# US 12,770,102 B2 · Method and apparatus for controlling item inventory, and device and medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,770,102 B2
- Document ID: US12770102B2
- Status: Granted
- Kind: B2
- Application number: 18/710,142
- Filed: 2022-11-15
- Published: 2025-01-02
- Granted: 2026-10-20
- Earliest claimed: 2021-11-25
- Assignees: Beijing Jingdong Zhenshi Information Technology Co., Ltd.
- Applicants: Beijing Jingdong Zhenshi Information Technology Co., Ltd.
- Inventors: Bingjie Zhong; Zhenyu Gao; Xiaotian Zhuang; Shengnan Wu
- Web page: https://patentgrep.com/patent/US12770102B2

## CPC

- G06Q 10/0875: Itemisation or classification of parts, supplies or services, e.g. bill of materials
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A method for controlling item inventory includes: for each to-be-processed item, determining a replenishment attribute value of a current to-be-processed item based on a current time and shipment quantity-associated information of the current to-be-processed item; in response to detecting that a target to-be-processed item whose replenishment attribute value is greater than a preset replenishment attribute threshold, determining a target inventory quantity of the target to-be-processed item based on the replenishment attribute value of the target to-be-processed item and a target inventory quantity determination model; and for each target to-be-processed item, determining a target replenishment quantity of a current target to-be-processed item based on the target inventory quantity and a net inventory quantity corresponding to the current time of the current target to-be-processed item.

## Claims

### Claim 1

A method for controlling item inventory, applied to at least one of a server and a terminal device, and comprising:
for each item of all items, determining, based on shipment dates and shipment quantities corresponding to the shipment dates of the item, a shipment interval duration between consecutive two shipments of the item, and updating the shipment interval duration to shipment quantity-associated information of the item, wherein the shipment quantity-associated information comprises the shipment dates and the shipment quantities;
determining at least one to-be-processed item from the all items based on shipment quantity-associated information of the all items, wherein each to-be-processed item of the at least one to-be-processed item is an item whose shipment frequency is less than a preset threshold;
for each to-be-processed item, determining a replenishment attribute value of the to-be-processed item based on a current time and the shipment quantity-associated information of the to-be-processed item, wherein the replenishment attribute value is used to represent urgency of replenishment of the to-be-processed item at the current time;
in response to the replenishment attribute value of the to-be-processed item being greater than a preset replenishment attribute threshold, determining the to-be-processed item as a target to-be-processed item, and determining a target inventory quantity of the target to-be-processed item based on the replenishment attribute value of the target to-be-processed item and a target inventory quantity determination model; and
for the target to-be-processed item, determining a target replenishment quantity of the target to-be-processed item based on the target inventory quantity and a net inventory quantity corresponding to the current time of the target to-be-processed item;
wherein in a case where the shipment quantity-associated information comprises at least one shipment interval duration, the determining at least one to-be-processed item from the all items based on shipment quantity-associated information of the all items comprises:
for each item of the all items, determining a variation coefficient of the item based on the at least one shipment interval duration corresponding to the item, wherein the variation coefficient is used to represent fluctuation of the at least one shipment interval duration, and the at least one shipment interval duration and the shipment interval duration between the consecutive two shipments are comprised in a set of shipment interval days corresponding to the item; and
determining the at least one to-be-processed item based on a preset variation coefficient threshold and the variation coefficient of the item;
wherein the determining a replenishment attribute value of the to-be-processed item based on a current time and the shipment quantity-associated information of the to-be-processed item comprises:
determining a target data processing method based on the shipment quantity-associated information of the to-be-processed item; and
processing the current time and the shipment quantity-associated information based on the target data processing method to obtain the replenishment attribute value of the to-be-processed item;
wherein the determining a target data processing method based on the shipment quantity-associated information of the to-be-processed item comprises:
determining the at least one shipment interval duration based on shipment quantities corresponding to all shipment dates in the shipment quantity-associated information;
in a case where the at least one shipment interval duration satisfies a preset uniform distribution, determining the target data processing method to be a mean estimation method; and
in a case where the at least one shipment interval duration does not satisfy the preset uniform distribution, determining the target data processing method to be a quantile estimation method.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining, based on shipment dates and shipment quantities corresponding to the shipment dates of the item, a shipment interval duration between consecutive two shipments of a respective item comprises:
in response to detecting that the shipment quantities of the item are greater than a preset shipment quantity threshold, determining shipment dates corresponding to the shipment quantities as to-be-processed shipment dates; and
based on the to-be-processed shipment dates corresponding to the item, determining the shipment interval duration between the consecutive two shipments of the item.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the determining a variation coefficient of the item based on the at least one shipment interval duration corresponding to the comprises:
determining an interval duration mean and an interval duration variance based on the at least one shipment interval duration corresponding to the item; and
determining the variation coefficient of the item based on the interval duration mean and the interval duration variance corresponding to the item.

### Claim 4 (depends on 1)

The method according to claim 1 wherein the determining the at least one to-be-processed item based on a preset variation coefficient threshold and the variation coefficient of the item comprises:
in response to the variation coefficient of the item being less than the preset variation coefficient threshold, taking the item as a to-be-processed item.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the processing the current time and the shipment quantity-associated information based on the target data processing method to obtain the replenishment attribute value of the to-be-processed item comprises:
determining a to-be-used shipment date from the shipment dates in the shipment quantity-associated information that has a smallest interval duration from the current time, wherein a shipment quantity corresponding to the to-be-used shipment date is greater than a preset shipment quantity threshold;
determining, based on a date corresponding to the current time and the to-be-used shipment date, a first duration; and
processing the first duration and the shipment quantity-associated information based on the target data processing method to obtain the replenishment attribute value of the current to-be-processed item.

### Claim 6 (depends on 5)

The method according to claim 5, wherein, in the case where the shipment quantity-associated information comprises the at least one shipment interval duration, the processing the first duration and the shipment quantity-associated information based on the target data processing method to obtain the replenishment attribute value of the current to-be-processed item, comprises:
in a case where the target data processing method is the mean estimation method, processing the first duration and interval duration variance determined according to the at least one shipment interval duration based on the mean estimation method to determine a replenishment attribute value of the to-be-processed item.

### Claim 7 (depends on 5)

The method according to claim 5, wherein the processing the first duration and the shipment quantity-associated information based on the target data processing method to obtain the replenishment attribute value of the to-be-processed item comprises:
in a case where the target data processing method is the quantile estimation method, determining a target quantile sub-estimation method based on the shipment quantity-associated information and a preset quantile; and
processing the first duration and the shipment quantity-associated information based on the target quantile sub-estimation method to determine the replenishment attribute value of the to-be-processed item.

### Claim 8 (depends on 7)

The method according to claim 7, wherein the shipment quantity-associated information comprises a number of shipments corresponding to the at least one shipment interval duration, and the determining a target quantile sub-estimation method based on the shipment quantity-associated information and a preset quantile comprises:
in a case where the preset quantile is less than or equal to a reciprocal of the number of shipments, determining the target quantile sub-estimation method to be a first quantile sub-estimation method; and
in a case where the preset quantile is greater than the reciprocal of the number of shipments, determining the target quantile sub-estimation method to be a second quantile sub-estimation method.

### Claim 9 (depends on 8)

The method according to claim 8, wherein the processing the first duration and the shipment quantity-associated information based on the target quantile sub-estimation method to determine the replenishment attribute value of the to-be-processed item comprising:
in a case where the target quantile sub-estimation method is the first quantile sub-estimation method, determining the replenishment attribute value of the to-be-processed item based on the at least one shipment interval duration, the preset quantile, the number of shipments and the first duration.

### Claim 10 (depends on 9)

The method according to claim 9, wherein the determining the replenishment attribute value of the to-be-processed item based on the at least one shipment interval duration, the preset quantile, the number of shipments and the first duration comprises:
obtaining a first data value based on a product of a minimum value of the at least one shipment interval duration, the preset quantile and the number of shipments; and
determining the replenishment attribute value of the to-be-processed item based on a ratio of the first duration to the first data value.

### Claim 11 (depends on 8)

The method according to claim 8, wherein the processing the first duration and the shipment quantity-associated information based on the target quantile sub-estimation method to determine the replenishment attribute value of the to-be-processed item comprises:
in a case where the target quantile sub-estimation method is the second quantile sub-estimation method, determining a target quantile fractile based on the preset quantile and the shipment quantity-associated information; and
determining the replenishment attribute value of the to-be-processed item based on the target quantile fractile and the first duration.

### Claim 12 (depends on 11)

The method according to claim 11, wherein the determining a target quantile fractile based on the preset quantile and the shipment quantity-associated information comprises:
fitting based on the at least one shipment interval duration in the shipment quantity-associated information to obtain a target empirical distribution; and
determining the target quantile fractile based on the preset quantile and the target empirical distribution.

### Claim 13 (depends on 1)

The method according to claim 1, wherein the in response to the replenishment attribute value of the to-be-processed item being greater than a preset replenishment attribute threshold, determining the to-be-processed item as a target to-be-processed item, the determining a target inventory quantity of the target to-be-processed item based on the replenishment attribute value of the target to-be-processed item and a target inventory determination model comprises:
based on the target data processing method corresponding to the replenishment attribute value, determining the preset replenishment attribute threshold; and
in response to the replenishment attribute value of the to-be-processed item being greater than a preset replenishment attribute threshold, determining the to-be-processed item as the target to-be-processed item, determining the target inventory quantity of the target to-be-processed item based on the replenishment attribute value and the target inventory determination model.

### Claim 14 (depends on 13)

The method according to claim 13, wherein the determining the target inventory quantity of the target to-be-processed item based on the replenishment attribute value and the target inventory determination model comprises:
determining the target inventory quantity of the target to-be-processed item by taking the replenishment attribute value as an input parameter of the target inventory determination model.

### Claim 15

An electronic device, comprising:
at least one processor; and
a storage apparatus configured to store at least one program,
wherein the at least one program, when being executed by the at least one processor, causes the at least one processor to implement a method for controlling item inventory, the electronic device comprises at least one of a server and a terminal device;
wherein the method for controlling item inventory comprises:
for each item of all items, determining, based on shipment dates and shipment quantities corresponding to the shipment dates of the item, a shipment interval duration between consecutive two shipments of the item, and updating the shipment interval duration to shipment quantity-associated information of the item, wherein the shipment quantity-associated information comprises the shipment dates and the shipment quantities;
determining at least one to-be-processed item from the all items based on shipment quantity-associated information of the all items, wherein each to-be-processed item of the at least one to-be-processed item is an item whose shipment frequency is less than a preset threshold;
for each to-be-processed item of the at least one to-be-processed item, determining a replenishment attribute value of the to-be-processed item based on a current time and shipment quantity-associated information of the to-be-processed item, wherein the replenishment attribute value is used to represent urgency of replenishment of the to-be-processed item at the current time;
in response to the replenishment attribute value of the to-be-processed item being greater than a preset replenishment attribute threshold, determining the to-be-processed item as a target to-be-processed item, and determining a target inventory quantity of the target to-be-processed item based on the replenishment attribute value of the target to-be-processed item and a target inventory quantity determination model; and
for the target to-be-processed item, determining a target replenishment quantity of the target to-be-processed item based on the target inventory quantity and a net inventory quantity corresponding to the current time of the target to-be-processed item;
wherein in a case where the shipment quantity-associated information comprises at least one shipment interval duration, the determining at least one to-be-processed item from the all items based on shipment quantity-associated information of the all items comprises:
for each item of the all items, determining a variation coefficient of the item based on the at least one shipment interval duration corresponding to the item, wherein the variation coefficient is used to represent fluctuation of the at least one shipment interval duration, and the at least one shipment interval duration and the shipment interval duration between the consecutive two shipments are comprised in a set of shipment interval days corresponding to the item; and
determining the at least one to-be-processed item based on a preset variation coefficient threshold and the variation coefficient of the item;
wherein the determining a replenishment attribute value of the to-be-processed item based on a current time and the shipment quantity-associated information of the to-be-processed item comprises:
determining a target data processing method based on the shipment quantity-associated information of the to-be-processed item; and
processing the current time and the shipment quantity-associated information based on the target data processing method to obtain the replenishment attribute value of the to-be-processed item;
wherein the determining a target data processing method based on the shipment quantity-associated information of the to-be-processed item comprises:
determining the at least one shipment interval duration based on shipment quantities corresponding to all shipment dates in the shipment quantity-associated information;
in a case where the at least one shipment interval duration satisfies a preset uniform distribution, determining the target data processing method to be a mean estimation method; and
in a case where the at least one shipment interval duration does not satisfy the preset uniform distribution, determining the target data processing method to be a quantile estimation method.

### Claim 16

A non-transitory storage medium storing a computer-executable instruction, wherein the computer-executable instruction, when being executed by a computer processor of at least one of a server and a terminal device, is used to perform a method for controlling item inventory;
wherein the method for controlling item inventory comprises:
for each item of all items, determining, based on shipment dates and shipment quantities corresponding to the shipment dates of the item, a shipment interval duration between consecutive two shipments of the item, and updating the shipment interval duration to shipment quantity-associated information of the item, wherein the shipment quantity-associated information comprises the shipment dates and the shipment quantities;
determining at least one to-be-processed item from the all items based on shipment quantity-associated information of the all items, wherein each to-be-processed item of the at least one to-be-processed item is an item whose shipment frequency is less than a preset threshold;
for each to-be-processed item of the at least one to-be-processed item, determining a replenishment attribute value of the to-be-processed item based on a current time and shipment quantity-associated information of the to-be-processed item, wherein the replenishment attribute value is used to represent urgency of replenishment of the to-be-processed item at the current time;
in response to the replenishment attribute value of the to-be-processed item being greater than a preset replenishment attribute threshold, determining the to-be-processed item as a target to-be-processed item, and determining a target inventory quantity of the target to-be-processed item based on the replenishment attribute value of the target to-be-processed item and a target inventory quantity determination model; and
for the target to-be-processed item, determining a target replenishment quantity of the target to-be-processed item based on the target inventory quantity and a net inventory quantity corresponding to the current time of the target to-be-processed item;
wherein in a case where the shipment quantity-associated information comprises at least one shipment interval duration, the determining at least one to-be-processed item from the all items based on shipment quantity-associated information of the all items comprises:
for each item of the all items, determining a variation coefficient of the item based on the at least one shipment interval duration corresponding to the item, wherein the variation coefficient is used to represent fluctuation of the at least one shipment interval duration, and the at least one shipment interval duration and the shipment interval duration between the consecutive two shipments are comprised in a set of shipment interval days corresponding to the item; and
determining the at least one to-be-processed item based on a preset variation coefficient threshold and the variation coefficient of the item;
wherein the determining a replenishment attribute value of the to-be-processed item based on a current time and the shipment quantity-associated information of the to-be-processed item comprises:
determining a target data processing method based on the shipment quantity-associated information of the to-be-processed item; and
processing the current time and the shipment quantity-associated information based on the target data processing method to obtain the replenishment attribute value of the to-be-processed item;
wherein the determining a target data processing method based on the shipment quantity-associated information of the to-be-processed item comprises:
determining the at least one shipment interval duration based on shipment quantities corresponding to all shipment dates in the shipment quantity-associated information;
in a case where the at least one shipment interval duration satisfies a preset uniform distribution, determining the target data processing method to be a mean estimation method; and
in a case where the at least one shipment interval duration does not satisfy the preset uniform distribution, determining the target data processing method to be a quantile estimation method.