CN113139767A

CN113139767A - Logistics object allocation method and device, electronic equipment and computer-readable storage medium

Info

Publication number: CN113139767A
Application number: CN202010067285.6A
Authority: CN
Inventors: 庄文辉; 谭又豪
Original assignee: Cainiao Smart Logistics Holding Ltd
Current assignee: Cainiao Smart Logistics Holding Ltd
Priority date: 2020-01-20
Filing date: 2020-01-20
Publication date: 2021-07-20

Abstract

The application discloses a logistics object allocation method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring historical data aiming at a plurality of users and a plurality of logistics objects, wherein the historical data at least comprises first dynamic data for identifying purchasing behaviors of the users aiming at the logistics objects; acquiring prediction data for predicting the purchasing behavior of at least one user for at least one logistics object according to the historical data; and performing allocation processing on the logistics objects according to the prediction data. The embodiment of the application predicts whether the target logistics object can be purchased by the target user or not based on the historical purchasing behavior of the user, and then allocates the logistics object in advance according to the prediction result, so that the waiting time after the user purchases can be reduced, the user experience is improved, meanwhile, the warehouse allocation planning is facilitated, the warehouse pressure can be relieved under the condition that the logistics transportation amount is large, and the transportation efficiency is improved.

Description

Logistics object allocation method and device, electronic equipment and computer-readable storage medium

Technical Field

The present application relates to the field of logistics technologies, and in particular, to a method and an apparatus for allocating logistics objects, an electronic device, and a computer-readable storage medium.

Background

In the current logistics industry, after a user places an order, the logistics objects are allocated and transported according to the receiving address of the user. Generally, a physical distribution object passes through a plurality of physical distribution sites (warehouses, etc.), and is finally delivered to a shipping address by a deliverer at an end site (a physical distribution site in an area where the shipping address is located).

However, the transmission of the logistics objects according to the actual ordering behavior of the user in the prior art is limited by various uncertain factors such as transportation means, road conditions, emergencies, and the like, which often results in that the user needs to wait for a long time to receive the ordered logistics objects after ordering. Particularly, when logistics transportation volume sharply increases on holidays or commodity sales promotion and the like, the situation of transportation overtime becomes more serious, and the shopping experience of users is greatly reduced.

Disclosure of Invention

The embodiment of the application provides a logistics object allocation method and device, electronic equipment and a computer readable storage medium, so as to solve the defect that in the prior art, after a user places an order, the logistics object is transported for too long time.

In order to achieve the above object, an embodiment of the present application provides a method for allocating logistics objects, including:

acquiring historical data aiming at a plurality of users and a plurality of logistics objects, wherein the historical data at least comprises first dynamic data for identifying purchasing behaviors of the users aiming at the logistics objects;

acquiring prediction data for predicting the purchasing behavior of at least one user for at least one logistics object according to the historical data;

and performing allocation processing on the logistics objects according to the prediction data.

The embodiment of the present application further provides a device is allocated to logistics object, include:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring historical data aiming at a plurality of users and a plurality of logistics objects, and the historical data at least comprises first dynamic data for identifying purchasing behaviors of the users aiming at the logistics objects;

the second acquisition module is used for acquiring prediction data for predicting the purchasing behavior of at least one user aiming at least one logistics object according to the historical data;

and the distribution processing module is used for carrying out distribution processing on the logistics objects according to the prediction data.

An embodiment of the present application further provides an electronic device, including:

a memory for storing a program;

a processor for executing the program stored in the memory for:

Embodiments of the present application further provide a computer-readable storage medium, on which instructions are stored, where the instructions include:

The logistics object allocation method and device, the electronic device and the computer readable storage medium provided by the embodiment of the application predict whether the target logistics object can be purchased by the target user or not based on the historical purchasing behavior of the user, and then allocate the logistics object in advance according to the prediction result, so that the waiting time after the user purchases can be reduced, the user experience is improved, meanwhile, the warehouse allocation planning is facilitated, under the condition that the logistics transportation volume is large, the warehousing pressure can be relieved, and the transportation efficiency is improved.

The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 is a scene schematic diagram of a logistics object allocation method provided in an embodiment of the present application;

fig. 2 is a flowchart of an embodiment of a logistics object allocation method provided in the present application;

fig. 3 is a flowchart of another embodiment of a logistics object allocation method provided by the present application;

fig. 4a is a first schematic application diagram of an embodiment of a logistics object allocation method provided by the present application;

fig. 4b is a schematic application diagram of a second embodiment of the logistics object allocation method provided by the present application;

fig. 4c is a schematic application diagram three of an embodiment of the logistics object allocation method provided by the present application;

fig. 5 is a schematic structural diagram of an embodiment of a logistics object allocation device provided in the present application;

fig. 6 is a schematic structural diagram of another embodiment of a logistics object allocation device provided by the present application;

fig. 7 is a schematic structural diagram of an embodiment of an electronic device provided in the present application.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Example one

The logistics object allocation method provided by the embodiment of the application can be applied to any business system with data processing capacity. Fig. 1 is a scene schematic diagram of a logistics object allocation method provided in an embodiment of the present application, and the scene shown in fig. 1 is only one example of a scene to which the technical solution of the present application can be applied. As shown in fig. 1, in a scenario of online shopping, a user places an order (orders a logistics object) through a shopping platform, a merchant obtains order information of the user from a server, then delivers the corresponding logistics object according to the order information of the user, and the logistics object is transmitted to an end node through a logistics transmission system and then delivered to the user by a delivery person. In the logistics transport system, the logistics objects are delivered from the warehouse (e.g., warehouse 1, warehouse 2, …, warehouse m shown in fig. 1), distributed and transported through one or more intermediate nodes (e.g., intermediate node 1, intermediate node 2, …, intermediate node n shown in fig. 1), and finally delivered to the end node closest to the user (e.g., end node 1, end node 2, …, end node p shown in fig. 1). However, as the logistics transportation usually needs to go from the warehouse where the logistics objects are stored, the logistics transportation goes through a plurality of intermediate nodes to reach the logistics distribution site (end node) in the area where the user is located and complete the distribution to the user. Therefore, in the prior art, the transmission of the logistics objects according to the actual ordering behavior of the user often results in that the user needs to wait for a long time to receive the ordered logistics objects after finishing the ordering of the logistics objects, thereby reducing the shopping experience of the user.

Therefore, the embodiment of the present application provides a logistics object allocation scheme, where in a range permitted by a user, historical ordering data and user information of the user are obtained, and whether a target logistics object is purchased by the target user is determined by analyzing dynamic behaviors (including, but not limited to, a purchasing behavior, a searching behavior, a browsing behavior, a collecting behavior, a shopping cart adding behavior, and the like) of a plurality of users for a plurality of logistics objects, static information (including, but not limited to, professional information, gender information, age information, region information, and the like) of the users, and static information (including, but not limited to, category information, producer information, or seller information, and the like) of the logistics objects, and allocating and transmitting the logistics object in advance according to the determination result. If the target user is predicted to purchase the target logistics object, the target object may be shipped from the warehouse in advance before the target user places an order, for example, the target logistics object may be transported to an end node (which may also be a certain logistics node in the logistics transmission link) for temporary storage. After the target user places an order to purchase the target logistics object, the target logistics object can be quickly transmitted from the temporarily stored logistics node, so that the waiting time of the user after shopping can be reduced, and particularly, the target logistics object can be directly sent to the target user under the condition that the target logistics object is temporarily stored in the tail end node, and therefore, the user experience can be greatly improved; meanwhile, the storage and transportation conditions of each logistics node on the logistics object transmission path can be determined based on the ordering data, so that the target logistics object is allocated to the logistics node with low warehousing pressure, the whole transmission path is optimized, warehousing planning is facilitated, warehousing pressure can be relieved under the condition that logistics transportation volume is large, and transportation efficiency is improved.

The above embodiments are illustrations of technical principles and exemplary application frameworks of the embodiments of the present application, and specific technical solutions of the embodiments of the present application are further described in detail below through a plurality of embodiments.

Example two

Fig. 2 is a flowchart of an embodiment of the logistics object allocation method provided in the present application, where an execution subject of the method may be various terminal or server devices with data processing capability, or may be a device or chip integrated on these devices. As shown in fig. 2, the logistics object allocation method includes the following steps:

s201, acquiring historical data aiming at a plurality of users and a plurality of logistics objects.

In the embodiment of the application, the historical data aiming at the user and the logistics object at least comprises first dynamic data for identifying the purchasing behavior of the user aiming at the logistics object. The first dynamic data identifies one-to-one, one-to-many, or many-to-one purchasing relationships between the plurality of users and the plurality of logistics objects. By analyzing the big data, the purchasing behavior to be performed can be predicted according to the historical data of the completed purchasing behavior.

S202, obtaining prediction data for predicting the purchasing behavior of at least one user aiming at least one logistics object according to the historical data.

In the embodiment of the application, the similarity between users or the similarity between logistics objects can be determined firstly based on historical data, and then the purchasing behavior of the users for the logistics objects can be predicted based on the similarity. For example, if it is determined that the user a and the user B are similar in interest or shopping habit according to the history data, the logistics objects purchased by the user a include the logistics objects that the user B has not purchased yet, and the probability of purchasing the logistics objects is higher; alternatively, if it is judged from the history data that the physical distribution object C and the physical distribution object D are similar in attributes or purchasing population, the possibility that the physical distribution object D will be purchased is high if the physical distribution object C has already been purchased.

And S203, performing allocation processing on the logistics objects according to the prediction data.

In the embodiment of the application, after the prediction data is obtained, the logistics objects are allocated according to the content displayed by the prediction data. For example, the predicted data shows that the probability that the user a will purchase the logistics object C is high, the terminal node of the logistics object transmission link can be obtained according to the common address information of the user a, the logistics object C is delivered to the terminal node in advance, and after the user a really places an order, the logistics object C is directly sent to the user from the terminal node, so that the waiting time after the user purchases the logistics object C is greatly reduced.

The logistics object allocation method provided by the embodiment of the application predicts whether the target logistics object can be purchased by the target user or not based on the historical purchasing behavior of the user, and then allocates the logistics object in advance according to the prediction result, so that the waiting time after the user purchases can be reduced, the user experience is improved, meanwhile, the warehouse allocation planning is facilitated, the warehousing pressure can be relieved under the condition that the logistics transportation volume is large, and the transportation efficiency is improved.

EXAMPLE III

Fig. 3 is a flowchart of another embodiment of the logistics object allocation method provided by the present application. As shown in fig. 3, on the basis of the embodiment shown in fig. 2, the logistics object allocation method provided in this embodiment may further include the following steps:

s301, historical data aiming at a plurality of users and a plurality of logistics objects are obtained.

S302, according to the historical data, similarity among a plurality of users is calculated.

In the embodiment of the present application, the historical data for the user and the logistics object may further include, in addition to the first dynamic data, second dynamic data that identifies at least one of a search behavior, a browse behavior, a collection behavior, and a shopping cart adding behavior of the user for the logistics object. Therefore, the similarity among the plurality of users can be calculated according to the second dynamic data, namely, the user similarity is determined according to the searching behavior, the browsing behavior, the collecting behavior or the shopping cart adding behavior and the like of the plurality of users.

On the other hand, in the embodiment of the present application, the history data for the user and the logistics object may include, in addition to the first dynamic data, first attribute data that identifies at least one of professional information, sex information, age information, and region information of the user. Therefore, the similarity between the plurality of users can be calculated according to the first attribute data, namely, the user similarity is determined according to the occupation, gender, age, region and other information of the plurality of users.

In another aspect, in an embodiment of the present application, the historical data for the user and the logistics object may include the first dynamic data, the second dynamic data, and the first attribute data. Therefore, the similarity among a plurality of users can be calculated by combining the searching behavior, the browsing behavior, the collecting behavior or the shopping cart adding behavior of the users and the information of the occupation, the gender, the age or the region of the users.

S303, at least one group of user groups with the similarity higher than a first preset threshold value is obtained.

In the embodiment of the present application, each group of user groups includes at least two users with higher similarity, that is, a first user and a second user.

S304, calculating a probability value of a first logistics object for which the second user expects to purchase the first dynamic data according to the first dynamic data related to the first user.

Fig. 4a is a schematic application diagram of a first logistics object allocation method according to an embodiment of the present application. In the embodiment of the present application, the above steps S302 to S304 describe an application example in which the similarity is calculated from the user dimension and the purchasing behavior prediction is performed. As shown in fig. 4a, it is assumed that at least the user 1 has purchased the logistics object 1, the user 2 has purchased the logistics object 3, and the user 3 has purchased the logistics object 2 are identified in the first dynamic data in the history data. And, a group of users is determined in the above manner, i.e. the users 1 and 2 with higher similarity (may be similar in interest or shopping habits), the logistics object 1 purchased by the user 1 can be seen from the first dynamic data of the user 1, and therefore, it can be inferred that the probability that the user 2 may purchase the logistics object 1 is higher, see the arrow direction in fig. 4 a.

Fig. 4b is a schematic application diagram of a second embodiment of the logistics object allocation method provided by the present application. In this embodiment of the application, the scheme of calculating the similarity from the user dimension and predicting the purchasing behavior in steps S302 to S304 may instead be to calculate the similarity between a plurality of logistics objects according to historical data; acquiring at least one group of logistics object groups with similarity higher than a second preset threshold, wherein each group of logistics object group at least comprises two logistics objects with high similarity, namely a first logistics object and a second logistics object; according to the first dynamic data aiming at the first logistics object, calculating a probability value of the first user which is related to the first dynamic data and is expected to buy the second logistics object. That is to say, the logistics object allocation method provided by the embodiment of the application can calculate the similarity from the logistics object dimension and predict the purchasing behavior. As shown in fig. 4b, it is assumed that at least the user 1 has purchased the logistics object 1, the user 2 has purchased the logistics object 3, and the user 3 has purchased the logistics object 2 are identified in the first dynamic data in the history data. Moreover, a group of logistics object groups is determined in the above manner, namely the logistics object 2 and the logistics object 3 with higher similarity (similar in terms of possible attributes or purchasing groups), and the logistics object 2 purchased by the user 3 can be seen from the first dynamic data of the logistics object 2, so that it can be inferred that the probability that the user 3 may purchase the logistics object 3 is higher, as shown in the arrow direction in fig. 4 b.

In addition, in the solution provided by the application example shown in fig. 4b, the historical data for the user and the logistics object may further include second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart behavior of the user for the logistics object, in addition to the first dynamic data. Therefore, the similarity among the plurality of logistics objects can be calculated according to the second dynamic data, that is, the similarity of the logistics objects is determined according to the searching behavior, the browsing behavior, the collecting behavior or the shopping cart adding behavior and the like corresponding to the plurality of logistics objects. On the other hand, in the embodiment of the present application, the history data for the user and the logistics object may include, in addition to the first dynamic data, second attribute data that identifies at least one of category information, producer information, and seller information of the logistics object. Therefore, the similarity between the plurality of physical distribution objects can be calculated according to the second attribute data, that is, the similarity of the physical distribution objects can be determined according to the information of the category, the producer or the seller of the plurality of physical distribution objects. In another aspect, in an embodiment of the present application, the historical data for the user and the logistics object may include the first dynamic data, the second dynamic data, and the second attribute data. Therefore, the similarity between the plurality of logistics objects can be calculated by combining the searching behavior, the browsing behavior, the collecting behavior or the shopping cart adding behavior corresponding to the logistics objects and the information of the category, the producer or the seller of the logistics objects.

Fig. 4c is a schematic application diagram three of the embodiment of the logistics object allocation method provided by the present application. In this embodiment of the application, the scheme of calculating the similarity from the user dimension and performing the purchasing behavior prediction in steps S302 to S304 may be replaced by calculating the similarity between a plurality of users and the similarity between a plurality of logistics objects according to historical data; acquiring at least one group of user groups with similarity higher than a first preset threshold and at least one group of logistics object groups with similarity higher than a second preset threshold, wherein each group of user groups at least comprises two users with high similarity, namely a first user and a second user, and each logistics object group at least comprises two logistics objects with high similarity, namely a first logistics object and a second logistics object; and calculating a probability value of the second user for expecting to purchase the second logistics object according to the first dynamic data for identifying the purchasing behavior of the first user aiming at the first logistics object. That is to say, the logistics object allocation method provided by the embodiment of the application can calculate the similarity from the user dimension and the logistics object dimension and predict the purchasing behavior. As shown in fig. 4c, it is assumed that at least the user 1 has purchased the logistics object 1, the user 2 has purchased the logistics object 3, and the user 3 has purchased the logistics object 2 are identified in the first dynamic data in the history data. Also, a set of user groups (user 1 and user 2) and a set of physical distribution object groups (physical distribution object 3 and physical distribution object 4) are determined in the above manner. The logistics object 3 purchased by the user 2 can be seen from the first dynamic data of the user 2, and therefore it can be inferred that the probability that the user 1 is likely to purchase the logistics object 4 is high, see the arrow direction in fig. 4 c.

In addition, in the solution provided by the application example shown in fig. 4c, the step of calculating the similarity between a plurality of users and the similarity between a plurality of logistics objects according to the historical data may be performed in any one of the following nine ways:

the first mode, the historical data also comprises second dynamic data for identifying at least one of searching behavior, browsing behavior, collecting behavior and shopping cart adding behavior of the user aiming at the logistics object.

The similarity is calculated by:

calculating the similarity among the plurality of users according to the second dynamic data;

and calculating the similarity among the plurality of logistics objects according to the second dynamic data.

And secondly, the historical data also comprises second dynamic data for identifying at least one behavior of a user in search behavior, browsing behavior, collecting behavior and shopping cart adding behavior for the logistics object, and second attribute data for identifying at least one information of category information, producer information and seller information of the logistics object.

The similarity is calculated by:

and calculating the similarity among the plurality of logistics objects according to the second attribute data.

And thirdly, the historical data also comprises second dynamic data for identifying at least one behavior of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user aiming at the logistics object, and second attribute data for identifying at least one information of category information, producer information and seller information of the logistics object.

The similarity is calculated by:

and calculating the similarity among the plurality of logistics objects according to the second dynamic data and the second attribute data.

And fourthly, the historical data also comprises first attribute data for identifying at least one of occupational information, gender information, age information and region information of the user, and second dynamic data for identifying at least one of searching behavior, browsing behavior, collecting behavior and shopping cart adding behavior of the user aiming at the logistics objects.

The similarity is calculated by:

calculating the similarity among a plurality of users according to the first attribute data;

Fifth, the history data further includes first attribute data identifying at least one of occupation information, gender information, age information, and region information of the user, and second attribute data including at least one of category information, producer information, and seller information identifying the logistics object,

the similarity is calculated by:

And the historical data also comprises first attribute data for identifying at least one of occupational information, gender information, age information and region information of the user, second dynamic data for identifying at least one of searching behavior, browsing behavior, collecting behavior and shopping cart adding behavior of the user aiming at the logistics object, and second attribute data for identifying at least one of category information, producer information and seller information of the logistics object.

The similarity is calculated by:

And seventh, the historical data further comprises second dynamic data for identifying at least one behavior of the user in searching behaviors, browsing behaviors, collecting behaviors and shopping cart adding behaviors aiming at the logistics objects, and first attribute data for identifying at least one information of occupational information, gender information, age information and region information of the user.

The similarity is calculated by:

calculating the similarity among the plurality of users according to the second dynamic data and the first attribute data;

And the historical data also comprises second dynamic data for identifying at least one behavior of the user in the searching behavior, the browsing behavior, the collecting behavior and the shopping cart adding behavior of the logistics object, first attribute data for identifying at least one information of occupational information, gender information, age information and region information of the user, and second attribute data for identifying at least one information of category information, producer information and seller information of the logistics object.

The similarity is calculated by:

The method ninth comprises the step that the historical data further comprises second dynamic data for identifying at least one of searching behaviors, browsing behaviors, collecting behaviors and shopping cart adding behaviors of the user aiming at the logistics objects, first attribute data for identifying at least one of professional information, sex information, age information and region information of the user, and second attribute data for identifying at least one of category information, producer information and seller information of the logistics objects.

The similarity is calculated by:

In the embodiment of the present application, the historical data may also be used as training data, for example, a part of the historical data is used as an input sample, another part of the historical data is used as an output sample, and then the part of the historical data is input to the machine learning model for training to generate the training model. Specifically, the training may be performed in a batch training manner or a streaming training manner. Therefore, in various embodiments of the present application, when obtaining prediction data from historical data, the historical data may be input into a training model to obtain corresponding prediction data. Finally, new order data which accord with the prediction result can be input into the training model again so as to improve the training model and form a closed loop.

In addition, in the embodiment of the application, statistical calculation can be performed on historical data; and according to the statistical calculation result, obtaining prediction data for predicting that at least one logistics object is allocated to the target logistics node. That is to say, statistics can be performed on multiple purchasing behaviors of multiple users, and the probability that the target logistics object is to be purchased by users in certain areas is predicted in advance according to the statistical result to be high, so that goods can be prepared in advance, and the target logistics object can be allocated to the target logistics node in advance.

In addition, in the embodiment of the present application, the historical data may further include third dynamic data identifying a change behavior of the user with respect to the logistics object. When prediction is performed based on the historical data, a probability value that the at least one user expects to switch the third logistics object to the fourth logistics object may be calculated based on the third dynamic data. For example, if the defect rate of a certain item is high and the replacement rate of the purchased user is high, the item can be prepared in advance according to the prediction data. Or, if the probability that the user replaces the purchased logistics object with the logistics object (for example, change style, change color, change size, etc.) of a different Stock Keeping Unit (SKU) is predicted to be higher according to the historical data, the user can Stock in advance and the replaced fourth logistics object can be allocated to the target logistics node in advance.

In addition, in the embodiment of the present application, the history data may further include third attribute data identifying different delivery addresses of the user for different logistics objects. When prediction is performed based on the historical data, a probability value that at least one user intends to send the physical distribution object to the target delivery address may be calculated based on the third attribute data and the attribute of the physical distribution object. For example, the user a is a young male, the collected or browsed items are logistics objects (such as health care products, old women's clothing, etc.) suitable for the elderly, and the user a can be predicted to purchase the logistics objects and send the logistics objects to the receiving address of the parent, so that the receiving address of the items which the user a purchased for the parent can be obtained from the historical order of the user a, and the items can be put in stock in advance according to the prediction result.

Further, when allocating the logistics objects according to the prediction data, the logistics object allocation method provided by the embodiment of the present application may further include:

s305, obtaining node information for identifying the terminal logistics node in the historical order of the user for which the prediction data aims.

S306, the node information is distributed to the logistics object aimed by the prediction data, so that the logistics object is distributed to the terminal logistics node.

In the embodiment of the application, the target logistics object can be directly transferred to the end node closest to the user for temporary storage. When the target user orders to purchase the target logistics object, the target logistics object can be rapidly and directly dispatched to the target user, so that the waiting time after the user purchases can be greatly reduced.

In addition, in this embodiment of the present application, the scheme of performing allocation processing on the logistics object according to the prediction data in steps S305 to S306 may instead be that node information for identifying each logistics node is acquired in a history order of a user to which a plurality of prediction data are directed; selecting one of the logistics nodes according to the available storage amount of the logistics nodes, and determining the target logistics node of the logistics object for which the prediction data is directed; and allocating node information of a target logistics node to the logistics object aimed by the prediction data so as to allocate the logistics object to the target logistics node. That is to say, in the embodiment of the present application, the storage and transportation conditions of each logistics node on the logistics object transmission path may be determined based on the historical ordering data, and then, the target logistics object is allocated to the logistics node with smaller warehousing pressure, so as to optimize the whole path, and reasonably warehouse in and warehouse in separate warehouses.

The logistics object allocation method provided by the embodiment of the application is based on historical purchasing behavior, searching behavior, browsing behavior, collecting behavior or shopping cart adding behavior of a user, occupation information, sex information, age information or region information of the user, category information of the logistics object, and producer information or seller information, whether a target logistics object is purchased by the target user is predicted in a machine learning mode, and then allocation processing is carried out on the logistics object in advance according to a prediction result, so that waiting time after shopping of the user can be reduced, user experience is improved, meanwhile, warehouse allocation planning is facilitated, warehouse pressure can be relieved under the condition that logistics transportation volume is large, and transportation efficiency is improved.

Example four

Fig. 5 is a schematic structural diagram of an embodiment of a logistics object allocation apparatus provided in the present application, which can be used to execute the method steps shown in fig. 2. As shown in fig. 5, the logistics object allocation apparatus may include: a first obtaining module 51, a second obtaining module 52 and a distribution processing module 53.

The first obtaining module 51 is configured to obtain historical data for a plurality of users and a plurality of logistics objects, where the historical data at least includes first dynamic data identifying purchasing behavior of the users for the logistics objects; the second obtaining module 52 is configured to obtain prediction data for predicting a purchasing behavior of at least one user with respect to at least one logistics object according to the historical data; the allocation processing module 53 is configured to perform allocation processing on the logistics objects according to the prediction data.

In this embodiment of the application, after the first obtaining module 51 obtains the historical data for the multiple users and the multiple logistics objects, the second obtaining module 52 obtains the prediction data for predicting the purchasing behavior of the at least one user for the at least one logistics object according to the historical data obtained by the first obtaining module 51. For example, the second obtaining module 52 may first determine the similarity between users or the similarity between logistics objects based on the historical data, and then predict the purchasing behavior of the users for the logistics objects based on the similarity. Finally, after the second obtaining module 52 obtains the prediction data, the allocating processing module 53 allocates the logistics objects according to the content displayed by the prediction data obtained by the second obtaining module 52.

The functions of the modules in the logistics object allocation device provided in the embodiment of the present application are described in detail in the above method embodiment, and are not described herein again.

The logistics object allocation device provided by the embodiment of the application is based on the historical purchasing behavior of the user, whether the target logistics object can be purchased by the target user or not is predicated, and then the logistics object is allocated in advance according to the predication result, so that the waiting time after the user purchases can be reduced, the user experience is improved, meanwhile, the warehouse allocation planning is facilitated, the warehousing pressure can be relieved under the condition that the logistics transportation volume is large, and the transportation efficiency is improved.

EXAMPLE five

Fig. 6 is a schematic structural diagram of another embodiment of the logistics object allocation apparatus provided by the present application, which can be used for executing the method steps shown in fig. 3. As shown in fig. 6, on the basis of the embodiment shown in fig. 5, in the logistics object allocation apparatus provided in the embodiment of the present application, the history data may further include second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and the second obtaining module 52 may include: a first calculation unit 521, a first acquisition unit 522, and a second calculation unit 523.

The first calculating unit 521 may be configured to calculate similarity between multiple users according to the second dynamic data; the first obtaining unit 522 may be configured to obtain at least one group of user groups with similarity higher than a first preset threshold, where the group of user groups includes at least a first user and a second user; the second calculating unit 523 may be configured to calculate, according to the first dynamic data related to the first user, a probability value of the first logistics object for which the second user expects to purchase the first dynamic data.

In addition, in this embodiment of the application, the history data may further include first attribute data that identifies at least one of professional information, gender information, age information, and region information of the user, and the second obtaining module 52 may further include: a third calculation unit (not shown in the figure). The third calculating unit may be configured to calculate a similarity between the plurality of users based on the first attribute data.

In addition, in this embodiment of the application, the history data may further include second dynamic data that identifies at least one of a search behavior, a browsing behavior, a collecting behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data that includes at least one of occupational information, gender information, age information, and region information that identifies the user, and the second obtaining module 52 may further include: a fourth calculating unit (not shown in the figure), which may be configured to calculate a similarity between the plurality of users based on the second dynamic data and the first attribute data.

On the other hand, in this embodiment of the application, the history data may further include second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and the second obtaining module 52 may further include: a fifth calculation unit 524, a second acquisition unit 525, and a sixth calculation unit 526.

The fifth calculating unit 524 may be configured to calculate similarities between the plurality of logistics objects according to the second dynamic data; the second obtaining unit 525 may be configured to obtain at least one logistics object group with similarity higher than a second preset threshold, where the logistics object group includes at least a first logistics object and a second logistics object; the sixth calculating unit 526 may be configured to calculate, according to the first dynamic data for the first logistics object, a probability value that the first user associated with the first dynamic data is expected to purchase the second logistics object.

In addition, in this embodiment of the application, the history data may further include second attribute data that identifies at least one of category information, producer information, and seller information of the logistics object, and the second obtaining module 52 may further include: a seventh calculating unit (not shown in the figure), which may be configured to calculate a similarity between the plurality of logistics objects based on the second attribute data.

In addition, in this embodiment of the application, the history data may further include second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior, and a shopping cart behavior of the user with respect to the logistics object, and second attribute data including at least one of category information, producer information, and vendor information identifying the logistics object, and the second obtaining module 52 may further include: an eighth calculating unit (not shown in the figure), which may be configured to calculate a similarity between the plurality of logistics objects according to the second dynamic data and the second attribute data.

On the other hand, in the embodiment of the present application, the second obtaining module 52 may further include: a ninth calculating unit 527, a third acquiring unit 528, and a tenth calculating unit 529.

Wherein, the ninth calculating unit 527 may be configured to calculate, according to the history data, a similarity between the plurality of users and a similarity between the plurality of logistics objects; the third obtaining unit 528 may be configured to obtain at least one group of user groups with similarity higher than a first preset threshold and at least one group of logistics objects with similarity higher than a second preset threshold, where the user groups include at least a first user and a second user, and the logistics object group includes at least a first logistics object and a second logistics object; the tenth calculating unit 529 may be configured to calculate a probability value that the second user expects to purchase the second logistics object according to the first dynamic data that identifies the purchasing behavior of the first user with respect to the first logistics object.

Specifically, the history data may further include second dynamic data identifying at least one of a search behavior, a browsing behavior, a collecting behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate, according to the second dynamic data, a similarity between the plurality of users; and calculating the similarity among the plurality of logistics objects according to the second dynamic data.

In addition, in this embodiment of the application, the history data may further include second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and second attribute data including at least one of category information, producer information, and vendor information identifying the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate similarity between the plurality of users according to the second dynamic data; and calculating the similarity between the plurality of logistics objects according to the second attribute data.

In addition, in this embodiment of the application, the history data may further include second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and second attribute data including at least one of category information, producer information, and vendor information identifying the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate similarity between the plurality of users according to the second dynamic data; and calculating the similarity between the plurality of logistics objects according to the second dynamic data and the second attribute data.

In addition, in this embodiment of the application, the historical data may further include first attribute data that identifies at least one of professional information, gender information, age information, and region information of the user, and second dynamic data that includes at least one of a search behavior, a browsing behavior, a collection behavior, and a shopping cart adding behavior of the user for the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate similarity between the multiple users according to the first attribute data; and calculating the similarity among the plurality of logistics objects according to the second dynamic data.

In addition, in this embodiment of the application, the historical data may further include first attribute data that identifies at least one of professional information, gender information, age information, and region information of the user, and second attribute data that includes at least one of category information, producer information, and seller information that identifies the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate, according to the first attribute data, a similarity between the plurality of users; and calculating the similarity between the plurality of logistics objects according to the second attribute data.

In addition, in this embodiment of the application, the historical data may further include first attribute data that identifies at least one of professional information, gender information, age information, and region information of the user, and second dynamic data that includes at least one of a search behavior, a browsing behavior, a collection behavior, and a shopping cart adding behavior of the user for the logistics object, and second attribute data that includes at least one of category information, producer information, and seller information that identifies the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate, according to the first attribute data, a similarity between the plurality of users; and calculating the similarity between the plurality of logistics objects according to the second dynamic data and the second attribute data.

In addition, in this embodiment of the application, the history data may further include second dynamic data identifying at least one of a search behavior, a browsing behavior, a collecting behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data including at least one of occupational information, gender information, age information, and region information identifying the user, and the ninth calculating unit 527 may be specifically configured to calculate the similarity between the multiple users according to the second dynamic data and the first attribute data; and calculating the similarity among the plurality of logistics objects according to the second dynamic data.

In addition, in this embodiment of the application, the history data may further include second dynamic data identifying at least one of a search behavior, a browsing behavior, a collecting behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data including at least one of occupational information, gender information, age information, and region information identifying the user, and second attribute data including at least one of category information, producer information, and vendor information identifying the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate a similarity between the plurality of users according to the second dynamic data and the first attribute data; and calculating the similarity between the plurality of logistics objects according to the second attribute data.

In addition, in this embodiment of the application, the history data may further include second dynamic data identifying at least one of a search behavior, a browsing behavior, a collecting behavior, and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data including at least one of occupational information, gender information, age information, and region information identifying the user, and second attribute data including at least one of category information, producer information, and vendor information identifying the logistics object, and the ninth calculating unit 527 may be specifically configured to calculate a similarity between the plurality of users according to the second dynamic data and the first attribute data; and calculating the similarity between the plurality of logistics objects according to the second dynamic data and the second attribute data.

In addition, the logistics object allocation device provided by the embodiment of the application can further comprise: and a training module 61, wherein the training module 61 may be configured to input the historical data as training data into a machine learning model for training to generate a training model for obtaining the prediction data.

In addition, in this embodiment of the application, the allocation processing module 53 may be specifically configured to obtain node information identifying an end logistics node from a historical order of a user for which the prediction data is directed; and the node information is distributed to the logistics objects aimed by the prediction data so as to distribute the logistics objects to the end logistics nodes.

Further, in this embodiment of the application, the allocating processing module 53 may be further specifically configured to obtain node information identifying each logistics node in a historical order of a user to which multiple pieces of predicted data are directed; the system comprises a plurality of logistics nodes and a target logistics node, wherein the target logistics node is used for selecting one of the logistics nodes according to the available storage amount of the logistics nodes and determining the target logistics node as a logistics object for which the prediction data aims; and the node information is used for allocating the target logistics node to the logistics object aimed by the prediction data so as to allocate the logistics object to the target logistics node.

The logistics object allocation device provided by the embodiment of the application, based on the historical purchasing behavior of the user, the searching behavior, the browsing behavior, the collecting behavior or the shopping cart adding behavior, the occupation information, the sex information, the age information or the region information of the user, the category information of the logistics object, the producer information or the seller information, whether the target logistics object can be purchased by the target user or not is predicted in a machine learning mode, and then the logistics object is allocated in advance according to the prediction result, so that the waiting time after the shopping of the user can be reduced, the user experience is improved, meanwhile, the warehouse allocation planning is facilitated, under the condition that the logistics transportation volume is large, the warehouse pressure can be relieved, and the transportation efficiency is improved.

EXAMPLE six

The internal function and structure of the logistics object allocation device, which can be implemented as an electronic device, are described above. Fig. 7 is a schematic structural diagram of an embodiment of an electronic device provided in the present application. As shown in fig. 7, the electronic device includes a memory 71 and a processor 72.

The memory 71 stores programs. In addition to the above-described programs, the memory 71 may also be configured to store other various data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phonebook data, messages, pictures, videos, and so forth.

The memory 71 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The processor 72 is not limited to a Central Processing Unit (CPU), but may be a processing chip such as a Graphic Processing Unit (GPU), a Field Programmable Gate Array (FPGA), an embedded neural Network Processor (NPU), or an Artificial Intelligence (AI) chip. A processor 72, coupled to the memory 71, that executes programs stored by the memory 71 to:

Further, as shown in fig. 7, the electronic device may further include: communication components 73, power components 74, audio components 75, a display 76, and the like. Only some of the components are schematically shown in fig. 7, and the electronic device is not meant to include only the components shown in fig. 7.

The communication component 73 is configured to facilitate wired or wireless communication between the electronic device and other devices. The electronic device may access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, or 5G, or a combination thereof. In an exemplary embodiment, the communication component 73 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 73 further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

A power supply component 74 provides power to the various components of the electronic device. The power components 74 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for an electronic device.

The audio component 75 is configured to output and/or input audio signals. For example, the audio component 75 includes a Microphone (MIC) configured to receive external audio signals when the electronic device is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in a memory 71 or transmitted via a communication component 73. In some embodiments, audio assembly 75 also includes a speaker for outputting audio signals.

The display 76 includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A logistics object allocation method is characterized by comprising the following steps:

2. The method according to claim 1, wherein the history data further includes second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the physical distribution object,

the obtaining of prediction data for predicting at least one purchase behavior of the user with respect to at least one logistics object according to the historical data includes:

calculating the similarity among a plurality of users according to the second dynamic data;

acquiring at least one group of user groups with similarity higher than a first preset threshold, wherein the user groups at least comprise a first user and a second user;

according to first dynamic data related to the first user, calculating a probability value of a first logistics object for which the second user expects to purchase the first dynamic data.

3. The logistics object allocation method of claim 1, wherein the history data further comprises first attribute data identifying at least one of occupational information, gender information, age information, and regional information of the user,

4. The method according to claim 1, wherein the history data further includes second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data including at least one of occupational information, gender information, age information and region information identifying the user,

calculating the similarity among a plurality of users according to the second dynamic data and the first attribute data;

5. The method according to claim 1, wherein the history data further includes second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the physical distribution object,

calculating the similarity among a plurality of logistics objects according to the second dynamic data;

acquiring at least one group of logistics object groups with similarity higher than a second preset threshold, wherein the logistics object groups at least comprise a first logistics object and a second logistics object;

according to the first dynamic data aiming at the first logistics object, calculating the probability value of the first user which is related to the first dynamic data and is expected to buy the second logistics object.

6. The logistics object allocation method of claim 1, wherein the history data further comprises second attribute data identifying at least one of category information, producer information and vendor information of the logistics object,

calculating the similarity among a plurality of logistics objects according to the second attribute data;

7. The logistics object allocation method of claim 1, wherein the history data further comprises a second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the logistics object, and a second attribute data comprising at least one of category information, producer information and vendor information identifying the logistics object,

calculating the similarity among a plurality of logistics objects according to the second dynamic data and the second attribute data;

8. The logistics object allocation method according to claim 1, wherein the obtaining of prediction data for predicting at least one purchase behavior of the user with respect to at least one logistics object according to the historical data comprises:

according to the historical data, calculating the similarity between a plurality of users and the similarity between a plurality of logistics objects;

acquiring at least one group of user groups with similarity higher than a first preset threshold and at least one group of logistics object groups with similarity higher than a second preset threshold, wherein the user groups at least comprise a first user and a second user, and the logistics object groups at least comprise a first logistics object and a second logistics object;

and calculating a probability value of the second user for expecting to purchase the second logistics object according to the first dynamic data for identifying the purchasing behavior of the first user aiming at the first logistics object.

9. The method according to claim 8, wherein the history data further includes second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the physical distribution object,

the calculating the similarity between a plurality of users and the similarity between a plurality of logistics objects according to the historical data comprises the following steps:

10. The logistics object allocation method of claim 8, wherein the history data further comprises a second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the logistics object, and a second attribute data comprising at least one of category information, producer information and vendor information identifying the logistics object,

11. The logistics object allocation method of claim 8, wherein the history data further comprises a second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the logistics object, and a second attribute data comprising at least one of category information, producer information and vendor information identifying the logistics object,

and calculating the similarity among a plurality of logistics objects according to the second dynamic data and the second attribute data.

12. The logistics object allocation method of claim 8, wherein the historical data further comprises a first attribute data identifying at least one of occupational information, gender information, age information and geographic information of the user, and a second dynamic data identifying at least one of search behavior, browsing behavior, collection behavior and shopping cart adding behavior of the user for the logistics object,

13. The logistics object allocation method of claim 8, wherein the history data further comprises a first attribute data identifying at least one of occupational information, gender information, age information, and region information of the user, and a second attribute data comprising at least one of category information, producer information, and vendor information identifying the logistics object,

14. The logistics object allocation method of claim 8, wherein the history data further comprises first attribute data identifying at least one of occupational information, gender information, age information, and regional information of the user, and second dynamic data identifying at least one of search behavior, browsing behavior, collection behavior, and shopping cart adding behavior of the user with respect to the logistics object, and second attribute data comprising at least one of category information, producer information, and seller information identifying the logistics object,

15. The method according to claim 8, wherein the history data further includes second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data including at least one of occupational information, gender information, age information and region information identifying the user,

16. The logistics object allocation method of claim 8, wherein the history data further comprises second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data comprising at least one of occupational information, gender information, age information and region information identifying the user, and second attribute data comprising at least one of category information, producer information and vendor information identifying the logistics object,

17. The logistics object allocation method of claim 8, wherein the history data further comprises second dynamic data identifying at least one of a search behavior, a browse behavior, a collection behavior and a shopping cart adding behavior of the user with respect to the logistics object, and first attribute data comprising at least one of occupational information, gender information, age information and region information identifying the user, and second attribute data comprising at least one of category information, producer information and vendor information identifying the logistics object,

18. The logistics object allocation method according to any one of claims 1 to 17, further comprising:

and inputting the historical data serving as training data into a machine learning model for training so as to generate a training model for acquiring the prediction data.

19. The method according to any one of claims 1 to 17, wherein the allocating the logistics objects according to the prediction data includes:

acquiring node information for identifying the terminal logistics node in the historical order of the user for which the prediction data is directed;

and allocating the node information to the logistics objects aimed by the prediction data so as to allocate the logistics objects to the terminal logistics nodes.

20. The method according to any one of claims 1 to 17, wherein the allocating the logistics objects according to the prediction data includes:

acquiring node information for identifying each logistics node in historical orders of users for which the plurality of prediction data aim at;

selecting one logistics node from the plurality of logistics nodes according to the available storage amount of the plurality of logistics nodes, and determining the target logistics node as a logistics object to which the prediction data aims;

and distributing the node information of the target logistics node to the logistics object aimed by the prediction data so as to distribute the logistics object to the target logistics node.

21. The logistics object allocation method according to claim 1, further comprising:

performing statistical calculation on the historical data;

and acquiring prediction data for predicting that at least one logistics object is allocated to a target logistics node according to the statistical calculation result.

22. The logistics object allocation method of claim 1, wherein the historical data further comprises third dynamic data for identifying a change behavior of a user for a logistics object, and the obtaining of the prediction data for predicting the purchasing behavior of at least one user for at least one logistics object according to the historical data comprises:

and calculating a probability value of the fact that at least one user expects to switch the third logistics object into the fourth logistics object according to the third dynamic data.

23. The logistics object allocation method of claim 1, wherein the historical data further comprises third attribute data identifying different delivery addresses of users for different logistics objects, and the obtaining of prediction data for predicting at least one purchase behavior of the users for at least one logistics object according to the historical data comprises:

and calculating a probability value of the logistics object expected to be sent to a target delivery address by at least one user according to the third attribute data and the attributes of the logistics object.

24. A logistics object allocation device is characterized by comprising:

25. An electronic device, comprising:

a memory for storing a program;

a processor for executing the program stored in the memory for:

26. A computer-readable storage medium having instructions stored thereon, the instructions comprising: