CN111667208A

CN111667208A - Article storage control method, device, equipment and medium

Info

Publication number: CN111667208A
Application number: CN201910176211.3A
Authority: CN
Inventors: 黄倩
Original assignee: Beijing Jingdong Century Trading Co Ltd; Beijing Jingdong Shangke Information Technology Co Ltd
Current assignee: Beijing Jingbangda Trade Co Ltd; Beijing Jingdong Zhenshi Information Technology Co Ltd
Priority date: 2019-03-08
Filing date: 2019-03-08
Publication date: 2020-09-15
Anticipated expiration: 2039-03-08
Also published as: CN111667208B

Abstract

The embodiment of the invention discloses a method, a device, equipment and a medium for controlling article storage, wherein the method comprises the following steps: acquiring a plurality of historical item acquisition tasks; according to the item attribution party information contained in each historical item acquisition task, generating task characteristic data corresponding to the historical item acquisition task and used for representing the item attribution party involved in the historical item acquisition task; and determining the association degree between the article attribution parties contained in the historical article acquisition task according to the task characteristic data, wherein the association degree is used as a deployment basis of the article attribution parties in the same bin. According to the method provided by the embodiment of the invention, the association degree between the object attribution parties is excavated through the historical object acquisition task data, the object attribution party in the same bin is recommended based on the association degree between the object attribution parties, the list splitting rate can be reduced, the logistics cost is further reduced, the overall logistics timeliness of the object acquisition task is improved, and the user experience is improved.

Description

Article storage control method, device, equipment and medium

Technical Field

The embodiment of the invention relates to the technical field of big data processing, in particular to a method, a device, equipment and a medium for controlling article storage.

Background

With the rapid development of the internet, online shopping has become an important shopping mode. Typically, each user purchase order may include items from multiple merchants, which in turn may be stored in warehouses in different regions.

Currently, when determining the storage mode of each merchant item, the storage mode is mainly based on the nearby delivery city of the merchant, or the storage mode is based on the city with the largest sales volume of the merchant. Such a distribution mode may result in an increased bill splitting rate.

Illustratively, when a customer order involves N merchants whose items are stored in M (M >1) warehouses, the order is split into more than two sub-orders. The order splitting rate is the ratio of the number of order splitting orders to the total number of orders. The order splitting situation can affect the goods scheduling and delivery process.

Therefore, high order splitting rate can cause high cost, and the overall logistics timeliness of the order can be influenced, and the user experience is influenced.

Disclosure of Invention

The embodiment of the invention provides an article storage control method, device, equipment and medium, which aim to reduce logistics cost, improve the overall logistics timeliness of an article acquisition task and further improve user experience.

In a first aspect, an embodiment of the present invention provides an article storage control method, including:

acquiring a plurality of historical item acquisition tasks;

according to the item attribution party information contained in each historical item acquisition task, generating task characteristic data corresponding to the historical item acquisition task, wherein the task characteristic data is used for representing the item attribution party involved in the historical item acquisition task;

and determining the association degree between the article attribution parties contained in the historical article acquisition task according to the task characteristic data, wherein the association degree is used as a deployment basis of the article attribution parties in the same bin.

In a second aspect, an embodiment of the present invention further provides an article storage control apparatus, including:

a historical task obtaining module for obtaining a plurality of historical item obtaining tasks,

the characteristic data generation module is used for generating task characteristic data corresponding to the historical article acquisition tasks according to article attribution party information contained in each historical article acquisition task, and the task characteristic data is used for representing the article attribution party involved in the historical article acquisition tasks;

and the association data determining module is used for determining the association degree between the article attribution parties contained in the historical article obtaining task according to the task characteristic data, wherein the association degree is used as a deployment basis of the article attribution parties in the same bin.

In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:

one or more processors;

storage means for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement a method of item storage control as provided by any of the embodiments of the invention.

In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the article storage control method according to any embodiment of the present invention.

The embodiment of the invention acquires tasks by acquiring a plurality of historical articles; according to the item attribution party information contained in each historical item acquisition task, generating task characteristic data which is corresponding to the historical item acquisition task and is used for representing the item attribution party in the historical item acquisition task; according to the task characteristic data, determining the relevance between the article attribution parties contained in the historical article obtaining task, wherein the relevance is used as a deployment basis of the article attribution parties in the same bin, recommending the article attribution parties in the same bin based on the relevance between the article attribution parties, reducing the list splitting rate, further reducing the logistics cost, improving the overall logistics timeliness of the article obtaining task, and improving the user experience.

Drawings

Fig. 1 is a flowchart of an article storage control method according to an embodiment of the present invention;

fig. 2 is a flowchart of an article storage control method according to a second embodiment of the present invention;

fig. 3 is a flowchart of an article storage control method according to a third embodiment of the present invention;

fig. 4a is a flowchart of an article storage control method according to a fourth embodiment of the present invention;

fig. 4b is a schematic structural diagram of a storage bin in an article storage control method according to an embodiment of the present invention;

fig. 5 is a flowchart of an article storage control method according to a fifth embodiment of the present invention;

fig. 6 is a schematic structural diagram of an article storage control device according to a sixth embodiment of the present invention;

fig. 7 is a schematic structural diagram of a computer device according to a seventh embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of an article storage control method according to an embodiment of the present invention. The embodiment can be applied to the situation when determining the association degree between the article attribution parties so as to determine the article storage mode of each article attribution party. The method may be performed by an article storage control apparatus, which may be implemented in software and/or hardware, for example, which may be configured in a computer device. As shown in fig. 1, the method includes:

and S110, acquiring a plurality of historical item acquisition tasks.

In this embodiment, the item acquisition task may be initiated by the user, and is used for the user to acquire the item of interest. The historical item acquisition task may be an item acquisition task before the current time, or an item acquisition task within a preset time period. Optionally, the obtaining of the plurality of historical item obtaining tasks may be obtaining all historical item obtaining tasks meeting preset item obtaining task types within a preset time period. The acquired plurality of historical item acquisition tasks may include item information, item acquisition task types, and other item acquisition task information of the acquired plurality of historical item acquisition tasks.

Taking the e-commerce platform as an example, the historical item acquisition task may be various commodity order orders acquired by the e-commerce platform, and the number of the commodity order orders is usually large. Optionally, the obtaining of the plurality of historical orders may be obtaining all historical orders meeting preset order types within a preset time period in the e-commerce platform. Optionally, all historical orders within a preset time period may be obtained in a background server of the e-commerce platform. Generally, when a user purchases a virtual commodity (such as a network game card, a telephone charge rechargeable card, etc.) through an e-commerce platform, the user does not purchase the virtual commodity in the same order as the physical commodity, so that after all historical orders are obtained, the obtained historical orders can be screened according to the commodity types, and the orders containing the virtual commodity in the historical orders are deleted.

For example, when the order quantity of the e-commerce platform is stable, a fixed time period may be preset according to the average daily order quantity of the platform. Alternatively, the preset time period may be 1 month. When the order quantity of the e-commerce platform is unstable, the time period can be determined according to the average daily quantity of the orders at the selected time point. For example, if the average daily number of orders at the selected time point is large (for example, larger than a certain threshold), a shorter time period may be selected as the preset time period; if the average number of days at the selected time point is small (e.g., less than a threshold), the predetermined time period may be a longer time period.

And S120, generating task characteristic data corresponding to the historical item acquisition tasks according to item attribution party information contained in each historical item acquisition task, wherein the task characteristic data is used for representing the item attribution party involved in the historical item acquisition tasks.

In this embodiment, corresponding item acquisition task feature data is generated for each historical item acquisition task, and is used to characterize an item attribution party included in the historical item acquisition task. Optionally, the form of the task feature data is not limited herein. For example, the item acquisition task feature data may be represented in an array, a set, or the like, as long as all item attributions included in the historical item acquisition task can be represented.

For example, when the item acquisition task feature data is in an array form, it may be determined whether an item attribution party corresponding to an element exists in the item acquisition task according to the value of the element in the item acquisition task feature data. If the task feature data corresponding to a certain historical item acquisition task is (0, 0, 1), and in the array, the item attribution party corresponding to the element 1 is the item attribution party 1, the item attribution party corresponding to the element 2 is the item attribution party 2, and the item attribution party corresponding to the element 3 is the item attribution party 3, the task feature data indicates that the item attribution party included in the historical item acquisition task is the item attribution party 3. When the item acquisition task feature data is in a set form, the item attribution party contained in the item acquisition task can be directly determined according to each element in the task feature data. If the item acquisition task feature data corresponding to a certain historical item acquisition task is { item attribution party 1, item attribution party 2}, the task feature data indicates that the item attribution parties included in the historical item acquisition task are item attribution party 1 and item attribution party 2.

Taking the e-commerce platform as an example, the item acquisition task may be an order placed by a user through the e-commerce platform, the item attribution party may be a merchant, and the task characteristic data of the historical item acquisition task may be order characteristic data of the historical order. After a plurality of historical orders are obtained, order characteristic data corresponding to each order can be determined according to the existence condition of each merchant in each order.

S130, determining the association degree between the article attribution parties included in the historical article acquisition task according to the task characteristic data, wherein the association degree is used as a deployment basis of the article attribution parties in the same bin.

In this embodiment, according to task feature data of all historical item acquisition tasks, the association degree between each item attribution party included in all historical item acquisition tasks is determined.

Optionally, an attribution party combination may be formed according to all the item attribution parties included in all the historical item acquisition tasks, and each attribution party combination includes two or more different item attribution parties. And determining the quantity of article acquisition tasks of article attributions in the attribution party combination in the same historical article acquisition task and the quantity of article acquisition tasks of the article attributions in the attribution party combination in the historical article acquisition task, and determining the association degree between the article attributions in the attribution party combination according to the quantity of the article acquisition tasks. Optionally, whether to place the items of the attribution parties of the items in the attribution party combination in the same warehouse may be determined according to the association degree between the attribution parties of the items in the attribution party combination.

Still taking the e-commerce platform as an example, the set of attributions may be a set of merchants. If the combination of the merchants is merchant 1 and merchant 2, counting that the obtained historical orders simultaneously include order quantity 1 of merchant 1 and merchant 2, the obtained historical orders include order quantity 2 of merchant 1, and the obtained historical orders include order quantity 3 of merchant 2, determining the association degree between merchant 1 and merchant 2 according to order quantity 1, order quantity 2, and order quantity 3, and then judging whether to place the commodities of merchant 1 and merchant 2 in the same warehouse according to the association degree.

On the basis of the scheme, the relevance preferably comprises compactness and lifting degree;

the closeness is used for representing the probability that different article attribution parties appear in the same article obtaining task at the same time, and the promotion degree is used for representing the strength of the relevance between the article attribution parties.

In this embodiment, the association degree between the attribution parties of the items includes the closeness between the attribution parties of the items and the promotion degree between the attribution parties of the items.

Optionally, the closeness between the article attributions represents whether the article attributions are close or not, specifically, the closeness represents the possibility that each article attribution appears in the same article acquisition task, the higher the closeness between each article attribution in the attribution group, the higher the possibility that each article attribution appears in the same article acquisition task, the lower the closeness between each article attribution in the attribution group, the lower the possibility that each article attribution appears in the same article acquisition task.

For example, if the closeness between the item attribution party 1 and the item attribution party 2 is 0.75 and the closeness between the item attribution party 2 and the item attribution party 3 is 0.5, the probability that the item attribution party 1 and the item attribution party 2 simultaneously appear in the same item acquisition task is higher than the probability that the item attribution party 2 and the item attribution party 3 simultaneously appear in the same item acquisition task.

However, when the closeness between the two article attribution parties is high, it does not represent that there is a positive association relationship between the two article attribution parties, and it is necessary to check the positive or negative relationship of the influence between the two article attribution parties through a lifting degree algorithm. Optionally, the degree of increase between the attribution parties of the items represents the strength of the association between the attribution parties of the items, and specifically, the numerical value of the degree of increase represents that the association between the attribution parties of the items is positive association, negative association or mutually independent. When the promotion degree is larger than 1, the relevance between the article attribution parties is positive relevance, the influence between the article attribution parties is mutual positive influence, and the larger the numerical value of the promotion degree is, the larger the relevance meaning between the article attribution parties is. When the promotion degree is smaller than 1, the relevance between the article attribution parties is negative relevance, and the influence between the article attribution parties is mutual negative influence. When the lifting degree is equal to 1, the article attribution parties are independent of each other.

For example, if the degree of lift between the item attribution party 1 and the item attribution party 2 is greater than 1, it indicates that the presence of the item attribution party 1 or the item attribution party 2 has a positive effect on the other party; if the promotion degree between the article attribution party 1 and the article attribution party 2 is smaller than 1, the negative influence on the other party is indicated by the appearance of the article attribution party 1 or the article attribution party 2; if the lifting degree between the article attribution party 1 and the article attribution party 2 is equal to 1, the lifting degree indicates that the appearance of the article attribution party 1 or the article attribution party 2 has no influence on the party, namely whether the article attribution party 1 exists, the appearance of the article attribution party 2 does not have influence, whether the article attribution party 2 exists, and the appearance of the article attribution party 1 does not have influence.

On the basis of the scheme, the method further comprises the following steps:

taking the attribution party combination corresponding to the closeness larger than the preset closeness threshold value as the same-bin candidate combination;

and if the lifting degree of the same-bin candidate combination is greater than a preset lifting degree threshold value, taking the same-bin candidate combination as a recommended same-bin attribution party combination.

In one embodiment of the present invention, whether a positive association relationship exists between the article attributions can be determined according to the closeness and the promotion degree between the article attributions. As can be seen from the above, when the compactness value is higher, it indicates that the probability that each article-belonging party appears in the same article acquisition task is higher, and when the degree of improvement is greater than 1, it indicates that the association between the article-belonging parties is positive, and the influence between the article-belonging parties is mutual positive. Therefore, a closeness threshold value can be preset, an affiliate combination with high closeness is screened out through the preset closeness threshold value, the screened affiliate combination is further screened out according to the promotion degree, an affiliate combination which is positively correlated with each other is obtained, and the affiliate combination which is positively correlated with each other is used as a recommended co-warehouse affiliate combination.

Optionally, the closeness threshold may be determined according to the closeness corresponding to each home party combination. For example, a mean or a variance of the closeness of each of the combinations of the attributions may be calculated, the mean or the variance of each of the combinations of the attributions may be used as a closeness threshold, or the closeness of each of the combinations of the attributions may be sorted from high to low, and the closeness corresponding to the preset sort number may be used as the closeness threshold. For example, the preset ranking number may be determined according to the number of combinations of the attributions. For example, when the number of the home party combinations is 300, the preset ranking number may be 101.

Optionally, the closeness of each affiliate combination may be sorted, and the affiliate combination corresponding to the closeness of the previous preset number or preset proportion is used as the candidate affiliate combination. For example, after the closeness of each of the combinations of the attributions is ranked, the top 30% of the combinations of the attributions may be selected as the candidate combinations of the attributions.

Taking an e-commerce platform as an example, by analyzing real and massive customer order data, the method provided by the embodiment of the invention can be used for mining out merchant combinations which are high in compactness and have positive influence on business of a consumer (B2C) in an enterprise in electronic commerce, storing commodities of the merchant combinations as intensively as possible, reducing the cost caused by 'order splitting rate', improving the overall logistics timeliness and improving the customer shopping experience.

Example two

Fig. 2 is a flowchart of an article storage control method according to a second embodiment of the present invention. The present embodiment is further optimized on the basis of the above-described embodiments. As shown in fig. 2, the method includes:

and S210, acquiring a plurality of historical item acquisition tasks.

S220, aiming at each historical article acquisition task, generating a task feature vector corresponding to the historical article acquisition task.

In this embodiment, the form of the task feature data is an array form, and the item attribution party included in the historical item acquisition task is represented in the form of the task feature vector. Optionally, the number of elements in the task feature vector is equal to the number of the article attribution parties included in all the historical article obtaining tasks, each element in the task feature vector corresponds to one article attribution party, and an element value of the element is used for representing the existence condition of the article attribution party corresponding to the element in the historical article obtaining tasks. Optionally, the element value corresponding to the existence condition of the article attribution party may be preset, and then the task feature vector corresponding to the historical article obtaining task is generated according to the existence condition of each article attribution party in the historical article obtaining task.

For example, it may be set that when the item holder exists in the historical item acquisition task, the corresponding element value is set to 1, and when the item holder does not exist in the historical item acquisition task, the corresponding element value is set to 0. And if the number of the article attribution parties contained in all the historical article acquisition tasks is 3, the dimensionality of the task feature vector corresponding to the historical article acquisition task is 3. Assuming that the article attribution party corresponding to the element 1 in the task feature vector is an article attribution party 1, the article attribution party corresponding to the element 2 is an article attribution party 2, the article attribution party corresponding to the element 3 is an article attribution party 3, and a certain historical article acquisition task only includes the article attribution party 3, the task feature vector corresponding to the historical article acquisition task is (0, 0, 1).

S230, two task feature vectors are randomly selected from the task feature vectors, and the element values of the corresponding positions of the selected task feature vectors are subjected to AND operation to obtain operation result vectors among the selected task feature vectors.

In this embodiment, after determining the task feature vectors corresponding to the historical item acquisition tasks, two task feature vectors are arbitrarily selected from all the task feature vectors, and the same item attributions included in the item acquisition tasks corresponding to the selected task feature vectors are obtained.

Optionally, the and operation is performed on the element values at the corresponding positions of the two selected task feature vectors to obtain an operation result vector between the two task feature vectors. The operation result vector is used for representing the existence condition of the same article attribution party in the two article acquisition tasks corresponding to the feature vectors of the two selected article acquisition tasks.

Illustratively, if the selected task feature vectors are (0, 0, 1) and (0, 1, 1), the element values of the corresponding positions are logically anded to obtain an operation result vector of (0, 0, 1). If the article attribution party corresponding to the element 1 in the article obtaining task feature vector is the article attribution party 1, the article attribution party corresponding to the element 2 is the article attribution party 2, and the article attribution party corresponding to the element 3 is the article attribution party 3, it indicates that the same article attribution party in the two article obtaining tasks corresponding to the two selected task feature vectors is the article attribution party 3.

S240, aiming at each operation result vector, determining the number of elements representing element values existing in an article attribution party in the operation result vector according to the element values of all the elements in the operation result vector, if the number of the elements is larger than the preset element number, determining an article attribution party identifier contained in the operation result vector according to the element values, establishing at least one attribution party combination according to the article attribution party identifier, and establishing a corresponding relation between the operation result vector and the at least one attribution party combination.

In this embodiment, after obtaining the operation result vector between the task feature vectors of any two article acquisition tasks in all historical article acquisition tasks, for each operation result vector, the home party combination corresponding to the operation result vector is determined.

Optionally, the number of the same article attribution parties between the article obtaining tasks may be any number, and in order to screen out the attribution party combination included in the operation result vector, the operation result vector is firstly screened according to the number of the article attribution parties included in the operation result vector. Optionally, if the number of the article attribution parties included in the operation result vector is greater than 2, it is determined that the article attribution parties included in the operation result vector can form at least one attribution party combination, and all the article attribution parties included in the operation result vector form at least one attribution party combination. Optionally, if the operation result vectorIf the number of the belongings included in the calculation result vector is n, the number of the belongings corresponding to the calculation result vector is C_n ²＝n(n-1)/2。

In this embodiment, the element value of the element in the operation result vector indicates the existence of the article attribution party corresponding to the element, so the operation result vector can be filtered by the number of elements in the operation result vector indicating the existence of the element value of the article attribution party. And if the number of the elements which represent the element values existing in the article attribution party in the operation result vector is more than 2, the number of the article attribution parties contained in the operation result vector is more than 2.

For example, if the element value indicating the existence of the item attribution party in the operation result vector is 1 and the operation result vector is (1, 1, 1), the number of elements indicating the existence of the item attribution party in the operation result vector is 3, and if the item attribution party corresponding to element 1 in the task feature vector is the item attribution party 1, the item attribution party corresponding to element 2 is the item attribution party 2, and the item attribution party corresponding to element 3 is the item attribution party 3, the item attribution parties existing in the operation result vector are the item attribution party 1, the item attribution party 2, and the item attribution party 3, and 3 combinations of attribution parties can be formed, and the formed combinations of attribution parties are (item attribution party 1, item attribution party 2), (item attribution party 2, item attribution party 3), and (item attribution party 1, item attribution party 3), respectively, then the combination of attribution parties corresponding to the operation result vector is (item attribution party 1, item attribution 2), (item attribution 2, item attribution 3) and (item attribution 1, item attribution 3).

And S250, aiming at each attribution party combination, determining the number of operation result vectors corresponding to the attribution party combination, and taking the number of the operation result vectors as the occurrence frequency of the attribution parties of all the articles in the attribution party combination in the historical article acquisition task at the same time.

In this embodiment, after the corresponding relationship between each operation feature vector and the attribution party combination is obtained, the occurrence frequency of each attribution party combination in all operation feature vectors is counted, and the occurrence frequency of each attribution party combination in all operation feature vectors is taken as the occurrence frequency of each item attribution party in the attribution party combination appearing in different historical item acquisition tasks at the same time. Optionally, the number of occurrences of the home party combination in all the operation feature vectors may be determined according to the number of operation result vectors corresponding to the home party combination. For example, if the number of operation result vectors corresponding to the affiliate group is 6, it is determined that the number of occurrences of the respective item affiliates in the affiliate group occurring in different historical item acquisition tasks at the same time is 6.

And S260, determining the association degree between the attribution parties of each article in the attribution party combination according to the occurrence frequency and the number of the attribution parties of each article in the attribution party combination contained in the historical article acquisition task.

In this embodiment, the association degree between the attributions of the articles in the attribution group can be obtained according to the number of occurrences of the attributions of the articles in the attribution group occurring simultaneously in different historical article obtaining tasks, and the number of article obtaining tasks including the attribution of the articles in the attribution group in the historical article obtaining tasks.

For example, if the attribution party combination includes an item attribution party 1 and an item attribution party 2, the association degree between the item attribution party 1 and the item attribution party 2 may be obtained according to the number of occurrences of the item attribution party 1 and the item attribution party 2 occurring in different historical item obtaining tasks at the same time, the number of item obtaining tasks including the item attribution party 1 in the historical item obtaining tasks, and the number of item obtaining tasks including the item attribution party 2 in the historical item obtaining tasks.

According to the technical scheme of the embodiment of the invention, the task feature data is embodied into the task feature vector on the basis of the embodiment, the scheme is embodied on the basis of the task feature vector, the task feature vector corresponding to the historical article acquisition task is generated, the occurrence times of the simultaneous occurrence of the attribution parties of the articles in the attribution party combination in the same article acquisition task are obtained on the basis of the task feature vector, and the association degree between the attribution parties of the articles in the attribution party combination is obtained according to the occurrence times and the number of the attribution parties of the articles in the attribution party combination in the historical article acquisition task, so that the association degree between the attribution parties of the articles is more accurate, and the basis of the same-bin arrangement of the attribution parties of the articles is more accurate.

On the basis of the above scheme, the determining the association degree between the attribution parties of each item in the attribution party combination according to the occurrence number and the number of the attribution parties of each item in the historical item acquisition task, including:

determining closeness between attributions of items in the attribution combination according to the following formula:

determining the promotion degree between the attributions of the items in the attribution combination according to the following formula:

the method comprises the following steps that density (X, Y) is the compactness between an article attribution party X and an article attribution party Y, Lift (X, Y) is the promotion degree between the article attribution party X and the article attribution party Y, N (X, Y) is the number of times that the article attribution party X and the article attribution party Y appear in historical article obtaining tasks at the same time, N (X) is the number of article obtaining tasks that the article attribution party X appears in the historical article obtaining tasks, N (Y) is the number of article obtaining tasks that the article attribution party Y appears in the historical article obtaining tasks, and N is the total number of article obtaining tasks of the historical article obtaining tasks.

In this embodiment, the manner of determining the closeness between the item attribution party X and the item attribution party Y may be:

the attribute (X, Y) is the closeness between an article attribution party X and an article attribution party Y, P (X, Y) is the probability that the article attribution party X and the article attribution party Y appear in the historical article acquisition task at the same time, P (X) is the probability that the article attribution party X appears in the historical article acquisition task, P (Y) is the probability that the article attribution party Y appears in the historical article acquisition task, N (X, Y) is the number of occurrences that the article attribution party X and the article attribution party Y appear in the historical article acquisition task at the same time, N (X) is the number of article acquisition tasks that the article attribution party X appears in the historical article acquisition task, N (Y) is the number of article acquisition tasks that the article attribution party Y appears in the historical article acquisition task, and N represents the total number of article acquisition tasks of the acquired historical article acquisition task.

For example, if the number of occurrences of the item attribution party X and the item attribution party Y occurring in the historical item acquiring task at the same time is 6, the number of the item acquiring tasks of the item attribution party X occurring in the historical item acquiring task is 6, and the number of the item acquiring tasks of the item attribution party Y occurring in the historical item acquiring task is 8, the closeness (X, Y) between the item attribution party X and the item attribution party Y is 6²/(6*8)＝0.75。

In this embodiment, the method for determining the degree of lifting between the article attribution party X and the article attribution party Y may be:

wherein, Lift (X, Y) is the degree of Lift between an article attribution party X and an article attribution party Y, P (X | Y) is the probability of the article attribution party X existing under the condition that the article attribution party Y exists, P (X, Y) is the probability of the article attribution party X and the article attribution party Y appearing in the historical article acquiring task at the same time, P (X) is the probability of the article attribution party X appearing in the historical article acquiring task, P (Y) is the probability of the article attribution party Y appearing in the historical article acquiring task, N (X, Y) is the number of occurrences of the article attribution party X and the article attribution party Y appearing in the historical article acquiring task at the same time, N (X) is the number of article acquiring tasks of the article attribution party X appearing in the historical article acquiring task, N (Y) is the number of article acquiring tasks of the article attribution party Y appearing in the historical article acquiring task, n represents the total item acquisition task number of the acquired historical item acquisition tasks.

As can be seen from the above determination manner, when the degree of lifting is greater than 1, it is indicated that the probability that the article attribution party X exists under the condition that the article attribution party Y exists is greater than the probability that the article attribution party X exists alone, that is, when the total number of article acquiring tasks is fixed, the number of article acquiring tasks that the article attribution party X and the article attribution party Y exist simultaneously is greater than the number of article acquiring tasks that the article attribution party X or the article attribution party Y appears in the article acquiring task, and therefore, when the degree of lifting is greater than 1, the article attribution party X and the article attribution party Y are mutually positively influenced. When the degree of lifting is smaller than 1, it is shown that the probability that the article attribution party X exists under the condition that the article attribution party Y exists is smaller than the probability that the article attribution party X exists alone, that is, when the total article obtaining task number is constant, the article obtaining task number that the article attribution party X and the article attribution party Y exist simultaneously is smaller than the article obtaining task number that the article attribution party X or the article attribution party Y appears in the article obtaining task, and therefore when the degree of lifting is smaller than 1, the article attribution party X and the article attribution party Y are mutually negatively influenced. When the degree of lifting is equal to 1, it is indicated that the probability of the existence of the article attribution party X under the condition that the article attribution party Y exists is equal to the probability of the existence of the article attribution party X alone, that is, when the total article obtaining task number is constant, the article obtaining task number of the article attribution party X and the article attribution party Y existing simultaneously is equal to the article obtaining task number of the article attribution party X or the article attribution party Y appearing in the article obtaining task, and therefore, when the degree of lifting is equal to 1, the article attribution party X and the article attribution party Y are independent from each other.

For example, if the number of occurrences of the item owner X and the item owner Y occurring in the historical item obtaining task at the same time is 6, the number of the item acquirement tasks occurring in the historical item obtaining task by the item owner X is 6, the number of the item acquirement tasks occurring in the historical item acquirement task by the item owner Y is 8, and the total number of the item acquirement tasks of the acquired historical item acquirement tasks is 10, the tightness Lift (X, Y) between the item owner X and the item owner Y is (6 × 10)/(6 × 8) 1.25.

EXAMPLE III

Fig. 3 is a flowchart of an article storage control method according to a third embodiment of the present invention. The present embodiment is further optimized on the basis of the above-described embodiments. As shown in fig. 3, the method includes:

and S310, acquiring a plurality of historical item acquisition tasks.

S320, aiming at each historical article acquisition task, determining an article attribution party set corresponding to the historical article acquisition task according to the article attribution party identification in the historical article acquisition task, and taking the article attribution party set as task characteristic data corresponding to the historical article acquisition task.

In this embodiment, the form of the task feature data is a set form, and the item attribution party included in the historical item acquisition task is represented in a form of an item attribution party set. Optionally, the number of elements in the item attribution party set is equal to the number of item attribution parties included in the historical item acquisition task corresponding to the item attribution party set. Optionally, the identifier of the item attribution party in the historical item obtaining task may be obtained, and an item attribution party set corresponding to the historical item obtaining task is formed according to the identifier of the item attribution party.

For example, when the item attribution parties included in the historical item acquisition task are the item attribution party 1 and the item attribution party 2, the set of item attribution parties corresponding to the historical item acquisition task is formed as { item attribution party 1, item attribution party 2 }.

S330, two item attribution party sets are selected from the item attribution party sets at will, and the intersection between the selected item attribution party sets is determined according to the elements contained in each item attribution party set in the selected item attribution party sets.

In this embodiment, after determining the item affiliate sets corresponding to the historical item acquisition tasks, two item affiliate sets are arbitrarily selected from all item affiliate sets, and the same item affiliate included in the item acquisition task corresponding to the selected item affiliate set is determined according to elements in each item affiliate set.

In an embodiment of the present invention, an intersection between the selected item-affiliating party sets may be calculated, and elements included in the obtained intersection are used as the same item-affiliating parties included in the item acquisition task corresponding to the selected item-affiliating party set.

Illustratively, if the selected item attribution party sets are { item attribution party 1, item attribution party 2} and { item attribution party 1, item attribution party 2, item attribution party 3}, the intersection between the two selected item attribution party sets is { item attribution party 1, item attribution party 2}, which indicates that the same item attribution parties in the item acquisition tasks corresponding to the two selected item attribution party sets are item attribution party 1 and item attribution party 2.

S340, aiming at each intersection, determining the number of the article attribution parties contained in the intersection according to the element number in the intersection, if the number of the article attribution parties is larger than the preset number of the article attribution parties, establishing at least one attribution party combination according to the article attribution party identification contained in the intersection, and establishing the corresponding relation between the intersection and the at least one attribution party combination.

In this embodiment, after obtaining an intersection between the item affiliate sets between any two item acquisition tasks in all historical item acquisition tasks, for each intersection, an affiliate combination corresponding to the intersection is determined.

Optionally, the number of the same item attribution parties between the item acquisition tasks may be any number, and in order to screen out the attribution party combination included in the transaction, the transaction set may be screened according to the number of the item attribution parties included in the transaction set. In one embodiment of the present invention, if the number of the article attributions included in the intersection is greater than 2, it is determined that the article attributions included in the intersection can form at least one attribution combination, and all the article attributions included in the intersection are arbitrarily combined in pairs to form at least one attribution combination. It can be understood that if the number of attributions of the items included in the intersection is n, the number of attribution combinations corresponding to the intersection is C_n ²＝n(n-1)/2。

For example, if the article attribution parties existing in the intersection are the article attribution party 1, the article attribution party 2 and the article attribution party 3, 3 combinations of attribution parties can be formed, the formed combinations of attribution parties are (article attribution party 1, article attribution party 2), (article attribution party 2, article attribution party 3) and (article attribution party 1, article attribution party 3), and the combination of attribution parties corresponding to the intersection is obtained as (article attribution party 1, article attribution party 2), (article attribution party 2, article attribution party 3) and (article attribution party 1, article attribution party 3).

S350, aiming at each attribution party combination, determining the number of intersections corresponding to the attribution party combination, and taking the number of the intersections as the occurrence times of the attribution parties of the items in the attribution party combination appearing in the historical item acquisition task at the same time.

In this embodiment, after determining the corresponding relationship between each intersection and the corresponding party combination, the number of occurrences of the corresponding party combination in all the intersections can be determined for each corresponding party combination, and the number of occurrences of the corresponding party combination in all the intersections is used as the number of occurrences that each article belonging party in the corresponding party combination appears in different historical article obtaining tasks at the same time. Optionally, the number of intersections corresponding to the home party combination may be used as the number of occurrences of the home party combination in all intersections. For example, if the number of intersections corresponding to the affiliate group is 6, it is determined that the number of times that each item affiliate in the affiliate group is simultaneously present in different historical item acquisition tasks is 6.

S360, determining the association degree between the attribution parties of the articles in the attribution party combination according to the occurrence times and the number of the attribution parties of the articles in the historical article acquisition task, wherein the number of the attribution parties comprises the number of the attribution parties of the articles in the attribution party combination.

Optionally, the manner of determining the association degree between the attribution parties of each item in the attribution party combination according to the number of the item obtaining tasks and the number of the attribution parties of each item in the historical item obtaining tasks included in the attribution party combination is the same as the manner of determining the association degree between the attribution parties of each item in the attribution party combination in the above embodiment. For more details, reference may be made to the above embodiments, which are not described herein again.

According to the technical scheme, the task characteristic data is embodied into the item attribution party set on the basis of the embodiment, the scheme is embodied on the basis of the item attribution party set, the item attribution party set corresponding to the historical item acquisition task is generated, the operation is performed on the basis of the item attribution party set, the occurrence times of the same item acquisition task of all the item attribution parties in the attribution party set are obtained, the association degree between all the item attribution parties in the attribution party set is determined according to the occurrence times and the number of all the item attribution parties in the attribution party set in the historical item acquisition task, and the determination process of the association degree between the item attribution parties is simplified.

Example four

Fig. 4a is a flowchart of an article storage control method according to a fourth embodiment of the present invention. The present embodiment is further optimized on the basis of the above-described embodiments. As shown in fig. 4a, the method comprises:

and S410, acquiring a plurality of historical item acquisition tasks.

And S420, generating task characteristic data corresponding to the historical item acquisition tasks according to item attribution party information contained in each historical item acquisition task, wherein the task characteristic data is used for representing item attribution parties involved in the historical item acquisition tasks.

And S430, determining the association degree between the attribution parties of the articles contained in the historical article acquisition task according to the characteristic data of each task.

And S440, determining at least one item home party combination deployed in the same bin according to the association degree between the item home parties.

In one embodiment of the present invention, a relevance threshold may be set, and when the relevance between the attributions of the articles in the combination of the attributions of the articles is greater than the preset relevance threshold, the combination of the attributions of the articles is taken as the combination of the attributions deployed in the same bin. Taking the example that the association degree preferably comprises the compactness and the promotion degree, when the compactness between the article attribution parties in the article attribution party combination is greater than a preset compactness threshold value and the promotion degree is greater than a preset promotion degree threshold value, the article attribution party combination is taken as the attribution party combination deployed in the same bin.

S450, aiming at each article attribution party combination deployed in the same bin, determining a storage bin identifier corresponding to the article attribution party combination, generating a storage scheduling instruction according to the attribution party combination and the storage bin identifier, and sending the storage scheduling instruction to a storage scheduling system.

In this embodiment, for each group of item affiliates deployed in the same bin, at least one storage bin may be arbitrarily selected from the original item storage bins of each item affiliate in the group of item affiliates as the storage bin corresponding to the group of item affiliates, or at least one storage bin may be selected as the storage bin corresponding to the group of item affiliates according to the task obtaining address of the historical item obtaining task corresponding to each item affiliate in the group of item affiliates and the address of each storage bin.

In an embodiment of the present invention, historical item acquiring tasks that all item affiliates in an item affiliate group appear simultaneously may be acquired, historical task acquiring addresses of the item affiliate group are determined according to task acquiring addresses in the acquired historical item acquiring tasks, areas to which all historical task acquiring addresses belong are determined according to preset address ranges corresponding to the areas, the number of the historical task acquiring addresses in each area is determined by counting the areas to which all historical task acquiring addresses belong, and a storage bin closest to the area containing the largest number of the historical task acquiring addresses is used as a storage bin corresponding to the item affiliate group. The address range corresponding to each area can be set according to actual conditions.

For example, taking an e-commerce platform as an example, suppose that a merchant group 1 includes a merchant 1 and a merchant 2, historical item acquisition tasks that occur at the same time in the merchant 1 and the merchant 2 include task 1, task 2, task 3, task 4 and task 5, correspondingly, historical task acquisition addresses include address 1, address 2, address 3, address 4 and address 5, and it is determined that address 1, address 3 and address 4 belong to area 1, address 2 belongs to area 2, and address 3 belongs to area 3 according to preset address ranges corresponding to the areas, the number of historical task acquisition addresses included in area 1 is the largest, and a storage bin closest to area 1 is taken as a storage bin corresponding to the merchant group 1.

In this embodiment, after determining the storage bin corresponding to each group of the goods-attributing party deployed in the same bin, generating a corresponding storage scheduling instruction for each goods-attributing party needing to be scheduled in the group of the goods-attributing parties, and sending the storage scheduling instruction to the storage scheduling system, so that the storage scheduling system stores the goods of the group of the goods-attributing parties into the storage bin corresponding to the storage bin identifier according to the storage scheduling instruction.

Optionally, it may be determined whether each item affiliate in the item affiliate group needs to perform storage scheduling according to the original storage bin of each item affiliate group in the item affiliate group and the storage bin corresponding to the determined item affiliate group. Illustratively, if the combination of the item affiliators includes an item affiliate 1 and an item affiliate 2, the corresponding storage bin is the storage bin 1, and the item of the item affiliate 1 is already stored in the storage bin 1 before being scheduled, and the item of the item affiliate 2 is stored in the storage bin 3 before being scheduled but not stored in the storage bin 1, then for the item affiliate 1, it is not necessary to generate a corresponding storage scheduling instruction, and for the item affiliate 2, it is necessary to generate a storage scheduling instruction that is scheduled from the storage bin 3 to the storage bin 1.

In an embodiment of the present invention, after receiving the storage scheduling instruction, the storage scheduling system parses the storage scheduling instruction to obtain an article affiliation party, an original storage bin identifier, and a target storage bin identifier included in the storage scheduling instruction, generates an article pickup instruction and an article storage instruction according to the article affiliation party, the original storage bin identifier, and the target storage bin identifier, sends the article pickup instruction to an original storage bin corresponding to the original storage bin identifier, and sends the article storage instruction to a target storage bin corresponding to the target storage bin identifier. After receiving the article dispatching instruction, the original storage bin carries the article to an original storage bin goods collection center through an original storage bin internal dispatching system, so that the logistics system transports the article from the original storage bin goods collection center to a target storage bin goods collection center, and after receiving the article storage instruction, the target storage bin carries the article from the target storage bin goods collection center to a corresponding goods position through a target storage bin internal dispatching system.

Fig. 4b is a schematic structural diagram of a storage bin in an article storage control method according to an embodiment of the present invention. As shown in fig. 4b, the storage bin 40 includes a cargo space 41, a cargo collection center 42, a robot 43, and a control device 44. The control device 44 is used for receiving an article calling instruction or an article storing instruction.

In the embodiment, after receiving the article dispatch command, the control device 44 determines the location of the article to be transported according to the article dispatch command, forms a transport command for transporting the article to be transported from the location of the article to be transported to the cargo collection center, sends the transport command to the robot 43, and the robot 43 transports the article to be transported from the location 41 to the cargo collection center 42 according to the received transport command. When the control device 44 receives the article dispatch storage, the target carrying position of the article to be carried is determined according to the article dispatch instruction, a carrying instruction for carrying the article to be carried from the article collection center of the article to be carried to the target carrying position is formed, the carrying instruction is sent to the robot 43, and the robot 43 carries the article to be carried from the article collection center 42 to the target carrying position 41 according to the received carrying instruction. And the same-warehouse deployment of each article attribution party in the article attribution parties is completed through the cooperation of the storage scheduling system, the logistics transportation system and the control system of each storage warehouse.

According to the technical scheme of the embodiment of the invention, the operation of forming the storage scheduling instruction and scheduling the articles according to the storage scheduling instruction is added on the basis of the embodiment, the storage bin identification corresponding to the article attribution party combination is determined by aiming at the article attribution party combination deployed in each same bin, the storage scheduling instruction is generated according to the attribution party combination and the storage bin identification, the storage scheduling instruction is sent to the storage scheduling system, and the same bin deployment of each article attribution party in the article attribution party is completed through the cooperation of the storage scheduling system, the logistics transportation system and the control systems of each storage bin.

EXAMPLE five

Fig. 5 is a flowchart of an article storage control method according to a fifth embodiment of the present invention. The present embodiment provides a preferred embodiment based on the above-described embodiments. The embodiment takes an e-commerce platform as an example, and embodies an article storage control method. In this embodiment, the item acquisition task is displayed in the form of an order, and the item attribution is displayed in the form of a merchant. As shown in fig. 5, the method includes:

s510, obtaining a plurality of historical orders and generating order feature codes for each order.

In this embodiment, it is assumed that 10 orders are generated in 12 months for a certain e-commerce enterprise, and 3 "merchants" are involved. All orders of the electronic commerce enterprise for 12 months are obtained, and an order feature code is generated for each order. Each digit of the order feature code represents a merchant, if the merchant appears in the order, the order feature code is marked as 1, otherwise, the order feature code is marked as 0. Illustratively, the correspondence between each order and the order feature code and the merchant is shown in table 1.

TABLE 1

Order identification	Merchant 1	Merchant 2	Merchant 3
				Order 001	0	1	1
Order 002	1	1	0
				Order 003	1	0	1
Order 004	1	1	0
				Order 005	0	1	1
Order 006	1	1	0
				Order 007	0	1	1
Order 008	1	0	1
				Order 009	0	1	0
Order 010	1	1	1

As shown in table 1, the merchants included in order 001 are merchant 2 and merchant 3, the corresponding order signatures thereof are 011, the merchant included in order 002 is merchant 1 and merchant 2, the corresponding order signature thereof is 110, the merchant included in order 003 is merchant 1 and merchant 3, the corresponding order signatures thereof are 101, the merchant included in order 004 is merchant 1 and merchant 2, the corresponding order signature thereof is 110, the merchant included in order 005 is merchant 2 and merchant 3, the corresponding order signatures thereof are 011, the merchant included in order 006 is merchant 1 and merchant 2, the corresponding order signature thereof is 110, the merchant included in order 007 is merchant 2 and merchant 3, the corresponding order signatures thereof are 011, the merchant included in order 008 is merchant 1 and merchant 3, the corresponding order signature thereof is 101, the merchant included in order 009 is merchant 2, the corresponding order feature code is 010, the merchants included in the order 010 are merchant 1, merchant 2 and merchant 3, and the corresponding order feature code is 111.

S520, calculating the same merchant combination among any 2 orders.

In this embodiment, the order feature codes of any 2 orders are subjected to logical and operation according to positions, so as to obtain the same merchant combination contained in the 2 orders.

Illustratively, the order feature code of the order 001 is 011, the order feature code of the order 002 is 010, and the same merchant combination of the order 001 and the order 002 is 010 after the logical and operation according to the positions is performed on the order 001 and the order feature code of the order 002. The order feature code of the order 001 is 011, the order feature code of the order 007 is 011, and the same merchant combination of the order 001 and the order 007 is 011 after the logical and operation according to the positions is carried out on the order feature codes of the order 001 and the order 007.

And S530, counting the same merchant combination with the occurrence number of 1 being more than or equal to 2.

Optionally, a set formed by operation results of the same merchant combination of any two orders in the whole orders is used as the result set. Aiming at each same merchant combination, calculating the times of the occurrence of the number 1 in the same merchant combination, and then counting the times of the occurrence of each same merchant combination with the times of the occurrence of 1 being more than or equal to 2 in the result set; and obtaining the occurrence times of each merchant combination in the result set.

Still taking the obtained historical orders as an example, through the statistics, the occurrence frequency of the same merchant combination 011 in the result set is 6 times; the number of occurrences of the same merchant group 101 in the result set is 3; the same merchant group 110 appears 6 times in the result set.

And S540, calculating the closeness and the promotion degree between two merchants in the merchant combination.

And calculating the closeness and the promotion degree between the two merchants according to the occurrence times of the same merchant combination in the result set and the occurrence times of the merchants in the historical orders in the same merchant combination.

Wherein the closeness between two merchants

Degree of improvement between two merchants

Wherein N (X, Y) is the number of occurrences of merchant X and merchant Y in the historical order, N (X) is the number of orders merchant X in the historical order, N (Y) is the number of orders merchant Y in the historical order, and N is the number of orders in the historical order.

Still taking the above obtained historical orders as an example, the following can be calculated according to the above formula:

and S550, screening the result.

In this embodiment, a compactness threshold may be set, and the combination of merchants whose compactness is higher than the compactness threshold and whose lifting degree is greater than 1 is selected, and the selected combination of merchants has high compactness and positive influence on each other. Optionally, the compactness threshold may be set to be 0.5, the same merchant combination (merchant 1, merchant 2) and the same merchant combination (merchant 1, merchant 3) are screened out, and the promotion degrees of the same merchant combination (merchant 1, merchant 2) and the same merchant combination (merchant 1, merchant 3) are both greater than 1, then it is determined that the same merchant combination (merchant 1, merchant 2) and the same merchant combination (merchant 1, merchant 3) are merchant combinations having high compactness and positive influence with each other.

And S560, applying the result.

Through the scheme, after the combination of merchants with high compactness and positive influence is screened out, the commodities of the merchants can be considered to be stored in a centralized manner.

Example 6

Fig. 6 is a schematic structural diagram of an article storage control device according to a fifth embodiment of the present invention. The article storage control device may be implemented in software and/or hardware, for example, the article storage control device may be configured in a computer device. As shown in fig. 6, the apparatus includes a historical item acquisition task acquisition module 610, a feature data generation module 620, and an associated data calculation module 630, where:

a historical task obtaining module 610 for obtaining a plurality of historical item obtaining tasks,

a feature data generating module 620, configured to generate task feature data corresponding to the historical item obtaining task according to item attribution party information included in each historical item obtaining task, where the task feature data is used to represent an item attribution party involved in the historical item obtaining task;

the association data determining module 630 is configured to determine, according to each of the task feature data, an association degree between each item attribution party included in the historical item obtaining task, where the association degree is used as a deployment basis for the same-bin item attribution party.

According to the embodiment of the invention, a plurality of historical item acquisition tasks are acquired by a historical task acquisition module 610; the feature data generation module 620 generates task feature data corresponding to the historical item acquisition task according to item attribution party information included in each historical item acquisition task; the association data determining module 630 determines the association degree between the article attribution parties included in the historical article obtaining task according to the task characteristic data, wherein the association degree is used as a deployment basis for the article attribution parties in the same bin, and the article attribution parties in the same bin are recommended based on the association degree between the article attribution parties, so that the order splitting rate can be reduced, the logistics cost is reduced, the overall logistics timeliness of the article obtaining task is improved, and the user experience is improved.

On the basis of the above scheme, the feature data generating module 620 is specifically configured to:

and generating a task feature vector corresponding to each historical article acquisition task, wherein each element in the task feature vector corresponds to an article attribution party, and the element value of each element is used for representing the existence condition of the article attribution party corresponding to the element in the historical article acquisition task.

On the basis of the above scheme, the association data determining module 630 includes:

a result vector determining unit, configured to arbitrarily select two task feature vectors from each of the task feature vectors, and perform and operation on the element values at the positions corresponding to the selected task feature vectors to obtain an operation result vector between the selected task feature vectors;

a corresponding relation determining unit, configured to determine, for each operation result vector, a quantity of elements representing element values existing in an article attribution party in the operation result vector according to element values of the elements in the operation result vector, if the quantity of the elements is greater than a preset quantity of elements, determine an article attribution party identifier included in the operation result vector according to the element values, establish at least one attribution party combination according to the article attribution party identifier, and establish a corresponding relation between the operation result vector and the at least one attribution party combination;

an article acquisition task number determining unit, configured to determine, for each affiliate combination, the number of operation result vectors corresponding to the affiliate combination, where the number of operation result vectors is used as the number of occurrences that each article affiliate in the affiliate combination occurs in the historical article acquisition task at the same time;

and the association degree determining unit is used for determining the association degree between the attribution parties of each article in the attribution party combination according to the occurrence times and the number of the attribution parties of each article in the attribution party combination contained in the historical article obtaining task.

and aiming at each historical article acquisition task, determining an article attribution party set corresponding to the historical article acquisition task according to the article attribution party identifier in the historical article acquisition task, and taking the article attribution party set as task characteristic data corresponding to the historical article acquisition task.

the intersection determining unit is used for randomly selecting two article attribution party sets from the article attribution party sets, and determining the intersection between the selected article attribution party sets according to elements contained in each article attribution party set in the selected article attribution party set;

a corresponding relation determining unit, configured to determine, for each intersection, a quantity of article affiliates included in the intersection according to the quantity of elements in the intersection, and if the quantity of the article affiliates is greater than a preset quantity of the article affiliates, establish at least one affiliate combination according to an article affiliate identifier included in the intersection, and establish a corresponding relation between the intersection and the at least one affiliate combination;

the task quantity determining unit is used for determining the quantity of intersection sets corresponding to the attribution party combination aiming at each attribution party combination, and taking the quantity of intersection sets as the occurrence times of the attribution parties of all the articles in the attribution party combination appearing in the historical article obtaining task at the same time;

On the basis of the above scheme, the association degree determining unit is specifically configured to:

On the basis of the scheme, the correlation degree comprises compactness and lifting degree;

On the basis of the scheme, the device further comprises a same-bin recommending module, which is used for:

and if the promotion degree of the candidate same-bin candidate combination is greater than a preset promotion degree threshold value, taking the same-bin candidate combination as a recommended same-bin attribution party combination.

On the basis of the above scheme, the apparatus further includes a scheduling instruction generating module, configured to:

determining at least one commodity attribution party combination deployed in the same bin according to the relevance between the commodity attribution parties;

and aiming at each article attribution party combination deployed in the same bin, determining a storage bin identifier corresponding to the article attribution party combination, generating a storage scheduling instruction according to the attribution party combination and the storage bin identifier, and sending the storage scheduling instruction to a storage scheduling system, so that the storage scheduling system stores the articles of the article attribution party combination into the storage bin corresponding to the storage bin identifier according to the storage scheduling instruction.

The article storage control device provided by the embodiment of the invention can execute the article storage control method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.

EXAMPLE seven

Fig. 7 is a schematic structural diagram of a computer device according to a seventh embodiment of the present invention. FIG. 7 illustrates a block diagram of an exemplary computer device 712 suitable for use to implement embodiments of the present invention. The computer device 712 shown in fig. 7 is only an example and should not bring any limitations to the functionality or scope of use of the embodiments of the present invention.

As shown in fig. 7, computer device 712 is embodied in the form of a general purpose computing device. Components of computer device 712 may include, but are not limited to: one or more processors 716, a system memory 728, and a bus 718 that couples the various system components (including the system memory 728 and the processors 716).

Bus 718 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and processor 716 or a local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Computer device 712 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 712 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 728 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)730 and/or cache memory 732. Computer device 712 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage device 734 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, and commonly referred to as a "hard drive"). Although not shown in FIG. 7, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 718 by one or more data media interfaces. Memory 728 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

Program/utility 740 having a set (at least one) of program modules 742 may be stored, for instance, in memory 728, such program modules 742 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may include an implementation of a network environment. Program modules 742 generally perform the functions and/or methodologies of embodiments of the invention as described herein.

Computer device 712 may also communicate with one or more external devices 714 (e.g., keyboard, pointing device, display 724, etc.), with one or more devices that enable a user to interact with computer device 712, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 712 to communicate with one or more other computing devices. Such communication may occur through input/output (I/O) interfaces 722. Also, computer device 712 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) through network adapter 720. As shown, network adapter 720 communicates with the other modules of computer device 712 via bus 718. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with computer device 712, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processor 716 executes various functional applications and data processing by executing programs stored in the system memory 728, for example, to implement the article storage control method provided by the embodiment of the present invention, the method includes:

acquiring a plurality of historical item acquisition tasks;

Of course, those skilled in the art will understand that the processor may also implement the technical solution of the article storage control method provided in any embodiment of the present invention.

Example eight

An eighth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements an article storage control method according to an embodiment of the present invention, where the method includes:

acquiring a plurality of historical item acquisition tasks;

and determining the association degree between the article attribution parties contained in the historical article acquisition task according to the article acquisition task characteristic data, wherein the association degree is used as a deployment basis of the article attribution parties in the same bin.

Of course, the computer program stored on the computer-readable storage medium provided by the embodiment of the present invention is not limited to the method operations described above, and may also perform related operations in the article storage control method provided by any embodiment of the present invention.

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: 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 the context of this document, 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.

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 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, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like 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).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An article storage control method, characterized by comprising:

acquiring a plurality of historical item acquisition tasks;

2. The method according to claim 1, wherein the generating item acquisition task feature data corresponding to the historical item acquisition task according to item attribution information included in each historical item acquisition task includes:

3. The method according to claim 2, wherein the determining, according to the task feature data, the degree of association between the item attributions included in the historical item acquisition task comprises:

randomly selecting two task feature vectors from the task feature vectors, and performing AND operation on element values at corresponding positions of the selected task feature vectors to obtain operation result vectors among the selected task feature vectors;

for each operation result vector, determining the number of elements representing element values existing in an article attribution party in the operation result vector according to the element values of the elements in the operation result vector, if the number of the elements is greater than the preset number of elements, determining an article attribution party identifier contained in the operation result vector according to the element values, establishing at least one attribution party combination according to the article attribution party identifier, and establishing a corresponding relation between the operation result vector and the at least one attribution party combination;

determining the number of operation result vectors corresponding to the attribution party combination aiming at each attribution party combination, and taking the number of the operation result vectors as the occurrence times of the attribution parties of all the articles in the attribution party combination appearing in the historical article obtaining task at the same time;

and determining the association degree between the attribution parties of the items in the attribution party combination according to the occurrence times and the number of the attribution parties of the items in the historical item acquisition task.

4. The method according to claim 1, wherein the generating task feature data corresponding to the historical item acquisition task according to item attribution information included in the historical item acquisition task includes:

5. The method according to claim 4, wherein the determining, according to the task feature data, the degree of association between the item attributions included in the historical item acquisition task comprises:

randomly selecting two article attribution party sets from each article attribution party set, and determining an intersection between the selected article attribution party sets according to elements contained in each article attribution party set in the selected article attribution party set;

for each intersection, determining the number of article attribution parties contained in the intersection according to the number of elements in the intersection, if the number of the article attribution parties is greater than the preset number of the article attribution parties, establishing at least one attribution party combination according to the article attribution party identification contained in the intersection, and establishing a corresponding relation between the intersection and the at least one attribution party combination;

determining the number of intersections corresponding to the attribution party combination aiming at each attribution party combination, and taking the number of the intersections as the occurrence times of the historical article acquisition task when the attribution party of each article in the attribution party combination simultaneously appears;

6. The method according to claim 3 or 5, wherein the determining the association degree between the attributions of the items in the attribution group according to the occurrence number and the number of the attributions of the items in the attribution group included in the historical item acquisition task comprises:

7. The method according to any of claims 1-5, wherein the correlation comprises a degree of closeness and a degree of lift;

8. The method of claim 6, further comprising:

9. The method of claim 1, further comprising:

10. An article storage control method apparatus, comprising:

11. A computer device, the device comprising:

one or more processors;

storage means for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the item storage control method of any of claims 1-9.

12. A computer-readable storage medium on which a computer program is stored, the program, when being executed by a processor, implementing an article storage control method according to any one of claims 1 to 9.