Replenishment duration information generation method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a replenishment duration information generation method and device, equipment, a medium and a program product. One specific embodiment of the method comprises the following steps: determining item circulation time period type information corresponding to a target item on a target date; determining a target replenishment time length information generation model corresponding to the target article according to the article circulation time period type information; and generating replenishment duration information corresponding to the target article according to the target replenishment duration information generation model and the article information corresponding to the target article. The implementation mode is related to an intelligent supply chain, and the accuracy of the determined replenishment duration is improved, so that the article loss can be reduced, and the transportation resources are saved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of intelligent supply chain technology, and in particular to a method, device, equipment, medium, and program product for generating replenishment duration information. Background Art

[0002] The replenishment timeliness (i.e., the time it takes for suppliers to deliver goods to warehouses during the replenishment process) is closely related to the stability of the supply chain. At present, the commonly used method for predicting replenishment time is: predicting replenishment time based on statistical or machine learning models. For example, the replenishment time is determined based on the mean, median, etc. of each historical replenishment time over a period of time. Or based on each historical replenishment time over a period of time, model training is performed to obtain a trained machine learning model for predicting replenishment time.

[0003] However, the inventors have found that when the above method is used to predict the replenishment time, the following technical problems often occur:

[0004] The replenishment time in different historical time periods fluctuates greatly (for example, the replenishment time in regular time periods and promotional time periods is quite different), but the historical time periods are not distinguished. The replenishment time is only predicted based on the historical replenishment time within a period of time, resulting in low accuracy of the predicted replenishment time, which in turn leads to low accuracy of the subsequent predicted replenishment quantity. When the replenishment quantity is large, there is a large backlog of items, resulting in more item losses, and when the replenishment quantity is small, the items are out of stock and need to be dispatched again, resulting in a waste of transportation resources.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0006] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0007] Some embodiments of the present disclosure propose a method, device, electronic device, computer-readable medium, and computer program product for generating replenishment duration information to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a method for generating replenishment duration information, the method comprising: determining item circulation period type information corresponding to a target item on a target date; determining a target replenishment duration information generation model corresponding to the target item based on the item circulation period type information; and generating replenishment duration information corresponding to the target item based on the target replenishment duration information generation model and item information corresponding to the target item.

[0009] Optionally, the above-mentioned determination of the item circulation period type information corresponding to the target item on the target date includes: determining at least one historical date corresponding to the above-mentioned target date; and determining the item circulation period type information corresponding to the above-mentioned target item on the above-mentioned target date based on the above-mentioned at least one historical date.

[0010] Optionally, the above-mentioned determining the item circulation time period type information corresponding to the above-mentioned target item on the above-mentioned target date based on the above-mentioned at least one historical date includes: performing anomaly detection on the historical concentrated circulation date sequence corresponding to the above-mentioned target item to obtain a historical abnormal concentrated circulation date information set; determining each item circulation time period type corresponding to each historical date in the above-mentioned at least one historical date based on the above-mentioned historical abnormal concentrated circulation date information set; determining the target item circulation time period type information corresponding to the above-mentioned target item on the above-mentioned target date based on each item circulation time period type corresponding to each historical date in the above-mentioned at least one historical date.

[0011] Optionally, the target replenishment duration information generation model is obtained through the following training steps: obtaining a historical concentrated circulation information set, wherein each historical concentrated circulation information in the historical concentrated circulation information set includes circulation channel information, and the historical concentrated circulation information set corresponds to the same item circulation period type; grouping each historical concentrated circulation information according to the circulation channel information included in each historical concentrated circulation information in the historical concentrated circulation information set to obtain a historical concentrated circulation information group set; for each historical concentrated circulation information group in the historical concentrated circulation information group set, generating a replenishment duration information generation model according to the historical concentrated circulation information group; according to each channel priority corresponding to each historical concentrated circulation information group in the historical concentrated circulation information group set, selecting a replenishment duration information generation model that meets a preset channel priority condition from the determined replenishment duration information generation models as the target replenishment duration information generation model.

[0012] Optionally, generating a replenishment time information generation model based on the historical concentrated circulation information group includes: training an initial model based on the historical concentrated circulation information group and a preset quantile loss function set to obtain a replenishment time information generation model set corresponding to the historical concentrated circulation information group; determining each accuracy information corresponding to each replenishment time information generation model in the replenishment time information generation model set; and screening out a replenishment time information generation model that meets a preset accuracy condition from the replenishment time information generation model set based on the determined accuracy information.

[0013] Optionally, the method further includes: generating replenishment quantity information corresponding to the above-mentioned target item according to the above-mentioned replenishment duration information.

[0014] Optionally, the method further includes: controlling the associated replenishment equipment to perform a replenishment operation corresponding to the target item according to the replenishment quantity information.

[0015] In a second aspect, some embodiments of the present disclosure provide a replenishment duration information generating device, the device comprising: a first determination unit, configured to determine the item circulation period type information corresponding to the target item on the target date; a second determination unit, configured to determine a target replenishment duration information generating model corresponding to the target item based on the item circulation period type information; a generating unit, configured to generate the replenishment duration information corresponding to the target item based on the target replenishment duration information generating model and the item information corresponding to the target item.

[0016] Optionally, the first determination unit is further configured to: determine at least one historical date corresponding to the target date; and determine, based on the at least one historical date, item circulation period type information of the target item corresponding to the target date.

[0017] Optionally, the first determination unit is further configured to: perform anomaly detection on the historical concentrated circulation date sequence corresponding to the target item to obtain a historical abnormal concentrated circulation date information set; determine the type of each item circulation period corresponding to each historical date in the at least one historical date based on the historical abnormal concentrated circulation date information set; determine the target item circulation period type information corresponding to the target item on the target date based on the type of each item circulation period corresponding to each historical date in the at least one historical date.

[0018] Optionally, the target replenishment duration information generation model is obtained through the following training steps: obtaining a historical concentrated circulation information set, wherein each historical concentrated circulation information in the historical concentrated circulation information set includes circulation channel information, and the historical concentrated circulation information set corresponds to the same item circulation period type; grouping each historical concentrated circulation information according to the circulation channel information included in each historical concentrated circulation information in the historical concentrated circulation information set to obtain a historical concentrated circulation information group set; for each historical concentrated circulation information group in the historical concentrated circulation information group set, generating a replenishment duration information generation model according to the historical concentrated circulation information group; according to each channel priority corresponding to each historical concentrated circulation information group in the historical concentrated circulation information group set, selecting a replenishment duration information generation model that meets a preset channel priority condition from the determined replenishment duration information generation models as the target replenishment duration information generation model.

[0019] Optionally, the second determination unit is further configured to: train the initial model according to the historical concentrated circulation information group and the preset quantile loss function set to obtain a replenishment time information generation model set corresponding to the historical concentrated circulation information group; determine each accuracy information corresponding to each replenishment time information generation model in the replenishment time information generation model set; and screen out a replenishment time information generation model that meets the preset accuracy condition from the replenishment time information generation model set according to the determined accuracy information.

[0020] Optionally, the replenishment duration information generating device further includes: a replenishment quantity information generating unit configured to generate replenishment quantity information corresponding to the target item according to the replenishment duration information.

[0021] Optionally, the replenishment duration information generating device further includes: a control unit configured to control the associated replenishment equipment to perform a replenishment operation corresponding to the target item according to the replenishment quantity information.

[0022] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and 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 implementation manner of the above-mentioned first aspect.

[0023] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0024] In a fifth aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which implements the method described in any implementation manner of the above-mentioned first aspect when executed by a processor.

[0025] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the replenishment duration determined by the replenishment duration information generation method of some embodiments of the present disclosure is more accurate, thereby reducing the loss of items and saving transportation resources. Specifically, the reason for the waste of item loss and transportation resources is that the volatility of the replenishment duration in different historical periods is large (for example, the replenishment duration in the regular period and the promotion period is large), and the historical periods are not distinguished. The replenishment duration is only predicted by each historical replenishment duration in a period of time, resulting in a low accuracy of the predicted replenishment duration, which leads to a low accuracy of the subsequent predicted replenishment quantity, and then when the obtained replenishment quantity is large, the items are piled up more, resulting in more item loss, and when the obtained replenishment quantity is small, the items are out of stock and need to be dispatched again, resulting in a waste of transportation resources. Based on this, the replenishment duration information generation method of some embodiments of the present disclosure first determines the item circulation period type information corresponding to the target item on the target date. Therefore, by determining the concentrated circulation type of the item on the target date, the replenishment duration information generation model corresponding to the concentrated circulation type can be determined. Then, according to the above-mentioned item circulation period type information, the target replenishment time information generation model corresponding to the above-mentioned target item is determined. Therefore, according to the time period type corresponding to the target date, the replenishment time information generation model corresponding to the time period type can be selected to predict the replenishment time. Finally, according to the above-mentioned target replenishment time information generation model and the item information corresponding to the above-mentioned target item, the replenishment time information corresponding to the above-mentioned target item is generated. Therefore, the replenishment time of the corresponding target item can be determined by the obtained target replenishment time information generation model. Also because the target replenishment time information generation model for determining the replenishment time is determined by the concentrated circulation type of the target date, the replenishment time information generation model corresponding to the time period type can be selected according to the time period type corresponding to the target date to determine the replenishment time, thereby improving the accuracy of the determined replenishment time, thereby reducing item loss and saving transportation resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0027] Figure 1 is a schematic diagram of an application scenario of a method for generating replenishment duration information according to some embodiments of the present disclosure;

[0028] Figure 2 is a flow chart of some embodiments of a method for generating replenishment duration information according to the present disclosure;

[0029] Figure 3 is a schematic diagram of an application scenario of a method for generating replenishment duration information according to other embodiments of the present disclosure;

[0030] Figure 4 is a flow chart of other embodiments of the method for generating replenishment duration information according to the present disclosure;

[0031] Figure 5 is a schematic diagram of the structure of some embodiments of the replenishment duration information generating device according to the present disclosure;

[0032] Figure 6 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0033] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0034] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0035] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0036] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0037] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0038] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0039] Figure 1It is a schematic diagram of an application scenario of the replenishment duration information generation method of some embodiments of the present disclosure.

[0040] exist Figure 1 In the application scenario, first, the computing device 101 can determine the item circulation period type information 103 corresponding to the target item on the target date 102. For example, the above target date 102 can be "2023.3.8". The above item circulation period type information 103 can be "big promotion procurement type". Then, the computing device 101 can determine the target replenishment duration information generation model 104 corresponding to the above target item according to the above item circulation period type information 103. Finally, the computing device 101 can generate the replenishment duration information 106 corresponding to the above target item according to the above target replenishment duration information generation model 104 and the item information 105 corresponding to the above target item. For example, the above item information 105 can be "XX brand pure milk, 220ml, XX yuan". The above replenishment duration information 106 can be "10h".

[0041] It should be noted that the computing device 101 can be hardware or software. When the computing 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 computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, or as a single software or software module. No specific limitation is made here.

[0042] It should be understood that Figure 1 The number of computing devices in the embodiment is only illustrative. Any number of computing devices may be provided according to implementation requirements.

[0043] Continue to refer Figure 2 , shows a process 200 of some embodiments of the method for generating replenishment duration information according to the present disclosure. The method for generating replenishment duration information comprises the following steps:

[0044] Step 201, determining the item circulation period type information corresponding to the target item on the target date.

[0045] In some embodiments, the execution subject of the replenishment time information generation method (for example Figure 1The computing device shown in the figure can determine the item circulation period type information corresponding to the target item on the target date. The target item can be any item. For example, the target item can be XX brand pure milk. "XX" can represent the brand of the target item. The target date can be the date of the replenishment time to be predicted. For example, the target date can be a date of a future day. The item circulation period type information can be information representing the type of concentrated circulation period corresponding to the target date. For example, the item circulation period type information can be a conventional item circulation period type or an unconventional item circulation period type. The conventional item circulation period type can represent that the target date is not in an unconventional concentrated circulation period (e.g., a promotion period). The unconventional item circulation period type can represent that the target date is in an unconventional concentrated circulation period. Specifically, when the target date is in an unconventional procurement period (e.g., a promotion period), the item circulation period type information can be an unconventional item circulation period type (i.e., a promotional procurement type). When the target date is not in an unconventional procurement period, the item circulation period type information can be a conventional item circulation period type. In practice, first, the execution subject may filter out the preset item circulation period type configuration information including the preset date that is the same as the target date from the preset item circulation period type configuration information set as the target item circulation period type configuration information. Each preset item circulation period type configuration information in the preset item circulation period type configuration information set may include a preset date and a preset centralized circulation type. The preset item circulation period type configuration information may be information for characterizing the correspondence between the preset date and the preset centralized circulation type. Then, the execution subject may determine the preset centralized circulation type included in the preset item circulation period type configuration information as the item circulation period type information.

[0046] Step 202: Determine a target replenishment duration information generation model for the target item based on the item circulation period type information.

[0047] In some embodiments, the execution subject may determine the target replenishment duration information generation model corresponding to the target item based on the item circulation period type information. As an example, in response to the item circulation period type information, the unconventional item circulation period type is characterized. The execution subject may determine the replenishment duration information generation model corresponding to the unconventional item circulation period type as the corresponding target replenishment duration information generation model. In response to the item circulation period type information, the conventional item circulation period type is characterized. The execution subject may determine the replenishment duration information generation model corresponding to the conventional item circulation period type as the corresponding target replenishment duration information generation model. The replenishment duration information generation model may be a classification model with item information as input and replenishment duration information as output. For example, the replenishment duration information generation model may be SVM (Support Vector Machine) or CNN (Convolutional Neural Network). The item information may include but is not limited to at least one of the following: item attributes and centralized circulation attributes. The above-mentioned item attributes may include but are not limited to at least one of the following: brand, model, configuration, grade, packaging capacity, unit, production date, shelf life and purpose. The above-mentioned centralized circulation attributes may include but are not limited to at least one of the following: centralized circulation channels (such as procurement channels), centralized circulation value (such as purchase price) and value circulation method (such as payment method). For example, the above-mentioned item information may be "XX brand pure milk, 220ml, XX yuan". "XX yuan" may be the circulation value (such as price) of the above-mentioned target item.

[0048] In some optional implementations of some embodiments, the target replenishment duration information generation model may be obtained through the following training steps:

[0049] The first step is to obtain a set of historical centralized circulation information. The execution subject of training the above target replenishment duration information generation model can be Figure 1The computing device described may also be other computing devices. The above-mentioned historical centralized circulation information may be information extracted from a historical centralized circulation order (such as a purchase order). The above-mentioned historical centralized circulation information may include historical item information. The above-mentioned historical item information may include historical item attributes and historical centralized circulation attributes. Each historical centralized circulation information in the above-mentioned historical centralized circulation information set includes circulation channel information. The above-mentioned circulation channel information may be information characterizing the way of centralized circulation of the above-mentioned target items (such as a procurement channel). The above-mentioned historical centralized circulation information set corresponds to the same item circulation period type. For example, each historical centralized circulation information in the above-mentioned historical centralized circulation information set may be information extracted from a historical centralized circulation order within an unconventional period. Each historical centralized circulation information in the above-mentioned historical centralized circulation information set may also be information extracted from a historical centralized circulation order within a regular period.

[0050] The second step is to group the historical centralized circulation information according to the circulation channel information included in each historical centralized circulation information in the above historical centralized circulation information set to obtain a historical centralized circulation information group set. In practice, the above execution subject can group the historical centralized circulation information with the same corresponding circulation channel information into one group to obtain a historical centralized circulation information group set.

[0051] The third step is to generate a replenishment time information generation model for each historical concentrated circulation information group in the above historical concentrated circulation information group set according to the above historical concentrated circulation information group. In practice, for each historical concentrated circulation information group in the above historical concentrated circulation information group set, the above execution subject can train the initial model through each historical concentrated circulation information included in the above historical concentrated circulation information group to obtain the replenishment time information generation model. As an example, the above execution subject can use each historical item information included in the above historical concentrated circulation information group as input and each circulation channel information included in the above historical concentrated circulation information group as output to train the initial model to obtain the replenishment time information generation model. Among them, the above initial model can be a decision tree model.

[0052] In the fourth step, according to each channel priority corresponding to each historical concentrated circulation information group in the above historical concentrated circulation information group set, a replenishment duration information generation model that meets the preset channel priority condition is selected from the determined replenishment duration information generation models as the target replenishment duration information generation model. Among them, the channel priority corresponding to the historical concentrated circulation information group can be the channel priority of the circulation channel information corresponding to the historical concentrated circulation information group that is preset. The above preset channel priority condition can be that the channel priority of the corresponding circulation channel information is the highest.

[0053] Therefore, different replenishment time information generation models are trained through replenishment channels, and then the replenishment time information generation model corresponding to the replenishment channel with high priority is selected as the target replenishment time information generation model, so that the replenishment time information generation model corresponding to the better replenishment channel can be screened out to predict the replenishment time, thereby improving the accuracy of the obtained replenishment time information.

[0054] In some optional implementations of some embodiments, the execution entity for generating the target replenishment duration information generation model may perform the following steps according to the historical centralized circulation information group:

[0055] The first step is to train the initial model according to the above historical concentrated circulation information group and the preset quantile loss function set to obtain the replenishment time information generation model set corresponding to the above historical concentrated circulation information group. In practice, the above execution subject can train the initial model through each preset quantile loss function in the preset quantile loss function set, with each historical item information included in the above historical concentrated circulation information group as input, and each circulation channel information included in the above historical concentrated circulation information group as output, to obtain at least one replenishment time information generation model. Among them, each preset quantile loss function corresponds to a replenishment time information generation model.

[0056] The second step is to determine the accuracy information corresponding to each replenishment time information generation model in the replenishment time information generation model set. The accuracy information can be any one of the following: AP (Average Precision) corresponding to the replenishment time information generation model, MAP (Mean Average Precision) corresponding to the replenishment time information generation model, and ROC (Receiver operating characteristic) corresponding to the replenishment time information generation model.

[0057] The third step is to select a replenishment time information generation model that meets a preset accuracy condition from the above replenishment time information generation model set according to the determined accuracy information. The above preset accuracy condition may be that the corresponding accuracy information is the highest. In practice, the above execution entity may select a replenishment time information generation model with the highest corresponding accuracy information from the above replenishment time information generation model set.

[0058] Therefore, by training the model through the quantile loss function set corresponding to different quantiles, and then selecting a more accurate replenishment time information generation model according to the model accuracy, the accuracy of the replenishment time information generation model prediction can be improved, thereby improving the accuracy of the obtained replenishment time information.

[0059] Step 203 : Generate replenishment time information of the corresponding target item according to the target replenishment time information generation model and the item information of the corresponding target item.

[0060] In some embodiments, the execution entity may generate the replenishment time information corresponding to the target item based on the target replenishment time information generation model and the item information of the target item. In practice, the execution entity may input the item information into the target replenishment time information generation model to obtain the replenishment time information corresponding to the target item.

[0061] Optionally, the execution subject may further perform the following steps: generating replenishment quantity information corresponding to the target item according to the replenishment duration information. The replenishment quantity information may be information characterizing the quantity of the target item that needs to be replenished. As an example, first, the execution subject may generate a safety inventory quantity according to the replenishment duration information. The execution subject may generate the safety inventory quantity according to the following formula:

[0062]

[0063] Wherein, NTR represents the preset stocking period. For example, the stocking period can be 7 days. VLT q Indicates the above replenishment time information. i Indicates the turnover of the target item on a certain day (e.g. sales volume). q Indicates the preset quantile. For example, the value range of the above quantile can be 0.8~0.95. i Indicates the standard deviation of the turnover of the target item on a certain day. Represents the safety stock amount.

[0064] Then, the execution entity may determine the absolute value of the difference between the safety inventory and the existing inventory as the replenishment quantity information corresponding to the target item. The existing inventory may be the quantity of the target item in the current warehouse.

[0065] Optionally, the execution subject may also control the associated replenishment equipment to perform the replenishment operation corresponding to the target item according to the replenishment quantity information. The associated replenishment equipment may be an item transportation equipment. For example, the associated replenishment equipment may be an AGV (Automated Guided Vehicle) cart. In practice, the execution subject may control the associated replenishment equipment to transport the items of the item replenishment quantity represented by the replenishment quantity information to the target location. The target location may be a warehouse.

[0066] The above-mentioned embodiments of the present disclosure have the following beneficial effects: the replenishment duration determined by the replenishment duration information generation method of some embodiments of the present disclosure is more accurate, thereby reducing the loss of items and saving transportation resources. Specifically, the reason for the waste of item loss and transportation resources is that the volatility of the replenishment duration in different historical periods is large (for example, the replenishment duration in the regular period and the promotion period is large), and the historical periods are not distinguished. The replenishment duration is only predicted by each historical replenishment duration in a period of time, resulting in a low accuracy of the predicted replenishment duration, which leads to a low accuracy of the subsequent predicted replenishment quantity, and then when the obtained replenishment quantity is large, the items are piled up more, resulting in more item loss, and when the obtained replenishment quantity is small, the items are out of stock and need to be dispatched again, resulting in a waste of transportation resources. Based on this, the replenishment duration information generation method of some embodiments of the present disclosure first determines the item circulation period type information corresponding to the target item on the target date. Therefore, by determining the concentrated circulation type of the item on the target date, the replenishment duration information generation model corresponding to the concentrated circulation type can be determined. Then, according to the above-mentioned item circulation period type information, the target replenishment time information generation model corresponding to the above-mentioned target item is determined. Therefore, according to the time period type corresponding to the target date, the replenishment time information generation model corresponding to the time period type can be selected to predict the replenishment time. Finally, according to the above-mentioned target replenishment time information generation model and the item information corresponding to the above-mentioned target item, the replenishment time information corresponding to the above-mentioned target item is generated. Therefore, the replenishment time of the corresponding target item can be determined by the obtained target replenishment time information generation model. Also because the target replenishment time information generation model for determining the replenishment time is determined by the concentrated circulation type of the target date, the replenishment time information generation model corresponding to the time period type can be selected according to the time period type corresponding to the target date to determine the replenishment time, thereby improving the accuracy of the determined replenishment time, thereby reducing item loss and saving transportation resources.

[0067] Figure 3 It is a schematic diagram of an application scenario of a method for generating replenishment duration information according to other embodiments of the present disclosure.

[0068] exist Figure 3In the application scenario, first, the computing device 301 may determine at least one historical date 303 corresponding to the target date 302. For example, the target date 303 may be "2023.3.8". The at least one historical date 303 includes "2022.3.8" 3031, "2021.3.8" 3032, and "2020.3.8" 3033. Secondly, the computing device 301 may perform anomaly detection on the historical concentrated circulation date sequence corresponding to the target item to obtain a historical abnormal concentrated circulation date information set 304. For example, the historical abnormal concentrated circulation date information set 304 may include "2022.3.1-2022.3.10" 3041, "2021.3.1-2021.3.10" 3042, and "2020.3.1-2020.3.10" 3043. Then, the computing device 301 may determine the item circulation time period types 305 corresponding to each historical date in the at least one historical date according to the historical abnormal concentrated circulation date information set 304. For example, the item circulation time period types 305 may include "big promotion purchase type" 3051, "big promotion purchase type" 3052, and "big promotion purchase type" 3053. Afterwards, the computing device 301 may determine the target item circulation time period type information 306 corresponding to the target item on the target date 302 according to the item circulation time period types 305 corresponding to each historical date in the at least one historical date. For example, the target item circulation time period type information 306 may be "big promotion purchase type". Then, the computing device 301 may determine the target replenishment time information generation model 307 corresponding to the target item according to the item circulation time period type information 306. Finally, the computing device 301 may generate the replenishment time information 309 corresponding to the target item according to the target replenishment time information generation model 307 and the item information 308 corresponding to the target item. For example, the item information 308 may be “XX brand pure milk, 220 ml, XX yuan”, and the replenishment time information 309 may be “10 hours”.

[0069] It should be noted that the computing device 301 can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, or it can be implemented as a single software or software module. No specific limitation is made here.

[0070] It should be understood that Figure 3 The number of computing devices in the embodiment is only illustrative. Any number of computing devices may be provided according to implementation requirements.

[0071] Further references Figure 4 , which shows a process 400 of another embodiment of a method for generating replenishment duration information. The process 400 of the method for generating replenishment duration information includes the following steps:

[0072] Step 401, determining at least one historical date corresponding to the target date.

[0073] In some embodiments, the execution entity (e.g. Figure 3 The computing device shown in the figure may determine at least one historical date corresponding to the target date. The historical date may be a historical date with the same month and day as the target date but a different year. For example, the target date may be March 8, 2023. The at least one historical date may include, but is not limited to, at least one of the following: March 8, 2022, March 8, 2021, March 8, 2020, and March 8, 2019.

[0074] Step 402 , performing anomaly detection on the historical concentrated circulation date sequence corresponding to the target item to obtain a historical abnormal concentrated circulation date information set.

[0075] In some embodiments, the execution subject may perform anomaly detection on the historical concentrated circulation date sequence corresponding to the target item to obtain a set of historical abnormal concentrated circulation date information. The historical abnormal concentrated circulation date information may include: a historical concentrated circulation date representing the start date of an unconventional period, and a historical concentrated circulation date representing the end date of an unconventional period. In practice, the execution subject may perform anomaly detection on the historical concentrated circulation date sequence corresponding to the target item through anomaly detection method to obtain a set of historical abnormal concentrated circulation date information. The anomaly detection method may include but is not limited to at least one of the following: mean square error, Random Cut Forest (RCF) algorithm, Isolation Forest algorithm and Isolation Forest.

[0076] Step 403, determining the type of each item circulation period corresponding to each historical date in at least one historical date according to the historical abnormal concentrated circulation date information set.

[0077] In some embodiments, the execution subject may determine the types of item circulation periods corresponding to the various historical dates in the at least one historical date according to the historical abnormal concentrated circulation date information set. In practice, first, the execution subject may determine the various unconventional time periods through the historical concentrated circulation dates representing the start date of the unconventional time period and the historical concentrated circulation dates representing the end date of the unconventional time period included in the historical abnormal concentrated circulation date information set. Then, for each historical date in the at least one historical date. First, determine whether the historical date is in any unconventional time period. Second, in response to determining that the historical date is in any unconventional time period, determine the unconventional item circulation time period type as the item circulation time period type corresponding to the historical date. Third, in response to determining that the historical date is not in any unconventional time period, determine the conventional item circulation time period type as the item circulation time period type corresponding to the historical date.

[0078] Step 404: Determine target item circulation period type information corresponding to the target item on the target date according to each item circulation period type corresponding to each historical date in at least one historical date.

[0079] In some embodiments, the execution subject may determine the target item circulation period type information corresponding to the target item on the target date according to the item circulation period types corresponding to each historical date in the at least one historical date. First, the execution subject may group the historical dates with the same item circulation period type into a group to obtain a historical date group set. Then, the item circulation period type corresponding to the historical date group that meets the preset quantity condition may be determined as the item circulation period type information. The preset quantity condition may include the largest number of historical dates.

[0080] Step 405: Determine a target replenishment duration information generation model for the target item based on the item circulation period type information.

[0081] Step 406 , generating a replenishment time information of the corresponding target item according to the target replenishment time information generation model and the item information of the corresponding target item.

[0082] In some embodiments, the specific implementation of steps 405-406 and the technical effects thereof can be referred to in Figure 2 The steps 202-203 in the corresponding embodiment will not be described in detail here.

[0083] from Figure 4 It can be seen that Figure 2 Compared with the description of some corresponding embodiments, Figure 4The process 400 of the replenishment duration information generation method in some corresponding embodiments reflects the determination of the item circulation period type information corresponding to the target date according to the historical date corresponding to the target date. Thus, when the staff has not set the item circulation period type corresponding to the target item on the target date, the item circulation period type corresponding to the target item on the target date can be automatically determined, and then the item circulation period types of a large number of target dates can be determined quickly, thereby improving the efficiency of replenishment duration information generation.

[0084] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a replenishment time information generating device. These device embodiments are similar to Figure 2 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0085] like Figure 5 As shown, in some embodiments, the replenishment duration information generating device 500 includes: a first determining unit 501, a second determining unit 502 and a generating unit 503. The first determining unit 501 is configured to determine the item circulation period type information corresponding to the target item on the target date. The second determining unit 502 is configured to determine the target replenishment duration information generating model corresponding to the target item according to the item circulation period type information. The generating unit 503 is configured to generate the replenishment duration information corresponding to the target item according to the target replenishment duration information generating model and the item information corresponding to the target item.

[0086] In some embodiments, the first determination unit 501 may be further configured to: determine at least one historical date corresponding to the target date; and determine the item circulation period type information of the target item corresponding to the target date based on the at least one historical date.

[0087] In some embodiments, the first determination unit 501 may be further configured to: perform anomaly detection on the historical concentrated circulation date sequence corresponding to the target item to obtain a historical abnormal concentrated circulation date information set; determine the type of each item circulation period corresponding to each historical date in the at least one historical date based on the historical abnormal concentrated circulation date information set; determine the target item circulation period type information corresponding to the target item on the target date based on the type of each item circulation period corresponding to each historical date in the at least one historical date.

[0088] In some embodiments, the target replenishment duration information generation model may be obtained through the following training steps: obtaining a set of historical concentrated circulation information, wherein each historical concentrated circulation information in the set of historical concentrated circulation information includes circulation channel information, and the set of historical concentrated circulation information corresponds to the same item circulation period type; grouping each historical concentrated circulation information according to the circulation channel information included in each historical concentrated circulation information in the set of historical concentrated circulation information to obtain a historical concentrated circulation information group set; for each historical concentrated circulation information group in the set of historical concentrated circulation information groups, generating a replenishment duration information generation model according to the historical concentrated circulation information group; according to the channel priorities corresponding to each historical concentrated circulation information group in the set of historical concentrated circulation information groups, selecting a replenishment duration information generation model that meets the preset channel priority condition from the determined replenishment duration information generation models as the target replenishment duration information generation model.

[0089] In some embodiments, the second determination unit 502 may be further configured to: train the initial model according to the historical concentrated circulation information group and the preset quantile loss function set to obtain a replenishment time information generation model set corresponding to the historical concentrated circulation information group; determine the accuracy information corresponding to each replenishment time information generation model in the replenishment time information generation model set; and select the replenishment time information generation model that meets the preset accuracy condition from the replenishment time information generation model set according to the determined accuracy information.

[0090] In some embodiments, the replenishment duration information generating device may further include: a replenishment quantity information generating unit (not shown in the figure), configured to generate replenishment quantity information corresponding to the target item according to the replenishment duration information.

[0091] In some embodiments, the replenishment duration information generating device may further include: a control unit (not shown in the figure), configured to control the associated replenishment equipment to perform a replenishment operation corresponding to the target item according to the replenishment quantity information.

[0092] It is understood that the units described in the device 500 are similar to those described in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 500 and the units included therein, and will not be described in detail here.

[0093] Reference below Figure 6 , which shows an electronic device 600 (eg, Figure 1 Schematic diagram of the structure of the computing device 101). Figure 6The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0094] like Figure 6 As shown, the electronic device 600 may include a processing device 601 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 602 (ROM) or a program loaded from a storage device 608 into a random access memory 603 (RAM). In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0095] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 6 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0096] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0097] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0098] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0099] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: determines the item circulation period type information corresponding to the target item on the target date; determines the target replenishment time information generation model corresponding to the target item based on the item circulation period type information; generates the replenishment time information corresponding to the target item based on the target replenishment time information generation model and the item information corresponding to the target item.

[0100] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] The units described in some embodiments of the present disclosure may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes a first determination unit, a second determination unit, and a generation unit. The names of these units do not constitute a limitation on the units themselves in some cases, for example, the generation unit may also be described as "a unit that generates replenishment duration information corresponding to the above-mentioned target item".

[0103] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0104] Some embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above-mentioned replenishment duration information generation methods when executed by a processor.

[0105] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for generating replenishment time information, comprising: Determine the item circulation period type information corresponding to the target item on the target date; Determine a target replenishment duration information generation model corresponding to the target item according to the item circulation period type information; The replenishment time information corresponding to the target item is generated according to the target replenishment time information generation model and the item information corresponding to the target item.

2. The method according to claim 1, wherein: The determining of the item circulation period type information corresponding to the target item on the target date includes: determining at least one historical date corresponding to the target date; According to the at least one historical date, the item circulation period type information corresponding to the target item on the target date is determined.

3. The method according to claim 2, wherein: The determining, based on the at least one historical date, the item circulation period type information corresponding to the target item on the target date includes: Performing anomaly detection on the historical concentrated circulation date sequence corresponding to the target item to obtain a historical abnormal concentrated circulation date information set; Determine, according to the historical abnormal concentrated circulation date information set, the type of each item circulation period corresponding to each historical date in the at least one historical date; According to each item circulation period type corresponding to each historical date in the at least one historical date, target item circulation period type information corresponding to the target item on the target date is determined.

4. The method according to claim 1, wherein: The target replenishment duration information generation model is obtained through the following training steps: Acquire a historical centralized circulation information set, wherein each historical centralized circulation information in the historical centralized circulation information set includes circulation channel information, and the historical centralized circulation information set corresponds to the same item circulation period type; According to each circulation channel information included in each historical concentrated circulation information in the historical concentrated circulation information set, each historical concentrated circulation information is grouped and processed to obtain a historical concentrated circulation information group set; For each historical concentrated circulation information group in the historical concentrated circulation information group set, generating a replenishment duration information generation model according to the historical concentrated circulation information group; According to each channel priority corresponding to each historical concentrated circulation information group in the historical concentrated circulation information group set, a replenishment duration information generation model that meets the preset channel priority condition is selected from the determined replenishment duration information generation models as the target replenishment duration information generation model.

5. The method according to claim 4, wherein: The generating a replenishment duration information generating model according to the historical centralized circulation information group includes: According to the historical concentrated circulation information group and the preset quantile loss function set, the initial model is trained to obtain a replenishment duration information generation model set corresponding to the historical concentrated circulation information group; Determine each accuracy information corresponding to each replenishment duration information generation model in the replenishment duration information generation model set; According to the determined accuracy information, a replenishment duration information generation model that meets a preset accuracy condition is selected from the replenishment duration information generation model set.

6. The method according to claim 1, wherein: The method further comprises: Generate replenishment quantity information corresponding to the target item according to the replenishment duration information.

7. The method according to claim 6, wherein: The method further comprises: According to the replenishment quantity information, the associated replenishment equipment is controlled to perform a replenishment operation corresponding to the target item.

8. A replenishment time information generating device, comprising: A first determining unit is configured to determine item circulation period type information corresponding to a target item on a target date; A second determining unit is configured to determine a target replenishment duration information generation model corresponding to the target item according to the item circulation period type information; The generating unit is configured to generate the replenishment time information corresponding to the target item according to the target replenishment time information generating model and the item information corresponding to the target item.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

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

Images