening data according to the productivity adjustment vector, generating a simulation adjustment result value, and generating an adjustable instruction when the simulation adjustment result value is greater than or equal to a preset qualified adjustment value;
step S154: and carrying out capacity adjustment on each current carton classification production line according to the adjustable instruction and the capacity adjustment vector.
Specifically, in order to ensure the normal capacity of each current carton sorting production line and to perform adjustment during abnormal capacity, when it is determined that the high-capacity screening data exceeds the theoretical sorting yield data, that is, when it is determined that each current carton sorting production line is not in a normal capacity working state according to the capacity comparison analysis result, a capacity adjustment command is generated, then adjustment parameters are obtained according to the capacity adjustment command from the capacity comparison analysis result, and a capacity adjustment vector is generated, wherein the capacity adjustment vector is a capacity to be increased or decreased, when the direction of the capacity adjustment vector is a positive direction, the capacity needs to be increased, when the direction of the capacity adjustment vector is a negative direction, the capacity needs to be decreased, and then the high-capacity screening data is simulation-adjusted according to the capacity adjustment vector, and generating a simulation adjustment result value, generating an adjustable instruction when the simulation adjustment result value is greater than or equal to a preset qualified adjustment value, and explaining that the adjustment is effective when the simulation adjustment result value is greater than or equal to the preset qualified adjustment value, so that the productivity of each current carton classification production line is adjusted according to the adjustable instruction and the productivity adjustment vector.
In summary, in order to ensure the normal operation of the sorting operation, the present invention first determines whether each current carton sorting production line is in a normal operation state before sorting the cartons to be sorted output by each current carton sorting production line, that is, by obtaining the preset real-time sorted capacity data of each current carton sorting production line and determining whether each current carton sorting production line is in a normal capacity operation state according to the real-time sorted capacity data, and when each current carton sorting production line is determined to be in a normal capacity operation state, in order to trace the source of the sorted data later, that is, from which production line each carton to be sorted is output, respectively generates the current capacity state identifier according to each current carton sorting production line, the current capacity state identification comprises capacity data of a current carton classification production line and line identification data of the current carton classification production line, the line identification data corresponds to the current carton classification production line and is used for representing the current carton classification production line, in order to further classify the cartons, actual output carton basic information of each current carton classification production line needs to be obtained, and complete degree values of the cartons to be classified are respectively obtained according to the actual output carton basic information, the complete degree values of the cartons to be classified are used for representing the complete degree of the cartons to be classified, through numerical value expansion, digitalized data display is achieved, subsequent classification efficiency is improved, in order to further classify the cartons, the actual output carton basic information corresponding to each current carton classification production line and the complete degree values of the cartons to be classified need to be obtained according to the actual output carton basic information and the complete degree values of the cartons to be classified Generating a basic data identifier of a paper box to be classified, wherein the basic data identifier of the paper box to be classified is an identifier associated with the integrity degree value of the box body of the paper box to be classified, and meanwhile, a standard classification reference set is preset and set in the standard classification reference set so as to generate updated classification information of the paper box for the purpose of judging whether the characteristic matching degree value of each basic data identifier of the paper box to be classified and each standard classification reference value meets a preset matching threshold value or not, when the characteristic matching degree value of each basic data identifier of the paper box to be classified and each standard classification reference value meets the preset matching threshold value, indicating that the paper box to be classified meeting the preset matching threshold value belongs to the corresponding standard classification category, then generating initial classification information of the paper box, and generating updated classification information of the paper box for the purpose of classification rigor classification consideration, further, the carton classification updating information is a result achieved after multi-aspect information is integrated, the accuracy and the reliability of carton classification are improved, repeated classification is not needed, and the carton classification efficiency is indirectly improved.
In one embodiment, as shown in fig. 2, there is provided a carton sorting system comprising:
the production capacity obtaining module is used for obtaining preset real-time classified production capacity data of each current carton classified production line and judging whether each current carton classified production line is in a normal production capacity working state or not according to the real-time classified production capacity data;
the information acquisition module is used for respectively generating current capacity state identifiers according to each current carton classification production line if the current production capacity state identifiers are judged to be yes, acquiring basic information of actual output cartons of each current carton classification production line, and simultaneously respectively acquiring complete degree values of cartons to be classified according to the basic information of the actual output cartons;
the threshold matching module is used for generating basic data identifiers of the paper boxes to be classified according to actual output paper box basic information and the integrity degree value of the paper boxes to be classified corresponding to each current paper box classification production line, and judging whether the feature matching degree value of each basic data identifier of the paper boxes to be classified and each standard classification reference value in a preset standard classification reference set meets a preset matching threshold or not, wherein one standard classification reference set corresponds to one standard classification category;
and the classification information module is used for generating initial classification information of the paper boxes if the judgment result is yes, and generating updated classification information of the paper boxes according to the initial classification information of the paper boxes, the current capacity state identifier, the complete degree value of the paper boxes to be classified and the basic data identifier of the paper boxes to be classified.
In one embodiment, the information obtaining module is further configured to:
acquiring a numerical value set of which the box body integrity degree value of the paper boxes to be classified corresponding to each current paper box classification production line is smaller than a preset paper box minimum damage degree value, wherein the set formed by the paper boxes to be classified corresponding to the numerical value set is a non-receiving paper box set; acquiring special carton product information matched with the minimum damage degree value of the carton; analyzing the breakage degree of the special carton product information to generate carton breakage degree data; generating paper box repair measure data according to the paper box damage degree data; and generating a repair information index value according to the paper box repair measure data, and adding the repair information index value to the paper box update classification information.
In one embodiment, the capacity obtaining module is further configured to:
acquiring theoretical classified yield data of each current carton classified production line; carrying out actual capacity statistics on each preset current carton classified production line, and acquiring real-time classified capacity data after the actual capacity statistics; carrying out capacity data screening on the capacity in the high-capacity monitoring time period in the real-time classified capacity data, and acquiring high-capacity state screening data; performing capacity state analysis and comparison according to the theoretical classified yield data and the high-capacity state screening data, and generating a capacity comparison and analysis result; judging whether each current carton classification production line is in a normal capacity working state or not according to the capacity comparison analysis result; presetting a high-productivity monitoring time period; performing data screening on the real-time classified capacity data according to the high-yield monitoring time period, and generating a high-yield state data change table; high-yield data bump collection is carried out according to the high-yield state data change table, high-difference energy data bumps are obtained, high-efficiency data collection is carried out on the high-yield state data change table, and high-efficiency data points are obtained; generating high-yield state screening data according to the high-difference energy data salient points and the high-efficiency data points; when the high-capacity state screening data exceeds the theoretical classified yield data, namely, when the current carton classified production line is judged not to be in a normal capacity working state according to the capacity comparison analysis result, generating a capacity adjusting instruction; acquiring adjustment parameters of the productivity comparison and analysis result according to the productivity adjustment instruction, and generating a productivity adjustment vector; performing simulation adjustment on the high-yield state screening data according to the productivity adjustment vector, generating a simulation adjustment result value, and generating an adjustable instruction when the simulation adjustment result value is greater than or equal to a preset qualified adjustment value; and carrying out capacity adjustment on each current carton classification production line according to the adjustable instruction and the capacity adjustment vector.
In one embodiment, as shown in fig. 3, a computer device comprises a memory storing a computer program and a processor implementing the steps of the above carton sorting method when the processor executes the computer program.
A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of the above-described carton sorting method.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. A method of carton sorting, the method comprising:
acquiring preset real-time classified capacity data of each current carton classified production line, and judging whether each current carton classified production line is in a normal capacity working state or not according to the real-time classified capacity data; if so, respectively generating current capacity state identifiers according to each current carton classifying production line, acquiring basic information of actual output cartons of each current carton classifying production line, and respectively acquiring complete degree values of cartons to be classified according to the basic information of the actual output cartons; generating basic data identifiers of the paper boxes to be classified according to actual output paper box basic information corresponding to each current paper box classification production line and the integrity degree value of the paper boxes to be classified, and judging whether the characteristic matching degree value of each basic data identifier of the paper boxes to be classified and each standard classification reference value in a preset standard classification reference set meets a preset matching threshold value or not, wherein one standard classification reference set corresponds to one standard classification category; if the classification information is judged to be the initial classification information, generating initial classification information of the paper boxes, and generating updated classification information of the paper boxes according to the initial classification information of the paper boxes, the generation time of the initial classification information of the paper boxes, the current capacity state identification, the complete degree value of the boxes of the paper boxes to be classified and the basic data identification of the paper boxes to be classified.
2. The carton classifying method according to claim 1, wherein if yes, respectively generating a current capacity status identifier according to each current carton classifying production line, and obtaining basic information of actual output cartons of each current carton classifying production line, and respectively obtaining a box integrity degree value of a carton to be classified according to each basic information of actual output cartons; then also comprises the following steps:
acquiring a numerical value set of which the box body integrity degree value of the paper boxes to be classified corresponding to each current paper box classification production line is smaller than a preset paper box minimum damage degree value, wherein the set formed by the paper boxes to be classified corresponding to the numerical value set is a non-receiving paper box set; acquiring special carton product information matched with the minimum damage degree value of the carton; analyzing the breakage degree of the special carton product information to generate carton breakage degree data; generating paper box repair measure data according to the paper box damage degree data; and generating a repair information index value according to the paper box repair measure data, and adding the repair information index value to the paper box update classification information.
3. The carton classifying method according to claim 2, wherein the step of obtaining preset real-time classified capacity data of each current carton classified production line and judging whether each current carton classified production line is in a normal capacity working state according to the real-time classified capacity data comprises the steps of:
acquiring theoretical classified yield data of each current carton classified production line; carrying out actual capacity statistics on each preset current carton classified production line, and acquiring real-time classified capacity data after the actual capacity statistics; carrying out capacity data screening on the capacity in the high-capacity monitoring time period in the real-time classified capacity data, and acquiring high-capacity state screening data; performing capacity state analysis and comparison according to the theoretical classified yield data and the high-capacity state screening data, and generating a capacity comparison and analysis result; and judging whether each current carton classification production line is in a normal capacity working state or not according to the capacity comparison analysis result.
4. A carton sorting method according to claim 3, wherein the capacity data is screened for capacity within the high-capacity monitoring period of the real-time sorted capacity data, and the high-capacity status screening data is obtained; the method specifically comprises the following steps:
presetting a high-productivity monitoring time period; performing data screening on the real-time classified capacity data according to the high-yield monitoring time period, and generating a high-yield state data change table; high-yield data bump collection is carried out according to the high-yield state data change table, high-difference energy data bumps are obtained, high-efficiency data collection is carried out on the high-yield state data change table, and high-efficiency data points are obtained; and generating high-yield state screening data according to the high-difference energy data salient points and the high-efficiency data points.
5. The carton classifying method according to claim 4, wherein the step of determining whether each of the current carton classifying production lines is in a normal capacity working state according to the productivity comparison analysis result further comprises:
and when the high-capacity state screening data exceeds the theoretical classified yield data, namely, when the current carton classified production line is judged not to be in a normal capacity working state according to the capacity comparison analysis result, generating a capacity adjusting instruction.
6. The carton sorting method of claim 5, wherein said generating a capacity adjustment command further comprises:
and acquiring adjustment parameters of the productivity comparison and analysis result according to the productivity adjustment instruction, and generating a productivity adjustment vector.
7. The carton sorting method of claim 6, wherein said generating a capacity adjustment vector further comprises:
and performing simulation adjustment on the high-yield state screening data according to the productivity adjustment vector, generating a simulation adjustment result value, and generating an adjustable instruction when the simulation adjustment result value is greater than or equal to a preset qualified adjustment value.
8. A carton sorting method according to claim 7, wherein said generating an adjustable instruction further comprises:
and carrying out capacity adjustment on each current carton classification production line according to the adjustable instruction and the capacity adjustment vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111167098.6A CN113592043B (en) | 2021-10-02 | 2021-10-02 | Carton classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111167098.6A CN113592043B (en) | 2021-10-02 | 2021-10-02 | Carton classification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113592043A CN113592043A (en) | 2021-11-02 |
| CN113592043B true CN113592043B (en) | 2021-12-07 |
Family
ID=78242824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111167098.6A Active CN113592043B (en) | 2021-10-02 | 2021-10-02 | Carton classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113592043B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116430818B (en) * | 2023-06-05 | 2023-09-15 | 鲁控数字技术(山东)有限公司 | Automatic production line production method and system based on control of multi-station program control equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393912A (en) * | 2011-11-01 | 2012-03-28 | 中国电子科技集团公司第二十八研究所 | Comprehensive target identification method based on uncertain reasoning |
| CN109178724A (en) * | 2018-11-12 | 2019-01-11 | 任杰 | Classification recycling client, checks and accepts device, recovery system and method at recycling bins |
| CN112306024A (en) * | 2020-05-08 | 2021-02-02 | 陈晓清 | Equipment operation state determination method combined with intelligent park and big data center |
| CN112718572A (en) * | 2021-04-02 | 2021-04-30 | 浙江大胜达包装股份有限公司 | Automatic management system and method for classification of recycled paper products |
| CN112819793A (en) * | 2021-02-01 | 2021-05-18 | 宁波港信息通信有限公司 | Container damage identification method, device, equipment and readable access medium |
| CN112989861A (en) * | 2021-02-08 | 2021-06-18 | 北京声智科技有限公司 | Sample identification code reading method and device, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008112209A (en) * | 2006-10-27 | 2008-05-15 | Omron Corp | Operating condition monitoring apparatus, method for monitoring operating condition and program |
| US8463805B2 (en) * | 2010-09-15 | 2013-06-11 | Cbs Interactive, Inc. | Mapping product identification information to a product |
-
2021
- 2021-10-02 CN CN202111167098.6A patent/CN113592043B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393912A (en) * | 2011-11-01 | 2012-03-28 | 中国电子科技集团公司第二十八研究所 | Comprehensive target identification method based on uncertain reasoning |
| CN109178724A (en) * | 2018-11-12 | 2019-01-11 | 任杰 | Classification recycling client, checks and accepts device, recovery system and method at recycling bins |
| CN112306024A (en) * | 2020-05-08 | 2021-02-02 | 陈晓清 | Equipment operation state determination method combined with intelligent park and big data center |
| CN112819793A (en) * | 2021-02-01 | 2021-05-18 | 宁波港信息通信有限公司 | Container damage identification method, device, equipment and readable access medium |
| CN112989861A (en) * | 2021-02-08 | 2021-06-18 | 北京声智科技有限公司 | Sample identification code reading method and device, electronic equipment and storage medium |
| CN112718572A (en) * | 2021-04-02 | 2021-04-30 | 浙江大胜达包装股份有限公司 | Automatic management system and method for classification of recycled paper products |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113592043A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113592043B (en) | Carton classification method | |
| CN116560327B (en) | Electric tool production control method and system based on Internet of things | |
| US20140303912A1 (en) | System and method for the automatic determination of critical parametric electrical test parameters for inline yield monitoring | |
| CN108764361B (en) | Working condition identification method of indicator diagram of beam-pumping unit based on integrated learning | |
| CN113537414B (en) | Lithium battery defect detection method, device, equipment and storage medium | |
| CN116992740B (en) | Intelligent regulation and control method and system for communication base station precise component production equipment | |
| CN114708587B (en) | Image recognition-based numerical control machine tool workpiece machining allowance determination method | |
| CN117608259A (en) | Control method and system for storage chip production equipment | |
| CN107194414A (en) | A kind of SVM fast Incremental Learning Algorithms based on local sensitivity Hash | |
| CN113487607A (en) | Defect detection method and device based on multi-view-field image | |
| CN116071298A (en) | Tool loss identification method and device based on target detection model | |
| CN115731220A (en) | Grey cloth defect positioning and classifying method, system, equipment and storage medium | |
| CN115301559A (en) | Efficient screening and sorting method and system for recycling retired batteries | |
| CN112580935A (en) | Industrial product production process traceability analysis method based on machine vision | |
| CN117952983B (en) | Intelligent manufacturing production process monitoring method and system based on artificial intelligence | |
| CN118015613A (en) | Machine learning-based apple picking multi-type image recognition method | |
| CN116776647B (en) | Performance prediction method and system for composite nickel-copper-aluminum heat dissipation bottom plate | |
| CN117095247B (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| CN113221548A (en) | BOM table identification method and device based on machine learning, computer equipment and medium | |
| CN110472656B (en) | Vehicle image classification method, device, computer equipment and storage medium | |
| CN116106331B (en) | Online detection device and detection method for automobile battery shell | |
| US20200082281A1 (en) | Verification device | |
| Zanon et al. | Analysis of IC manufacturing process deformations: An automated approach using SRAM bit fail maps | |
| CN111401467B (en) | Remote sensing image classification method, image processing device and computer readable storage device | |
| CN118505688B (en) | Method, device, equipment and storage medium for detecting images of keyboard screen printing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |