WO2023134188A1 - 指标确定方法、装置、电子设备和计算机可读介质 - Google Patents

指标确定方法、装置、电子设备和计算机可读介质 Download PDF

Info

Publication number
WO2023134188A1
WO2023134188A1 PCT/CN2022/118576 CN2022118576W WO2023134188A1 WO 2023134188 A1 WO2023134188 A1 WO 2023134188A1 CN 2022118576 W CN2022118576 W CN 2022118576W WO 2023134188 A1 WO2023134188 A1 WO 2023134188A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
sequence
index
inventory
item
Prior art date
Application number
PCT/CN2022/118576
Other languages
English (en)
French (fr)
Inventor
于莹
马晓雯
高振羽
庄晓天
张轩琪
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 WO2023134188A1 publication Critical patent/WO2023134188A1/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
    • 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

Definitions

  • the embodiments of the present disclosure relate to the field of computer technology, and specifically relate to an index determination method, device, electronic equipment, and computer-readable medium.
  • Demand forecasting refers to a technology that makes accurate estimates of future development trends based on existing data. Since different forecasting methods often have different forecasting capabilities, that is, there are often differences in accuracy. Therefore, predictive evaluation needs to be carried out through predictive indicators. At present, when selecting predictive indicators for predictive evaluation, the usual method is to select predictive indicators through manual screening.
  • Some embodiments of the present disclosure provide an index determination method, device, electronic device, and computer-readable medium to solve one or more of the technical problems mentioned in the background art section above.
  • some embodiments of the present disclosure provide a method for determining an index, the method comprising: acquiring an item information set, wherein the item information in the item information set includes: item circulation information sequence and item replenishment quantity information sequence ; According to the item circulation information sequence and the item replenishment information sequence included in each item information in the above item information set, generate the inventory satisfaction information group, and obtain the inventory satisfaction information group sequence; according to the inventory satisfaction information group sequence in the above inventory satisfaction information group sequence; For each index to be screened in the information group and the index sequence to be screened, generate the inventory satisfaction rate information group and the forecast accuracy rate information group, and obtain the inventory satisfaction rate information group sequence and the forecast accuracy rate information group sequence; according to the above inventory satisfaction rate information group sequence and the above-mentioned prediction accuracy information group sequence, and perform linear regression to generate the index evaluation information corresponding to each index to be screened in the above-mentioned index sequence to be screened, and obtain the index evaluation information sequence; according to the above-mentioned index evaluation information sequence, from the above-
  • some embodiments of the present disclosure provide an indicator determination device, the device includes: an acquisition unit configured to acquire an item information set, wherein the item information in the above item information set includes: item circulation information sequence and item Replenishment quantity information sequence; the first generation unit is configured to generate an inventory satisfaction information group according to the item circulation information sequence and item replenishment quantity information sequence included in each item information in the above item information set, and obtain the inventory satisfaction information set Sequence; the second generation unit is configured to generate the inventory satisfaction rate information group and the forecast accuracy information group according to the inventory satisfaction information group in the above-mentioned inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, and obtain Inventory satisfaction rate information group sequence and prediction accuracy rate information group sequence; the linear regression unit is configured to perform linear regression according to the above-mentioned inventory satisfaction rate information group sequence and the above-mentioned prediction accuracy rate information group sequence, to generate the above-mentioned to-be-screened index sequence The index evaluation information corresponding to each index to be screened to obtain the
  • some embodiments of the present disclosure provide an electronic device, including: at least one processor; and a storage device, on which at least one program is stored.
  • the device implements the method described in any implementation manner of the first aspect above.
  • some embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, wherein, when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
  • FIG. 1 is a schematic diagram of an application scenario of an indicator determination method in some embodiments of the present disclosure
  • FIG. 2 is a flowchart of some embodiments of an indicator determination method according to the present disclosure
  • Fig. 3 is a flow chart of another embodiment of the indicator determination method according to the present disclosure.
  • Fig. 4 is the schematic diagram of linear fitting curve
  • Fig. 5 is a schematic structural diagram of some embodiments of an indicator determination device according to the present disclosure.
  • FIG. 6 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure.
  • some embodiments of the present disclosure propose an index determination method and device, which improves the evaluation ability of the prediction result and reduces the occurrence of inventory backlog or stock shortage.
  • Fig. 1 is a schematic diagram of an application scenario of an indicator determination method in some embodiments of the present disclosure.
  • the computing device 101 can obtain the item information set 102, wherein the item information in the item information set 102 includes: item circulation information sequence 103 and item replenishment quantity information sequence 104; secondly, calculate The device 101 can generate the inventory satisfaction information group according to the item circulation information sequence 103 and the item replenishment quantity information sequence 104 included in each item information in the above item information set 102, and obtain the inventory satisfaction information group sequence 105; then, the computing device 101 According to the inventory satisfaction information group in the above-mentioned inventory satisfaction information group sequence 105, and each index to be screened in the index sequence 106 to be screened, the inventory satisfaction rate information group and the forecast accuracy rate information group are generated to obtain the inventory satisfaction rate information group sequence 107 and the prediction accuracy rate information group sequence 108; then, the computing device 101 can perform linear regression according to the above-mentioned inventory satisfaction rate information group sequence 107 and the above-mentioned prediction accuracy rate information group sequence 108, so as to generate each of the above-mentioned to-
  • the above-mentioned computing device 101 may be hardware or software.
  • the computing device When the computing device is hardware, it can be realized as a distributed cluster composed of multiple servers or terminal devices, or as a single server or a single terminal device.
  • the computing device When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented, for example, as a plurality of software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.
  • the indicator determination method includes the following steps:
  • Step 201 acquire item information set.
  • the executing subject of the indicator determination method may obtain the above item information set through a wired connection or a wireless connection.
  • the item information in the above item information set may include: item circulation information sequence and item replenishment quantity information sequence.
  • the item information in the above item information set may be historical item information of items in the same domain.
  • the item circulation information sequence included in the item information can represent the item circulation situation of the corresponding item within the target time period.
  • the item replenishment quantity information sequence included in the item information may represent the item replenishment situation of the corresponding item within the aforementioned target time period.
  • the item circulation information in the item circulation information sequence may include: the actual sales volume of the item and the predicted sales volume of the item.
  • the aforementioned target time period may be a historical time period.
  • the above target time period may be from November 10, 2020 to November 17, 2020.
  • the above item information collection may be:
  • Step 202 according to the item circulation information sequence and the item replenishment quantity information sequence included in each item information set in the item information set, an inventory satisfaction information group is generated to obtain an inventory satisfaction information group sequence.
  • the execution subject can generate the inventory satisfaction information group according to the item circulation information sequence and the item replenishment quantity information sequence included in each item information set in the above item information set, and obtain the above inventory satisfaction information group sequence.
  • the inventory fulfillment information in the above-mentioned inventory fulfillment information group sequence may represent the inventory fulfillment condition of the item.
  • the inventory fulfillment information in the above inventory fulfillment information group sequence may include: first inventory fulfillment information and second inventory fulfillment information.
  • the first inventory satisfaction information may be characterized by the difference between the actual sales volume of the item and the predicted sales volume of the item included in the item circulation information.
  • the second inventory fulfillment information can be represented by the difference between the actual sales volume of the item included in the item circulation information and the item replenishment quantity information corresponding to the item circulation information in the item replenishment quantity information sequence.
  • the above-mentioned executive body can generate the inventory satisfaction information group through the following formula according to the item circulation information sequence and the item replenishment quantity information sequence included in each item information in the above-mentioned item information set:
  • i represents the serial number.
  • B represents the actual sales of the item.
  • C represents the predicted sales of items.
  • B i represents the real sales volume of the item included in the ith item circulation information in the above item circulation information sequence.
  • C i represents the predicted sales volume of the item included in the ith item circulation information in the above item circulation information sequence.
  • D represents item replenishment quantity information in the aforementioned item replenishment quantity information sequence.
  • D i represents the replenishment quantity information of the i-th item in the above item replenishment quantity information sequence.
  • A1 represents the first inventory fulfillment information included in the inventory fulfillment information in the aforementioned inventory fulfillment information group.
  • A2 represents the second inventory fulfillment information included in the inventory fulfillment information in the aforementioned inventory fulfillment information group.
  • a 1,i represents the first inventory fulfillment information included in the i-th inventory fulfillment information in the aforementioned inventory fulfillment information group.
  • a 2,i represents the second inventory fulfillment information included in the i-th inventory fulfillment information in the aforementioned inventory fulfillment information group.
  • the item information and inventory satisfaction information group corresponding to "item A" can be:
  • Step 203 according to the inventory satisfaction information group in the inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, generate the inventory satisfaction rate information group and the forecast accuracy rate information group, and obtain the inventory satisfaction rate information group sequence and forecast Accuracy information group sequence.
  • the execution subject may generate an inventory satisfaction rate information group and a prediction accuracy information group according to the inventory satisfaction information group in the inventory satisfaction information group sequence and each index to be screened in the above index to be screened sequence, Obtain the above-mentioned information group sequence of inventory satisfaction rate and the above-mentioned sequence of prediction accuracy rate information group.
  • the to-be-screened indicators in the above-mentioned to-be-screened indicator sequence may be predictive indicators for evaluating the prediction results.
  • the indicators to be screened in the above index sequence to be screened may include predictive indicators of relative error type and absolute error type of predictive indicators.
  • the above-mentioned absolute error type characterizes that the forecasting indicator is used to calculate the absolute difference between the forecasted sales volume and the replenishment volume of the item.
  • the above-mentioned relative error types characterize the forecasting index used to calculate the relative difference between the predicted sales volume and the replenishment volume of the item.
  • the predictor of the above absolute error type can be but not limited to any of the following: MAE (Mean Absolute Error, mean absolute error) predictor, MSE (Mean Square Error, mean square error) predictor, RMAE (Root Mean Absolute Error, root mean absolute error) predictor and RMSE (Root Mean Square Error, root mean square error) predictor.
  • the predictor of the above relative error type can be but not limited to any of the following: MAPE (Mean Absolute Percentage Error, average absolute percentage error) predictor, sMAPE (Symmetric Mean Absolute Percentage Error, symmetric mean absolute percentage error) predictor and MASE (Mean Absolute Scaled Error, average absolute scaled error) predictor.
  • the inventory fulfillment rate information in the aforementioned inventory fulfillment rate information group sequence can represent the inventory fulfillment rate.
  • the prediction accuracy rate information in the above prediction accuracy rate information group sequence can represent the prediction accuracy rate of item sales.
  • the execution subject may bring the first inventory satisfaction information included in the inventory satisfaction information in the inventory satisfaction information group in the inventory satisfaction information group sequence into the formula corresponding to the index to be screened, so as to determine the prediction accuracy information.
  • the execution subject may determine the inventory fulfillment rate information according to the second inventory fulfillment information included in the inventory fulfillment information. For example, when the second inventory fulfillment information is negative, the inventory fulfillment rate information may be 0%. When the second inventory fulfillment information is a positive number, the inventory fulfillment rate information may be 100%.
  • the prediction accuracy rate information group and inventory satisfaction rate information group corresponding to "item A" can be:
  • Step 204 Perform linear regression according to the inventory satisfaction rate information group sequence and the forecast accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened, and obtain an index evaluation information sequence.
  • the execution subject may perform linear regression according to the above-mentioned inventory satisfaction rate information group sequence and the above-mentioned prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened, Obtain the above index evaluation information sequence.
  • the index evaluation information in the above index evaluation information sequence can be used to evaluate the index evaluation ability of the index to be screened.
  • the above-mentioned executive body can use each inventory satisfaction rate information in the above-mentioned inventory satisfaction rate information group as a dependent variable, and combine the above-mentioned inventory satisfaction information with the above-mentioned
  • the corresponding prediction accuracy information is used as an independent variable and brought into the following linear regression equation for linear fitting:
  • y represents the inventory satisfaction rate information.
  • x represents the prediction accuracy information.
  • j represents the serial number.
  • y j represents the jth inventory fulfillment rate information in the inventory fulfillment rate information group.
  • x j represents the jth prediction accuracy rate information in the prediction accuracy rate information group.
  • b represents the intercept.
  • a represents the index evaluation information.
  • the prediction accuracy rate information group and inventory satisfaction rate information group corresponding to "item A" and "item B" may be:
  • the obtained indicator evaluation information may be -0.088134.
  • Step 205 according to the index evaluation information sequence, select the index to be screened that meets the screening condition from the index sequence to be screened as the target index, and obtain a target index set.
  • the above-mentioned executive body may select, from the above-mentioned sequence of indicators to be screened, the indicators to be screened that meet the screening conditions as target indicators according to the above-mentioned index evaluation information sequence, and obtain the above-mentioned target index set.
  • the above screening condition may be that the index evaluation information corresponding to the index to be screened is smaller than the target value.
  • the above-mentioned target value may be the same as the sorted index evaluation information of the target position in the sorted index evaluation information sequence.
  • the above-mentioned target position can be manually determined.
  • the above index sequence to be screened may be [MAE predictor, MSE predictor, RMAE predictor, RMSE predictor, MAPE predictor, sMAPE predictor, MASE predictor].
  • the above index evaluation information sequence may be [-0.007, -0.011, -0.09, -0.007, -0.012, -0.029, -0.244].
  • the aforementioned target position may be "3".
  • the sorted indicator evaluation information sequence may be [-0.244, -0.09, -0.029, -0.012, -0.011, -0.007, -0.007].
  • the above target value is "-0.029”.
  • the indicators to be screened that meet the above screening conditions are used as the target indicators, and the obtained target indicator set is [MASE predictors, RMAE predictors].
  • the index determination methods of some embodiments of the present disclosure have the following beneficial effects: through the index determination methods of some embodiments of the present disclosure, the ability to evaluate the prediction results is improved, and the occurrence of inventory backlog or stock-out is reduced. Specifically, the reason for the backlog of inventory or stock out of stock is that there is no unified and standard selection method for forecasting indicators through manual screening, so that the selected forecasting indicators are often unable to accurately evaluate the forecast results, resulting in inventory Overstock or out of stock situations arise. Based on this, the index determination method of some embodiments of the present disclosure first acquires an item information set, wherein the item information in the item information set includes: an item circulation information sequence and an item replenishment quantity information sequence.
  • an inventory satisfaction information group is generated to obtain an inventory satisfaction information group sequence.
  • the inventory replenishment accuracy rate corresponding to the item is determined through the circulation and replenishment status of the item corresponding to each item information.
  • the inventory satisfaction rate information group and the forecast accuracy rate information group are generated, and the inventory satisfaction rate information group sequence and forecast are obtained.
  • each forecasting indicator Through historical inventory replenishment accuracy and each forecasting indicator, the forecasting accuracy and inventory fulfillment of each forecasting indicator are determined. Then, perform linear regression according to the above-mentioned inventory satisfaction rate information group sequence and the above-mentioned prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the above-mentioned index sequence to be screened, and obtain an index evaluation information sequence. The predictive power of each predictor is quantified by means of linear regression. Finally, according to the above-mentioned index evaluation information sequence, the to-be-screened indexes that meet the screening conditions are selected from the above-mentioned to-be-screened index sequence as target indexes, and a target index set is obtained. Through screening to determine the predictive indicators with strong predictive evaluation ability.
  • the selection method of forecasting indicators is unified and standardized, and at the same time, the forecasting and evaluation ability of each forecasting indicator is quantified, so as to solve the problem that the demand forecasting results are easily affected by manual screening (such as randomness) , improving the accuracy of the evaluation of the forecast results, reducing the occurrence of inventory backlog or stock out of stock.
  • FIG. 3 shows a flow 300 of another embodiment of an indicator determination method.
  • the process 300 of the indicator determination method includes the following steps:
  • Step 301 acquire item information set.
  • step 301 for the specific implementation of step 301 and the technical effects brought about by it, reference may be made to step 201 in those embodiments corresponding to FIG. 2 , which will not be repeated here.
  • Step 302 for each item replenishment quantity information in the item replenishment quantity information sequence included in the item information, in response to determining that the item replenishment quantity information is greater than the target item circulation information, determine the inventory full information as the item replenishment quantity information The corresponding inventory status identifier included in the inventory fulfillment information.
  • the execution body of the indicator determination method may respond to determining the item replenishment quantity information for each item replenishment quantity information in the item replenishment quantity information sequence included in the item information.
  • the quantity information is greater than the target item circulation information
  • the inventory full information is determined as the inventory status identifier included in the inventory satisfaction information corresponding to the item replenishment quantity information.
  • the inventory fulfillment information in the aforementioned inventory fulfillment information group sequence includes: inventory state identification.
  • the above-mentioned inventory status identifier can be used to represent the inventory fulfillment situation.
  • the target item circulation information may be item circulation information corresponding to the item replenishment quantity information in the item circulation information sequence included in the item information.
  • the above full inventory information may indicate that the item replenishment quantity information is greater than the actual sales volume of the item included in the target logistics transfer information. For example, the above item replenishment quantity information may be represented by "1".
  • Step 303 for each item replenishment quantity information in the item replenishment quantity information sequence included in the item information, in response to determining that the item replenishment quantity information is less than or equal to the target item circulation information, determine the inventory out-of-stock information as item replenishment The inventory status identifier included in the inventory fulfillment information corresponding to the quantity information.
  • the execution subject may, for each item replenishment quantity information in the item replenishment quantity information sequence included in the item information, respond to determining that the item replenishment quantity information is less than or equal to the target item circulation information, and make the inventory out of stock
  • the information is determined as the inventory status identifier included in the inventory fulfillment information corresponding to the item replenishment quantity information.
  • the above-mentioned inventory out-of-stock information may indicate that the item replenishment quantity information is greater than the actual sales volume of the item included in the target logistics transfer information. For example, the above-mentioned out-of-stock information may be represented by "0".
  • the item information corresponding to "item A" and the corresponding inventory fulfillment information group may be:
  • Step 304 according to the inventory satisfaction information group in the inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, generate the inventory satisfaction rate information group and the forecast accuracy rate information group, and obtain the inventory satisfaction rate information group sequence and forecast Accuracy information group sequence.
  • the execution subject may generate an inventory satisfaction rate information group and a prediction accuracy information group according to the inventory satisfaction information group in the inventory satisfaction information group sequence and each index to be screened in the above index to be screened sequence, Obtain the above-mentioned information group sequence of inventory satisfaction rate and the above-mentioned sequence of prediction accuracy rate information group.
  • the above-mentioned execution subject may perform the following processing steps for each inventory-satisfaction information group in the above-mentioned inventory-satisfaction information group sequence:
  • the above-mentioned inventory satisfaction information group is divided to generate sub-inventory satisfaction information groups, and a sequence of sub-inventory satisfaction information groups is obtained.
  • the size of the above-mentioned sliding window may be manually set.
  • the aforementioned preset sliding length may represent a moving step of the aforementioned sliding window.
  • the above sliding window may be "7”.
  • the aforementioned preset sliding length may be "1".
  • the inventory fulfillment information group corresponding to "item A" can be:
  • the time span of the inventory satisfaction information group corresponding to "item A" may be from 2021-04-15 to 2021-07-10, a total of 86 days.
  • the above-mentioned executive body may divide the above-mentioned 86 items of inventory satisfaction information by using 7 days as a sliding window and 1 day as a preset sliding length to generate 80 sub-inventory satisfaction information groups.
  • the second step is to generate inventory satisfaction rate information and forecast accuracy rate information based on each sub-inventory satisfaction information group in the above-mentioned sub-inventory satisfaction information group sequence and each to-be-screened index in the above-mentioned to-be-screened index sequence, and obtain the above-mentioned inventory satisfaction information Inventory satisfaction rate information group and forecast accuracy information group corresponding to the group.
  • the inventory fulfillment rate information may represent each inventory fulfillment rate corresponding to a sub-stock fulfillment information group.
  • the prediction accuracy rate information may represent the prediction accuracy rate of each index to be screened corresponding to a sub-inventory satisfaction information group.
  • the execution subject may determine the ratio of the quantity of the sub-inventory satisfaction information whose inventory state is "1" contained in the sub-inventory satisfaction information group to the length of the sliding window as a value in the inventory satisfaction rate information.
  • “item A” is within 2021-04-15 to 2021-07-10, corresponding to 80 sub-inventory satisfaction information groups, and the corresponding inventory satisfaction rate information can be [95%, 90%, 97%, 96%, ..., 91%].
  • the aforementioned index sequence to be screened may be [MAE predictive index, MSE predictive index, RMAE predictive index, RMSE predictive index] the above-mentioned prediction accuracy rate information may be [8.8, 7.7, 3.2, 4.4].
  • “8.8” can represent the prediction accuracy of the "MAE prediction index”.
  • “7.7” can characterize the prediction accuracy of "MSE predictor”.
  • “3.2” can characterize the prediction accuracy of "RMAE predictor”.
  • “4.4” can characterize the prediction accuracy of "RMSE predictor”.
  • Step 305 Perform linear regression according to the inventory satisfaction rate information group sequence and the forecast accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened, and obtain an index evaluation information sequence.
  • the execution subject performs linear regression according to the above-mentioned inventory satisfaction rate information group sequence and the above-mentioned prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened, and obtain
  • the above index evaluation information sequence may include the following steps:
  • the first step is to divide the inventory satisfaction rate information in the above-mentioned inventory satisfaction rate information group sequence and the prediction accuracy rate information in the above-mentioned prediction accuracy rate information group sequence according to the above-mentioned item circulation information sequence, so as to generate the divided inventory Satisfaction rate information group sequence and divided prediction accuracy rate information group sequence.
  • the above-mentioned execution subject separately analyzes the inventory satisfaction rate information in the above-mentioned inventory satisfaction rate information group sequence and the prediction accuracy rate in the above-mentioned prediction accuracy rate information group sequence
  • the information is divided to generate the divided sequence of inventory satisfaction rate information group and the divided sequence of forecast accuracy rate information group.
  • the divided inventory satisfaction rate information group is the inventory satisfaction rate information group corresponding to the item circulation information included in the corresponding item circulation information and the actual sales volume of the item is similar.
  • the above item information set may be [item information A, item information B, item information C, item information D, item information F].
  • the inventory satisfaction rate information group sequence corresponding to the above item information set can be ⁇ [inventory satisfaction rate information A, inventory satisfaction rate information B, inventory satisfaction rate information C], [inventory satisfaction rate information D, inventory satisfaction rate information E, inventory satisfaction rate information Rate Information F], [Inventory Satisfaction Rate Information G, Inventory Satisfaction Rate Information H, Inventory Satisfaction Rate Information I], [Inventory Satisfaction Rate Information J, Inventory Satisfaction Rate Information K, Inventory Satisfaction Rate Information L, [Inventory Satisfaction Rate Information M , Inventory fulfillment rate information N, Inventory fulfillment rate information 0] ⁇ .
  • “Item Information A” and the real sales volume of items included in “Item Information B” are similar to the real sales volume of items included in “Item Information B”. Therefore, [Inventory Satisfaction Rate Information A, Inventory Satisfaction Rate Information B, Inventory Satisfaction Rate Information C] and [Inventory Satisfaction rate information D, inventory satisfaction rate information E, inventory satisfaction rate information F] combination, to generate divided inventory satisfaction rate information group [inventory satisfaction rate information A, inventory satisfaction rate information B, inventory satisfaction rate information C, inventory satisfaction rate information Rate information D, inventory fulfillment rate information E, inventory fulfillment rate information F].
  • the above item information set may be [item information A, item information B, item information C].
  • the corresponding prediction accuracy rate information group sequence can be ⁇ [prediction accuracy rate information A, prediction accuracy rate information B], [prediction accuracy rate information C, prediction accuracy rate information D], [prediction accuracy rate information E, prediction accuracy rate information F] ⁇ .
  • "Item Information A” and the real sales volume of items included in "Item Information B" are similar to the real sales volume of items included in "Item Information B". Therefore, [prediction accuracy rate information A, prediction accuracy rate information B] and [prediction accuracy rate information C, prediction Accuracy rate information D] combined to generate divided prediction accuracy rate information groups.
  • each divided inventory satisfaction rate information group in the above-mentioned divided inventory satisfaction rate information group sequence, and the divided prediction accuracy rate information group corresponding to the above-mentioned divided inventory satisfaction rate information group perform Unit linear regression to generate index evaluation information corresponding to each index to be screened in the above index sequence to be screened.
  • the above set of indicators to be screened may be [MAE predictor, MSE predictor, RMAE predictor, RMSE predictor].
  • the above-mentioned executive body may, according to the above-mentioned divided inventory satisfaction rate information group, and the divided prediction accuracy rate information group corresponding to the above-mentioned divided inventory satisfaction rate information group, Carry out unit linear regression through the following first linear regression formula to generate an index evaluation value in the index evaluation information corresponding to the above-mentioned index to be screened:
  • a represents an index evaluation value in the index evaluation information.
  • b represents the intercept.
  • ⁇ represents the volatility term.
  • the above-mentioned fluctuation item may be manually set.
  • s represents the position of the s-th divided inventory satisfaction rate information in the above-mentioned divided inventory satisfaction rate information group, or represents the position of the s-th divided forecast accuracy rate information in the divided forecast accuracy rate information group .
  • e represents the position of the e-th inventory satisfaction rate included in the s-th divided inventory satisfaction rate information group in the above-mentioned divided inventory satisfaction rate information group, or represents the s-th one in the above-mentioned divided forecast accuracy rate information group The location of the e-th prediction accuracy rate included in the divided prediction accuracy rate information.
  • y represents the inventory fulfillment rate included in the above divided inventory fulfillment rate information.
  • y s, e represent the e-th inventory fulfillment rate included in the s-th divided inventory fulfillment rate information in the above-mentioned divided inventory fulfillment rate information group.
  • x represents the divided prediction accuracy rate information in the above divided prediction accuracy rate information group.
  • x s, e represent the e-th prediction accuracy rate in the s-th divided prediction accuracy rate information in the above-mentioned divided prediction accuracy rate information group.
  • FIG. 4 shows a linear fitting curve 401 corresponding to the above formula.
  • the set of indicators to be screened may be [MAE predictor, MAE predictor, RMAE predictor, RMSE predictor, MAPE predictor, sMAPE predictor, MASE predictor].
  • the index evaluation information set corresponding to the above index set to be screened may be:
  • the above-mentioned executive body may perform multiple linear regression according to the above-mentioned divided inventory satisfaction rate information group sequence and the above-mentioned divided forecast accuracy rate information group sequence, so as to generate each to-be-screened index in the above-mentioned to-be-screened index sequence Corresponding index evaluation information.
  • the above-mentioned executive body can use the following second linear regression formula according to the above-mentioned divided inventory satisfaction information group sequence and the above-mentioned divided prediction accuracy information group sequence, Perform multiple linear regression to generate an index evaluation value in the index evaluation information corresponding to the above-mentioned index to be screened:
  • a represents an index evaluation value in the index evaluation information.
  • b represents the intercept.
  • ⁇ represents the volatility term.
  • the above-mentioned fluctuation item may be manually set.
  • s represents the position of the s-th divided inventory satisfaction rate information in the above-mentioned divided inventory satisfaction rate information group, or represents the position of the s-th divided forecast accuracy rate information in the divided forecast accuracy rate information group .
  • e represents the position of the e-th inventory satisfaction rate included in the s-th divided inventory satisfaction rate information group in the above-mentioned divided inventory satisfaction rate information group, or represents the s-th one in the above-mentioned divided forecast accuracy rate information group The location of the e-th prediction accuracy rate included in the divided prediction accuracy rate information.
  • y represents the inventory fulfillment rate included in the above divided inventory fulfillment rate information.
  • y s, e represent the e-th inventory fulfillment rate included in the s-th divided inventory fulfillment rate information in the above-mentioned divided inventory fulfillment rate information group.
  • x represents the divided prediction accuracy rate information in the above divided prediction accuracy rate information group.
  • x s, e represent the e-th prediction accuracy rate in the s-th divided prediction accuracy rate information in the above-mentioned divided prediction accuracy rate information group.
  • P represents the number of divided inventory satisfaction rate information groups in the above-mentioned divided inventory satisfaction rate information group sequence.
  • k represents the serial number.
  • Band k represents the item category of the item information group corresponding to the kth divided inventory satisfaction rate information.
  • c 1+k represents the coefficient of the item category of the item information group corresponding to the kth divided inventory satisfaction rate information.
  • the above set of indicators to be screened may be [MAE predictor, MAE predictor, RMAE predictor, RMSE predictor, MAPE predictor, sMAPE predictor, MASE predictor].
  • the index evaluation information set corresponding to the above index set to be screened may be:
  • the above-mentioned executive body can perform unit linear regression and multiple linear regression according to the above-mentioned divided inventory satisfaction rate information group sequence and divided forecast accuracy rate information group sequence to generate each of the above-mentioned to-be-screened index sequences
  • the index evaluation information corresponding to the index to be screened is obtained to obtain the above index evaluation information sequence.
  • the above-mentioned executive body may use the above-mentioned first linear regression formula and the above-mentioned second linear regression formula to determine the index evaluation information corresponding to the above-mentioned to-be-screened index.
  • Step 306 according to the index evaluation information sequence, select the index to be screened that meets the screening condition from the index sequence to be screened as the target index, and obtain a target index set.
  • step 306 for the specific implementation of step 306 and the technical effects brought about by it, reference may be made to step 205 in those embodiments corresponding to FIG. 2 , which will not be repeated here.
  • the above-mentioned executive body can use the following steps to select the index to be screened that meets the screening conditions from the above-mentioned index sequence to be screened according to the above-mentioned index evaluation information sequence as the target index, and obtain the above-mentioned target index set :
  • the first step for each index evaluation information in the index evaluation information set, determine that the index evaluation values satisfying the screening conditions in the above index evaluation information correspond to the predictive indexes to be screened, and obtain a candidate predictive index group.
  • the screening condition is that the index evaluation value is less than the target value.
  • the aforementioned target values may be the same as the index evaluation values of the sorted target positions in the index evaluation information.
  • the above-mentioned target position can be manually determined.
  • the second step is to determine the number of occurrences of the candidate predictors in at least one candidate predictor group obtained, and use the candidate predictors whose occurrences meet the screening conditions of the candidate predictors as target indicators to obtain the above target indicator set.
  • the screening condition for the candidate predictors above may be that the number of occurrences of the candidate predictors is greater than the target number of occurrences.
  • the above target number of occurrences may be 2.
  • the inventory satisfaction rate information in the above-mentioned inventory satisfaction rate information group sequence is respectively , and divide the forecast accuracy rate information in the above forecast accuracy rate information group sequence to generate the divided inventory satisfaction rate information group sequence and the divided forecast accuracy rate information group sequence.
  • Inventory satisfaction rate information corresponding to items with similar actual sales volume is located in the same group, and prediction accuracy rate information corresponding to items with similar actual sales volume is located in the same group.
  • each divided inventory satisfaction rate information group in the above-mentioned divided inventory satisfaction rate information group sequence, and the divided prediction accuracy rate information group corresponding to the above-mentioned divided inventory satisfaction rate information group perform unit linearization Regression, to generate index evaluation information corresponding to each index to be screened in the above index sequence to be screened. So that there will not be many discrete points on both sides of the fitting curve after unit linear regression.
  • predictors with better prediction and evaluation capabilities are screened out through the intersection of index evaluation information obtained under different linear fitting methods based on the index to be screened.
  • the present disclosure provides some embodiments of an indicator determination device, these device embodiments correspond to those method embodiments shown in FIG. 2 , and the device can specifically Used in various electronic equipment.
  • the indicator determination device 500 of some embodiments includes: an acquisition unit 501 configured to acquire an item information set, wherein the item information in the above item information set includes: item circulation information sequence and item replenishment quantity information Sequence; the first generation unit 502 is configured to generate the inventory satisfaction information group according to the item circulation information sequence and the item replenishment quantity information sequence included in each item information in the above item information set, and obtain the inventory satisfaction information group sequence; The second generation unit 503 is configured to generate an inventory satisfaction rate information group and a prediction accuracy information group according to the inventory satisfaction information group in the above-mentioned inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, and obtain the inventory satisfaction rate information group.
  • the linear regression unit 504 is configured to perform linear regression according to the above-mentioned inventory satisfaction rate information group sequence and the above-mentioned prediction accuracy rate information group sequence, so as to generate the above-mentioned indicators to be screened in the sequence
  • the index evaluation information corresponding to each index to be screened is obtained to obtain an index evaluation information sequence
  • the screening unit 505 is configured to select, from the above index sequence to be screened, the index to be screened that meets the screening conditions as the target index according to the above index evaluation information sequence , to get the set of target indicators.
  • the inventory fulfillment information in the inventory fulfillment information group sequence includes: an inventory status identifier; and the first generation unit 502 is configured to: replenish the items included in the item information For each item replenishment quantity information in the quantity information sequence, in response to determining that the above item replenishment quantity information is greater than the target item circulation information, the inventory full information is determined as the inventory status included in the inventory satisfaction information corresponding to the above item replenishment quantity information Identification, wherein the target item circulation information is the item circulation information corresponding to the item replenishment quantity information in the item circulation information sequence included in the item information.
  • the above-mentioned first generation unit 502 is configured to: for each item replenishment quantity information in the item replenishment quantity information sequence included in the above-mentioned item information, in response to determining that the above-mentioned item The replenishment quantity information is less than or equal to the target item circulation information, and the inventory out-of-stock information is determined as the inventory status identifier included in the inventory fulfillment information corresponding to the item replenishment quantity information.
  • the above-mentioned second generation unit 503 is configured to: for each inventory-satisfaction information group in the above-mentioned inventory-satisfaction information group sequence, perform the following processing steps: based on a preset sliding window Size and preset sliding length, divide the above-mentioned inventory satisfaction information groups to generate sub-inventory satisfaction information groups, and obtain the sequence of sub-inventory satisfaction information groups; For each index to be screened in the index sequence to be screened, the inventory satisfaction rate information and the forecast accuracy rate information are generated, and the inventory satisfaction rate information group and the forecast accuracy rate information group corresponding to the above inventory satisfaction information group are obtained.
  • the above-mentioned linear regression unit 504 is configured to: according to the above-mentioned item circulation information sequence, respectively analyze the inventory satisfaction rate information in the above-mentioned inventory satisfaction rate information group sequence and the above-mentioned prediction accuracy rate
  • the forecast accuracy rate information in the information group sequence is divided to generate the divided inventory satisfaction rate information group sequence and the divided forecast accuracy rate information group sequence.
  • the linear regression unit 504 is configured to: perform unit linear regression and multiple Linear regression, to generate index evaluation information corresponding to each index to be screened in the above index sequence to be screened, to obtain the above index evaluation information sequence.
  • the above-mentioned linear regression unit 504 is configured to: according to each divided inventory satisfaction rate information group in the above-mentioned divided inventory satisfaction rate information group sequence, and the above-mentioned divided The divided prediction accuracy information group corresponding to the inventory satisfaction rate information group is subjected to unit linear regression to generate index evaluation information corresponding to each index to be screened in the above index sequence to be screened.
  • the above-mentioned linear regression unit 504 is configured to: perform multiple linear regression according to the above-mentioned divided inventory satisfaction rate information group sequence and the above-mentioned divided prediction accuracy rate information group sequence, To generate index evaluation information corresponding to each index to be screened in the above index sequence to be screened.
  • the units recorded in the device 500 correspond to the steps in the method described with reference to FIG. 2 . Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 500 and the units contained therein, and will not be repeated here.
  • FIG. 6 it shows a schematic structural diagram of an electronic device (computing device 101 as shown in FIG. 1 ) 600 suitable for implementing some embodiments of the present disclosure.
  • the electronic device shown in FIG. 6 is only an example, and should not limit the functions and scope of use of the embodiments of the present disclosure.
  • an electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may be randomly accessed according to a program stored in a read-only memory (ROM) 602 or loaded from a storage device 608.
  • a processing device such as a central processing unit, a graphics processing unit, etc.
  • RAM memory
  • various programs and data necessary for the operation of the electronic device 600 are also stored.
  • the processing device 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O) interface 605 is also connected to the bus 604 .
  • the following devices can be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, a liquid crystal display (LCD), speaker, vibration an output device 607 such as a computer; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609.
  • the communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While FIG. 6 shows electronic device 600 having various means, it should be understood that implementing or having all of the means shown is not a requirement. More or fewer means may alternatively be implemented or provided. Each block shown in FIG. 6 may represent one device, or may represent multiple devices as required.
  • the processes described above with reference to the flowcharts may be implemented as computer software programs.
  • some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts.
  • the computer program may be downloaded and installed from a network via communication means 609, or from storage means 608, or from ROM 602.
  • the processing device 601 When the computer program is executed by the processing device 601, the above functions defined in the methods of some embodiments of the present disclosure are performed.
  • the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two.
  • a computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: electrical connections having at least one lead, portable computer diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable Read memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code thereon. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer readable medium may be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
  • the client and the server can communicate using any currently known or future network protocols such as HTTP (HyperText Transfer Protocol, Hypertext Transfer Protocol), and can communicate with digital data in any form or medium
  • HTTP HyperText Transfer Protocol
  • the communication eg, communication network
  • Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device, or may exist independently without being incorporated into the electronic device.
  • the above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: acquires a set of item information, wherein the item information in the above-mentioned item information set includes: Circulation information sequence and item replenishment quantity information sequence; according to the item circulation information sequence and item replenishment quantity information sequence included in each item information in the above item information set, an inventory satisfaction information group is generated to obtain an inventory satisfaction information group sequence; according to The inventory satisfaction information group in the above-mentioned inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened generate an inventory satisfaction rate information group and a prediction accuracy information group, and obtain the inventory satisfaction rate information group sequence and prediction accuracy information Group sequence; According to the above-mentioned inventory satisfaction rate information group sequence and the above-mentioned prediction
  • Computer program code for carrying out operations of some embodiments of the present disclosure may be written in one or more programming languages, or combinations thereof, including object-oriented programming languages—such as Java, Smalltalk, C++, Also included are conventional procedural programming languages - such as the "C" language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, using an Internet service provider to connected via the Internet).
  • LAN local area network
  • WAN wide area network
  • Internet service provider for example, using an Internet service provider to connected via the Internet.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code that contains at least one programmable logic function for implementing the specified logical function.
  • Execute instructions may also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified functions or operations , or may be implemented by a combination of dedicated hardware and computer instructions.
  • the units described in some embodiments of the present disclosure may be realized by software or by hardware.
  • the described units may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a first generation unit, a second generation unit, a linear regression unit and a screening unit. Wherein, the names of these units do not constitute a limitation to the unit itself under certain circumstances.
  • the acquisition unit can also be described as "obtaining a collection of item information, wherein the item information in the above item information collection includes: item circulation Elements of information sequence and item replenishment quantity information sequence".
  • exemplary types of hardware logic components include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), System on Chips (SOCs), Complex Programmable Logical device (CPLD) and so on.
  • FPGAs Field Programmable Gate Arrays
  • ASICs Application Specific Integrated Circuits
  • ASSPs Application Specific Standard Products
  • SOCs System on Chips
  • CPLD Complex Programmable Logical device

Landscapes

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

Abstract

本公开的实施例公开了指标确定方法、装置、电子设备和计算机可读介质。该方法的一具体实施方式包括：获取物品信息集合；根据物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组；根据库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组；根据库存满足率信息组序列和预测准确率信息组序列，进行线性回归，以生成待筛选指标序列中的每个待筛选指标对应的指标评价信息；从待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标。

Description

指标确定方法、装置、电子设备和计算机可读介质
相关申请的交叉引用
本申请要求于申请日为2022年1月11日提交的，申请号为202210024267.9、发明名称为“指标确定方法、装置、电子设备和计算机可读介质”的中国专利申请的优先权，其全部内容作为整体并入本申请中。
技术领域
本公开的实施例涉及计算机技术领域，具体涉及指标确定方法、装置、电子设备和计算机可读介质。
背景技术
需求预测，是指根据现有的数据对未来的发展趋势做出准确估计的一项技术。由于不同的预测方法的预测能力往往不同，即准确性往往存在差异。因此，需要通过预测指标进行预测评价。目前，在选用预测指标进行预测评价时，通常采用的方式为：通过人工筛选的方式选取预测指标。
发明内容
本公开的内容部分用于以简要的形式介绍构思，这些构思将在后面的具体实施方式部分被详细描述。本公开的内容部分并不旨在标识要求保护的技术方案的关键特征或必要特征，也不旨在用于限制所要求的保护的技术方案的范围。
本公开的一些实施例提出了指标确定方法、装置、电子设备和计算机可读介质，来解决以上背景技术部分提到的技术问题中的一项或多项。
第一方面，本公开的一些实施例提供了一种指标确定方法，该方 法包括：获取物品信息集合，其中，上述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列；根据上述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列；根据上述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列；根据上述库存满足率信息组序列和上述预测准确率信息组序列，进行线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列；根据上述指标评价信息序列，从上述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
第二方面，本公开的一些实施例提供了一种指标确定装置，装置包括：获取单元，被配置成获取物品信息集合，其中，上述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列；第一生成单元，被配置成根据上述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列；第二生成单元，被配置成根据上述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列；线性回归单元，被配置成根据上述库存满足率信息组序列和上述预测准确率信息组序列，进行线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列；筛选单元，被配置成根据上述指标评价信息序列，从上述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
第三方面，本公开的一些实施例提供了一种电子设备，包括：至少一个处理器；存储装置，其上存储有至少一个程序，当至少一个程序被至少一个处理器执行，使得至少一个处理器实现上述第一方面任一实现方式所描述的方法。
第四方面，本公开的一些实施例提供了一种计算机可读介质，其 上存储有计算机程序，其中，程序被处理器执行时实现上述第一方面任一实现方式所描述的方法。
附图说明
结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，元件和元素不一定按照比例绘制。
图1是本公开的一些实施例的指标确定方法的一个应用场景的示意图；
图2是根据本公开的指标确定方法的一些实施例的流程图；
图3是根据本公开的指标确定方法的另一些实施例的流程图；
图4是线性拟合曲线的示意图；
图5是根据本公开的指标确定装置的一些实施例的结构示意图；
图6是适于用来实现本公开的一些实施例的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例。相反，提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。
另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“至少一个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。
相关的指标确定方法，例如，通过人工筛选的方式选取预测指标等经常会存在如下技术问题：通过人工筛选的方式，缺乏统一和标准的预测指标选取方法，使得选取的预测指标，往往无法对预测结果进行准确评估，从而造成库存积压或库存缺货的情况出现。
为了解决以上所阐述的问题，本公开的一些实施例提出了指标确定方法及装置，提高了对预测结果的评估能力，减少了库存积压或库存缺货的情况出现。
下面将参考附图并结合实施例来详细说明本公开。
图1是本公开的一些实施例的指标确定方法的一个应用场景的示意图。
在图1的应用场景中，首先，计算设备101可以获取物品信息集合102，其中，上述物品信息集合102中的物品信息包括：物品流转信息序列103和物品补货量信息序列104；其次，计算设备101可以根据上述物品信息集合102中的每个物品信息包括的物品流转信息序列103和物品补货量信息序列104，生成库存满足信息组，得到库存满足信息组序列105；然后，计算设备101可以根据上述库存满足信息组序列105中的库存满足信息组，和待筛选指标序列106中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列107和预测准确率信息组序列108；接着，计算设备101可以根据上述库存满足率信息组序列107和上述预测准确率信息组序列108，进行线性回归，以生成上述待筛选指标序列106中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列109；最后，计算设备101可以根据上述指标评价信息序列109，从上述待筛选指标序列106中筛选出满足筛选条件的待筛选指标作为目标指 标，得到目标指标集合110。
需要说明的是，上述计算设备101可以是硬件，也可以是软件。当计算设备为硬件时，可以实现成多个服务器或终端设备组成的分布式集群，也可以实现成单个服务器或单个终端设备。当计算设备体现为软件时，可以安装在上述所列举的硬件设备中。其可以实现成例如用来提供分布式服务的多个软件或软件模块，也可以实现成单个软件或软件模块。在此不做具体限定。
应该理解，图1中的计算设备的数目仅仅是示意性的。根据实现需要，可以具有任意数目的计算设备。
继续参考图2，示出了根据本公开的指标确定方法的一些实施例的流程200。该指标确定方法，包括以下步骤：
步骤201，获取物品信息集合。
在一些实施例中，指标确定方法的执行主体(例如图1所示的计算设备101)可以通过有线连接，或无线连接的方式获取上述物品信息集合。其中，上述物品信息集合中的物品信息可以包括：物品流转信息序列和物品补货量信息序列。上述物品信息集合中的物品信息可以是相同领域内的物品的历史物品信息。物品信息包括的物品流转信息序列可以表征对应的物品在目标时间段内的物品流转情况。物品信息包括的物品补货量信息序列可以表征对应的物品在上述目标时间段内的物品补货情况。例如，物品流转信息序列中的物品流转信息可以包括：物品真实销量和物品预测销量。上述目标时间段可以是历史时间段。例如，上述目标时间段可以是2020年11月10日至2020年11月17日。
作为示例，上述物品信息集合可以是：
Figure PCTCN2022118576-appb-000001
步骤202，根据物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列。
在一些实施例中，上述执行主体可以根据上述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到上述库存满足信息组序列。其中，上述库存满足信息组序列中的库存满足信息可以表征物品的库存满足情况。
作为示例，上述库存满足信息组序列中的库存满足信息可以包括：第一库存满足信息和第二库存满足信息。其中，第一库存满足信息可以用物品流转信息包括的物品真实销量和物品预测销量的差值的表征。第二库存满足信息可以用物品流转信息包括的物品真实销量和物品补货量信息序列中与物品流转信息对应的物品补货量信息的差值表征。例如，上述执行主体可以根据上述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，通过以下公式，生成库存满足信息组：
Figure PCTCN2022118576-appb-000002
其中，i表示序号。B表示物品真实销量。C表示物品预测销量。B i表示上述物品流转信息序列中的第i个物品流转信息包括的物品真实销量。C i表示上述物品流转信息序列中的第i个物品流转信息包括的物品预测销量。D表示上述物品补货量信息序列中的物品补货量信息。 D i表示上述物品补货量信息序列中的第i个物品补货量信息。A 1表示上述库存满足信息组中的库存满足信息包括的第一库存满足信息。A 2表示上述库存满足信息组中的库存满足信息包括的第二库存满足信息。A 1，i表示上述库存满足信息组中的第i个库存满足信息包括的第一库存满足信息。A 2，i表示上述库存满足信息组中的第i个库存满足信息包括的第二库存满足信息。
例如，“物品A”对应的物品信息和库存满足信息组可以是：
Figure PCTCN2022118576-appb-000003
步骤203，根据库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列。
在一些实施例中，上述执行主体可以根据上述库存满足信息组序列中的库存满足信息组和上述待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到上述库存满足率信息组序列和上述预测准确率信息组序列。其中，上述待筛选指标序列中的待筛选指标可以是用于对预测结果进行评价的预测指标。上述待筛选指标序列中的待筛选指标可以包括相对误差类型的预测指标和绝对误差类型的预测指标。上述绝对误差类型表征预测指标用于计算预测销量和物品补货量的绝对差值。上述相对误差类型表征预测指标用于计算预测销量和物品补货量的相对差值。例如，上述绝对误差类型的预测指标可以是但不限于以下任意一项：MAE(Mean Absolute Error，平均绝对误差)预测指标，MSE(Mean Square Error，均方误差)预测指标，RMAE(Root Mean Absolute Error，平均根值绝对误差)预测指标和RMSE(Root Mean Square Error，均方根值误差)预测指标。上述相对误差类型的预测指标可以是但不限于以下任意一项：MAPE(Mean Absolute Percentage Error，平均绝对百分比误差)预测 指标，sMAPE(Symmetric Mean Absolute Percentage Error，对称平均绝对百分比误差)预测指标和MASE(Mean Absolute Scaled Error，平均绝对标度误差)预测指标。上述库存满足率信息组序列中的库存满足率信息可以表征库存的满足率。上述预测准确率信息组序列中的预测准确率信息可以表征物品销量的预测准确率。
其中，上述执行主体可以将库存满足信息组序列中的库存满足信息组中的库存满足信息包括的第一库存满足信息带入上述待筛选指标对应的公式中，以此确定预测准确率信息。上述执行主体可以根据库存满足信息包括的第二库存满足信息，以此确定库存满足率信息。例如，当第二库存满足信息为负数时，库存满足率信息可以为0％。当第二库存满足信息为正数时，库存满足率信息可以为100％。
作为示例，当待筛选指标为RMAE预测指标时，“物品A”对应的预测准确率信息组和库存满足率信息组可以是：
Figure PCTCN2022118576-appb-000004
步骤204，根据库存满足率信息组序列和预测准确率信息组序列，进行线性回归，以生成待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列。
在一些实施例中，上述执行主体可以根据上述库存满足率信息组序列和上述预测准确率信息组序列，进行线性回归，以生成待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到上述指标评价信息序列。其中，上述指标评价信息序列中的指标评价信息可以用于评价待筛选指标的指标评估能力。
作为示例，对于上述库存满足率信息组序列中的每个库存满足率信息组，上述执行主体可以将上述库存满足率信息组中的每个库存满足率信息作为因变量，将与上述库存满足信息对应的预测准确率信息作为自变量，带入如下线性回归方程，进行线性拟合：
y j＝ax j+b
其中，y表示库存满足率信息。x表示预测准确率信息。j表示序号。y j表示库存满足率信息组中的第j个库存满足率信息。x j表示预测准确率信息组中的第j个预测准确率信息。b表示截距。a表示指标评价信息。
作为示例，当待筛选指标为RMAE预测指标时，“物品A”和“物品B”对应的预测准确率信息组和库存满足率信息组可以是：
Figure PCTCN2022118576-appb-000005
得到的指标评价信息可以是-0.088134。其中，指标评价信息对应的数值越小，表征库存满足越好。
步骤205，根据指标评价信息序列，从待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
在一些实施例中，上述执行主体可以根据上述指标评价信息序列，从上述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到上述目标指标集合。其中，上述筛选条件可以是待筛选指标对应的指标评价信息小于目标数值。上述目标数值可以与排序后的指标评价信息序列中的目标位置的排序后的指标评价信息相同。上述目标位置可以人为确定。
作为示例，上述待筛选指标序列可以是[MAE预测指标，MSE预 测指标，RMAE预测指标，RMSE预测指标，MAPE预测指标，sMAPE预测指标，MASE预测指标]。上述指标评价信息序列可以是[-0.007，-0.011，-0.09，-0.007，-0.012，-0.029，-0.244]。上述目标位置可以是“3”。排序后的指标评价信息序列可以是[-0.244，-0.09，-0.029，-0.012，-0.011，-0.007，-0.007]。则上述目标数值为“-0.029”。则将满足上述筛选条件的待筛选指标作为目标指标，得到的目标指标集合为[MASE预测指标，RMAE预测指标]。
本公开的上述各个实施例具有如下有益效果：通过本公开的一些实施例的指标确定方法，提高了对预测结果的评估能力，减少了库存积压或库存缺货的情况出现。具体来说，造成库存积压或库存缺货的原因在于：通过人工筛选的方式，缺乏统一和标准的预测指标选取方法，使得选取的预测指标，往往无法对预测结果就像准确评估，从而造成库存积压或库存缺货的情况出现。基于此，本公开的一些实施例的指标确定方法，首先，获取物品信息集合，其中，上述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列。通过获取历史，以使得可以根据历史数据进行预测指标的评估。其次，根据上述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列。通过每个物品信息对应的物品的流转情况和补货情况，以此确定物品对应的库存补货准确率情况。然后，根据上述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列。通过历史库存补货准确率情况和每个预测指标，以此确定每个预测指标的预测准确率和库存满足情况。然后，根据上述库存满足率信息组序列和上述预测准确率信息组序列，进行线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列。通过线性回归的方式，以此量化每个预测指标的预测能力。最后，根据上述指标评价信息序列，从上述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。通过筛选以此确定预测评价能力较强的预测 指标。通过此种方式，统一化和标准化了预测指标的选取方式，同时量化了每个预测指标的预测评价能力，以此解决了需求预测结果易受到人工筛选存在的问题(如，随机性)的影响，提高了对预测结果的评估准确性，减少了库存积压或库存缺货情况的出现。
参考图3，其示出了指标确定方法的另一些实施例的流程300。该指标确定方法的流程300，包括以下步骤：
步骤301，获取物品信息集合。
在一些实施例中，步骤301的具体实现及其所带来的技术效果，可以参考图2对应的那些实施例中的步骤201，在此不再赘述。
步骤302，对于物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定物品补货量信息大于目标物品流转信息，将库存满载信息，确定为物品补货量信息对应的库存满足信息包括的库存状态标识。
在一些实施例中，指标确定方法的执行主体(例如图1所示的计算设备101)可以对于物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定物品补货量信息大于目标物品流转信息，将库存满载信息，确定为物品补货量信息对应的库存满足信息包括的库存状态标识。其中，上述库存满足信息组序列中的库存满足信息包括：库存状态标识。上述库存状态标识可以用于表征库存满足情况。上述目标物品流转信息可以是上述物品信息包括的物品流转信息序列中与上述物品补货量信息对应的物品流转信息。上述库存满载信息可以表征物品补货量信息大于目标物流转信息包括的物品真实销量。例如，上述物品补货量信息可以用“1”表征。
步骤303，对于物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定物品补货量信息小于等于目标物品流转信息，将库存缺货信息，确定为物品补货量信息对应的库存满足信息包括的库存状态标识。
在一些实施例中，上述执行主体可以对于物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定物品补货量信息 小于等于目标物品流转信息，将库存缺货信息，确定为物品补货量信息对应的库存满足信息包括的库存状态标识。上述库存缺货信息可以表征物品补货量信息大于目标物流转信息包括的物品真实销量。例如，上述库存缺货信息可以用“0”表征。
作为示例，“物品A”对应的物品信息和对应的库存满足信息组可以是：
Figure PCTCN2022118576-appb-000006
步骤304，根据库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列。
在一些实施例中，上述执行主体可以根据上述库存满足信息组序列中的库存满足信息组和上述待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到上述库存满足率信息组序列和上述预测准确率信息组序列。其中，上述执行主体可以对于上述库存满足信息组序列中的每个库存满足信息组，执行以下处理步骤：
第一步，基于预设的滑动窗口大小和预设滑动长度，对上述库存满足信息组进行划分，以生成子库存满足信息组，得到子库存满足信息组序列。
其中，上述滑动窗口的大小可以是人工设置的。上述预设滑动长度可以表征上述滑动窗口的移动步长。例如，上述滑动窗口可以是“7”。上述预设的滑动长度可以是“1”。
作为示例，“物品A”对应的库存满足信息组可以是：
日期 第一库存满足信息 库存状态标识
2021-04-15 24 0
2021-04-16 -2 1
2021-04-17 11 1
... ... ...
2021-07-10 2 0
其中，“物品A”对应的库存满足信息组的时间跨度可以是从2021-04-15至2021-07-10，共计86天。上述执行主体可以以7天为一个滑动窗口，1天为预设滑动长度，对上述86条库存满足信息进行划分，以生成80个子库存满足信息组。
第二步，基于上述子库存满足信息组序列中的每个子库存满足信息组和上述待筛选指标序列中的每个待筛选指标，生成库存满足率信息和预测准确率信息，得到上述库存满足信息组对应的库存满足率信息组和预测准确率信息组。
其中，库存满足率信息可以表征一个子库存满足信息组对应的各个库存满足率。预测准确率信息可以表征一个子库存满足信息组对应的各个待筛选指标的预测准确率。
作为示例，上述执行主体可以将上述子库存满足信息组中包含的库存状态标识为“1的”子库存满足信息的数量与滑动窗口的长度的比值，确定为库存满足率信息中的一个值。例如，“物品A”在2021-04-15至2021-07-10内，对应的80个子库存满足信息组，对应的库存满足率信息可以是[95％，90％，97％，96％，...，91％]。上述待筛选指标序列可以是[MAE预测指标，MSE预测指标，RMAE预测指标，RMSE预测指标]上述预测准确率信息可以是[8.8，7.7，3.2，4.4]。其中，“8.8”可以表征“MAE预测指标”的预测准确率。“7.7”可以表征“MSE预测指标”的预测准确率。“3.2”可以表征“RMAE预测指标”的预测准确率。“4.4”可以表征“RMSE预测指标”的预测准确率。
步骤305，根据库存满足率信息组序列和预测准确率信息组序列， 进行线性回归，以生成待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列。
在一些实施例中，上述执行主体根据上述库存满足率信息组序列和上述预测准确率信息组序列，进行线性回归，以生成待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到上述指标评价信息序列，可以包括以下步骤：
第一步，根据上述物品流转信息序列，分别对上述库存满足率信息组序列中的库存满足率信息，和上述预测准确率信息组序列中的预测准确率信息进行划分，以生成划分后的库存满足率信息组序列和划分后的预测准确率信息组序列。
作为示例，上述执行主体根据物品流转信息序列中物品流转信息包括的物品真实销量，分别对上述库存满足率信息组序列中的库存满足率信息，和上述预测准确率信息组序列中的预测准确率信息进行划分，以生成划分后的库存满足率信息组序列和划分后的预测准确率信息组序列。其中，划分后的库存满足率信息组，为对应的物品流转信息包括的物品真实销量相近的物品流转信息对应的库存满足率信息组。
例如，上述物品信息集合可以是[物品信息A，物品信息B，物品信息C，物品信息D，物品信息F]。上述物品信息集合对应的库存满足率信息组序列可以是{[库存满足率信息A，库存满足率信息B，库存满足率信息C]，[库存满足率信息D，库存满足率信息E，库存满足率信息F]，[库存满足率信息G，库存满足率信息H，库存满足率信息I]，[库存满足率信息J，库存满足率信息K，库存满足率信息L，[库存满足率信息M，库存满足率信息N，库存满足率信息0]}。“物品信息A”和包括的物品真实销量和“物品信息B”包括的物品真实销量相近，因此，可以将[库存满足率信息A，库存满足率信息B，库存满足率信息C]和[库存满足率信息D，库存满足率信息E，库存满足率信息F]组合，以生成划分后的库存满足率信息组[库存满足率信息A，库存满足率信息B，库存满足率信息C，库存满足率信息D，库存满足率信息E，库存满足率信息F]。
又如，上述物品信息集合可以是[物品信息A，物品信息B，物品信息C]。对应的预测准确率信息组序列可以是{[预测准确率信息A，预测准确率信息B]，[预测准确率信息C，预测准确率信息D]，[预测准确率信息E，预测准确率信息F]}。“物品信息A”和包括的物品真实销量和“物品信息B”包括的物品真实销量相近，因此，可以将[预测准确率信息A，预测准确率信息B]和[预测准确率信息C，预测准确率信息D]组合，以生成划分后的预测准确率信息组。
第二步，根据上述划分后的库存满足率信息组序列中的每个划分后的库存满足率信息组，和上述划分后的库存满足率信息组对应的划分后的预测准确率信息组，进行单元线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息。
作为示例，上述待筛选指标集合可以是[MAE预测指标，MSE预测指标，RMAE预测指标，RMSE预测指标]。对于上述待筛选指标集合中的每个待筛选指标，上述执行主体可以根据上述划分后的库存满足率信息组，和上述划分后的库存满足率信息组对应的划分后的预测准确率信息组，通过以下第一线性回归公式，进行单元线性回归，以生成上述待筛选指标对应的指标评价信息中的一个指标评价数值：
y s，e＝ax s，e+b+ε
其中，a表示指标评价信息中的一个指标评价数值。b表示截距。ε表示波动项。其中，上述波动项可以是人工设置的。s表示上述划分后的库存满足率信息组中的第s个划分后的库存满足率信息的位置，或表示划分后的预测准确率信息组中的第s个划分后的预测准确率信息的位置。e表示上述划分后的库存满足率信息组中的第s个划分后的库存满足率信息包括的第e个库存满足率的位置，或表示上述划分后的预测准确率信息组中的第s个划分后的预测准确率信息包括的第e个预测准确率的位置。y表示上述划分后的库存满足率信息中包括的库存满足率。y s，e表示上述划分后的库存满足率信息组中的第s个划分后的库存满足率信息包括的第e个库存满足率。x表示上述划分后的预测准确率信息组中的划分后的预测准确率信息。x s，e表示上述划分后的预测准确率信息组中的第s个划分后的预测准确率信息中的第e个 预测准确率。
作为示例，如图4所示，其中，图4示出了上述公式对应的线性拟合曲线401。
作为又一示例，上述待筛选指标集合可以是[MAE预测指标，MAE预测指标，RMAE预测指标，RMSE预测指标，MAPE预测指标，sMAPE预测指标，MASE预测指标]。上述待筛选指标集合对应的指标评价信息集合可以是：
Figure PCTCN2022118576-appb-000007
可选地，上述执行主体可以根据上述划分后的库存满足率信息组序列和上述划分后的预测准确率信息组序列，进行多元线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息。其中，对于上述待筛选指标序列中的每个待筛选指标，上述执行主体可以根据上述划分后的库存满足信息组序列和上述划分后的预测准确率信息组序列，通过以下第二线性回归公式，进行多元线性回归，以生成上述待筛选指标对应的指标评价信息中的一个指标评价数值：
Figure PCTCN2022118576-appb-000008
其中，a表示指标评价信息中的一个指标评价数值。b表示截距。ε表示波动项。其中，上述波动项可以是人工设置的。s表示上述划分后的库存满足率信息组中的第s个划分后的库存满足率信息的位置，或表示划分后的预测准确率信息组中的第s个划分后的预测准确率信息的位置。e表示上述划分后的库存满足率信息组中的第s个划分后的库存满足率信息包括的第e个库存满足率的位置，或表示上述划分后的预测准确率信息组中的第s个划分后的预测准确率信息包括的第e个预测准确率的位置。y表示上述划分后的库存满足率信息中包括的 库存满足率。y s，e表示上述划分后的库存满足率信息组中的第s个划分后的库存满足率信息包括的第e个库存满足率。x表示上述划分后的预测准确率信息组中的划分后的预测准确率信息。x s，e表示上述划分后的预测准确率信息组中的第s个划分后的预测准确率信息中的第e个预测准确率。P表示上述划分后的库存满足率信息组序列中的划分后的库存满足率信息组的数量。k表示序号。Band k表示第k个划分后的库存满足率信息对应的物品信息组的物品类别。c 1+k表示第k个划分后的库存满足率信息对应的物品信息组的物品类别的系数。
作为示例，上述待筛选指标集合可以是[MAE预测指标，MAE预测指标，RMAE预测指标，RMSE预测指标，MAPE预测指标，sMAPE预测指标，MASE预测指标]。上述待筛选指标集合对应的指标评价信息集合可以是：
指标名称 指标评价信息
MAE预测指标 -0.007
MAE预测指标 -0.011
RMAE预测指标 -0.090
RMSE预测指标 -0.007
MAPE预测指标 -0.012
sMAPE预测指标 -0.029
MASE预测指标 -0.244
可选地，上述执行主体可以根据上述划分后的库存满足率信息组序列和划分后的预测准确率信息组序列，进行单元线性回归和多元线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到上述指标评价信息序列。
其中，上述执行主体可以采用上述第一线性回归公式和上述第二线性回归公式，确定上述待筛选指标对应的指标评价信息。
步骤306，根据指标评价信息序列，从待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
在一些实施例中，步骤306具体实现及其所带来的技术效果，可以参考图2对应的那些实施例中的步骤205在此不再赘述。
可选地，当上述执行主体根据上述划分后的库存满足率信息组序列和划分后的预测准确率信息组序列，进行单元线性回归和多元线性 回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息时，上述执行主体可以通过以下步骤，根据上述指标评价信息序列，从上述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到上述目标指标集合：
第一步，对于所述指标评价信息集合中的每个指标评价信息，确定上述指标评价信息中满足筛选条件的指标评价数值对应待筛选预测指标，得到候选预测指标组。
其中，所述筛选条件为，指标评价数值小于目标数值。上述目标数值可以与指标评价信息中排序后的目标位置的指标评价数值相同。上述目标位置可以人为确定。
第二步，确定得到的至少一个候选预测指标组中的候选预测指标的出现次数，以及将出现次数满足候选预测指标筛选条件的候选预测指标作为目标指标，得到上述目标指标集合。
作为示例，上述候选预测指标筛选条件可以是，候选预测指标出现次数大于目标出现次数。例如，上述目标出现次数可以是2。
与图2对应的一些实施例相比，图3对应的一些实施例中的指标确定方法的流程300，首先，根据物品流转信息序列，分别对上述库存满足率信息组序列中的库存满足率信息，和上述预测准确率信息组序列中的预测准确率信息进行划分，以生成划分后的库存满足率信息组序列和划分后的预测准确率信息组序列。以使得物品实际销量相似的物品对应的库存满足率信息位于同组中，以及使得实际销量相似的物品对应的预测准确率信息位于同组中。然后，根据上述划分后的库存满足率信息组序列中的每个划分后的库存满足率信息组，和上述划分后的库存满足率信息组对应的划分后的预测准确率信息组，进行单元线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息。以使得单元线性回归后的拟合曲线两侧不会存在较多地离散点。此外，在进行单元线性拟合和多元线性拟合时，通过根据待筛选指标在不同线性拟合方法下得到的指标评价信息的交集，从而筛选出具有较好预测评价能力的预测指标。
参考图5，作为对上述各图所示方法的实现，本公开提供了一种指标确定装置的一些实施例，这些装置实施例与图2所示的那些方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图5所示，一些实施例的指标确定装置500包括：获取单元501，被配置成获取物品信息集合，其中，上述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列；第一生成单元502，被配置成根据上述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列；第二生成单元503，被配置成根据上述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列；线性回归单元504，被配置成根据上述库存满足率信息组序列和上述预测准确率信息组序列，进行线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列；筛选单元505，被配置成根据上述指标评价信息序列，从上述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
在一些实施例的一些可选地实现方式中，上述库存满足信息组序列中的库存满足信息包括：库存状态标识；以及上述第一生成单元502被配置成：对于上述物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定上述物品补货量信息大于目标物品流转信息，将库存满载信息，确定为上述物品补货量信息对应的库存满足信息包括的库存状态标识，其中，上述目标物品流转信息是上述物品信息包括的物品流转信息序列中与上述物品补货量信息对应的物品流转信息。
在一些实施例的一些可选地实现方式中，上述第一生成单元502被配置成：对于上述物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定上述物品补货量信息小于等于上述目标物品流转信息，将库存缺货信息，确定为上述物品补货量信息对应的库存满足信息包括的库存状态标识。
在一些实施例的一些可选地实现方式中，上述第二生成单元503被配置成：对于上述库存满足信息组序列中的每个库存满足信息组，执行以下处理步骤：基于预设的滑动窗口大小和预设滑动长度，对上述库存满足信息组进行划分，以生成子库存满足信息组，得到子库存满足信息组序列；基于上述子库存满足信息组序列中的每个子库存满足信息组和上述待筛选指标序列中的每个待筛选指标，生成库存满足率信息和预测准确率信息，得到上述库存满足信息组对应的库存满足率信息组和预测准确率信息组。
在一些实施例的一些可选地实现方式中，上述线性回归单元504被配置成：根据上述物品流转信息序列，分别对上述库存满足率信息组序列中的库存满足率信息，和上述预测准确率信息组序列中的预测准确率信息进行划分，以生成划分后的库存满足率信息组序列和划分后的预测准确率信息组序列。
在一些实施例的一些可选地实现方式中，上述线性回归单元504被配置成：根据上述划分后的库存满足率信息组序列和划分后的预测准确率信息组序列，进行单元线性回归和多元线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到上述指标评价信息序列。
在一些实施例的一些可选地实现方式中，上述线性回归单元504被配置成：根据上述划分后的库存满足率信息组序列中的每个划分后的库存满足率信息组，和上述划分后的库存满足率信息组对应的划分后的预测准确率信息组，进行单元线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息。
在一些实施例的一些可选地实现方式中，上述线性回归单元504被配置成：根据上述划分后的库存满足率信息组序列和上述划分后的预测准确率信息组序列，进行多元线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息。
可以理解的是，该装置500中记载的诸单元与参考图2描述的方法中的各个步骤相对应。由此，上文针对方法描述的操作、特征以及产生的有益效果同样适用于装置500及其中包含的单元，在此不再赘 述。
下面参考图6，其示出了适于用来实现本公开的一些实施例的电子设备(如图1所示的计算设备101)600的结构示意图。图6示出的电子设备仅仅是一个示例，不应对本公开的实施例的功能和使用范围带来任何限制。
如图6所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)601，其可以根据存储在只读存储器(ROM)602中的程序或者从存储装置608加载到随机访问存储器(RAM)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有电子设备600操作所需的各种程序和数据。处理装置601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。
通常，以下装置可以连接至I/O接口605：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置606；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置607；包括例如磁带、硬盘等的存储装置608；以及通信装置609。通信装置609可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。图6中示出的每个方框可以代表一个装置，也可以根据需要代表多个装置。
特别地，根据本公开的一些实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的一些实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的一些实施例中，该计算机程序可以通过通信装置609从网络上被下载和安装，或者从存储装置608被安装，或者从ROM 602被安装。在该计算机程序被处理装置601执行时，执行本公开的一些实施例的方法中限定的上述功能。
需要说明的是，本公开的一些实施例中记载的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有至少一个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开的一些实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开的一些实施例中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。
在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使 得该电子设备：获取物品信息集合，其中，上述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列；根据上述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列；根据上述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列；根据上述库存满足率信息组序列和上述预测准确率信息组序列，进行线性回归，以生成上述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列；根据上述指标评价信息序列，从上述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
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公开的一些实施例的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)——连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含至少一个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是， 框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开的一些实施例中的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括获取单元、第一生成单元、第二生成单元、线性回归单元和筛选单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，获取单元还可以被描述为“获取物品信息集合，其中，上述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列的单元”。
本文中以上描述的功能可以至少部分地由至少一个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
以上描述仅为本公开的一些较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开的实施例中所涉及的发明范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开的实施例中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (11)

  1. 一种指标确定方法，包括：
    获取物品信息集合，其中，所述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列；
    根据所述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列；
    根据所述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列；
    根据所述库存满足率信息组序列和所述预测准确率信息组序列，进行线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列；
    根据所述指标评价信息序列，从所述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
  2. 根据权利要求1所述的方法，其中，所述库存满足信息组序列中的库存满足信息包括：库存状态标识；以及
    所述根据所述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，包括：
    对于所述物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定所述物品补货量信息大于目标物品流转信息，将库存满载信息，确定为所述物品补货量信息对应的库存满足信息包括的库存状态标识，其中，所述目标物品流转信息是所述物品信息包括的物品流转信息序列中与所述物品补货量信息对应的物品流转信息。
  3. 根据权利要求2所述的方法，其中，所述根据所述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，还包括：
    对于所述物品信息包括的物品补货量信息序列中的每个物品补货量信息，响应于确定所述物品补货量信息小于等于所述目标物品流转信息，将库存缺货信息，确定为所述物品补货量信息对应的库存满足信息包括的库存状态标识。
  4. 根据权利要求1-3之一所述的方法，其中，所述根据所述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，包括：
    对于所述库存满足信息组序列中的每个库存满足信息组，执行以下处理步骤：
    基于预设的滑动窗口大小和预设滑动长度，对所述库存满足信息组进行划分，以生成子库存满足信息组，得到子库存满足信息组序列；
    基于所述子库存满足信息组序列中的每个子库存满足信息组和所述待筛选指标序列中的每个待筛选指标，生成库存满足率信息和预测准确率信息，得到所述库存满足信息组对应的库存满足率信息组和预测准确率信息组。
  5. 根据权利要求1-4之一所述的方法，其中，所述根据所述库存满足率信息组序列和所述预测准确率信息组序列，进行线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列，包括：
    根据物品流转信息序列，分别对所述库存满足率信息组序列中的库存满足率信息，和所述预测准确率信息组序列中的预测准确率信息进行划分，以生成划分后的库存满足率信息组序列和划分后的预测准确率信息组序列。
  6. 根据权利要求5所述的方法，其中，所述根据所述库存满足率信息组序列和所述预测准确率信息组序列，进行线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列，还包括：
    根据所述划分后的库存满足率信息组序列和划分后的预测准确率信息组序列，进行单元线性回归和多元线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到所述指标评价信息序列。
  7. 根据权利要求5所述的方法，其中，所述根据所述库存满足率信息组序列和所述预测准确率信息组序列，进行线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息，还包括：
    根据所述划分后的库存满足率信息组序列中的每个划分后的库存满足率信息组，和所述划分后的库存满足率信息组对应的划分后的预测准确率信息组，进行单元线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息。
  8. 根据权利要求5所述的方法，其中，所述根据所述库存满足率信息组序列和所述预测准确率信息组序列，进行线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息，还包括：
    根据所述划分后的库存满足率信息组序列和所述划分后的预测准确率信息组序列，进行多元线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息。
  9. 一种指标确定装置，包括：
    获取单元，被配置成获取物品信息集合，其中，所述物品信息集合中的物品信息包括：物品流转信息序列和物品补货量信息序列；
    第一生成单元，被配置成根据所述物品信息集合中的每个物品信息包括的物品流转信息序列和物品补货量信息序列，生成库存满足信息组，得到库存满足信息组序列；
    第二生成单元，被配置成根据所述库存满足信息组序列中的库存满足信息组和待筛选指标序列中的每个待筛选指标，生成库存满足率信息组和预测准确率信息组，得到库存满足率信息组序列和预测准确率信息组序列；
    线性回归单元，被配置成根据所述库存满足率信息组序列和所述预测准确率信息组序列，进行线性回归，以生成所述待筛选指标序列中的每个待筛选指标对应的指标评价信息，得到指标评价信息序列；
    筛选单元，被配置成根据所述指标评价信息序列，从所述待筛选指标序列中筛选出满足筛选条件的待筛选指标作为目标指标，得到目标指标集合。
  10. 一种电子设备，包括：
    至少一个处理器；
    存储装置，其上存储有至少一个程序；
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1至8中任一所述的方法。
  11. 一种计算机可读介质，其上存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1至8中任一所述的方法。
PCT/CN2022/118576 2022-01-11 2022-09-14 指标确定方法、装置、电子设备和计算机可读介质 WO2023134188A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210024267.9A CN114049072B (zh) 2022-01-11 2022-01-11 指标确定方法、装置、电子设备和计算机可读介质
CN202210024267.9 2022-01-11

Publications (1)

Publication Number Publication Date
WO2023134188A1 true WO2023134188A1 (zh) 2023-07-20

Family

ID=80213671

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/118576 WO2023134188A1 (zh) 2022-01-11 2022-09-14 指标确定方法、装置、电子设备和计算机可读介质

Country Status (2)

Country Link
CN (1) CN114049072B (zh)
WO (1) WO2023134188A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117077982A (zh) * 2023-10-16 2023-11-17 北京国电通网络技术有限公司 项目物资调度方法、装置、电子设备和可读介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114049072B (zh) * 2022-01-11 2022-06-07 北京京东振世信息技术有限公司 指标确定方法、装置、电子设备和计算机可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100125486A1 (en) * 2008-11-14 2010-05-20 Caterpillar Inc. System and method for determining supply chain performance standards
CN111325587A (zh) * 2018-12-13 2020-06-23 北京京东尚科信息技术有限公司 用于生成信息的方法和装置
CN112036802A (zh) * 2020-11-04 2020-12-04 北京每日优鲜电子商务有限公司 物品补货信息显示方法、装置、电子设备和可读介质
CN113837678A (zh) * 2021-03-01 2021-12-24 北京京东振世信息技术有限公司 补货任务信息生成方法、装置、电子设备以及存储介质
CN114049072A (zh) * 2022-01-11 2022-02-15 北京京东振世信息技术有限公司 指标确定方法、装置、电子设备和计算机可读介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170024751A1 (en) * 2015-07-23 2017-01-26 Wal-Mart Stores, Inc. Fresh production forecasting methods and systems
CN109961198B (zh) * 2017-12-25 2021-12-31 北京京东尚科信息技术有限公司 关联信息生成方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100125486A1 (en) * 2008-11-14 2010-05-20 Caterpillar Inc. System and method for determining supply chain performance standards
CN111325587A (zh) * 2018-12-13 2020-06-23 北京京东尚科信息技术有限公司 用于生成信息的方法和装置
CN112036802A (zh) * 2020-11-04 2020-12-04 北京每日优鲜电子商务有限公司 物品补货信息显示方法、装置、电子设备和可读介质
CN113837678A (zh) * 2021-03-01 2021-12-24 北京京东振世信息技术有限公司 补货任务信息生成方法、装置、电子设备以及存储介质
CN114049072A (zh) * 2022-01-11 2022-02-15 北京京东振世信息技术有限公司 指标确定方法、装置、电子设备和计算机可读介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117077982A (zh) * 2023-10-16 2023-11-17 北京国电通网络技术有限公司 项目物资调度方法、装置、电子设备和可读介质
CN117077982B (zh) * 2023-10-16 2024-01-12 北京国电通网络技术有限公司 项目物资调度方法、装置、电子设备和可读介质

Also Published As

Publication number Publication date
CN114049072A (zh) 2022-02-15
CN114049072B (zh) 2022-06-07

Similar Documents

Publication Publication Date Title
WO2023134188A1 (zh) 指标确定方法、装置、电子设备和计算机可读介质
US10608905B2 (en) Method and system for temporal sampling in evolving network
CN109697522B (zh) 一种数据预测的方法和装置
JP7294369B2 (ja) 情報処理に用いられる方法、装置、電子機器及びプログラム
CN115085196B (zh) 电力负荷预测值确定方法、装置、设备和计算机可读介质
CN114004425B (zh) 物品流转信息预测模型生成方法、信息生成方法、装置
CN111783810A (zh) 用于确定用户的属性信息的方法和装置
CN110766184A (zh) 订单量预测方法和装置
US11645540B2 (en) Deep graph de-noise by differentiable ranking
CN116822803A (zh) 基于智能算法的碳排放数据图构建方法、装置与设备
CN113435632A (zh) 信息生成方法、装置、电子设备和计算机可读介质
CN113326449A (zh) 预测交通流量的方法、装置、电子设备和介质
CN112102043A (zh) 物品推荐页面生成方法、装置、电子设备和可读介质
CN116128135A (zh) 数据处理方法及装置、电子设备和存储介质
CN112906723B (zh) 一种特征选择的方法和装置
CN116523446A (zh) 物品流转量信息发送方法、装置、设备和计算机可读介质
WO2023155425A1 (zh) 调货方法、装置、电子设备和计算机可读介质
CN114792258B (zh) 信息生成方法、装置、电子设备和计算机可读介质
CN116862319B (zh) 电力指标信息生成方法、装置、电子设备和介质
CN117077982B (zh) 项目物资调度方法、装置、电子设备和可读介质
WO2024060587A1 (zh) 自监督学习模型的生成方法和转化率预估模型的生成方法
CN110147489B (zh) 互联网用户信息预测方法
CN114612128A (zh) 基于大数据的数字优惠券生成方法、装置、设备及介质
CN115567406A (zh) 一种管理网络节点的方法、装置和系统
CN115640917A (zh) 物品需求量生成方法、装置、设备、介质和程序产品

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: 22919824

Country of ref document: EP

Kind code of ref document: A1