Intelligent logistics collaborative sorting method based on demand customization

Abstract

The invention discloses an intelligent logistics collaborative sorting method based on demand customization, and relates to the field of logistics transportation, and the method comprises the following steps: obtaining at least one sorting device in a logistics assembly line; forming a synergistic proportioning coefficient; a sorting demand function of the logistics assembly line is formed, and a burst sorting demand prediction function is formed; the maximum time interval with the sorting demand change smaller than the preset amplitude is obtained and serves as the characteristic time; a power consumption recognition model for calibrating the sorting equipment is established, and the feature demand package amount after the feature time is obtained; forming a historical time interval; obtaining the compensation demand package quantity after the characteristic time; the sudden demand parcel quantity after the characteristic time is obtained; and calculating to obtain the characteristic power consumption of the logistics assembly line. By establishing the power consumption identification model for calibrating the sorting equipment and analyzing the sorting demand package quantity in the historical time interval, the mutability and uncertainty of the sorting demand package quantity are considered, and therefore the sorting demand of the logistics assembly line is well met.

Description

Technical Field

[0001] The present invention relates to the field of logistics transportation, and specifically relates to an intelligent logistics collaborative sorting method based on demand customization. Background Art

[0002] A logistics sorting machine sorts a large number of logistics according to pre-set computer instructions and delivers the sorted goods to designated positions. It mainly scans the single numbers on the surface of each logistics good through a visual recognition system. After collecting the single number information, it can judge the channel to which the good needs to flow, and thus control the good to move for a certain time to reach the corresponding sorting area and then turn.

[0003] Due to the uncertainty of the number of packages received by the logistics pipeline, it is difficult to predict the power consumption of the logistics pipeline sorting. In order to avoid missing package sorting, almost all the sorting of the logistics pipeline runs at full load and at the fastest speed, resulting in more power consumption. Summary of the Invention

[0004] To solve the above technical problems, an intelligent logistics collaborative sorting method based on demand customization is provided, and this technical solution solves the problems raised in the above background art.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] An intelligent logistics collaborative sorting method based on demand customization, including:

[0007] Obtain at least one sorting device in the logistics pipeline;

[0008] Take the sorting device located in the middle position of the logistics pipeline as the calibration sorting device, and take the remaining sorting devices as collaborative sorting devices;

[0009] Form a collaborative ratio coefficient of the collaborative sorting device relative to the calibration sorting device;

[0010] Form a sorting demand function of the logistics pipeline and a sudden sorting demand prediction function;

[0011] Obtain the maximum time interval with the sorting demand change less than the preset amplitude as the characteristic time;

[0012] Establish a power consumption identification model of the calibration sorting device, and use the sorting demand function to obtain the characteristic demand package quantity after the characteristic time;

[0013] Form a historical time interval, which is composed of historical times with a distance from the current moment less than the characteristic time;

[0014] Based on the analysis of the parcel volume of sorting requirements in the historical time interval, the compensated demand parcel volume after the characteristic time is obtained;

[0015] Based on the sudden sorting demand prediction function, the sudden demand parcel volume after the characteristic time is obtained;

[0016] Based on the characteristic demand parcel volume, the compensated demand parcel volume and the sudden demand parcel volume, the characteristic power consumption of the logistics pipeline is calculated;

[0017] When the characteristic power consumption is greater than the current power consumption of the logistics pipeline, the power setting is performed according to the characteristic power consumption during the characteristic time of the current moment. Otherwise, the power setting is performed according to the current power consumption of the logistics pipeline during the characteristic time of the current moment.

[0018] Preferably, the formation of the collaborative ratio coefficient of the collaborative sorting device relative to the calibrated sorting device includes the following steps:

[0019] The time within a day is equally spaced into at least one sampling point. At the sampling point, the first sampling power of the collaborative sorting device is obtained, and at the sampling point, the second sampling power of the calibrated sorting device is obtained;

[0020] The sampling points are paired with the first sampling power and fitted to obtain the first fitting function;

[0021] The sampling points are paired with the second sampling power and fitted to obtain the second fitting function;

[0022] The first fitting function is divided by the second fitting function to obtain the coordination ratio function;

[0023] Integrate the coordination ratio function over 0 - 24 hours and divide by 24 to obtain the collaborative ratio coefficient of the collaborative sorting device relative to the calibrated sorting device.

[0024] Preferably, the formation of the sorting demand function of the logistics pipeline includes the following steps:

[0025] Within the preset number of days, the sorting requirements at the sampling points every day are counted to obtain at least one sorting demand parcel volume;

[0026] Based on the minimum and maximum values of at least one sorting demand parcel volume, a sorting demand interval is formed;

[0027] The sorting demand interval is equally spaced to obtain at least one sorting demand block;

[0028] The proportion of the sorting demand parcel volume included in the sorting demand block is used as the occurrence probability of the sorting demand block;

[0029] The sorting demand blocks with an occurrence probability greater than the preset probability are used as characteristic sorting demand blocks, where the preset probability is a probability value set based on experience;

[0030] Multiply the midpoint of the characteristic sorting demand block by the occurrence probability of the sorting demand block and then accumulate to obtain the total demand package quantity;

[0031] Pair the sampling points with the total demand package quantity and fit to obtain the sorting demand function of the logistics pipeline.

[0032] Preferably, the forming of the sudden sorting demand prediction function includes the following steps:

[0033] Substitute the sampling points into the sorting demand function to obtain sampling characteristic values;

[0034] Within the preset number of days, count the sorting demand at the sampling points every day to obtain at least one sorting demand package quantity, subtract the sampling characteristic value from the sorting demand package quantity to obtain the sudden package quantity;

[0035] Based on the minimum and maximum values of at least one sudden package quantity, form a sudden request interval;

[0036] Equally spaced divide the sudden request interval to obtain at least one sudden request block;

[0037] Take the proportion of the sudden package quantity included in the sudden request block as the occurrence probability of the sudden request block;

[0038] Multiply the midpoint of the characteristic sudden request block by the occurrence probability of the sudden request block and then accumulate to obtain the total sudden package quantity;

[0039] Pair the sampling points with the total sudden package quantity and fit to obtain the sudden package quantity function.

[0040] Preferably, the obtaining of the maximum time interval with the sorting demand change less than the preset amplitude as the characteristic time includes the following steps:

[0041] Evenly divide the time within a day into at least one recognition point, the spacing between adjacent recognition points is equal to the preset spacing, and count the difference in the sorting demand package quantity between adjacent recognition points as the characteristic difference;

[0042] When there is a characteristic difference not less than the preset amplitude, update the preset spacing to half of the original and repeat the previous step until all characteristic differences are less than the preset amplitude, otherwise, take the spacing between adjacent recognition points as the characteristic time;

[0043] Wherein, the power consumption change caused by the preset amplitude is the maximum value of the power consumption fluctuation allowed by the logistics pipeline.

[0044] Preferably, the establishment of the power consumption identification model for the calibration and sorting equipment includes the following steps:

[0045] Obtain the power consumption range of the calibration and sorting equipment, and equally divide the power consumption range of the calibration and sorting equipment to obtain at least one power consumption point;

[0046] Under the condition that the power consumption of the calibration and sorting equipment is equal to the power consumption point, obtain the conditional parcel volume of the logistics pipeline;

[0047] Pair and fit the conditional parcel volume with the value at the power consumption point to obtain a power consumption fitting function, where the conditional parcel volume is the independent variable and the power consumption point is the dependent variable.

[0048] Preferably, the use of the sorting demand function to obtain the characteristic demand parcel volume after the characteristic time includes the following steps:

[0049] Substitute the sum of the current moment and the characteristic time into the sorting demand function to obtain the characteristic demand parcel volume after the characteristic time.

[0050] Preferably, the analysis based on the sorting demand parcel volume in the historical time interval to obtain the compensated demand parcel volume after the characteristic time includes the following steps:

[0051] Evenly divide the historical time interval into at least one marked point, where the value of the rightmost marked point is equal to the current moment;

[0052] Obtain the actual demand parcel volume at the marked point, substitute the marked point into the sorting demand function to obtain the target demand parcel volume;

[0053] Take the difference between the actual demand parcel volume and the target demand parcel volume to obtain the quantity to be compensated;

[0054] Pair and fit the marked point with the quantity to be compensated to obtain a compensation fitting function, and take the derivative of the compensation fitting function to obtain a compensation derivative function;

[0055] Substitute at least one marked point into the compensation derivative function respectively and then take the average value to obtain the average slope;

[0056] Use the average slope to form a characteristic compensation function, and the characteristic compensation function is y = k(x - t) + b, where y is the compensation value, k is the average slope, x is the time variable, t is the current moment, and b is the quantity to be compensated at the current moment;

[0057] Let the time variable be equal to the characteristic time in the characteristic compensation function to obtain the compensated demand parcel volume after the characteristic time.

[0058] Preferably, the use of the sudden sorting demand prediction function to obtain the sudden demand parcel volume after the characteristic time includes the following steps:

[0059] Superimpose the current time on the characteristic time and substitute the result into the sudden sorting demand prediction function to obtain the quantity of parcels with sudden demand after the characteristic time.

[0060] Preferably, calculating the characteristic power consumption of the logistics pipeline based on the quantity of parcels with characteristic demand, the quantity of parcels with compensation demand, and the quantity of parcels with sudden demand includes the following steps:

[0061] Accumulate the quantity of parcels with characteristic demand, the quantity of parcels with compensation demand, and the quantity of parcels with sudden demand to obtain the estimated demand quantity of parcels;

[0062] Substitute the estimated demand quantity of parcels into the power consumption fitting function to obtain the first estimated power consumption of the calibrated sorting equipment;

[0063] Multiply the first estimated power consumption by the collaborative ratio coefficient of the collaborative sorting equipment relative to the quasi-sorting equipment to obtain the second estimated power consumption of the collaborative sorting equipment;

[0064] Accumulate the first estimated power consumption and at least one second estimated power consumption to obtain the characteristic power consumption of the logistics pipeline.

[0065] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0066] By forming a collaborative ratio coefficient, forming a sorting demand function for the logistics pipeline, forming a sudden sorting demand prediction function, establishing a power consumption identification model for the calibrated sorting equipment, and analyzing the quantity of parcels with sorting demand in the historical time interval, the quantity of parcels with characteristic demand, the quantity of parcels with compensation demand, and the quantity of parcels with sudden demand after the characteristic time are predicted, so that the quantity of parcels with sorting demand can be predicted in advance, and the sorting speed can be adjusted in advance. The prediction result takes into account the suddenness and uncertainty of the quantity of parcels with sorting demand, so that it can better meet the sorting demand of the logistics pipeline. At the same time, there is no need to perform full-power operation. Therefore, the waste of electricity can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic flow chart of the intelligent logistics collaborative sorting method based on demand customization of the present invention;

[0068] Figure 2 It is a schematic flow chart of forming the collaborative ratio coefficient of the collaborative sorting equipment relative to the calibrated sorting equipment of the present invention;

[0069] Figure 3 It is a schematic flow chart of forming the sorting demand function of the logistics pipeline of the present invention;

[0070] Figure 4 It is a schematic flow chart of forming the sudden sorting demand prediction function of the present invention;

[0071] Figure 5Schematic flow chart of obtaining the maximum time interval in which the change in sorting demand is less than a preset amplitude as the characteristic time according to the present invention;

[0072] Figure 6 Schematic flow chart of establishing a power consumption identification model for a calibrated sorting device according to the present invention;

[0073] Figure 7 Schematic flow chart of obtaining the compensated demand package quantity after the characteristic time based on the analysis of the package quantity of sorting demand in the historical time interval according to the present invention;

[0074] Figure 8 Schematic flow chart of calculating the characteristic power consumption of the logistics pipeline based on the characteristic demand package quantity, the compensated demand package quantity and the sudden demand package quantity according to the present invention. Detailed implementation manners

[0075] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0076] Referring to Figure 1 As shown, an intelligent logistics collaborative sorting method based on demand customization includes:

[0077] Obtain at least one sorting device in the logistics pipeline;

[0078] Use the sorting device located in the middle position of the logistics pipeline as the calibrated sorting device, and use the remaining sorting devices as collaborative sorting devices;

[0079] Form a collaborative ratio coefficient of the collaborative sorting device relative to the calibrated sorting device;

[0080] Form a sorting demand function of the logistics pipeline and a sudden sorting demand prediction function;

[0081] Obtain the maximum time interval in which the change in sorting demand is less than a preset amplitude as the characteristic time;

[0082] Establish a power consumption identification model for the calibrated sorting device, and use the sorting demand function to obtain the characteristic demand package quantity after the characteristic time;

[0083] Form a historical time interval, which is composed of historical times whose distance from the current moment is less than the characteristic time;

[0084] Based on the analysis of the package quantity of sorting demand in the historical time interval, obtain the compensated demand package quantity after the characteristic time;

[0085] Based on the sudden sorting demand prediction function, obtain the sudden demand package quantity after the characteristic time;

[0086] Based on the characteristic demand parcel volume, compensation demand parcel volume, and sudden demand parcel volume, the characteristic power consumption of the logistics pipeline is calculated;

[0087] When the characteristic power consumption is greater than the current power consumption of the logistics pipeline, the power is set according to the characteristic power consumption during the characteristic time at the current moment; otherwise, the power is set according to the current power consumption of the logistics pipeline during the characteristic time at the current moment.

[0088] When performing power setting, the characteristic power consumption is distributed to the sorting equipment according to the proportional relationship of the collaborative ratio coefficient of the sorting equipment, thereby synchronously increasing the sorting speed of all sorting equipment;

[0089] Although the demand parcel volume received by the logistics pipeline during daily operation shows a certain regularity, there are still fluctuations, and the demand parcel volume at the same moment every day is somewhat different. At the same time, during the operation process, there will also be situations of sudden sorting requirements. Therefore, a certain redundancy needs to be set for the power setting of the sorting equipment, that is, a certain value higher than the current required sorting speed is needed to cope with a large number of suddenly initiated sorting requirements. In this solution, corresponding steps are set to specifically solve the above problems;

[0090] Since the sorting speeds of the sorting equipment on the logistics pipeline are proportional, when there are many parcels, the speeds increase synchronously, and when there are few parcels, the speeds decrease synchronously. Therefore, when modeling, only one of them needs to be modeled. Therefore, a power consumption identification model for the calibrated sorting equipment is established to predict the power consumption of the calibrated sorting equipment through the demand parcel volume, and the power consumption of the collaborative sorting equipment is obtained through the collaborative ratio coefficient of the collaborative sorting equipment relative to the calibrated sorting equipment. Furthermore, the power supply can deliver the corresponding electricity to the corresponding sorting equipment, thereby achieving uniform coordination.

[0091] Refer to Figure 2 As shown, the steps for forming the collaborative ratio coefficient of the collaborative sorting equipment relative to the calibrated sorting equipment are as follows:

[0092] The time within a day is equally spaced and divided into at least one sampling point. At the sampling point, the first sampling power of the collaborative sorting equipment is obtained, and at the sampling point, the second sampling power of the calibrated sorting equipment is obtained;

[0093] Pair the sampling points with the first sampling power and fit them to obtain the first fitting function;

[0094] Pair the sampling points with the second sampling power and fit them to obtain the second fitting function;

[0095] Divide the first fitting function by the second fitting function to obtain the coordination ratio function;

[0096] Integrate the coordination ratio function over 0 - 24 hours and divide by 24 to obtain the coordination ratio coefficient of the collaborative sorting device relative to the calibrated sorting device.

[0097] Since the simultaneous power consumption of the collaborative sorting device and the calibrated sorting device is not completely constant because the situation of each sorting device is different, when it is operating, in order to more accurately estimate the coordination ratio coefficient, the method of integrating over 0 - 24 hours is used to obtain the comprehensive proportional relationship.

[0098] Refer to Figure 3 As shown, the steps to form the sorting demand function of the logistics pipeline are as follows:

[0099] Within a preset number of days, count the sorting demand at the sampling point every day to obtain at least one sorting demand package quantity;

[0100] Based on the minimum and maximum values of at least one sorting demand package quantity, form a sorting demand interval;

[0101] Equally spaced divide the sorting demand interval to obtain at least one sorting demand block;

[0102] Take the proportion of the sorting demand package quantity included in the sorting demand block as the occurrence probability of the sorting demand block;

[0103] Take the sorting demand blocks with occurrence probability greater than the preset probability as the characteristic sorting demand blocks, where the preset probability is a probability value set based on experience;

[0104] Multiply the midpoint of the characteristic sorting demand block by the occurrence probability of the sorting demand block and accumulate to obtain the total demand package quantity;

[0105] Pair and fit the sampling point with the total demand package quantity to obtain the sorting demand function of the logistics pipeline.

[0106] Here, the sorting demand blocks are screened to obtain the characteristic sorting demand blocks. The purpose is to delete the sudden sorting requests. Because usually, the probability of sudden requests is low, so they can be screened by probability. In addition, by comprehensively counting the situations of multiple days, the data obtained can reflect the requests received by the logistics pipeline. Therefore, the function obtained by fitting can roughly estimate the sorting demand, but there are certain errors in the results, which need to be compensated later.

[0107] Refer to Figure 4 As shown, the steps to form the sudden sorting demand prediction function are as follows:

[0108] Substitute the sampling point into the sorting demand function to obtain the sampling characteristic value;

[0109] Within a preset number of days, count the sorting requirements at the sampling point every day to obtain at least one sorted demand parcel volume. Subtract the sampling characteristic value from the sorted demand parcel volume to obtain the unexpected parcel volume.

[0110] Based on the minimum and maximum values of at least one unexpected parcel volume, form an unexpected request interval.

[0111] Equidistantly divide the unexpected request interval to obtain at least one unexpected request block.

[0112] Take the proportion of the unexpected parcel volume included in the unexpected request block as the occurrence probability of the unexpected request block.

[0113] Multiply the midpoint of the characteristic unexpected request block by the occurrence probability of the unexpected request block and accumulate to obtain the total unexpected parcel volume.

[0114] Pair and fit the sampling point with the total unexpected parcel volume to obtain an unexpected parcel volume function.

[0115] The unexpected parcel volume function is used to predict unexpected situations. Thus, when setting the power of the sorting equipment, the redundant power consumption can be determined. When an unexpected request occurs, the provided power consumption can meet the additional power setting requirements caused by the unexpected request.

[0116] Refer to Figure 5 As shown, obtaining the maximum time interval with the sorting requirement change less than the preset amplitude as the characteristic time includes the following steps:

[0117] Evenly divide the time within a day into at least one identification point. The distance between adjacent identification points is equal to the preset distance. Count the difference in the sorted demand parcel volume between adjacent identification points as the characteristic difference.

[0118] When there is a characteristic difference not less than the preset amplitude, update the preset distance to half of the original and repeat the previous step until all characteristic differences are less than the preset amplitude. Otherwise, take the distance between adjacent identification points as the characteristic time.

[0119] Among them, the power consumption change caused by the preset amplitude is the maximum value of the power consumption fluctuation allowed by the logistics pipeline.

[0120] The role of the characteristic time is to determine the length of the time for early prediction. Since the power supply cannot make corresponding adjustments when the request appears, due to the delay in adjustment, the logistics pipeline will not be able to meet the processing requirements. In the characteristic time, since the time is short, the number of sorting requirements is almost unchanged. Therefore, within the characteristic time length, existing data can be used to predict unknown data. Here, it is mainly used to obtain the compensated demand parcel volume after the characteristic time based on the analysis of the sorted demand parcel volume in the historical time interval.

[0121] Refer to Figure 6 As shown, establishing a power consumption identification model for the calibration sorting device includes the following steps:

[0122] Obtain the power consumption range of the calibration sorting device, and equally divide the power consumption range of the calibration sorting device to obtain at least one power consumption point;

[0123] Under the condition that the power consumption of the calibration sorting device is equal to the power consumption point, obtain the conditional parcel volume of the logistics pipeline;

[0124] Pair and fit the conditional parcel volume with the value at the power consumption point to obtain a power consumption fitting function, where the conditional parcel volume is the independent variable and the power consumption point is the dependent variable.

[0125] There is a certain functional relationship between power consumption and the sorting demand parcel volume. Therefore, when the sorting demand parcel volume can be predicted, it is also necessary to establish a power consumption identification model for the calibration sorting device. Thus, the power consumption of the calibration sorting device can be predicted according to the sorting demand parcel volume, and then based on the collaborative ratio coefficient, the power consumption of the collaborative sorting device can be predicted. Thus, the power setting power consumption of the sorting device can be obtained, and then the power is set according to this power consumption, which can not only meet the usage requirements, but also the sorting device does not need to operate at full power.

[0126] Using the sorting demand function to obtain the characteristic demand parcel volume after the characteristic time includes the following steps:

[0127] Superimpose the current time and the characteristic time and substitute them into the sorting demand function to obtain the characteristic demand parcel volume after the characteristic time.

[0128] Refer to Figure 7 As shown, based on the analysis of the sorting demand parcel volume in the historical time interval, obtaining the compensated demand parcel volume after the characteristic time includes the following steps:

[0129] Evenly divide the historical time interval into at least one marked point, where the value of the rightmost marked point is equal to the current time;

[0130] Obtain the actual demand parcel volume at the marked point, substitute the marked point into the sorting demand function to obtain the target demand parcel volume;

[0131] Take the difference between the actual demand parcel volume and the target demand parcel volume to obtain the quantity to be compensated;

[0132] Pair and fit the marked point with the quantity to be compensated to obtain a compensation fitting function, and take the derivative of the compensation fitting function to obtain a compensation derivative function;

[0133] Substitute at least one marked point into the compensation derivative function and then take the average value to obtain the average slope;

[0134] A feature compensation function is formed using the average slope. The feature compensation function is y = k(x - t) + b, where y is the compensation value, k is the average slope, x is the time variable, t is the current moment, and b is the quantity to be compensated at the current moment;

[0135] In the feature compensation function, let the time variable be equal to the feature time to obtain the compensated demand package quantity after the feature time.

[0136] Since the sorting demand per day is regular but not completely certain, there are certain deviations in the data predicted by the sorting demand function, so compensation is required. Since the request situations within the feature time length are similar, based on the analysis of the compensation situations in the historical time interval, the compensated demand package quantity after the feature time is predicted. Because the time length is small and its compensation has a certain similarity, this prediction can be carried out and the deviation predicted by the sorting demand function can be reduced.

[0137] Based on the sudden sorting demand prediction function, obtaining the sudden demand package quantity after the feature time includes the following steps:

[0138] Substitute the sum of the current moment and the feature time into the sudden sorting demand prediction function to obtain the sudden demand package quantity after the feature time.

[0139] Refer to Figure 8 As shown, based on the feature demand package quantity, the compensated demand package quantity, and the sudden demand package quantity, calculating the characteristic power consumption of the logistics pipeline includes the following steps:

[0140] Accumulate the feature demand package quantity, the compensated demand package quantity, and the sudden demand package quantity to obtain the estimated demand package quantity;

[0141] Substitute the estimated demand package quantity into the power consumption fitting function to obtain the first estimated power consumption of the calibrated sorting equipment;

[0142] Multiply the first estimated power consumption by the cooperation ratio coefficient of the collaborative sorting equipment relative to the quasi-sorting equipment to obtain the second estimated power consumption of the collaborative sorting equipment;

[0143] Accumulate the first estimated power consumption and at least one second estimated power consumption to obtain the characteristic power consumption of the logistics pipeline.

[0144] Furthermore, this solution also proposes a storage medium on which a computer-readable program is stored. When the computer-readable program is called, it executes the above-mentioned intelligent logistics collaborative sorting method based on demand customization.

[0145] It can be understood that the storage medium can be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid-state drive (SSD).

[0146] In summary, the advantages of the present invention are as follows: by forming a collaborative ratio coefficient, forming a sorting demand function for the logistics pipeline, forming a prediction function for sudden sorting demand, establishing a power consumption identification model for calibrating sorting equipment, and analyzing the sorted demand package volume in the historical time interval, the sorted demand package volume, compensation demand package volume, and sudden demand package volume after the characteristic time are predicted, so that the sorted demand package volume can be predicted in advance and the sorting speed can be adjusted in advance. The prediction result takes into account the suddenness and uncertainty of the sorted demand package volume, so that it can better meet the sorting demand of the logistics pipeline. At the same time, there is no need to perform full-power operation. Therefore, the waste of electricity can be reduced.

[0147] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the principles described in the specification are only the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent logistics collaborative sorting method based on requirement customization, characterized in that, Including: Obtain at least one sorting device in the logistics pipeline; Take the sorting device located in the middle position of the logistics pipeline as the calibrated sorting device, and the remaining sorting devices as collaborative sorting devices; Form a collaborative ratio coefficient of the collaborative sorting device relative to the calibrated sorting device; Form a sorting demand function of the logistics pipeline and a sudden sorting demand prediction function; Obtain the maximum time interval when the change in sorting demand is less than a preset amplitude as the characteristic time; Establish a power consumption identification model for the calibrated sorting device, and use the sorting demand function to obtain the characteristic demand package quantity after the characteristic time; Form a historical time interval, which is composed of historical times whose distance from the current moment is less than the characteristic time; Based on the analysis of the sorting demand package quantity in the historical time interval, obtain the compensated demand package quantity after the characteristic time; Based on the sudden sorting demand prediction function, obtain the sudden demand package quantity after the characteristic time; Based on the characteristic demand package quantity, compensated demand package quantity, and sudden demand package quantity, calculate the characteristic power consumption of the logistics pipeline; When the characteristic power consumption is greater than the current power consumption of the logistics pipeline, the power is set according to the characteristic power consumption within the characteristic time of the current moment. Otherwise, the power is set according to the current power consumption of the logistics pipeline within the characteristic time of the current moment.

2. The intelligent logistics collaborative sorting method based on requirement customization according to claim 1, wherein, The formation of the collaborative ratio coefficient of the collaborative sorting device relative to the calibrated sorting device includes the following steps: Equally divide the time within a day into at least one sampling point. At the sampling point, obtain the first sampling power of the collaborative sorting device, and at the sampling point, obtain the second sampling power of the calibrated sorting device; Pair the sampling points with the first sampling power and fit them to obtain the first fitting function; Pair the sampling points with the second sampling power and fit them to obtain the second fitting function; Divide the first fitting function by the second fitting function to obtain the coordination ratio function; Integrate the coordination ratio function over 0 - 24 hours and divide by 24 to obtain the collaborative ratio coefficient of the collaborative sorting device relative to the calibrated sorting device.

3. The intelligent logistics collaborative sorting method customized based on requirements according to claim 2, wherein The formation of the sorting demand function of the logistics pipeline includes the following steps: Within a preset number of days, count the sorting demands at the sampling points every day to obtain at least one sorting demand package quantity; Based on the minimum and maximum values of at least one sorting demand package quantity, form a sorting demand interval; Equally divide the sorting demand interval to obtain at least one sorting demand block; Take the proportion of the sorting demand package quantity included in the sorting demand block as the occurrence probability of the sorting demand block; Take the sorting demand block with an occurrence probability greater than the preset probability as the characteristic sorting demand block, where the preset probability is a probability value set based on experience; Multiply the midpoint of the characteristic sorting demand block by the occurrence probability of the sorting demand block and accumulate to obtain the total demand package quantity; Pair the sampling points with the total demand package quantity and fit them to obtain the sorting demand function of the logistics pipeline.

4. The intelligent logistics collaborative sorting method customized based on requirements according to claim 3, characterized in that, The formation of the sudden sorting demand prediction function includes the following steps: Substitute the sampling points into the sorting demand function to obtain the sampling characteristic values; Within a preset number of days, count the sorting requirements at the sampling point each day to obtain at least one sorting requirement package quantity. Subtract the sampling characteristic value from the sorting requirement package quantity to obtain the sudden package quantity. Based on the minimum and maximum values of at least one sudden package quantity, form a sudden request interval. Equally spaced divide the sudden request interval to obtain at least one sudden request block. Take the proportion of the sudden package quantity included in the sudden request block as the occurrence probability of the sudden request block. Multiply the midpoint of the characteristic sudden request block by the occurrence probability of the sudden request block and accumulate to obtain the overall sudden package quantity. Pair the sampling point with the overall sudden package quantity and fit to obtain the sudden package quantity function.

5. The intelligent logistics collaborative sorting method customized based on requirements according to claim 4, characterized in that, The step of obtaining the maximum time interval with the sorting requirement change less than the preset amplitude as the characteristic time includes the following: Evenly divide the time within a day into at least one identification point, where the spacing between adjacent identification points is equal to the preset spacing. Count the difference in the sorting requirement package quantity between adjacent identification points as the characteristic difference. When there is a characteristic difference not less than the preset amplitude, update the preset spacing to half of the original, and repeat the previous step until all characteristic differences are less than the preset amplitude. Otherwise, take the spacing between adjacent identification points as the characteristic time. Among them, the power consumption change caused by the preset amplitude is the maximum value of the power consumption fluctuation allowed by the logistics pipeline.

6. The intelligent logistics collaborative sorting method customized based on requirements according to claim 5, characterized in that, The step of establishing the power consumption identification model for the calibrated sorting equipment includes the following: Obtain the power consumption range of the calibrated sorting equipment, and equally spaced divide the power consumption range of the calibrated sorting equipment to obtain at least one power consumption point. Under the condition that the power consumption of the calibrated sorting equipment is equal to the power consumption point, obtain the conditional package quantity of the logistics pipeline. Pair the conditional package quantity with the value at the power consumption point and fit to obtain the power consumption fitting function, where the conditional package quantity is the independent variable and the power consumption point is the dependent variable.

7. A customized intelligent logistics collaborative sorting method based on requirements according to claim 6, characterized in that, The step of using the sorting requirement function to obtain the characteristic demand package quantity after the characteristic time includes the following: Substitute the sum of the current moment and the characteristic time into the sorting requirement function to obtain the characteristic demand package quantity after the characteristic time.

8. An intelligent logistics collaborative sorting method customized based on requirements according to claim 7, characterized in that, The step of obtaining the compensated demand package quantity after the characteristic time based on the analysis of the sorting requirement package quantity in the historical time interval includes the following: Evenly divide the historical time interval into at least one marked point, where the value of the rightmost marked point is equal to the current moment. Obtain the actual demand package quantity at the marked point, substitute the marked point into the sorting requirement function to obtain the target demand package quantity. Subtract the target demand package quantity from the actual demand package quantity to obtain the quantity to be compensated. Pair the marked point with the quantity to be compensated and fit to obtain the compensation fitting function, and take the derivative of the compensation fitting function to obtain the compensation derivative function. Substitute at least one marked point into the compensation derivative function respectively and take the average value to obtain the average slope. Use the average slope to form the characteristic compensation function, and the characteristic compensation function is y = k(x - t) + b, where y is the compensation value, k is the average slope, x is the time variable, t is the current moment, and b is the quantity to be compensated at the current moment. Let the time variable be equal to the characteristic time in the characteristic compensation function to obtain the compensated demand package quantity after the characteristic time.

9. The intelligent logistics collaborative sorting method customized based on requirements according to claim 8, wherein The steps for obtaining the volume of parcels with sudden demand after the characteristic time based on the sudden sorting demand prediction function are as follows: Superimpose the current time and the characteristic time and substitute the result into the sudden sorting demand prediction function to obtain the volume of parcels with sudden demand after the characteristic time.

10. A demand-based customized intelligent logistics collaborative sorting method according to claim 9, characterized in that, The steps for calculating the characteristic power consumption of the logistics pipeline based on the volume of parcels with characteristic demand, the volume of parcels with compensation demand, and the volume of parcels with sudden demand are as follows: Accumulate the volume of parcels with characteristic demand, the volume of parcels with compensation demand, and the volume of parcels with sudden demand to obtain the estimated volume of parcels with demand; Substitute the estimated volume of parcels with demand into the power consumption fitting function to obtain the first estimated power consumption of the calibrated sorting equipment; Multiply the first estimated power consumption by the collaborative ratio coefficient of the collaborative sorting equipment relative to the quasi-sorting equipment to obtain the second estimated power consumption of the collaborative sorting equipment; Accumulate the first estimated power consumption and at least one second estimated power consumption to obtain the characteristic power consumption of the logistics pipeline.

Images