Preceding warehouse address information generation method, device and equipment and computer readable medium

Abstract

Embodiments of the present disclosure disclose a front warehouse address information generation method, device and equipment and a computer readable medium. A specific implementation of the method comprises: obtaining a historical order information set and a candidate front warehouse information set; generating a historical order cluster information set, a target candidate front warehouse information set and a predicted order cluster information set based on the historical order information set and the candidate front warehouse information set; performing feature extraction processing on each historical order cluster information in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information, thereby obtaining a feature order cluster information set; and generating front warehouse address information based on the target candidate front warehouse information set, the predicted order cluster information set and the feature order cluster information set. The implementation is related to artificial intelligence and can improve the accuracy of generating front warehouse address information.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, specifically to a method, apparatus, device, and computer-readable medium for generating pre-position warehouse address information. Background Technology

[0002] Choosing the right location for a forward warehouse is a major challenge for forward warehouse services. The typical approach to generating forward warehouse address information is to use a neural network model to predict the turnover value of goods corresponding to each candidate forward warehouse address, thereby selecting the optimal forward warehouse address from among the candidates.

[0003] However, the inventors discovered that when generating the pre-positioning warehouse address information using the above method, the following technical problems often occur:

[0004] Predicting the item turnover value of candidate front warehouse address information without considering the historical item turnover value and future changes in user demand corresponding to the candidate front warehouse address information leads to a decrease in the accuracy of generating front warehouse address information.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] Some embodiments of this disclosure provide a method, apparatus, device, and computer-readable medium for generating pre-position warehouse address information to address one or more of the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of this disclosure provide a method for generating pre-positioned warehouse address information. The method includes: acquiring a historical order information set and a candidate pre-positioned warehouse information set; generating a historical order cluster information set, a target candidate pre-positioned warehouse information set, and a predicted order cluster information set based on the historical order information set and the candidate pre-positioned warehouse information set; performing feature extraction processing on each historical order cluster information in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information, thereby obtaining a feature order cluster information set; and generating pre-positioned warehouse address information based on the target candidate pre-positioned warehouse information set, the predicted order cluster information set, and the feature order cluster information set.

[0009] Optionally, the above method for generating the front warehouse address information further includes: sending the front warehouse address information to a display terminal for staff to select the front warehouse address.

[0010] Optionally, the above-mentioned acquisition of historical order information set and candidate front warehouse information set includes: acquiring the full order information set; filtering the full order information set to obtain a filtered order information set; and integrating each filtered order information in the filtered order information set to generate historical order information and candidate front warehouse information, thus obtaining the historical order information set and the candidate front warehouse information set.

[0011] Optionally, the above-mentioned generation of a historical order cluster information set, a target candidate front-end warehouse information set, and a predicted order cluster information set based on the historical order information set and the candidate front-end warehouse information set includes: performing clustering processing on the historical order information set to obtain the historical order cluster information set; updating each candidate front-end warehouse information in the candidate front-end warehouse information set based on the historical order cluster information set to obtain the target candidate front-end warehouse information set; and generating predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set to obtain the predicted order cluster information set.

[0012] Optionally, the historical order information in the aforementioned historical order information set includes: order address information; and the aforementioned clustering process of the aforementioned historical order information set to obtain a historical order cluster information set includes: matching the order address information included in every two historical order information sets in the aforementioned historical order information set to generate address matching results, obtaining an address matching result set; integrating the aforementioned historical order information set based on the address matching result set to obtain a matched historical order information set; and clustering the aforementioned matched historical order information set to obtain the aforementioned historical order cluster information set.

[0013] Optionally, generating the predicted order cluster information corresponding to each historical order cluster in the historical order cluster information set includes: splitting the historical order cluster information to obtain historical order cluster trend information and historical order cluster remainder information; generating a predicted order cluster trend value sequence based on the historical order cluster trend information; generating a predicted order cluster remainder value sequence based on the historical order cluster trend information; for each predicted order cluster trend value in the predicted order cluster trend value sequence, determining the predicted order cluster item circulation value as the sum of the predicted order cluster remainder value corresponding to the predicted order cluster trend value and the predicted order cluster trend value in the predicted order cluster remainder value sequence, thereby obtaining a predicted order cluster item circulation value sequence; and generating the predicted order cluster information based on the predicted order cluster item circulation value sequence.

[0014] Optionally, the above-mentioned feature extraction processing of each historical order cluster in the historical order cluster information set to generate feature order cluster information based on the predicted order cluster information set includes: determining the predicted order cluster information corresponding to the historical order cluster information in the predicted order cluster information set as the target predicted order cluster information; performing feature extraction processing on the historical order cluster information and the target predicted order cluster information respectively to obtain historical order cluster feature information and predicted order cluster feature information; determining historical fluctuation values, historical trend values, and historical predictable values ​​based on the historical order cluster feature information; determining predicted fluctuation values, predicted trend values, and predicted predictable values ​​based on the predicted order cluster feature information; determining feature order cluster fluctuation values, feature order cluster predicted trend values, and feature order cluster predicted predictable values ​​based on the historical fluctuation values, historical trend values, historical predictable values, predicted fluctuation values, predicted trend values, and predicted predictable values; and performing fusion processing on the feature order cluster fluctuation values, feature order cluster predicted trend values, and feature order cluster predicted predictable values ​​to obtain the feature order cluster information.

[0015] Optionally, generating front warehouse address information based on the aforementioned target candidate front warehouse information set, the aforementioned predicted order cluster information set, and the aforementioned feature order cluster information set includes: generating front warehouse coverage constraint information based on the aforementioned target candidate front warehouse information set, a preset maximum number of front warehouses to be built, and a preset order fulfillment rate; generating front warehouse capacity constraint information based on the aforementioned target candidate front warehouse information set and the aforementioned predicted order cluster information set; generating front warehouse delivery range constraint information based on the aforementioned target candidate front warehouse information set and a preset distance adjustment coefficient; and determining the aforementioned front warehouse address information based on the aforementioned feature order cluster information set, the aforementioned front warehouse coverage constraint information, the aforementioned front warehouse capacity constraint information, the aforementioned front warehouse delivery range constraint information, and the preset front warehouse address constraint information.

[0016] Secondly, some embodiments of this disclosure provide a pre-position warehouse address information generation apparatus, which includes: an acquisition unit configured to acquire a historical order information set and a candidate pre-position warehouse information set; a first generation unit configured to generate a target candidate pre-position warehouse information set and a predicted order cluster information set based on the historical order information set and the candidate pre-position warehouse information set; a feature extraction unit configured to perform feature extraction processing on each historical order cluster information in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information, thereby obtaining a feature order cluster information set; and a second generation unit configured to generate pre-position warehouse address information based on the target candidate pre-position warehouse information set, the predicted order cluster information set, and the feature order cluster information set.

[0017] Optionally, the aforementioned pre-position warehouse address information generation device further includes: a sending unit configured to send the aforementioned pre-position warehouse address information to a display terminal for staff to select a pre-position warehouse address.

[0018] Optionally, the acquisition unit is further configured to: acquire the full set of order information; filter the full set of order information to obtain a filtered set of order information; integrate each filtered order information in the filtered set of order information to generate historical order information and candidate front warehouse information, thereby obtaining the historical order information set and the candidate front warehouse information set.

[0019] Optionally, the first generation unit is further configured to: perform clustering processing on the historical order information set to obtain the historical order cluster information set; based on the historical order cluster information set, update the information of each candidate front warehouse in the candidate front warehouse information set to obtain the target candidate front warehouse information set; and generate predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set to obtain the predicted order cluster information set.

[0020] Optionally, the historical order information in the aforementioned historical order information set includes: order address information; and the aforementioned first generation unit is further configured to: perform matching processing on the order address information included in every two historical order information in the aforementioned historical order information set to generate address matching results, thereby obtaining an address matching result set; based on the aforementioned address matching result set, perform integration processing on the aforementioned historical order information set to obtain a matched historical order information set; and perform clustering processing on the aforementioned matched historical order information set to obtain the aforementioned historical order cluster information set.

[0021] Optionally, the first generation unit is further configured to: split the historical order cluster information to obtain historical order cluster trend information and historical order cluster remainder information; generate a predicted order cluster trend value sequence based on the historical order cluster trend information; generate a predicted order cluster remainder value sequence based on the historical order cluster trend information; for each predicted order cluster trend value in the predicted order cluster trend value sequence, determine the predicted order cluster item circulation value by summing the predicted order cluster remainder value corresponding to the predicted order cluster trend value and the predicted order cluster trend value in the predicted order cluster remainder value sequence, thereby obtaining a predicted order cluster item circulation value sequence; and generate the predicted order cluster information based on the predicted order cluster item circulation value sequence.

[0022] Optionally, the feature extraction unit is further configured to: determine the predicted order cluster information corresponding to the historical order cluster information in the predicted order cluster information set as the target predicted order cluster information; perform feature extraction processing on the historical order cluster information and the target predicted order cluster information respectively to obtain historical order cluster feature information and predicted order cluster feature information; determine historical fluctuation value, historical trend value, and historical predictable value based on the historical order cluster feature information; determine predicted fluctuation value, predicted trend value, and predicted predictable value based on the predicted order cluster feature information; determine feature order cluster fluctuation value, feature order cluster predicted trend value, and feature order cluster predicted predictable value based on the historical fluctuation value, the historical trend value, the historical predictable value, the predicted fluctuation value, the predicted trend value, and the predicted predictable value; and perform fusion processing on the feature order cluster fluctuation value, the feature order cluster predicted trend value, and the feature order cluster predicted predictable value to obtain the feature order cluster information.

[0023] Optionally, the second generation unit is further configured to: generate front warehouse coverage constraint information based on the target candidate front warehouse information set, the preset maximum number of front warehouses to be built, and the preset order fulfillment rate; generate front warehouse capacity constraint information based on the target candidate front warehouse information set and the predicted order cluster information set; generate front warehouse delivery range constraint information based on the target candidate front warehouse information set and the preset distance adjustment coefficient; and determine the front warehouse address information based on the feature order cluster information set, the front warehouse coverage constraint information, the front warehouse capacity constraint information, the front warehouse delivery range constraint information, and the preset front warehouse address constraint information.

[0024] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the implementations of the first aspect above.

[0025] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0026] Fifthly, some embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0027] The above embodiments of this disclosure have the following beneficial effects: the method for generating front warehouse address information according to some embodiments of this disclosure can improve the accuracy of generating front warehouse address information. Specifically, the reason for the reduced accuracy of generating front warehouse address information is that only the item turnover value of candidate front warehouse address information is predicted, without considering the historical item turnover value and future changes in user demand corresponding to the candidate front warehouse address information. Based on this, the method for generating front warehouse address information according to some embodiments of this disclosure first obtains a historical order information set and a candidate front warehouse information set. Second, based on the above historical order information set and the above candidate front warehouse information set, a historical order cluster information set, a target candidate front warehouse information set, and a predicted order cluster information set are generated. Thus, the obtained historical order cluster information set can represent the historical item turnover value corresponding to the candidate front warehouse address information, the predicted order cluster information set can represent the future changes in user demand corresponding to the candidate front warehouse address information, and the target candidate front warehouse information set can represent the front warehouse address information of each candidate. Then, based on the aforementioned predicted order cluster information set, feature extraction processing is performed on each historical order cluster information in the aforementioned historical order cluster information set to generate feature order cluster information, thus obtaining a feature order cluster information set. Therefore, by combining the historical item turnover values ​​corresponding to the candidate front-end warehouse address information and future changes in user demand, a feature order cluster information set that can characterize the order cluster features can be obtained. Finally, based on the aforementioned target candidate front-end warehouse information set, the aforementioned predicted order cluster information set, and the aforementioned feature order cluster information set, front-end warehouse address information is generated. Thus, front-end warehouse address information can be selected from the target candidate front-end warehouse information set. Therefore, the front-end warehouse address information generation method of this disclosure, by combining the predicted order cluster information and the historical order cluster information to obtain feature order cluster information, considers historical item turnover values ​​and future changes in user demand, and can improve the accuracy of generating front-end warehouse address information. Attached Figure Description

[0028] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0029] Figure 1 This is a schematic diagram of an application scenario of the method for generating pre-position warehouse address information according to some embodiments of this disclosure;

[0030] Figure 2 These are flowcharts of some embodiments of the method for generating pre-position warehouse address information according to this disclosure;

[0031] Figure 3 This is a flowchart of some other embodiments of the method for generating pre-position warehouse address information according to this disclosure;

[0032] Figure 4 This is a schematic diagram of the coverage area of ​​the front warehouses based on the method for generating front warehouse address information according to this disclosure;

[0033] Figure 5 These are schematic diagrams of some embodiments of the pre-position warehouse address information generation device according to this disclosure;

[0034] Figure 6 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0035] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0036] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0037] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0038] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0039] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0040] Before performing any of the operations involving the collection, storage, or use of user personal information (such as user profiles and user historical behavior) disclosed in this disclosure, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, informing the personal information subjects, and obtaining prior authorization and consent from the personal information subjects.

[0041] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0042] Figure 1 This is a schematic diagram illustrating an application scenario of a recommendation information generation method according to some embodiments of the present disclosure.

[0043] exist Figure 1 and Figure 2 In the application scenario, firstly, the electronic device 101 can acquire historical order information set 102 and candidate front-end warehouse information set 103. The historical order information set 102 can include historical order information 1021, 1022, 1023, and 1024. For example, historical order information 1021 could be "Order Code: 0049, Item Code: 020, Item Weight: 2 kg". The candidate front-end warehouse information set 103 can include candidate front-end warehouse information 1031, 1032, 1033, and 1034. For example, candidate front-end warehouse information 1031 could be "Front-end Warehouse Code: 001, Average Productivity per Employee in Warehouse: 50, Average Productivity per Rider: 50, Maximum Number of Employees in Warehouse: 100, Maximum Number of Riders: 100". Secondly, the electronic device 101 can generate a historical order cluster information set 104, a target candidate pre-positioning warehouse information set 105, and a predicted order cluster information set 106 based on the aforementioned historical order information set 102 and the aforementioned candidate pre-positioning warehouse information set 103. In this application scenario, the aforementioned historical order cluster information set 104 may include historical order cluster information 1041 and historical order cluster information 1042. The aforementioned target candidate pre-positioning warehouse information set 105 may include target candidate pre-positioning warehouse information 1051 corresponding to candidate pre-positioning warehouse information 1031, target candidate pre-positioning warehouse information 1052 corresponding to candidate pre-positioning warehouse information 1032, target candidate pre-positioning warehouse information 1053 corresponding to candidate pre-positioning warehouse information 1033, and target candidate pre-positioning warehouse information 1054 corresponding to candidate pre-positioning warehouse information 1034. The aforementioned predicted order cluster information set 106 may include predicted order cluster information 1061 corresponding to historical order cluster information 1041 and predicted order cluster information 1062 corresponding to historical order cluster information 1042. Then, based on the predicted order cluster information set 106, the electronic device 101 can perform feature extraction processing on each historical order cluster information in the historical order cluster information set 104 to generate feature order cluster information, resulting in a feature order cluster information set 107. In this application scenario, the feature order cluster information set 107 may include feature order cluster information 1071 corresponding to historical order cluster information 1041 and feature order cluster information 1072 corresponding to historical order cluster information 1042. Finally, the electronic device 101 can generate pre-position warehouse address information 108 based on the target candidate pre-position warehouse information set 105, the predicted order cluster information set 106, and the feature order cluster information set 107.

[0044] It should be noted that the aforementioned electronic device 101 can be either hardware or software. When the electronic device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the electronic device is software, it can be installed in the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0045] It should be understood that Figure 1 The number of electronic devices shown is merely illustrative. Any number of electronic devices can be used depending on the implementation requirements.

[0046] Continue to refer to Figure 2 , Figure 2 A flow 200 is shown illustrating some embodiments of a method for generating pre-position warehouse address information according to this disclosure. This method for generating pre-position warehouse address information includes the following steps:

[0047] Step 201: Obtain the historical order information set and the candidate forward warehouse information set.

[0048] In some embodiments, the execution entity of the pre-warehouse address information generation method (e.g., Figure 1 The electronic device 101 shown can acquire historical order information sets and candidate pre-positioning warehouse information sets. In practice, the aforementioned executing entity can acquire the aforementioned historical order information sets and candidate pre-positioning warehouse information sets from the terminal device via wired or wireless connections.

[0049] In some optional implementations of certain embodiments, the process by which the executing entity obtains the historical order information set and the candidate pre-positioning warehouse information set may include the following steps:

[0050] The first step is to obtain the complete order information set. This complete order information set can be obtained from the terminal device via wired or wireless connection. The complete order information set may include, but is not limited to, at least one of the following: historical order information, historical waybill information, order item information, candidate forward warehouse address information, and order cost information.

[0051] As an example, the aforementioned historical order information may include, but is not limited to, at least one of the following: user order date, order code, item code, item turnover value (item sales volume), province of delivery location, city of delivery location, and order address information. Here, the aforementioned user order date can represent the time when the user placed the order. The aforementioned order code can uniquely identify an order. The aforementioned item code can uniquely identify an item. For example, the aforementioned item can be, but is not limited to, at least one of the following: apples, spinach, or pork. The aforementioned historical waybill information may include, but is not limited to, at least one of the following: waybill code, order code, geographical longitude and geographical latitude of delivery location. The aforementioned order item information may include, but is not limited to, at least one of the following: item code, item name, primary category of the item (e.g., clothing), secondary category of the item (e.g., trench coat), tertiary category of the item (e.g., short trench coat), item weight, item volume, and selection tag. Here, the aforementioned selection tag can indicate whether the aforementioned item should be placed in the forward warehouse. When the selected item is marked as 1, it indicates that the item should be placed in the pre-warehouse; when the selected item is marked as 0, it indicates that the item should not be placed in the pre-warehouse. The candidate pre-warehouse address information may include, but is not limited to, at least one of the following: pre-warehouse code, pre-warehouse coverage area, geographical longitude of the pre-warehouse address, geographical latitude of the pre-warehouse address, maximum pre-warehouse capacity, average productivity per employee in the warehouse, average productivity per rider, maximum number of employees in the warehouse, and maximum number of riders. Here, the pre-warehouse code uniquely represents a pre-warehouse. The pre-warehouse coverage area represents the maximum delivery range of the pre-warehouse corresponding to the pre-warehouse code. The maximum pre-warehouse capacity represents the maximum capacity that the pre-warehouse corresponding to the pre-warehouse code can hold. The average productivity per employee in the warehouse represents the average number of orders produced per employee per day in the pre-warehouse corresponding to the pre-warehouse code. The average productivity per rider represents the average number of orders completed per rider per day in the pre-warehouse corresponding to the pre-warehouse code. The order cost information mentioned above may include, but is not limited to, at least one of the following: warehouse code, average daily production order volume, total average cost per order, average cost per production order in the main warehouse, average cost per replenishment order, average cost per operation order within the warehouse, and average cost per delivery order for riders. Here, the total average cost per order can be the sum of the average cost per production order in the main warehouse, the average cost per replenishment order, the average cost per operation order within the warehouse, and the average cost per delivery order for riders. The average daily production order volume represents the number of orders generated daily by the warehouse corresponding to the warehouse code mentioned above. The average cost per production order in the main warehouse represents the average cost per production order in the main warehouse that provides replenishment to the warehouse corresponding to the warehouse code mentioned above.

[0052] The second step is to filter the entire set of order information to obtain a filtered set of order information. This filtering process can include removing empty entries, deduplicating entries, and validating field types. Specifically, removing empty entries involves deleting all empty orders from the set. Deduplication can be performed using a pre-defined algorithm. Field type validation can be performed using a pre-defined algorithm.

[0053] As an example, the preset deduplication algorithm mentioned above can be, but is not limited to, at least one of the following: SimHash (similarity hash) algorithm or MinHash (minimum hash) algorithm. The preset field verification algorithm mentioned above can be the CRC (Cyclic Redundancy Check) algorithm.

[0054] The third step involves integrating each filtered order information in the aforementioned filtered order information set to generate historical order information and candidate front-end warehouse information, resulting in the aforementioned historical order information set and candidate front-end warehouse information set. Specifically, the order code, item code, item weight, item volume, and item turnover value corresponding to the item code, as well as the order address information corresponding to the order code, included in the filtered order information, can be determined as the order code, item code, item weight, item volume, item turnover value, and order address information included in the historical order information. Then, the following information included in the above-mentioned filtered order information—pre-warehouse code, geographical longitude and latitude of the pre-warehouse address, maximum pre-warehouse capacity, average productivity per employee in the warehouse, average productivity per rider, maximum number of employees in the warehouse, maximum number of riders, and the average daily production volume and total average cost per order corresponding to the aforementioned pre-warehouse code—is determined as the following information included in the above-mentioned candidate pre-warehouse information: pre-warehouse code, geographical longitude and latitude of the pre-warehouse address, geographical latitude and latitude of the pre-warehouse address, maximum pre-warehouse capacity, average productivity per employee in the warehouse, average productivity per rider, maximum number of employees in the warehouse, maximum number of riders, average daily production volume, and total average cost per order.

[0055] Step 202: Based on the historical order information set and the aforementioned candidate front warehouse information set, generate a historical order cluster information set, a target candidate front warehouse information set, and a predicted order cluster information set.

[0056] In some embodiments, the aforementioned executing entity can generate a historical order cluster information set, a target candidate front-end warehouse information set, and a predicted order cluster information set based on the aforementioned historical order information set and the aforementioned candidate front-end warehouse information set. The historical order cluster information in the aforementioned historical order cluster information set may include, but is not limited to, at least one of the following: order cluster code, order cluster date, order quantity, and front-end warehouse code set. Here, the aforementioned order cluster code may correspond to multiple front-end warehouse codes. The target candidate front-end warehouse information in the aforementioned target candidate front-end warehouse information set may include, but is not limited to, at least one of the following: front-end warehouse code, geographical longitude of the front-end warehouse address, geographical latitude of the front-end warehouse address, maximum front-end warehouse capacity, average productivity per employee in the warehouse, average productivity per rider, maximum number of employees in the warehouse, maximum number of riders, average daily production volume, average total cost per order, order cluster code set, and the number of order clusters covered by the front-end warehouse. Here, the aforementioned front-end warehouse code may correspond to multiple order cluster codes, and the number of order clusters covered by the front-end warehouse may be the number of order cluster codes in the aforementioned order cluster code set. The predicted order cluster information in the aforementioned predicted order cluster information set may include: average daily item turnover value.

[0057] In practice, the aforementioned historical order information set can be clustered to obtain the aforementioned historical order cluster information set. Then, based on the aforementioned historical order cluster information set, the aforementioned candidate front-end warehouse information set is integrated to obtain the aforementioned target candidate front-end warehouse information set. Finally, prediction is performed on each historical order cluster information in the aforementioned historical order cluster information set to generate the aforementioned predicted order cluster information set. Here, a preset clustering algorithm can be used to cluster the aforementioned historical order information set. A preset prediction algorithm can be used to predict each historical order cluster information in the aforementioned historical order cluster information set.

[0058] As examples, the preset clustering algorithms mentioned above may include, but are not limited to: DBSCAN (Density-Based Spatial Clustering of Applications with Noise), OPTICS (Ordering points to identify the clustering structure), and DENCLUE (Density Clustering). The preset prediction algorithms mentioned above may include, but are not limited to: grey prediction algorithms or Markov prediction algorithms.

[0059] Step 203: Based on the predicted order cluster information set, perform feature extraction processing on each historical order cluster information in the historical order cluster information set to generate feature order cluster information, thus obtaining the feature order cluster information set.

[0060] In some embodiments, the execution entity may perform feature extraction processing on each historical order cluster in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information, thus obtaining a feature order cluster information set. Specifically, based on the predicted order cluster information set, a preset feature extraction model can be used to perform feature extraction processing on each historical order cluster in the historical order cluster information set to generate the feature order cluster information.

[0061] As an example, the aforementioned preset feature extraction model may be, but is not limited to, at least one of the following: ARCH (Autoregressive Conditional Heteroskedasticity) model or SVAR (Structural Vector Autoregression) model.

[0062] In some optional implementations of certain embodiments, the execution entity performs feature extraction processing on each historical order cluster in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information, which may include the following steps:

[0063] The first step is to determine the target predicted order cluster information by combining the predicted order cluster information with the predicted order cluster information corresponding to the historical order cluster information.

[0064] The second step involves performing feature extraction processing on the aforementioned historical order cluster information and the aforementioned target predicted order cluster information, respectively, to obtain historical order cluster feature information and predicted order cluster feature information. Specifically, a preset feature extraction algorithm can be used to perform feature extraction processing on the historical order cluster information and the aforementioned target predicted order cluster information. The aforementioned historical order cluster feature information may include, but is not limited to, at least one of the following: historical coefficient of variation values, historical discontinuity values, historical trend strength values, historical seasonal intensity values, historical stationarity test values, and historical white noise test values. The aforementioned predicted order cluster feature information may include, but is not limited to, at least one of the following: predicted coefficient of variation values, predicted discontinuity values, predicted trend strength values, predicted seasonal intensity values, predicted stationarity test values, and predicted white noise test values.

[0065] As an example, the aforementioned preset feature extraction algorithm can be the TsFresh (time series data feature mining) algorithm.

[0066] The third step, based on the aforementioned historical order cluster characteristic information, is to determine the historical volatility value, historical trend value, and historical predictable value. This can be achieved through the following sub-steps:

[0067] The first sub-step involves determining the sum of the historical coefficient of variation and the historical seasonal intensity value, which are included in the aforementioned historical order cluster feature information, as the aforementioned historical fluctuation value.

[0068] The second sub-step involves determining the historical trend strength value included in the aforementioned historical order cluster feature information as the aforementioned historical trend value.

[0069] The third sub-step involves determining the difference between the historical white noise test value and the historical discontinuity value included in the aforementioned historical order cluster feature information as the historical difference value.

[0070] The fourth sub-step is to determine the difference between the aforementioned historical difference value and the historical stationarity test value included in the aforementioned historical order cluster feature information as the aforementioned historical observable value.

[0071] The fourth step is to determine the predicted fluctuation value, predicted trend value, and predicted predictable value based on the above-mentioned predicted order cluster feature information.

[0072] In practice, determining the predicted volatility value, predicted trend value, and predicted predictable value based on the aforementioned predicted order cluster feature information may include the following sub-steps:

[0073] The first sub-step involves determining the sum of the predicted coefficient of variation and the predicted seasonal intensity value, which are included in the aforementioned predicted order cluster feature information, as the aforementioned predicted volatility value.

[0074] The second sub-step involves determining the predicted trend strength value, which is included in the predicted order cluster feature information, as the predicted trend value.

[0075] The third sub-step involves determining the difference between the predicted white noise test value and the predicted discontinuity value, which are included in the aforementioned predicted order cluster feature information, as the predicted difference value.

[0076] The fourth sub-step is to determine the difference between the predicted difference value and the predicted stationarity test value included in the predicted order cluster feature information as the predicted observable value.

[0077] Fifth step: Based on the above historical fluctuation values, historical trend values, historical predictable values, predicted fluctuation values, predicted trend values, and predicted predictable values, determine the fluctuation value, predicted trend value, and predicted predictable value of the characteristic order cluster.

[0078] Based on the aforementioned historical fluctuation values, historical trend values, historical predictable values, predicted fluctuation values, predicted trend values, and predicted predictable values, the fluctuation values, predicted trend values, and predicted predictable values ​​of the characteristic order clusters can be determined through the following sub-steps:

[0079] The first sub-step is to determine the average of the above-mentioned historical volatility values ​​and the above-mentioned predicted volatility values ​​as the volatility value of the above-mentioned characteristic order cluster.

[0080] The second sub-step is to determine the average of the above historical trend values ​​and the above predicted trend values ​​as the trend value of the above characteristic order cluster.

[0081] The third sub-step is to determine the average of the above-mentioned historical predictable values ​​and the above-mentioned predicted predictable values ​​as the above-mentioned characteristic order cluster predictable values.

[0082] Step 6: The fluctuation value, predicted trend value, and predictable value of the aforementioned characteristic order clusters are fused to obtain the characteristic order cluster information. Specifically, the fluctuation value, predicted trend value, and predictable value of the aforementioned characteristic order clusters can be defined as the characteristic order cluster fluctuation value, predicted trend value, and predictable value included in the characteristic order cluster information.

[0083] Step 204: Generate the front warehouse address information based on the target candidate front warehouse information set, the predicted order cluster information set, and the feature order cluster information set.

[0084] In some embodiments, the executing entity can generate front-end warehouse address information based on the target candidate front-end warehouse information set, the predicted order cluster information set, and the feature order cluster information set. The front-end warehouse address information includes a front-end warehouse code set, an order cluster code set, the number of front-end warehouse personnel, and the number of front-end warehouse riders. This front-end warehouse address information can be generated using a preset location selection model.

[0085] As an example, the above-mentioned preset location model may be, but is not limited to, at least one of the following: coverage model, maximum coverage model, p-cernter Problem model, p-dispersion Problem model, or p-median Problem model.

[0086] In some optional implementations of certain embodiments, generating the pre-warehouse address information based on the target candidate pre-warehouse information set, the predicted order cluster information set, and the feature order cluster information set may include the following steps:

[0087] The first step, based on the aforementioned target candidate front-end warehouse information set, the preset maximum number of front-end warehouses to be built, and the preset order fulfillment rate, generates front-end warehouse coverage constraint information. The preset order fulfillment rate represents the ratio of orders that a front-end warehouse can fulfill to the total number of orders. The preset maximum number of front-end warehouses to be built represents the maximum number of front-end warehouses that can be built. The aforementioned front-end warehouse coverage constraint information can be defined by the following formula:

[0088]

[0089] Where I represents the front warehouse code set, which consists of the front warehouse codes included in the target candidate front warehouse information set. i represents the front warehouse sequence number. K represents the order cluster code set, which consists of the order cluster codes included in the target candidate front warehouse information set. j represents the order cluster sequence number. x represents the front warehouse delivery value, which can characterize whether the front warehouse needs to deliver the order cluster. i，j This represents the delivery value of the front warehouse corresponding to the j-th order cluster included in the i-th front warehouse, when x i，j When x is 1, it means that the first front warehouse needs the j-th order cluster. i，j A value of 0 indicates that the i-th front-end warehouse does not need to deliver the j-th order cluster. y represents the selected front-end warehouse value; when y is 1, the front-end warehouse is selected; when y is 0, the front-end warehouse is not selected. i This represents the selected value of the front warehouse corresponding to the i-th front warehouse, when y i When y is 1, it means that the j-th front-end warehouse is selected; when y is 1, it means that the j-th front-end warehouse is selected. i A value of 0 indicates that the i-th front warehouse is not selected. N represents the maximum number of front warehouses that can be built as preset. λ1 represents the preset order fulfillment rate as preset. m represents the number of order clusters covered by the front warehouses included in the target candidate front warehouse information set. i This represents the number of order clusters covered by the i-th front warehouse. When a is 1, it means the front warehouse corresponds to an order cluster; when a is 0, it means the front warehouse does not correspond to an order cluster. i，j When a is 1, it indicates that the i-th forward warehouse corresponds to the j-th order cluster. i，j When the value is 0, it means that the i-th forward warehouse does not correspond to the j-th order cluster.

[0090] As an example, the maximum number of pre-positioned warehouses that can be built, as preset above, can be 3. The order fulfillment rate that can be preset above is 0.9.

[0091] The second step involves generating front-end warehouse capacity constraint information based on the aforementioned target candidate front-end warehouse information set and the aforementioned predicted order cluster information set. This front-end warehouse capacity constraint information can be defined using the following formula:

[0092]

[0093] Where c represents the average daily item turnover value included in the predicted order cluster information set mentioned above. j This represents the average daily item turnover value corresponding to the j-th order cluster. cmax represents the upper limit of the front warehouse capacity included in the target candidate front warehouse information set mentioned above. iRepresents the upper limit value of the pre - warehouse capacity of the \(i\) - th pre - warehouse. \(s\) represents the number of pre - warehouse employees. \(s\) i Represents the number of pre - warehouse employees corresponding to the \(i\) - th pre - warehouse. \(se_{fa}\) represents the per - capita production capacity of employees in the warehouse included in the target candidate pre - warehouse information in the above - mentioned target candidate pre - warehouse information set. \(se_{ff}\) i Represents the per - capita production capacity of employees in the warehouse corresponding to the \(i\) - th pre - warehouse. \(s_{max}\) represents the upper limit value of the number of employees in the warehouse included in the target candidate pre - warehouse information in the above - mentioned target candidate pre - warehouse information set. \(s_{max}\) i Represents the upper limit value of the number of employees in the warehouse corresponding to the \(i\) - th pre - warehouse. \(q\) represents the number of pre - warehouse riders. \(q\) i Represents the number of pre - warehouse riders corresponding to the \(i\) - th pre - warehouse. \(q_{ef}\) represents the per - capita production capacity of riders included in the target candidate pre - warehouse information in the above - mentioned target candidate pre - warehouse information set. \(q_{ef}\) i Represents the per - capita production capacity of riders corresponding to the \(i\) - th pre - warehouse. \(q_{max}\) represents the upper limit value of the number of riders included in the target candidate pre - warehouse information in the above - mentioned target candidate pre - warehouse information set. \(q_{max}\) i Represents the upper limit value of the number of riders corresponding to the \(i\) - th pre - warehouse.

[0094] Step 3: Based on the above - mentioned target candidate pre - warehouse information set and the preset distance adjustment coefficient, generate pre - warehouse distribution range constraint information. Among them, the following formula can be determined as the above - mentioned pre - warehouse distribution range constraint information:

[0095]

[0096] Among them, \(d\) represents the pre - warehouse order cluster distance value in the pre - warehouse order cluster distance value set included in the target candidate pre - warehouse information in the above - mentioned target candidate pre - warehouse information set. \(d\) i，j Represents the pre - warehouse order cluster distance value between the \(i\) - th pre - warehouse and the \(j\) - th order cluster. \(m_d\) represents the minimum distribution radius value. \(m_d\) i Represents the minimum distribution radius value corresponding to the \(i\) - th pre - warehouse. \(\lambda_2\) represents the above - mentioned preset distance adjustment coefficient.

[0097] As an example, the above - mentioned preset distance adjustment coefficient can be 0.3.

[0098] Step 4: Based on the above - mentioned characteristic order cluster information set, the above - mentioned pre - warehouse coverage range constraint information, the above - mentioned pre - warehouse production capacity constraint information, the above - mentioned pre - warehouse distribution range constraint information, the preset weight coefficient set and the preset pre - warehouse address constraint information, determine the above - mentioned pre - warehouse address information. The above - mentioned preset pre - warehouse address constraint information can be the following formula:

[0099]

[0100] First, the target optimization function and the target forward warehouse delivery value included in the aforementioned forward warehouse address information can be determined using the following formula:

[0101]

[0102] Where A represents the first objective optimization sub-function. cost represents the total average cost per unit included in the aforementioned candidate front-end warehouse information set. i Let BB represent the total average cost per order corresponding to the i-th front-end warehouse. Let w represent the weight coefficients in the aforementioned preset weight coefficient set. w1 represents the first weight coefficient in the aforementioned preset weight coefficient set. w2 represents the second weight coefficient in the aforementioned preset weight coefficient set. w3 represents the third weight coefficient in the aforementioned preset weight coefficient set. w4 represents the fourth weight coefficient in the aforementioned preset weight coefficient set. w5 represents the fifth weight coefficient in the aforementioned preset weight coefficient set. Let C represent the third objective optimization sub-function. let st represent the fluctuation value of the feature order cluster included in the feature order cluster information set. j This represents the fluctuation value of the feature order cluster corresponding to the j-th order cluster. `tr` represents the trend value of the feature order clusters included in the feature order cluster information set mentioned above. j This represents the trend value of the feature order cluster corresponding to the j-th order cluster. fr represents the predictable value of the feature order clusters included in the feature order cluster information set mentioned above. j Let z represent the predictable value of the feature order cluster corresponding to the j-th order cluster. z represents the objective optimization function mentioned above. This indicates the target forward warehouse delivery value included in the aforementioned forward warehouse address information. `argmin` represents the minimum value function, which can be used to determine the independent variable value that minimizes the aforementioned objective optimization function. Here, the values ​​of each weight coefficient in the aforementioned weight coefficient set are not limited.

[0103] Then, the target front warehouse selected value, the target front warehouse employee number set, and the target front warehouse rider number set can be determined by using the aforementioned front warehouse coverage constraint information, the aforementioned front warehouse capacity constraint information, the aforementioned front warehouse delivery range constraint information, and the various formulas included in the pre-set front warehouse address constraint information system.

[0104] Optionally, the aforementioned implementing entity may also send the aforementioned forward warehouse address information to the display terminal for staff to select the forward warehouse address.

[0105] The above embodiments of this disclosure have the following beneficial effects: the method for generating front warehouse address information according to some embodiments of this disclosure can improve the accuracy of generating front warehouse address information. Specifically, the reason for the reduced accuracy of generating front warehouse address information is that only the item turnover value of candidate front warehouse address information is predicted, without considering the historical item turnover value and future changes in user demand corresponding to the candidate front warehouse address information. Based on this, the method for generating front warehouse address information according to some embodiments of this disclosure first obtains a historical order information set and a candidate front warehouse information set. Second, based on the above historical order information set and the above candidate front warehouse information set, a historical order cluster information set, a target candidate front warehouse information set, and a predicted order cluster information set are generated. Thus, the obtained historical order cluster information set can represent the historical item turnover value corresponding to the candidate front warehouse address information, the predicted order cluster information set can represent the future changes in user demand corresponding to the candidate front warehouse address information, and the target candidate front warehouse information set can represent the front warehouse address information of each candidate. Then, based on the aforementioned predicted order cluster information set, feature extraction processing is performed on each historical order cluster information in the aforementioned historical order cluster information set to generate feature order cluster information, thus obtaining a feature order cluster information set. Therefore, by combining the historical item turnover values ​​corresponding to the candidate front-end warehouse address information and future changes in user demand, a feature order cluster information set that can characterize the order cluster features can be obtained. Finally, based on the aforementioned target candidate front-end warehouse information set, the aforementioned predicted order cluster information set, and the aforementioned feature order cluster information set, front-end warehouse address information is generated. Thus, front-end warehouse address information can be selected from the target candidate front-end warehouse information set. Therefore, the front-end warehouse address information generation method of this disclosure, by combining the predicted order cluster information and the historical order cluster information to obtain feature order cluster information, considers historical item turnover values ​​and future changes in user demand, and can improve the accuracy of generating front-end warehouse address information.

[0106] Further reference Figure 3 , Figure 3 A flow 300 of another embodiment of the pre-positioning warehouse address information generation method according to the present disclosure is shown. This pre-positioning warehouse address information generation method includes the following steps:

[0107] Step 301: Obtain the historical order information set and the candidate forward warehouse information set.

[0108] In some embodiments, the specific implementation of step 301 and its resulting technical effects can be found in [reference needed]. Figure 2 Step 201 in the corresponding embodiment will not be repeated here.

[0109] Step 302: Cluster the historical order information set to obtain the historical order cluster information set.

[0110] In some embodiments, the execution entity of the pre-warehouse address information generation method (e.g., Figure 1 The electronic device 101 shown can perform clustering processing on the above-mentioned historical order information set to obtain a historical order cluster information set.

[0111] In some optional implementations of certain embodiments, the above-mentioned clustering process of the historical order information set to obtain a historical order cluster information set may include the following steps:

[0112] The first step involves matching the order address information of every two historical order records in the aforementioned historical order information set to generate an address matching result set. This can be achieved using a pre-defined address matching algorithm. The address matching result can be either "address match" or "address mismatch".

[0113] As an example, the aforementioned preset address matching algorithm can be a regular expression matching algorithm.

[0114] The second step involves integrating the aforementioned address matching result set with the historical order information set to obtain a matching historical order information set. Specifically, for each historical order in the historical order information set, the aforementioned historical order and all historical orders in the set whose address matching result is "address match" are merged into an initial matching historical order information set. This initial matching historical order information set is then deduplicated to obtain the final matching historical order information set.

[0115] The third step is to perform clustering processing on the aforementioned set of matched historical order information to obtain the aforementioned set of historical order cluster information. This clustering processing can be performed using a preset order clustering algorithm. The historical order cluster information in the aforementioned set of historical order cluster information may include: order cluster codes.

[0116] As an example, the preset order clustering algorithm mentioned above can be the k-means clustering algorithm. The information of each historical order cluster in the historical order cluster information set can be the cluster center information of each cluster obtained by the k-means clustering algorithm.

[0117] Step 303: Based on the historical order cluster information set, update the information of each candidate front warehouse in the candidate front warehouse information set to obtain the target candidate front warehouse information set.

[0118] In some embodiments, the executing entity may update the candidate front-end warehouse information in the candidate front-end warehouse information set based on the historical order cluster information set to obtain the target candidate front-end warehouse information set. Specifically, this can be achieved by determining the correspondence between the front-end warehouse coverage area included in the candidate front-end warehouse information and the order cluster address information included in each historical order cluster information in the historical order cluster information set; determining the correspondence between the front-end warehouse codes included in the candidate front-end warehouse information and the order cluster codes included in each historical order cluster information in the historical order cluster information set; then, determining each order cluster code corresponding to the front-end warehouse code as an order cluster code set and adding it to the candidate front-end warehouse information in the candidate front-end warehouse information set; and determining the number of order cluster codes in the order cluster code set as the number of order clusters covered by the front-end warehouse and adding it to the candidate front-end warehouse information in the candidate front-end warehouse information set, thus obtaining the target candidate front-end warehouse information set.

[0119] As an example, the coverage area of ​​the aforementioned forward warehouse can be referenced. Figure 4 The diagram illustrates the coverage area 400 of the front warehouses according to the front warehouse address information generation method of this disclosure. The front warehouses corresponding to the candidate front warehouse information in the aforementioned candidate front warehouse information set can be referenced. Figure 4 The front-end warehouse 401 or front-end warehouse 402. Figure 4 The circle corresponding to the front warehouse 401 can represent the coverage area of ​​the front warehouse 401. Figure 4 The circle corresponding to front warehouse 402 represents the coverage area of ​​the front warehouse 402. The order cluster sets corresponding to each order cluster code in the historical order cluster information set can be referenced. Figure 4 The front warehouse 401 includes order clusters 4011 and 4012, or the front warehouse 402 includes order clusters 4021 or 4022. For example, the value "321" in order cluster 4011 can indicate that the number of order clusters included in order cluster 4011 is 321.

[0120] Step 304: Generate predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set, and obtain the predicted order cluster information set.

[0121] In some embodiments, the execution entity may generate predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set, thereby obtaining a predicted order cluster information set.

[0122] In some optional implementations of certain embodiments, generating the predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set, to obtain the predicted order cluster information set, may include the following steps:

[0123] The first step is to split the aforementioned historical order cluster information to obtain historical order cluster trend information and historical order cluster remainder information. This splitting can be performed using a preset splitting algorithm.

[0124] As an example, the preset splitting algorithm mentioned above can be an STL (Seasonal and Trend decomposition using Loess) algorithm. The historical order cluster trend information mentioned above may include, but is not limited to, at least one of the following: order cluster address information, the item turnover value of the historical order cluster in the past month, and the average item turnover value of the historical order cluster in the past three months. The remaining information of the historical order cluster may include, but is not limited to, at least one of the following: the month in which the historical order cluster is located, the quarter in which the historical order cluster is located, and the item turnover value of the historical order cluster in the past month.

[0125] The second step is to generate a predicted order cluster trend value sequence based on the aforementioned historical order cluster trend information. This can be achieved using a pre-defined trend value generation model.

[0126] As an example, the preset trend value generation model mentioned above can be a linear regression model.

[0127] The third step is to generate a predicted sequence of order cluster remainder values ​​based on the aforementioned historical order cluster trend information. This can be achieved using a pre-defined remainder value generation model.

[0128] As an example, the preset residual value generation calculation model mentioned above can be the XGB (eXtreme Gradient Boosting) model.

[0129] Fourth step: For each predicted order cluster trend value in the above predicted order cluster trend value sequence, the sum of the predicted order cluster remainder value corresponding to the above predicted order cluster trend value and the above predicted order cluster trend value in the above predicted order cluster remainder value sequence is determined as the predicted order cluster item flow value, thus obtaining the predicted order cluster item flow value sequence.

[0130] Fifth, based on the predicted order cluster item flow value sequence, generate the predicted order cluster information. Specifically, the order cluster code, order cluster date, and predicted order cluster item flow value sequence included in the historical order cluster information can be determined as the order cluster number, order cluster date, and predicted order cluster item flow value sequence included in the predicted order cluster information.

[0131] Step 305: Based on the predicted order cluster information set, perform feature extraction processing on each historical order cluster information in the historical order cluster information set to generate feature order cluster information, thus obtaining the feature order cluster information set.

[0132] In some embodiments, the execution entity may perform feature extraction processing on each historical order cluster information in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information, thereby obtaining a feature order cluster information set.

[0133] Step 306: Generate the front warehouse address information based on the target candidate front warehouse information set, the predicted order cluster information set, and the feature order cluster information set.

[0134] In some embodiments, the execution entity may generate front warehouse address information based on the target candidate front warehouse information set, the predicted order cluster information set, and the feature order cluster information set.

[0135] from Figure 3 It can be seen from this that, with Figure 2 Compared to the description of some corresponding embodiments, Figure 3 The flowchart 300 of the pre-position warehouse address information generation method in some corresponding embodiments further emphasizes the specific steps of generating the historical order cluster information set, the target candidate pre-position warehouse information set, and the predicted order cluster information set. Therefore, the schemes described in these embodiments can centralize information that characterizes order features through clustering and prediction methods, thereby determining the orders that can be delivered by the pre-position warehouse and improving the customer acquisition capacity of the pre-position warehouse after its construction.

[0136] Further reference Figure 5 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a pre-position warehouse address information generation device, which are similar to... Figure 3 Corresponding to the method embodiments shown, this front warehouse address information generation device can be specifically applied to various electronic devices.

[0137] like Figure 5As shown, a pre-position warehouse address information generation device 500 in some embodiments includes: an acquisition unit 501, a first generation unit 502, a feature extraction unit 503, and a second generation unit 504. The acquisition unit 501 is configured to acquire a historical order information set and a candidate pre-position warehouse information set; the first generation unit 502 is configured to generate a target candidate pre-position warehouse information set and a predicted order cluster information set based on the historical order information set and the candidate pre-position warehouse information set; the feature extraction unit 503 is configured to perform feature extraction processing on each historical order cluster information in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information; and the second generation unit 504 is configured to generate pre-position warehouse address information based on the target candidate pre-position warehouse information set, the predicted order cluster information set, and the feature order cluster information set.

[0138] Optionally, the aforementioned pre-position warehouse address information generation device further includes: a sending unit configured to send the aforementioned pre-position warehouse address information to a display terminal for staff to select a pre-position warehouse address.

[0139] Optionally, the acquisition unit 501 is further configured to: acquire the full set of order information; perform filtering processing on the full set of order information to obtain a filtered set of order information; and integrate each filtered order information in the filtered set of order information to generate historical order information and candidate front warehouse information, thereby obtaining the historical order information set and the candidate front warehouse information set.

[0140] Optionally, the first generation unit 502 is further configured to: perform clustering processing on the historical order information set to obtain the historical order cluster information set; based on the historical order cluster information set, update the information of each candidate front warehouse in the candidate front warehouse information set to obtain the target candidate front warehouse information set; and generate predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set to obtain the predicted order cluster information set.

[0141] Optionally, the historical order information in the aforementioned historical order information set includes: order address information; and the aforementioned first generation unit 502 is further configured to: perform matching processing on the order address information included in every two historical order information in the aforementioned historical order information set to generate address matching results, thereby obtaining an address matching result set; based on the aforementioned address matching result set, perform integration processing on the aforementioned historical order information set to obtain a matched historical order information set; and perform clustering processing on the aforementioned matched historical order information set to obtain the aforementioned historical order cluster information set.

[0142] Optionally, the first generation unit 502 is further configured to: split the historical order cluster information to obtain historical order cluster trend information and historical order cluster remainder information; generate a predicted order cluster trend value sequence based on the historical order cluster trend information; generate a predicted order cluster remainder value sequence based on the historical order cluster trend information; for each predicted order cluster trend value in the predicted order cluster trend value sequence, determine the predicted order cluster item circulation value by summing the predicted order cluster remainder value corresponding to the predicted order cluster trend value and the predicted order cluster trend value in the predicted order cluster remainder value sequence, thereby obtaining a predicted order cluster item circulation value sequence; and generate the predicted order cluster information based on the predicted order cluster item circulation value sequence.

[0143] Optionally, the feature extraction unit 503 is further configured to: determine the predicted order cluster information corresponding to the historical order cluster information in the predicted order cluster information set as the target predicted order cluster information; perform feature extraction processing on the historical order cluster information and the target predicted order cluster information respectively to obtain historical order cluster feature information and predicted order cluster feature information; determine historical fluctuation value, historical trend value, and historical predictable value based on the historical order cluster feature information; determine predicted fluctuation value, predicted trend value, and predicted predictable value based on the predicted order cluster feature information; determine feature order cluster fluctuation value, feature order cluster predicted trend value, and feature order cluster predicted predictable value based on the historical fluctuation value, the historical trend value, the historical predictable value, the predicted fluctuation value, the predicted trend value, and the predicted predictable value; and perform fusion processing on the feature order cluster fluctuation value, the feature order cluster predicted trend value, and the feature order cluster predicted predictable value to obtain the feature order cluster information.

[0144] Optionally, the second generation unit 504 is further configured to: generate front warehouse coverage constraint information based on the target candidate front warehouse information set, the preset maximum number of front warehouses to be built, and the preset order fulfillment rate; generate front warehouse capacity constraint information based on the target candidate front warehouse information set and the predicted order cluster information set; generate front warehouse delivery range constraint information based on the target candidate front warehouse information set and the preset distance adjustment coefficient; and determine the front warehouse address information based on the feature order cluster information set, the front warehouse coverage constraint information, the front warehouse capacity constraint information, the front warehouse delivery range constraint information, and the preset front warehouse address constraint information.

[0145] It is understandable that the units recorded in the pre-positioning warehouse address information generation device 500 are related to the reference. Figure 3The steps in the described method for generating pre-position warehouse address information correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method for generating pre-position warehouse address information also apply to the pre-position warehouse address information generation device 500 and the units contained therein, and will not be repeated here.

[0146] The following is for reference. Figure 6 This document illustrates a structural schematic of an electronic device 600 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The terminal device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0147] like Figure 6 As shown, electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of electronic device 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0148] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 6 Each box shown can represent a device or multiple devices as needed.

[0149] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0150] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0151] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0152] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire a set of historical order information and a set of candidate pre-positioning warehouse information; based on the aforementioned historical order information set and the aforementioned candidate pre-positioning warehouse information set, generate a set of historical order cluster information, a set of target candidate pre-positioning warehouse information, and a set of predicted order cluster information; based on the aforementioned predicted order cluster information set, perform feature extraction processing on each historical order cluster information in the aforementioned historical order cluster information set to generate feature order cluster information, thus obtaining a set of feature order cluster information; and based on the aforementioned target candidate pre-positioning warehouse information set, the aforementioned predicted order cluster information set, and the aforementioned feature order cluster information set, generate pre-positioning warehouse address information.

[0153] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0154] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0155] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an acquisition unit, a first generation unit, a feature extraction unit, and a second generation unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit may also be described as "a unit that acquires a set of historical order information and a set of candidate pre-positioned warehouse information."

[0156] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0157] Some embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements any of the above-described methods for generating front-end address information.

[0158] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for generating pre-positioned warehouse address information, comprising: Obtain historical order information set and candidate forward warehouse information set; Based on the historical order information set and the candidate front warehouse information set, a historical order cluster information set, a target candidate front warehouse information set, and a predicted order cluster information set are generated. Based on the predicted order cluster information set, feature extraction processing is performed on each historical order cluster information in the historical order cluster information set to generate feature order cluster information, thus obtaining the feature order cluster information set. Based on the target candidate front warehouse information set, the predicted order cluster information set, and the feature order cluster information set, front warehouse address information is generated, including: generating front warehouse coverage constraint information based on the target candidate front warehouse information set, a preset maximum number of front warehouses to be built, and a preset order fulfillment rate; generating front warehouse capacity constraint information based on the target candidate front warehouse information set and the predicted order cluster information set; generating front warehouse delivery range constraint information based on the target candidate front warehouse information set and a preset distance adjustment coefficient; and determining the front warehouse address information based on the feature order cluster information set, the front warehouse coverage constraint information, the front warehouse capacity constraint information, the front warehouse delivery range constraint information, a preset weight coefficient set, and a preset front warehouse address constraint information.

2. The method according to claim 1, wherein, The method further includes: The forward warehouse address information is sent to the display terminal so that staff can select the forward warehouse address.

3. The method according to claim 1, wherein, The acquisition of the historical order information set and the candidate pre-positioning warehouse information set includes: Obtain the complete order information set; The full set of order information is filtered to obtain a filtered set of order information; Each filtered order information in the filtered order information set is integrated and processed to generate historical order information and candidate front warehouse information, thus obtaining the historical order information set and the candidate front warehouse information set.

4. The method according to claim 1, wherein, The step of generating a historical order cluster information set, a target candidate front-end warehouse information set, and a predicted order cluster information set based on the historical order information set and the candidate front-end warehouse information set includes: The historical order information set is clustered to obtain the historical order cluster information set; Based on the historical order cluster information set, the information of each candidate front warehouse in the candidate front warehouse information set is updated to obtain the target candidate front warehouse information set; Generate predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set, and obtain the predicted order cluster information set.

5. The method according to claim 4, wherein, The historical order information in the historical order information set includes: order address information; and The process of clustering the historical order information set to obtain the historical order cluster information set includes: The order address information included in every two historical order information in the historical order information set is matched to generate an address matching result set. Based on the address matching result set, the historical order information set is integrated and processed to obtain the matching historical order information set; The historical order information set is clustered to obtain the historical order cluster information set.

6. The method according to claim 4, wherein, The generation of predicted order cluster information corresponding to each historical order cluster information in the historical order cluster information set includes: The historical order cluster information is split to obtain historical order cluster trend information and historical order cluster remaining information; Based on the historical order cluster trend information, a sequence of predicted order cluster trend values ​​is generated; Based on the historical order cluster trend information, a sequence of predicted order cluster remainder values ​​is generated; For each predicted order cluster trend value in the predicted order cluster trend value sequence, the sum of the predicted order cluster remainder value corresponding to the predicted order cluster trend value and the predicted order cluster trend value in the predicted order cluster remainder value sequence is determined as the predicted order cluster item flow value, thus obtaining the predicted order cluster item flow value sequence; Based on the predicted order cluster item flow value sequence, the predicted order cluster information is generated.

7. The method according to claim 1, wherein, The step of performing feature extraction processing on each historical order cluster in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information includes: The predicted order cluster information that corresponds to the historical order cluster information in the predicted order cluster information set is determined as the target predicted order cluster information; Feature extraction processing is performed on the historical order cluster information and the target predicted order cluster information respectively to obtain historical order cluster feature information and predicted order cluster feature information; Based on the historical order cluster feature information, historical fluctuation values, historical trend values, and historical predictable values ​​are determined; Based on the predicted order cluster feature information, the predicted fluctuation value, predicted trend value, and predicted predictable value are determined; Based on the historical fluctuation value, the historical trend value, the historical predictable value, the predicted fluctuation value, the predicted trend value, and the predicted predictable value, the fluctuation value of the characteristic order cluster, the predicted trend value of the characteristic order cluster, and the predicted predictable value of the characteristic order cluster are determined. The fluctuation value, predicted trend value, and predictable value of the feature order cluster are fused to obtain the feature order cluster information.

8. A device for generating pre-positioned warehouse address information, comprising: The acquisition unit is configured to acquire a set of historical order information and a set of candidate forward warehouse information. The first generation unit is configured to generate a historical order cluster information set, a target candidate front warehouse information set, and a predicted order cluster information set based on the historical order information set and the candidate front warehouse information set. The feature extraction unit is configured to perform feature extraction processing on each historical order cluster information in the historical order cluster information set based on the predicted order cluster information set to generate feature order cluster information, thereby obtaining the feature order cluster information set. The second generation unit is configured to generate front-end warehouse address information based on the target candidate front-end warehouse information set, the predicted order cluster information set, and the feature order cluster information set. This includes: generating front-end warehouse coverage constraint information based on the target candidate front-end warehouse information set, a preset maximum number of front-end warehouses to be built, and a preset order fulfillment rate; generating front-end warehouse capacity constraint information based on the target candidate front-end warehouse information set and the predicted order cluster information set; generating front-end warehouse delivery range constraint information based on the target candidate front-end warehouse information set and a preset distance adjustment coefficient; and determining the front-end warehouse address information based on the feature order cluster information set, the front-end warehouse coverage constraint information, the front-end warehouse capacity constraint information, the front-end warehouse delivery range constraint information, a preset weight coefficient set, and a preset front-end warehouse address constraint information.

9. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

11. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images