Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
Fig. 1 is a schematic diagram of a main flow of a bin selection method according to a first embodiment of the present invention. As shown in fig. 1, the bin selection method according to the embodiment of the present invention includes:
step S101, goods order historical data of a user are processed based on the trained first deep learning model, and goods order prediction data of the user in a preset time period are obtained.
In an optional implementation manner, the goods order history data of the user can be obtained in real time, and the goods order history data is processed in real time based on the trained first deep learning model, so that goods order prediction data of the user in a preset time period is obtained. Illustratively, the preset period of time may be one month, one half year, one year, or the like. Wherein the first deep learning model comprises: a time recursive neural network model, an LSTM (long short term memory network) model, or other deep learning models that can be used for timing prediction.
In another optional embodiment, the goods order history data of each user may be obtained in advance, processed based on the trained first deep learning model, and then the goods order prediction data of each user obtained through processing is stored in the database. When the warehouse selection method provided by the embodiment of the invention is executed, the goods order prediction data of a user in a preset time period can be acquired by directly querying the database.
In addition, in the implementation, besides the goods order prediction data, data required for calculation such as available warehouse set, goods storage unit price, goods delivery and transportation unit price, goods transportation distance, goods volume and the like are determined. And then, inputting the determined goods order prediction data of the user in a preset time period and other data required by operation into the warehouse selection model.
And S102, inputting the goods order prediction data into a pre-constructed warehouse selection model so as to select an optimal storage warehouse from all available warehouses for the user. Wherein, the objective function of the bin selection model is as follows: the total cost required by the user to store and deliver the goods based on the selected warehouse is minimized.
Further, the bin selection model satisfies at least one constraint condition as follows: firstly, the ratio of the goods order quantity capable of meeting the distribution timeliness requirement to the total order quantity is greater than or equal to a first threshold value; secondly, the total number of the selected storage warehouses is smaller than or equal to a second threshold value; wherein the first threshold and/or the second threshold are/is set in advance according to user input. By setting the constraint conditions, the requirements of the user on order delivery timeliness and the number of selected storage warehouses can be met, and the flexibility of the warehouse selection model is improved.
In addition, in specific implementation, in order to improve the solving efficiency of the bin selection model, a branch-and-bound algorithm can be adopted for solving. The branch-and-bound method is a very versatile algorithm, and the basic idea is to search all feasible solution spaces of an optimization problem with constraint conditions. The algorithm, when executed in detail, partitions the overall feasible solution space into smaller and smaller subsets (called branches) and computes a lower bound or upper bound (called delimitation) for the values of the solution within each subset. After each branch, no further branches are taken for those subsets for which the bounds exceed the known feasible solution values. In this way, many subsets of the solution (i.e., many points on the search tree) can be eliminated from consideration, thereby narrowing the search. This process continues until a feasible solution is found whose value is not greater than the bounds of any subset.
The bin selection model is described in detail below with reference to a specific example. In this particular example, the objective function of the binning model may be represented as:
wherein the first item
Representing the cost required by the user to store the goods based on the selected warehouse; second item
Representing the cost required by the user for goods delivery based on the selected warehouse; x is the number of
ijIs a decision variable with a value of 1 or 0, x
ijA value of 1 indicates that warehouse i can cover the area where warehouse j is located (i.e. the order in the area where warehouse j is located in the distribution range of warehouse i), and x
ijA value of 0 indicates that warehouse i cannot cover the area where warehouse j is located; f. of
ijIs a decision variable with a value of 1 or 0, f
ijTo 1 denotes the selection of warehouse i as the storage warehouse, f
ijA value of 0 indicates that warehouse i is not selected as the storage warehouse; q. q.s
jmIs a known variable with a value of 1 or 0, q
jmA number of 1 indicates the existence of an order for delivery to the area of warehouse j, q
jmA value of 0 indicates that there is no order for delivery to the area of warehouse j; p is a radical of
mnA known variable representing the number of items n contained in the order m; c. C
inIs a known variable and represents the single-piece inventory cost of the goods n in the warehouse i; v
nIs a known variable representing the volume of cargo n; d
ijIs a known variable representing the distance from warehouse i to warehouse j; r + F is a known variable representing the set of all available warehouses; w is a known variable representing the unit price of the goods per cubic meter per kilometer of delivery and transportation; m is a known variable representing a set of orders over a preset time period (e.g., half a year), and N is a known variable representing a set of goods in an order.
Further, in this particular example, the constraints of the binning model may be expressed as:
wherein the constraints (1) and (2) represent the decision variable fiAnd xijConstraint (3) indicates that if warehouse i is selected as a storage warehouse, warehouse i can cover the area where warehouse i is located (i.e. the order of the area where warehouse i is located can be delivered by warehouse i); constraint (4) indicates that the number of first type warehouses (such as RDC warehouses) is less than a preset threshold RN; the constraint (5) indicates that the number of second type warehouses (such as FDC warehouses) is less than a preset threshold FN; constraint (6) indicates that the total number of available warehouses (such as FDC warehouses) is less than a preset threshold DN; the constraint (7) indicates that all storage warehouses selected for the user can cover all available warehouses; the constraint condition (8) indicates that the proportion of the goods Order quantity capable of meeting the delivery timeliness requirement to the total Order quantity Order of the user is more than or equal to a preset threshold value Per; the constraint (9) indicates that if an order for a warehouse location can be delivered by multiple warehouses, the warehouse closest to the warehouse location is selected for delivery.
Among the above constraints, the preset thresholds RN, FN, DN and Per may be selectively set by the user. When the system is implemented specifically, a user can input the number of warehouses used by the user and the proportion of the order quantity which is expected to meet the aging requirement according to the requirement of the user. For example, the user may set the values of DN and Per, and the user may set the values of RN, FN and Per.
In the embodiment of the invention, a bin selection model is constructed in advance, and an objective function of the bin selection model is set as follows: the method has the advantages that the total cost required by the user for storing and delivering the goods based on the selected warehouse is minimized, then the goods order prediction data of the user in the preset time period are input into the pre-constructed warehouse selection model for processing, and the like, an optimal warehouse selection scheme can be automatically planned for the user, the rationality of warehouse selection is improved, the goods storage and delivery cost is reduced, and the goods delivery timeliness is improved. Furthermore, the self-storage resources can be utilized to provide personalized and scientific logistics services for users (such as merchants).
Fig. 2 is a schematic diagram of a main flow of a bin selection method according to a second embodiment of the present invention. As shown in fig. 2, the bin selection method according to the embodiment of the present invention includes:
step S201, obtaining goods order history data of a user.
Wherein the goods order history data of the user may include: the user has made orders for various goods delivered from regional warehouses over a period of time in the past (e.g., a day, a week, a month, etc.).
Step S202, the goods order historical data are processed based on the trained LSTM model, so that goods order prediction data of a user in a preset time period are obtained.
In an embodiment of the present invention, the first deep learning model is an LSTM (long short term memory network) model. The LSTM model is an RNN model that performs well in sequence model prediction, mainly including forgetting gates, input gates, and output gates.
Further, before step S202, the method of the embodiment of the present invention further includes: and constructing a training data set based on the goods order historical data of the user, and training the LSTM model according to the training data set to obtain the trained LSTM model.
Next, when processing is performed based on the trained LSTM model, the amount of orders for goods in a next cycle (e.g., next day) can be predicted from the amount of orders for goods in a cycle (e.g., one day), and then the amount of orders for goods in the next cycle (e.g., next day) can be predicted based on the predicted amount of orders for goods, so that the amount of orders for goods in a preset period (e.g., one month) in the future can be predicted. In the embodiment of the invention, the goods order prediction accuracy can be improved by adopting the LSTM model to predict the goods order.
And S203, inputting the goods order prediction data into a pre-constructed warehouse selection model so as to select an optimal storage warehouse from all available warehouses for the user.
Further, the bin selection model meets the following constraint conditions: firstly, the ratio of the goods order quantity capable of meeting the distribution timeliness requirement to the total order quantity is greater than or equal to a first threshold value; secondly, the total number of the selected storage warehouses is smaller than or equal to a second threshold value; wherein the first threshold and/or the second threshold are/is set in advance according to user input. By setting the constraint conditions, the requirements of the user on order delivery timeliness and the number of selected storage warehouses can be met, and the flexibility of the warehouse selection model is improved.
In addition, in specific implementation, in order to improve the solving efficiency of the bin selection model, a branch-and-bound algorithm can be adopted for solving. The branch-and-bound method is a very versatile algorithm, and the basic idea is to search all feasible solution spaces of an optimization problem with constraint conditions. The algorithm, when executed in detail, partitions the overall feasible solution space into smaller and smaller subsets (called branches) and computes a lower bound or upper bound (called delimitation) for the values of the solution within each subset. After each branch, no further branches are taken for those subsets for which the bounds exceed the known feasible solution values. In this way, many subsets of the solution (i.e., many points on the search tree) can be eliminated from consideration, thereby narrowing the search. This process continues until a feasible solution is found whose value is not greater than the bounds of any subset.
And step S204, returning the information of the optimal storage warehouse selected for the user to the user.
For example, after the optimal storage warehouse of the user is obtained through steps S201 to S203, the information of the optimal storage warehouse of the user may be sent to the front end, so as to be visually displayed through a front end (such as a client) page, so that the user can obtain the optimal warehouse selection scheme in time. In addition, in the specific implementation, the goods order prediction data obtained in the steps S201 to S202 can be sent to the user, so that the user can know the sales prediction situation of the goods in time.
In the embodiment of the invention, the goods order historical data of the user is processed based on the trained LSTM model to obtain the goods order prediction data of the user in a preset time period, so that the prediction accuracy of the goods order can be improved, and the subsequent warehouse selection effect can be improved; the optimal warehouse selection scheme can be automatically planned for the user by the steps of constructing a warehouse selection model in advance, setting the objective function of the warehouse selection model to be 'minimum total cost required by the user for storing and delivering the goods based on the selected warehouse', inputting the goods order prediction data of the user in a preset time period into the pre-constructed warehouse selection model for processing and the like, so that the rationality of warehouse selection is improved, the goods storage and delivery cost is reduced, and the goods delivery timeliness is improved.
Fig. 3 is a schematic diagram of a main flow of a bin selection method according to a third embodiment of the present invention. As shown in fig. 3, the bin selection method according to the embodiment of the present invention includes:
step S301, goods order history data of the user is obtained.
Wherein the goods order history data of the user may include: the user has made orders for various goods delivered from regional warehouses over a period of time in the past (e.g., a day, a week, a month, etc.).
Step S302, the goods order historical data are processed based on the trained first deep learning model, so that goods order prediction data of a user in a preset time period are obtained.
Illustratively, the first deep learning model comprises: the LSTM (long short term memory network) model. The LSTM model is an RNN model that performs well in sequence model prediction, mainly including forgetting gates, input gates, and output gates.
Further, before step S302, the method of the embodiment of the present invention further includes: and constructing a training data set based on the goods order historical data of the user, and training the LSTM model according to the training data set to obtain the trained LSTM model.
When processing is performed based on the trained LSTM model, the quantity of orders for the next cycle (e.g., the next day) can be learned and predicted using the quantity of orders for the next cycle (e.g., the one day), and then the quantity of orders for the next cycle (e.g., the next day) can be learned and predicted based on the predicted quantity of orders for the next cycle, so that the quantity of orders for a predetermined period (e.g., one month) in the future can be predicted. In the embodiment of the invention, the goods order prediction is carried out by adopting the trained LSTM model, so that the prediction accuracy of the goods order can be improved.
Step S303, inputting the goods order prediction data into a pre-constructed warehouse selection module so as to select an optimal storage warehouse from all available warehouses for the user.
Further, the bin selection model satisfies at least one constraint condition as follows: firstly, the ratio of the goods order quantity capable of meeting the distribution timeliness requirement to the total order quantity is greater than or equal to a first threshold value; secondly, the total number of the selected storage warehouses is smaller than or equal to a second threshold value; wherein the first threshold and/or the second threshold are/is set in advance according to user input. By setting the constraint conditions, the requirements of the user on order delivery timeliness and the number of selected storage warehouses can be met, and the flexibility of the warehouse selection model is improved.
In addition, in specific implementation, in order to improve the solving efficiency of the bin selection model, a branch-and-bound algorithm can be adopted for solving. The branch-and-bound method is a very versatile algorithm, and the basic idea is to search all feasible solution spaces of an optimization problem with constraint conditions. The algorithm, when executed in detail, partitions the overall feasible solution space into smaller and smaller subsets (called branches) and computes a lower bound or upper bound (called delimitation) for the values of the solution within each subset. After each branch, no further branches are taken for those subsets for which the bounds exceed the known feasible solution values. In this way, many subsets of the solution (i.e., many points on the search tree) can be eliminated from consideration, thereby narrowing the search. This process continues until a feasible solution is found whose value is not greater than the bounds of any subset.
And step S304, acquiring the goods order prediction data of the user in each optimal storage warehouse.
For example, the goods order history data of each optimal storage warehouse can be processed based on the trained first deep learning model to obtain the goods order prediction data of the optimal storage warehouse.
Step S305, processing the goods order prediction data of the optimal storage warehouse based on the trained second deep learning module to obtain inventory prediction data of the user in the optimal storage warehouse.
Illustratively, the second deep learning model is a linear chain random field model. Further, when the goods order prediction data of the optimal storage warehouse is processed based on the trained linear chain random field model, the stock prediction data of the user in the optimal storage warehouse can be solved by using a Viterbi (Viterbi) algorithm.
A conditional random field is a conditional probability distribution model for a given set of input sequences to yield another set of output sequences. The linear chain element random field model is a conditional random field model that requires the input sequence to have the same structure as the output sequence. In the embodiment of the invention, the input sequence of the linear chain piece random field model is a sales sequence constructed based on goods order prediction data: x ═ x1,x2,…xn) The output sequence is a stock sequence: y ═ y1,y2,…yn) The prediction problem of the linear chain piece random field model in the embodiment of the invention is as follows: and solving the problem of the stock sequence y with the maximum conditional probability.
Specifically, the linear chain element random field model can be expressed as the inner product of vector w and vector F (y, x):
wherein w ═ w1,w2,…wK),F(y,x)=(f1(y,x),f2(y,x),…fK(y,x))T,wk(K is 1,2, … K) is the weight corresponding to the characteristic function, fk(y, x) (K ═ 1,2, … K) is a characteristic function of inventory and sales variables.
Further, the prediction problem of conditional random fields can be transformed into a problem of solving the output sequence with the highest probability of non-normalization, which can be expressed as:
so as to obtain the compound with the characteristics of,
wherein, Fi(yi-1,yi,x)=(f1(yi-1,yi,x,i),f2(yi-1,yi,x,i),…fK(yi-1,yi,x,i))T,w=(w1,w2,…wK)。
Further, the method for solving the inventory forecast data of the user in the optimal storage warehouse based on the Viterbi algorithm mainly comprises the following steps:
1. initialize the unnormalized probabilities for each inventory label:
δ1(l)=w·F1(y0=start,y1=l,x)l=1,2,…m (14)
2. for i 2,3, … n, the maximum value δ of the unnormalized probabilities for each inventory annotation is recursively calculatedi(l) And recording the sequence of probability maxima psii(l):
3. Ending when calculating that i-n, the end point of the maximum probability sequence is:
4. outputting a most probable inventory sequence y*:
And S306, returning the optimal storage warehouse selected for the user and the inventory forecast data of each optimal storage warehouse to the user.
For example, after the optimal storage warehouse of the user and the inventory prediction data of the optimal storage warehouse are obtained through the above steps, the information of the optimal storage warehouse of the user and the inventory prediction data of each optimal storage warehouse can be sent to the front end, so that the information can be visually displayed through a front end (such as a client) page, and the user can conveniently obtain the optimal warehouse selection scheme and the inventory prediction condition of the optimal warehouse in time.
In the embodiment of the invention, a bin selection model is constructed in advance, and an objective function of the bin selection model is set as follows: the total cost required by the user for storing and delivering the goods based on the selected warehouse is minimized, then the goods order prediction data of the user in the preset time period is input into a pre-constructed warehouse selection model for processing, and the like, so that an optimal warehouse selection scheme can be automatically planned for the user, the rationality of warehouse selection is improved, the goods storage and delivery cost is reduced, and the goods delivery timeliness is improved; furthermore, the goods sales volume condition is predicted through the trained first deep learning model, the optimal storage warehouse of the user is determined through the bin selection model, and the goods inventory condition in the optimal storage warehouse is predicted through the trained second deep learning model, so that the user can conveniently and reasonably arrange the goods.
Fig. 4 is a schematic diagram of main modules of a bin selection device according to a fourth embodiment of the invention. As shown in fig. 4, the bin selecting device 400 of the embodiment of the present invention includes: a determining module 401 and a selecting module 402.
The determining module 401 is configured to process the historical data of the goods orders of the user based on the trained first deep learning model to obtain the predicted data of the goods orders of the user in a preset time period.
In an optional embodiment, the determining module 401 may obtain the historical data of the goods order of the user in real time, and perform real-time processing on the historical data of the goods order based on the trained first deep learning model to obtain the predicted data of the goods order of the user in a preset time period. Illustratively, the preset period of time may be one month, one half year, one year, or the like.
In another optional embodiment, the goods order history data of each user may be obtained in advance, processed based on the trained first deep learning model, and then the goods order prediction data of each user obtained through processing is stored in the database. When the bin selection method of the embodiment of the invention is executed, the determining module 401 may directly query the database to obtain the goods order prediction data of the user in the preset time period.
In addition, in the implementation, besides the goods order prediction data, data required for calculation such as available warehouse set, goods storage unit price, goods delivery and transportation unit price, goods transportation distance, goods volume and the like are determined. And then, inputting the determined goods order prediction data of the user in a preset time period and other data required by operation into the warehouse selection model.
A selecting module 402 for inputting the goods order forecast data into a pre-constructed warehouse selection model to select an optimal storage warehouse for the user from all available warehouses. Wherein, the objective function of the bin selection model is as follows: the total cost required by the user to store and deliver the goods based on the selected warehouse is minimized.
Further, the bin selection model satisfies at least one constraint condition as follows: firstly, the ratio of the goods order quantity capable of meeting the distribution timeliness requirement to the total order quantity is greater than or equal to a first threshold value; secondly, the total number of the selected storage warehouses is smaller than or equal to a second threshold value; wherein the first threshold and/or the second threshold are/is set in advance according to user input. By setting the constraint conditions, the requirements of the user on order delivery timeliness and the number of selected storage warehouses can be met, and the flexibility of the warehouse selection model is improved.
In addition, in a specific implementation, in order to improve the solving efficiency of the bin selection model, the selecting module 402 may adopt a branch-and-bound algorithm to solve. The branch-and-bound method is a very versatile algorithm, and the basic idea is to search all feasible solution spaces of an optimization problem with constraint conditions. The algorithm, when executed in detail, partitions the overall feasible solution space into smaller and smaller subsets (called branches) and computes a lower bound or upper bound (called delimitation) for the values of the solution within each subset. After each branch, no further branches are taken for those subsets for which the bounds exceed the known feasible solution values. In this way, many subsets of the solution (i.e., many points on the search tree) can be eliminated from consideration, thereby narrowing the search. This process continues until a feasible solution is found whose value is not greater than the bounds of any subset.
In the device provided by the embodiment of the invention, the warehouse selection model is constructed in advance, the objective function of the warehouse selection model is set as 'the total cost required by the user for storing and delivering the goods based on the selected warehouse is the minimum', the goods order prediction data of the user in a preset time period is determined by the determination module, and the goods order prediction data is input into the pre-constructed warehouse selection model by the selection module for processing, so that an optimal warehouse selection scheme can be planned for the user automatically, the rationality of warehouse selection is improved, the goods storage and delivery cost is reduced, and the goods delivery time is improved. Furthermore, the self-storage resources can be utilized to provide personalized and scientific logistics services for users (such as merchants).
Fig. 5 is a schematic diagram of main modules of a bin selection device according to a fifth embodiment of the invention. As shown in fig. 5, the bin selecting device 500 of the embodiment of the present invention includes: a determination module 501, a selection module 502, an inventory prediction module 503, and a sending module 504.
The determining module 501 is configured to obtain historical data of a goods order of a user, and process the historical data of the goods order based on the trained first deep learning model to obtain predicted data of the goods order of the user in a preset time period.
Wherein the goods order history data of the user may include: the amount of orders for various goods delivered by regional warehouses by the user over a period of time in the past (e.g., a day, a week, a month, etc.); the goods order prediction data of the user in the preset time period may include: the user may be required to order quantities of various goods for distribution from regional warehouses for a future period of time.
Illustratively, the first deep learning model comprises: the LSTM (long short term memory network) model. The LSTM model is an RNN model that performs well in sequence model prediction, mainly including forgetting gates, input gates, and output gates.
When processing is performed based on the trained LSTM model, the quantity of orders for the next cycle (e.g., the next day) can be learned and predicted using the quantity of orders for the next cycle (e.g., the one day), and then the quantity of orders for the next cycle (e.g., the next day) can be learned and predicted based on the predicted quantity of orders for the next cycle, so that the quantity of orders for a predetermined period (e.g., one month) in the future can be predicted. In the embodiment of the invention, the goods order prediction is carried out by adopting the trained LSTM model, so that the prediction accuracy can be improved.
A selecting module 502 for inputting the goods order forecast data into a pre-constructed warehouse selection model to select an optimal storage warehouse for the user from all available warehouses. Wherein, the objective function of the bin selection model is as follows: the total cost required by the user to store and deliver the goods based on the selected warehouse is minimized.
Further, the bin selection model satisfies at least one constraint condition as follows: firstly, the ratio of the goods order quantity capable of meeting the distribution timeliness requirement to the total order quantity is greater than or equal to a first threshold value; secondly, the total number of the selected storage warehouses is smaller than or equal to a second threshold value; wherein the first threshold and/or the second threshold are/is set in advance according to user input. By setting the constraint conditions, the requirements of the user on order delivery timeliness and the number of selected storage warehouses can be met, and the flexibility of the warehouse selection model is improved. In addition, in specific implementation, in order to improve the solving efficiency of the bin selection model, a branch-and-bound algorithm can be adopted for solving.
The inventory prediction module 503 is configured to obtain the goods order prediction data of the user in each optimal storage warehouse, and process the goods order prediction data of the optimal storage warehouse based on the trained second deep learning model to obtain the inventory prediction data of the user in the optimal storage warehouse.
Illustratively, the second deep learning model is a linear chain random field model. Further, when the goods order prediction data of the optimal storage warehouse is processed based on the trained linear chain random field model, the stock prediction data of the user in the optimal storage warehouse can be solved by using a Viterbi (Viterbi) algorithm.
A sending module 504, configured to return the selected optimal storage warehouse for the user and the inventory prediction data of each optimal storage warehouse to the user.
For example, after the optimal storage warehouse of the user and the inventory prediction data of the optimal storage warehouse are obtained, the information of the optimal storage warehouse of the user and the inventory prediction data of each optimal storage warehouse can be sent to the front end, so that the information can be visually displayed through a front end (such as a client) page, and the user can conveniently obtain the optimal warehouse selection scheme and the inventory prediction condition of the optimal warehouse in time.
In the device provided by the embodiment of the invention, the warehouse selection model is constructed in advance, the objective function of the warehouse selection model is set as 'the total cost required by the user for storing and delivering the goods based on the selected warehouse is the minimum', the goods order prediction data of the user in a preset time period is determined by the determination module, and the goods order prediction data is input into the pre-constructed warehouse selection model by the selection module for processing, so that an optimal warehouse selection scheme can be planned for the user automatically, the rationality of warehouse selection is improved, the goods storage and delivery cost is reduced, and the goods delivery timeliness is improved; furthermore, the goods sales volume condition is predicted through the trained first deep learning model, the optimal storage warehouse of the user is determined through the bin selection model, and the goods inventory condition in the optimal storage warehouse is predicted through the trained second deep learning model, so that the user can conveniently and reasonably arrange the goods.
Fig. 6 illustrates an exemplary system architecture 600 to which the bin selection method or bin selection apparatus of embodiments of the invention may be applied.
As shown in fig. 6, the system architecture 600 may include terminal devices 601, 602, 603, a network 604, and a server 605. The network 604 serves to provide a medium for communication links between the terminal devices 601, 602, 603 and the server 605. Network 604 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.
A user may use the terminal devices 601, 602, 603 to interact with the server 605 via the network 604 to receive or send messages or the like. Various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, and the like, may be installed on the terminal devices 601, 602, and 603.
The terminal devices 601, 602, 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 605 may be a server that provides various services, such as a background management server that supports a goods storage and distribution service client or a goods storage and distribution service website browsed by a user using the terminal devices 601, 602, 603. The background management server may analyze and perform other processing on the received data such as the warehouse selection request, and feed back a processing result (e.g., the selected optimal storage warehouse) to the terminal device.
It should be noted that the binning method provided by the embodiment of the present invention is generally executed by the server 605, and accordingly, the binning device is generally disposed in the server 605.
It should be understood that the number of terminal devices, networks, and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use with the electronic device implementing an embodiment of the present invention. The computer system illustrated in FIG. 7 is only an example and should not impose any limitations on the scope of use or functionality of embodiments of the invention.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU)701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 701.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor includes a determination module and a selection module. Where the names of these modules do not in some cases constitute a limitation on the module itself, for example, a determination module may also be described as a "module that determines goods order forecast data".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to perform the following: processing the goods order history data of the user based on the trained first deep learning model to obtain goods order prediction data of the user in a preset time period; inputting the goods order prediction data into a pre-constructed warehouse selection model so as to select an optimal storage warehouse from all available warehouses for the user; wherein, the objective function of the bin selection model is as follows: the total cost required by the user to store and deliver the goods based on the selected warehouse is minimized.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.