CN115186906A

CN115186906A - Intelligent prediction method and platform for returning containers for container operational leasing

Info

Publication number: CN115186906A
Application number: CN202210830100.1A
Authority: CN
Inventors: 李涵; 顾寅俊; 陈玺文
Original assignee: Florence China Co ltd; Cosco Shipping Technology Co Ltd
Current assignee: Florence China Co ltd; Cosco Shipping Technology Co Ltd
Priority date: 2022-07-15
Filing date: 2022-07-15
Publication date: 2022-10-14
Anticipated expiration: 2042-07-15
Also published as: CN115186906B

Abstract

The invention relates to an intelligent prediction method and a platform for returning containers for container operational leasing, wherein the method is characterized in that based on contract historical data and the number of returned containers planned by a client, historical actual returned container data of the client are obtained, the predicted number of returned containers and the proportion of returned containers of a certain container type of a certain port are determined, and specific analysis methods and calculation methods are adopted to respectively analyze and calculate according to three conditions that the contract deadline is not expired, the contract deadline is expired and no historical actual returned container data exists in the previous month of the month where the current time exists, the amount of returned containers of the certain container type of the certain port in each month is predicted, and the predicted amount of returned containers is displayed according to a preset chart type. The invention can accurately reveal the box returning trend, assist enterprises to predict the future box returning situation, help enterprises to adjust management operation strategies in time, and display the predicted trend by the preset chart type, so that the data presentation mode is more visual and clear.

Description

Intelligent prediction method and platform for returning containers for container operational leasing

Technical Field

The invention relates to the technical field of container management and informatization construction, in particular to an intelligent prediction method and platform for returning containers for container operational leasing.

Background

In the face of complex and changeable market environments, the renting and returning of containers is always an important link in business, and the quantity of the returned containers directly influences the stock quantity of container asset management enterprises in each port and further influences the sales strategy of companies and the like.

The method comprises the following steps that (1) the existing container asset management enterprise faces the following problems in the process of returning a container by a container, wherein the position of returning the container by the container is uncertain, and although the container returning order exists in the container returning by the returning of the container, whether a customer returns the container according to the position specified by a contract or not cannot be controlled; 2. due to uncertainty of the time for returning the boxes by renting, the situation that the time for returning the boxes is delayed is inevitable when a client returns the boxes, so that the actual time for returning the boxes is difficult to reasonably estimate; 3. the behavior of returning boxes for renting is difficult to predict, and although boxes in ports do not return in the past several months, the behavior of returning boxes for the clients cannot be predicted whether to return boxes in the future.

Due to the uncertainty of the behavior of returning the containers for renting and returning the containers, the upper limit of the containers for returning the containers in each country and port and other factors, a scientific and effective prediction model for returning the containers for renting and returning the containers for the containers does not exist in the industry at present. Meanwhile, the container asset management enterprise is intervened by more internal and external environmental factors such as dispatching cost, air route factors, expected income and the like, and at present, no set of available refunds and returns prediction models is available for effectively guiding the development of the refunds and returns of the containers, so that the operation management efficiency and the asset utilization rate of the enterprise are improved in an auxiliary manner.

Disclosure of Invention

In order to solve the problems faced by the container asset management enterprises in the process of relegating and returning containers, the invention provides an intelligent prediction method for container returning through container business leasing, which is based on historical data, considers the factors such as the upper limit of the container returning in the region, the upper limit of the container returning in the port, the upper limit of the container returning in the month and the like, adopts a specific calculation mode to intelligently predict the amount of the returned containers, can automatically and accurately reveal the trend of the returned containers, assists the container asset management enterprises in predicting the future condition of the returned containers, helps the enterprises in timely adjusting and managing operation strategies, displays the prediction trends in the modes of region division, box division and port division, displays the trend and the variation amplitude of the returned container data, and enables the presentation mode of the data to be more visual and clear. The invention also relates to an intelligent prediction platform for returning the containers for the container operational leasing.

The technical scheme of the invention is as follows:

an intelligent prediction method for returning containers for container operational leasing is characterized by comprising the following steps:

s1: automatically acquiring historical actual box returning data of a client according to the historical contract data, automatically determining the estimated box returning month number according to the planned box returning month number of the client and/or the historical contract data, intelligently analyzing and determining the box returning proportion of a certain box of a certain port according to the historical actual box returning data, then automatically judging the contract time limit, executing the step S2 when the contract time limit is not expired, and executing the step S3 or the step S4 when the contract time limit is expired;

s2: when the contract deadline is not expired, intelligently predicting the box returning amount of a certain box of a certain port every month by a Prophet algorithm according to the predicted number of the box returning months and the box returning proportion of the certain box of the certain port, and combining the monthly box returning amount upper limit of the certain box of the certain port and/or the box returning amount upper limit of the certain box of the certain region and historical actual box returning data, and entering the step S5 after the prediction is finished;

s3: when the contract period is expired and no historical actual box returning data exists, but a client applies for a box returning plan, the box returning amount in the first month is used as a predicted box returning amount according to the pre-box returning amount in the box returning plan applied by the client, the box returning amount in the second month and the months after the second month is intelligently predicted according to the prediction mode of the step S2, and the step S5 is carried out after the prediction is finished;

s4: when the contract deadline is expired and the historical actual box returning data exists in the month before the current time, the box returning delay time of each box is obtained according to the box returning time data in the historical actual box returning data of the month, and the average box returning delay time of each box is calculated; calculating the number of boxes which can be returned in the last month of the month in which the current time is located in all the unreturned boxes according to the average box returning delay time of each box, and intelligently predicting the box returning amount in the last month of the month in which the current time is located by adopting a Prophet algorithm according to the number of boxes returned in the last month of the month in which the current time is located, the average box returning delay time and the monthly box returning amount upper limit of a certain box type of a certain port;

calculating the weekly average box returning quantity and the weekly average box returning increment according to the actual box returning quantity of the month before the month where the current time is and the predicted box returning quantity of the month after the month where the current time is, intelligently predicting the box returning quantity of a certain week in the future according to the weekly average box returning quantity and the weekly average box returning increment, and further intelligently predicting the box returning quantity of a certain month in the future;

s5: and displaying the intelligently predicted box returning amount according to a preset chart type.

Preferably, in the step S4, after predicting the amount of returned boxes for a month in the future, the method further includes the following steps:

the first step is as follows: comparing the predicted box returning amount of a certain box type of a certain port in a future month with the monthly box returning amount upper limit of the certain box type of the certain port, and if the predicted box returning amount of the certain box type of the certain port in the future month is smaller than the monthly box returning amount upper limit of the certain box type of the certain port, taking the predicted box returning amount of the certain box type of the certain port in the month as the actual box returning amount of the month;

if the predicted box returning amount of a certain box type of a certain port in a certain future month is more than or equal to the monthly box returning amount upper limit of the certain box type of the certain port, taking the monthly box returning amount upper limit of the box type of the certain port as the actual box returning amount of the certain month;

the second step is as follows: comparing the total quantity of all predicted returned box quantities and the total quantity of the returned box quantities of a certain box type in a certain area before a certain month in the future and the month with the upper limit of the returned box quantity of the certain box type in the certain area, and if the total quantity is smaller than the upper limit of the returned box quantity of the box type in the certain area, taking all predicted returned box quantities of the box type in the certain area before the month and the month as the actual returned box quantity of the certain area;

and if the total quantity is more than or equal to the upper limit of the box returning quantity of the box type in the area, taking the upper limit of the box returning quantity of the box type in the area as the actual box returning quantity of the area, uniformly distributing the quantity of the box exceeding the upper limit of the box returning quantity to each port under the area, and subtracting the uniformly distributed quantity of the box exceeding the upper limit part from the predicted box returning quantity of the last week of each port.

Preferably, after the actual box returning amount of a month in the future is judged, if the total predicted box returning amount in the latter month or the latter months of the month is equal to zero, the box returning prediction process is ended; if the total predicted case returning amount in the next month or a few months after the month is more than zero, automatically judging whether the number of all the months before the month is less than the maximum predicted case returning month number, if the number of all the months before the month is less than the maximum predicted case returning month number, continuously predicting the predicted case returning amount in the next month, and if the number of all the months before the month is more than or equal to the predicted case returning month number, ending the case returning prediction process.

Preferably, in the step S5, the chart type includes at least one of a summary histogram, a regional graph, a box-type line chart, and a port histogram.

Preferably, in the step S1, a theme table is further created according to historical actual box returning data, where the theme table includes a client ID, a contract number, a contract type, a box returning area, a box returning port, and a box returning amount.

An intelligent prediction platform for returning containers for commercial renting of containers is characterized by comprising a first module, a second module, a third module, a fourth module and a fifth module, wherein the first module is respectively connected with the second module, the third module and the fourth module, the second module, the third module and the fourth module are all connected with the fifth module,

the system comprises a first module, a second module and a third module, wherein the first module automatically acquires historical actual case returning data of a client according to the historical contract data, automatically determines the predicted case returning month number according to the planned case returning month number of the client and/or the historical contract data, intelligently analyzes and determines the case returning proportion of a certain case type of a certain port according to the historical actual case returning data, then automatically judges the contract period, executes the second module when the contract period is not expired, and executes the third module or the fourth module when the contract period is expired;

the second module intelligently predicts the box returning amount of a certain box at a certain port every month by adopting a Prophet algorithm according to the predicted box returning month number, the box returning proportion of a certain box at a certain port and the monthly box returning amount upper limit of the certain box at the certain port and/or the box returning amount upper limit of the certain box at a certain area and the historical actual box returning data when the contract deadline is not expired, and enters the fifth module after the prediction is finished;

the third module is used for intelligently predicting the box returning amount in the second month and the months after the second month according to the prediction mode of the second module when the contract period is expired and no historical actual box returning data exists but a client applies for the box returning plan, and the box returning amount in the second month and the months after the second month and the third month enters the fifth module;

the fourth module is used for obtaining the box returning delay time of each box according to the box returning time data in the historical actual box returning data of the month when the contract period is expired and the historical actual box returning data exists in the month before the current time, and calculating the average box returning delay time of each box; calculating the number of boxes which can be returned in the month after the month of the current time in all the unreturned boxes according to the average box returning delay time of each box, and intelligently predicting the box returning amount in the month after the month of the current time by adopting a Prophet algorithm according to the number of boxes returned in the month after the month of the current time, the average box returning delay time and the upper limit of the box returning amount in the month of a certain box at a certain port;

calculating the average weekly returning amount and the average weekly returning increment according to the actual returning amount of the month before the month at which the current time is positioned and the predicted returning amount of the month after the month at which the current time is positioned, intelligently predicting the returning amount of a week in the future according to the average weekly returning amount and the average weekly returning increment, and further intelligently predicting the returning amount of a month in the future;

and the fifth module is used for displaying the intelligently predicted box returning amount according to the type of a preset chart.

Preferably, in the fourth module, after the box returning amount of a certain port in a future month is predicted, the predicted box returning amount of a certain box in a certain port in the future month is compared with the monthly box returning amount upper limit of a certain box in a certain port, and if the predicted box returning amount of a certain box in a certain port in the future month is smaller than the monthly box returning amount upper limit of a certain box in a certain port, the predicted box returning amount of the certain box in the port in the month is used as the actual box returning amount of the month;

comparing the total quantity of all predicted box returning quantities and the total box returning quantities of a certain box type in a certain area in a future month and before the month with the upper limit of the box returning quantity of the certain box type in the certain area, and if the total quantity is smaller than the upper limit of the box returning quantity of the box type in the area, taking all predicted box returning quantities of the box type in the area in the month and before the month as the actual box returning quantity of the area;

and if the total quantity is more than or equal to the upper limit of the box-type returning quantity of the area, taking the upper limit of the box-type returning quantity of the area as the actual box-returning quantity of the area, uniformly distributing the quantity of the boxes exceeding the upper limit of the box-returning quantity to each port under the area, and subtracting the uniformly distributed quantity of the boxes exceeding the upper limit part from the predicted box-returning quantity of the last week of the month of each port.

Preferably, in the fourth module, after the actual box returning amount of a month in the future is judged, if the total predicted box returning amount in the latter month or the latter months of the month is equal to zero, the box returning prediction process is ended; if the total predicted case returning amount in the latter month or the latter months of the month is more than zero, judging whether the number of all the months before the month is less than the maximum predicted case returning month number, if the number of all the months before the month is less than the maximum predicted case returning month number, continuing to predict the predicted case returning amount in the next month of the month, and if the number of all the months before the month is more than or equal to the predicted case returning month number, ending the case returning prediction process.

Preferably, the chart type includes at least one of a summary histogram, a zone graph, a box-type line graph, and a port histogram.

Preferably, in the first module, a theme table is further created according to historical actual box returning data, and the theme table comprises a client ID, a contract number, a contract type, a box returning area, a box returning port and a box returning amount.

The invention has the following technical effects:

the invention provides an intelligent prediction method for returning containers for the operative leasing of containers, which comprises the steps of obtaining historical actual container returning data of a client based on historical contract data, determining the estimated container returning month number according to the planned container returning month number of the client and/or the historical contract data, analyzing and determining the container returning proportion of a certain container type of a certain port according to the historical actual container returning data, and intelligently predicting the container returning amount under various conditions by adopting a specific calculation mode while considering factors such as the upper limit of the regional container returning, the container type of the port, the upper limit of the monthly container returning and the like under the two conditions of unexpired contract time limit and expired contract time limit, so that the calculation result is more scientific and reasonable, and the container returning trend can be accurately revealed by means of a large amount of historical data and calculation means on the basis of applying objective rules. According to the method, historical data is referred to according to a lease contract, future box returning conditions are predicted, risks of long-term idle boxes can be avoided in advance, a container asset management enterprise is assisted to predict the future box returning conditions, the enterprise is helped to adjust management operation strategies in time, prediction trends are shown by dividing regions, boxes and ports in the forms of bar charts, curve graphs and line graphs, and the changing trend and the changing amplitude of box returning data are displayed, so that the data presentation mode is more visual and clear.

The invention also provides an intelligent prediction platform for the operative renting and returning of the container, which corresponds to the intelligent prediction method for the operative renting and returning of the container, can be understood as a platform for realizing the intelligent prediction method for the operative renting and returning of the container, and is essentially a background or a server. The invention is based on the actual business scene, highly integrates the management requirements of the container asset management enterprise, the related internal and external business data and historical data, designs and realizes a set of intelligent prediction platform which meets the requirement of the container asset management enterprise on the container returning and renting, helps the manager know the future returning situation in advance, and carries out further analysis based on the returning situation.

Drawings

FIG. 1 is a flow chart of the intelligent prediction method for the container operational leasing and returning.

FIG. 2 is a preferred flow chart of the intelligent prediction method for the container operational leasing and returning.

Fig. 3-9 are further preferred flow charts of the container operational lease bin return intelligent prediction method of the present invention.

FIG. 10 is a diagram illustrating the effect of the present invention on the monthly forecast rebinned data.

FIG. 11 is a diagram illustrating another effect of the weekly prediction of the present invention on binning data.

FIG. 12 is a prediction detail data presentation diagram of the present invention.

Detailed Description

The present invention will be described with reference to the accompanying drawings.

The invention relates to an intelligent prediction method for returning returned containers for returning containers for operative leasing, wherein a flow chart of the method is shown in figure 1, and the method sequentially comprises the following steps:

s1: acquiring historical actual box returning data of a client according to the historical contract data, automatically determining the estimated box returning month number according to the planned box returning month number of the client and/or the historical contract data, intelligently analyzing and determining the box returning proportion of a certain box type of a certain port according to the historical actual box returning data, then automatically judging the contract time limit, executing the step S2 when the contract time limit is not expired, and executing the step S3 or the step S4 when the contract time limit is expired;

specifically, as shown in the preferred flowchart of fig. 2, the estimated number of returned boxes MF is first determined according to the number of returned boxes selected by the customer, when the number of returned boxes MF is not selected by the customer, that is, the estimated number of returned boxes MF is empty, the predicted number of months according to the Build down from & Build down to under contract is used, when both of the above mentioned are empty, the predicted number of months is defaulted to 12 months, and when neither of the above mentioned is empty, the predicted number of months is used to MF months.

And then manually inputting a reference contract number, automatically acquiring historical actual box returning data of a client in two years on a reference contract according to the historical contract data, if the reference contract number is not manually input, acquiring the historical actual box returning data of the client in two years of the corresponding type of the contract, creating a theme table according to the historical actual box returning data, and intelligently analyzing and determining the box returning proportion of a certain box of a certain port according to the historical actual box returning data. Wherein, the theme table structure is: customer ID, contract number, contract type, box return Region, box return port, and box return volume.

S2: when the contract deadline is not expired, intelligently predicting the box returning amount of a certain box at a certain port every month by adopting a Prophet algorithm (time series prediction algorithm) according to the predicted box returning month number, the box returning proportion of the certain box at the certain port, the Monthly box returning amount upper limit (namely Monthly Caps of the contract) of the certain box at the certain port and/or the box returning amount upper limit (namely the Region Caps of the contract) of the certain box at a certain Region and historical actual box returning data, and displaying the intelligently predicted box returning amount according to a preset chart type after intelligently predicting the box returning amount of the certain box at the certain port every month;

specifically, when there is no Region Caps & no Monthly Caps, the Monthly box return amount of a certain box of a certain port = the box rental amount/predicted box return month number (/ total historical box return amount of a certain box of a certain port);

for example: customer a, contract currently rented 1000 lots, expected return to the box for months MF =6 months, historical return to the box as follows:

AM LAX D20 20 QTY

AM NYC D20 20 QTY

AP SHA D20 20 QTY

AP NGB D20 10 QTY

EU FRA D20 15 QTY

EU LON D20 25 QTY

note: AM refers to the American region, AP refers to the Asian region, and EU refers to the European region; LAX, NYC, SHA, NGB, FRA, LON are all Port code abbreviations; d20 is a box type; QTY refers to a unit of measure. The fourth column, 20, 10, 15, 25, represents historical bin returns.

Suppose that: without Region Caps and without Monthly Caps, the predicted box return amount for each box type of each port is reduced by one: i.e. the round function returns the floating point number five cut six.

AM LAX D20 round(1000/6,0)*(20/(20+20+20+10+15+25)＝31

AM NYC D20 round(1000/6,0)*(20/(20+20+20+10+15+25)＝31

AP SHA D20 round(1000/6,0)*(20/(20+20+20+10+15+25)＝31

AP NGB D20 round(1000/6,0)*(10/(20+20+20+10+15+25)＝16

EU FRA D20 round(1000/6,0)*(15/(20+20+20+10+15+25)＝23

EU LON D20 round(1000/6,0)-(31+31+31+16+23)＝34

Predicted return volume in the last month: (1000-round (1000/6, 0) × 5) =170

AM LAX D20 170*(20/(20+20+20+10+15+25)＝31

AM NYC D20 170*(20/(20+20+20+10+15+25)＝31

AP SHA D20 170*(20/(20+20+20+10+15+25)＝31

AP NGB D20 170*(10/(20+20+20+10+15+25)＝16

EU FRA D20 170*(15/(20+20+20+10+15+25)＝24

EU LON D20 170-(31+31+31+16+24)＝37

When there is no Region Caps & Monthly Caps, the Monthly box returning amount of a certain box in a certain port = the box renting amount/the expected box returning month number (the historical box returning amount of a certain box in a certain port/the total historical box returning amount of certain box in all ports); if the Monthly box returning amount of a certain box of a certain port is more than Monthly Caps, the Monthly box returning amount of the certain box of the certain port = Monthly Caps; if the Monthly box returning amount of a certain box of a certain port is less than Monthly Caps, taking the Monthly predicted box returning amount of the certain box of the certain port as the actual box returning amount of the certain month;

suppose that: when there are no Region Caps & Monthly Caps, LAX and NYC have Monthly Caps =30, ports with Monthly Caps calculate preferentially:

AM LAX D20 round(1000/6,0)*(20/(20+20+20+10+15+25)＝31then 30

AM NYC D20 round(1000/6,0)*(20/(20+20+20+10+15+25)＝31then 30

AP SHA D20 round(1000/6,0)*(20/(20+20+20+10+15+25)＝31

AP NGB D20 round(1000/6,0)*(10/(20+20+20+10+15+25)＝16

EU FRA D20 round(1000/6,0)*(15/(20+20+20+10+15+25)＝23

EU LON D20 round(1000/6,0)-(30+30+31+16+23)＝36

predicted return volume in the last month: (1000-round (1000/6, 0) × 5) =170

AM LAX D20 170*(20/(20+20+20+10+15+25)＝31then 30

AM NYC D20 170*(20/(20+20+20+10+15+25)＝31then 30

AP SHA D20 170*(20/(20+20+20+10+15+25)＝31

AP NGB D20 170*(10/(20+20+20+10+15+25)＝16

EU FRA D20 170*(15/(20+20+20+10+15+25)＝24

EU LON D20 170-(30+30+31+16+24)＝39

When there are Region Caps and no Monthly Caps, if the number of the belonging sub-Region Caps (a small upper limit range below the Region Caps) is more than or equal to the quantity of boxes of a certain box of the belonging sub-Region, the Monthly box returning quantity of a certain box of a certain port = the quantity of boxes of a certain box of the belonging sub-Region/predicted box returning month number (the historical box returning quantity of a certain box of a certain port/the total historical box returning quantity of a certain box of the belonging sub-Region);

if the subordinated child Region Caps are smaller than the box renting amount of the subordinated child Region box, the monthly box returning amount of the subordinated child Region Caps/the estimated box returning month number of the subordinated child Region (the historical box returning amount of the subordinated child Region box/the total historical box returning amount of the subordinated child Region box);

suppose that: with Region Caps & without Monthly Caps, AM =300, with the priority calculation of Region Caps, region Caps need to deduct the number of the returned boxes for calculation:

AM LAX D20 round(300/6,0)*(20/(20+20)＝25

AM NYC D20 round(300/6,0)*(20/(20+20)＝25

AP SHA D20 round(1000-300)/6,0)*(20/(20+10+15+25)＝34

AP NGB D20 round(1000-300)/6,0)*(10/(20+10+15+25)＝17

EU FRA D20 round(1000-300)/6,0)*(15/(20+10+15+25)＝25

EU LON D20 round(1000-300)/6,0)-(34+17+25)＝41

predicted case return volume in the last month: AM 300-300/6 × 5=50 (700-round (700/6, 0) × 5) =115

AM LAX D20 50*(20/(20+20)＝25

AM NYC D20 50*(20/(20+20)＝25

AP SHA D20 115*(20/(20+10+15+25)＝33

AP NGB D20 115*(10/(20+10+15+25)＝17

EU FRA D20 115*(15/(20+10+15+25)＝25

EU LON D20 115-(33+17+25)＝40

1) When there are Region Caps and Monthly Caps, if the number of the subordinate sub-Region Caps is more than or equal to the number of the subordinate sub-Region boxes in a box-renting amount, the Monthly box-returning amount of the port box = the number of the subordinate sub-Region boxes in a box-renting amount/predicted box-returning months (the historical box-returning amount of a certain port box/the total historical box-returning amount of the subordinate sub-Region boxes);

if the Monthly box returning amount of the port box is larger than Monthly Caps, the Monthly box returning amount = Monthly Caps

If the Monthly box returning amount of the port box is less than Monthly Caps, the Monthly box returning amount = the Monthly box returning amount of the port box

2) If the subordinate child Region Caps are smaller than the subordinate child Region box type renting amount, the port box type monthly returning amount = the subordinate child Region Caps/estimated returning amount monthly (a certain port box type historical returning amount/the subordinate child Region box type total historical returning amount);

if the Monthly box return amount of the harbor box is more than Monthly Caps, the Monthly box return amount = Monthly Caps

If the Monthly box return amount of the port box is less than Monthly Caps, the Monthly box return amount = the Monthly box return amount of the port box

Suppose that: there are Region Caps & Monthly Caps, AM (american regional upper limit) =300, LAX and NYC monthlycaps =24, SHA and NGB Monthly Caps =32, there is a priority calculation for Region Caps, there is a second priority calculation for Monthly Caps, and Region Caps need to be calculated by deducting the number of the returned boxes:

AM LAX D20 round (300/6,0) (20/(20 + 20)) =25then 24 (regional upper limit & month upper limit)

AM NYC D20 round (300/6, 0) (20/(20 + 20)) =25then 24 (regional upper limit & monthly upper limit)

AP SHA D20 round ((1000-300)/6, 0) ((20/(20 +10+15+ 25)) =34then 32 (upper limit of month)

AP NGB D20 round((1000-300)/6,0)*(10/(20+10+15+25))＝17

EU FRA D20 round((1000-300)/6,0)*(15/(20+10+15+25))＝25

EU LON D20 round((1000-300)/6,0)-(32+17+25)＝43

Predicted return volume in the last month:

in the AM area: total stock return (48 × 5= 240) =60 in the first 5 months in 300-AM region

AP & EU region: total stock return (117 × 5= 585) =115 for the first 5 months in 700-AP & EU area

AM LAX D20 60 (20/(20 + 20) =30then 24 (regional upper limit & month upper limit)

AM NYC D20 (20/(20 + 20) = 30thenn 24 (regional upper limit & month upper limit)

AP SHA D20 115 (= 20+10+15+ 25) =33then 32 (upper limit of month)

AP NGB D20 115*(10/(20+10+15+25)＝17

EU FRA D20 115*(15/(20+10+15+25)＝25

EU LON D20 115-(32+17+25)＝41

S3: when the contract deadline is expired and no actual box returning data exists, but a client applies for a box returning plan, the box returning amount in the box returning plan applied by the client in the first month is used as a predicted box returning amount, the box returning amount in the second month and the following months (namely future MF-1 month) is intelligently predicted according to the prediction mode when the contract deadline is not expired, after the box returning amount of a certain box in a certain port in each month is intelligently predicted, the step S5 is entered, and the intelligently predicted box returning amount is displayed according to the type of a preset chart.

S4: when the contract deadline is expired and historical actual box returning data exists in a month before the current time, obtaining the box returning delay time of each box according to the box returning time precleaner data in the historical actual box returning data of the month, and then averaging to obtain the average box returning delay time GI LAG of each box; calculating the number of boxes which can be returned in the month after the month of the current time in all the unreturned boxes according to the average box returning delay time of each box, and intelligently predicting the box returning amount in the month after the month of the current time by adopting a Prophet algorithm according to the number of boxes returned in the month after the month of the current time, the average box returning delay time and the upper limit of the box returning amount in the month of a certain box at a certain port;

specifically, as shown in fig. 3-4, preclean data is obtained according to the contract number, that is, actual box returning data of each box type of each port in the month (1 st to 4th weeks) before the month of the current time is obtained; obtaining open precleaner data according to a contract number, namely the number of the applied boxes is not yet available, and precleaner date of each open precleaner, namely the box returning time of all the returned boxes in the contract, obtaining the box returning delay time of each box according to the box returning time precleaner date of all the returned boxes in the contract, and then averaging to obtain the average box returning delay time GI LAG; then calculating the number of boxes which can be returned in the next month (namely 5-8 weeks and the 1 st month in the future) of the month in which the current time is located in all the unreturned boxes according to the average box returning delay time; and finally, intelligently predicting the final box returning amount of the month (namely 5-8 weeks) after the month of the current time by adopting a Prophet algorithm according to the box returning amount in the month (namely 5-8 weeks) after the month of the current time, the average box returning delay time GI LAG and the monthly box returning amount upper limit monthly cap of a certain port box.

Then, the weekly average box returning amount and the weekly average box returning increment are calculated according to the actual box returning amount of the month before the month where the current time is and the predicted box returning amount of the month after the month where the current time is, the box returning amount of a certain week in the future is intelligently predicted according to the weekly average box returning amount and the weekly average box returning increment, and the box returning amount of a certain month in the future is further intelligently predicted.

Specifically, as shown in fig. 5, the amount of the in-rented boxes and the amount of all the pre clear yet-to-be-returned boxes are obtained according to the contract number, and the total amount of the yet-to-be-returned boxes which needs to be predicted in 9 to (4 + mf + 4) weeks is calculated;

then, as shown in fig. 6, the amount of bins remaining for the future i-th month is predicted: according to the actual box returning amount of the previous month (namely 1-4 weeks) of the month of the current time and the predicted box returning amount of the next month (namely 5-8 weeks) of the month of the current time, calculating the average box returning amount Q and the average box returning increment QD every week by using the box returning amount of the 8 weeks, calculating the box returning amount of the K week in the future by using Q + K QD, and taking K =1,2,3,4 \8230, n corresponding to 9,10,11,12 \8230, n weeks corresponding to 2,3, \8230, n month (4 weeks of the i month are 4i + 1-4 i + 4);

taking the case returning amount of 4 weeks as an example, if the case returning amounts from the first week to the fourth week are 5,5, 10, 10 in turn, the average case returning amount Q = (5 + 10)/4 =7.5 ≈ 8, and the average case returning increment QD = [ (5-5) + (10-5) + (10-10) ]/3=1.666 ≈ 2.

After the box returning amount of the future K week is predicted, as shown in FIG. 7, the predicted box returning amount of a certain box type of a certain port in the ith future month (i is more than or equal to 2) (i.e. 4i +1 to 4 i- +4 weeks) is compared with the Monthly box returning amount upper limit Monthly cap of the certain box type of the certain port, the box returning amount of the ith future month is judged according to Monthly cap, and if the predicted box returning amount of the certain box type of the certain port in the ith month is less than the Monthly box returning amount upper limit of the certain box type of the certain port, i.e. the predicted box returning amount of the certain box type of the port in the month is less than Monthly cap, the predicted box returning amount of the certain box type of the port in the month is taken as the actual box returning amount;

if the predicted box returning amount of a certain box of a certain port in the ith month is more than or equal to the Monthly box returning amount upper limit of the certain box of the certain port, namely the predicted box returning amount of the certain box of the port in the month is more than or equal to Monthly cap, taking the Monthly box returning amount upper limit of the certain box of the port as the actual box returning amount;

for example: if the box returning amount of a certain box type of a certain port is 210,230,250,270 in a certain month, and Monthly cap of the box type of the port is 800, 210+230+250+270=960>800, 160 boxes cannot be returned, and only 110 boxes can be returned in the 4th week of the month, namely the box returning amount of the month is 210,230,250,110.

As shown in fig. 8, comparing the total amount of both the box returning amount and the box returning amount predicted for a certain box in a certain area in the ith (i is more than or equal to 2) month in the future (i.e. 4i +1 to 4 i- +4 weeks), and before the month with the box returning amount upper limit regional cap of the certain box in the certain area, judging the box returning amount in the ith month in the future according to the regional cap, and if the total amount is less than the box returning amount upper limit of the box in the certain area, i.e. all the box returning amount predicted for the box in the certain area in the month and before the month + the box returning amount is less than the regional cap, taking all the predicted box returning amount for the box in the certain area in the month and before the month as the actual box returning amount;

if the total number is larger than or equal to the upper limit of the box-type returning quantity of the area, namely, the sum of all predicted returning quantity of the box-type in the area before the month and the sum of the predicted returning quantity of the box-type in the area before the month is larger than or equal to the regional cap, the upper limit of the box-type returning quantity of the area is used as the actual returning quantity, the quantity of the box exceeding the upper limit of the returning quantity is evenly distributed to all ports in the area, and the evenly distributed quantity of the box exceeding the upper limit is subtracted from the predicted returning quantity of the box in the last week of the month in all the ports.

For example: if the returned box amount of a month, AP area, D20 box type, port 1 is 210,230,250,270, the returned box amount of the month and the previous is 1900, the returned box amount of the Port 2 is 230,250,270,290, the returned box amount of the month and the previous is 2000, the total returned box amount of the AP area is 3900, the regional local cap of the box type is 3700, the monthly box type of the month area has 200 boxes which can not be returned, the 200 boxes are equally divided into the two ports under the region, the returned box amount of the month D20 box type, the returned box amount of the Port 1 is 210,230,250,170, port 2 is 230,250,270,190.

After the box returning amount of month i is judged, as shown in FIG. 9, the predicted box returning amount of months 2-i of the total box returning amount of 9 to (4 + MF + 4) weeks (MF month is predicted if the predicted box returning amount of months MF is filled, MF month is predicted if no MF is filled, 12 months are predicted, 9 to 12 weeks is future month 2, \\ 8230; (8230304), MF +4 is 1 to 4 weeks is future month MF), whether the remaining box returning amount is greater than zero is judged, and if no box returning amount remains, the operation is finished; if the residual box returning amount is larger than zero, judging whether i is smaller than MF, if i is smaller than MF, performing cycle i = i +1, and continuously predicting the box returning amount of the next month; otherwise, if i is larger than or equal to MF, ending.

S5: and displaying the intelligently predicted box returning amount according to a preset chart type. Preferably, the chart type includes at least one of a summary histogram, a zone graph, a box-type line graph, and a port histogram, wherein the summary histogram shows the total trend of the box forecast; the region curve chart shows a box returning prediction trend according to regions; the box type line graph shows a box returning prediction trend according to the box type; the port histogram shows the bin return prediction trend according to the port.

The step S5 is to perform a chart display of the monthly or weekly returning stock amounts intelligently predicted in the steps S2, S3, S4, etc., wherein fig. 10 is an embodiment display effect diagram of predicted monthly returning stock data, which respectively displays monthly prediction trends according to regions, boxes, and ports, wherein curves representing the regions of america, asia, and europe show regional prediction trends according to months, a curve shows a prediction trend of a D4H box according to months, a bar graph of B shows a port with the monthly returning stock amount being equal to or greater than the monthly upper limit, and other bar graphs show ports with the monthly returning stock amount being less than the monthly upper limit. FIG. 11 is an exemplary effect graph of predicted weekly returning bin data showing predicted trends for region, box, and port, respectively, where curves representing the American, asian, and European regions show the regional predicted trend by week, curve C shows the predicted trend by D4H box by week, histogram D shows ports with weekly returning bin amounts greater than or equal to the monthly ceiling, and other histograms show ports with weekly returning bin amounts less than the monthly ceiling. The method can also be used for displaying by using a map, the map can have a certain box type returning prediction detail of a certain port, the port marked with the box returning is marked on the map, the predicted box returning amount of each box type in the future months can be displayed by clicking the port, and the box type returning prediction detail data of the box type in the port can be displayed by clicking the box type. As shown in fig. 12, the detailed prediction result may be downloaded in a list, and the downloading button is clicked to download the prediction detail data of the box returning process, which includes: time, area, port, box type, box returning quantity QTY and TEU.

The invention also relates to an intelligent prediction platform for the operative renting and returning of the container, which corresponds to the intelligent prediction method for the operative renting and returning of the container, can be understood as a platform for realizing the intelligent prediction method for the operative renting and returning of the container, is a background or a server in essence, can be inherited as an intelligent prediction APP for the operative renting and returning of the container, and comprises a first module, a second module, a third module, a fourth module and a fifth module, wherein the first module is respectively connected with the second module, the third module and the fourth module, the second module, the third module and the fourth module are respectively connected with the fifth module,

the third module is used for intelligently predicting the box returning amount of the second month and the months after the second month according to the predicting mode of the second module when the contract period is expired and no historical actual box returning data exists but a client applies for the box returning plan, and the box returning amount of the second month and the months after the second month is predicted and enters the fifth module after the prediction is finished;

calculating the weekly average box returning quantity and the weekly average box returning increment according to the actual box returning quantity of the month before the month in which the current time is positioned and the predicted box returning quantity of the month after the month in which the current time is positioned, intelligently predicting the box returning quantity of a certain week in the future according to the weekly average box returning quantity and the weekly average box returning increment, and further intelligently predicting the box returning quantity of a certain month in the future;

a fifth module: and displaying the intelligently predicted box returning amount of the second module, the third module or the fourth module according to a preset chart type.

Preferably, in the fourth module, after the box returning amount of a certain port in a certain future month is predicted, the predicted box returning amount of a certain box in a certain port in a certain future month is compared with the monthly box returning amount upper limit of a certain box in a certain port, and if the predicted box returning amount of a certain box in a certain port in a certain future month is smaller than the monthly box returning amount upper limit of a certain box in a certain port, the predicted box returning amount of the certain box in the certain port in the month is used as the actual box returning amount of the certain month;

if the predicted box returning amount of a certain box type of a certain port in a future month is more than or equal to the monthly box returning amount upper limit of the certain box type of the certain port, taking the monthly box returning amount upper limit of the box type of the certain port as the actual box returning amount of the month;

Preferably, in the fourth module, after the actual box returning amount of a month in the future is judged, if the total predicted box returning amount in the next month or several months after the month is equal to zero, the box returning prediction process is ended; if the total predicted case returning amount in the latter month or the latter months of the month is more than zero, judging whether the number of all the months before the month is less than the maximum predicted case returning month number, if the number of all the months before the month is less than the maximum predicted case returning month number, continuing to predict the predicted case returning amount in the next month of the month, and if the number of all the months before the month is more than or equal to the predicted case returning month number, ending the case returning prediction process.

Preferably, the chart type includes at least one of a summary bar chart, a zone graph, a box line chart, and a port bar chart.

Preferably, in the first module, a theme table is further created according to historical actual box returning data, wherein the theme table comprises a client ID, a contract number, a contract type, a box returning area, a box returning port and a box returning amount.

The platform PC end frame is based on the package of a lightweight J2EE framework of Spring Boot + Hibernate JPA, a front end interface layer adopts Vue technology, and an Ant design UI frame is used; the back end adopts a micro-service architecture, RPC communication, zookeeper is used as a registration center, redis cache service and a Nacos configuration center are used, a Docker container technology is introduced, and Tomcat is used as a method application server and is deployed on Linux. The front-end infrastructure adopts an MVVM design mode and adopts http to communicate with a network. The MVVM mode is an event-driven programming method that simplifies the user interface.

The platform PC end frame uses the current popular B/S structure, and is divided into three layers:

front end interface layer: according to the WEB front end of the data interaction standard required by the ant design or the front end of the anti design UI development framework, a user can operate only by a common WEB browser.

An application server layer: by adopting the mature technology in the industry, the application Tomcat7 is used as a method application server and is deployed on Linux to provide encapsulated application service support.

A database access layer: the Hibernate JPA has a Session mechanism and a second-level cache in the aspect of tuning and optimizing, and simultaneously can optimize and design SQL. The method can perfectly support large-scale database methods such as Oracle, mySQL, SQL Server and the like.

Spring is a lightweight controlled inversion (IoC) and section-oriented (AOP) container framework. It has the following characteristics:

lightweight-Spring is lightweight in both size and overhead.

Control inversion-Spring promotes loose coupling through a technique called control inversion (IoC).

The section-oriented Spring provides rich support for section-oriented programming, and allows cohesive development of business logic and method-level services (such as transaction management) of separated applications.

Spring Boot is a completely new framework provided by Pivotal team, and the design purpose of Spring Boot is to simplify the initial set-up and development process of new Spring applications. The framework uses a specific way to configure, thereby eliminating the need for developers to define a templated configuration.

Docker is an open source application container engine that allows developers to package their applications and dependencies into a portable container and then publish to any popular Linux machine, as well as to implement virtualization. The containers are fully sandboxed without any borrowing from each other.

RPC (Remote Procedure Call) -a Remote Call Procedure, a protocol that requests services from a Remote computer program over a network without knowledge of the underlying network technology. The RPC protocol assumes the existence of some transport protocol, such as TCP or UDP, for carrying information data between communication procedures. In the OSI network communication model, RPC spans the transport and application layers. RPC makes it easier to develop applications including network distributed multiprogrammers.

RPC employs a client/server model. The requesting program is a client and the service provider is a server. First, the client calling process sends a calling message with process parameters to the service process and then waits for a response message. On the server side, the process remains dormant until the call information arrives. When a calling message arrives, the server obtains the process parameters, calculates the result, sends the reply message, then waits for the next calling message, and finally the client calls the process to receive the reply message, obtains the process result, and then calls execution to continue.

Nacos is a service infrastructure that builds up modern application architectures (e.g., microservices paradigm, cloud-native paradigm) centered around "services". The method supports DNS-based and RPC-based service discovery (which can be used as a registration center of springclosed), dynamic configuration service (which can be used as a configuration center) and dynamic DNS service. Efforts are made to help discover, configure and manage microservices. A simple and easy-to-use feature set is provided, and dynamic service discovery, service configuration management, service and flow management are facilitated. The microservice platform is more agile and easy to build, deliver, and manage.

A Data Transfer Object (DTO) is a software application method for transferring Data between design patterns. Often the data transfer objective is for a data access object to retrieve data from a database. The difference between a data transfer object and a data interaction object or data access object is that the data (access and accessor) has no action other than storing and retrieving.

Hibernate is an object relational mapping solution in Java. Object relational mapping or ORM framework is a technique that maps application data model objects to relational database tables. Hibernate focuses not only on the mapping of Java classes to database tables, but also Java data types to SQL data types.

Web2.0 is a generic term for a new class of Internet applications relative to Web1.0. Web2.0 focuses more on the interaction of users, and a new generation of Internet mode is realized by using new theories and technologies such as xml and ajax. Better interaction mode and user experience can be provided for users.

By using the reverse proxy server, the request can be uniformly forwarded to a plurality of application servers, or the cached data can be directly returned to the client, so that the access speed can be increased to a certain extent by the acceleration mode, and the purpose of load balancing is achieved. By using the reverse proxy, the load balancing and the caching technology of the proxy server can be combined together, the beneficial performance and stability are provided, and the effective guarantee that the 7 × 24 service can be provided is provided.

The invention provides an objective and scientific intelligent container renting and returning prediction method and platform for container management leasing, which can accurately reveal a container returning trend, assist a container asset management enterprise in predicting a future container returning situation and help the enterprise to adjust and manage an operation strategy in time by adopting a specific calculation mode to predict the container returning quantity while considering factors such as an upper limit of a regional container returning limit, an upper limit of a port container returning limit in a monthly mode and the like based on historical data.

It should be noted that the above-described embodiments may enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail with reference to the drawings and examples, it will be understood by those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention.

Claims

1. An intelligent prediction method for returning containers for container business leasing is characterized by comprising the following steps:

s1: automatically acquiring historical actual case returning data of a client according to the historical contract data, automatically determining the predicted case returning month number according to the planned case returning month number of the client and/or the historical contract data, intelligently analyzing and determining the case returning proportion of a certain case type of a certain port according to the historical actual case returning data, then automatically judging the contract time limit, executing the step S2 when the contract time limit is not expired, and executing the step S3 or the step S4 when the contract time limit is expired;

s4: when the contract deadline is expired and the historical actual box returning data exists in the month before the current time, the box returning delay time of each box is obtained according to the box returning time data in the historical actual box returning data of the month, and the average box returning delay time of each box is calculated; calculating the number of boxes which can be returned in the month after the month of the current time in all the unreturned boxes according to the average box returning delay time of each box, and intelligently predicting the box returning amount in the month after the month of the current time by adopting a Prophet algorithm according to the number of boxes returned in the month after the month of the current time, the average box returning delay time and the upper limit of the box returning amount in the month of a certain box at a certain port;

2. The intelligent prediction method for the operational lease of containers as claimed in claim 1, wherein said step S4 further comprises the following steps after predicting the amount of returned containers in a month in the future:

3. The intelligent prediction method for the operational lease of containers as claimed in claim 2, wherein after the actual amount of containers returned in a month in the future is judged, if the total predicted amount of containers returned in the next month or several months after the month is equal to zero, the prediction process of containers returned is ended; if the total predicted case returning amount in the next month or the next months of the month is more than or equal to the predicted case returning month number, the case returning prediction process is ended.

4. The method for intelligently forecasting operational rental of containers as claimed in any one of claims 1 to 3, wherein in the step S5, the chart type includes at least one of a summary histogram, a zone graph, a box-type line graph and a port histogram.

5. The container operational leasing box-returning intelligent prediction method according to one of claims 1 to 3, wherein in the step S1, a theme table is created according to historical actual box-returning data, and the theme table comprises a customer ID, a contract number, a contract type, a box-returning area, a box-returning port and a box-returning amount.

6. An intelligent prediction platform for returning containers for commercial renting is characterized by comprising a first module, a second module, a third module, a fourth module and a fifth module, wherein the first module is respectively connected with the second module, the third module and the fourth module, the second module, the third module and the fourth module are all connected with the fifth module,

the system comprises a first module, a second module and a third module, wherein the first module is used for automatically acquiring historical actual case returning data of a client according to the historical contract data, automatically determining the predicted case returning month number according to the planned case returning month number of the client and/or the historical contract data, intelligently analyzing and determining the case returning proportion of a certain case type of a certain port according to the historical actual case returning data, then automatically judging the contract time limit, executing the second module when the contract time limit is not expired, and executing the third module or the fourth module when the contract time limit is expired;

the fourth module is used for obtaining the box returning delay time of each box according to the box returning time data in the historical actual box returning data of the month when the contract period is expired and the historical actual box returning data exists in the month before the current time, and calculating the average box returning delay time of each box; calculating the number of boxes which can be returned in the last month of the month in which the current time is located in all the unreturned boxes according to the average box returning delay time of each box, and intelligently predicting the box returning amount in the last month of the month in which the current time is located by adopting a Prophet algorithm according to the number of boxes returned in the last month of the month in which the current time is located, the average box returning delay time and the monthly box returning amount upper limit of a certain box type of a certain port;

7. The intelligent container rental and return forecasting platform according to claim 6, wherein the fourth module is configured to compare the predicted amount of the returned container for the certain port box in the certain month with the monthly upper limit of the amount of the returned container for the certain port box after predicting the amount of the returned container in the certain month in the future, and if the predicted amount of the returned container for the certain port box in the certain month is less than the monthly upper limit of the amount of the returned container for the certain port box in the certain month, the predicted amount of the returned container for the certain port box in the month is used as the actual amount of the returned container in the month;

comparing the total quantity of all predicted returned box quantities and the total quantity of the returned box quantities of a certain box type in a certain area before a certain month in the future with the upper limit of the returned box quantity of the certain box type in the certain area, and if the total quantity is smaller than the upper limit of the returned box quantity of the box type in the certain area, taking all predicted returned box quantities of the box type in the certain area before the month as the actual returned box quantity of the certain area;

8. The intelligent platform for container operational rental refund of claim 7, wherein in the fourth module, after determining the actual refund amount of a month in the future, if the total predicted refund amount in the latter month or several months of the month is equal to zero, the refund prediction process is ended; if the total predicted case returning amount in the latter month or the latter months of the month is more than zero, judging whether the number of all the months before the month is less than the maximum predicted case returning month number, if the number of all the months before the month is less than the maximum predicted case returning month number, continuing to predict the predicted case returning amount in the next month of the month, and if the number of all the months before the month is more than or equal to the predicted case returning month number, ending the case returning prediction process.

9. The container operational rental return intelligent prediction platform of any of claims 6-8, wherein the chart types include at least one of summary histograms, area graphs, box-type line graphs, and port histograms.

10. The container operational lease bin returning intelligent prediction platform according to one of claims 6 to 8, wherein in the first module, a theme table is further created according to historical actual bin returning data, wherein the theme table comprises a customer ID, a contract number, a contract type, a box type, a bin returning area, a bin returning port and a bin returning amount.