CN111612385B - Method and device for clustering articles to be distributed - Google Patents

Method and device for clustering articles to be distributed Download PDF

Info

Publication number
CN111612385B
CN111612385B CN201910132026.4A CN201910132026A CN111612385B CN 111612385 B CN111612385 B CN 111612385B CN 201910132026 A CN201910132026 A CN 201910132026A CN 111612385 B CN111612385 B CN 111612385B
Authority
CN
China
Prior art keywords
association
degree
orders
order
distributed
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910132026.4A
Other languages
Chinese (zh)
Other versions
CN111612385A (en
Inventor
武玉东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingbangda Trade Co Ltd
Beijing Jingdong Zhenshi Information Technology Co Ltd
Original Assignee
Beijing Jingdong Zhenshi Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Zhenshi Information Technology Co Ltd filed Critical Beijing Jingdong Zhenshi Information Technology Co Ltd
Priority to CN201910132026.4A priority Critical patent/CN111612385B/en
Publication of CN111612385A publication Critical patent/CN111612385A/en
Application granted granted Critical
Publication of CN111612385B publication Critical patent/CN111612385B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Operations Research (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a method and a device for clustering objects to be distributed, and relates to the technical field of computers. One embodiment of the method comprises the following steps: acquiring splitting information of an order, wherein the splitting information comprises a sub order split according to the order and articles to be distributed included in the sub order; determining the association relation of the objects to be distributed among the sub orders according to the splitting information of the orders, and calculating the association degree of the association relation; and determining the articles to be clustered according to the association degree. According to the method and the system for clustering the to-be-distributed objects, the to-be-distributed objects to be clustered can be determined according to the split information of the historical orders, so that the splitting rate is reduced, the order distribution cost is saved, the task operation is saved, the time-efficiency control of order distribution is improved, and the customer experience is optimized.

Description

Method and device for clustering articles to be distributed
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, an electronic device, and a computer readable medium for clustering objects to be distributed.
Background
One of the production indexes focused on in the warehouse production process by the current e-commerce platform is the bill disassembly rate. The split rate is the ratio of the split order quantity to the total order quantity, and the split operation is possible in the following scene:
(1) The distribution of the to-be-distributed object warehouse included in the order is different;
(2) The order includes different shippers of the to-be-dispensed items (such as third party sellers or self-camping shipments);
(3) The customer selects the first shipment of goods;
(4) Other splitting scenes, such as that the order contains articles to be distributed (such as high-value articles to be distributed, large articles to be distributed, foods, dangerous articles such as perfume and the like, and the articles to be distributed can not be packaged and distributed together with other articles to be distributed) which can not be packaged and distributed simultaneously, and different logistics companies have special requirements on the weight or the volume of single packages, and the splitting is also required beyond the limit of the logistics companies.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
one main reason for splitting orders is that the to-be-distributed object warehouses included in the orders are distributed differently, so that the to-be-distributed objects have to be split into a plurality of independent orders and then distributed by the warehouses, the order distribution cost is increased in multiple, processing tasks such as tracking, collecting and processing of order distribution information are increased simultaneously, control of order distribution timeliness is not facilitated, and customer experience is reduced.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method and an apparatus for clustering objects to be distributed, which can determine the objects to be distributed that need to be clustered according to the split information of the historical order, so as to reduce the splitting rate, save the order distribution cost, save the task operation, thereby improving the aging control of order distribution and optimizing the customer experience.
To achieve the above object, according to one aspect of the embodiments of the present invention, there is provided a method for clustering objects to be distributed, including: acquiring splitting information of an order, wherein the splitting information comprises a sub order split according to the order and articles to be distributed included in the sub order; determining the association relation of the objects to be distributed among the sub orders according to the splitting information of the orders, and calculating the association degree of the association relation; and determining the articles to be clustered according to the association degree.
Optionally, the association degree includes one or more of a support degree, a confidence degree, and a promotion degree; wherein the support degree is a ratio of the number of orders of the to-be-distributed objects to the total number of orders in the association relation; the confidence is the ratio of the number of orders of the to-be-delivered objects in the association relationship to the number of orders of the to-be-delivered objects in at least one sub-order in the association relationship; the lifting degree is the ratio of the confidence degree to the support degree of the objects to be distributed in the association relation.
Optionally, the method for determining the objects to be clustered according to the association degree comprises the following steps: sorting the association relations according to the association degree from high to low; and selecting the articles to be delivered in the association relation with the association degree larger than or equal to the first threshold value.
Optionally, the method for determining the objects to be clustered according to the association degree comprises the following steps: sorting the association relations according to the association degree from high to low; calculating the order splitting rate of the orders after the objects to be distributed in the M incidence relations before sorting are clustered, wherein the order splitting rate is the ratio of the number of the split orders to the total number of the orders; determining whether the split rate is greater than a second threshold; and if the splitting rate is greater than a second threshold, increasing the number of M until the splitting rate after the M incidence relations before sorting are calculated and clustered is not greater than the second threshold, and determining that the M incidence relations are to be clustered.
Optionally, after determining that the to-be-delivered items in the M association relationships are categories of to-be-delivered items to be clustered, the method further includes: and determining the quantity of the articles to be clustered according to the predicted sales quantity of the articles to be clustered.
To achieve the above object, according to another aspect of an embodiment of the present invention, there is provided an apparatus for clustering objects to be distributed, including: the system comprises an acquisition module, a distribution module and a distribution module, wherein the acquisition module is used for acquiring splitting information of an order, wherein the splitting information comprises a sub order split according to the order and an object to be distributed included in the sub order; the calculating module is used for determining the association relation of the objects to be distributed among the sub orders according to the splitting information of the orders and calculating the association degree of the association relation; and the clustering module is used for determining the articles to be clustered according to the association degree.
Optionally, the association degree includes one or more of a support degree, a confidence degree, and a promotion degree; wherein the support degree is a ratio of the number of orders of the to-be-distributed objects to the total number of orders in the association relation; the confidence is the ratio of the number of orders of the to-be-delivered objects in the association relationship to the number of orders of the to-be-delivered objects in at least one sub-order in the association relationship; the lifting degree is the ratio of the confidence degree to the support degree of the objects to be distributed in the association relation.
Optionally, the clustering module is further configured to sort the association relationships according to the association degree from high to low; and selecting the articles to be delivered in the association relation with the association degree larger than or equal to the first threshold value.
Optionally, the clustering module is further configured to sort the association relationships according to the association degree from high to low; calculating the order splitting rate of the orders after the objects to be distributed in the M incidence relations before sorting are clustered, wherein the order splitting rate is the ratio of the number of the split orders to the total number of the orders; determining whether the split rate is greater than a second threshold; and if the splitting rate is greater than a second threshold, increasing the number of M until the splitting rate after the M incidence relations before sorting are calculated and clustered is not greater than the second threshold, and determining that the M incidence relations are to be clustered.
Optionally, the clustering module is further configured to determine the number of the to-be-clustered objects according to the predicted sales of the to-be-clustered objects.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic device including: one or more processors; and the storage device is used for storing one or more programs, and the one or more programs are executed by the one or more processors, so that the one or more processors realize any one of the methods for clustering the articles to be distributed.
To achieve the above object, according to yet another aspect of an embodiment of the present invention, there is provided a computer-readable medium having stored thereon a computer program which, when executed by one or more processors, implements any one of the methods of clustering items to be distributed.
One embodiment of the above invention has the following advantages or benefits: because the association degree of the articles to be distributed among the sub orders is determined according to the splitting information of the orders, and the technical means of the articles to be distributed which need to be clustered is determined according to the association degree, the technical problems of high splitting rate and high logistics cost of the orders in the traditional method are solved, and the technical effects of reducing the splitting rate and logistics cost of the orders and improving customer experience are achieved.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic illustration of the main steps of a method of clustering items to be distributed according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the main steps of a method for determining items to be clustered for delivery according to the degree of association according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing the main steps of inter-warehouse reconciliation in accordance with an embodiment of the invention;
FIG. 4 is a schematic illustration of the main parts of an apparatus for clustering items to be dispensed according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
fig. 6 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
FIG. 1 is a schematic diagram of the main steps of a method for clustering items to be distributed according to an embodiment of the present invention, as shown in FIG. 1:
step S101 represents obtaining split information of an order, where the split information includes a sub-order split according to the order and an object to be delivered included in the sub-order. The basis for analyzing the association degree of the objects to be distributed is the objects to be distributed in the split sub-orders, and the aim of the step is to determine the data source and reduce the calculation range.
The acquired orders can have a certain time range, such as acquiring historical orders of last week or last 2 months, inquiring split orders in the historical orders, acquiring split information of the split orders, wherein the split information can comprise the number of split sub orders, the number of split orders, the order number of the sub orders, the order generation time, the number, the price and other information of the to-be-distributed objects included in the orders, besides the sub orders split according to the orders and to-be-distributed objects included in the sub orders, and further can determine split reasons of the split orders, so that the split orders can be selected, for example, due to the fact that the split orders are not in the same warehouse.
The obtained historical orders can be selected according to brands of the objects to be distributed, delivery warehouses and the classification range of the objects to be distributed, for example, warehouse order detail data of the first ten of the disassembly rates are extracted according to the delivery warehouses, and the disassembly order data under the warehouses are analyzed; or extracting order data of the to-be-delivered object classification with the first ten splitting rates according to the to-be-delivered object classification, and analyzing splitting order data corresponding to all the classes under the to-be-delivered object classification.
The retrieved split order data may be saved in a text file (e.g., csv format). For example, as shown in Table 1, orders with order numbers 1-5 are split into sub-orders. Specifically, for order number 1, it includes to-be-delivered items 1, 2, 3, wherein to-be-delivered items 1, 3 belong to the same warehouse, and are split into sub-orders 1-1, and the warehouse in which to-be-delivered item 2 is located is different from the warehouse in which to-be-delivered items 1, 3 are located, and are split into sub-orders 1-2.
TABLE 1
Furthermore, the order data can be stored by using a sparse matrix, so that the storage and calculation are convenient. For example, the disassembly information in table 1 is converted into that in table 2, each row represents a sub-order, the element with the value of 0 in the row represents that the sub-order does not include the to-be-dispensed item corresponding to the column, the element with the value of not 0 represents that the sub-order includes the to-be-dispensed item corresponding to the column, and the quantity of the to-be-dispensed items is the value of the element. Specifically, for the purpose of calculating and storing convenience, the number of the to-be-dispensed articles may be omitted, wherein 1 indicates that the corresponding to-be-dispensed articles are included in the sub-order, and 0 indicates that the corresponding to-be-dispensed articles are not included in the sub-order.
TABLE 2
After the split orders are selected, the current split rate is calculated, and a comparison basis is provided for the optimization of the follow-up split rate.
Step S102 is to determine the association relation of the objects to be distributed among the sub orders according to the split information, and calculate the association degree of the association relation. The association degree indicates that a certain association relationship exists between the articles to be delivered in the association relationship, and the association relationship can be measured by the value of the association degree. In the embodiment of the invention, an association relationship is determined according to the relationship between the to-be-delivered objects in each sub-order in the split orders, for example, a certain order is split into a sub-order a and a sub-order B, wherein the sub-order a further comprises the to-be-delivered object 1 and the to-be-delivered object 2, and the sub-order B further comprises the to-be-delivered object 3, and the association relationship is the association of { to-be-delivered object 1, the to-be-delivered object 2} and { to-be-delivered object 3} and the other association relationship. When the association degree of the association relation is calculated, the two association relations are preferably calculated respectively, and further, when one order is split into more than two sub orders, the association degree of all the association relations is preferably calculated, so that the subsequent selection of the association degree is more accurate. Wherein the association includes one or more of a support, a confidence, and a promotion.
The support degree is the ratio of the number of orders of the to-be-distributed objects to the total number of orders in the association relation; the Support (Support) is defined by setting the proportion of s% in the set W to Support the sets X and Y simultaneously, and s% is called the Support of the association relation X to Y. The support describes the probability that the intersection Z of the two sets X and Y occurs in set W. Further, the support of the set X to the set Y is equal to the support of the set Y to the set X.
For example, in a history order, the total amount of orders is N; the quantity of orders comprising the article A to be delivered and the article B to be delivered is N AB In these orders, the to-be-delivered object a and the to-be-delivered object B are often split into two sub-orders, and when the two sub-orders are determined as the association relation of { to-be-delivered object a } to { to-be-delivered object B }, the support degree S of the to-be-delivered object a to be-delivered object B in the association relation is determined A-B The calculation formula of (2) is as follows:
S A-B ＝N AB /N
the confidence is the ratio of the number of orders of the to-be-delivered objects in the association relationship to the number of orders of the to-be-delivered objects in at least one sub-order in the association relationship; the definition of Confidence is that when set X is supported in set W, c% is proportional to and also supports set Y, and c% is called the Confidence of association X to Y. Confidence refers to how much probability that set Y is also occurring at the same time in the case that set X occurs, described as the confidence of set X to set Y.
For example, in a history order, the total amount of orders is N; order quantity N including article A to be dispensed A The order quantity including the articles B to be distributed is N B The method comprises the steps of carrying out a first treatment on the surface of the The quantity of orders comprising the article A to be delivered and the article B to be delivered is N AB (wherein N AB ＝N A ∩N B ) The method comprises the steps of carrying out a first treatment on the surface of the In these orders, the to-be-dispensed article a and the to-be-dispensed article B are often split into two sub-orders; when the relationship between { to-be-delivered article A } and { to-be-delivered article B } is determined, the confidence coefficient C of the to-be-delivered article A to the to-be-delivered article B is determined A-B The calculation formula of (2) is as follows:
C A-B ＝N AB /N A
when the relationship between { to-be-delivered object B } and { to-be-delivered object A } is determined, the confidence coefficient of the to-be-delivered object B to the to-be-delivered object A is C B-A The calculation formula of (2) is as follows:
C B-A ＝N AB /N B
the lifting degree is the ratio of the confidence degree of the to-be-delivered object in the association relation to the support degree of the to-be-delivered object. The degree of promotion (Lift) is used to describe how much one thing promotes another in the presence of some association, and this promotion is relative, i.e., the degree of promotion of set X to set Y is equal to the degree of promotion of set Y to set X.
For example, in a history order, an article to be delivered a and an article to be delivered B are often split into two sub-orders, the total amount of orders is N, and the amount of orders including the article to be delivered a and the article to be delivered B is N AB The order quantity including the articles A to be distributed is N A The order quantity including the articles A to be distributed is N B When the relationship between { to-be-delivered article A } and { to-be-delivered article B } is determined, the lift L of the to-be-delivered article A and the to-be-delivered article B is determined A-B The calculated formula is as follows:
L A-B ＝C A-B /S B ＝N AB /N A /(N B /N)＝N AB ·N/(N A ·N B )
wherein S is B Is the independent support degree S of the articles B to be distributed B ＝N B I.e., the ratio of the number of orders comprising the item to be dispensed to the total order number.
When the relationship between { to-be-delivered object B } and { to-be-delivered object A } is determined, the lifting degree L of the to-be-delivered object A of the to-be-delivered object B is determined B-A The calculated formula is as follows:
L B-A ＝C B-A /S A ＝N AB /N B /(N A /N)＝N AB ·N/(N A ·N B )
from this, it can be seen that L A-B ＝L B-A . Further, if in the history order, the total amount of orders is N; the to-be-dispensed object A and the to-be-dispensed object B are often split into the same sub-order, and the to-be-dispensed object C and the to-be-dispensed object D are split into another sub-order; the quantity of orders comprising the article A to be delivered and the article B to be delivered is N AB Order quantity N including both the articles C and D to be dispensed CD The order number of the articles to be distributed A, B, C and D is N ABCD (N ABCD ＝N AB ∩N CD ) When the association relation between { to-be-delivered object A, to-be-delivered object B } and { to-be-delivered object C, to-be-delivered object D } is determined, the lifting degree L of the to-be-delivered object A, the to-be-delivered object B, the to-be-delivered object C and the to-be-delivered object D in the association relation is determined AB-CD The calculated formula is as follows:
L AB-CD ＝C AB-CD /S CD ＝N ABCD /N AB /(N CD /N)＝N ABCD ·N/(N AB ·N CD )
for example, if the total order number is N, the to-be-delivered object 2 and the to-be-delivered object 3 are split into two sub-orders according to the order splitting information in table 2, the association relationship is determined to be { to-be-delivered object 2} to { to-be-delivered object 3}, the order number including the to-be-delivered object 2 and the to-be-delivered object 3 is 1, the order number including the to-be-delivered object 2 is 2, the order number including the to-be-delivered object 3 is 2, and the to-be-delivered object 2 is to-be-deliveredSupport S of article 3 1-2 Confidence C of 1/N for the article 2 to be dispensed and the article 3 to be dispensed 2-3 1/2 of the lifting degree L of the to-be-dispensed object 3 of the to-be-dispensed object 2 2-3 N/4, i.e. 1.N/(2.2).
The above calculation steps can also use an Apriori machine learning algorithm (the Apriori algorithm is a frequent item set algorithm for mining association relations, the core idea is to mine a frequent item set through two stages of candidate set generation and downward closed detection of episodes, the algorithm is widely applied to various fields of business, network security and the like), an association degree calculation model of the association relations is established, and in the training process of the model, numerical values of the support degree, the confidence degree and/or the lifting degree can be initialized, and order data with lower support degree, confidence degree and/or lifting degree values can be screened out.
Example codes are:
grocery_rules<-apriori(data＝Groceries,parameter＝list(support＝,confidence＝,minlen＝))
step S103 represents determining the objects to be clustered according to the association degree. The association relation is determined according to the split orders, so that after the association degree of the association relation is calculated, the articles to be distributed in the sub orders can be measured according to the value of the association degree, the higher the association degree is, the stronger the association relation exists among the articles to be distributed in the sub orders, the articles to be distributed with the high association degree are selected for clustering, the splitting operation caused by the fact that the articles to be distributed are not in the same warehouse can be reduced, and the splitting rate is reduced. Further, it is preferable to measure the association degree of the articles to be delivered by combining three association degrees of the support degree, the confidence degree and the lifting degree. It should be noted that, the clustering of the articles to be distributed in the invention not only means to logically cluster the articles to be distributed, but also means to physically cluster the articles to be distributed, which may be referred to as a bin closing operation in the field of logistics.
Further, the association relationship can be ranked according to the association degree from high to low; and selecting the articles to be delivered in the association relation with the association degree larger than or equal to the first threshold value. After the association degree is calculated, the association degree can be summarized in a table, as shown in table 3, which is the association degree calculation result of a certain association relationship, wherein the support degree of the sub-order { to be delivered article 1, to be delivered article 2} to the sub-order { to be delivered article 4} is 0.0069, the confidence degree is 0.40, and the lifting degree is 2.8, and the values indicate that in all orders, the customer has a probability of purchasing to be delivered article 4 while purchasing to be delivered article 1 and to be delivered article 2, and the probability of purchasing to be delivered article 4 is 0.69%; the probability of 40% among customers who purchase the articles 1 and 2 is also that the articles 4 are purchased at the same time, so that the articles 1 and 2 have a great lifting effect on the articles 4. According to the sorting result of the lifting degree, if the first threshold is set to be 1, the association relation larger than the first threshold is { to be delivered article 1} pair { to be delivered article 3} and { to be delivered article 1, to be delivered article 2} pair { to be delivered article 4}, so that the need of clustering to be carried out on the to-be delivered article 1 and the to-be delivered article 3 and the clustering to be delivered article 1 and the to-be delivered article 2 and the to-be delivered article 4 can be determined, the splitting operation can be reduced, and the splitting rate can be reduced.
TABLE 3 Table 3
As shown in fig. 2, the method for determining the objects to be clustered according to the association degree further includes:
s201, sorting the association relations according to the association degree from high to low; the association relationships may be ranked according to the confidence level and the promotion level, respectively.
S202, calculating the order splitting rate of the orders after the objects to be distributed in M incidence relations before sorting are selected to be clustered, wherein the order splitting rate is the ratio of the number of the split orders to the total number of the orders; the first M correlations of the confidence and promotion ranks may be selected separately, and the initial value of M may be 1 or selected empirically.
S203, determining whether the splitting ratio is larger than a second threshold; the second threshold may be a preset maximum threshold of the split rate.
And S204, if the order splitting rate is larger than the second threshold, increasing the number of M until the order splitting rate after the M association relations before sorting are calculated and clustered is not larger than the second threshold, and determining that the M association relations are to be clustered.
It should be noted that the purpose of the steps S201-204 is to perform trial calculation on the splitting rate of the historical order under the condition that the to-be-clustered objects are removed from the split order data of the historical order, so as to achieve the purpose of determining the to-be-clustered objects and further optimizing the splitting rate.
For example, after sorting according to the association relationship, selecting all the articles to be delivered in the association relationship of the first 10 of the sorting to perform clustering operation, namely after removing the split orders of the articles to be delivered in the history orders, calculating the splitting rate of the history orders, if the splitting rate is still greater than a second threshold, calculating all the articles to be delivered in the association relationship of the first 11 of the sorting to perform clustering operation, and calculating the splitting rate of the history orders, if the splitting rate is not greater than the second threshold, determining that all the articles to be delivered in the association relationship of the first 11 of the sorting are the articles to be delivered to be clustered.
Further, after determining that the N items to be delivered are items of items to be delivered that need to be clustered, the method may further include: and determining the quantity of the articles to be clustered according to the predicted sales quantity of the articles to be clustered. After determining the articles to be clustered, future sales of the articles to be clustered can be predicted, so that the number of the articles to be clustered can be determined according to the predicted sales.
For example, after determining that the to-be-delivered object 1 and the to-be-delivered object 2 are to-be-clustered to-be-delivered objects, sales of the to-be-delivered object 1 and the to-be-delivered object 2 within one month of the future may be further predicted based on historical sales of the to-be-delivered object 1 and the to-be-delivered object 2, and assuming that the predicted sales of the to-be-delivered object 1 is 100 and the predicted sales of the to-be-delivered object 2 is 200, it may be further determined that the clustering operation of the 100 to-be-delivered objects 1 and the 200 to-be-delivered objects 2 is required. As shown in fig. 3, step S301 represents determining the to-be-clustered articles according to the association degree, step S302 represents querying the inventory quantity of the to-be-clustered articles in each warehouse, and if the positions of the shipping warehouses are not considered, in order to balance the inventory among the warehouses, and ensure that the quantity of the to-be-clustered articles determined among each warehouse is the same, step S303 is executed to allocate the to-be-clustered articles among the warehouses, so that the quantity of the to-be-clustered articles determined among each warehouse is the same.
Fig. 4 is a schematic diagram of the main parts of an apparatus 400 for clustering articles to be distributed according to an embodiment of the present invention, as shown in fig. 4:
the acquiring module 401 is configured to acquire splitting information of an order, where the splitting information includes a sub-order split according to the order and an object to be delivered included in the sub-order. The purpose is to determine the data source and reduce the calculation range.
The acquiring module 401 may acquire a certain time range of the order, for example, acquire a history order of last week or last 2 months, query split orders in the history orders, acquire split information of the split orders, where the split information may include, besides sub-orders split according to the order and to-be-delivered objects included in the sub-orders, the number of the split sub-orders, the single number of the sub-orders, the order generation time, and information such as the number, name, quantity, price, etc. of to-be-delivered objects included in the order, and further determine split reasons of the split orders, so as to pick out the order split due to not being in the same warehouse.
The historical orders acquired by the acquisition module 401 can be selected according to brands of the objects to be distributed, delivery warehouses and classification ranges of the objects to be distributed, for example, according to the delivery warehouses, the acquisition module 401 extracts warehouse order detail data of ten front disassembly rates, and analyzes the disassembly order data under the warehouses; or extracting order data of the to-be-delivered object classification with the first ten splitting rates according to the to-be-delivered object classification, and analyzing splitting order data corresponding to all the classes under the to-be-delivered object classification.
The split order data acquired by the acquisition module 401 may be saved in a text file (e.g., csv format). For example, as shown in Table 1, orders with order numbers 1-5 are split into sub-orders. Specifically, for order number 1, it includes to-be-delivered items 1, 2, 3, wherein to-be-delivered items 1, 3 belong to the same warehouse, and are split into sub-orders 1-1, and the warehouse in which to-be-delivered item 2 is located is different from the warehouse in which to-be-delivered items 1, 3 are located, and are split into sub-orders 1-2.
Further, the acquisition module 401 may also use a sparse matrix to store order data, which is convenient for storage and calculation. For example, the disassembly information in table 1 is converted into that in table 2, each row represents a sub-order, the element with the value of 0 in the row represents that the sub-order does not include the to-be-dispensed item corresponding to the column, the element with the value of not 0 represents that the sub-order includes the to-be-dispensed item corresponding to the column, and the quantity of the to-be-dispensed items is the value of the element. Specifically, for the purpose of calculating and storing convenience, the number of the to-be-dispensed articles may be omitted, wherein 1 indicates that the corresponding to-be-dispensed articles are included in the sub-order, and 0 indicates that the corresponding to-be-dispensed articles are not included in the sub-order.
A calculating module 402, configured to determine an association relationship of the objects to be delivered between the sub orders according to the split information of the orders, and calculate an association degree for the association relationship; the association degree indicates that a certain association relationship exists between the articles to be delivered in the association relationship, and the association relationship can be measured by the value of the association degree. In the embodiment of the invention, an association relationship is determined according to the relationship between the to-be-delivered objects in each sub-order in the split orders, for example, a certain order is split into a sub-order a and a sub-order B, wherein the sub-order a further comprises the to-be-delivered object 1 and the to-be-delivered object 2, and the sub-order B further comprises the to-be-delivered object 3, and the association relationship is the association of { to-be-delivered object 1, the to-be-delivered object 2} and { to-be-delivered object 3} and the other association relationship. When the association degree of the association relation is calculated, the two association relations are preferably calculated respectively, and further, when one order is split into more than two sub orders, the association degree of all the association relations is preferably calculated, so that the subsequent selection of the association degree is more accurate. Wherein the association includes one or more of a support, a confidence, and a promotion.
Wherein the support degree is a ratio of the number of orders of the to-be-distributed objects to the total number of orders in the association relation;
the confidence is the ratio of the number of orders of the to-be-delivered objects in the association relationship to the number of orders of the to-be-delivered objects in at least one sub-order in the association relationship;
the lifting degree is the ratio of the confidence degree to the support degree of the objects to be distributed in the association relation.
An Apriori machine learning algorithm (Apriori algorithm is a frequent item set algorithm for mining association relations and has the core idea of mining frequent item sets through two stages of candidate set generation and downward closed detection of episodes, the algorithm is widely applied to various fields of business, network security and the like), an association degree calculation model of the association relations is built, and in the training process of the model, numerical values of the support degree, the confidence degree and/or the lifting degree can be initialized, and order data with lower support degree, confidence degree and/or lifting degree values can be screened out.
And the clustering module 403 is configured to determine the to-be-delivered items to be clustered according to the association degree. Since the association relationship is determined according to the split order, after the calculation module 402 calculates the association degree of the association relationship, the clustering module 403 may measure the articles to be delivered in the sub-order according to the value of the association degree, and the higher the value of the association degree, the stronger the association relationship between the articles to be delivered in the sub-order is indicated, and the clustering module 403 selects the articles to be delivered with high association degree to perform clustering, so that the splitting operation caused by the articles to be delivered not being in the same warehouse can be reduced, and then the splitting rate is reduced. Further, the clustering module 403 preferably measures the association degree of the to-be-delivered objects by combining three association degrees, namely, the support degree, the confidence degree and the lifting degree.
The clustering module 403 is further configured to sort the association relationships according to the association degrees from high to low; and selecting the articles to be delivered in the association relation with the association degree larger than or equal to the first threshold value.
The clustering module 403 is further configured to sort the association relationships according to the association degrees from high to low; calculating the order splitting rate of the orders after the objects to be distributed in the M incidence relations before sorting are clustered, wherein the order splitting rate is the ratio of the number of the split orders to the total number of the orders; determining whether the split rate is greater than a second threshold; and if the splitting rate is greater than a second threshold, increasing the number of M until the splitting rate after the M incidence relations before sorting are calculated and clustered is not greater than the second threshold, and determining that the M incidence relations are to be clustered.
The clustering module 403 is further configured to determine the number of the to-be-distributed objects to be clustered according to the predicted sales amount of the to-be-distributed objects.
Fig. 5 illustrates an exemplary system architecture 500 of a method of clustering items to be distributed or an apparatus for clustering items to be distributed to which embodiments of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 is used as a medium to provide communication links between the terminal devices 501, 502, 503 and the server 505. The network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 505 via the network 504 using the terminal devices 501, 502, 503 to receive or send messages or the like.
The terminal devices 501, 502, 503 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server providing support for users with the terminal devices 501, 502, 503. The background management server may analyze and process the received data such as the information query request, and feed back the processing result (for example, order splitting information) to the terminal device.
It should be noted that, in the embodiment of the present invention, a method for clustering objects to be distributed is generally performed by the server 505, and accordingly, a device for clustering objects to be distributed is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Fig. 6 is a schematic diagram of a computer system 600 suitable for use in implementing the terminal device of the embodiment of the present invention. The terminal device shown in fig. 6 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.
In particular, the processes described in the above step diagrams may be implemented as computer software programs according to the disclosed embodiments of the invention. For example, 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 shown in the step diagrams. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 601.
The computer readable medium shown in the present invention includes a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium includes, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, semiconductor system, apparatus, or device, or any combination of the preceding. Computer-readable storage media 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 combination of the foregoing. In the context of this disclosure, a computer-readable storage medium includes any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device; a computer readable signal medium includes a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave, and the propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any combination thereof. A computer readable signal medium may also 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: wireless, wire, fiber optic cable, RF (radio frequency), or the like, or any combination of the foregoing.
The steps of the figures or block diagrams, which illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention, may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should 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 or step diagrams, and combinations of blocks in the block diagrams or step diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.
The modules or units involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules or units may also be provided in a processor, for example, as: a processor includes an acquisition module, a calculation module, and a clustering module. Where the names of the modules or units do not in some way constitute a limitation of the module or unit itself, the acquisition module may also be described as "module for acquiring split information of an order", for example.
In another aspect, the embodiment of the present invention further provides a computer readable medium, which may be included in the apparatus described in the above embodiment; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include: acquiring splitting information of an order, wherein the splitting information comprises a sub order split according to the order and articles to be distributed included in the sub order; determining the association relation of the objects to be distributed among the sub orders according to the splitting information of the orders, and calculating the association degree of the association relation; and determining the articles to be clustered according to the association degree.
According to the technical scheme provided by the embodiment of the invention, the articles to be distributed which need to be clustered can be determined according to the split information of the historical orders, so that the splitting rate is reduced, the order distribution cost is saved, the task operation is saved, the time-efficiency control on order distribution is improved, and the customer experience is optimized.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims (10)

1. A method of clustering items to be distributed, comprising:
acquiring splitting information of an order, wherein the splitting information comprises a sub order split according to the order and articles to be distributed included in the sub order;
determining the association relation of the objects to be distributed among the sub orders according to the splitting information of the orders, and calculating the association degree of the association relation;
determining the articles to be clustered according to the association degree, wherein the articles to be clustered comprise:
sorting the association relations according to the association degree from high to low;
calculating the order splitting rate of the orders after the objects to be distributed in the M incidence relations before sorting are clustered, wherein the order splitting rate is the ratio of the number of the split orders to the total number of the orders;
determining whether the split rate is greater than a second threshold;
and if the splitting rate is greater than a second threshold, increasing the number of M until the splitting rate after the M incidence relations before sorting are calculated and clustered is not greater than the second threshold, and determining that the M incidence relations are to be clustered.
2. The method of claim 1, wherein the degree of association comprises one or more of a degree of support, a degree of confidence, and a degree of promotion;
Wherein the support degree is a ratio of the number of orders of the to-be-distributed objects to the total number of orders in the association relation;
the confidence is the ratio of the number of orders of the to-be-delivered objects in the association relationship to the number of orders of the to-be-delivered objects in at least one sub-order in the association relationship;
the lifting degree is the ratio of the confidence degree to the support degree of the objects to be distributed in the association relation.
3. The method according to claim 1 or 2, wherein the method for determining the objects to be clustered according to the degree of association comprises:
sorting the association relations according to the association degree from high to low;
and selecting the articles to be delivered in the association relation with the association degree larger than or equal to the first threshold value.
4. The method of claim 1, wherein after determining that the to-be-delivered item in the M associations is a category of to-be-delivered items to be clustered, the method further comprises:
and determining the quantity of the articles to be clustered according to the predicted sales quantity of the articles to be clustered.
5. An apparatus for clustering items to be distributed, comprising:
The system comprises an acquisition module, a distribution module and a distribution module, wherein the acquisition module is used for acquiring splitting information of an order, wherein the splitting information comprises a sub order split according to the order and an object to be distributed included in the sub order;
the calculating module is used for determining the association relation of the objects to be distributed among the sub orders according to the splitting information of the orders and calculating the association degree of the association relation;
the clustering module is used for determining articles to be clustered according to the association degree, and sequencing the association relation from high to low according to the association degree;
calculating the order splitting rate of the orders after the objects to be distributed in the M incidence relations before sorting are clustered, wherein the order splitting rate is the ratio of the number of the split orders to the total number of the orders;
determining whether the split rate is greater than a second threshold;
and if the splitting rate is greater than a second threshold, increasing the number of M until the splitting rate after the M incidence relations before sorting are calculated and clustered is not greater than the second threshold, and determining that the M incidence relations are to be clustered.
6. The apparatus of claim 5, wherein the degree of association comprises one or more of a degree of support, a degree of confidence, and a degree of promotion;
Wherein the support degree is a ratio of the number of orders of the to-be-distributed objects to the total number of orders in the association relation;
the confidence is the ratio of the number of orders of the to-be-delivered objects in the association relationship to the number of orders of the to-be-delivered objects in at least one sub-order in the association relationship;
the lifting degree is the ratio of the confidence degree to the support degree of the objects to be distributed in the association relation.
7. The apparatus of claim 5 or 6, wherein the clustering module is further configured to rank the association relationships from high to low according to the association degree; and selecting the articles to be delivered in the association relation with the association degree larger than or equal to the first threshold value.
8. The apparatus of claim 5, wherein the clustering module is further configured to determine the number of items to be clustered based on a predicted sales of the items to be clustered.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.
10. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by one or more processors, implements the method according to any of claims 1-4.
CN201910132026.4A 2019-02-22 2019-02-22 Method and device for clustering articles to be distributed Active CN111612385B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910132026.4A CN111612385B (en) 2019-02-22 2019-02-22 Method and device for clustering articles to be distributed

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910132026.4A CN111612385B (en) 2019-02-22 2019-02-22 Method and device for clustering articles to be distributed

Publications (2)

Publication Number Publication Date
CN111612385A CN111612385A (en) 2020-09-01
CN111612385B true CN111612385B (en) 2024-04-16

Family

ID=72199625

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910132026.4A Active CN111612385B (en) 2019-02-22 2019-02-22 Method and device for clustering articles to be distributed

Country Status (1)

Country Link
CN (1) CN111612385B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112053068B (en) * 2020-09-09 2021-08-24 上海有个机器人有限公司 Cloud scheduling method and device for delivery robot and server
CN114186903A (en) * 2020-09-14 2022-03-15 上海顺如丰来技术有限公司 Warehouse product selection method and device, computer equipment and storage medium
CN113393192A (en) * 2021-06-16 2021-09-14 北京京东振世信息技术有限公司 Method, device and equipment for delivering articles out of warehouse and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107016073A (en) * 2017-03-24 2017-08-04 北京科技大学 A kind of text classification feature selection approach
CN107545381A (en) * 2016-06-24 2018-01-05 北京京东尚科信息技术有限公司 Manage the method and warehouse management system of warehouse inventory
WO2018074851A1 (en) * 2016-10-18 2018-04-26 주식회사 우아한형제들 Delivery order distribution system and method
WO2018205760A1 (en) * 2017-05-09 2018-11-15 北京京东尚科信息技术有限公司 Address selection method and device for delivery station
CN109146646A (en) * 2018-09-25 2019-01-04 北京三快在线科技有限公司 Singulated settlement method, device, electronic equipment and computer-readable medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107545381A (en) * 2016-06-24 2018-01-05 北京京东尚科信息技术有限公司 Manage the method and warehouse management system of warehouse inventory
WO2018074851A1 (en) * 2016-10-18 2018-04-26 주식회사 우아한형제들 Delivery order distribution system and method
CN107016073A (en) * 2017-03-24 2017-08-04 北京科技大学 A kind of text classification feature selection approach
WO2018205760A1 (en) * 2017-05-09 2018-11-15 北京京东尚科信息技术有限公司 Address selection method and device for delivery station
CN109146646A (en) * 2018-09-25 2019-01-04 北京三快在线科技有限公司 Singulated settlement method, device, electronic equipment and computer-readable medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Water Distribution System Clustering and Partitioning Based on Social Network Algorithms;Armando Di Nardo等;《Procedia Engineering》;20151231;全文 *
数据挖掘在电商运营策略中的应用研究;尹胜燕;《中国优秀硕士学位论文全文数据库 经济与管理科学辑》;第2018年卷(第1期);第3章 *
面向最小化拆单率的基于订单分配顺序的库存优化研究;李建斌;孙哲;陈威帆;李文秀;;工业工程与管理;20171210(第06期);全文 *

Also Published As

Publication number Publication date
CN111612385A (en) 2020-09-01

Similar Documents

Publication Publication Date Title
CN106980955B (en) Method and apparatus for outputting information
CN111612385B (en) Method and device for clustering articles to be distributed
CN112184348B (en) Order data processing method, device, electronic equipment and medium
CN110059991B (en) Warehouse item selection method, system, electronic device and computer readable medium
CN113095893A (en) Method and device for determining sales of articles
CN110826953B (en) Warehouse storage equipment planning method and device
CN113793081A (en) Storage monitoring method and device, computer readable medium and electronic equipment
CN109255563B (en) Method and device for determining storage area of article
CN110956417A (en) Store commodity processing method and device
CN113762863A (en) Inventory management method and device
CN112784212B (en) Inventory optimization method and device
CN110826948B (en) Warehouse selecting method and device
CN112784861A (en) Similarity determination method and device, electronic equipment and storage medium
CN113112048A (en) Method and device for returning articles to warehouse
CN110490682B (en) Method and device for analyzing commodity attributes
CN110956478A (en) Method and device for determining goods input quantity
CN107357847B (en) Data processing method and device
CN114677174A (en) Method and device for calculating sales volume of unladen articles
CN110880119A (en) Data processing method and device
CN115525665A (en) Information processing method and device, electronic equipment and computer readable medium
CN113379173B (en) Method and device for marking warehouse goods with labels
CN110084541B (en) Method and apparatus for predicting supplier delivery duration
CN110738538B (en) Method and device for identifying similar objects
CN114723354A (en) Online business opportunity mining method, equipment and medium for suppliers
CN113743972B (en) Method and device for generating article information

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
TA01 Transfer of patent application right

Effective date of registration: 20210304

Address after: 101, 1st floor, building 2, yard 20, Suzhou street, Haidian District, Beijing 100080

Applicant after: Beijing Jingbangda Trading Co.,Ltd.

Address before: 100086 8th Floor, 76 Zhichun Road, Haidian District, Beijing

Applicant before: BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY Co.,Ltd.

Applicant before: BEIJING JINGDONG CENTURY TRADING Co.,Ltd.

Effective date of registration: 20210304

Address after: 6 / F, 76 Zhichun Road, Haidian District, Beijing 100086

Applicant after: Beijing Jingdong Zhenshi Information Technology Co.,Ltd.

Address before: 101, 1st floor, building 2, yard 20, Suzhou street, Haidian District, Beijing 100080

Applicant before: Beijing Jingbangda Trading Co.,Ltd.

TA01 Transfer of patent application right
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant