WO2023116075A1 - 站点到货量预测方法、装置、电子设备和计算机可读介质 - Google Patents

站点到货量预测方法、装置、电子设备和计算机可读介质 Download PDF

Info

Publication number
WO2023116075A1
WO2023116075A1 PCT/CN2022/118580 CN2022118580W WO2023116075A1 WO 2023116075 A1 WO2023116075 A1 WO 2023116075A1 CN 2022118580 W CN2022118580 W CN 2022118580W WO 2023116075 A1 WO2023116075 A1 WO 2023116075A1
Authority
WO
WIPO (PCT)
Prior art keywords
historical
volume
site
cargo
cargo volume
Prior art date
Application number
PCT/CN2022/118580
Other languages
English (en)
French (fr)
Inventor
苏小龙
王煜
庄晓天
严良
吴盛楠
Original Assignee
北京京东振世信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京京东振世信息技术有限公司 filed Critical 北京京东振世信息技术有限公司
Publication of WO2023116075A1 publication Critical patent/WO2023116075A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0838—Historical data

Definitions

  • the embodiments of the present disclosure relate to the field of computer technology, and in particular to a site-to-shipment volume forecasting method, device, electronic device, and computer-readable medium.
  • the logistics distribution network model of the first sorting center-last sorting center-site is usually used for distribution.
  • the site arrival quantity of each site can be predicted based on the predicted total volume of the final sorting center. Therefore, it is necessary to first determine that the proportion of the station's cargo volume in the final sorting center is stable, so that the site's arrival volume can be predicted based on the stable cargo volume ratio.
  • the usual method is: based on variance analysis or graph analysis, determine whether the proportion of the volume of each site corresponding to the last sorting center is stable from the dimension of the sorting center, and then predict the arrival of the site. volume.
  • Some embodiments of the present disclosure propose a method, device, electronic device, and computer-readable medium for forecasting site arrival quantity, so as to solve the technical problems mentioned in the background art section above.
  • some embodiments of the present disclosure provide a method for predicting the quantity of goods arriving at a site, the method including: acquiring a set of goods quantity information of a target sorting center within a preset historical period, wherein, in the above-mentioned set of goods quantity information
  • the volume information includes the historical volumes sorted by the target sorting center to the corresponding sites; based on each of the above sites, according to the historical volumes of the corresponding sites included in the volume information set, generate The historical cargo volume proportions of the above-mentioned sites within the above-mentioned preset historical period are used as the historical cargo volume proportion group to obtain the historical cargo volume proportion group set; based on the above-mentioned historical cargo volume proportion group set and each of the above-mentioned sites , to determine whether the historical cargo volume proportion of the above-mentioned site is stable within the above-mentioned preset historical period; For each historical volume of the target site, generate the proportion of the target volume, wherein the above-mentioned historical
  • some embodiments of the present disclosure provide a device for predicting the quantity of goods arriving at a site.
  • the quantity information in the quantity information set includes each historical quantity of goods sorted by the above-mentioned target sorting center to each corresponding site;
  • the first generation unit is configured to, based on each of the above-mentioned stations, Each historical cargo volume corresponding to the above-mentioned sites included in the collection generates the historical cargo volume ratio of each of the above-mentioned sites within the preset historical period as a historical cargo volume percentage group, and obtains a set of historical cargo volume percentage groups;
  • the determination unit is configured Based on the above-mentioned set of historical volume ratio groups and each of the above-mentioned sites, determine whether the historical volume ratio of the above-mentioned site within the above-mentioned preset historical period is stable;
  • the second generating unit is configured to respond to the determination of the above-mentioned The historical cargo volume ratio of the target site in each site is stable, and the target cargo
  • some embodiments of the present disclosure provide an electronic device, including: at least one processor; and a storage device, on which at least one program is stored.
  • the device implements the method described in any implementation manner of the first aspect above.
  • some embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
  • FIG. 1 is a schematic diagram of an application scenario of a method for forecasting site arrival volume according to some embodiments of the present disclosure
  • FIG. 2 is a flow chart of some embodiments of a site arrival quantity prediction method according to the present disclosure
  • Fig. 3 is a flow chart of other embodiments of the method for predicting the quantity of goods arriving at a site according to the present disclosure
  • Fig. 4 is a flow chart of some other embodiments of the site arrival quantity prediction method according to the present disclosure.
  • Fig. 5 is a structural schematic diagram of some embodiments of an apparatus for predicting the quantity of goods arriving at a site according to the present disclosure
  • FIG. 6 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure.
  • Relevant site arrival forecast methods determine from the sorting center dimension whether the proportion of goods at each site corresponding to the last sorting center is stable, and then predict the site arrival volume, etc.
  • some embodiments of the present disclosure propose methods and devices for forecasting site arrival volume, which can automatically and quickly determine the stability of the volume ratio of each site corresponding to the sorting center, and the predicted site arrival Cargo volume accuracy has been improved.
  • Fig. 1 is a schematic diagram of an application scenario of a site arrival quantity prediction method according to some embodiments of the present disclosure.
  • the computing device 101 may acquire the quantity information set 102 of the target sorting center within a preset historical period.
  • the quantity information in the above-mentioned quantity information set 102 includes each historical quantity of goods sorted by the above-mentioned target sorting center to each corresponding site.
  • the computing device 101 may, based on each of the above-mentioned stations, generate the proportion of each historical cargo volume of the above-mentioned stations within the above-mentioned preset historical period according to the respective historical cargo volumes corresponding to the above-mentioned stations included in the above-mentioned cargo volume information set 102 As the historical cargo volume proportion group, the historical cargo volume proportion group set 103 is obtained.
  • the computing device 101 may determine whether the historical cargo volume ratio of the aforementioned site within the aforementioned preset historical period is stable based on the aforementioned historical cargo volume proportion group set 103 and each of the aforementioned sites. Secondly, the computing device 101 may generate the target cargo volume according to the historical volume set 104 and the historical cargo volume corresponding to the target site in the historical cargo volume set 104 in response to determining that the historical volume ratio of the target site in each of the above sites is stable. The volume accounted for 105. Wherein, the historical cargo volume collection 104 is a collection of historical cargo volumes included in the cargo volume information collection 102 . Finally, the computing device 101 can generate a site arrival volume 107 corresponding to the above target site according to the above target cargo volume ratio 105 and the predicted total cargo volume 106 corresponding to the above target sorting center.
  • the above-mentioned computing device 101 may be hardware or software.
  • the computing device When the computing device is hardware, it can be realized as a distributed cluster composed of multiple servers or terminal devices, or as a single server or a single terminal device.
  • the computing device When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented, for example, as a plurality of software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.
  • the site arrival quantity forecasting method includes the following steps:
  • Step 201 acquire the quantity information set of the target sorting center within a preset historical period.
  • the execution subject of the method for predicting the arrival quantity at a site can obtain the quantity of goods at the target sorting center within a preset historical period from the terminal through a wired connection or a wireless connection. collection of information.
  • the aforementioned preset historical period may be any previously set historical period.
  • the specific setting of the preset historical period is not limited here.
  • the above-mentioned target sorting center can be any final sorting center.
  • the final sorting center mentioned above may be a sorting warehouse for directly delivering goods to various stations.
  • the number of stations corresponding to the above-mentioned target sorting center may be greater than or equal to the preset number.
  • the preset number can be 3.
  • the specific setting of the preset quantity is not limited.
  • Each piece of cargo volume information in the aforementioned cargo volume information set corresponds to each time granularity within the aforementioned preset historical period.
  • the aforementioned preset historical period may be "2021/10/11-2021/10/24".
  • the first volume information in the above volume information set corresponds to the time granularity 2021/10/11.
  • the second volume information in the above volume information set corresponds to the time granularity of 2021/10/12.
  • the above cargo quantity information may include each historical quantity of cargo sorted by the above target sorting center to each corresponding station. It can be understood that the above cargo volume information may include the historical cargo volume of each site at a time granularity.
  • the above-mentioned historical volume may be the historical number of packages arriving at a site of the above-mentioned target sorting center.
  • the aforementioned preset historical period may be "2021/10/11-2021/10/14".
  • the above volume information collection can be:
  • the time granularity corresponding to the first volume information [site a: 60, site b: 40, site c: 20, site d: 80] is 2021/10/11.
  • the time granularity corresponding to the second volume information [site a: 40, site b: 40, site c: 80, site d: 40] is 2021/10/12.
  • the time granularity corresponding to the third volume information [site a: 50, site b: 60, site c: 80, site d: 30] is 2021/10/13.
  • the fourth volume information [site a: 50, site b: 50, site c: 70, site d: 40] corresponds to a time granularity of 2021/10/14.
  • the above wireless connection methods may include but not limited to 3G/4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods known or developed in the future . Therefore, the acquired cargo volume information set within the preset historical period can be used as a real historical data source for determining the stability of the cargo volume ratio of each site corresponding to the target sorting center.
  • the execution subject may determine the historical cargo volume sequence of each of the aforementioned sites within the aforementioned preset historical period according to the individual cargo volume information included in the aforementioned cargo volume information set, and obtain the historical cargo volume sequence gather.
  • the above-mentioned executive body can extract the historical cargo volume of the above-mentioned site at each time granularity from the above-mentioned various cargo volume information, and obtain the historical cargo volume sequence.
  • each historical volume sequence whose historical cargo volume is smaller than the preset cargo volume threshold value will be included.
  • the volume sequence is determined as a set of historical volume sequences to be deleted.
  • the aforementioned preset cargo volume threshold may be a preset minimum cargo volume threshold.
  • the specific setting of the above cargo volume threshold is not limited.
  • each historical volume included in the above-mentioned historical volume sequence set to be deleted may be deleted from the above-mentioned volume information set.
  • the execution subject may respond to at least one historical volume sequence whose historical volume satisfies the preset outlier condition in the above-mentioned historical volume sequence set, and include each history whose historical volume satisfies the aforementioned preset outlier condition
  • the volume sequence is determined as a set of historical volume sequences to be smoothed.
  • the above preset outlier conditions may include but not limited to at least one of the following: there is a historical volume in the historical volume sequence that is greater than N times the average value of each historical volume included in the historical volume sequence, and the historical volume sequence There is a historical cargo volume in M times that is less than M times the mean value of each historical cargo volume included in the above-mentioned historical cargo volume sequence, and there is a historical cargo volume in the historical cargo volume sequence that is greater than the sum of the upper quartile and X times the interquartile range, There are historical volumes in the historical volume series that are less than the difference between the lower quartile and Y times the interquartile range.
  • a quarter of the historical volumes in the above-mentioned series of historical volumes are greater than the above-mentioned upper quartile.
  • a quarter of the historical volumes in the above-mentioned series of historical volumes are smaller than the above-mentioned lower quartile.
  • the above-mentioned interquartile range is the difference between the above-mentioned upper quartile and the above-mentioned lower quartile.
  • N is a numerical value greater than 1.
  • N can be 10.
  • M is a numerical value less than 1.
  • M can be 0.1.
  • X and Y are values greater than 1.
  • both X and Y may be 1.5.
  • the specific settings of N, M, X and Y are not limited.
  • the above-mentioned historical cargo volume can be generated according to the above-mentioned historical cargo volume sequence to be smoothed.
  • the smoothed historical volume of volume and replace the above historical volume with the above smoothed historical volume.
  • the above-mentioned executive body may remove the above-mentioned historical cargo volume from the above-mentioned historical cargo volume sequence to be smoothed. Then, the average value of the historical cargo volume to be smoothed included in the historical cargo volume sequence to be smoothed after the above historical cargo volume is excluded may be determined as the smoothed historical cargo volume. Afterwards, the above-mentioned smoothed historical cargo volume may be added to the position corresponding to the above-mentioned historical cargo volume in the above-mentioned historical cargo volume sequence to be smoothed. Thus, extremely large or extremely small historical volumes can be smoothed.
  • Step 202 based on each of the stations, according to the historical cargo volume of the corresponding site included in the cargo volume information set, generate the proportion of each historical cargo volume of the site within the preset historical period as the historical cargo volume proportion group, and obtain A collection of historical volume proportion groups.
  • the execution subject can generate the historical cargo volumes of the above-mentioned sites within the preset historical period according to the historical cargo volumes of the above-mentioned sites included in the cargo-volume information set.
  • the volume proportion is used as the historical cargo volume proportion group, and the historical cargo volume proportion group set is obtained.
  • the executive body may determine the sum of the historical cargo volumes corresponding to the aforementioned sites included in the cargo volume information set as the total historical cargo volume of the site.
  • the ratio of each historical cargo volume corresponding to the above-mentioned site included in the cargo volume information set to the total historical cargo volume of the above-mentioned site may be determined as the historical cargo volume proportion, and a historical cargo volume proportion group is obtained. Then a set of historical volume proportion groups can be obtained.
  • the proportion of the historical volume of each site at each time granularity within the preset historical period can be determined.
  • the above-mentioned executive body can determine the ratio of the historical cargo volume 60 to the total historical cargo volume of the above-mentioned site as 3/10 .
  • the above-mentioned executive body can determine the ratio of the historical cargo volume 40 to the total historical cargo volume of the above-mentioned site 200 as the ratio of historical cargo volume to 2/10 .
  • the above-mentioned executive body can determine the ratio of the historical cargo volume 50 to the total historical cargo volume 200 of the above-mentioned site as the historical cargo volume. than 1/4.
  • the historical volume ratio group corresponding to site a is obtained as [3/10, 2/10, 1/4, 1/4].
  • the obtained historical volume ratio group corresponding to station b is [4/19, 4/19, 6/19, 5/19].
  • the obtained historical volume ratio group corresponding to site c is [2/25, 8/25, 8/25, 7/25].
  • the obtained historical volume ratio group corresponding to station d is [8/19, 4/19, 3/19, 4/19].
  • Step 203 based on the set of historical cargo volume proportion groups and each of the stations, determine whether the historical cargo volume proportion of the site is stable within a preset historical period.
  • the execution subject may determine whether the historical cargo volume ratio of the above-mentioned site is stable within the preset historical period based on the above-mentioned historical volume proportion group set and each of the above-mentioned sites.
  • the above-mentioned executive body can determine the difference between the largest historical cargo volume ratio and the minimum historical cargo volume ratio included in each historical cargo volume ratio group in the above-mentioned historical cargo volume ratio group set as the cargo volume ratio Very poor, get the set of very poor proportions of goods volume.
  • the volume proportion is extremely poor 1/10.
  • the extreme difference in volume ratio is 2/19.
  • the extreme difference in volume proportion is 6/25.
  • the volume proportion range is 5/19.
  • the obtained volume ratio range set is [1/10, 2/19, 6/25, 5/19].
  • the sum of the historical cargo volumes included in the cargo volume information in the above cargo volume information set may be determined as the sum of the historical cargo volumes.
  • the stations corresponding to the respective ranges of the cargo volume proportions in the above-mentioned volume proportion range set that are less than or equal to the preset ranges may be determined as the candidate site set.
  • the preset extreme difference may be 0.25.
  • the ranges of the proportion of goods that are less than or equal to the preset range of 0.25 are 1/10, 2/19 and 6/25.
  • the stations corresponding to the extremely poor proportion of cargo volume of 1/10, 2/19 and 6/25 are site a, site b and site c respectively.
  • the set of candidate sites is [site a, site b, site c].
  • the sum of the historical cargo volumes corresponding to the candidate sites in the candidate site set included in the cargo volume information set may be determined as the site historical cargo volume sum.
  • the respective historical cargo volumes corresponding to the site a to be selected are 60, 40, 50 and 50.
  • the respective historical volumes corresponding to the candidate site b are 40, 40, 60 and 50.
  • the respective historical volumes corresponding to the candidate site c are 20, 80, 80 and 70.
  • the above-mentioned set of candidate sites may be determined as a set of candidate sites.
  • the sum of historical cargo volumes of the aforementioned sites may be 640.
  • the sum of the above historical volumes may be 830.
  • the ratio of the historical cargo volume sum 640 of the above-mentioned site to the above-mentioned historical cargo volume sum 830 is 64/83 (about 0.77).
  • the aforementioned preset ratio may be 0.7.
  • the ratio 64/83 of the above-mentioned site historical volume sum 640 to the above-mentioned historical volume sum 830 is greater than the above-mentioned preset ratio 0.7, and the above-mentioned executive body can determine the above-mentioned candidate site set [site a, site b, site c] as A collection of alternative sites.
  • the above-mentioned site may be site a, and the above-mentioned execution subject may determine the history of the above-mentioned site a within the above-mentioned preset historical period in response to determining that the above-mentioned site a exists in the above-mentioned candidate site set [site a, site b, site c] The volume ratio is stable.
  • the stability of the historical cargo volume ratio of the site can be determined according to the historical volume ratios of each site at each time granularity within the preset historical period.
  • the above-mentioned executive body may determine the above-mentioned station’s price in the above-mentioned preset historical period based on the above-mentioned set of historical cargo volume proportion groups and each of the above-mentioned stations through the following steps: Is the proportion of historical volume stable?
  • the first step based on each historical volume proportion group in the above historical volume proportion group set, determine the historical volume proportion range corresponding to the above historical volume proportion group, and obtain the historical volume proportion range gather.
  • the above-mentioned extreme difference of historical cargo volume proportion may be the difference between the largest historical cargo volume proportion and the smallest historical cargo volume proportion in the above-mentioned historical cargo volume proportion group.
  • the sum of the various historical volumes included in the above historical volume collection is determined as the total historical volume within the preset historical period.
  • the third step is to determine the sites corresponding to the ranges of the historical cargo volume proportions less than or equal to the preset range in the above-mentioned historical volume proportion range set as the candidate site set.
  • the above-mentioned preset range may be a preset range.
  • no limitation is set for the specific setting of the preset range.
  • the above-mentioned executive body can determine the station corresponding to each historical cargo volume ratio range less than or equal to the preset range in the above-mentioned historical volume ratio range set as the candidate site, and obtain the candidate site set .
  • the sum of the historical cargo volumes included in the historical cargo volume set and corresponding to the candidate site set is determined as the site historical cargo volume sum.
  • the execution subject can determine the sum of the historical cargo volumes included in the historical cargo volume set corresponding to each candidate site in the candidate site set as the single-site historical cargo volume sum, and obtain the single-site Historical volumes and collections. Then, the sum of the single-site historical cargo volume sums included in the single-site historical cargo volume sum set may be determined as the site historical cargo volume sum.
  • each station corresponding to the sum of historical cargo volumes of the above-mentioned stations is determined as a set of candidate stations.
  • the aforementioned preset ratio may be a preset ratio less than or equal to 1.
  • the specific setting of the preset ratio is not limited.
  • the sum of the historical cargo volumes of each site corresponding to the historical cargo volume sum of the above-mentioned sites is the historical cargo volume sum of the above-mentioned sites.
  • Step 6 In response to the fact that the set of candidate sites includes the above-mentioned site, and the range of historical cargo volume corresponding to the above-mentioned site in the above-mentioned cargo volume information set is less than or equal to the preset cargo volume range, determine The proportion of historical volume of the above sites is stable.
  • the above-mentioned preset extreme difference of cargo volume may be a preset extreme difference of cargo volume.
  • no limitation is set for the specific setting of the extreme difference in the preset volume.
  • the total proportion of historical cargo volume of each site whose historical volume ratio range is less than the preset range is greater than or equal to the preset ratio, and the range of each historical volume of the current site is less than or equal to the preset volume When it is extremely poor, it is determined that the proportion of historical cargo volume at the current site is stable.
  • Step 204 in response to determining that the historical cargo volume ratio of the target site in each site is stable, generate the target cargo volume percentage according to the historical cargo volume set and each historical cargo volume corresponding to the target site in the historical cargo volume set.
  • the execution subject in response to determining that the proportion of the historical cargo volume of the target site in each of the aforementioned sites is stable, the execution subject may generate Target volume ratio.
  • the above-mentioned historical cargo volume collection may be a collection composed of historical cargo volumes included in the above-mentioned cargo volume information collection.
  • the above-mentioned target site may be any one of the above-mentioned various sites.
  • the above-mentioned executive body can select the historical cargo volume of the above-mentioned target site at each time granularity from the above-mentioned historical cargo volume collection as the target historical cargo volume , to obtain the target historical volume collection.
  • the above target site may be site a.
  • the collection of historical volume can be:
  • the historical cargo volumes of the above-mentioned target site a in the above-mentioned historical volume collection at each time granularity are 60, 40, 50, and 50.
  • the obtained target historical volume set is [60, 40, 50, 50].
  • the sum of the target historical cargo volumes included in the target historical cargo volume set may be determined as the sum of the target historical cargo volumes.
  • the ratio of the above-mentioned target historical cargo volume sum to the above-mentioned historical cargo volume sum corresponding to the above-mentioned historical cargo volume set may be determined as the target cargo volume ratio.
  • the sum of the above-mentioned target historical cargo volumes may be 200.
  • the sum of the above historical volumes may be 830.
  • the determined target volume ratio is 20/83.
  • Step 205 according to the proportion of the target cargo volume and the predicted total cargo volume of the corresponding target sorting center, the site arrival volume corresponding to the target site is generated.
  • the execution subject can generate the site arrival volume corresponding to the target site according to the proportion of the target volume and the predicted total volume corresponding to the target sorting center.
  • the above-mentioned predicted total volume may be the total volume of the above-mentioned target sorting center predicted in advance.
  • the above-mentioned executive body may determine the product of the above-mentioned target cargo volume ratio and the above-mentioned predicted total cargo volume as the site arrival volume corresponding to the above-mentioned target site. In this way, according to the previously predicted total cargo volume of the sorting center and the predicted cargo volume ratio of the site in the sorting center, the site arrival volume from the sorting center to the site can be predicted.
  • the above-mentioned predicted total cargo volume may be 996.
  • the above-mentioned target volume ratio can be 20/83.
  • the above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the site arrival volume prediction method of some embodiments of the present disclosure, the stability of the volume proportion of each site corresponding to the sorting center can be determined automatically and quickly, and the predicted The accuracy of site arrivals has been improved.
  • the reasons for the inability to automatically and quickly determine the stability of the volume ratio of each site corresponding to the sorting center and the low accuracy of the predicted site arrival volume are: the final sorting is determined from the dimension of the sorting center Whether the volume ratio of each station corresponding to the center is stable, does not consider the fluctuation of the volume ratio of each station in the time dimension, and requires the use of expert experience and knowledge to determine whether the proportion of cargo volume is stable, the analysis speed is slow, and the analysis The results are highly subjective, resulting in low accuracy of predicted site arrivals.
  • the method for predicting the quantity of goods arriving at a site firstly, a set of quantity information of a target sorting center within a preset historical period is obtained.
  • the cargo volume information in the above cargo volume information set includes each historical volume of cargo sorted by the above target sorting center to each corresponding station. Therefore, the acquired cargo volume information set within the preset historical period can be used as a real historical data source for determining the stability of the cargo volume ratio of each site corresponding to the target sorting center.
  • the historical cargo volume ratio of each of the above-mentioned sites within the preset historical period is generated as the historical cargo volume percentage. Compare groups to get the set of historical volume proportion groups. Thus, from the dimension of the site, the proportion of the historical volume of each site at each time granularity within the preset historical period can be determined. Afterwards, based on the above-mentioned set of historical volume proportion groups and each of the above-mentioned sites, it is determined whether the historical volume proportion of the above-mentioned sites within the above-mentioned preset historical period is stable.
  • the stability of the historical cargo volume ratio of the site can be determined according to the historical volume ratios of each site at each time granularity within the preset historical period.
  • the target cargo volume ratio is generated according to the historical cargo volume set and each historical cargo volume corresponding to the above target site in the historical cargo volume set.
  • the above-mentioned historical cargo volume collection is a collection of historical cargo volumes included in the above-mentioned cargo volume information set. Therefore, for sites with a stable historical cargo volume ratio, it is possible to comprehensively predict their cargo volume ratio in the sorting center.
  • the site arrival volume corresponding to the above-mentioned target site is generated.
  • the site arrival volume from the sorting center to the site can be predicted.
  • each historical volume ratio group is the historical volume ratio of each site at each time granularity within the preset historical period, it can reflect the fluctuation of the historical cargo volume ratio in the time dimension, so that the historical cargo volume of the site can be automatically determined.
  • the stability of the volume ratio As a result, the stability of the volume ratio of each site corresponding to the sorting center can be automatically and quickly determined, thereby improving the accuracy of the predicted site arrival volume.
  • FIG. 3 it shows a flow 300 of another embodiment of a method for forecasting site arrival quantity.
  • the flow 300 of the method for forecasting the quantity of arrival at the site includes the following steps:
  • Step 301 acquire the quantity information set of the target sorting center within a preset historical period.
  • Step 302 based on each of the stations, according to the historical cargo volumes of the corresponding sites included in the cargo volume information set, the historical cargo volume ratios of the stations within the preset historical period are generated as the historical cargo volume ratio group, and the obtained A collection of historical volume proportion groups.
  • Step 303 based on the set of historical cargo volume proportion groups and each of the stations, determine whether the historical cargo volume proportion of the site is stable within a preset historical period.
  • Step 304 in response to determining that the historical cargo volume ratio of the target site in each site is stable, generate the target cargo volume percentage according to the historical cargo volume set and each historical cargo volume corresponding to the target site in the historical cargo volume set.
  • Step 305 according to the proportion of the target cargo volume and the predicted total cargo volume of the corresponding target sorting center, the site arrival volume corresponding to the target site is generated.
  • steps 301-305 for the specific implementation of steps 301-305 and the technical effects brought about by them, reference may be made to steps 201-205 in those embodiments corresponding to FIG. 2 , which will not be repeated here.
  • Step 306 according to the predicted total cargo volume of each sorting center corresponding to the target site and the target cargo volume ratio of the target site corresponding to each sorting center, generate the total amount of site arrivals corresponding to the target site.
  • the execution body of the method for predicting the arrival quantity at a site can be based on the predicted total cargo volume of each sorting center corresponding to the above-mentioned target site and the above-mentioned target site corresponding to each of the above-mentioned
  • the proportion of the target cargo volume of the sorting center to generate the total amount of site arrivals corresponding to the above target sites is stable.
  • Each of the above-mentioned sorting centers may be a final sorting center for directly delivering goods to the above-mentioned target site.
  • the executive body may determine the product of the predicted total cargo volume corresponding to the above sorting center and the proportion of the target cargo volume as the site arrival volume. Then, the sum of the obtained site arrival quantities can be determined as the total site arrival quantity.
  • the flow 300 of the method for predicting the quantity of goods arriving at a site in some embodiments corresponding to FIG. 3 reflects the principle of expanding the total quantity of goods arriving at a site step. Therefore, the solutions described in these embodiments can predict the station from each sorting center to the site according to the previously predicted total cargo volume of each sorting center and the predicted site's cargo volume ratio in each sorting center The total amount of arrivals. Improved accuracy of predicted total site arrivals.
  • FIG. 4 it shows a flow 400 of some other embodiments of the site arrival quantity prediction method.
  • the process 400 of the method for forecasting the quantity of arrival at the site includes the following steps:
  • step 401 the collection of cargo volume information of the target sorting center within a preset historical period is acquired.
  • the execution subject of the method for predicting the quantity of goods arriving at a site may acquire the quantity information set of the target sorting center within a preset historical period.
  • the cargo volume information in the above cargo volume information set may also include the historical total cargo volume of each site.
  • the above-mentioned total volume of historical goods may be the total volume of goods corresponding to the historical volume of goods at the site, and may include but not limited to at least one of the following: total volume of historical goods and total weight of historical goods.
  • the total volume of historical goods may be the total volume of goods corresponding to the historical volume of goods at the site.
  • the historical total weight of goods may be the total weight of goods corresponding to the historical volume of goods at the site.
  • Step 402 based on each of the stations, according to the historical cargo volume of the corresponding site included in the cargo volume information set, generate the proportion of each historical cargo volume of the site in the preset historical period as the historical cargo volume proportion group, and obtain A collection of historical volume proportion groups.
  • Step 403 based on the set of historical cargo volume proportion groups and each of the stations, determine whether the historical cargo volume proportion of the site is stable within a preset historical period.
  • Step 404 in response to determining that the historical cargo volume ratio of the target site in each site is stable, generate the target cargo volume percentage according to the historical cargo volume set and each historical cargo volume corresponding to the target site in the historical cargo volume set.
  • Step 405 according to the proportion of the target cargo volume and the predicted total cargo volume of the corresponding target sorting center, the site arrival volume corresponding to the target site is generated.
  • steps 402-405 for the specific implementation of steps 402-405 and the technical effects brought about by them, reference may be made to steps 202-205 in those embodiments corresponding to FIG. 2 , and details are not repeated here.
  • Step 406 extracting the total historical cargo volume of the corresponding target site from each volume information included in the cargo volume information set to obtain a historical total cargo volume set.
  • the execution subject may extract the total historical cargo volume corresponding to the target site from each cargo volume information included in the cargo volume information set to obtain a historical total cargo volume set.
  • the above-mentioned executive body can sequentially extract the historical total volume of cargo corresponding to the above-mentioned target site from each cargo volume information, and obtain a set of historical total cargo volume.
  • Step 407 Determine the target total quantity of goods according to the set of historical total quantity of goods.
  • the execution subject may determine the target total quantity of goods according to the set of historical total quantity of goods.
  • the executive body may determine the average value of the total volume of each historical cargo included in the total historical cargo volume set as the target total volume of cargo.
  • the execution subject may determine the average value of the total historical cargo weights included in the total historical cargo volume set as the target total cargo weight.
  • the above target total volume of goods and the above target total weight of goods may be combined into the target total quantity of goods.
  • the combination method may be character splicing.
  • the target total quantity of goods at the target site can be predicted according to the historical total quantity of goods corresponding to the target site.
  • Step 408 according to the total quantity of target goods and the arrival quantity at the site, select the transport vehicle identification corresponding to the target site from the preset transport vehicle identification group.
  • the executive body may select a transport vehicle ID corresponding to the target site from a preset transport vehicle ID group according to the total target cargo volume and the site arrival volume.
  • the above-mentioned transport vehicle identification group may be a set of preset transport vehicle identifications.
  • the transport vehicle ID can uniquely represent the transport vehicle.
  • the executive body may select the transport vehicle identification corresponding to the above-mentioned total target cargo volume and the above-mentioned site arrival volume from the transport vehicle identification table corresponding to the above-mentioned transport vehicle identification group.
  • the above-mentioned transportation vehicle identification table may be a table containing the transportation vehicle identifications corresponding to both the total quantity of goods and the delivery quantity at the site.
  • the transport vehicle ID corresponding to a total quantity of goods and a delivery quantity at a site can be queried from the transport vehicle identification table.
  • the transport vehicle used to transport the goods at the target site can be determined according to the predicted total quantity of target goods at the target site.
  • Step 409 control the transport vehicle corresponding to the transport vehicle ID to travel to the target sorting center.
  • the execution subject may control the transport vehicle corresponding to the transport vehicle identifier to travel to the target sorting center.
  • the execution subject may send an instruction representing traveling to the target sorting center to the vehicle-mounted terminal of the transport vehicle corresponding to the transport vehicle ID, so that the transport vehicle travels to the target sorting center.
  • the determined transport vehicle can be controlled to travel to the target sorting center where the goods at the target site are stored.
  • the aforementioned execution subject may control the associated item handling equipment to transport the item corresponding to the aforementioned target site to the aforementioned transport vehicle.
  • the above-mentioned article conveying equipment may be a device for conveying articles, for example, may be a mechanical arm.
  • the items corresponding to the above target site may be items that actually arrive at the target sorting center and need to be delivered to the above target site.
  • an instruction representing transporting the item corresponding to the target site to the transport vehicle may be sent to the item handling device, so that the item handling device transports the item corresponding to the target site to the transport vehicle.
  • the transportation vehicle loaded with the items corresponding to the above-mentioned target site can be controlled to travel to the above-mentioned target site.
  • an instruction representing traveling to the target site may be sent to the vehicle-mounted terminal of the transport vehicle, so that the transport vehicle travels to the target site.
  • the item handling equipment can be used to load the item, and then the transport vehicle loaded with the item can drive to the target site, so as to realize the delivery of the item to the target site.
  • the present disclosure provides some embodiments of a device for predicting the amount of arrival at a site. These device embodiments correspond to those method embodiments shown in FIG. 2 , the The device can be specifically applied to various electronic devices.
  • an apparatus 500 for predicting site arrival volume in some embodiments includes: an acquisition unit 501 , a first generation unit 502 , a determination unit 503 , a second generation unit 504 and a third generation unit 505 .
  • the obtaining unit 501 is configured to obtain a set of cargo volume information of the target sorting center within a preset historical period, wherein the cargo volume information in the above-mentioned cargo volume information set includes the volume information sorted by the above-mentioned target sorting center to the corresponding stations.
  • the first generation unit 502 is configured to, based on each of the above-mentioned sites, according to the historical cargo volumes corresponding to the above-mentioned sites included in the above-mentioned cargo volume information set, generate the above-mentioned site within the preset historical period
  • Each historical cargo volume proportion is used as a historical cargo volume proportion group to obtain a historical cargo volume proportion group set
  • the determining unit 503 is configured to determine the above-mentioned Whether the historical cargo volume ratio of the above-mentioned sites is stable within the preset historical period
  • the second generation unit 504 is configured to respond to determining that the historical cargo volume ratio of the target site in each of the above-mentioned sites is stable, according to the historical cargo volume set and the above-mentioned historical cargo volume
  • Each historical cargo volume corresponding to the above-mentioned target site in the volume set generates a target volume ratio, wherein the above-mentioned historical cargo volume set is a collection of historical cargo volumes included in the above-ment
  • the site arrival quantity forecasting device 500 may further include: a site arrival total quantity generating unit (not shown in the figure), configured to calculate the total quantity of goods at each sorting center corresponding to the above-mentioned target site and the above-mentioned
  • the target site corresponds to the target volume ratio of the above-mentioned sorting centers, and generates the total amount of site arrivals corresponding to the above-mentioned target sites, wherein, the historical cargo volume ratio of the above-mentioned target sites in the above-mentioned various sorting centers within the above-mentioned preset historical period than stable.
  • the cargo volume information in the above cargo volume information set also includes the historical total cargo volume of each site.
  • the site arrival volume prediction device 500 may further include: a historical total volume extraction unit, a target total volume generation unit, a transport vehicle identification selection unit, and a first transport vehicle control unit (not shown in the figure).
  • the total historical cargo volume extraction unit is configured to extract the historical total cargo volume corresponding to the above-mentioned target site from each cargo volume information included in the above cargo volume information set, to obtain a historical total cargo volume set.
  • the target total quantity of goods generating unit is configured to determine the target total quantity of goods according to the above-mentioned set of historical total quantity of goods.
  • the transport vehicle identification selection unit is configured to select the transport vehicle identification corresponding to the above-mentioned target site from the preset transport vehicle identification group according to the above-mentioned total quantity of target goods and the above-mentioned site arrival quantity.
  • the first transport vehicle control unit is configured to control the transport vehicle corresponding to the transport vehicle identifier to drive to the target sorting center.
  • the station arrival volume prediction device 500 may further include: a control unit for the object handling equipment and a second transport vehicle control unit (not shown in the figure).
  • the item handling equipment control unit is configured to control the associated item handling equipment to transport the item corresponding to the above-mentioned target station to the above-mentioned transportation vehicle.
  • the second transport vehicle control unit is configured to control the transport vehicle loaded with the items corresponding to the above target site to travel to the above target site.
  • the determining unit 503 may include: a unit for determining the proportion of historical cargo volume extreme difference, a unit for determining the total historical cargo volume, a unit for determining the set of sites to be selected, a unit for determining the sum of historical cargo volumes at sites, and a unit for determining the set of alternative sites (not shown in the figure).
  • the historical cargo volume percentage range determining unit is configured to determine the historical cargo volume percentage range corresponding to the historical cargo volume percentage group based on each historical cargo volume percentage group in the above-mentioned historical cargo volume percentage group set. Poor, get the collection of historical volume ratio extreme difference.
  • the total historical cargo volume determining unit is configured to determine the sum of the historical cargo volumes included in the historical cargo volume set as the total historical cargo volume within the preset historical period.
  • the candidate site set determination unit is configured to determine each site corresponding to each historical cargo volume proportion range less than or equal to the preset range in the above-mentioned historical cargo volume range range set as the candidate site set.
  • the site historical cargo volume sum determining unit is configured to determine the sum of the historical cargo volumes included in the historical cargo volume set and corresponding to the candidate site set as the site historical cargo volume sum.
  • the candidate site set determining unit is configured to determine each site corresponding to the above-mentioned site historical cargo volume sum as the candidate site set in response to determining that the ratio of the above-mentioned site historical cargo volume sum to the above-mentioned total historical cargo volume is greater than or equal to a preset ratio.
  • the determining unit 503 may further include: a historical volume ratio stability determining unit (not shown in the figure), configured to respond to the above-mentioned candidate site set including the above-mentioned site, and the above-mentioned volume information set corresponding to The range of historical cargo volume at each of the above stations is less than or equal to the preset cargo volume range, and it is determined that the proportion of historical cargo volume at the above site within the preset historical period is stable.
  • a historical volume ratio stability determining unit (not shown in the figure), configured to respond to the above-mentioned candidate site set including the above-mentioned site, and the above-mentioned volume information set corresponding to The range of historical cargo volume at each of the above stations is less than or equal to the preset cargo volume range, and it is determined that the proportion of historical cargo volume at the above site within the preset historical period is stable.
  • the site arrival volume prediction device 500 may also include: a historical cargo volume sequence determination unit, a historical cargo volume sequence set determination unit to be deleted, and a historical cargo volume elimination unit (not shown in the figure) .
  • the historical cargo volume sequence determining unit is configured to determine the historical cargo volume sequence of each of the above-mentioned stations in the above-mentioned preset historical period according to the various cargo-volume information included in the above-mentioned cargo-volume information set, and obtain the historical cargo volume collection of sequences.
  • the determination unit for the set of historical volume sequences to be deleted is configured to respond to at least one historical volume sequence in the above-mentioned set of historical volume sequences that includes historical volumes that are all less than a preset volume threshold, and includes historical volumes that are all less than a preset volume threshold.
  • Each historical volume series of the above-mentioned preset volume thresholds is determined as a set of historical volume series to be eliminated.
  • the historical volume eliminating unit is configured to delete each historical volume included in the above-mentioned historical volume sequence set to be deleted from the above-mentioned volume information set.
  • the site arrival volume prediction device 500 may further include: a unit for determining a set of historical volume sequences to be smoothed and a historical volume smoothing unit (not shown in the figure).
  • the unit for determining the set of historical cargo volume sequences to be smoothed is configured to respond to at least one historical cargo volume sequence in which the included historical cargo volume satisfies a preset outlier condition in the above-mentioned historical cargo volume sequence set, and the included historical cargo volume satisfies
  • Each historical volume series with the above-mentioned preset outlier conditions is determined as a set of historical volume series to be smoothed.
  • the historical volume smoothing unit is configured to, for each historical volume that satisfies the preset outlier condition included in each historical volume sequence to be smoothed in the set of historical volume sequences to be smoothed, according to the historical volume sequence to be smoothed , generate the smoothed historical volume of the above historical volume, and replace the above historical volume with the above smoothed historical volume.
  • the units recorded in the device 500 correspond to the steps in the method described with reference to FIG. 2 . Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 500 and the units contained therein, and will not be repeated here.
  • FIG. 6 shows a structural schematic diagram of an electronic device (for example, the computing device 101 in FIG. 1 ) 600 suitable for implementing some embodiments of the present disclosure.
  • the electronic device shown in FIG. No limitations should be imposed on the function and scope of use of the embodiments of the present disclosure.
  • an electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may be randomly accessed according to a program stored in a read-only memory (ROM) 602 or loaded from a storage device 608.
  • a processing device such as a central processing unit, a graphics processing unit, etc.
  • RAM memory
  • various programs and data necessary for the operation of the electronic device 600 are also stored.
  • the processing device 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604 .
  • the following devices can be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speaker, vibration an output device 607 such as a computer; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609.
  • the communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While FIG. 6 shows electronic device 600 having various means, it should be understood that implementing or having all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided. Each block shown in FIG. 6 may represent one device, or may represent multiple devices as required.
  • the processes described above with reference to the flowcharts may be implemented as computer software programs.
  • some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts.
  • the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602.
  • the processing device 601 When the computer program is executed by the processing device 601, the above functions defined in the methods of some embodiments of the present disclosure are performed.
  • the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to, electrical connections having at least one lead, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable Read memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and the server can communicate using any currently known or future network protocols such as HTTP (HyperText Transfer Protocol, Hypertext Transfer Protocol), and can communicate with digital data in any form or medium
  • HTTP HyperText Transfer Protocol
  • the communication eg, communication network
  • Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains a set of cargo volume information of the target sorting center within a preset historical period, wherein, The volume information in the above volume information set includes the historical volumes sorted by the above target sorting center to the corresponding stations; based on each of the above sites, according to the corresponding above site included in the above volume information set Each historical cargo volume of the above-mentioned preset historical period is generated as the historical cargo volume proportion group, and the historical cargo volume proportion group set is obtained; based on the above-mentioned historical cargo volume proportion group set and the above For each of the stations, determine whether the historical cargo volume ratio of the above-mentioned site is stable within the preset historical period; in response to determining that the historical
  • Computer program code for carrying out operations of some embodiments of the present disclosure may be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, Also included are conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, using an Internet service provider to connected via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service provider for example, using an Internet service provider to connected via the Internet.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code that contains at least one programmable logic function for implementing the specified logical function.
  • Execute instructions may also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the units described in some embodiments of the present disclosure may be realized by software or by hardware.
  • the described units may also be set in a processor, for example, it may be described as: a processor includes an acquiring unit, a first generating unit, a determining unit, a second generating unit, and a third generating unit.
  • a processor includes an acquiring unit, a first generating unit, a determining unit, a second generating unit, and a third generating unit.
  • the names of these units do not constitute a limitation of the unit itself under certain circumstances, for example, the acquisition unit can also be described as "a unit that acquires the volume information collection of the target sorting center within a preset historical period".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), System on Chips (SOCs), Complex Programmable Logical device (CPLD) and so on.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs System on Chips
  • CPLD Complex Programmable Logical device

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

站点到货量预测方法、装置、电子设备和计算机可读介质。该方法包括：获取预设历史时段内目标分拣中心的货量信息集合；基于每个站点，根据货量信息集合包括的对应站点的各个历史货量，生成各个历史货量占比作为历史货量占比组，得到历史货量占比组集合；基于历史货量占比组集合和每个站点，确定站点的历史货量占比是否稳定；响应于确定目标站点的历史货量占比稳定，根据历史货量集合和对应目标站点的各个历史货量，生成目标货量占比；根据目标货量占比和目标分拣中心的预测总货量，生成站点到货量。

Description

站点到货量预测方法、装置、电子设备和计算机可读介质
相关申请的交叉引用
本申请要求于申请日为2021年12月24日提交的，申请号为202111593778.4、发明名称为“站点到货量预测方法、装置、电子设备和计算机可读介质”的中国专利申请的优先权，其全部内容作为整体并入本申请中。
技术领域
本公开的实施例涉及计算机技术领域，具体涉及站点到货量预测方法、装置、电子设备和计算机可读介质。
背景技术
在进行物流配送时，通常采用首分拣中心-末分拣中心-站点的物流配送网络模式进行配送。对末分拣中心至站点的货物进行配送前，可以根据预测的末分拣中心的总货量预测到达每一站点的站点到货量。因此，需要首先确定站点在末分拣中心的货量占比稳定，才能根据稳定的货量占比预测站点到货量。目前，在预测站点到货量时，通常采用的方式为：基于方差分析或看图分析，从分拣中心维度确定末分拣中心对应的各个站点的货量占比是否稳定，进而预测站点到货量。
发明内容
本公开的内容部分用于以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。本公开的内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
本公开的一些实施例提出了站点到货量预测方法、装置、电子设备和计算机可读介质，来解决以上背景技术部分提到的技术问题。
第一方面，本公开的一些实施例提供了一种站点到货量预测方法，该方法包括：获取预设历史时段内目标分拣中心的货量信息集合，其中，上述货量信息集合中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历史货量；基于上述各个站点中的每个站点，根据上述货量信息集合包括的对应上述站点的各个历史货量，生成上述预设历史时段内上述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合；基于上述历史货量占比组集合和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历史货量占比是否稳定；响应于确定上述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和上述历史货量集合中对应上述目标站点的各个历史货量，生成目标货量占比，其中，上述历史货量集合为上述货量信息集合所包括的历史货量的集合；根据上述目标货量占比和对应上述目标分拣中心的预测总货量，生成对应上述目标站点的站点到货量。
第二方面，本公开的一些实施例提供了一种站点到货量预测装置，装置包括：获取单元，被配置成获取预设历史时段内目标分拣中心的货量信息集合，其中，上述货量信息集合中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历史货量；第一生成单元，被配置成基于上述各个站点中的每个站点，根据上述货量信息集合包括的对应上述站点的各个历史货量，生成上述预设历史时段内上述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合；确定单元，被配置成基于上述历史货量占比组集合和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历史货量占比是否稳定；第二生成单元，被配置成响应于确定上述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和上述历史货量集合中对应上述目标站点的各个历史货量，生成目标货量占比，其中，上述历史货量集合为上述货量信息集合所包括的历史货量的集合；第三生成单元，被配置成根据上述目标货量占比和对应上述目标分拣中心的预测总货量，生成对应上述目标站点的站点到货量。
第三方面，本公开的一些实施例提供了一种电子设备，包括：至 少一个处理器；存储装置，其上存储有至少一个程序，当至少一个程序被至少一个处理器执行，使得至少一个处理器实现上述第一方面任一实现方式所描述的方法。
第四方面，本公开的一些实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，程序被处理器执行时实现上述第一方面任一实现方式所描述的方法。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，元件和元素不一定按照比例绘制。
图1是根据本公开的一些实施例的站点到货量预测方法的一个应用场景的示意图；
图2是根据本公开的站点到货量预测方法的一些实施例的流程图；
图3是根据本公开的站点到货量预测方法的另一些实施例的流程图；
图4是根据本公开的站点到货量预测方法的又一些实施例的流程图；
图5是根据本公开的站点到货量预测装置的一些实施例的结构示意图；
图6是适于用来实现本公开的一些实施例的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本 公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“至少一个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
相关的站点到货量预测方法，例如，基于方差分析或看图分析，从分拣中心维度确定末分拣中心对应的各个站点的货量占比是否稳定，进而预测站点到货量等经常会存在如下技术问题：从分拣中心维度确定末分拣中心对应的各个站点的货量占比是否稳定，未考虑每一站点的货量占比在时间维度的波动，需要利用专家经验知识才能确定货量占比是否稳定，分析速度较慢，且分析结果的主观性较强，造成预测的站点到货量的准确性较低。
为了解决以上所阐述的问题，本公开的一些实施例提出了站点到货量预测方法及装置，可以自动化且快速地确定分拣中心对应的各个站点的货量占比稳定性，预测的站点到货量的准确性有所提高。
下面将参考附图并结合实施例来详细说明本公开。
图1是根据本公开一些实施例的站点到货量预测方法的一个应用场景的示意图。
在图1的应用场景中，首先，计算设备101可以获取预设历史时段内目标分拣中心的货量信息集合102。其中，上述货量信息集合102中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历 史货量。然后，计算设备101可以基于上述各个站点中的每个站点，根据上述货量信息集合102包括的对应上述站点的各个历史货量，生成上述预设历史时段内上述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合103。之后，计算设备101可以基于上述历史货量占比组集合103和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历史货量占比是否稳定。其次，计算设备101可以响应于确定上述各个站点中目标站点的历史货量占比稳定，根据历史货量集合104和上述历史货量集合104中对应上述目标站点的各个历史货量，生成目标货量占比105。其中，上述历史货量集合104为上述货量信息集合102所包括的历史货量的集合。最后，计算设备101可以根据上述目标货量占比105和对应上述目标分拣中心的预测总货量106，生成对应上述目标站点的站点到货量107。
需要说明的是，上述计算设备101可以是硬件，也可以是软件。当计算设备为硬件时，可以实现成多个服务器或终端设备组成的分布式集群，也可以实现成单个服务器或单个终端设备。当计算设备体现为软件时，可以安装在上述所列举的硬件设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的计算设备的数目仅仅是示意性的。根据实现需要，可以具有任意数目的计算设备。
继续参考图2，示出了根据本公开的站点到货量预测方法的一些实施例的流程200。该站点到货量预测方法，包括以下步骤：
步骤201，获取预设历史时段内目标分拣中心的货量信息集合。
在一些实施例中，站点到货量预测方法的执行主体(例如图1所示的计算设备101)可以通过有线连接方式或者无线连接方式从终端获取预设历史时段内目标分拣中心的货量信息集合。其中，上述预设历史时段可以为在先设定的任意历史时段。这里对于预设历史时段的具体设定，不作限定。上述目标分拣中心可以为任意一个末分拣中心。上述末分拣中心可以为用于直接向各个站点配送货物的分拣仓。上述 目标分拣中心对应的站点的数量可以大于等于预设数量。例如，预设数量可以为3。这里，对于上述预设数量的具体设定，不作限定。
上述站点可以直接供用户提取货物。上述货量信息集合中的各个货量信息对应上述预设历史时段内的各个时间粒度。例如，上述预设历史时段可以为“2021/10/11-2021/10/24”。则上述货量信息集合中的第一个货量信息对应时间粒度2021/10/11。上述货量信息集合中的第二个货量信息对应时间粒度2021/10/12。上述货量信息可以包括上述目标分拣中心分拣至对应的各个站点的各个历史货量。可以理解为，上述货量信息可以包括一个时间粒度下各个站点的历史货量。上述历史货量可以为到达上述目标分拣中心的一站点的历史包裹数量。
作为示例，上述预设历史时段可以为“2021/10/11-2021/10/14”。上述货量信息集合可以为：
[站点a：60，站点b：40，站点c：20，站点d：80]；
[站点a：40，站点b：40，站点c：80，站点d：40]；
[站点a：50，站点b：60，站点c：80，站点d：30]；
[站点a：50，站点b：50，站点c：70，站点d：40]。
其中，第一个货量信息[站点a：60，站点b：40，站点c：20，站点d：80]对应的时间粒度为2021/10/11。第二个货量信息[站点a：40，站点b：40，站点c：80，站点d：40]对应的时间粒度为2021/10/12。第三个货量信息[站点a：50，站点b：60，站点c：80，站点d：30]对应的时间粒度为2021/10/13。第四个货量信息[站点a：50，站点b：50，站点c：70，站点d：40]对应的时间粒度为2021/10/14。
需要指出的是，上述无线连接方式可以包括但不限于3G/4G连接、WiFi连接、蓝牙连接、WiMAX连接、Zigbee连接、UWB(ultra wideband)连接、以及其他现在已知或将来开发的无线连接方式。由此，获取的预设历史时段内的货量信息集合可以作为确定目标分拣中心对应的各个站点的货量占比稳定性的真实历史数据源。
可选地，首先，上述执行主体可以根据上述货量信息集合包括的各个货量信息，确定上述各个站点中的每个站点在上述预设历史时段内的历史货量序列，得到历史货量序列集合。实践中，上述执行主体 可以从上述各个货量信息中提取上述站点在各个时间粒度的历史货量，得到历史货量序列。然后，可以响应于上述历史货量序列集合中存在至少一个包括的历史货量均小于预设货量阈值的历史货量序列，将包括的历史货量均小于上述预设货量阈值的各个历史货量序列确定为待剔除历史货量序列集合。其中，上述预设货量阈值可以为预先设定的最小货量阈值。这里，对于上述货量阈值的具体设定，不作限定。最后，可以从上述货量信息集合中剔除上述待剔除历史货量序列集合包括的各个历史货量。由此，可以预先剔除每个时间粒度的历史货量均小于预设货量阈值的站点的历史货量。
可选地，在上述根据上述货量信息集合包括的各个货量信息，确定上述各个站点中的每个站点在上述预设历史时段内的历史货量序列，得到历史货量序列集合之后，首先，上述执行主体可以响应于上述历史货量序列集合中存在至少一个包括的历史货量满足预设离群条件的历史货量序列，将包括的历史货量满足上述预设离群条件的各个历史货量序列确定为待平滑历史货量序列集合。
其中，上述预设离群条件可以包括但不限于以下至少一项：历史货量序列中存在大于上述历史货量序列包括的各个历史货量的均值的N倍的历史货量，历史货量序列中存在小于上述历史货量序列包括的各个历史货量的均值的M倍的历史货量，历史货量序列中存在大于上四分位数与四分位间距X倍的和的历史货量，历史货量序列中存在小于下四分位数与四分位间距Y倍的差的历史货量。上述历史货量序列中四分之一的历史货量大于上述上四分位数。上述历史货量序列中四分之一的历史货量小于上述下四分位数。上述四分位间距为上述上四分位数与上述下四分位数的差。这里，N为大于1的数值。例如，N可以为10。M为小于1的数值。例如，M可以为0.1。X和Y为大于1的数值。例如，X、Y可以均为1.5。对于N、M、X和Y的具体设定，不作限定。然后，对于上述待平滑历史货量序列集合中每个待平滑历史货量序列包括的满足上述预设离群条件的每个历史货量，可以根据上述待平滑历史货量序列，生成上述历史货量的平滑历史货量，以及将上述历史货量替换为上述平滑历史货量。
实践中，首先，上述执行主体可以将上述历史货量从上述待平滑历史货量序列中剔除。然后，可以将剔除上述历史货量后的待平滑历史货量序列包括的待平滑历史货量的均值确定为平滑历史货量。之后，可以，将上述平滑历史货量添加至上述待平滑历史货量序列中上述历史货量对应的位置。由此，可以对极大或极小的历史货量进行平滑处理。
步骤202，基于各个站点中的每个站点，根据货量信息集合包括的对应站点的各个历史货量，生成预设历史时段内站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合。
在一些实施例中，上述执行主体可以基于上述各个站点中的每个站点，根据上述货量信息集合包括的对应上述站点的各个历史货量，生成上述预设历史时段内上述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合。实践中，对于上述各个站点中的每个站点，首先，上述执行主体可以将上述货量信息集合包括的对应上述站点的各个历史货量的和确定为站点总历史货量。然后，可以将上述货量信息集合包括的对应上述站点的每个历史货量与上述站点总历史货量的比值确定为历史货量占比，得到历史货量占比组。进而可以得到历史货量占比组集合。由此，可以从站点维度，确定每一站点在预设历史时段内各个时间粒度的历史货量占比。
作为示例，对于步骤201中示例的货量信息集合中的站点a，上述货量信息集合包括的对应上述站点a的各个历史货量的和为200(60+40+50+50＝200)。对于上述货量信息集合包括的对应上述站点a的第一个历史货量60，上述执行主体可以将历史货量60与上述站点总历史货量200的比值确定为历史货量占比3/10。对于上述货量信息集合包括的对应上述站点a的第二个历史货量40，上述执行主体可以将历史货量40与上述站点总历史货量200的比值确定为历史货量占比2/10。对于上述货量信息集合包括的对应上述站点a的第三个或第四个历史货量50，上述执行主体可以将历史货量50与上述站点总历史货量200的比值确定为历史货量占比1/4。由此，得到的对应站点a的历史货量占比组为[3/10，2/10，1/4，1/4]。得到的对应站点b的历 史货量占比组为[4/19，4/19，6/19，5/19]。得到的对应站点c的历史货量占比组为[2/25，8/25，8/25，7/25]。得到的对应站点d的历史货量占比组为[8/19，4/19，3/19，4/19]。
步骤203，基于历史货量占比组集合和各个站点中的每个站点，确定预设历史时段内站点的历史货量占比是否稳定。
在一些实施例中，上述执行主体可以基于上述历史货量占比组集合和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历史货量占比是否稳定。实践中，首先，上述执行主体可以将上述历史货量占比组集合中每个历史货量占比组包括的最大历史货量占比与最小历史货量占比的差确定为货量占比极差，得到货量占比极差集合。作为示例，对于步骤202示例的历史货量占比组集合中对应站点a的历史货量占比组[3/10，2/10，1/4，1/4]，货量占比极差为1/10。对于对应站点b的历史货量占比组[4/19，4/19，6/19，5/19]，货量占比极差为2/19。对于对应站点c的历史货量占比组[2/25，8/25，8/25，7/25]，货量占比极差为6/25。对于对应站点d的历史货量占比组[8/19，4/19，3/19，4/19]，货量占比极差为5/19。得到的货量占比极差集合为[1/10，2/19，6/25，5/19]。
然后，可以将上述货量信息集合中各个货量信息所包括的各个历史货量的和确定为历史货量总和。作为示例，步骤201示例的货量信息集合中第一个货量信息所包括的各个历史货量的和为200(60+40+20+80＝200)。第二个货量信息所包括的各个历史货量的和为200(40+40+80+40＝200)。第三个货量信息所包括的各个历史货量的和为220(50+60+80+30＝220)。第四个货量信息所包括的各个历史货量的和为210(50+50+70+40＝210)。则步骤201示例的历史货量占比组集合中四个货量信息所包括的各个历史货量的和为830(200+200+220+210＝830)。
之后，可以将上述货量占比极差集合中小于等于预设极差的各个货量占比极差对应的各个站点确定为待备选站点集合。作为示例，上述预设极差可以为0.25。则货量占比极差集合[1/10，2/19，6/25，5/19]中小于等于上述预设极差0.25的货量占比极差为1/10、2/19和6/25。 货量占比极差1/10、2/19和6/25对应的站点分别为站点a、站点b和站点c。则待备选站点集合为[站点a，站点b，站点c]。
其次，可以将上述货量信息集合包括的对应上述待备选站点集合中各个待备选站点的各个历史货量的和确定为站点历史货量和。作为示例，步骤201示例的货量信息集合中对应待备选站点a的各个历史货量为60、40、50和50。对应待备选站点b的各个历史货量为40、40、60和50。对应待备选站点c的各个历史货量为20、80、80和70。由此，确定的站点历史货量和为640(60+40+50+50+40+40+60+50+20+80+80+70＝640)。
之后，可以响应于确定上述站点历史货量和与上述历史货量总和的比值大于等于预设比值，将上述待备选站点集合确定为备选站点集合。作为示例，上述站点历史货量和可以为640。上述历史货量总和可以为830。上述站点历史货量和640与上述历史货量总和830的比值为64/83(约为0.77)。上述预设比值可以为0.7。则上述站点历史货量和640与上述历史货量总和830的比值64/83大于上述预设比值0.7，上述执行主体可以将上述待备选站点集合[站点a，站点b，站点c]确定为备选站点集合。
最后，可以响应于确定上述站点存在于上述备选站点集合，确定上述预设历史时段内上述站点的历史货量占比稳定。这里，对于预设极差和预设比值的具体设定，不作限定。作为示例，上述站点可以为站点a，上述执行主体可以响应于确定上述站点a存在于上述备选站点集合[站点a，站点b，站点c]，确定上述预设历史时段内上述站点a的历史货量占比稳定。
由此，可以根据每一站点在预设历史时段内各个时间粒度的历史货量占比，确定站点历史货量占比的稳定性。
在一些实施例的一些可选的实现方式中，上述执行主体可以通过以下步骤，基于上述历史货量占比组集合和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历史货量占比是否稳定：
第一步，基于上述历史货量占比组集合中的每个历史货量占比组，确定上述历史货量占比组对应的历史货量占比极差，得到历史货量占 比极差集合。其中，上述历史货量占比极差可以为上述历史货量占比组中最大的历史货量占比和最小的历史货量占比的差。
第二步，将上述历史货量集合包括的各个历史货量的和确定为上述预设历史时段内的总历史货量。
第三步，将上述历史货量占比极差集合中小于等于预设极差的各个历史货量占比极差对应的各个站点确定为待备选站点集合。其中，上述预设极差可以为预先设定的极差。这里，对于预设极差的具体设定，不作限定。实践中，上述执行主体可以将上述历史货量占比极差集合中小于等于预设极差的每个历史货量占比极差对应的站点确定为待备选站点，得到待备选站点集合。
第四步，将上述历史货量集合包括的对应上述待备选站点集合的各个历史货量的和确定为站点历史货量和。实践中，首先，上述执行主体可以将上述历史货量集合包括的对应上述待备选站点集合中每个待备选站点的各个历史货量的和确定为单站点历史货量和，得到单站点历史货量和集合。然后，可以将上述单站点历史货量和集合所包括的单站点历史货量和的和确定为站点历史货量和。
第五步，响应于确定上述站点历史货量和与上述总历史货量的比值大于等于预设比值，将对应上述站点历史货量和的各个站点确定为备选站点集合。其中，上述预设比值可以为预先设定的小于等于1的比值。这里，对于预设比值的具体设定，不作限定。对应上述站点历史货量和的各个站点的历史货量的和为上述站点历史货量和。
第六步，响应于上述备选站点集合包括上述站点，且上述货量信息集合中对应于上述站点的各个历史货量的极差小于等于预设货量极差，确定上述预设历史时段内上述站点的历史货量占比稳定。其中，上述预设货量极差可以为预先设定的货量的极差。这里，对于预设货量极差的具体设定，不作限定。
由此，可以在历史货量占比极差小于预设极差的各个站点的历史货量总占比大于等于预设比值，且当前站点的各个历史货量的极差小于等于预设货量极差时，才确定当前站点的历史货量占比稳定。
步骤204，响应于确定各个站点中目标站点的历史货量占比稳定， 根据历史货量集合和历史货量集合中对应目标站点的各个历史货量，生成目标货量占比。
在一些实施例中，上述执行主体可以响应于确定上述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和上述历史货量集合中对应上述目标站点的各个历史货量，生成目标货量占比。其中，上述历史货量集合可以为由上述货量信息集合所包括的历史货量组成的集合。上述目标站点可以为上述各个站点中任意一个站点。实践中，响应于确定上述各个站点中目标站点的历史货量占比稳定，首先，上述执行主体可以从上述历史货量集合中选择上述目标站点在各个时间粒度的历史货量作为目标历史货量，得到目标历史货量集合。作为示例，上述目标站点可以为站点a。历史货量集合可以为：
[60(站点a)，40(站点b)，20(站点c)，80(站点d)]；
[40(站点a)，40(站点b)，80(站点c)，40(站点d)]；
[50(站点a)，60(站点b)，80(站点c)，30(站点d)]；
[50(站点a)，50(站点b)，70(站点c)，40(站点d)]。
上述历史货量集合中上述目标站点a在各个时间粒度的历史货量为60、40、50和50。得到的目标历史货量集合为[60，40，50，50]。
然后，可以将上述目标历史货量集合所包括的各个目标历史货量的和确定为目标历史货量总和。作为示例，上述目标历史货量集合[60，40，50，50]所包括的各个目标历史货量的和为200(60+40+50+50＝200)。
之后，可以将上述目标历史货量总和与上述历史货量集合对应的上述历史货量总和的比值确定为目标货量占比。作为示例，上述目标历史货量总和可以为200。上述历史货量总和可以为830。则确定的目标货量占比为20/83。
由此，针对历史货量占比稳定的站点，可以综合预测其在分拣中心的货量占比。
步骤205，根据目标货量占比和对应目标分拣中心的预测总货量，生成对应目标站点的站点到货量。
在一些实施例中，上述执行主体可以根据上述目标货量占比和对 应上述目标分拣中心的预测总货量，生成对应上述目标站点的站点到货量。其中，上述预测总货量可以为预先预测的上述目标分拣中心的总货量。这里，对于预测上述预测总货量的方式，不作限定。实践中，上述执行主体可以将上述目标货量占比与上述预测总货量的乘积确定为对应上述目标站点的站点到货量。由此，可以根据在先预测的分拣中心的预测总货量和预测的站点在该分拣中心的货量占比，预测从该分拣中心到该站点的站点到货量。
作为示例，上述预测总货量可以为996。上述目标货量占比可以为20/83。则对应目标站点a的站点到货量可以为240(996×20/83＝240)。
本公开的上述各个实施例具有如下有益效果：通过本公开的一些实施例的站点到货量预测方法，可以自动化且快速地确定分拣中心对应的各个站点的货量占比稳定性，预测的站点到货量的准确性有所提高。具体来说，造成不能自动化且快速地确定分拣中心对应的各个站点的货量占比稳定性以及预测的站点到货量的准确性较低的原因在于：从分拣中心维度确定末分拣中心对应的各个站点的货量占比是否稳定，未考虑每一站点的货量占比在时间维度的波动，需要利用专家经验知识才能确定货量占比是否稳定，分析速度较慢，且分析结果的主观性较强，造成预测的站点到货量的准确性较低。
基于此，本公开的一些实施例的站点到货量预测方法，首先，获取预设历史时段内目标分拣中心的货量信息集合。其中，上述货量信息集合中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历史货量。由此，获取的预设历史时段内的货量信息集合可以作为确定目标分拣中心对应的各个站点的货量占比稳定性的真实历史数据源。然后，基于上述各个站点中的每个站点，根据上述货量信息集合包括的对应上述站点的各个历史货量，生成上述预设历史时段内上述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合。由此，可以从站点维度，确定每一站点在预设历史时段内各个时间粒度的历史货量占比。之后，基于上述历史货量占比组集合和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历 史货量占比是否稳定。
由此，可以根据每一站点在预设历史时段内各个时间粒度的历史货量占比，确定站点历史货量占比的稳定性。其次，响应于确定上述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和上述历史货量集合中对应上述目标站点的各个历史货量，生成目标货量占比。其中，上述历史货量集合为上述货量信息集合所包括的历史货量的集合。由此，针对历史货量占比稳定的站点，可以综合预测其在分拣中心的货量占比。
最后，根据上述目标货量占比和对应上述目标分拣中心的预测总货量，生成对应上述目标站点的站点到货量。由此，可以根据在先预测的分拣中心的预测总货量和预测的站点在该分拣中心的货量占比，预测从该分拣中心到该站点的站点到货量。也因为每个历史货量占比组是每一站点在预设历史时段内各个时间粒度的历史货量占比，可以体现历史货量占比在时间维度的波动，从而可以自动确定站点历史货量占比的稳定性。由此，可以自动化且快速地确定分拣中心对应的各个站点的货量占比稳定性，进而提高了预测的站点到货量的准确性。
参考图3，其示出了站点到货量预测方法的另一些实施例的流程300。该站点到货量预测方法的流程300，包括以下步骤：
步骤301，获取预设历史时段内目标分拣中心的货量信息集合。
步骤302，基于各个站点中的每个站点，根据货量信息集合包括的对应站点的各个历史货量，生成预设历史时段内站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合。
步骤303，基于历史货量占比组集合和各个站点中的每个站点，确定预设历史时段内站点的历史货量占比是否稳定。
步骤304，响应于确定各个站点中目标站点的历史货量占比稳定，根据历史货量集合和历史货量集合中对应目标站点的各个历史货量，生成目标货量占比。
步骤305，根据目标货量占比和对应目标分拣中心的预测总货量，生成对应目标站点的站点到货量。
在一些实施例中，步骤301-305的具体实现及所带来的技术效果可以参考图2对应的那些实施例中的步骤201-205，在此不再赘述。
步骤306，根据对应目标站点的各个分拣中心的预测总货量和目标站点对应于各个分拣中心的目标货量占比，生成对应目标站点的站点到货总量。
在一些实施例中，站点到货量预测方法的执行主体(例如图1所示的计算设备101)可以根据对应上述目标站点的各个分拣中心的预测总货量和上述目标站点对应于上述各个分拣中心的目标货量占比，生成对应上述目标站点的站点到货总量。其中，上述预设历史时段内上述目标站点在上述各个分拣中心的历史货量占比稳定。上述各个分拣中心可以为用于直接向上述目标站点配送货物的末分拣中心。实践中，对于上述各个分拣中心中的每个分拣中心，上述执行主体可以将对应上述分拣中心的预测总货量和目标货量占比的乘积确定为站点到货量。然后，可以将所得到的站点到货量的和确定为站点到货总量。
从图3中可以看出，与图2对应的一些实施例的描述相比，图3对应的一些实施例中的站点到货量预测方法的流程300体现了对站点到货总量进行扩展的步骤。由此，这些实施例描述的方案可以根据在先预测的各个分拣中心的预测总货量和预测的站点在各个分拣中心的货量占比，预测从各个分拣中心到该站点的站点到货总量。提高了预测的站点到货总量的准确性。
参考图4，其示出了站点到货量预测方法的又一些实施例的流程400。该站点到货量预测方法的流程400，包括以下步骤：
步骤401，获取预设历史时段内目标分拣中心的货量信息集合。
在一些实施例中，站点到货量预测方法的执行主体(例如图1所示的计算设备101)可以获取预设历史时段内目标分拣中心的货量信息集合。其中，上述货量信息集合中的货量信息还可以包括各个站点的历史货物总体量。上述历史货物总体量可以为对应站点的历史货量的货物的总体量，可以包括但不限于以下中的至少一项：历史货物总体积，历史货物总重量。历史货物总体积可以为对应站点的历史货量 的货物的总体积。历史货物总重量可以为对应站点的历史货量的货物的总重量。
步骤402，基于各个站点中的每个站点，根据货量信息集合包括的对应站点的各个历史货量，生成预设历史时段内站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合。
步骤403，基于历史货量占比组集合和各个站点中的每个站点，确定预设历史时段内站点的历史货量占比是否稳定。
步骤404，响应于确定各个站点中目标站点的历史货量占比稳定，根据历史货量集合和历史货量集合中对应目标站点的各个历史货量，生成目标货量占比。
步骤405，根据目标货量占比和对应目标分拣中心的预测总货量，生成对应目标站点的站点到货量。
在一些实施例中，步骤402-405的具体实现及所带来的技术效果可以参考图2对应的那些实施例中的步骤202-205，在此不再赘述。
步骤406，从货量信息集合包括的各个货量信息中提取对应目标站点的历史货物总体量，得到历史货物总体量集合。
在一些实施例中，上述执行主体可以从上述货量信息集合包括的各个货量信息中提取对应上述目标站点的历史货物总体量，得到历史货物总体量集合。实践中，上述执行主体可以依次从各个货量信息中提取对应上述目标站点的历史货物总体量，得到历史货物总体量集合。
步骤407，根据历史货物总体量集合，确定目标货物总体量。
在一些实施例中，上述执行主体可以根据上述历史货物总体量集合，确定目标货物总体量。实践中，首先，上述执行主体可以将上述历史货物总体量集合包括的各个历史货物总体积的均值确定为目标货物总体积。然后，上述执行主体可以将上述历史货物总体量集合包括的各个历史货物总重量的均值确定为目标货物总重量。最后，可以将上述目标货物总体积和上述目标货物总重量组合为目标货物总体量。其中，组合方式可以为字符拼接。由此，可以根据目标站点对应的历史货物总体量集合，预测目标站点的目标货物总体量。
步骤408，根据目标货物总体量和站点到货量，从预设的运输车 辆标识组中选择对应目标站点的运输车辆标识。
在一些实施例中，上述执行主体可以根据上述目标货物总体量和上述站点到货量，从预设的运输车辆标识组中选择对应上述目标站点的运输车辆标识。其中，上述运输车辆标识组可以为预先设定的各个运输车辆标识的集合。运输车辆标识可以唯一表示运输车辆。实践中，上述执行主体可以从对应上述运输车辆标识组的运输车辆标识表中选择对应上述目标货物总体量和上述站点到货量的运输车辆标识。上述运输车辆标识表可以为包含货物总体量和站点到货量同时对应的运输车辆标识的表。即，可以从运输车辆标识表中查询到同时对应一货物总体量和一站点到货量的运输车辆标识。由此，可以根据预测的目标站点的目标货物总体量，确定用于运输目标站点的货物的运输车辆。
步骤409，控制运输车辆标识对应的运输车辆行驶至目标分拣中心。
在一些实施例中，上述执行主体可以控制上述运输车辆标识对应的运输车辆行驶至上述目标分拣中心。实践中，上述执行主体可以向上述运输车辆标识对应的运输车辆的车载终端发送表征行驶至上述目标分拣中心的指令，使得上述运输车辆行驶至上述目标分拣中心。由此，可以控制所确定的运输车辆行驶至存储了目标站点的货物的目标分拣中心。
可选地，首先，上述执行主体可以控制相关联的物品搬运设备将对应于上述目标站点的物品搬运至上述运输车辆。其中，上述物品搬运设备可以为用于搬运物品的设备，例如，可以为机械臂。对应于上述目标站点的物品可以为实际到达目标分拣中心的需配送至上述目标站点的物品。实践中，可以向上述物品搬运设备发送表征将对应于上述目标站点的物品搬运至上述运输车辆的指令，使得上述物品搬运设备将对应于上述目标站点的物品搬运至上述运输车辆。然后，可以控制装载有对应于上述目标站点的物品的运输车辆行驶至上述目标站点。实践中，可以向上述运输车辆的车载终端发送表征行驶至上述目标站点的指令，使得上述运输车辆行驶至上述目标站点。由此，可以在运输车辆行驶至目标分拣中心后，通过物品搬运设备进行物品装载， 进而可以使得装载有物品的运输车辆行驶至目标站点，以实现对目标站点的物品配送。
从图4中可以看出，与图2对应的一些实施例的描述相比，图4对应的一些实施例中的站点到货量预测方法的流程400体现了对控制运输车辆行驶至目标分拣中心进行扩展的步骤。由此，这些实施例描述的方案可以根据目标站点对应的历史货物总体量集合，预测目标站点的目标货物总体量。从而可以根据预测的目标站点的目标货物总体量，确定用于运输目标站点的货物的运输车辆。进而可以控制所确定的运输车辆行驶至存储了目标站点的货物的目标分拣中心。
参考图5，作为对上述各图所示方法的实现，本公开提供了一种站点到货量预测装置的一些实施例，这些装置实施例与图2所示的那些方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，一些实施例的站点到货量预测装置500包括：获取单元501、第一生成单元502、确定单元503、第二生成单元504和第三生成单元505。其中，获取单元501被配置成获取预设历史时段内目标分拣中心的货量信息集合，其中，上述货量信息集合中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历史货量；第一生成单元502被配置成基于上述各个站点中的每个站点，根据上述货量信息集合包括的对应上述站点的各个历史货量，生成上述预设历史时段内上述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合；确定单元503被配置成基于上述历史货量占比组集合和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历史货量占比是否稳定；第二生成单元504被配置成响应于确定上述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和上述历史货量集合中对应上述目标站点的各个历史货量，生成目标货量占比，其中，上述历史货量集合为上述货量信息集合所包括的历史货量的集合；第三生成单元505被配置成根据上述目标货量占比和对应上述目标分拣中心的预测总货量，生成对应上述目标站点的站点到货量。
可选地，站点到货量预测装置500还可以包括：站点到货总量生成单元(图中未示出)，被配置成根据对应上述目标站点的各个分拣中心的预测总货量和上述目标站点对应于上述各个分拣中心的目标货量占比，生成对应上述目标站点的站点到货总量，其中，上述预设历史时段内上述目标站点在上述各个分拣中心的历史货量占比稳定。
可选地，上述货量信息集合中的货量信息还包括各个站点的历史货物总体量。
可选地，站点到货量预测装置500还可以包括：历史货物总体量提取单元、目标货物总体量生成单元、运输车辆标识选择单元和第一运输车辆控制单元(图中未示出)。其中，历史货物总体量提取单元被配置成从上述货量信息集合包括的各个货量信息中提取对应上述目标站点的历史货物总体量，得到历史货物总体量集合。目标货物总体量生成单元被配置成根据上述历史货物总体量集合，确定目标货物总体量。运输车辆标识选择单元被配置成根据上述目标货物总体量和上述站点到货量，从预设的运输车辆标识组中选择对应上述目标站点的运输车辆标识。第一运输车辆控制单元被配置成控制上述运输车辆标识对应的运输车辆行驶至上述目标分拣中心。
可选地，站点到货量预测装置500还可以包括：物品搬运设备控制单元和第二运输车辆控制单元(图中未示出)。其中，物品搬运设备控制单元被配置成控制相关联的物品搬运设备将对应于上述目标站点的物品搬运至上述运输车辆。第二运输车辆控制单元被配置成控制装载有对应于上述目标站点的物品的运输车辆行驶至上述目标站点。
可选地，确定单元503可以包括：历史货量占比极差确定单元、总历史货量确定单元、待备选站点集合确定单元、站点历史货量和确定单元和备选站点集合确定单元(图中未示出)。其中，历史货量占比极差确定单元被配置成基于上述历史货量占比组集合中的每个历史货量占比组，确定上述历史货量占比组对应的历史货量占比极差，得到历史货量占比极差集合。总历史货量确定单元被配置成将上述历史货量集合包括的各个历史货量的和确定为上述预设历史时段内的总历史货量。待备选站点集合确定单元被配置成将上述历史货量占比极差集 合中小于等于预设极差的各个历史货量占比极差对应的各个站点确定为待备选站点集合。站点历史货量和确定单元被配置成将上述历史货量集合包括的对应上述待备选站点集合的各个历史货量的和确定为站点历史货量和。备选站点集合确定单元被配置成响应于确定上述站点历史货量和与上述总历史货量的比值大于等于预设比值，将对应上述站点历史货量和的各个站点确定为备选站点集合。
可选地，确定单元503还可以包括：历史货量占比稳定性确定单元(图中未示出)，被配置成响应于上述备选站点集合包括上述站点，且上述货量信息集合中对应于上述站点的各个历史货量的极差小于等于预设货量极差，确定上述预设历史时段内上述站点的历史货量占比稳定。
可选地，在获取单元501之后，站点到货量预测装置500还可以包括：历史货量序列确定单元、待剔除历史货量序列集合确定单元和历史货量剔除单元(图中未示出)。其中，历史货量序列确定单元被配置成根据上述货量信息集合包括的各个货量信息，确定上述各个站点中的每个站点在上述预设历史时段内的历史货量序列，得到历史货量序列集合。待剔除历史货量序列集合确定单元被配置成响应于上述历史货量序列集合中存在至少一个包括的历史货量均小于预设货量阈值的历史货量序列，将包括的历史货量均小于上述预设货量阈值的各个历史货量序列确定为待剔除历史货量序列集合。历史货量剔除单元被配置成从上述货量信息集合中剔除上述待剔除历史货量序列集合包括的各个历史货量。
可选地，在历史货量序列确定单元之后，站点到货量预测装置500还可以包括：待平滑历史货量序列集合确定单元和历史货量平滑单元(图中未示出)。其中，待平滑历史货量序列集合确定单元被配置成响应于上述历史货量序列集合中存在至少一个包括的历史货量满足预设离群条件的历史货量序列，将包括的历史货量满足上述预设离群条件的各个历史货量序列确定为待平滑历史货量序列集合。历史货量平滑单元被配置成对于上述待平滑历史货量序列集合中每个待平滑历史货量序列包括的满足上述预设离群条件的每个历史货量，根据上述待平 滑历史货量序列，生成上述历史货量的平滑历史货量，以及将上述历史货量替换为上述平滑历史货量。
可以理解的是，该装置500中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作、特征以及产生的有益效果同样适用于装置500及其中包含的单元，在此不再赘述。
下面参考图6，其示出了适于用来实现本公开的一些实施例的电子设备(例如图1中的计算设备101)600的结构示意图图6示出的电子设备仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图6所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储装置608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有电子设备600操作所需的各种程序和数据。处理装置601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储装置608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图6中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的一些实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的一些实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该 计算机程序包含用于执行流程图所示的方法的程序代码。在这样的一些实施例中，该计算机程序可以通过通信装置609从网络上被下载和安装，或者从存储装置608被安装，或者从ROM 602被安装。在该计算机程序被处理装置601执行时，执行本公开的一些实施例的方法中限定的上述功能。
需要说明的是，本公开的一些实施例中记载的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的一些实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开的一些实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端 网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取预设历史时段内目标分拣中心的货量信息集合，其中，上述货量信息集合中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历史货量；基于上述各个站点中的每个站点，根据上述货量信息集合包括的对应上述站点的各个历史货量，生成上述预设历史时段内上述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合；基于上述历史货量占比组集合和上述各个站点中的每个站点，确定上述预设历史时段内上述站点的历史货量占比是否稳定；响应于确定上述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和上述历史货量集合中对应上述目标站点的各个历史货量，生成目标货量占比，其中，上述历史货量集合为上述货量信息集合所包括的历史货量的集合；根据上述目标货量占比和对应上述目标分拣中心的预测总货量，生成对应上述目标站点的站点到货量。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的一些实施例的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点 上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含至少一个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的一些实施例中的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单元、第一生成单元、确定单元、第二生成单元和第三生成单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取单元还可以被描述为“获取预设历史时段内目标分拣中心的货量信息集合的单元”。
本文中以上描述的功能可以至少部分地由至少一个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
以上描述仅为本公开的一些较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (11)

  1. 一种站点到货量预测方法，包括：
    获取预设历史时段内目标分拣中心的货量信息集合，其中，所述货量信息集合中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历史货量；
    基于所述各个站点中的每个站点，根据所述货量信息集合包括的对应所述站点的各个历史货量，生成所述预设历史时段内所述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合；
    基于所述历史货量占比组集合和所述各个站点中的每个站点，确定所述预设历史时段内所述站点的历史货量占比是否稳定；
    响应于确定所述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和所述历史货量集合中对应所述目标站点的各个历史货量，生成目标货量占比，其中，所述历史货量集合为所述货量信息集合所包括的历史货量的集合；
    根据所述目标货量占比和对应所述目标分拣中心的预测总货量，生成对应所述目标站点的站点到货量。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    根据对应所述目标站点的各个分拣中心的预测总货量和所述目标站点对应于所述各个分拣中心的目标货量占比，生成对应所述目标站点的站点到货总量，其中，所述预设历史时段内所述目标站点在所述各个分拣中心的历史货量占比稳定。
  3. 根据权利要求1或2所述的方法，其中，所述货量信息集合中的货量信息还包括各个站点的历史货物总体量，所述方法还包括：
    从所述货量信息集合包括的各个货量信息中提取对应所述目标站点的历史货物总体量，得到历史货物总体量集合；
    根据所述历史货物总体量集合，确定目标货物总体量；
    根据所述目标货物总体量和所述站点到货量，从预设的运输车辆 标识组中选择对应所述目标站点的运输车辆标识；
    控制所述运输车辆标识对应的运输车辆行驶至所述目标分拣中心。
  4. 根据权利要求3所述的方法，其中，所述方法还包括：
    控制相关联的物品搬运设备将对应于所述目标站点的物品搬运至所述运输车辆；
    控制装载有对应于所述目标站点的物品的运输车辆行驶至所述目标站点。
  5. 根据权利要求1-4之一所述的方法，其中，所述基于所述历史货量占比组集合和所述各个站点中的每个站点，确定所述预设历史时段内所述站点的历史货量占比是否稳定，包括：
    基于所述历史货量占比组集合中的每个历史货量占比组，确定所述历史货量占比组对应的历史货量占比极差，得到历史货量占比极差集合；
    将所述历史货量集合包括的各个历史货量的和确定为所述预设历史时段内的总历史货量；
    将所述历史货量占比极差集合中小于等于预设极差的各个历史货量占比极差对应的各个站点确定为待备选站点集合；
    将所述历史货量集合包括的对应所述待备选站点集合的各个历史货量的和确定为站点历史货量和；
    响应于确定所述站点历史货量和与所述总历史货量的比值大于等于预设比值，将对应所述站点历史货量和的各个站点确定为备选站点集合。
  6. 根据权利要求5所述的方法，其中，所述确定所述预设历史时段内所述站点的历史货量占比是否稳定，包括：
    响应于所述备选站点集合包括所述站点，且所述货量信息集合中对应于所述站点的各个历史货量的极差小于等于预设货量极差，确定 所述预设历史时段内所述站点的历史货量占比稳定。
  7. 根据权利要求1-6之一所述的方法，其中，在所述获取预设历史时段内目标分拣中心的货量信息集合之后，所述方法还包括：
    根据所述货量信息集合包括的各个货量信息，确定所述各个站点中的每个站点在所述预设历史时段内的历史货量序列，得到历史货量序列集合；
    响应于所述历史货量序列集合中存在至少一个包括的历史货量均小于预设货量阈值的历史货量序列，将包括的历史货量均小于所述预设货量阈值的各个历史货量序列确定为待剔除历史货量序列集合；
    从所述货量信息集合中剔除所述待剔除历史货量序列集合包括的各个历史货量。
  8. 根据权利要求7所述的方法，其中，在所述根据所述货量信息集合包括的各个货量信息，确定所述各个站点中的每个站点在所述预设历史时段内的历史货量序列，得到历史货量序列集合之后，所述方法还包括：
    响应于所述历史货量序列集合中存在至少一个包括的历史货量满足预设离群条件的历史货量序列，将包括的历史货量满足所述预设离群条件的各个历史货量序列确定为待平滑历史货量序列集合；
    对于所述待平滑历史货量序列集合中每个待平滑历史货量序列包括的满足所述预设离群条件的每个历史货量，根据所述待平滑历史货量序列，生成所述历史货量的平滑历史货量，以及将所述历史货量替换为所述平滑历史货量。
  9. 一种站点到货量预测装置，包括：
    获取单元，被配置成获取预设历史时段内目标分拣中心的货量信息集合，其中，所述货量信息集合中的货量信息包括上述目标分拣中心分拣至对应的各个站点的各个历史货量；
    第一生成单元，被配置成基于所述各个站点中的每个站点，根据 所述货量信息集合包括的对应所述站点的各个历史货量，生成所述预设历史时段内所述站点的各个历史货量占比作为历史货量占比组，得到历史货量占比组集合；
    确定单元，被配置成基于所述历史货量占比组集合和所述各个站点中的每个站点，确定所述预设历史时段内所述站点的历史货量占比是否稳定；
    第二生成单元，被配置成响应于确定所述各个站点中目标站点的历史货量占比稳定，根据历史货量集合和所述历史货量集合中对应所述目标站点的各个历史货量，生成目标货量占比，其中，所述历史货量集合为所述货量信息集合所包括的历史货量的集合；
    第三生成单元，被配置成根据所述目标货量占比和对应所述目标分拣中心的预测总货量，生成对应所述目标站点的站点到货量。
  10. 一种电子设备，包括：
    至少一个处理器；
    存储装置，其上存储有至少一个程序，
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-8中任一所述的方法。
  11. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-8中任一所述的方法。
PCT/CN2022/118580 2021-12-24 2022-09-14 站点到货量预测方法、装置、电子设备和计算机可读介质 WO2023116075A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111593778.4 2021-12-24
CN202111593778.4A CN113988485B (zh) 2021-12-24 2021-12-24 站点到货量预测方法、装置、电子设备和计算机可读介质

Publications (1)

Publication Number Publication Date
WO2023116075A1 true WO2023116075A1 (zh) 2023-06-29

Family

ID=79734213

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/118580 WO2023116075A1 (zh) 2021-12-24 2022-09-14 站点到货量预测方法、装置、电子设备和计算机可读介质

Country Status (2)

Country Link
CN (1) CN113988485B (zh)
WO (1) WO2023116075A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113988485B (zh) * 2021-12-24 2022-06-07 北京京东振世信息技术有限公司 站点到货量预测方法、装置、电子设备和计算机可读介质
CN116992988A (zh) * 2022-04-21 2023-11-03 北京京东振世信息技术有限公司 运单量拆分方法、装置、电子设备和计算机可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017179577A1 (ja) * 2016-04-15 2017-10-19 裕之 本地川 ピッキング作業管理システム、及びプログラム
CN110866786A (zh) * 2019-11-12 2020-03-06 德邦物流股份有限公司 一种货量预测方法、装置、电子设备及存储介质
CN111325398A (zh) * 2020-02-19 2020-06-23 上海东普信息科技有限公司 网点货量的预测方法及系统、存储介质
CN112906930A (zh) * 2019-12-04 2021-06-04 顺丰科技有限公司 场地货量预测方法、装置、设备及存储介质
CN113988485A (zh) * 2021-12-24 2022-01-28 北京京东振世信息技术有限公司 站点到货量预测方法、装置、电子设备和计算机可读介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015040790A1 (ja) * 2013-09-20 2015-03-26 日本電気株式会社 払出量予測装置、払出量予測方法、記録媒体、及び払出量予測システム
CN107093096B (zh) * 2016-12-15 2022-03-25 口碑(上海)信息技术有限公司 一种业务量预测方法及装置
CN113128820B (zh) * 2020-01-16 2024-03-01 北京京东振世信息技术有限公司 评估仓库调整计划的方法、装置、设备和计算机可读介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017179577A1 (ja) * 2016-04-15 2017-10-19 裕之 本地川 ピッキング作業管理システム、及びプログラム
CN110866786A (zh) * 2019-11-12 2020-03-06 德邦物流股份有限公司 一种货量预测方法、装置、电子设备及存储介质
CN112906930A (zh) * 2019-12-04 2021-06-04 顺丰科技有限公司 场地货量预测方法、装置、设备及存储介质
CN111325398A (zh) * 2020-02-19 2020-06-23 上海东普信息科技有限公司 网点货量的预测方法及系统、存储介质
CN113988485A (zh) * 2021-12-24 2022-01-28 北京京东振世信息技术有限公司 站点到货量预测方法、装置、电子设备和计算机可读介质

Also Published As

Publication number Publication date
CN113988485A (zh) 2022-01-28
CN113988485B (zh) 2022-06-07

Similar Documents

Publication Publication Date Title
WO2023116075A1 (zh) 站点到货量预测方法、装置、电子设备和计算机可读介质
CN110309142B (zh) 规则管理的方法和装置
CN109345166B (zh) 用于生成信息的方法和装置
WO2023134188A1 (zh) 指标确定方法、装置、电子设备和计算机可读介质
CN112836128A (zh) 信息推荐方法、装置、设备和存储介质
WO2023134189A1 (zh) 补货信息生成方法、装置、电子设备和计算机可读介质
CN114202130A (zh) 流转量预测多任务模型生成方法、调度方法、装置和设备
CN110766348A (zh) 一种组合拣货任务的方法和装置
CN116756616A (zh) 数据处理方法、装置、计算机可读介质及电子设备
CN113205300B (zh) 配送车辆调度方法、装置、电子设备和计算机可读介质
CN113222205A (zh) 一种路径规划的方法和装置
CN116862319B (zh) 电力指标信息生成方法、装置、电子设备和介质
CN112365109A (zh) 配送路径信息生成方法、装置、电子设备和可读介质
CN113610460A (zh) 物品封装方法、装置、电子设备和计算机可读介质
CN111324470B (zh) 用于生成信息的方法及装置
CN112581043A (zh) 设备控制方法、装置、电子设备和计算机可读介质
CN113762674A (zh) 订单配送方法和装置
CN116796233A (zh) 数据分析方法、装置、计算机可读介质及电子设备
CN112308477A (zh) 库存定位方法和装置
CN114691503B (zh) 一种面向测试的管理方法、装置、设备及介质
CN116245595A (zh) 供应端物品运输方法、装置、电子设备和计算机可读介质
CN114429273A (zh) 仓库储位调整任务信息生成方法、装置、设备和计算机可读介质
CN113986959A (zh) 物流信息采集方法、装置、电子设备和计算机可读介质
CN112906723B (zh) 一种特征选择的方法和装置
CN112837003B (zh) 一种确定快递员配送范围的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22909393

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE