CN114049072B

CN114049072B - Index determination method and device, electronic equipment and computer readable medium

Info

Publication number: CN114049072B
Application number: CN202210024267.9A
Authority: CN
Inventors: 于莹; 马晓雯; 高振羽; 庄晓天; 张轩琪
Original assignee: Beijing Jingdong Zhenshi Information Technology Co Ltd
Current assignee: Beijing Jingdong Zhenshi Information Technology Co Ltd
Priority date: 2022-01-11
Filing date: 2022-01-11
Publication date: 2022-06-07
Anticipated expiration: 2042-01-11
Also published as: CN114049072A; WO2023134188A1

Abstract

The embodiment of the disclosure discloses an index determination method, an index determination device, electronic equipment and a computer readable medium. One embodiment of the method comprises: acquiring an article information set; generating an inventory satisfaction information group according to an article circulation information sequence and an article replenishment quantity information sequence which are included in each article information in the article information set; generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index to be screened in the index sequence to be screened in the inventory satisfaction information group sequence; performing linear regression according to the inventory satisfaction rate information group sequence and the 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 screening the indexes to be screened which meet the screening conditions from the index sequences to be screened as target indexes. The embodiment improves the accuracy of the estimation of the prediction result and reduces the occurrence of stock backlog or stock shortage.

Description

Index determination method and device, electronic equipment and computer readable medium

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to an index determination method, an index determination device, electronic equipment and a computer readable medium.

Background

Demand forecasting refers to a technique for accurately estimating future development trends according to existing data. Since the prediction capabilities of different prediction methods are often different, i.e., there is often a difference in accuracy. Therefore, it is necessary to perform prediction evaluation by a prediction index. Currently, when a prediction index is selected for prediction evaluation, the following methods are generally adopted: and selecting a prediction index by a manual screening mode.

However, when the above-described manner is adopted, there are often technical problems as follows:

due to the fact that a unified and standard prediction index selection method is lacked in a manual screening mode, the selected prediction index cannot accurately evaluate a prediction result, and the condition of stock overstock or stock shortage occurs.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose index determination methods, apparatuses, electronic devices, and computer readable media to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide an index determination method, including: acquiring an article information set, wherein article information in the article information set comprises: the article circulation information sequence and the article replenishment quantity information sequence; generating an inventory satisfaction information group according to an article circulation information sequence and an article replenishment quantity information sequence which are included in each article information in the article information set, and obtaining an inventory satisfaction information group sequence; generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index sequence to be screened in the inventory satisfaction information group sequence to obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence; performing linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened, so as to obtain an index evaluation information sequence; and according to the index evaluation information sequence, screening the indexes to be screened which meet the screening condition from the index sequences to be screened as target indexes to obtain a target index set.

Optionally, the inventory satisfaction information in the sequence of inventory satisfaction information sets includes: identifying the stock state; and the generating of the stock satisfaction information group according to the article circulation information sequence and the article replenishment quantity information sequence included in each article information in the article information set comprises: and 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 target item circulation information, determining inventory full information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information, 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.

Optionally, the generating an 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 item information set further includes: and 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, determining inventory shortage information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information.

Optionally, the generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index to be screened in the inventory satisfaction information group sequence includes: for each inventory fulfillment information group in the sequence of inventory fulfillment information groups, performing the following processing steps: dividing the stock meeting information group based on the size of a preset sliding window and a preset sliding length to generate a sub-stock meeting information group and obtain a sub-stock meeting information group sequence; and generating inventory satisfaction rate information and prediction accuracy rate information based on each sub-inventory satisfaction information group in the sub-inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, and obtaining an inventory satisfaction rate information group and a prediction accuracy rate information group corresponding to the inventory satisfaction information group.

Optionally, the performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence includes: and according to the article circulation information sequence, respectively dividing the inventory satisfaction rate information in the inventory satisfaction rate information group sequence and the prediction accuracy rate information in the prediction accuracy rate information group sequence to generate a divided inventory satisfaction rate information group sequence and a divided prediction accuracy rate information group sequence.

Optionally, the performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence, further includes: and performing unit linear regression and multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened, so as to obtain the index evaluation information sequence.

Optionally, the performing linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate the index evaluation information corresponding to each index to be screened in the index sequence to be screened further includes: and performing unit linear regression according to each divided inventory satisfaction rate information group in the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group corresponding to the divided inventory satisfaction rate information group to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened.

Optionally, the performing linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate the index evaluation information corresponding to each index to be screened in the index sequence to be screened further includes: and performing multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened.

In a second aspect, some embodiments of the present disclosure provide an index determining apparatus, the apparatus comprising: an acquisition unit configured to acquire an item information set, wherein item information in the item information set includes: the article circulation information sequence and the article replenishment quantity information sequence; the first generating unit is configured to generate an inventory satisfaction information group according to an article circulation information sequence and an article replenishment quantity information sequence which are included in each article information in the article information set, and obtain an inventory satisfaction information group sequence; a second generating unit configured to generate an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index to be screened in the inventory satisfaction information group sequence, and obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence; a linear regression unit configured to perform linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence; and the screening unit is configured to screen out the indexes to be screened which meet the screening conditions from the index sequences to be screened as target indexes according to the index evaluation information sequences to obtain a target index set.

Optionally, the inventory satisfaction information in the sequence of inventory satisfaction information sets includes: identifying the stock state; and the first generating unit is further configured to: and 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 target item circulation information, determining inventory full information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information, 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.

Optionally, the first generating unit is further configured to: and 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, determining inventory shortage information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information.

Optionally, the second generating unit is further configured to: for each inventory fulfillment information group in the sequence of inventory fulfillment information groups, performing the following processing steps: dividing the stock meeting information group based on the size of a preset sliding window and a preset sliding length to generate a sub-stock meeting information group and obtain a sub-stock meeting information group sequence; and generating inventory satisfaction rate information and prediction accuracy rate information based on each sub-inventory satisfaction information group in the sub-inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, and obtaining an inventory satisfaction rate information group and a prediction accuracy rate information group corresponding to the inventory satisfaction information group.

Optionally, the linear regression unit is further configured to: and according to the article circulation information sequence, respectively dividing the inventory satisfaction rate information in the inventory satisfaction rate information group sequence and the prediction accuracy rate information in the prediction accuracy rate information group sequence to generate a divided inventory satisfaction rate information group sequence and a divided prediction accuracy rate information group sequence.

Optionally, the linear regression unit is further configured to: and performing unit linear regression and multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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, so as to obtain the index evaluation information sequence.

Optionally, the linear regression unit is further configured to: and performing unit linear regression according to each divided inventory satisfaction rate information group in the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group corresponding to the divided inventory satisfaction rate information group to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened.

Optionally, the linear regression unit is further configured to: and performing multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following advantages: through the index determination method of some embodiments of the disclosure, the evaluation capability of the prediction result is improved, and the occurrence of stock backlog or stock shortage is reduced. Specifically, the reasons for backlog or stock backorder are: due to the fact that a unified and standard prediction index selection method is lacked in a manual screening mode, the selected prediction index cannot accurately evaluate the prediction result, and the condition of stock overstock or stock shortage occurs. Based on this, the index determining method of some embodiments of the present disclosure first obtains an item information set, where item information in the item information set includes: the article circulation information sequence and the article replenishment quantity information sequence. By acquiring the history, it is possible to make the evaluation of the prediction index from the history data. Secondly, according to the article circulation information sequence and the article replenishment quantity information sequence included by each article information in the article information set, an inventory satisfaction information group is generated, and an inventory satisfaction information group sequence is obtained. And determining the inventory replenishment accuracy condition corresponding to the article according to the circulation condition and the replenishment condition of the article corresponding to each article information. And then, generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index sequence to be screened in the inventory satisfaction information group sequence to obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence. And determining the prediction accuracy and the inventory satisfaction condition of each prediction index according to the historical inventory replenishment accuracy and each prediction index. And then, performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence. The prediction ability of each prediction index is quantified by means of linear regression. And finally, according to the index evaluation information sequence, screening the indexes to be screened which meet the screening condition from the index sequences to be screened as target indexes to obtain a target index set. And determining the prediction index with strong prediction evaluation capability by screening. By the method, the selection mode of the prediction indexes is unified and standardized, and the prediction evaluation capability of each prediction index is quantized, so that the problem that the demand prediction result is easily influenced by manual screening (such as randomness) is solved, the evaluation accuracy of the prediction result is improved, and the stock overstock or stock shortage is reduced.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.

FIG. 1 is a schematic diagram of one application scenario of an index determination method of some embodiments of the present disclosure;

FIG. 2 is a flow diagram of some embodiments of an index determination method according to the present disclosure;

FIG. 3 is a flow diagram of further embodiments of an index determination method according to the present disclosure;

FIG. 4 is a schematic illustration of a linear fit curve;

FIG. 5 is a schematic block diagram of some embodiments of an index determination apparatus according to the present disclosure;

FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 is a schematic diagram of an application scenario of the index determination method of some embodiments of the present disclosure.

In the application scenario of fig. 1, first, the computing device 101 may obtain an item information set 102, where item information in the item information set 102 includes: an article circulation information sequence 103 and an article replenishment quantity information sequence 104; secondly, the computing device 101 may generate an 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 item information set 102, so as to obtain an inventory satisfaction information group sequence 105; then, the computing device 101 may generate an inventory satisfaction rate information group and a prediction accuracy rate information group according to the inventory satisfaction information group in the inventory satisfaction information group sequence 105 and each index to be screened in the index sequence to be screened 106, so as to obtain an inventory satisfaction rate information group sequence 107 and a prediction accuracy rate information group sequence 108; then, the computing device 101 may perform linear regression according to the inventory satisfaction rate information group sequence 107 and the prediction accuracy rate information group sequence 108 to generate index evaluation information corresponding to each index to be screened in the index sequence 106 to be screened, so as to obtain an index evaluation information sequence 109; finally, the computing device 101 may screen out the to-be-screened index satisfying the screening condition from the to-be-screened index sequence 106 as a target index according to the index evaluation information sequence 109, so as to obtain a target index set 110.

The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules for providing distributed services, or as a single software or software module. And is not particularly limited herein.

It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.

With continued reference to fig. 2, a flow 200 of some embodiments of an index determination method according to the present disclosure is shown. The index determining method comprises the following steps:

step 201, acquiring an item information set.

In some embodiments, the subject (e.g., the computing device 101 shown in fig. 1) performing the index determination method may obtain the item information set by means of a wired connection or a wireless connection. Wherein, the item information in the item information set may include: the article circulation information sequence and the article replenishment quantity information sequence. The item information in the item information set may be historical item information of items in the same domain. The article circulation information sequence included in the article information can represent the article circulation condition of the corresponding article in the target time period. The article replenishment quantity information sequence included in the article information can represent the article replenishment condition of the corresponding article in the target time period. For example, the article circulation information in the article circulation information sequence may include: true sales of the item and predicted sales of the item. The target period may be a history period. For example, the target time period may be 11/10/2020 to 11/17/2020.

As an example, the item information set may be:

step 202, generating an inventory satisfaction information group according to the article circulation information sequence and the article replenishment quantity information sequence included in each article information in the article information set, and obtaining an inventory satisfaction information group sequence.

In some embodiments, the execution subject may generate an inventory satisfaction information group according to an item circulation information sequence and an item replenishment quantity information sequence included in each item information in the item information set, so as to obtain the inventory satisfaction information group sequence. The inventory satisfaction information in the inventory satisfaction information group sequence can represent the inventory satisfaction condition of the article.

As an example, the inventory satisfaction information in the above-mentioned sequence of inventory satisfaction information sets may include: first inventory fulfillment information and second inventory fulfillment information. Wherein the first inventory fulfillment information may be characterized by a difference between the actual sales of the item and the predicted sales of the item included in the item circulation information. The second inventory satisfaction information may be characterized by a difference between the actual sales of the item included in the item transfer information and the replenishment quantity information of the item corresponding to the item transfer information in the item replenishment quantity information sequence. For example, the execution main body may generate the inventory satisfaction information group according to an item circulation information sequence and an item replenishment quantity information sequence included in each item information in the item information set by the following formula:

wherein the content of the first and second substances,

indicating a serial number.

Representing the true sales volume of the item.

Representing the predicted sales of the item.

Indicating the second in the article circulation information sequence

The article circulation information comprises the actual sales volume of the article.

Indicating the second in the article circulation information sequence

The item circulation information includes an item forecast sales amount.

And the article replenishment quantity information in the article replenishment quantity information sequence is shown.

Indicating the second in the above-mentioned article replenishment quantity information sequence

And (4) the replenishment quantity information of each article.

The first stock satisfaction information included in the stock satisfaction information group is indicated.

And second inventory satisfaction information included in the inventory satisfaction information group.

Indicating the first in the inventory satisfaction information group

The individual inventory fulfillment information includes first inventory fulfillment information.

Indicating the first in the inventory satisfaction information group

The individual inventory fulfillment information includes second inventory fulfillment information.

For example, the item information and inventory satisfaction information group for "item a" may be:

and step 203, generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index to be screened in the inventory satisfaction information group sequence to obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence.

In some embodiments, the execution main body may generate an inventory satisfaction rate information group and a prediction accuracy rate information group 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, so as to obtain the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence. The index to be screened in the index sequence to be screened can be a prediction index for evaluating a prediction result. The indexes to be screened in the index sequence to be screened may include a prediction index of a relative error type and a prediction index of an absolute error type. The absolute error type characterization prediction index is used for calculating the absolute difference value of the predicted sales amount and the goods replenishment amount. The relative error type characterization prediction index is used for calculating a relative difference value between the predicted sales amount and the article replenishment amount. For example, the above-mentioned prediction index of the absolute error type may be, but is not limited to, any one of the following: MAE (Mean Absolute Error) predictor, MSE (Mean Square Error) predictor, RMAE (Root Mean Absolute Error) predictor, and RMSE (Root Mean Square Error) predictor. The prediction index of the above relative error type may be, but is not limited to, any one of the following: MAPE (Mean Absolute Percentage Error) predictor, sMAPE (Symmetric Mean Absolute Percentage Error) predictor and MASE (Mean Absolute Scaled Error) predictor. The inventory satisfaction rate information in the inventory satisfaction rate information group sequence can represent the satisfaction rate of the inventory. The prediction accuracy information in the prediction accuracy information group sequence can represent the prediction accuracy of the commodity sales volume.

The execution main body can bring first inventory satisfaction information included by the inventory satisfaction information in the inventory satisfaction information group sequence into a formula corresponding to the index to be screened so as to determine prediction accuracy information. The execution subject may determine the inventory satisfaction rate information according to second inventory satisfaction information included in the inventory satisfaction 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%.

As an example, when the index to be screened is the RMAE prediction index, the prediction accuracy rate information group and the inventory satisfaction rate information group corresponding to "article a" may be:

and 204, performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence.

In some embodiments, the execution main body may perform linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened, so as to obtain the index evaluation information sequence. The index evaluation information in the index evaluation information sequence can be used for evaluating the index evaluation capability of the index to be screened.

As an example, for each inventory satisfaction rate information group in the sequence of inventory satisfaction rate information groups, the execution subject may perform linear fitting by substituting each inventory satisfaction rate information in the inventory satisfaction rate information group as a dependent variable and prediction accuracy information corresponding to the inventory satisfaction information as an independent variable into the following linear regression equation:

wherein the content of the first and second substances,

indicating inventory fulfillment rate information.

Representing prediction accuracy information.

Indicating a serial number.

Indicating the first in the inventory satisfaction rate information set

Individual inventory fulfillment rate information.

Indicating the first in the set of prediction accuracy information

And (4) prediction accuracy information.

The intercept is represented.

Indicating index evaluation information.

As an example, when the index to be screened is the RMAE prediction index, the prediction accuracy rate information group and the inventory satisfaction rate information group corresponding to "article a" and "article B" may be:

the obtained index evaluation information may be-0.088134. The smaller the numerical value corresponding to the index evaluation information is, the better the representation inventory is.

And step 205, according to the index evaluation information sequence, screening the indexes to be screened which meet the screening conditions from the index sequences to be screened as target indexes to obtain a target index set.

In some embodiments, the execution main body may screen, according to the index evaluation information sequence, an index to be screened that meets a screening condition from the index sequence to be screened as a target index, so as to obtain the target index set. The screening condition may be that the index evaluation information corresponding to the index to be screened is smaller than the target value. The target value may be the same as the sorted index evaluation information of the target position in the sorted index evaluation information sequence. The target position may be determined manually.

By way of example, the sequence of indicators to be screened may be [ MAE predictor, MSE predictor, RMAE predictor, RMSE predictor, MAPE predictor, sMAPE predictor, MASE predictor ]. The index evaluation information sequence may be [ -0.007, -0.011, -0.09, -0.007, -0.012, -0.029, -0.244 ]. The target position may be "3". The sorted index 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". Then the indexes to be screened which meet the screening conditions are taken as target indexes, and the obtained target indexes are collected as [ MASE prediction indexes, RMAE prediction indexes ].

The above embodiments of the present disclosure have the following beneficial effects: through the index determination method of some embodiments of the disclosure, the evaluation capability of the prediction result is improved, and the occurrence of stock backlog or stock shortage is reduced. Specifically, the reasons for backlog or stock backorder are: due to the fact that a unified and standard prediction index selection method is lacked in a manual screening mode, the selected prediction index cannot accurately evaluate the prediction result, and the condition of stock overstock or stock shortage occurs. Based on this, the index determining method of some embodiments of the present disclosure first obtains an item information set, where item information in the item information set includes: the article circulation information sequence and the article replenishment quantity information sequence. By acquiring the history, it is possible to make the evaluation of the prediction index from the history data. Secondly, according to the article circulation information sequence and the article replenishment quantity information sequence included by each article information in the article information set, an inventory satisfaction information group is generated, and an inventory satisfaction information group sequence is obtained. And determining the inventory replenishment accuracy condition corresponding to the article according to the circulation condition and the replenishment condition of the article corresponding to each article information. And then, generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index sequence to be screened in the inventory satisfaction information group sequence to obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence. And determining the prediction accuracy and the inventory satisfaction condition of each prediction index according to the historical inventory replenishment accuracy and each prediction index. And then, performing linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened, so as to obtain an index evaluation information sequence. The prediction ability of each prediction index is quantified by means of linear regression. And finally, according to the index evaluation information sequence, screening the indexes to be screened which meet the screening condition from the index sequences to be screened as target indexes to obtain a target index set. And determining the prediction index with strong prediction evaluation capability by screening. By the method, the selection mode of the prediction indexes is unified and standardized, and the prediction evaluation capability of each prediction index is quantized, so that the problem that the demand prediction result is easily influenced by manual screening (such as randomness) is solved, the evaluation accuracy of the prediction result is improved, and the stock overstock or stock shortage is reduced.

With further reference to FIG. 3, a flow 300 of further embodiments of an index determination method is illustrated. The process 300 of the index determination method includes the following steps:

step 301, an item information set is obtained.

In some embodiments, the specific implementation of step 301 and the technical effect thereof may refer to step 201 in those embodiments corresponding to fig. 2, and are not described herein again.

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, determining inventory full-load information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information.

In some embodiments, the executing subject of the index determination method (e.g., the computing device 101 shown in fig. 1) may determine, for each item replenishment quantity information in the item replenishment quantity information sequence included in the item information, the inventory full information as the inventory state identification included in the inventory satisfaction information corresponding to the item replenishment quantity information in response to determining that the item replenishment quantity information is greater than the target item circulation information. Wherein, the inventory satisfaction information in the inventory satisfaction information group sequence comprises: and identifying the stock state. The inventory status identifier may be used to characterize inventory fulfillment. The target article circulation information may be article circulation information corresponding to the article replenishment quantity information in an article circulation information sequence included in the article information. The inventory full information can represent that the article replenishment quantity information is larger than the actual sales quantity of the articles contained in the target logistics transfer information. For example, the above item replenishment quantity information may be characterized by "1".

And 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, determining inventory shortage information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information.

In some embodiments, the execution subject may determine, for each item replenishment quantity information in the item replenishment quantity information sequence included in the item information, the stock shortage information as the stock state identifier included in the stock satisfaction information corresponding to the item replenishment quantity information in response to determining that the item replenishment quantity information is less than or equal to the target item circulation information. The stock shortage information can represent that the article replenishment quantity information is larger than the actual sales quantity of the articles contained in the target logistics transfer information. For example, the stock backorder information may be characterized by a "0".

As an example, the item information and corresponding inventory satisfaction information group for "item a" may be:

and step 304, generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index to be screened in the inventory satisfaction information group sequence to obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence.

In some embodiments, the execution main body may generate an inventory satisfaction rate information set and a prediction accuracy rate information set according to an inventory satisfaction information set in the inventory satisfaction information set sequence and each index to be screened in the index to be screened sequence, so as to obtain the inventory satisfaction rate information set sequence and the prediction accuracy rate information set sequence. Wherein the executing body may execute the following processing steps for each stock satisfaction information group in the stock satisfaction information group sequence:

the method comprises the steps of firstly, dividing the inventory satisfaction information groups based on the size of a preset sliding window and a preset sliding length to generate sub-inventory satisfaction information groups and obtain sub-inventory satisfaction information group sequences.

The size of the sliding window can be manually set. The preset sliding length may represent a moving step of the sliding window. For example, the sliding window may be "7". The preset sliding length may be "1".

As an example, the inventory satisfaction information group for "item a" may be:

the time span of the inventory satisfaction information group corresponding to the article A can be 2021-04-15 to 2021-07-10 for 86 days. The execution main body may divide the 86 pieces of inventory satisfaction information by using 7 days as a sliding window and 1 day as a preset sliding length, so as to generate 80 sub-inventory satisfaction information groups.

And secondly, generating inventory satisfaction rate information and prediction accuracy rate information based on each sub-inventory satisfaction information group in the sub-inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, and obtaining an inventory satisfaction rate information group and a prediction accuracy rate information group corresponding to the inventory satisfaction information group.

The inventory satisfaction rate information may represent each inventory satisfaction rate corresponding to one sub-inventory satisfaction information group. The prediction accuracy information can represent the prediction accuracy of each index to be screened corresponding to a sublibrary satisfaction information group.

As an example, the execution subject may determine a ratio of the number of sub-inventory fulfillment information items whose inventory status included in the sub-inventory fulfillment information group is identified as "1" to the length of the sliding window as one value of the inventory fulfillment rate information. For example, "article a" is within 2021-04-15 to 2021-07-10, corresponding to 80 sub-inventories satisfying the information set, and corresponding inventory satisfaction rate information may be [95%, 90%, 97%, 96%,. 9% ]. The index sequence to be screened may be [ MAE prediction index, MSE prediction index, RMAE prediction index, RMSE prediction index ] and the prediction accuracy information may be [8.8, 7.7, 3.2, 4.4 ]. Wherein "8.8" can characterize the prediction accuracy of the "MAE prediction index". "7.7" may characterize the prediction accuracy of the "MSE predictor". "3.2" may characterize the prediction accuracy of "RMAE prediction index". "4.4" may characterize the prediction accuracy of "RMSE predictor".

And 305, performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence.

In some embodiments, the performing main body performs linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in an index sequence to be screened, so as to obtain the index evaluation information sequence, and the method may include the following steps:

the first step is that according to the article circulation information sequence, inventory satisfaction rate information in the inventory satisfaction rate information group sequence and prediction accuracy rate information in the prediction accuracy rate information group sequence are divided respectively to generate a divided inventory satisfaction rate information group sequence and a divided prediction accuracy rate information group sequence.

As an example, the execution main body divides the inventory satisfaction rate information in the inventory satisfaction rate information group sequence and the prediction accuracy rate information in the prediction accuracy rate information group sequence according to the actual sales volume of the article included in the article circulation information sequence, so as to generate a divided inventory satisfaction rate information group sequence and a divided prediction accuracy rate information group sequence. The divided inventory satisfaction rate information groups are inventory satisfaction rate information groups corresponding to the article circulation information with similar article real sales included in the corresponding article circulation information.

For example, the item information set may be [ item information a, item information B, item information C, item information D, and item information F ]. The sequence of the stock satisfaction rate information groups corresponding to the article information set may be { [ stock satisfaction rate information a, stock satisfaction rate information B, stock satisfaction rate information C ], [ stock satisfaction rate information D, stock satisfaction rate information E, stock satisfaction rate information F ], [ stock satisfaction rate information G, stock satisfaction rate information H, stock satisfaction rate information I ], [ stock satisfaction rate information J, stock satisfaction rate information K, stock satisfaction rate information L, [ stock satisfaction rate information M, stock satisfaction rate information N, stock satisfaction rate information 0] }. The "article information a" and the included article actual sales amount are close to the article actual sales amount included in the "article information B", and therefore [ stock satisfaction rate information a, stock satisfaction rate information B, stock satisfaction rate information C ] and [ stock satisfaction rate information D, stock satisfaction rate information E, stock satisfaction rate information F ] may be combined to generate a divided stock satisfaction rate information group [ stock satisfaction rate information a, stock satisfaction rate information B, stock satisfaction rate information C, stock satisfaction rate information D, stock satisfaction rate information E, stock satisfaction rate information F ].

For another example, the item information set may be [ item information a, item information B, and item information C ]. The corresponding prediction accuracy information group sequence may be { [ prediction accuracy information a, prediction accuracy information B ], [ prediction accuracy information C, prediction accuracy information D ], [ prediction accuracy information E, prediction accuracy information F ] }. The "article information a" and the included article true sales amount are close to the article true sales amount included in the "article information B", and therefore, the [ prediction accuracy rate information a, prediction accuracy rate information B ] and the [ prediction accuracy rate information C, prediction accuracy rate information D ] may be combined to generate the divided prediction accuracy rate information group.

And secondly, performing unit linear regression according to each divided inventory satisfaction rate information group in the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group corresponding to the divided inventory satisfaction rate information group to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened.

As an example, the set of indicators to be screened may be [ MAE predictor, MSE predictor, RMAE predictor, RMSE predictor ]. For each index to be screened in the index set to be screened, the execution main body may perform unit linear regression according to the divided inventory satisfaction rate information group and the divided prediction accuracy rate information group corresponding to the divided inventory satisfaction rate information group by using the following first linear regression formula to generate an index evaluation value in the index evaluation information corresponding to the index to be screened:

wherein the content of the first and second substances,

an index evaluation value in the index evaluation information is indicated.

The intercept is represented.

Representing a fluctuation term. Wherein, the fluctuation item can be manually set.

Indicating the first of the divided inventory satisfaction rate information groups

The position of each divided inventory satisfaction rate information, or the position of the second of the divided prediction accuracy rate information groups

The location of the partitioned prediction accuracy information.

The first of the divided inventory satisfaction rate information

The position of the individual stock satisfaction rate, or the second position in the divided prediction accuracy rate information group

The divided prediction accuracy information includes

And the location of the prediction accuracy.

Indicating the stock satisfaction rate included in the divided stock satisfaction rate information.

The information of the divided inventory satisfaction rate includes

Individual inventory fulfillment rate.

And indicating the divided prediction accuracy information in the divided prediction accuracy information group.

Indicating the first of the divided prediction accuracy information groups

First in the divided prediction accuracy information

Individual prediction accuracy.

As an example, as shown in fig. 4, wherein fig. 4 shows a linear fit curve 401 corresponding to the above formula.

As another example, the set of indicators to be filtered may be [ MAE predictor, RMAE predictor, RMSE predictor, MAPE predictor, mappe predictor, MASE predictor ]. The index evaluation information set corresponding to the index set to be screened may be:

optionally, the executing body may perform multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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. For each index to be screened in the index sequence to be screened, the execution main body may perform multiple linear regression according to the divided inventory satisfaction information group sequence and the divided prediction accuracy information group sequence by using the following second linear regression formula to generate an index evaluation value in the index evaluation information corresponding to the index to be screened:

wherein, the first and the second end of the pipe are connected with each other,

an index evaluation value in the index evaluation information is indicated.

The intercept is represented.

The location of the partitioned prediction accuracy information.

The first of the divided inventory satisfaction rate information

The position of the inventory satisfaction rate, or the second of the divided prediction accuracy rate information groups

The divided prediction accuracy information includes

And the location of the prediction accuracy.

The first of the divided inventory satisfaction rate information

Individual inventory fulfillment rate.

Indicating the second of the divided prediction accuracy information groups

First in the divided prediction accuracy information

Individual prediction accuracy.

The number of the divided stock satisfaction rate information sets in the divided stock satisfaction rate information set sequence is indicated.

Indicating a serial number.

Is shown as

The article type of the article information group corresponding to the divided inventory satisfaction rate information.

Denotes the first

The coefficients of the item categories of the item information groups corresponding to the divided stock satisfaction rate information.

As an example, the set of indexes to be filtered may be [ MAE predictor, RMAE predictor, RMSE predictor, MAPE predictor, sMAPE predictor, MASE predictor ]. The index evaluation information set corresponding to the index set to be screened may be:

optionally, the execution main body may perform unit linear regression and multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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, so as to obtain the index evaluation information sequence.

The executing body may determine the index evaluation information corresponding to the index to be screened by using the first linear regression formula and the second linear regression formula.

And step 306, according to the index evaluation information sequence, screening the indexes to be screened which meet the screening conditions from the index sequences to be screened as target indexes to obtain a target index set.

In some embodiments, the specific implementation of step 306 and the technical effect thereof may refer to step 205 in those embodiments corresponding to fig. 2, which are not described herein again.

Optionally, when the execution main body performs unit linear regression and multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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, the execution main body may obtain the target index set by screening the index to be screened which satisfies the screening condition from the index sequence to be screened as a target index according to the index evaluation information sequence by the following steps:

the method comprises the steps of firstly, determining the index evaluation value meeting the screening condition in the index evaluation information corresponding to the prediction index to be screened to obtain a candidate prediction index group for each index evaluation information in the index evaluation information set.

Wherein the screening condition is that the index evaluation value is smaller than the target value. The target value may be the same as the index evaluation value of the target position sorted in the index evaluation information. The target position may be determined manually.

And secondly, determining the occurrence frequency of the candidate prediction indexes in at least one candidate prediction index group, and taking the candidate prediction indexes with the occurrence frequency meeting the candidate prediction index screening condition as target indexes to obtain the target index set.

As an example, the candidate prediction index screening condition may be that the number of occurrences of the candidate prediction index is greater than the target number of occurrences. For example, the target number of occurrences may be 2.

Compared with some embodiments corresponding to fig. 2, in the process 300 of the index determining method in some embodiments corresponding to fig. 3, first, according to the article circulation information sequence, the inventory satisfaction rate information in the inventory satisfaction rate information group sequence and the prediction accuracy rate information in the prediction accuracy rate information group sequence are respectively divided to generate a divided inventory satisfaction rate information group sequence and a divided prediction accuracy rate information group sequence. So that the inventory satisfaction rate information corresponding to items with similar actual sales volumes are in the same group and the prediction accuracy rate information corresponding to items with similar actual sales volumes are in the same group. Then, according to each divided inventory satisfaction rate information group in the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group corresponding to the divided inventory satisfaction rate information group, unit linear regression is performed to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened. So that no more discrete points exist on both sides of the fitted curve after the unit linear regression. In addition, when unit linear fitting and multiple linear fitting are carried out, the prediction indexes with better prediction evaluation capability are screened out through intersection of index evaluation information obtained by indexes to be screened under different linear fitting methods.

With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an index determining apparatus, which correspond to those of the method embodiments shown in fig. 2, and which may be applied in various electronic devices in particular.

As shown in fig. 5, the index determining apparatus 500 of some embodiments includes: an obtaining unit 501 configured to obtain an item information set, where item information in the item information set includes: the article circulation information sequence and the article replenishment quantity information sequence; a first generating unit 502 configured to generate an inventory satisfaction information group according to an item circulation information sequence and an item replenishment quantity information sequence included in each item information in the item information set, so as to obtain an inventory satisfaction information group sequence; a second generating unit 503 configured to generate an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index to be screened in the inventory satisfaction information group sequence, and obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence; a linear regression unit 504 configured to perform linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened, so as to obtain an index evaluation information sequence; and a screening unit 505 configured to screen out the to-be-screened indexes satisfying the screening condition from the to-be-screened index sequences as target indexes according to the index evaluation information sequences, so as to obtain a target index set.

In some optional implementations of some embodiments, the inventory satisfaction information in the sequence of inventory satisfaction information sets includes: identifying the stock state; and the first generating unit 502 is further configured to: and 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 target item circulation information, determining inventory full information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information, 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.

In some optional implementations of some embodiments, the first generating unit 502 is further configured to: and 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, determining inventory shortage information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information.

In some optional implementations of some embodiments, the second generating unit 503 is further configured to: for each inventory fulfillment information group in the sequence of inventory fulfillment information groups, performing the following processing steps: dividing the stock meeting information group based on the size of a preset sliding window and a preset sliding length to generate a sub-stock meeting information group and obtain a sub-stock meeting information group sequence; and generating inventory satisfaction rate information and prediction accuracy rate information based on each sub-inventory satisfaction information group in the sub-inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, and obtaining an inventory satisfaction rate information group and a prediction accuracy rate information group corresponding to the inventory satisfaction information group.

In some optional implementations of some embodiments, the linear regression unit 504 is further configured to: and according to the article circulation information sequence, respectively dividing the inventory satisfaction rate information in the inventory satisfaction rate information group sequence and the prediction accuracy rate information in the prediction accuracy rate information group sequence to generate a divided inventory satisfaction rate information group sequence and a divided prediction accuracy rate information group sequence.

In some optional implementations of some embodiments, the linear regression unit 504 is further configured to: and performing unit linear regression and multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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, so as to obtain the index evaluation information sequence.

In some optional implementations of some embodiments, the linear regression unit 504 is further configured to: and performing unit linear regression according to each divided inventory satisfaction rate information group in the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group corresponding to the divided inventory satisfaction rate information group to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened.

In some optional implementations of some embodiments, the linear regression unit 504 is further configured to: and performing multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened.

It will be understood that the elements described in the apparatus 500 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 500 and the units included therein, and are not described herein again.

Referring now to FIG. 6, a block diagram of an electronic device (such as computing device 101 shown in FIG. 1) 600 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, or the like; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, 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 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may be alternatively implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that 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 two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (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.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring an article information set, wherein article information in the article information set comprises: the article circulation information sequence and the article replenishment quantity information sequence; generating an inventory satisfaction information group according to an article circulation information sequence and an article replenishment quantity information sequence which are included in each article information in the article information set, and obtaining an inventory satisfaction information group sequence; generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index sequence to be screened in the inventory satisfaction information group sequence to obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence; performing linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index sequences to be screened, so as to obtain an index evaluation information sequence; and according to the index evaluation information sequence, screening the indexes to be screened which meet the screening condition from the index sequences to be screened as target indexes to obtain a target index set.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming 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. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should 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 the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and 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. The names of these units do not form a limitation on the units themselves in some cases, for example, the acquiring unit may also be described as "acquiring an item information set, where the item information in the item information set includes: and (5) units of the article circulation information sequence and the article replenishment quantity information sequence.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. An index determination method, comprising:

acquiring an item information set, wherein item information in the item information set comprises: the article circulation information sequence and the article replenishment quantity information sequence;

generating an inventory satisfaction information group according to an article circulation information sequence and an article replenishment quantity information sequence which are included by each article information in the article information set, and obtaining an inventory satisfaction information group sequence, wherein the inventory satisfaction information represents an inventory satisfaction condition of the article, and the inventory satisfaction information comprises: the inventory information comprises first inventory satisfaction information and second inventory satisfaction information, the first inventory satisfaction information represents the difference value of the actual sales volume of the article and the predicted sales volume of the article, which are included in the article circulation information, and the second inventory satisfaction information represents the difference value of the actual sales volume of the article and the replenishment volume of the article, which are included in the article circulation information, in the article circulation information sequence and correspond to the article circulation information;

generating an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group sequence and the index sequence to be screened to obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence, wherein the index to be screened in the index sequence to be screened is a prediction index for evaluating a prediction result, and first inventory satisfaction information included in the inventory satisfaction information group sequence is brought into a formula corresponding to the index to be screened so as to determine the prediction accuracy rate information; determining inventory satisfaction rate information according to second inventory satisfaction information included in the inventory satisfaction information;

performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence;

and according to the index evaluation information sequence, screening the indexes to be screened which meet screening conditions from the index sequences to be screened as target indexes to obtain a target index set.

2. The method of claim 1, wherein the inventory fulfillment information in the sequence of inventory fulfillment information groups comprises: identifying the stock state; and

the generating of the inventory satisfaction information group according to the article circulation information sequence and the article replenishment quantity information sequence included in each article information in the article information set comprises:

for each item replenishment quantity information in an item replenishment quantity information sequence included in the item information, in response to determining that the item replenishment quantity information is greater than target item circulation information, determining inventory full-loading information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information, wherein the target item circulation information is item circulation information corresponding to the item replenishment quantity information in an item circulation information sequence included in the item information.

3. The method according to claim 2, wherein the generating of 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 item information set further comprises:

and 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, determining inventory shortage information as an inventory state identifier included in inventory satisfaction information corresponding to the item replenishment quantity information.

4. The method of claim 1, wherein the generating an inventory fulfillment rate information set and a prediction accuracy rate information set from each of the inventory fulfillment information sets in the sequence of inventory fulfillment information sets and the sequence of indicators to be filtered comprises:

for each inventory fulfillment information group in the sequence of inventory fulfillment information groups, performing the following processing steps:

dividing the inventory satisfaction information groups based on the size of a preset sliding window and a preset sliding length to generate sub-inventory satisfaction information groups to obtain a sub-inventory satisfaction information group sequence;

and generating inventory satisfaction rate information and prediction accuracy rate information based on each sub-inventory satisfaction information group in the sub-inventory satisfaction information group sequence and each index to be screened in the index sequence to be screened, and obtaining an inventory satisfaction rate information group and a prediction accuracy rate information group corresponding to the inventory satisfaction information group.

5. The method according to claim 1, wherein performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence, includes:

and according to the article circulation information sequence, respectively dividing the inventory satisfaction rate information in the inventory satisfaction rate information group sequence and the prediction accuracy rate information in the prediction accuracy rate information group sequence to generate a divided inventory satisfaction rate information group sequence and a divided prediction accuracy rate information group sequence.

6. The method according to claim 5, wherein performing linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence, further comprises:

and performing unit linear regression and multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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, so as to obtain the index evaluation information sequence.

7. The method according to claim 5, wherein performing linear regression according to the inventory satisfaction rate information group sequence and the 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 further comprises:

and performing unit linear regression according to each divided inventory satisfaction rate information group in the divided inventory satisfaction rate information group sequence and the divided prediction accuracy rate information group corresponding to the divided inventory satisfaction rate information group to generate index evaluation information corresponding to each index to be screened in the index sequence to be screened.

8. The method of claim 5, wherein performing linear regression according to the inventory satisfaction rate information group sequence and the prediction accuracy rate information group sequence to generate index evaluation information corresponding to each index to be screened in the index to be screened sequence further comprises:

and performing multiple linear regression according to the divided inventory satisfaction rate information group sequence and the divided 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.

9. An index determination apparatus comprising:

an acquisition unit configured to acquire an item information set, wherein item information in the item information set includes: the article circulation information sequence and the article replenishment quantity information sequence;

a first generating unit, configured to generate an inventory satisfaction information group according to an item circulation information sequence and an item replenishment quantity information sequence included in each item information in the item information set, to obtain an inventory satisfaction information group sequence, where the inventory satisfaction information represents an inventory satisfaction condition of the item, and the inventory satisfaction information includes: the inventory information comprises first inventory satisfaction information and second inventory satisfaction information, the first inventory satisfaction information represents the difference value of the actual sales volume of the article and the predicted sales volume of the article, which are included in the article circulation information, and the second inventory satisfaction information represents the difference value of the actual sales volume of the article and the replenishment volume of the article, which are included in the article circulation information, in the article circulation information sequence and correspond to the article circulation information;

a second generating unit configured to generate an inventory satisfaction rate information group and a prediction accuracy rate information group according to each index to be screened in the inventory satisfaction information group and the index to be screened in the inventory satisfaction information group sequence, and obtain an inventory satisfaction rate information group sequence and a prediction accuracy rate information group sequence, wherein the index to be screened in the index to be screened is a prediction index for evaluating a prediction result, and first inventory satisfaction information included in the inventory satisfaction information group sequence is brought into a formula corresponding to the index to be screened, so that prediction accuracy rate information is determined; determining inventory satisfaction rate information according to second inventory satisfaction information included in the inventory satisfaction information;

a linear regression unit configured to perform linear regression according to the inventory satisfaction rate information group sequence and the 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, so as to obtain an index evaluation information sequence;

and the screening unit is configured to screen out the indexes to be screened which meet screening conditions from the index sequences to be screened as target indexes according to the index evaluation information sequences to obtain a target index set.

10. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-8.

11. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1 to 8.