CN117314243A - Method for evaluating efficiency of operators based on cluster analysis - Google Patents
Method for evaluating efficiency of operators based on cluster analysis Download PDFInfo
- Publication number
- CN117314243A CN117314243A CN202311285041.5A CN202311285041A CN117314243A CN 117314243 A CN117314243 A CN 117314243A CN 202311285041 A CN202311285041 A CN 202311285041A CN 117314243 A CN117314243 A CN 117314243A
- Authority
- CN
- China
- Prior art keywords
- efficiency
- picker
- picking
- operation behavior
- clustering
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000007621 cluster analysis Methods 0.000 title claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 27
- 101000762967 Homo sapiens Lymphokine-activated killer T-cell-originated protein kinase Proteins 0.000 claims description 6
- 102100026753 Lymphokine-activated killer T-cell-originated protein kinase Human genes 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 46
- 238000003860 storage Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 2
- 235000018185 Betula X alpestris Nutrition 0.000 description 1
- 235000018212 Betula X uliginosa Nutrition 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000011265 semifinished product Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of e-commerce warehouse logistics, in particular to a method for evaluating the efficiency of operators based on cluster analysis; the method comprises the following steps: s1, defining a picker operation behavior index by combining picker historical behavior data, wherein the picker operation behavior index comprises a piece dimension picking efficiency and a position dimension picking efficiency; s2, carrying out cluster analysis on the working efficiency of the pickers through a plurality of clustering algorithms according to the operation behavior indexes of the pickers, selecting the clustering algorithm closest to the actual clustering algorithm, and outputting the clustering result of the clustering algorithm to obtain the evaluation result of the working efficiency of the pickers; through setting a plurality of parameters in the dimension and the position dimension, the parameters in the two dimensions are paired one by one, clustering is carried out through a plurality of clustering algorithms, the most suitable clustering algorithm is obtained, the most accurate evaluation result in the clustering algorithm is obtained, the cluster analysis of the work efficiency of the pickers can be more accurately obtained, the follow-up pickers are favorably distributed, and the improvement of the pickers is favorably realized.
Description
Technical Field
The invention relates to the technical field of e-commerce warehouse logistics, in particular to a method for evaluating the efficiency of operators based on cluster analysis.
Background
The logistics refers to the whole process of planning, implementing and managing raw materials, semi-finished products, finished products or related information from the place of production of the commodity to the place of consumption of the commodity by means of transportation, storage, distribution and the like in order to meet the demands of customers. Along with the development of economy and the rise of electronic commerce, electronic commerce logistics accounts for the vast majority of logistics industry, electronic commerce logistics efficiency determines the efficiency of the whole logistics industry, and electronic commerce logistics in-house operation efficiency is an important ring in an electronic commerce logistics supply chain, wherein in-house goods picking operation efficiency accounts for more than half of the whole in-house operation cost, so that improvement of in-house operation efficiency is a key step of electronic commerce logistics improvement efficiency.
The prior art CN111738539a discloses a method, a device, equipment and a medium for distributing a picking task, wherein the distributing method comprises the following steps: when the order picking task allocation instruction is triggered, acquiring position information of the order picking task to be allocated; clustering the picking tasks to be distributed according to the position information to obtain a target clustering result; according to the target clustering result, the goods picking tasks to be distributed are distributed, the goods picking tasks to be distributed are clustered according to the position information of the goods picking tasks to be distributed, and task distribution is carried out according to the clustering result, but the method only mentions how to cluster the goods picking tasks, defaults that all the goods pickers have the same goods picking speed and equal capacity, but in practice, the goods picking speeds of the goods pickers are not equal, and therefore the goods picking efficiency can be affected.
Therefore, it is desirable to provide a method for evaluating the efficiency of operators based on cluster analysis, which clusters the work efficiency of pickers and further improves the picking efficiency compared with the prior art.
Disclosure of Invention
The invention solves the technical problems in the prior art, and provides a method for evaluating the efficiency of operators based on cluster analysis.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a method for evaluating the efficiency of operators based on cluster analysis comprises the following steps:
s1, defining a picker operation behavior index by combining picker historical behavior data, wherein the picker operation behavior index comprises a piece dimension picking efficiency and a position dimension picking efficiency;
s2, carrying out cluster analysis on the working efficiency of the pickers through a plurality of clustering algorithms according to the operation behavior indexes of the pickers, selecting the clustering algorithm closest to the actual clustering algorithm, and outputting the clustering result of the clustering algorithm to obtain the evaluation result of the working efficiency of the pickers.
Further, the piece dimension picking efficiency comprises daily piece average picking efficiency, the median of piece daily average picking efficiency, 1/4 of the number of digits on the piece and 1/4 of the number of digits under the piece, and the bit dimension picking efficiency comprises daily average picking efficiency, the median of bit daily average picking efficiency, 1/4 of the number of digits on the bit and 1/4 of the number of digits under the bit;
the daily piece average picking efficiency and the daily position average picking efficiency are set as a first operation behavior index group; the median of the piece average picking efficiency and the median of the bit average picking efficiency are set as a second operation behavior index group; setting 1/4 quantiles on the piece and 1/4 quantiles on the bit as a third operation behavior index group; the 1/4 quantile under the piece and the 1/4 quantile under the piece are set as a fourth operation behavior index group.
Further, S2 specifically includes the following steps:
s201, processing data in the first operation behavior index group by the following formula:
in the above-mentioned method, the step of,represents x i Daily piece average picking efficiency or daily position average picking efficiency after treatment, u represents x i Delta represents x i Standard deviation of (2);
s202, performing clustering analysis by adopting a plurality of clustering algorithms according to the processed first operation behavior index group data, wherein each clustering algorithm respectively obtains two clustering results of 3 clusters or 4 clusters;
s203, obtaining the Hamming distances or the correlation sizes of different clustering algorithms under the first operation behavior index by adopting a method for checking the performance ranking index in the period or a method for linear correlation according to the actual performance standard;
s204, sequentially replacing the first operation behavior index group in the step S201 with the second operation behavior index group, the third operation behavior index group and the fourth operation behavior index group, and sequentially performing the steps S201-S203 to obtain all clustering results of the four groups of operation behavior index groups by a plurality of clustering algorithms, the Hamming distance or the correlation of each clustering result, selecting the clustering algorithm with the smallest Hamming distance or the largest correlation as a final clustering algorithm, and selecting the clustering result with the smallest Hamming distance or the largest correlation as a final evaluation result.
Further, the method for checking the performance ranking index in the period comprises the following steps: and (3) giving TOPK ranks of the daily piece average picking efficiency after treatment and the daily position average picking efficiency after treatment, and comparing the TOPK ranks with performance ranking indexes in a period respectively to obtain the Hamming distance.
Further, if the minimum hamming distance obtained by the method for verifying the performance ranking index in the period corresponds to two or more algorithms, the number of clusters is increased until the minimum hamming distance is the only algorithm.
Further, the method for linear correlation according to the actual performance standard is as follows: the correlation size is determined by the following equation:
in the above formula, X, Y represents a variable;mean value of X, < >>Represents the mean value of Y; r is (r) x1 Representing the correlation between the X variable and the Y variable; x is X i Representing the value, Y, of the variable X corresponding to the ith picker i The value of the variable Y corresponding to the ith picker is represented, and n represents the number of pickers.
Further, the evaluation results of the work efficiency of the pickers are classified into three kinds of evaluation results or four kinds of evaluation results; the three kinds of evaluation results are high-efficiency working population, normal-efficiency working population and low-efficiency working population, and the four kinds of evaluation results are high-efficiency working population, good-efficiency working population, qualified efficiency working population and unqualified efficiency working population;
for new staff or staff without classified data, the staff is divided into inefficient working groups or efficient working groups.
Further, the daily piece picking efficiency is calculated by the following formula:
in the above, avg_cout_day (x i ) Representing the picking efficiency of the picking person i day pieces; d (D) i Indicating the number of days of the ith picker's labor; cout (Cout) ij Indicating the pick efficiency of picker i for all the items on day j; x is x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0;
daily order picking efficiency is calculated by the following formula:
in the above formula, avg_loc_day (x i ) Indicating the daily average picking efficiency of the pickers i; d (D) i Indicating the number of days of the ith picker's labor; loci j Indicating the position of picker i on day jPicking efficiency; xi indicates whether the ith picker is selected or not, with a selection indicated as 1 and an unselected selection indicated as 0.
Still further, the median of the piece daily picking efficiency is calculated by the following formula:
when Ni is an odd number, it is,
when Ni is an even number, it is,
in the above formula, med_cout (x i ) A median representing the pick rate for the i daily picks; x is x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;express pick i +.>The number of pickups for each task; />Express pick i +.>The number of pickups for each task; />Express pick i +.>The number of pickups for each task;
the median of the average picking efficiency of the bit is calculated by the following formula:
when Ni is an odd number, it is,
when Ni is an even number, it is,
in the above formula, med_loc (x i ) A median representing the i-bit daily picking efficiency of the pickers; x is x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;express pick i +.>The order picking number of the individual tasks; />Express pick i +.>The order picking number of the individual tasks; />Express pick i +.>Order picking number of individual tasks.
Still further, the method further comprises the steps of,
the 1/4 quantile on the part is calculated by the following formula:
when 3 (N) i When +1)/4 is an integer, the number of the units,
when 3 (N) i When +1)/4 is not an integer,
the number of 1/4 quantiles below the piece is calculated by the following formula:
when (N) i When +1)/4 is an integer, the number of the units,
when (N) i When +1)/4 is not an integer,
the 1/4 quantile on the bit is calculated by the following formula:
when 3 (N) i When +1)/4 is an integer, the number of the units,
when 3 (N) i When +1)/4 is not an integer,
the 1/4 quantile under the bit is calculated by the following formula:
when (N) i When +1)/4 is an integer, the number of the units,
when (N) i When +1)/4 is not an integer,
in the above, x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;3 rd (N) representing picker i i +1)/4 order count of tasks, +.>[3 (N) th of the order picker i i +1)/4+1]Order count of task, < >>(N) th of the order picker i i +1)/4 order count of tasks, +.>[ (N) th of the order picker i i +1)/4+1]The number of items picked for the task; />3 rd (N) representing picker i i +1)/4 order picking number, < ->[3 (N) th of the order picker i i +1)/4+1]Order of individual tasks, +.>(N) th of the order picker i i +1)/4 order picking number, < ->[ (N) th of the order picker i i +1)/4+1]Order picking number of individual tasks.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the invention, the parameters in the two dimensions are matched one by one through setting the parameters in the dimension and the position dimension, clustering is carried out through the plurality of clustering algorithms, the most suitable clustering algorithm is obtained, and the most accurate evaluation result in the clustering algorithm is obtained, so that the cluster analysis of the work efficiency of the pickers can be more accurately obtained, the subsequent pickers are favorably distributed, and the improvement of the pickers is favorably realized.
Drawings
Fig. 1 is a flow chart of the method of the present invention.
FIG. 2 is a schematic diagram of a clustering result obtained by the clustering algorithm according to the first operation behavior index set.
Detailed Description
The technical solutions of the present invention will be clearly described below with reference to the accompanying drawings, and it is obvious that the described embodiments are not all embodiments of the present invention, and all other embodiments obtained by a person skilled in the art without making any inventive effort are within the scope of protection of the present invention.
As shown in fig. 1, the invention provides a method for evaluating the efficiency of operators based on cluster analysis, which comprises the following steps:
s1, defining a picker operation behavior index by combining picker historical behavior data, wherein the picker operation behavior index comprises a piece dimension picking efficiency and a bit dimension picking efficiency, the piece dimension picking efficiency comprises a daily piece average picking efficiency, a median of piece daily average picking efficiency, an upper 1/4 score and a lower 1/4 score of piece, and the bit dimension picking efficiency comprises a daily average picking efficiency, a median of bit daily average picking efficiency, an upper 1/4 score and a lower 1/4 score.
Further, the piece dimension pick efficiency: the daily piece average picking efficiency, the average piece average picking efficiency median, the piece upper 1/4 score and the piece lower 1/4 score are obtained by combining the picking behavior data of at least two single pieces in the actual storage and the picking behaviors of the pickers and the date range.
Daily piece picking efficiency is calculated by the following formula:
in the above, avg_cout_day (x i ) Representing the picking efficiency of the picking person i day pieces; d (D) i Indicating the number of days of the ith picker's labor; cout (Cout) ii Indicating the pick efficiency of picker i for all the items on day j; x is x i Indicating whether the ith picker is selected or not, with a selection indicated as 1 and an unselected selection indicated as 0.
The median of the average picking efficiency of the piece days is calculated by the following formula:
when N is i In the case of an odd number of the number,
when N is i In the case of an even number of the number,
in the above formula, med_cout (x i ) A median representing the pick rate for the i daily picks; x is x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;express pick i +.>The number of pickups for each task; />Express pick i +.>The number of pickups for each task; />Express pick i +.>The order count of each task.
The 1/4 quantile on the part is calculated by the following formula:
when 3 (N) i When +1)/4 is an integer, the number of the units,
when 3 (N) i When +1)/4 is not an integer,
the number of 1/4 quantiles below the piece is calculated by the following formula:
when (N) i When +1)/4 is an integer, the number of the units,
when (N) i When +1)/4 is not an integer,
in the above, x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;3 rd (N) representing picker i i +1)/4 order count of tasks, +.>[3 (N) th of the order picker i i +1)/4+1]Order count of task, < >>(N) th of the order picker i i +1)/4 order count of tasks, +.>[ (N) th of the order picker i i +1)/4+1]The order count of the task.
Further, the bit dimension pick efficiency: the automatic sorting system is obtained by sorting operation behavior aggregation through combination of the picking behaviors of single-piece independent storage in actual storage, wherein the sorting efficiency is equal to the average sorting efficiency of the daily positions, the median of the average sorting efficiency of the daily positions, the 1/4 quantile of the upper position and the 1/4 quantile of the lower position.
Daily order picking efficiency is calculated by the following formula:
in the above formula, avg_loc_day (x i ) Indicating the daily average picking efficiency of the pickers i; d (D) i Indicating the number of days of the ith picker's labor; loc ij Indicating the pick efficiency of picker i at day j; x is x i Indicating whether the ith picker is selected or not, with a selection indicated as 1 and an unselected selection indicated as 0.
The median of the average picking efficiency of the bit is calculated by the following formula:
when N is i In the case of an odd number of the number,
when N is i In the case of an even number of the number,
in the above formula, med_loc (x i ) A median representing the i-bit daily picking efficiency of the pickers; x is x i Indicating whether the ith picker is selected or not, with the selection indicated as l and the unselected indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;express pick i +.>The order picking number of the individual tasks; />Express pick i +.>The order picking number of the individual tasks; />Express pick i +.>Order picking number of individual tasks.
The 1/4 quantile on the bit is calculated by the following formula:
when 3 (N) i When +1)/4 is an integer, the number of the units,
when 3 (N) i When +1)/4 is not an integer,
the 1/4 quantile under the bit is calculated by the following formula:
when (N) i When +1)/4 is an integer, the number of the units,
when (N) i When +1)/4 is not an integer,
in the above, x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;3 rd (N) representing picker i i +1)/4 order picking number, < ->[3 (N) th of the order picker i i +1)/4+1]Order of individual tasks, +.>(N) th of the order picker i i +1)/4 task pickingNumber of goods and->[ (N) th of the order picker i i +1)/4+1]Order picking number of individual tasks.
S2, carrying out cluster analysis on operators (pickers) through a plurality of clustering algorithms according to the operation behavior index set, selecting the clustering algorithm with the clustering result closest to the actual clustering algorithm, and finally obtaining three kinds of evaluation results or four kinds of evaluation results; the three kinds of evaluation results are high-efficiency working population, normal-efficiency working population and low-efficiency working population, and the four kinds of evaluation results are high-efficiency working population, good-efficiency working population, qualified efficiency working population and unqualified efficiency working population.
Specifically, the operation behavior index group is provided with a plurality of groups, four groups are preferably arranged, namely a first operation behavior index group, a second operation behavior index group, a third operation behavior index group and a fourth operation behavior index group, wherein the first operation behavior index group comprises daily piece average picking efficiency and daily position average picking efficiency, the second operation behavior index group comprises the median of piece daily average picking efficiency and the median of position daily average picking efficiency, the third operation behavior index group comprises 1/4 fraction on a piece and 1/4 fraction on a piece, the fourth operation behavior index group comprises 1/4 fraction under a piece and 1/4 fraction under a piece, namely, each clustering algorithm needs to perform clustering analysis according to the four groups of operation behavior index groups respectively, and four clustering results are obtained respectively.
S2 specifically comprises the following steps:
s201, processing the first operation behavior index group by the following formula:
in the above-mentioned method, the step of,represents x i Daily piece average picking efficiency or daily position average picking efficiency after treatment, u represents x i Are all of (1)The value, delta, represents x i Standard deviation of (2).
S202, performing cluster analysis by adopting a plurality of clustering algorithms according to the processed first operation behavior index group data, wherein each clustering algorithm respectively obtains 3 clusters or 4 clusters of clustering results, the clustering algorithm of the embodiment is preferably a k-means, BIRCH, dbscan algorithm, but is not limited to the three algorithms, and the clustering data visualization result after the algorithm cluster analysis of the first operation behavior index group through a preferred strategy (S205) is shown in fig. 2.
S203, a method for checking the performance ranking index in the period or a method for linear correlation according to the actual performance standard is adopted, and the Hamming Distance (Hamming Distance) or the correlation of different clustering algorithms under the first operation behavior index is obtained.
Specifically, the method for checking the performance ranking index in the period comprises the following steps: and (3) giving TOPK ranks of the daily piece average picking efficiency after treatment and the daily position average picking efficiency after treatment, and comparing the TOPK ranks with performance ranking indexes in a period respectively to obtain a Hamming Distance (Hamming Distance).
The method for linear correlation according to the actual performance standard comprises the following steps: the correlation size is determined by the following equation:
in the above formula, X, Y represents a variable;mean value of X, < >>Represents the mean value of Y; r is (r) XY The correlation between the X variable and the Y variable is represented as [ -1,1]；X i Representing the value, Y, of the variable X corresponding to the ith picker i A value of a variable Y corresponding to the ith picker, n representing the number of pickers; specifically, clustering results obtained according to a first operation behavior index group and through a k-means algorithmThe actual performance may be X, Y as described above, and other combinations of the set of operation behavior indicators and other algorithms may be one of the variables described above, which are not described herein.
The performance ranking index and the actual performance standard in the period are obtained according to the internal data of the enterprise.
S204, sequentially replacing the first operation behavior index group in the step S201 with the second operation behavior index group, the third operation behavior index group and the fourth operation behavior index group, sequentially performing the steps S201-S203 to obtain all clustering results of the four groups of operation behavior index groups by a plurality of clustering algorithms, and the Hamming Distance or the correlation magnitude of each clustering result, selecting the clustering algorithm with the smallest Hamming Distance or the largest correlation as the final clustering algorithm, and selecting the clustering result with the smallest Hamming Distance or the largest correlation as the final evaluation result, thereby obtaining three kinds of evaluation results or four kinds of evaluation results.
Further, in step S204, if the obtained minimum hamming distance corresponds to two or more algorithms, the number of clusters is increased until the minimum hamming distance is the only algorithm, and the initial K is set to 3.
S205, for new staff or staff without classified data, if three kinds of evaluation results are obtained, dividing the staff into working crowds with low efficiency; and if four types of evaluation results are obtained, dividing into an efficiency unqualified working population or an efficiency qualified working population.
According to the invention, the parameters in the two dimensions are matched one by one through setting the parameters in the dimension and the position dimension, clustering is carried out through the plurality of clustering algorithms, the most suitable clustering algorithm is obtained, and the most accurate evaluation result in the clustering algorithm is obtained, so that the cluster analysis of the work efficiency of the pickers can be more accurately obtained, the subsequent pickers are favorably distributed, and the improvement of the pickers is favorably realized.
Finally, it should be noted that the above description is only for illustrating the technical solution of the present invention, and not for limiting the scope of the present invention, and that the simple modification and equivalent substitution of the technical solution of the present invention can be made by those skilled in the art without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. The method for evaluating the efficiency of the operators based on the cluster analysis is characterized by comprising the following steps:
s1, defining a picker operation behavior index by combining picker historical behavior data, wherein the picker operation behavior index comprises a piece dimension picking efficiency and a position dimension picking efficiency;
s2, carrying out cluster analysis on the working efficiency of the pickers through a plurality of clustering algorithms according to the operation behavior indexes of the pickers, selecting the clustering algorithm closest to the actual clustering algorithm, and outputting the clustering result of the clustering algorithm to obtain the evaluation result of the working efficiency of the pickers.
2. The method for evaluating the efficiency of operators based on cluster analysis according to claim 1, wherein the piece dimension picking efficiency comprises daily piece average picking efficiency, piece daily average picking efficiency median, piece 1/4 score, piece lower 1/4 score, and the bit dimension picking efficiency comprises daily average picking efficiency, bit daily average picking efficiency median, bit upper 1/4 score, and bit lower 1/4 score;
the daily piece average picking efficiency and the daily position average picking efficiency are set as a first operation behavior index group; the median of the piece average picking efficiency and the median of the bit average picking efficiency are set as a second operation behavior index group; setting 1/4 quantiles on the piece and 1/4 quantiles on the bit as a third operation behavior index group; the 1/4 quantile under the piece and the 1/4 quantile under the piece are set as a fourth operation behavior index group.
3. The method for evaluating the efficiency of operators based on cluster analysis according to claim 2, wherein S2 specifically comprises the steps of:
s201, processing data in the first operation behavior index group by the following formula:
in the above-mentioned method, the step of,represents x i Daily piece average picking efficiency or daily position average picking efficiency after treatment, u represents x i Delta represents x i Standard deviation of (2);
s202, performing clustering analysis by adopting a plurality of clustering algorithms according to the processed first operation behavior index group data, wherein each clustering algorithm respectively obtains two clustering results of 3 clusters or 4 clusters;
s203, obtaining the Hamming distances or the correlation sizes of different clustering algorithms under the first operation behavior index by adopting a method for checking the performance ranking index in the period or a method for linear correlation according to the actual performance standard;
s204, sequentially replacing the first operation behavior index group in the step S201 with the second operation behavior index group, the third operation behavior index group and the fourth operation behavior index group, and sequentially performing the steps S201-S203 to obtain all clustering results of the four groups of operation behavior index groups by a plurality of clustering algorithms, the Hamming distance or the correlation of each clustering result, selecting the clustering algorithm with the smallest Hamming distance or the largest correlation as a final clustering algorithm, and selecting the clustering result with the smallest Hamming distance or the largest correlation as a final evaluation result.
4. A method for evaluating efficiency of operators based on cluster analysis as claimed in claim 3, wherein the method for checking the performance ranking index in the period is as follows: and (3) giving TOPK ranks of the daily piece average picking efficiency after treatment and the daily position average picking efficiency after treatment, and comparing the TOPK ranks with performance ranking indexes in a period respectively to obtain the Hamming distance.
5. The method for evaluating efficiency of operators based on cluster analysis according to claim 4, wherein if the minimum hamming distance obtained by checking the performance ranking index in the period corresponds to two or more algorithms, the number of clusters is increased until the minimum hamming distance is the only algorithm.
6. A method for evaluating efficiency of operators based on cluster analysis according to claim 3, wherein the method for linear correlation according to actual performance criteria is as follows: the correlation size is determined by the following equation:
in the above formula, X, Y represents a variable;mean value of X, < >>Represents the mean value of Y; r is (r) XY Representing the correlation between the X variable and the Y variable; x is X i Representing the value, Y, of the variable X corresponding to the ith picker i The value of the variable Y corresponding to the ith picker is represented, and n represents the number of pickers.
7. A method for evaluating the efficiency of operators based on cluster analysis according to claim 3, wherein the evaluation results of the work efficiency of the pickers are classified into three kinds of evaluation results or four kinds of evaluation results; the three kinds of evaluation results are high-efficiency working population, normal-efficiency working population and low-efficiency working population, and the four kinds of evaluation results are high-efficiency working population, good-efficiency working population, qualified efficiency working population and unqualified efficiency working population;
for new staff or staff without classified data, the staff is divided into inefficient working groups or efficient working groups.
8. The method for evaluating the efficiency of operators based on cluster analysis according to claim 2, wherein the daily piece picking efficiency is calculated by the following formula:
in the above, avg_cout_day (x i ) Representing the picking efficiency of the picking person i day pieces; d (D) i Indicating the number of days of the ith picker's labor; cout (Cout) ij Indicating the pick efficiency of picker i for all the items on day j; x is x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0;
daily order picking efficiency is calculated by the following formula:
in the above formula, avg_loc_day (x i ) Indicating the daily average picking efficiency of the pickers i; d (D) i Indicating the number of days of the ith picker's labor; loc ij Indicating the pick efficiency of picker i at day j; x is x i Indicating whether the ith picker is selected or not, with a selection indicated as 1 and an unselected selection indicated as 0.
9. The method for evaluating the efficiency of operators based on cluster analysis according to claim 2, wherein the median of the average picking efficiency of the piece days is calculated by the following formula:
when N is i In the case of an odd number of the number,
when N is i In the case of an even number of the number,
in the above formula, med_cout (x i ) A median representing the pick rate for the i daily picks; x is x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;express pick i +.>The number of pickups for each task; />Express pick i +.>The number of pickups for each task; />Express pick i +.>The number of pickups for each task;
the median of the average picking efficiency of the bit is calculated by the following formula:
when N is i In the case of an odd number of the number,
when N is i In the case of an even number of the number,
in the above formula, med_loc (x i ) A median representing the i-bit daily picking efficiency of the pickers; x is x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;express pick i +.>The order picking number of the individual tasks; />Express pick i +.>The order picking number of the individual tasks; />Express pick i +.>Order picking number of individual tasks.
10. The method for evaluating efficiency of operators based on cluster analysis according to claim 2, wherein,
the 1/4 quantile on the part is calculated by the following formula:
when 3 (N) i When +1)/4 is an integer, the number of the units,
when 3 (N) i When +1)/4 is not an integer,
the number of 1/4 quantiles below the piece is calculated by the following formula:
when (N) i When +1)/4 is an integer, the number of the units,
when (N) i When +1)/4 is not an integer,
the 1/4 quantile on the bit is calculated by the following formula:
when 3 (N) i When +1)/4 is an integer, the number of the units,
when 3 (N) i When +1)/4 is not an integer,
the 1/4 quantile under the bit is calculated by the following formula:
when (N) i When +1)/4 is an integer, the number of the units,
when (N) i When +1)/4 is not an integer,
in the above, x i Indicating whether the ith picker is selected, with the selection being indicated as 1, and the unselected selection being indicated as 0; n (N) i Indicating that the ith picker is at D i Total number of pick tasks in the day;3 rd (N) representing picker i i +1)/4 order count of tasks, +.>[3 (N) th of the order picker i i +1)/4+1]Order count of task, < >>(N) th of the order picker i i +1)/4 order count of tasks, +.>[ (N) th of the order picker i i +1)/4+1]The number of items picked for the task; />3 rd (N) representing picker i i +1)/4 order picking number, < ->[3 (N) th of the order picker i i +1)/4+1]Order of individual tasks, +.>(N) th of the order picker i i +1)/4 order picking number, < ->[ (N) th of the order picker i i +1)/4+1]Order picking number of individual tasks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311285041.5A CN117314243B (en) | 2023-09-28 | 2023-09-28 | Method for evaluating efficiency of operators based on cluster analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311285041.5A CN117314243B (en) | 2023-09-28 | 2023-09-28 | Method for evaluating efficiency of operators based on cluster analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117314243A true CN117314243A (en) | 2023-12-29 |
| CN117314243B CN117314243B (en) | 2024-09-03 |
Family
ID=89236805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311285041.5A Active CN117314243B (en) | 2023-09-28 | 2023-09-28 | Method for evaluating efficiency of operators based on cluster analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314243B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446803A (en) * | 2018-03-23 | 2018-08-24 | 山东财经大学 | A kind of intensive storage position optimization method and device towards B2C electric business orders |
| CN111062573A (en) * | 2019-11-19 | 2020-04-24 | 平安金融管理学院(中国·深圳) | Staff performance data determination method, device, medium and computer equipment |
| CN111144677A (en) * | 2018-11-06 | 2020-05-12 | 北京京东振世信息技术有限公司 | Efficiency evaluation method and efficiency evaluation system |
| CN111222747A (en) * | 2019-11-22 | 2020-06-02 | 南宁职业技术学院 | Picking method and device for fresh goods |
| CN113191533A (en) * | 2021-04-13 | 2021-07-30 | 上海东普信息科技有限公司 | Warehouse employment prediction method, device, equipment and storage medium |
| CN113792981A (en) * | 2021-08-18 | 2021-12-14 | 宜卡科技(深圳)有限公司 | Efficiency statistical method, device and computer readable storage medium |
| CN115018357A (en) * | 2022-06-23 | 2022-09-06 | 中国农业大学 | Farmer portrait construction method and system for production performance improvement |
| US20220300884A1 (en) * | 2021-03-16 | 2022-09-22 | Hcl Technologies Limited | Method and system for evaluating performance of developers using artificial intelligence (ai) |
| WO2022206308A1 (en) * | 2021-03-31 | 2022-10-06 | 深圳市库宝软件有限公司 | Order assignment method and apparatus, device, and storage medium |
| CN115689334A (en) * | 2022-09-30 | 2023-02-03 | 深圳市库宝软件有限公司 | Efficiency analysis method and system of warehouse management system and computer equipment |
| CN115759862A (en) * | 2022-11-30 | 2023-03-07 | 上海韵达高新技术有限公司 | Reservation package service assessment method, device, equipment and storage medium |
| CN116167733A (en) * | 2023-02-20 | 2023-05-26 | 中移动信息技术有限公司 | Performance evaluation method, device, equipment and medium |
-
2023
- 2023-09-28 CN CN202311285041.5A patent/CN117314243B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446803A (en) * | 2018-03-23 | 2018-08-24 | 山东财经大学 | A kind of intensive storage position optimization method and device towards B2C electric business orders |
| CN111144677A (en) * | 2018-11-06 | 2020-05-12 | 北京京东振世信息技术有限公司 | Efficiency evaluation method and efficiency evaluation system |
| CN111062573A (en) * | 2019-11-19 | 2020-04-24 | 平安金融管理学院(中国·深圳) | Staff performance data determination method, device, medium and computer equipment |
| CN111222747A (en) * | 2019-11-22 | 2020-06-02 | 南宁职业技术学院 | Picking method and device for fresh goods |
| US20220300884A1 (en) * | 2021-03-16 | 2022-09-22 | Hcl Technologies Limited | Method and system for evaluating performance of developers using artificial intelligence (ai) |
| WO2022206308A1 (en) * | 2021-03-31 | 2022-10-06 | 深圳市库宝软件有限公司 | Order assignment method and apparatus, device, and storage medium |
| CN113191533A (en) * | 2021-04-13 | 2021-07-30 | 上海东普信息科技有限公司 | Warehouse employment prediction method, device, equipment and storage medium |
| CN113792981A (en) * | 2021-08-18 | 2021-12-14 | 宜卡科技(深圳)有限公司 | Efficiency statistical method, device and computer readable storage medium |
| CN115018357A (en) * | 2022-06-23 | 2022-09-06 | 中国农业大学 | Farmer portrait construction method and system for production performance improvement |
| CN115689334A (en) * | 2022-09-30 | 2023-02-03 | 深圳市库宝软件有限公司 | Efficiency analysis method and system of warehouse management system and computer equipment |
| CN115759862A (en) * | 2022-11-30 | 2023-03-07 | 上海韵达高新技术有限公司 | Reservation package service assessment method, device, equipment and storage medium |
| CN116167733A (en) * | 2023-02-20 | 2023-05-26 | 中移动信息技术有限公司 | Performance evaluation method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117314243B (en) | 2024-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751371B (en) | Commodity inventory risk early warning method and system based on statistical four-bit distance and computer readable storage medium | |
| CN108733003B (en) | Method and system for predicting working hours of rotary part working procedures based on kmeans clustering algorithm | |
| CN109446251A (en) | System and method for distributed artificial intelligence application development | |
| EP3701480B1 (en) | Systems and methods for intelligently grouping financial product users into cohesive cohorts | |
| CN117314091B (en) | Operation task list distribution method considering behaviors | |
| Hazarika et al. | Genetic algorithm approach for machine cell formation with alternative routings | |
| CN108491991A (en) | Constraints analysis system based on the industrial big data product duration and method | |
| CN117591572A (en) | High-value data screening system for big data directional mining | |
| CN117633571A (en) | Abnormal user early warning method and device based on multiple clusters | |
| CN114611738A (en) | Load prediction method based on user electricity consumption behavior analysis | |
| CN117314243B (en) | Method for evaluating efficiency of operators based on cluster analysis | |
| CN116307761A (en) | Business invitation data management system based on cloud platform | |
| CN113762563A (en) | Warehousing goods space optimal layout method and system based on order grey correlation analysis | |
| Ma et al. | A review of algorithms for order batching problem in distribution center | |
| CN105787113A (en) | Mining algorithm for DPIPP (distributed parameterized intelligent product platform) process information on basis of PLM (product lifecycle management) database | |
| CN112330246B (en) | Order summarizing method, order summarizing device, computer equipment and storage medium | |
| CN112783948A (en) | Regional economic operation data analysis method, device and storage medium | |
| CN118278866A (en) | Warehouse management method and system based on digitization | |
| Li et al. | Simulation of multivariate scheduling optimization for open production line based on improved genetic algorithm | |
| CN106779245A (en) | Civil aviaton's needing forecasting method and device based on event | |
| CN117453664A (en) | Tracing data anomaly detection method and blockchain tracing data storage method | |
| CN115860465A (en) | Enterprise associated data processing early warning method, system and device | |
| CN117314092B (en) | Labor-intensive job task list distribution method considering behaviors | |
| KR102328019B1 (en) | Natural gas demand predicting method using statistical learning | |
| CN118427650A (en) | Information determination method, apparatus, device and computer readable storage medium |
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 |