WO2023093567A1 - 物品库存的控制方法、装置、设备及介质 - Google Patents

物品库存的控制方法、装置、设备及介质 Download PDF

Info

Publication number
WO2023093567A1
WO2023093567A1 PCT/CN2022/131900 CN2022131900W WO2023093567A1 WO 2023093567 A1 WO2023093567 A1 WO 2023093567A1 CN 2022131900 W CN2022131900 W CN 2022131900W WO 2023093567 A1 WO2023093567 A1 WO 2023093567A1
Authority
WO
WIPO (PCT)
Prior art keywords
item
processed
target
replenishment
shipment
Prior art date
Application number
PCT/CN2022/131900
Other languages
English (en)
French (fr)
Inventor
钟冰洁
高振羽
庄晓天
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 WO2023093567A1 publication Critical patent/WO2023093567A1/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
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2474—Sequence data queries, e.g. querying versioned data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • the present application relates to the field of computer technology, for example, to a method, device, device and medium for controlling item inventory.
  • each item will have a certain amount of inventory.
  • the inventory of each item is randomly determined. For example, when the inventory of an item is checked at a time and is less than the preset threshold, the corresponding item is acquired; or, at a certain interval, a certain amount of items is acquired and stored.
  • the present application provides a method, device, equipment and medium for controlling inventory of items, so as to achieve the technical effect of effectively controlling inventory costs.
  • the present application provides a method for controlling inventory of items, the method comprising:
  • For each item to be processed determine the replenishment attribute value of the item to be processed according to the current time and the shipment volume associated information of the item to be processed currently;
  • the target replenishment amount of the target item to be processed is determined according to the target inventory amount of the current target item to be processed and the net inventory amount corresponding to the current time.
  • an item inventory control device which includes:
  • the collection and calculation module is configured to determine the replenishment attribute value of the current item to be processed according to the current time and the shipment related information of the item to be processed for each item to be processed;
  • the inventory strategy operation module is configured to determine the target item to be processed according to the replenishment attribute value and the target inventory determination model if it is detected that there is a target item to be processed with a replenishment attribute value greater than a preset replenishment attribute threshold The target inventory quantity;
  • the result output module is configured to, for each target item to be processed, determine the target replenishment amount of the target item to be processed according to the target inventory amount and the net inventory amount corresponding to the current time.
  • the present application also provides an electronic device, the electronic device comprising:
  • processors one or more processors
  • a storage device configured to store one or more programs
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned item inventory control method.
  • the present application also provides a storage medium containing computer-executable instructions, the computer-executable instructions are used to execute the above-mentioned item inventory control method when executed by a computer processor.
  • FIG. 1 is a schematic flow diagram of a method for controlling an item inventory provided in an embodiment of the present application
  • FIG. 2 is a schematic flow diagram of determining items to be processed from multiple items provided by the embodiment of the present application;
  • FIG. 3 is a schematic flowchart of a method for controlling inventory of items provided in an embodiment of the present application
  • FIG. 4 is a schematic flowchart of a replenishment vertical screen calculation logic provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of another method for controlling inventory of items provided in the embodiment of the present application.
  • FIG. 6 is a schematic flow diagram of another method for controlling inventory of items provided in the embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of a business data processing device provided in an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • Fig. 1 is a schematic flowchart of an item inventory control method provided by the embodiment of the present application. This embodiment is applicable to the situation where the replenishment quantity of each item is determined, and then the inventory cost is effectively controlled based on the replenishment quantity.
  • the method can be executed by an item inventory control device, and the device can be implemented in the form of software and/or hardware.
  • the hardware can be an electronic device, and the electronic device can be a mobile terminal, a personal computer (Personal Computer, PC) terminal, and the like.
  • the execution of the technical solution may be executed by a server, or by a terminal device, or by cooperation of the server and the terminal device.
  • the method includes:
  • S110 Determine at least one item to be processed according to the shipment volume associated information of each item.
  • the shipping volume associated information includes a shipping date sequence and a shipping volume corresponding to each shipping date.
  • the shipping date can be the date of each day, and the shipping amount can be the amount corresponding to the items sold every day, then the shipping amount can be 0 or any value greater than 0.
  • the items determined according to the shipment volume correlation information are regarded as items to be processed.
  • the items to be processed may be all items, or some items in all items.
  • the manner of determining the items to be processed may be: determining the number of days between shipments according to the associated information of the shipment volume. If the number of days between shipments is greater than the threshold value of the preset number of days between intervals, the item corresponding to the shipment volume associated information may be used as an item to be processed.
  • the quantity of at least one item to be processed may include one, two or even more, and its data is determined according to the associated information about the shipment of the item.
  • the technical solution can determine the target replenishment quantity of all items, and is especially suitable for the target replenishment quantity of items to be processed that meet certain conditions, such as some items with low shipping frequency, for example, automobile spare parts and the like.
  • the shipment-volume-associated information of each item can be acquired at a preset time point.
  • the preset time point may be a relative time point or an absolute time point.
  • the relative time point may be to obtain the shipment related information of the item at a certain interval, for example, the interval may be one week.
  • the absolute time point may be a fixed time point every day, for example, the fixed time point may be at 10 o'clock in the evening every day to obtain the shipment related information of each item.
  • the item corresponding to the acquired shipment related information may be an item corresponding to a stock keeping unit (Stock Keeping Unit, SKU), or it may be an item corresponding to multiple SKUs, or it may be all items.
  • SKU stock keeping unit
  • the shipment volume associated information includes the shipment date and the shipment volume corresponding to the shipment date, and before determining at least one item to be processed according to the shipment volume association information of each item, further Including: according to the shipment date and corresponding shipment volume of each item, determine the shipment interval between two adjacent shipments of each item, and update the shipment interval to the shipment volume association of the corresponding item information.
  • the shipment related information includes the shipment of each item on each date, that is, the time series and the shipment corresponding to each time point in the time series.
  • the time at this time is mainly the date, and the time series in the Dates are consecutive dates.
  • the shipment volume of a date may be 0, and a date will be omitted.
  • this date can be added to the time series, and the shipment volume of this date can be marked as 0.
  • the shipping interval between two adjacent shipments can be determined, and the shipping interval can be used as part of the shipping volume related information.
  • determining the shipment interval may be: for each item's shipment volume associated information, when it is detected that the current item's shipment volume is greater than the preset shipment volume threshold, then determine the shipment volume Corresponding to-be-processed shipping date; according to the to-be-processed shipping date corresponding to each item, determine the shipping interval between two adjacent shipments of each item.
  • the value in the shipment can be 0, or any data greater than 0, and its data value corresponds to the actual sales volume of the day.
  • the default shipment threshold may be 0. If the shipment volume corresponding to a shipment date is greater than the preset shipment volume threshold, the shipment date is determined to be a shipment date to be processed.
  • the shipping interval between two adjacent shipments can be determined according to each pending shipping date of each item. At this time, the determined number of shipping intervals can be 0 or any value greater than 0.
  • Each item has a set of corresponding shipping intervals, and each shipping interval set includes at least one shipping interval. That is, the shipping interval is an element in the shipping interval set.
  • 2 means that the interval between two adjacent shipments is 2 days
  • 8 means that the interval between two adjacent shipments is 8 days. Since the SKU has not been sold in the last few days, the 0 in the last part is not included in the number of days between sales.
  • the method further includes: determining the coefficient of variation of the corresponding item according to at least one shipping interval corresponding to each item; Determine at least one item to be processed according to a preset coefficient of variation threshold and each coefficient of variation.
  • the coefficient of variation is used to represent the fluctuation of the item shipment interval. Generally, the smaller the coefficient of variation, the smaller the fluctuation of the item sales interval. Correspondingly, the larger the variation coefficient, the greater the fluctuation of the item sales interval.
  • the preset coefficient of variation threshold is a value set according to theoretical data. According to the coefficient of variation of each item and the preset threshold value of the coefficient of variation, the item to be processed is determined. For example, the item whose coefficient of variation is greater than the preset threshold value of the coefficient of variation can be regarded as the item to be processed.
  • determining the coefficient of variation corresponding to each item may be: for the shipping interval of each item, according to at least one shipping interval corresponding to the current item, determine the mean value of the time interval and the variance of the time interval ; Determine the coefficient of variation of each item according to the mean value of the time interval and the variance of the time interval corresponding to each item.
  • the mean value of the time interval can be calculated according to the shipment interval in the current item shipment related information, and at the same time, the variance of the time interval can be calculated. Determines the coefficient of variation based on the ratio between the variance of the time interval and the mean of the time interval.
  • an item whose coefficient of variation is smaller than a preset threshold value of the coefficient of variation may be used as the item to be processed.
  • the advantage of determining the items to be processed according to the coefficient of variation is that the intermittently sold items can be determined from all the items, thereby realizing the technical effect of processing the intermittently sold items.
  • the current time can be the current date.
  • the replenishment attribute value is used to represent the urgency of replenishment for the current item to be processed at the current time. If the replenishment attribute value is high, it means that the current pending item needs to be replenished, and if the replenishment attribute value is small, it means that the current pending item does not need to be replenished.
  • the replenishment attribute value of each item to be processed can be determined according to the current time, the shipment date and the shipment volume of the item to be processed, so as to determine whether to replenish the item to be processed according to the replenishment attribute value .
  • the preset replenishment attribute threshold is predetermined, which can be used as a reference standard for determining whether to perform replenishment.
  • Target pending items are pending items that need to be replenished.
  • the target inventory determination model is a predetermined mathematical model for determining the target inventory of each item to be processed according to the replenishment attribute value of the item to be processed.
  • the target stock quantity may be the stock quantity corresponding to the current item.
  • the target inventory quantities of different items to be processed may be the same or different, and whether they are the same is related to the replenishment attribute value of the items to be processed. That is, the value of the target stock quantity is determined by the target replenishment attribute value of each target pending item.
  • the replenishment attribute value of each item to be processed it may be determined whether there is an item to be processed whose replenishment attribute value is greater than a preset replenishment attribute threshold. If there is an item to be processed whose replenishment attribute value is greater than a preset replenishment attribute threshold, the item to be processed may be used as a target item to be processed. For each target item to be processed, the replenishment attribute value of the current target item to be processed can be input into the target inventory determination model to obtain the target inventory corresponding to the current target item to be processed. Other target items to be processed can be processed in the same manner, so as to obtain the corresponding target inventory.
  • the target replenishment quantity is determined based on the determined target inventory quantity and the corresponding net inventory quantity.
  • the target replenishment amount of the current target item to be processed is determined by calculating the difference between the target inventory amount of the current target item to be processed and the net inventory amount corresponding to the current time.
  • the technical solution of the embodiment of the present application is mainly determined according to the (T, S) strategy.
  • the replenishment attribute value of each item to be processed can be determined according to the current time and the shipment related information of each item to be processed. If there is a replenishment attribute value greater than the preset replenishment attribute threshold value of the target item to be processed, the replenishment attribute value of the target item to be processed can be used as the input of the target inventory determination model to determine the target inventory corresponding to the target item to be processed, and then based on the target inventory and the target to be processed.
  • the existing net inventory of the item at the current time determines the target replenishment amount, which solves the problem that the inventory amount of the item in the related technology is randomly determined or fixed, resulting in the determined replenishment amount and the actual required amount Inappropriate, which causes the problem of high inventory cost, realizes the determination of the target replenishment amount based on the shipment related information of each item to be processed, improves the accuracy of determining the target replenishment amount, and is effective for inventory costs Technical effects of control.
  • Fig. 2 is a schematic flowchart of determining an item to be processed from multiple items provided by an embodiment of the present application.
  • the technical solution can determine the target inventory of each item on each date, and is especially suitable for determining the target inventory of intermittently sold items. Therefore, before determining the target inventory of the intermittently sold items, the intermittently sold items, that is, the items to be processed, can be determined first.
  • technical terms that are the same as or corresponding to those in the foregoing embodiments will not be repeated here.
  • the method includes:
  • the user can set corresponding filtering conditions, for example, the filtering condition is to obtain items of category A, and determine the items to be processed from the items of category A.
  • the filtering condition is to obtain items of category A, and determine the items to be processed from the items of category A.
  • the filtering condition is to obtain items of category A, and determine the items to be processed from the items of category A.
  • the associated information of the shipment volume of each item within a preset period of time may be obtained, for example, the shipment date is a date within two months, and the shipment volume corresponding to each shipment date is determined.
  • S220 Determine the mean value of the time interval and the variance of the time interval of each item according to the set of delivery interval days of each item.
  • the delivery intervals of the items are 2 and 8 respectively, the calculated average of the interval days is 5, and the variance of the interval days is 3. That is, the mean value of the duration interval is 5, the variance of the duration interval is 3, and the unit is day.
  • the coefficient of variation is used to characterize the fluctuation in the sales interval of an item.
  • Items whose coefficient of variation is smaller than a preset threshold value of coefficient of variation can be regarded as items to be processed. Items to be processed can be added to the item list to regularly determine whether the items in the item list need to be replenished, so as to effectively control the inventory cost.
  • variation coefficient When the variation coefficient is less than the preset variation coefficient threshold, it means that the shipment interval of the item to be shipped fluctuates little. Items that ship at short intervals can be treated as pending items for intermittent sale.
  • the items to be processed that are sold intermittently can be processed to determine the target inventory corresponding to each item to be processed, and then determine the target replenishment amount of the corresponding item to be processed, so as to effectively control the inventory cost technical effect.
  • At least one shipment interval corresponding to each item may be determined by processing the shipment-related information of each item.
  • the coefficient of variation of each item can be determined, so as to determine the items to be processed according to the coefficient of variation.
  • Fig. 3 is a schematic flowchart of an item inventory control method provided by the embodiment of the present application.
  • Fig. 3 is a schematic flowchart of an item inventory control method provided by the embodiment of the present application.
  • the method includes:
  • S310 Determine at least one item to be processed according to the shipment volume associated information of each item.
  • the target data processing method may be a processing method for determining the replenishment attribute value of the item currently to be processed.
  • the data processing methods are also different. In order to improve the effective control of inventory costs, different data processing methods can be used to process the shipment related information.
  • the processing method for processing the shipment-related information can be determined according to the shipment-related information of the items to be processed, and this processing method can be used as the target data processing method, so that based on the target data processing
  • the method processes the shipment related information of the corresponding item to be processed, and obtains the replenishment attribute value of the corresponding item to be processed.
  • determining the target data processing method according to the shipment related information may be: determining at least one shipment interval according to the shipment corresponding to each shipment date in the shipment related information; If the at least one shipping interval satisfies a preset uniform distribution, then determine that the target data processing method is a mean value estimation method; if the at least one shipping interval does not satisfy a preset uniform distribution, then determine the target data The processing method is the quantile estimation method.
  • At least one shipping interval is concentrated in a numerical range, it can be determined that the shipping interval is relatively uniform, and at this time it can be determined that the shipping interval satisfies a uniform distribution.
  • the variance can represent the fluctuation degree of the value.
  • To determine whether the uniform distribution is satisfied it can also be determined whether the variance of the time interval is less than the preset threshold. If the variance of the time interval is less than the preset threshold, it means that the shipment interval of the item to be processed satisfies the uniform distribution. If the variance of the time interval is not less than the preset threshold, it means that the time interval between shipments of the item to be processed does not satisfy the uniform distribution.
  • the data processing method used when the preset uniform distribution is met is used as the mean value estimation method, and the data processing method adopted when the preset uniform distribution is not satisfied is used as the quantile estimation method.
  • the quantile estimation method is to determine the quantile point based on the shipment related information, and then determine the replenishment attribute value based on the quantile point.
  • the means of estimating the mean value is determined according to the mean value of the time interval between shipments and the variance of the time interval between shipments in the associated information of the shipment volume.
  • the corresponding target data processing method can be determined according to the shipment interval time in the shipment related information of the item to be processed, so as to determine the corresponding target data processing method based on the target data processing method The item's replenishment attribute value.
  • the replenishment attribute value is used to represent the extent to which the items to be processed need to be replenished. For example, the larger the value of the replenishment attribute, the greater the demand for replenishment of the item to be processed, and the smaller the value of the replenishment attribute, it indicates that the item to be processed needs There is less need for replenishment.
  • the shipment volume related information of the item to be processed can be processed based on the target data processing method to obtain the replenishment attribute value of the corresponding item to be processed.
  • other related information corresponding to the item to be processed may be determined first, and then the target data processing method is used to obtain the replenishment attribute value. For example, determine the shipment date to be used in the shipment volume related information that is greater than the preset shipment volume threshold and has the smallest interval with the current time; according to the date corresponding to the current time and the to-be-used shipment date The first time length is determined based on the delivery date; based on the target data processing method, the first time length and the shipment related information are processed to obtain the replenishment attribute value of the current item to be processed.
  • the current time mainly refers to the current date.
  • the first duration is mainly the duration interval between the current time and the shipping date to be used.
  • the shipping date to be used can be the date that is closest to the current time and the sale occurs. For example, if the current date is 6.20, and the last sale date before the current date is 5.31, then the date to be used is 5.31. Correspondingly, the first duration is 20 days.
  • the default shipment threshold may be 0.
  • the shipping date to be used with the smallest distance from the current time and whose shipment volume is greater than the preset shipment volume threshold can be determined according to the shipment interval time in the shipment volume associated information of the current item to be processed.
  • the first duration can be determined.
  • the replenishment attribute value of the current item to be processed can be determined.
  • the target data method includes any one of the above two methods.
  • the target data processing method to process the shipment-related information of the corresponding item to be processed refer to the following expression:
  • the first implementation manner may be: mean value estimation manner. Based on the mean value estimation method, the first duration and the variance of the duration interval determined according to the duration of the shipment interval are processed to determine the replenishment attribute value of the item currently to be processed.
  • the target processing method of the current item to be processed is the mean value estimation method
  • the variance of the shipping interval and the mean value of the shipping interval may be determined according to the shipping interval.
  • the replenishment attribute value of the current item to be processed is obtained.
  • the replenishment attribute value of the SKU can be obtained by calculating the ratio between the first time length and the mean value of the shipping interval time, such as That is, the replenishment attribute value of the SKU is obtained as 0.3125.
  • the second implementation manner may be: quantile estimation manner.
  • the quantile estimation method includes two sub-methods, and the corresponding sub-estimation method can be determined according to the shipment volume correlation information.
  • the target data processing method is a quantile estimation method
  • determine the target quantile sub-estimation method based on the target quantile sub-estimation method, the first The duration and the related information of the shipment volume are processed to determine the replenishment attribute value of the item currently to be processed.
  • the shipment related information of the item to be processed can determine the processing method adopted when the item to be processed is processed.
  • the method of determining the target quantile estimation method according to the shipment volume correlation information may be: the shipment volume correlation information includes the number of shipments corresponding to the shipment interval, and the shipment volume correlation information and preset quantiles to determine the target quantile sub-estimation method, including:
  • the preset quantile is less than or equal to the reciprocal of the number of shipments, then determine that the target quantile sub-estimation method is the first quantile sub-estimation method; if the preset quantile is greater than the reciprocal of the number of shipments, then The method of determining the target quantile sub-trajectory is the second quantile sub-estimation method.
  • the number of shipments may be the number of times items are sold within a preset period of time. That is to say, the number of shipments can be determined according to the number of times corresponding to the number of days between shipments in the shipment related information, that is, the number of shipments is the same as the number corresponding to the number of days between shipments.
  • the preset quantile is a percentage set by the user according to actual needs. Optionally, the percentage can be 0.8.
  • the empirical distribution can be obtained by fitting the shipment interval time in the shipment volume related information of the current item to be processed. If the preset quantile is less than or equal to the reciprocal of the number of shipments, it means that the number of shipments within a certain period of time is small. At this time, the first quantile sub-estimation method can be used to determine the replenishment attribute value of the current item to be processed. If the preset division is greater than the threshold value of the number of shipments, the second quantile sub-estimation method can be used to determine the replenishment attribute value. In this embodiment, determining the sub-estimation methods corresponding to different items to be processed improves the accuracy of determining the replenishment attribute value of the item to be processed.
  • the first implementation manner may be: if the target quantile sub-estimation method is the first quantile sub-estimation method, then according to the number of days between shipments, the preset quantile, the number of shipments, and the first duration, determine the current waiting period Handles the item's replenishment attribute value.
  • At least one shipment interval of the currently pending item can be obtained, and the replenishment attribute value of the pending item can be obtained by processing the shipment interval, the preset quantile, the number of shipments, and the first duration.
  • the replenishment attribute value of the item currently to be processed is determined, including: according to the minimum value of the days between shipments, the preset The product of the quantile and the number of shipments is used to obtain the first data value; based on the ratio of the first duration to the first data value, the replenishment attribute value of the current item to be processed is determined.
  • the minimum value of the target shipment interval may be obtained from at least one number of days between shipments corresponding to the current item to be processed. Calculate the product of the target shipment interval, the preset quantile, and the number of shipments to obtain an intermediate value, that is, the first data value. By calculating the ratio between the first duration and the first data value, the replenishment attribute value of the item currently to be processed is obtained.
  • the second implementation manner may be: determining the replenishment attribute value of the current item to be processed based on the target quantile sub-estimation method, including: if the target quantile sub-estimation method is the second quantile sub-estimation method , then determine the target quantile point according to the preset quantile and the shipment related information; determine the replenishment attribute value of the current item to be processed according to the target quantile point and the first duration.
  • the target quantile point can be determined according to the shipment interval time and the preset quantile in the shipment related information. By calculating the wallpaper between the first duration and the target quantile point, the replenishment attribute value of the item to be processed is obtained.
  • the determining the target quantile point according to the preset quantile and shipment related information includes: fitting the target empirical distribution according to the number of days between shipments in the shipment related information ; Determine the target quantile point according to the preset quantile and the target empirical distribution.
  • the target empirical distribution of the item to be processed can be obtained by fitting according to the related information of the shipment volume of the item to be processed currently. According to the preset quantile and the target empirical distribution, the target quantile corresponding to the preset quantile can be determined. For each item to be processed, the above method can be used to determine the corresponding target quantile point.
  • the set Inv of shipping interval days can be obtained for the historical sales volume of each SKU, and the length of each shipping interval in the interval number set Inv can be used as a sample to fit an empirical distribution.
  • the target quantile is determined to be 19.8.
  • the sales interval ⁇ quantiles of all SKUs can be obtained by the above method.
  • the input parameter is the number k of days from the last sale, that is, the first duration k.
  • a target empirical distribution F corresponding to the current item to be processed may be obtained by fitting based on at least one shipping interval of the item currently to be processed. Based on the preset quantile point ⁇ of the empirical distribution F, the target quantile d ⁇ is obtained. If the preset quantile point is less than or equal to the reciprocal of the number of shipments, the first quantile sub-estimation method will be used; if the preset quantile point is greater than the reciprocal of the number of shipments, the second quantile sub-estimation method will be used.
  • the first sub-estimation quantile method is: the mean value estimation method is used to determine whether SKUs with relatively uniform sales intervals trigger replenishment. For SKUs with uneven distribution of sales intervals, a more general calculation method, that is, quantile fixed value method, can be proposed.
  • the historical sales data set H of the SKU in the past 60 days is known.
  • the sample set of the interval days between two sales can be obtained from H as Thus, the empirical distribution F of the interval days D is obtained.
  • N is The length of , that is, the number of shipments, Indicates the minimum value of the current delivery interval of items to be processed, and ⁇ indicates the preset quantile point.
  • the replenishment level calculation is triggered, that is, the target replenishment quantity determination model is used to process the replenishment attribute value to obtain the target replenishment quantity; if p i (k) ⁇ p 0 , The target replenishment quantity is 0.
  • the net inventory level corresponding to the current time can be determined.
  • the net inventory can be the remaining inventory in the warehouse minus the sold ones.
  • the target replenishment quantity of the corresponding item to be processed can be determined.
  • the technical solution of the embodiment of the present application can determine the target data processing method corresponding to each item to be processed according to the shipment related information, and then determine the replenishment attribute value of the corresponding item to be processed according to the target data processing method, which improves the The accuracy rate of the determination of the replenishment attribute value, thereby achieving the technical effect of effectively controlling the item inventory of the item to be processed.
  • FIG. 5 is a schematic flowchart of another method for controlling inventory of items provided by the embodiment of the present application.
  • the target inventory of the corresponding target item to be processed can be determined according to the replenishment attribute value, and then the target replenishment amount can be determined based on the target inventory amount , in order to achieve effective control of inventory costs.
  • technical terms that are the same as or corresponding to those in the foregoing embodiments will not be repeated here.
  • the method includes:
  • S510 Determine at least one item to be processed according to the shipment volume associated information of each item.
  • the technical solution can be applied to intermittently shipped items.
  • the binomial distribution method can be used to determine the occurrence probability of demand for each item at the current time, that is, the replenishment attribute value of the item at the current time.
  • the objective function for calculating the target inventory is determined, that is, the target inventory determination model.
  • the target inventory determination model is a preset mathematical model.
  • the mathematical model can be a derivative function.
  • the mathematical model looks like this:
  • h is the inventory holding cost and is a known value
  • T represents the preset period for determining the replenishment attribute value of the item to be processed
  • p represents the determined replenishment attribute value
  • b represents the out-of-stock cost, and this cost is a known value
  • L indicates the preset advance time, and the unit of time is days
  • r indicates the current time is the number of days in the cycle
  • k indicates the first time, that is, the interval between the current time and the previous shipment
  • ⁇ D,k (S) represents the cumulative distribution function of Chint distribution, which is a known function.
  • the derivative function is an increasing function, so when the value of the derivative function is 0, the corresponding extreme value can be the target inventory of the target item to be processed.
  • ⁇ D,k (S) is the probability density function of the sales volume. Since the shipment volume obeys the normal distribution, it is the probability density function of the normal distribution.
  • the target replenishment amount of the corresponding item to be processed can be determined according to the replenishment attribute value of each item to be processed, that is, for different items to be processed, the corresponding target replenishment amount is Different, it solves the technical problem that in the related technology, different target replenishment quantities are randomly set for different items, or the same target inventory quantity is set, which does not match the actual situation, resulting in the inability to effectively control the inventory cost.
  • FIG. 6 is a schematic flowchart of another method for controlling inventory of items provided in the embodiment of the present application. As shown in Figure 6, the method includes:
  • the first module may be a data preprocessing model configured to determine items to be processed. For example, the historical sales data of each item is obtained, and the items to be processed are determined according to the historical sales data of each item, that is, item screening is performed. Get historical sales time series data for each item within a preset period of time. Determine the number of days between sales between two adjacent sales based on historical sales time series data. According to the sales interval days of each item, determine the mean and variance of the sales interval; according to the mean and variance of the sales interval of each item, determine the coefficient of variation of the corresponding item. Items whose coefficient of variation is smaller than the preset threshold value of coefficient of variation are regarded as items to be processed, that is, the list of items to be processed with a smaller coefficient of variation is screened out.
  • the second module is the adoption calculation module, which is set to obtain the historical sales data of each item to be processed in the list of items to be processed, and determine the number of days between sales according to the historical sales data. According to the sales interval days of each item, an empirical distribution can be fitted, and the target quantile point can be calculated according to the empirical distribution.
  • the third module is the inventory strategy operation module, which is mainly set to determine the existing inventory and the target inventory, and determine the target replenishment amount according to the existing inventory and the target inventory.
  • For each item determine the number of days between the current item and the previous sales interval at the current time, and determine the replenishment attribute value corresponding to the current item at the current time according to the target quantile. If the replenishment attribute value is greater than the preset replenishment attribute threshold, it is determined that the current item to be processed is the target item to be processed.
  • the fourth module is the result output module.
  • the replenishment attribute value of the current target item to be processed can be input into the pre-obtained target inventory determination model to obtain the corresponding value of the current target item to be processed.
  • Target replenishment volume According to the target replenishment amount and the net inventory of the current target items to be processed, the target replenishment amount can be determined. For example, if the net inventory is greater than the target inventory, no replenishment is required; if the net inventory is less than the preset target inventory , then the target replenishment quantity can be determined based on the difference between the target inventory quantity and the net inventory quantity.
  • the replenishment attribute value of each item to be processed can be determined according to the current time and the shipment related information of each item to be processed. If there is a replenishment attribute value greater than the preset replenishment attribute threshold value of the target item to be processed, the replenishment attribute value of the target item to be processed can be used as the input of the target inventory determination model to determine the target inventory corresponding to the target item to be processed, and then based on the target inventory and the target to be processed.
  • the existing net inventory of the item at the current time determines the target replenishment amount, which solves the problem that the inventory amount of the item in the related technology is randomly determined or fixed, resulting in the determined replenishment amount and the actual required amount Inappropriate, which caused the problem of high inventory cost, realized the determination of the target replenishment amount based on the related information of the shipment volume of the items to be processed, improved the accuracy of determining the target replenishment amount, and effectively controlled the inventory cost technical effect.
  • FIG. 7 is a schematic structural diagram of a business data processing device provided by an embodiment of the present application. As shown in FIG.
  • the acquisition and calculation module 710 is configured to determine the replenishment attribute value of the current item to be processed according to the current time and the shipment related information of the item to be processed for each item to be processed; the inventory strategy calculation module 720 is configured to If it is detected that there is a target to-be-processed item whose replenishment attribute value is greater than the preset replenishment attribute threshold, the target of the target to-be-processed item is determined according to the replenishment attribute value of the target to-be-processed item and the target inventory determination model The inventory quantity; the result output module 730 is configured to determine the target replenishment quantity of the target item to be processed according to the net inventory quantity corresponding to the target inventory quantity and the current time.
  • the shipment related information includes the shipment date and the shipment volume corresponding to the shipment date
  • the device also includes an item determination module to be processed, which is configured to Quantity-related information, before determining at least one item to be processed, it is also set to: determine the shipping interval between two adjacent shipments of each item according to the shipping date and corresponding shipping volume of each item, and calculate all The above-mentioned shipment interval is updated to the shipment-related information of the corresponding item.
  • the item-to-be-processed determination module is set to the shipment volume associated information for each item, and when it is detected that the shipment volume of the current item is greater than the preset shipment volume threshold, then Determine the shipping date to be processed corresponding to the shipment amount; determine the time interval between two adjacent shipments of each item according to the shipping date to be processed corresponding to each item.
  • the device further includes: a data preprocessing module configured to determine at least one item to be processed according to the shipment volume associated information of each item.
  • the data preprocessing module is also set to:
  • the data preprocessing module is set to:
  • For the shipping interval of each item according to at least one shipping interval corresponding to the current item, determine the mean value of the time interval and the variance of the time interval; according to the mean value of the time interval and the variance of the time interval corresponding to each item, determine The coefficient of variation of an item.
  • the data preprocessing module is set to:
  • the acquisition and calculation module 710 is set to:
  • the acquisition and calculation module 710 is set to:
  • the data processing method is a mean value estimation method; if the at least one shipping interval does not satisfy a preset uniform distribution, then determine that the target data processing method is a quantile estimation method.
  • the acquisition and calculation module 710 is set to:
  • the acquisition and calculation module 710 is set to:
  • the target data processing method is the mean value estimation method
  • the acquisition and calculation module 710 is set to:
  • the target data processing method is a quantile estimation method
  • determine the target quantile sub-estimation method based on the target quantile sub-estimation method, the first The duration and the related information of the shipment volume are processed to determine the replenishment attribute value of the item currently to be processed.
  • the collection and calculation module 710 is set to: if the preset quantile is less than or equal to the reciprocal of the number of shipments, determine that the target quantile sub-estimation method is the first quantile sub-estimation method; if the preset quantile is greater than the reciprocal of the number of shipments, then determine the target quantile sub-estimation method as the second quantile sub-estimation method.
  • the acquisition and calculation module 710 is set to:
  • the target quantile sub-estimation method is the first quantile sub-estimation method, then determine the replenishment attribute value of the current item to be processed according to the number of days between shipments, the preset quantile, the number of shipments, and the first duration.
  • the acquisition and calculation module 710 is set to:
  • the first data value is obtained; based on the ratio of the first time length to the first data value, the supplementary value of the current item to be processed is determined. Goods attribute value.
  • the acquisition and calculation module 710 is set to:
  • the target quantile sub-estimation method is the second quantile sub-estimation method, then determine the target quantile point according to the preset quantile and shipment related information; according to the target quantile point and the The first duration is to determine the replenishment attribute value of the item currently to be processed.
  • the acquisition and calculation module is further configured to: obtain the target empirical distribution by fitting according to the number of days between shipments in the shipment related information; Describe the target empirical distribution and determine the target quantile.
  • the inventory strategy calculation module 720 is set to:
  • the target data processing method corresponding to each replenishment attribute value determine the corresponding preset replenishment attribute threshold; when it is detected that there is a target pending item with a replenishment attribute value greater than the corresponding preset replenishment attribute threshold, then Determine the target inventory of the target item to be processed according to the replenishment attribute value and the target inventory determination model.
  • the inventory strategy calculation module 720 is set to:
  • replenishment attribute value as an input parameter of the target inventory determination model to determine the target inventory of the target item to be processed.
  • the replenishment attribute value of each item to be processed can be determined according to the current time and the shipment related information of each item to be processed. If there is a replenishment attribute value greater than the preset replenishment attribute threshold value of the target item to be processed, the replenishment attribute value of the target item to be processed can be used as the input of the target inventory determination model to determine the target inventory corresponding to the target item to be processed, and then based on the target inventory and the target to be processed.
  • the existing net inventory of the item at the current time determines the target replenishment amount, which solves the problem that the inventory amount of the item in the related technology is randomly determined or fixed, resulting in the determined replenishment amount and the actual required amount Inappropriate, which caused the problem of high inventory cost, realized the determination of the target replenishment amount based on the related information of the shipment volume of the items to be processed, improved the accuracy of determining the target replenishment amount, and effectively controlled the inventory cost technical effect.
  • the item inventory control device provided in the embodiment of the present application can execute the item inventory control method provided in any embodiment of the application, and has corresponding functional modules and effects for executing the method.
  • the multiple units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the names of multiple functional units are only for the convenience of distinguishing each other , which is not intended to limit the scope of protection of the embodiments of the present application.
  • FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 8 shows a block diagram of an exemplary electronic device 80 suitable for implementing the embodiments of the present application.
  • the electronic device 80 shown in FIG. 8 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.
  • electronic device 80 takes the form of a general-purpose computing device.
  • Components of the electronic device 80 may include, but are not limited to: one or more processors or processing units 801 , a system memory 802 , and a bus 803 connecting different system components (including the system memory 802 and the processing unit 801 ).
  • Bus 803 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include but are not limited to Industry Standard Architecture (Industry Standard Architecture, ISA) bus, Micro Channel Architecture (Micro Channel Architecture, MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (Video Electronics Standards Association, VESA) local bus and peripheral component interconnect (Peripheral Component Interconnect, PCI) bus.
  • Electronic device 80 includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 80 and include both volatile and nonvolatile media, removable and non-removable media.
  • System memory 802 may include computer system readable media in the form of volatile memory, such as random access memory (Random Access Memory, RAM) 804 and/or cache memory 805 .
  • Electronic device 80 may include other removable/non-removable, volatile/nonvolatile computer system storage media.
  • storage system 806 may be configured to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 8, commonly referred to as a "hard drive”).
  • a disk drive configured to read and write to a removable non-volatile disk (such as a "floppy disk") may be provided, as well as a removable non-volatile disk (such as a Compact Disc ROM (Compact Disc).
  • the memory 802 may include at least one program product, which has a set of (for example, at least one) program modules configured to execute the functions of the embodiments of the present application.
  • the program module 807 generally executes the functions and/or methods in the embodiments described in this application.
  • the electronic device 80 may also communicate with one or more external devices 809 (such as a keyboard, pointing device, display 810, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 80, and/or communicate with Any device (eg, network card, modem, etc.) that enables the electronic device 80 to communicate with one or more other computing devices. Such communication may be performed through an input/output (Input/Output, I/O) interface 811 .
  • the electronic device 80 can also communicate with one or more networks (such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN) and/or a public network, such as the Internet) through the network adapter 812.
  • networks such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN) and/or a public network, such as the Internet
  • network adapter 812 communicates with other modules of electronic device 80 via bus 803 .
  • other hardware and/or software modules may be used in conjunction with electronic device 80, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays of Independent Disks, RAID) systems, tape drives, and data backup storage systems.
  • the processing unit 801 executes a variety of functional applications and data processing by running the programs stored in the system memory 802, for example, implementing the method for controlling the inventory of items provided in the embodiment of the present application.
  • the embodiment of the present application also provides a storage medium containing computer-executable instructions, and the computer-executable instructions are used to implement a method for controlling item inventory when executed by a computer processor.
  • the method includes:
  • For each item to be processed determine the replenishment attribute value of the current item to be processed according to the current time and the shipment volume associated information of the current item to be processed; if it is detected that the replenishment attribute value is greater than the preset replenishment attribute threshold , then determine the target inventory of the target item to be processed according to the replenishment attribute value and the target inventory determination model; for each target item to be processed, according to the target inventory of the current target item to be processed Quantity and the net inventory corresponding to the current time to determine the target replenishment quantity of the current target item to be processed.
  • the computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media.
  • the computer readable medium may be a computer readable signal medium or a computer readable storage medium.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. Examples (non-exhaustive list) of computer readable storage media include: electrical connection with one or more conductors, portable computer disk, hard disk, RAM, ROM, Erasable Programmable Read Only Memory (Erasable Programmable Read Only Memory) , EPROM or flash memory), optical fiber, CD-ROM, optical storage device, magnetic storage device, 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 carrying computer readable program code in baseband or as part of a carrier wave. 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 wireless, wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.
  • any appropriate medium including but not limited to wireless, wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.
  • Computer program codes for performing the operations of the embodiments of the present application may be written in one or more programming languages or combinations thereof, the programming languages including object-oriented programming languages—such as Java, Smalltalk, C++, including A conventional procedural programming language - such as "C" or a similar programming language.
  • 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 can be connected to the user computer through any kind of network, including a LAN or WAN, or it can be connected to an external computer (eg via the Internet using an Internet Service Provider).

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Fuzzy Systems (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Human Resources & Organizations (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • General Factory Administration (AREA)

Abstract

本申请提供了一种物品库存的控制方法、装置、设备及介质。该物品库存的控制方法包括：针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定当前待处理物品的补货属性值；如果检测到存在补货属性值大于预设补货属性阈值的目标待处理物品，则根据补货属性值和目标库存量确定模型，确定目标待处理物品的目标库存量；针对每个目标待处理物品，根据当前目标待处理物品的目标库存量与当前时间所对应的净库存量，确定目标待处理物品的目标补货量。

Description

物品库存的控制方法、装置、设备及介质
本申请要求在2021年11月25日提交中国专利局、申请号为202111413044.3的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及计算机技术领域，例如涉及一种物品库存的控制方法、装置、设备及介质。
背景技术
为了满足用户对不同物品的需求，每个物品都会有一定的库存。每个物品的库存都是随机确定的，如，在一个时间检查物品的库存量小于预设阈值时，则获取相应物品；或者是，每间隔一定的时长，获取一定量的物品并存储。
上述方式存在如下问题：
用户对不同物品的需求程度不同，相应的，不同物品所对应的库存需求也是不同的，因此针对不对的物品来说，其库存量应该是存在一定的差异的，且库存量应与物品的需求相匹配。
但是，上述方式中不同物品的库存都是随机确定的，而且大多数物品的目标库存量都是相同的，因此存在库存成本较高以及供货不足的问题。
发明内容
本申请提供一种物品库存的控制方法、装置、设备及介质，以实现对库存成本进行有效控制的技术效果。
第一方面，本申请提供了一种物品库存的控制方法，该方法包括：
针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值；
如果检测到存在补货属性值大于预设补货属性阈值的目标待处理物品，则根据所述补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量；
针对每个目标待处理物品，根据当前目标待处理物品的目标库存量与当前时间所对应的净库存量，确定所述目标待处理物品的目标补货量。
第二方面，本申请还提供了一种物品库存控制装置，该装置包括：
采集计算模块，设置为针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值；
库存策略运算模块，设置为如果检测到存在补货属性值大于预设补货属性阈值的目标待处理物品，则根据所述补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量；
结果输出模块，设置为针对每个目标待处理物品，根据所述目标库存量与当前时间所对应的净库存量，确定所述目标待处理物品的目标补货量。
第三方面，本申请还提供了一种电子设备，所述电子设备包括：
一个或多个处理器；
存储装置，设置为存储一个或多个程序；
当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现上述的物品库存的控制方法。
第四方面，本申请还提供了一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行上述的物品库存的控制方法。
附图说明
图1为本申请实施例所提供的一种物品库存的控制方法的流程示意图；
图2为本申请实施例所提供的一种从多个物品中确定待处理物品的流程示意图；
图3为本申请实施例所提供的一种物品库存的控制方法的流程示意图；
图4为本申请实施例所提供的一种补货竖屏计算逻辑的流程示意图；
图5为本申请实施例所提供的另一种物品库存的控制方法的流程示意图；
图6为本申请实施例所提供的另一种物品库存的控制方法的流程示意图；
图7为本申请实施例所提供的一种业务数据处理装置的结构示意图；
图8为本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作说明。此处所描述的具体实施例仅仅用于解释本申请，为了便于描述，附图中仅示出了与本申请相关的部分。
图1为本申请实施例所提供的一种物品库存的控制方法的流程示意图，本 实施例可适用于确定每个物品的补货量，进而基于补货量有效对库存成本进行控制的情况，该方法可以由物品库存的控制装置来执行，该装置可以通过软件和/或硬件的形式实现，该硬件可以是电子设备，电子设备可以是移动终端、个人电脑(Personal Computer，PC)端等。该技术方案的执行可以由服务器执行、也可以由终端设备来执行、还可以由服务器和终端设备配合执行。
在介绍本申请实施例技术方案之前，可以先对应用场景进行示例性说明。在实际生活中，一些物品的出货频率较高，出货量较多，此种类型的物品可以设定目标库存量以及相应的补货周期。同时，也可以采用本申请实施例所提供的技术方案，确定每个物品的目标库存量，进而根据已有库存量确定目标补货量。
如图1所示，所述方法包括：
S110、根据每个物品的出货量关联信息，确定至少一个待处理物品。
出货量关联信息中包括出货日期序列，和与每个出货日期相对应的出货量。出货日期可以是每天的日期，出货量可以是每天出售物品所对应的量，那么出货量可以是0也可以是大于0的任意数值。将根据出货量关联信息确定出的物品作为待处理物品。待处理物品可以是全部的物品，也可以是全部物品中的部分物品。例如，确定待处理物品的方式可以是：根据出货量关联信息，确定出货间隔天数。如果出货间隔天数大于预设间隔天数阈值的数量，则可以将该出货量关联信息对应的物品作为待处理物品。
至少一个待处理物品的数量可以包括一个、两个甚至多个，其数据是根据物品的出货量关联信息确定的。
本技术方案可以确定所有物品的目标补货量，尤其适用于满足一定条件的待处理物品的目标补货量，如，一些出货频率较低的物品，例如，汽车备件等。
可以在预设时间点获取每个物品的出货量关联信息。预设时间点可以是相对时间点，也可以是绝对时间点。相对时间点可以是每间隔一定的时长获取物品的出货量关联信息，例如，间隔时长可以是一星期。绝对时间点可以是每天的固定时间点，例如，固定时间点可以是每天的晚上十点获取每个物品的出货量关联信息。获取的出货量关联信息对应的物品可以是一个库存量单位(Stock Keeping Unit，SKU)所对应的物品，也可以是多个SKU所对应的物品，还可以是所有的物品。
在本实施例中，出货量关联信息中包括出货日期和与出货日期所对应的出货量，所述根据每个物品的出货量关联信息，确定至少一个待处理物品之前，还包括：根据每个物品的出货日期和相应的出货量，确定每个物品相邻两次出 货的出货间隔时长，并将所述出货间隔时长更新至相应物品的出货量关联信息中。
出货量关联信息中包括每个物品在每个日期的出货量，即包括时间序列和与时间序列中每个时间点对应的出货量，此时的时间主要是日期，时间序列中的日期为连续日期。在实际应用中，可能一个日期的出货量为0，会省略一个日期，此时可以将此日期添加在时间序列中，并将该日期的出货量标记为0。根据每个物品的出货日期和相应的出货量，确定相邻两次出货的出货间隔时长，可以将出货间隔时长作为出货量关联信息中的部分信息。
在本实施例中，确定出货间隔时长可以是：针对每个物品的出货量关联信息，当检测到当前物品的出货量大于预设出货量阈值时，则确定所述出货量对应的待处理出货日期；根据与每个物品所对应的待处理出货日期，确定每个物品相邻两次出货的出货间隔时长。
出货量中的数值可以是0，也可以是大于0的任意一个数据，其数据值是与当天的实际售出物品量相对应。
预设出货量阈值可以是0。如果一个出货日期所对应的出货量大于预设出货量阈值，则确定该出货日期为待处理出货日期。根据每个物品的每个待处理出货日期可以确定相邻两次出货的出货间隔时长，此时确定出的出货间隔时长的数量可以是0，也可以是大于0的任意数值。每个物品都存在一个与其相对应的出货间隔时长集合，每个出货间隔时长集合中包括至少一个出货间隔时长。即，出货间隔时长为出货间隔时长集合中的一个元素。
示例性的，可以获取一个SKU在12天的出货量关联信息，其中，每天的出货量依次可以是：H＝[0,1,0,0,0,0,0,0,0,10,0,0]。根据出货量关联信息可以确定出货间隔天数集合为Inv＝[2,8]。其中，2表示相邻两次出货的间隔时长为2天，8表示相邻两次出货的间隔时长为8天。由于最后几天该SKU没有售出，所以最后部分的0不计入发生销售的间隔天数。
在上述技术方案的基础上，在确定与每个物品相对应的出货间隔天数之后，所述方法还包括：根据与每个物品对应的至少一个出货间隔时长，确定相应物品的变异系数；根据预设变异系数阈值和每个变异系数，确定至少一个待处理物品。
变异系数用于表征物品出货间隔波动，通常，变异系数越小，说明物品销售间隔波动越小，相应的，变异系数越大，说明物品销售间隔波动越大。预设变异系数阈值为根据理论数据设置的值。根据每个物品的变异系数和预设变异系数阈值，确定待处理物品，例如，可以将变异系数大于预设变异系数阈值的 物品作为待处理物品。
在本实施例中，确定每个物品所对应的变异系数可以是：针对每个物品的出货间隔时长，根据与当前物品相对应的至少一个出货间隔时长，确定时长间隔均值和时长间隔方差；根据每个物品所对应的时长间隔均值和时长间隔方差，确定每个物品的变异系数。
针对每个待处理物品的出货量关联信息，可以根据当前物品出货量关联信息中的出货间隔时长，计算得到时长间隔均值，同时，可以计算得到时长间隔方差。基于时长间隔方差和时长间隔均值之间的比值，确定变异系数。在本实施例中，可以将变异系数小于预设变异系数阈值的物品作为所述待处理物品。
在本实施例中，根据变异系数确定待处理物品的好处在于：可以从所有物品中确定出间歇性销售的物品，从而实现了对间歇性出售的物品进行处理的技术效果。
S120、针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值。
当前时间可以为当前日期。补货属性值用于表征当前时间当前待处理物品需要补货的急需程度。如果补货属性值较高，说明需要对当前待处理物品进行补货，如果补货属性值较小，说明不需要对当前待处理物品进行补货。
针对每个待处理物品，可以根据当前时间与待处理物品的出货日期和出货量，确定每个待处理物品的补货属性值，以根据补货属性值确定是否对待处理物品进行补货。
S130、如果检测到存在补货属性值大于预设补货属性阈值的目标待处理物品，则根据所述目标待处理物品的补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量。
预设补货属性阈值为预先确定的，可以将其作为确定是否进行补货的参考标准。目标待处理物品为需要对其进行补货的待处理物品。目标库存量确定模型为预先确定的数学模型，用于根据每个待处理物品的补货属性值确定该待处理物品的目标库存量。目标库存量可以为相应当前物品应该有的库存量。
不同待处理物品的目标库存量可以相同，也可以不同，其是否相同与待处理物品的补货属性值相关。也就是说，目标库存量的数值由每个目标待处理物品的目标补货属性值确定的。
在确定每个待处理物品的补货属性值后，可以确定补货属性值中是否存在大于预设补货属性阈值的待处理物品。如果存在补货属性值大于预设补货属性阈值的待处理物品，可以将此待处理物品作为目标待处理物品。针对每个目标 待处理物品，可以将当前目标待处理物品的补货属性值输入至目标库存量确定模型中，得到与当前目标待处理物品相对应的目标库存量。对于其他目标待处理物品可以采用相同的方式对其进行处理，从而得到与其相对应的目标库存量。
S140、针对每个目标待处理物品，根据当前目标待处理物品的目标库存量与当前时间所对应的净库存量，确定所述当前目标待处理物品的目标补货量。
每个待处理物品存在一个与其相对应的目标库存量。目标库存量的数目可以相同也可以不同。目标补货量是根据确定的目标库存量和相应的净库存量确定的。
针对每个目标待处理物品，通过计算当前目标待处理物品的目标库存量和与当前时间所对应的净库存量的差值，确定当前待处理目标物品的目标补货量。
本申请实施例的技术方案，主要是依据(T，S)策略确定。
本申请实施例的技术方案，通过根据当前时间以及每个待处理物品的出货量关联信息，可以确定每个待处理物品的补货属性值，如果存在补货属性值大于预设补货属性阈值的目标待处理物品，则可以将目标待处理物品的补货属性值作为目标库存量确定模型的输入，确定与目标待处理物品相对应的目标库存量，进而基于目标库存量和目标待处理物品在当前时间已有的净库存量，确定目标补货量，解决了相关技术中物品的库存量是随机确定的，或者是固定的，导致确定出的补货量与实际所需的货量不适配，从而引起库存成本较高的问题，实现了根据每个待处理物品的出货量关联信息，确定目标补货量，提高了确定目标补货量的准确率，以及对库存成本有效控制的技术效果。
图2为本申请实施例所提供的一种从多个物品中确定待处理物品的流程示意图。本技术方案可以确定每个物品在每个日期的目标库存量，尤其适用于确定间歇性出售的物品的目标库存量。因此在确定间歇性出售物品的目标库存量之前，可以先确定间歇性出售的物品，即待处理物品。其中，与上述实施例相同或相应的技术术语在此不再赘述。
如图2所示，所述方法包括：
S210、根据每个物品的历史出货量关联信息，确定每个物品相邻两次出货的出货间隔天数集合。
在实际应用过程中，用户可以设置相应的筛选条件，如，筛选条件为获取品类为A的物品，并从品类为A的物品中确定出待处理物品。当然，也可以是从所有物品中确定出待处理物品。
可以获取每个物品的在预设时长内的出货量关联信息，例如，出货日期为两个月内的日期，并确定与每个出货日期所对应的出货量。将出货量大于预设出货量阈值的出货日期作为待处理出货日期，并确定相邻两个日期的出货间隔天数，将每个出货间隔天数作为出货间隔天数集合中的一个元素。
示例性的，预设时长可以是12天，每个日期的出货量分别是H＝[0,1,0,0,0,0,0,0,0,10,0,0]。基于出货量可以确定第二天、第十天有出货量，可以确定相邻两次出货间隔天数为2和8，相应的，出货间隔天数集合为Inv＝[2,8]。因为最后几天该SKU没有售出，所以最后部分的0不计入发生出货的间隔天数。
S220、根据每个物品的出货间隔天数集合，确定每个物品的时长间隔均值和时长间隔方差。
示例性的，如果物品的出货间隔天数分别为2和8，则计算得到的间隔天数均值为5，间隔天数方差为3。即，时长间隔均值为5，时长间隔方差为3，其单位为天。
S230、根据每个物品的间隔时长均值和间隔时长方差，确定与相应物品相对应的变异系数。
示例性的，在确定每个物品的间隔时长均值和间隔时长方差之后，通过计算每个物品的间隔时长方差和间隔时长均值之间的比值，得到变异系数。如，SKUA＝3/5＝0.6，即SKUA的变异系数为0.6。
S240、将变异系数小于预设变异系数阈值的物品，作为待处理物品。
通常，变异系数用于表征物品销售间隔的波动。变异系数越小说明销售间隔波动越小，变异系数越大，销售间隔波动越大。
在实际应用的过程中，如果物品的销售间隔波动较大，那么此物品在一个时间的出货量是不好预测的，因此可以针对销售间隔波动不大的物品进行处理。
可以将变异系数小于预设变异系数阈值的物品，作为待处理物品。可以将待处理物品添加至物品列表中，以定时确定物品列表中的物品是否需要补货，从而有效对库存成本进行控制。
当变异系数小于预设变异系数阈值，说明待物品的出货间隔波动不大。可以将出货间隔不大的物品作为间歇性出售的待处理物品。本实施例可以对间歇性出售的待处理物品进行处理，以确定与每个待处理物品相对应的目标库存量，进而确定相应待处理物品的目标补货量，从而有效的对库存成本进行控制的技术效果。
本申请实施例的技术方案，通过对每个物品的出货量关联信息进行处理， 可以确定与每个物品相对应的至少一个出货间隔天数。根据与每个物品所对应的至少一个出货间隔天数，可以确定每个物品的变异系数，以根据变异系数确定待处理物品，本技术方案提高了确定间隔出售物品的目标库存量，进而达到根据目标库存量和已有库存量对每个待处理物品的库存成本进行有效控制的技术效果。
图3为本申请实施例所提供的一种物品库存的控制方法的流程示意图，在前述实施例的基础上，可以对确定每个待处理物品的补货属性值进行说明，其实施方式可参见本实施例的阐述。其中，与上述实施例相同或者相应的技术术语在此不再赘述。
如图3所示，所述方法包括：
S310、根据每个物品的出货量关联信息，确定至少一个待处理物品。
S320、根据所述当前待处理物品的出货量关联信息，确定目标数据处理方式。
目标数据处理方式可以为确定当前待处理物品的补货属性值的处理方式。对于不同的出货量关联信息来说，对其所采用的数据处理方式也不尽相同，为了提高对库存成本的有效控制，可以采用不同的数据处理方式对出货量关联信息进行处理。
在确定出待处理物品后，可以根据待处理物品的出货量关联信息，确定对出货量关联信息进行处理的处理方式，并将此种处理方式作为目标数据处理方式，从而基于目标数据处理方式对相应待处理物品的出货量关联信息进行处理，得到相应待处理物品的补货属性值。
在本实施例中，根据出货量关联信息确定目标数据处理方式可以是：根据所述出货量关联信息中的每个出货日期所对应的出货量，确定至少一个出货间隔时长；如果所述至少一个出货间隔时长满足预设均匀分布，则确定所述目标数据处理方式为均值估计方式；如果所述至少一个出货间隔时长不满足预设均匀分布，则确定所述目标数据处理方式为分位数估计方式。
如果至少一个出货间隔时长集中在一个数值范围内，则可以确定出货间隔时长比较均匀，此时可以确定出货间隔时长满足均匀分布。方差可以表征数值的波动程度，确定是否满足均匀分布还可以是确定时长间隔方差是否小于预设阈值，如果时长间隔方差小于预设阈值，则说明该待处理物品的出货间隔时长满足均匀分布，如果时长间隔方差不小于预设阈值，则说明该待处理物品的出货间隔时长不满足均匀分布。将满足预设均匀分布时所采用的数据处理方式作 为均值估计方式，将不满足预设均匀分布所采用的数据处理方式作为分位数估计方式。分位数估计方式为根据出货量关联信息，确定分位点，进而基于分位点确定补货属性值。均值估计方式为根据出货量关联信息中的出货间隔时长均值和出货间隔时长方差确定的。
在对每个待处理物品进行处理时，可以先根据待处理物品的出货量关联信息中的出货间隔时长，确定与其相对应的目标数据处理方式，以基于目标数据处理方式确定相应待处理物品的补货属性值。
S330、基于所述目标数据处理方式对所述当前时间以及出货量关联信息进行处理，得到所述当前待处理物品的补货属性值。
补货属性值用于表征待处理物品需要补货的程度，如，补货属性值越大说明需要对待处理物品进行补货的需求就越大，补货属性值越小，说明待处理物品需要补货的需求较小。
在确定与每个待处理物品相对应的目标数据处理方式后，可以基于目标数据处理方式对待处理物品的出货量关联信息进行处理，以得到相应待处理物品的补货属性值。
在本实施例中，可以在确定补货属性值之前，可以先确定与待处理物品相对应的其它关联信息，进而采用目标数据处理方式，得到补货属性值。例如，确定所述出货量关联信息中出货量大于预设出货量阈值，且与当前时间间隔最小的待使用出货日期；根据所述当前时间所对应的日期以及所述待使用出货日期，确定第一时长；基于所述目标数据处理方式对所述第一时长以及所述出货量关联信息进行处理，得到当前待处理物品的补货属性值。
当前时间主要是指当前日期。第一时长主要是当前时间和待使用出货日期的时长间隔。待使用出货日期可以是距离当前时间最近且发生销售的日期，例如，当前日期为6.20号，当前日期之前最后一次发生销售的日期为5.31号，那么待使用日期为5.31号。相应的，第一时长为20天。预设出货量阈值可以是0。
针对每个待处理物品，可以根据当前待处理物品的出货量关联信息中的出货间隔时长，确定距离当前时间距离最小且出货量大于预设出货量阈值的待使用出货日期。根据当前日期以及待使用出货日期，可以确定第一时长。通过对第一时长以及出货量关联信息进行处理，可以确定当前待处理物品的补货属性值。
在本实施例中，目标数据方式包括上述两种方式中的任意一种，相应的，基于目标数据处理方式对相应待处理物品的出货量关联信息进行处理的处理方式，参见下述表述：
第一种实施方式可以是：均值估计方式。基于所述均值估计方式对所述第一时长和根据出货间隔时长确定的时长间隔方差进行处理，确定当前待处理物品的补货属性值。
如果当前待处理物品的目标处理方式为均值估计方式，则可以根据出货间隔时长确定出货间隔时长方差，以及出货间隔时长均值。通过计算第一时长和出货间隔时长方差的比值，得到当前待处理物品的补货属性值。
示例性的，k是随着日期变化的变量，例如上一次发生销售的日期是2021年3月1日，在2021年3月6日检查库存时，第一时长k＝5。如果在3月6日给出当天一个SKU的补货建议，可以确定该SKU历史60天的出货间隔天数为[10,25,12]，计算出货间隔时长均值
Figure PCTCN2022131900-appb-000001
向上取整为16。通过计算第一时长和出货间隔时长均值之间的比值，可以得到该SKU的补货属性值，如
Figure PCTCN2022131900-appb-000002
即得到该SKU补货属性值为0.3125。
第二种实施方式可以是：分位数估计方式。分位数估计方式中包括两种子方式，可以根据出货量关联信息确定相应的子估计方式。
如果所述目标数据处理方式为分位数估计方式，则根据所述出货量关联信息和预设分位数，确定目标分位数子估计方式；基于目标分位数子估计方式对所述第一时长以及所述出货量关联信息进行处理，确定所述当前待处理物品的补货属性值。
待处理物品的出货量关联信息可以确定对待处理物品处理时，所采用的处理方式。
在本实施例中，根据出货量关联信息确定目标分位数子估计方式可以是：出货量关联信息中包括与出货间隔时长相对应出货次数，所述根据所述出货量关联信息和预设分位数，确定目标分位数子估计方式，包括：
如果所述预设分位数小于或等于出货次数的倒数，则确定目标分位数子估计方式为第一分位数子估计方式；如果所述预设分位数大于出货次数的倒数，则确定目标分位数子轨迹方式为第二分位数子估计方式。
每个待处理物品都存在与其相对应的出货次数。出货次数可以为在预设时长内，销售出物品的次数。也就是说，可以根据出货量关联信息中出货间隔天数所对应的次数，确定出货次数，即出货次数与出货间隔天数所对应的个数相同。预设分位数是用户根据实际需求设置的百分数，可选的，百分数可以是0.8。
在确定当前待处理物品所对应的目标数据处理方式为目标分位数子估计方式时，可对当前待处理物品的出货量关联信息中的出货间隔时长进行拟合，得到经验分布。如果预设分位数小于或等于出货次数的倒数，则说明一定时长内 的出货次数较小，此时可以采用第一分位数子估计方式确定当前待处理物品的补货属性值。如果预设分为大于出货次数的阈值，则可以采用第二分位数子估计方式确定补货属性值。在本实施例中，确定与不同待处理物品相对应的子估计方式，提高了对待处理物品补货属性值确定的准确性。
接下来阐述采用不同的分位数子估计方式如何对待处理物品的出货关联信息进行处理，以得到待处理物品的补货属性值。
第一种实施方式可以是：如果所述目标分位数子估计方式为第一分位数子估计方式，则根据出货间隔天数、预设分位数、出货次数以及第一时长，确定当前待处理物品的补货属性值。
针对每个待处理物品来说，都存在至少一个与其相对应的出货间隔天数。可以获取当前待处理物品的至少一个出货间隔天数，并通过对出货间隔天数、预设分位数、出货次数以及第一时长进行处理，可以得到待处理物品的补货属性值。
在本实施例中，根据出货间隔天数、预设分位数、出货次数以及第一时长，确定当前待处理物品的补货属性值，包括：根据出货间隔天数的最小值、预设分位数以及出货次数的乘积，得到第一数据值；基于所述第一时长与所述第一数据值的比值，确定当前待处理物品的补货属性值。
针对当前待处理物品，可以从与当前待处理物品相对应的至少一个出货间隔天数中获取最小数值的目标出货间隔时长。计算目标出货间隔时长、预设分位数以及出货次数的乘积，得到中间值，即第一数据值。通过计算第一时长与第一数据值之间的比值，得到当前待处理物品的补货属性值。第二种实施方式可以是：所述基于目标分位数子估计方式，确定所述当前待处理物品的补货属性值，包括：如果所述目标分位数子估计方式为第二分位数子估计方式，则根据所述预设分位数和出货量关联信息，确定目标分位点；根据所述目标分位点和所述第一时长，确定当前待处理物品的补货属性值。
可以根据出货量关联信息中的出货间隔时长和预设分位数，确定目标分位点。通过计算第一时长和目标分位点之间的壁纸，得到待处理物品的补货属性值。
在采用第二分位数子估计方式确定补货属性值时，需要确定与该待处理物品相对应的目标分位点，进而基于目标分位点确定补货属性值。可选的，所述根据所述预设分位数和出货量关联信息，确定目标分位点，包括：根据所述出货量关联信息中的出货间隔天数，拟合得到目标经验分布；根据所述预设分位数和所述目标经验分布，确定目标分位点。
针对每个待处理物品，可以根据当前待处理物品的出货量关联信息拟合得到当前待处理物品的目标经验分布。根据预设分位数和目标经验分布，可以确定与预设分位数相对应的目标分位点。对于每个待处理物品均可以采用上述方式，确定与其相对应的目标分位点。
示例性的，可以针对每个SKU的历史销量获得的出货间隔天数集合Inv，间隔天数集合Inv中的每个出货间隔时长可以作为样本拟合出一个经验分布。可以根据经验分布获得一个α分位点，即预设分位点。例如Inv＝[10,25,12]，表示该SKU在过去的一段时间内(如60天)销售了3次，每次销售间隔的天数分别为10，25，12天，可以基于上述天数拟合得到一个与该SKU相对应的目标经验分布。基于目标经验分布和预设分位点α＝80％，确定目标分位点为19.8。由上述方法可以获得所有SKU的销售间隔α分位点。
取多少分位点在于企业对库存水平的期望。如果将α定的较大，说明企业认为的期望销售间隔时间会较长，应该补货的间隔也会延长；将α定的较小，说明企业认为的期望销售间隔时间会较短，应该补货的间隔也会缩短。也就是说，用户可以根据实际需求设置预设分位点。
为了了解每种分位数子估计方式对出货量关联信息进行处理的处理条件和方式，可以参见下述示例性说明。
示例性的，参见图4，输入参数，距离上次销售的间隔天数k，即第一时长k。可以基于当前待处理物品的至少一个出货间隔时长拟合得到与当前待处理物品对应的目标经验分布F。基于经验分布F的预设分位点α，得到目标分位数d α。如果预设分位点小于或等于出货次数的倒数，则采用第一分位数子估计方式，如果预设分位点大于出货次数的倒数，则采用第二分位数子估计方式。
第一子估计分位方式为：均值估计方式用于确定销售间隔较为均匀的SKU是否触发补货。对于销售间隔分布不均匀的SKU，可以提出采用一种更加普适的计算方法，即分位数定值法。对于随机变量D i，由历史数据可以得到一个销售间隔的样本，如
Figure PCTCN2022131900-appb-000003
根据样本可以拟合出一个经验分布，然后针对该经验分布给出一个80％分位数d 0.8＝19.2。已知该SKU过去60天的历史销量数据集合H。可以由H得到每两次发生销售的间隔天数样本集合如
Figure PCTCN2022131900-appb-000004
从而得到间隔天数D的经验分布F。由F可以计算出该SKU销售间隔的α分位数d α，如d 0.8＝19.2。将分位数的值代入公式p(k)。即，得到当前待处理物品在当前时间的补货属性值。
Figure PCTCN2022131900-appb-000005
由于目标SKU在过去60天可能销售次数很少，如
Figure PCTCN2022131900-appb-000006
此时设置 的α<0.3，那么通过拟合得到的经验分布F无法获得α分位数。此时需要通过如下方法计算p(k)：
Figure PCTCN2022131900-appb-000007
式中N是
Figure PCTCN2022131900-appb-000008
的长度，即出货次数，
Figure PCTCN2022131900-appb-000009
表示当前待处理物品出货间隔时长的最小值，α表示预设分位点。
若p(k)≥1则令S＝μ(μ表示预设目标补货量)，或者采用采用目标补货量确定模型，确定当前待处理物品的最优的S(目标补货量)；若p(k)<1，目标补货量为0，即不用确定目标补货量。
第二子估计分位方式：如果预设分位数大于出货次数的倒数，则可以采用第二子估计方式。例如上一次发生销售的日期是2021年3月1日，那么在2021年3月6日检查库存时，k＝5。接下来要在3月6日给出当天一个SKU的补货建议，步骤如下：假设该SKU历史60天的销售间隔天数采样为[10,25,12]，计算间隔天数的均值
Figure PCTCN2022131900-appb-000010
向上取整为16。因为当前k＝5，所以
Figure PCTCN2022131900-appb-000011
Figure PCTCN2022131900-appb-000012
事前设定一个阈值p 0＝0.5。若p i(k)≥p 0，则触发补货水平计算，即采用目标补货量确定模型，对补货属性值进行处理，得到目标补货量；若p i(k)<p 0，目标补货量为0。
基于上述可知，不同的数据处理方式，预设补货属性阈值也不相同。因此，在确定补货属性值之后，可以根据与数据处理方式相对应的补货属性值阈值，确定是否确定与其相对应的目标补货量，即当前待处理物品是否需要补货。
S340、根据所述目标库存量与当前时间所对应的净库存量，确定所述目标待处理物品的目标补货量。
可以确定当前时间所对应的净库存量。净库存量可以是仓库中当前已有的减去售出的，所剩余的库存量。通过计算目标库存量和净库存量的差值，可以确定相应待处理物品的目标补货量。
本申请实施例的技术方案，可以根据出货量关联信息，确定与每个待处理物品相对应的目标数据处理方式，进而根据目标数据处理方式确定相应待处理物品的补货属性值，提高了补货属性值确定的准确率，进而实现有效控制待处理物品的物品库存的技术效果。
图5为本申请实施例所提供的另一种物品库存的控制方法的流程示意图。在前述实施例的基础上，在确定每个目标待处理物品的补货属性值后，可以依据补货属性值确定相应目标待处理物品的目标库存量，进而基于目标库存量确 定目标补货量，以实现对库存成本进行有效控制。其中，与上述实施例相同或者相应的技术术语在此不再赘述。
如图5所示，所述方法包括：
S510、根据每个物品的出货量关联信息，确定至少一个待处理物品。
S520、针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值。
S530、如果检测到存在补货属性值大于预设补货属性阈值的目标待处理物品，则将补货属性值作为目标库存量确定模型的输入参数，确定目标待处理物品的目标库存量。
本技术方案可以适用于间歇性出货的物品。针对间歇性出货的物品，可以采用二项分布的方法确定每个物品在当前时间需求的发生概率，即物品在当前时间的补货属性值。再基于二项分布的基础上，确定计算目标库存量的目标函数，即目标库存量确定模型。
目标库存量确定模型为预先设置的数学模型。该数学模型可以是一个求导函数。该数学模型如下所示：
Figure PCTCN2022131900-appb-000013
式中，h库存持有成本，且为已知数值；T表示预先设置的确定待处理物品的补货属性值的周期；p表示确定出的补货属性值；b表示缺货成本，此成本为已知数值；L表示预先设置的提前时长，时长单位为天；r表示当前时间为周期中的第几天，k表示第一时长，即当前时间与前一次出货之间的间隔时长；Φ D,k(S)表示正泰分布的累计分布函数，为已知函数。
该导函数为一个递增函数，那么当导函数值为0时，所对应的极值可以为 目标待处理物品的目标库存量。
示例性的，令导数左边＝0，可以得到：
Figure PCTCN2022131900-appb-000014
可以对该式子进行数学变换：
Figure PCTCN2022131900-appb-000015
Figure PCTCN2022131900-appb-000016
Figure PCTCN2022131900-appb-000017
如果已知数据值分别为：h＝10，b＝20，L＝2，p＝0.6，将其代入，可得：
Figure PCTCN2022131900-appb-000018
Φ D,k(S)是销量的概率密度函数，由于出货量服从正态分布，那么它就是正态分布的概率密度函数。可以从历史数据中得到销量的均值和方差，如果均值为3，方差为1，则可以得到：Φ D,k(S)＝0.637。
求正态分布的逆函数，可以直接用python的正态分布函数包计算。代码如下：
from scipy.stats import norm
S＝(norm(3,1).ppf(0.637)
得到最优的S，此时S＝3.3505500627559512。
向上取整，取S＝4。即可以得到目标库存量为4。
S540、基于所述目标库存能量与当前时间所对应的净库存量的差值，确定所述目标待处理物品的目标补货量。
本申请实施例的技术方案，可以根据每个待处理物品的补货属性值，确定相应待处理物品的目标补货量，即对于不同待处理物品来说，与其相对应的目标补货量是不同的，解决了相关技术中为不同物品随机设置不同的目标补货量，或者设置相同的目标库存量时，与实际情况不相符，导致存在无法有效控制库存成本的技术问题，实现了有效对库存成本进行控制的技术效果。
作为上述实施例的一可选实施例，图6为本申请实施例所提供的另一种物品库存的控制方法的流程示意图。如图6所示，所述方法包括：
参见图6，确定目标待处理物品的目标补货量可以基于四个模块来实现。第一个模块可以是数据预处理模型，设置为确定待处理物品。例如，获取每个物品的历史销售数据，并根据每个物品的历史销售数据确定出待处理物品，即进行物品筛选。获取每个物品在预设时长内的历史销售时间序列数据。根据历史销售时间序列数据确定相邻两次销售的销售间隔天数。根据每个物品的销售间隔天数，确定销售间隔均值和方差；根据每个物品的销售间隔均值和方差，确定相应物品的变异系数。将变异系数小于预设变异系数阈值的物品作为待处理品，即筛选出变异系数较小的待处理物品列表。
第二个模块为采用计算模块，设置为获取待处理物品列表中的每个待处理物品的历史销售数据，并根据历史销售数据确定出销售间隔天数。根据每个物品的销售间隔天数可以拟合得到一个经验分布，根据经验分布计算目标分位点。
第三个模块为库存策略运算模块，该模块主要设置为确定现有库存量和目标库存量，并根据现有库存量和目标库存量，确定目标补货量。
针对每个物品，确定当前物品的在当前时刻距离前一销售间隔的天数，并根据目标分位点确定当前物品在当前时刻所对应的补货属性值。如果补货属性值大于预设补货属性阈值，则确定当前待处理物品为目标待处理物品。
第四个模块为结果输出模块，针对每个目标待处理物品，可以将当前目标待处理物品的补货属性值输入至预先得到的目标库存量确定模型中，得到与当前目标待处理物品对应的目标补货量。根据目标补货量和当前目标待处理物品的净库存量，可以确定目标补货量，例如，如果净库存量大于目标库存量，则 可以不用补货，如果净库存量小于预设目标库存量，则可以基于目标库存量和净库存量的差值，确定目标补货量。
本申请实施例的技术方案，通过根据当前时间以及每个待处理物品的出货量关联信息，可以确定每个待处理物品的补货属性值，如果存在补货属性值大于预设补货属性阈值的目标待处理物品，则可以将目标待处理物品的补货属性值作为目标库存量确定模型的输入，确定与目标待处理物品相对应的目标库存量，进而基于目标库存量和目标待处理物品在当前时间已有的净库存量，确定目标补货量，解决了相关技术中物品的库存量是随机确定的，或者是固定的，导致确定出的补货量与实际所需的货量不适配，从而引起库存成本较高的问题，实现了根据待处理物品的出货量关联信息，确定目标补货量，提高了确定目标补货量的准确率，以及对库存成本有效控制的技术效果。
图7为本申请实施例所提供的一种业务数据处理装置的结构示意图，如图7所述，所述装置包括：采集计算模块710、库存策略运算模块720、以及结果输出模块730。
采集计算模块710，设置为针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值；库存策略运算模块720，设置为如果检测到存在补货属性值大于预设补货属性阈值的目标待处理物品，则根据所述目标待处理物品的补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量；结果输出模块730，设置为根据所述目标库存量与当前时间所对应的净库存量，确定所述目标待处理物品的目标补货量。
在上述技术方案的基础上，出货量关联信息中包括出货日期和与出货日期所对应的出货量，所述装置还包括待处理物品确定模块，设置为根据每个物品的出货量关联信息，确定至少一个待处理物品之前，还设置为：根据每个物品的出货日期和相应的出货量，确定每个物品相邻两次出货的出货间隔时长，并将所述出货间隔时长更新至相应物品的出货量关联信息中。
在上述技术方案的基础上，所述待处理物品确定模块，设置为所述针对每个物品的出货量关联信息，当检测到当前物品的出货量大于预设出货量阈值时，则确定所述出货量对应的待处理出货日期；根据与每个物品所对应的待处理出货日期，确定每个物品相邻两次出货的出货间隔时长。
在上述技术方案的基础上，所述装置还包括：数据预处理模块，设置为根据每个物品的出货量关联信息，确定至少一个待处理物品。
在上述技术方案的基础上，所述数据预处理模块，还设置为：
根据与每个物品对应的至少一个出货间隔时长，确定相应物品的变异系数；
根据预设变异系数阈值和每个变异系数，确定至少一个待处理物品。
在上述技术方案的基础上，所述数据预处理模块，设置为：
针对每个物品的出货间隔时长，根据与当前物品相对应的至少一个出货间隔时长，确定时长间隔均值和时长间隔方差；根据每个物品所对应的时长间隔均值和时长间隔方差，确定每个物品的变异系数。
在上述技术方案的基础上，所述数据预处理模块，设置为：
将变异系数小于预设变异系数阈值的物品，作为所述待处理物品。
在上述技术方案的基础上，所述采集计算模块710，设置为：
根据所述当前待处理物品的出货量关联信息，确定目标数据处理方式；基于所述目标数据处理方式对所述当前时间以及出货量关联信息进行处理，得到所述当前待处理物品的补货属性值。
在上述技术方案的基础上，所述采集计算模块710，设置为：
根据所述出货量关联信息中的每个出货日期所对应的出货量，确定至少一个出货间隔时长；如果所述至少一个出货间隔时长满足预设均匀分布，则确定所述目标数据处理方式为均值估计方式；如果所述至少一个出货间隔时长不满足预设均匀分布，则确定所述目标数据处理方式为分位数估计方式。
在上述技术方案的基础上，所述采集计算模块710，设置为：
确定所述出货量关联信息中出货量大于预设出货量阈值，且与当前时间间隔最小的待使用出货日期；根据所述当前时间所对应的日期以及所述待使用出货日期，确定第一时长；基于所述目标数据处理方式对所述第一时长以及所述出货量关联信息进行处理，得到当前待处理物品的补货属性值。
在上述技术方案的基础上，所述采集计算模块710，设置为：
如果所述目标数据处理方式为均值估计方式，则基于所述均值估计方式对所述第一时长和根据出货间隔时长确定的时长间隔方差进行处理，确定当前待处理物品的补货属性值。
在上述技术方案的基础上，所述采集计算模块710，设置为：
如果所述目标数据处理方式为分位数估计方式，则根据所述出货量关联信息和预设分位数，确定目标分位数子估计方式；基于目标分位数子估计方式对所述第一时长以及所述出货量关联信息进行处理，确定所述当前待处理物品的 补货属性值。
在上述技术方案的基础上，所述采集计算模块710，设置为：如果所述预设分位数小于或等于出货次数的倒数，则确定目标分位数子估计方式为第一分位数子估计方式；如果所述预设分位数大于出货次数的倒数，则确定目标分位数子估计方式为第二分位数子估计方式。
在上述技术方案的基础上，所述采集计算模块710，设置为：
如果所述目标分位数子估计方式为第一分位数子估计方式，则根据出货间隔天数、预设分位数、出货次数以及第一时长，确定当前待处理物品的补货属性值。
在上述技术方案的基础上，所述采集计算模块710，设置为：
根据出货间隔时长的最小值、预设分位数以及出货次数的乘积，得到第一数据值；基于所述第一时长与所述第一数据值的比值，确定当前待处理物品的补货属性值。
在上述技术方案的基础上，所述采集计算模块710，设置为：
如果所述目标分位数子估计方式为第二分位数子估计方式，则根据所述预设分位数和出货量关联信息，确定目标分位点；根据所述目标分位点和所述第一时长，确定当前待处理物品的补货属性值。
在上述技术方案的基础上，所述采集计算模块，还设置为：根据所述出货量关联信息中的出货间隔天数，拟合得到目标经验分布；根据所述预设分位数和所述目标经验分布，确定目标分位点。
在上述技术方案的基础上，所述库存策略运算模块720，设置为：
根据每个补货属性值所对应的目标数据处理方式，确定相应的预设补货属性阈值；当检测到存在补货属性值大于相应的预设补货属性阈值的目标待处理物品时，则根据所述补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量。
在上述技术方案的基础上，所述库存策略运算模块720，设置为：
将所述补货属性值作为所述目标库存量确定模型的输入参数，确定所述目标待处理物品的目标库存量。
本申请实施例的技术方案，通过根据当前时间以及每个待处理物品的出货量关联信息，可以确定每个待处理物品的补货属性值，如果存在补货属性值大于预设补货属性阈值的目标待处理物品，则可以将目标待处理物品的补货属性值作为目标库存量确定模型的输入，确定与目标待处理物品相对应的目标库存 量，进而基于目标库存量和目标待处理物品在当前时间已有的净库存量，确定目标补货量，解决了相关技术中物品的库存量是随机确定的，或者是固定的，导致确定出的补货量与实际所需的货量不适配，从而引起库存成本较高的问题，实现了根据待处理物品的出货量关联信息，确定目标补货量，提高了确定目标补货量的准确率，以及对库存成本有效控制的技术效果。
本申请实施例所提供的物品库存的控制装置可执行本申请任意实施例所提供的物品库存的控制方法，具备执行方法相应的功能模块和效果。
上述装置所包括的多个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，多个功能单元的名称也只是为了便于相互区分，并不用于限制本申请实施例的保护范围。
图8为本申请实施例提供的一种电子设备的结构示意图。图8示出了适于用来实现本申请实施例实施方式的示例性电子设备80的框图。图8显示的电子设备80仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图8所示，电子设备80以通用计算设备的形式表现。电子设备80的组件可以包括但不限于：一个或者多个处理器或者处理单元801，系统存储器802，连接不同系统组件(包括系统存储器802和处理单元801)的总线803。
总线803表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(Industry Standard Architecture，ISA)总线，微通道体系结构(Micro Channel Architecture，MCA)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association，VESA)局域总线以及外围组件互连(Peripheral Component Interconnect，PCI)总线。
电子设备80包括多种计算机系统可读介质。这些介质可以是任何能够被电子设备80访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
系统存储器802可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory，RAM)804和/或高速缓存存储器805。电子设备80可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统806可以设置为读写不可移动的、非易失性磁介质(图8未显示，通常称为“硬盘驱动器”)。尽管图8中未示出，可以提供设置为对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非 易失性光盘(例如光盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)，数字通用光盘只读存储器(Digital Video Disc-ROM，DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线803相连。存储器802可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请实施例的功能。
具有一组(至少一个)程序模块807的程序/实用工具808，可以存储在例如存储器802中，这样的程序模块807包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或一种组合中可能包括网络环境的实现。程序模块807通常执行本申请所描述的实施例中的功能和/或方法。
电子设备80也可以与一个或多个外部设备809(例如键盘、指向设备、显示器810等)通信，还可与一个或者多个使得用户能与该电子设备80交互的设备通信，和/或与使得该电子设备80能与一个或多个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(Input/Output，I/O)接口811进行。并且，电子设备80还可以通过网络适配器812与一个或者多个网络(例如局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器812通过总线803与电子设备80的其它模块通信。应当明白，尽管图8中未示出，可以结合电子设备80使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、磁盘阵列(Redundant Arrays of Independent Disks，RAID)系统、磁带驱动器以及数据备份存储系统等。
处理单元801通过运行存储在系统存储器802中的程序，从而执行多种功能应用以及数据处理，例如实现本申请实施例所提供的物品库存的控制方法。
本申请实施例还提供一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行物品库存的控制方法。
该方法包括：
针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值；如果检测到存在补货属性值大于预设补货属性阈值的目标待处理物品，则根据所述补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量；针对每个目标待处理物品， 根据当前目标待处理物品的目标库存量与当前时间所对应的净库存量，确定所述当前目标待处理物品的目标补货量。
本申请实施例的计算机存储介质，可以采用一个或多个计算机可读的介质的任意组合。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。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例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、RAM、ROM、可擦式可编程只读存储器(Erasable Programmable Read Only Memory，EPROM或闪存)、光纤、CD-ROM、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，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。
计算机可读的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。计算机可读的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——但不限于无线、电线、光缆、射频(Radio Frequency，RF)等等，或者上述的任意合适的组合。
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申请实施例操作的计算机程序代码，所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LAN或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)。

Claims (22)

  1. 一种物品库存的控制方法，包括：
    针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值；
    在检测到存在所述补货属性值大于预设补货属性阈值的目标待处理物品的情况下，根据所述目标待处理物品的补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量；
    针对每个目标待处理物品，根据当前目标待处理物品的目标库存量与当前时间所对应的净库存量，确定所述当前目标待处理物品的目标补货量。
  2. 根据权利要求1所述的方法，其中，所述出货量关联信息中包括出货日期和与所述出货日期所对应的出货量，在所述根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值之前，还包括：
    根据每个物品的出货日期和相应的出货量，确定所述每个物品相邻两次出货的出货间隔时长，并将所述出货间隔时长更新至相应物品的出货量关联信息中。
  3. 根据权利要求2所述的方法，其中，所述根据每个物品的出货日期和相应的出货量，确定所述每个物品相邻两次出货的出货间隔时长，包括：
    针对每个物品的出货量关联信息，在检测到当前物品的出货量大于预设出货量阈值的情况下，确定所述出货量对应的待处理出货日期；
    根据与每个物品所对应的待处理出货日期，确定每个物品相邻两次出货的出货间隔时长。
  4. 根据权利要求2所述的方法，还包括：
    根据每个物品的出货量关联信息，确定至少一个待处理物品。
  5. 根据权利要求4所述的方法，其中，在所述出货量关联信息中包括出货间隔时长的情况下，所述根据每个物品的出货量关联信息，确定至少一个待处理物品，包括：
    根据与每个物品对应的至少一个出货间隔时长，确定相应物品的变异系数；
    根据预设变异系数阈值和每个变异系数，确定至少一个待处理物品。
  6. 根据权利要求5所述的方法，其中，所述根据与每个物品对应的至少一个出货间隔时长，确定相应物品的变异系数，包括：
    针对每个物品的出货间隔时长，根据与当前物品相对应的至少一个出货间隔时长，确定时长间隔均值和时长间隔方差；
    根据每个物品所对应的时长间隔均值和时长间隔方差，确定每个物品的变异系数。
  7. 根据权利要求5所述的方法，其中，所述根据预设变异系数阈值和每个变异系数，确定至少一个待处理物品，包括：
    将变异系数小于预设变异系数阈值的物品，作为所述待处理物品。
  8. 根据权利要求1所述的方法，其中，所述根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值，包括：
    根据所述当前待处理物品的出货量关联信息，确定目标数据处理方式；
    基于所述目标数据处理方式对所述当前时间以及所述出货量关联信息进行处理，得到所述当前待处理物品的补货属性值。
  9. 根据权利要求8所述的方法，其中，所述根据所述当前待处理物品的出货量关联信息，确定目标数据处理方式，包括：
    根据所述出货量关联信息中的每个出货日期所对应的出货量，确定至少一个出货间隔时长；
    在所述至少一个出货间隔时长满足预设均匀分布的情况下，确定所述目标数据处理方式为均值估计方式；
    在所述至少一个出货间隔时长不满足预设均匀分布的情况下，确定所述目标数据处理方式为分位数估计方式。
  10. 根据权利要求8所述的方法，其中，所述基于所述目标数据处理方式对所述当前时间以及所述出货量关联信息进行处理，得到所述当前待处理物品的补货属性值，包括：
    确定所述出货量关联信息中出货量大于预设出货量阈值，且与当前时间间隔最小的待使用出货日期；
    根据所述当前时间所对应的日期以及所述待使用出货日期，确定第一时长；
    基于所述目标数据处理方式对所述第一时长以及所述出货量关联信息进行处理，得到当前待处理物品的补货属性值。
  11. 根据权利要求10所述的方法，其中，在所述出货量关联信息中包括出货间隔时长的情况下，所述基于所述目标数据处理方式对所述第一时长以及所述出货量关联信息进行处理，得到当前待处理物品的补货属性值，包括：
    在所述目标数据处理方式为均值估计方式的情况下，基于所述均值估计方式对所述第一时长和根据出货间隔时长确定的时长间隔方差进行处理，确定当 前待处理物品的补货属性值。
  12. 根据权利要求10所述的方法，其中，所述基于所述目标数据处理方式对所述第一时长以及所述出货量关联信息进行处理，得到当前待处理物品的补货属性值，包括：
    在所述目标数据处理方式为分位数估计方式的情况下，根据所述出货量关联信息和预设分位数，确定目标分位数子估计方式；
    基于所述目标分位数子估计方式对所述第一时长以及所述出货量关联信息进行处理，确定所述当前待处理物品的补货属性值。
  13. 根据权利要求12所述的方法，其中，所述出货量关联信息中包括与出货间隔时长相对应出货次数，所述根据所述出货量关联信息和预设分位数，确定目标分位数子估计方式，包括：
    在所述预设分位数小于或等于出货次数的倒数的情况下，确定所述目标分位数子估计方式为第一分位数子估计方式；
    在所述预设分位数大于出货次数的倒数的情况下，确定所述目标分位数子估计方式为第二分位数子估计方式。
  14. 根据权利要求13所述的方法，其中，所述基于所述目标分位数子估计方式对所述第一时长以及所述出货量关联信息进行处理，确定所述当前待处理物品的补货属性值，包括：
    在所述目标分位数子估计方式为第一分位数子估计方式的情况下，根据出货间隔天数、预设分位数、出货次数以及所述第一时长，确定所述当前待处理物品的补货属性值。
  15. 根据权利要求14所述的方法，其中，所述根据出货间隔天数、预设分位数、出货次数以及所述第一时长，确定所述当前待处理物品的补货属性值，包括：
    根据出货间隔时长的最小值、所述预设分位数以及所述出货次数的乘积，得到第一数据值；
    基于所述第一时长与所述第一数据值的比值，确定所述当前待处理物品的补货属性值。
  16. 根据权利要求13所述的方法，其中，所述基于目标分位数子估计方式对所述第一时长以及所述出货量关联信息进行处理，确定所述当前待处理物品的补货属性值，包括：
    在所述目标分位数子估计方式为第二分位数子估计方式的情况下，根据所述预设分位数和所述出货量关联信息，确定目标分位点；
    根据所述目标分位点和所述第一时长，确定所述当前待处理物品的补货属性值。
  17. 根据权利要求16所述的方法，其中，所述根据所述预设分位数和所述出货量关联信息，确定目标分位点，包括：
    根据所述出货量关联信息中的出货间隔天数，拟合得到目标经验分布；
    根据所述预设分位数和所述目标经验分布，确定所述目标分位点。
  18. 根据权利要求1所述的方法，其中，所述在检测到存在补货属性值大于预设补货属性阈值的目标待处理物品的情况下，根据所述补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量，包括：
    根据每个补货属性值所对应的目标数据处理方式，确定相应的预设补货属性阈值；
    在检测到存在补货属性值大于相应的预设补货属性阈值的目标待处理物品的情况下，根据所述补货属性值和所述目标库存量确定模型，确定所述目标待处理物品的目标库存量。
  19. 根据权利要求18所述的方法，其中，所述据所述补货属性值和所述目标库存量确定模型，确定所述目标待处理物品的目标库存量，包括：
    将所述补货属性值作为所述目标库存量确定模型的输入参数，确定所述目标待处理物品的目标库存量。
  20. 一种物品库存控制装置，包括：
    采集计算模块，设置为针对每个待处理物品，根据当前时间以及当前待处理物品的出货量关联信息，确定所述当前待处理物品的补货属性值；
    库存策略运算模块，设置为在检测到存在补货属性值大于预设补货属性阈值的目标待处理物品的情况下，根据所述补货属性值和目标库存量确定模型，确定所述目标待处理物品的目标库存量；
    结果输出模块，设置为针对每个目标待处理物品，根据当前目标待处理物品的目标库存量与当前时间所对应的净库存量，确定所述当前目标待处理物品的目标补货量。
  21. 一种电子设备，包括：
    至少一个处理器；
    存储装置，设置为存储至少一个程序；
    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1-19中任一所述的物品库存的控制方法。
  22. 一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行如权利要求1-19中任一所述的物品库存的控制方法。
PCT/CN2022/131900 2021-11-25 2022-11-15 物品库存的控制方法、装置、设备及介质 WO2023093567A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111413044.3A CN113837706B (zh) 2021-11-25 2021-11-25 物品库存的控制方法、装置、设备及介质
CN202111413044.3 2021-11-25

Publications (1)

Publication Number Publication Date
WO2023093567A1 true WO2023093567A1 (zh) 2023-06-01

Family

ID=78971375

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/131900 WO2023093567A1 (zh) 2021-11-25 2022-11-15 物品库存的控制方法、装置、设备及介质

Country Status (2)

Country Link
CN (1) CN113837706B (zh)
WO (1) WO2023093567A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113837706B (zh) * 2021-11-25 2022-06-07 北京京东振世信息技术有限公司 物品库存的控制方法、装置、设备及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110363454A (zh) * 2018-04-09 2019-10-22 杉数科技(北京)有限公司 用于确定商品补货量的方法及装置
CN111429048A (zh) * 2019-01-09 2020-07-17 北京沃东天骏信息技术有限公司 确定补货信息的方法、装置及设备
US20210174300A1 (en) * 2018-07-06 2021-06-10 Beijing Jingdong Shangke Information Technology Co., Ltd. Commodity replenishment method and device
CN113449939A (zh) * 2020-03-24 2021-09-28 北京京东振世信息技术有限公司 库存数据预测的方法、装置、计算设备及介质
CN113837706A (zh) * 2021-11-25 2021-12-24 北京京东振世信息技术有限公司 物品库存的控制方法、装置、设备及介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10839348B2 (en) * 2017-01-27 2020-11-17 Walmart Apollo, Llc System and method for optimizing inventory replenishment
CN109840734A (zh) * 2017-11-29 2019-06-04 北京京东尚科信息技术有限公司 信息输出方法和装置
CN109978429B (zh) * 2017-12-28 2021-09-03 北京京东尚科信息技术有限公司 用于输出信息的方法和装置
CN108596540B (zh) * 2018-04-23 2021-12-14 北京京东乾石科技有限公司 补货方法及装置、计算机可读存储介质、电子设备
CN112561414A (zh) * 2019-09-25 2021-03-26 顺丰科技有限公司 库存管理方法、装置及计算机可读存储介质
CN112347417A (zh) * 2019-12-12 2021-02-09 北京沃东天骏信息技术有限公司 补货量确定方法和装置
CN113537861B (zh) * 2020-04-16 2024-03-05 北京京东振世信息技术有限公司 补货方法和补货装置
CN113128932B (zh) * 2021-04-16 2024-04-16 北京京东振世信息技术有限公司 仓库备货处理方法、装置、存储介质与电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110363454A (zh) * 2018-04-09 2019-10-22 杉数科技(北京)有限公司 用于确定商品补货量的方法及装置
US20210174300A1 (en) * 2018-07-06 2021-06-10 Beijing Jingdong Shangke Information Technology Co., Ltd. Commodity replenishment method and device
CN111429048A (zh) * 2019-01-09 2020-07-17 北京沃东天骏信息技术有限公司 确定补货信息的方法、装置及设备
CN113449939A (zh) * 2020-03-24 2021-09-28 北京京东振世信息技术有限公司 库存数据预测的方法、装置、计算设备及介质
CN113837706A (zh) * 2021-11-25 2021-12-24 北京京东振世信息技术有限公司 物品库存的控制方法、装置、设备及介质

Also Published As

Publication number Publication date
CN113837706B (zh) 2022-06-07
CN113837706A (zh) 2021-12-24

Similar Documents

Publication Publication Date Title
US8600843B2 (en) Method and computer system for setting inventory control levels from demand inter-arrival time, demand size statistics
CN111242524B (zh) 一种确定单品补货量的方法、系统、设备及存储介质
US20090024444A1 (en) Forecasting based on a collection of data
US9990597B2 (en) System and method for forecast driven replenishment of merchandise
CN110751497A (zh) 一种商品补货方法和装置
US20130297530A1 (en) Methods and Apparatus for Improving Factor Risk Model Responsiveness
US20180096290A1 (en) Sharing inventory between ordering channels
US9292336B1 (en) Systems and methods providing optimization data
CN113128932B (zh) 仓库备货处理方法、装置、存储介质与电子设备
CN109961198B (zh) 关联信息生成方法和装置
US20150186907A1 (en) Data mining
CN111932188B (zh) 用于库存管理的方法、电子设备和存储介质
WO2023093567A1 (zh) 物品库存的控制方法、装置、设备及介质
US20180260880A1 (en) Online platform for processing merchandise shipping
CN111798167B (zh) 一种仓库补货的方法和装置
CN110619407B (zh) 对象销量的预测方法及系统、电子设备和存储介质
US7756676B1 (en) Detecting data change based on adjusted data values
CN109978421B (zh) 信息输出方法和装置
CN114663015A (zh) 补货方法和装置
US20130103456A1 (en) Method, system and program storage device for production planning
CN115482116A (zh) 资产投资策略信息的推荐方法、装置、设备及介质
CN113436003A (zh) 时长确定方法、装置、电子设备、介质和程序产品
CN112632384A (zh) 针对应用程序的数据处理方法、装置、电子设备和介质
CN111681008A (zh) 一种风险控制方法、装置、设备及存储介质
US8126765B2 (en) Market demand estimation method, system, and apparatus

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: 22897650

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022897650

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2022897650

Country of ref document: EP

Effective date: 20240328

WWE Wipo information: entry into national phase

Ref document number: 2401003035

Country of ref document: TH