Commodity processing method and device, electronic equipment and computer storage medium

Abstract

The invention provides a commodity processing method and apparatus, an electronic device and a computer storage medium. The method comprises the steps of obtaining basic information of a commodity; when it is determined that the basic information meets the preset requirement and it is determined that the issuing wave is triggered at the current time, obtaining commodity data of the previous issuing wave; processing based on the basic information and the commodity data to obtain a target predicted sales volume of a time period corresponding to the current issuing wave of the commodity; and issuing the target predicted sales volume to a production storage warehouse, so that the production storage warehouse prepares goods for producing the commodities based on the target predicted sales volume, and carries out commodity production based on the goods for producing the commodities. According to the method, the basic information and the commodity data of the commodity are processed through the pre-constructed prediction model, so that the target predicted sales volume of the time period corresponding to the current issuing wave of the commodity is determined, and the commodity is produced through the target predicted sales volume. Therefore, the influence on the shopping experience of the customer can be reduced under the condition that the production cost is controllable.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a commodity processing method, device, electronic equipment and computer storage medium. Background Art

[0002] In order to enhance customers' shopping experience and improve the fulfillment of order arrival time, single products are often produced in advance through manual planning. The above manual method is prone to overproduction or underproduction of single products, which leads to uncontrollable production costs and affects customers' shopping experience. Summary of the invention

[0003] In view of this, the embodiments of the present invention provide a commodity processing method, device, electronic device and computer storage medium to solve the problem in the prior art that the production cost is uncontrollable and affects the customer's shopping experience.

[0004] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0005] The first aspect of the embodiment of the present invention shows a commodity processing method, which is applied to a sales-end server, and the sales-end server is connected to a production storage warehouse. The method includes:

[0006] Get basic information about the product;

[0007] When it is determined that the basic information meets the preset requirements, determining a production volume forecast for the commodity;

[0008] After determining the current time to trigger the distribution wave, obtain the product data of the previous distribution wave;

[0009] Based on the basic information and product data, the target predicted sales volume of the product for the time period corresponding to the current delivery wave is obtained;

[0010] The target predicted sales volume is sent to the production storage warehouse so that the production storage warehouse prepares to produce the goods of the goods based on the target predicted sales volume, and produces the goods based on the goods prepared to produce the goods.

[0011] Optionally, determining that the basic information meets preset requirements includes:

[0012] Determine whether the historical sales volume of the commodity in the basic information within a preset time period meets the preset quantity;

[0013] Determine whether the popularity of the product in the basic information reaches a preset threshold within a preset time period;

[0014] Determine whether the category to which the product in the basic information belongs exists in the preset category;

[0015] Determine whether the actual inventory quantity of the product in the basic information is the preset inventory quantity;

[0016] If it is determined that the sales volume of the commodity within the preset time period meets the preset quantity, the popularity of the commodity within the preset time period reaches the preset threshold, and the commodity belongs to a preset category of commodities, the actual inventory quantity of the commodity in the basic information is not the preset inventory quantity, or it is determined that the basic information meets the preset requirements.

[0017] Optionally, the processing based on the basic information and the commodity data to obtain the target predicted sales volume of the commodity includes:

[0018] Inputting the basic information into a pre-built prediction model, processing the basic information based on the prediction model, and outputting a first predicted sales volume of the commodity, wherein the prediction model is obtained by training based on a historical sample data set;

[0019] The first predicted sales volume and commodity data are calculated to obtain a target predicted sales volume.

[0020] Optionally, the process of building the prediction model based on the historical sample data set includes:

[0021] Acquire a sample data set, wherein the sample data includes historical sales data, historical price data, historical activity data of the commodity in a historical period, and category data of the same category as the commodity;

[0022] The sample data set is used for training to obtain a trained prediction model.

[0023] Optionally, also include:

[0024] When determining that the current time triggers the distribution wave, the actual sales volume and the target predicted sales volume of the product in the corresponding time period of the previous distribution wave are obtained;

[0025] Calculate the forecast accuracy based on the actual sales volume of the product in the corresponding time period of the previous delivery wave and the target forecast sales volume;

[0026] If the prediction accuracy is higher than or equal to the preset probability, it is determined that the prediction model can be used;

[0027] If the prediction accuracy is lower than the preset probability, the prediction model is updated to obtain an updated prediction model.

[0028] Optionally, also include:

[0029] Get the actual sales volume of the product in the corresponding time period of the previous delivery wave;

[0030] If it is determined that the actual sales volume is inconsistent with the target predicted sales volume, calculating commodity data based on the actual sales volume and the target predicted sales volume, the commodity data including excess data or missing data;

[0031] The commodity data is stored.

[0032] Optionally, also include:

[0033] The target forecast sales volume is revised to obtain a revised target forecast sales volume.

[0034] The second aspect of the embodiment of the present invention shows a commodity processing device, which is applied to a sales-end server, and the sales-end server is connected to a production storage warehouse, and the device includes:

[0035] A first acquisition unit, used to acquire basic information of a product;

[0036] A determination unit, configured to determine a production volume forecast for the commodity when it is determined that the basic information meets preset requirements;

[0037] The second acquisition unit is used to determine the current time to trigger the distribution wave and obtain the commodity data of the previous distribution wave;

[0038] A processing unit, configured to perform processing based on the basic information and the commodity data to obtain a target predicted sales volume for a time period corresponding to a current delivery wave of the commodity;

[0039] The sending unit is used to send the target predicted sales volume to the production storage warehouse, so that the production storage warehouse prepares to produce the goods of the goods based on the target predicted sales volume, and produces the goods based on the goods prepared to produce the goods.

[0040] A third aspect of an embodiment of the present invention shows an electronic device, which is used to run a program, wherein the program, when running, executes the commodity processing method shown in the first aspect of the embodiment of the present invention.

[0041] A fourth aspect of an embodiment of the present invention shows a computer storage medium, which includes a storage program, wherein when the program is running, the device where the storage medium is located is controlled to execute the commodity processing method shown in the first aspect of the embodiment of the present invention.

[0042] Based on the above-mentioned embodiment of the present invention, a commodity processing method, device, electronic device and computer storage medium are provided. The method includes: applying to a sales-end server, the sales-end server is connected to a production storage warehouse, and the method includes: obtaining basic information of the commodity; when determining that the basic information meets the preset requirements, determining to predict the production volume of the commodity; determining to trigger the release wave at the current time, obtaining the commodity data of the previous release wave; processing based on the basic information and commodity data to obtain the target predicted sales volume of the commodity in the corresponding time period of the current release wave; sending the target predicted sales volume to the production storage warehouse, so that the production storage warehouse prepares to produce the goods of the commodity based on the target predicted sales volume, and produces the goods based on the goods to be produced. In the embodiment of the present invention, the basic information and commodity data of the commodity are processed by a pre-constructed prediction model to determine the target predicted sales volume of the corresponding time period of the current release wave of the commodity, and produce the commodity according to the target predicted sales volume. Thereby, the impact on the customer's shopping experience can be reduced while the production cost is controllable. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0044] Figure 1 This is a schematic diagram of the architecture of a sales server 10, a production storage warehouse 20, and a processing warehouse 30 according to an embodiment of the present invention;

[0045] Figure 2 A flowchart of a commodity processing method according to an embodiment of the present invention;

[0046] Figure 3 A schematic flow chart of another commodity processing method according to an embodiment of the present invention;

[0047] Figure 4 A schematic diagram of a flow chart showing whether a prediction model is used according to an embodiment of the present invention;

[0048] Figure 5 The present invention is a schematic structural diagram of a commodity processing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0051] It should be noted that the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0052] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0053] See also Figure 1 , is a schematic diagram of the architecture of a sales server 10, a production storage warehouse 20 and a processing warehouse 30 according to an embodiment of the present invention;

[0054] The sales server 10 is connected to the production storage warehouse 20 , and the production storage warehouse 20 is connected to the processing warehouse 30 .

[0055] The number of the production storage warehouse 20 and the number of the processing warehouse 30 are both multiple.

[0056] The processing warehouse 30 and the production storage warehouse 20 may be set in different areas according to actual conditions. There is a corresponding relationship between the production storage warehouse 20 and the processing warehouse 30, that is, there must be a production storage warehouse 20 and a processing warehouse 30 in one area.

[0057] It should be noted that the production codes of different commodities are different, that is, the processing warehouses 30 of different commodities are different, and therefore the corresponding production storage warehouses 20 are also different.

[0058] The production storage warehouse 20 stores the code information, storage information and outbound information of the commodities, the goods to be produced, and the commodities corresponding to the commodity data.

[0059] The code information of the commodity at least includes the packaging code of the commodity, whether to convert the packaging code and other information.

[0060] The incoming information at least includes verifying whether the product is new and collecting the packaging code of the new product;

[0061] It should be noted that non-new products or products with configured packaging codes can be put into storage according to any level of packaging code. The system records the packaging code collected when the current product is put into storage.

[0062] The packaging code includes 5 levels from 1 to 5.

[0063] The outbound information includes obtaining the maximum packaging code of the product by product, and converting the picking quantity according to the packaging code when picking.

[0064] The processing warehouse 30 can communicate with the production storage warehouse 20 to receive the prepared goods, produce according to the actual customer order quantity, or produce according to the target predicted sales volume; and return the excess goods to the production storage warehouse 20 for storage.

[0065] Optional, Figure 1 A financial system 40 is also included.

[0066] The financial system 40 is used to calculate the production cost of the sales products, excluding the excess charges in the production process from the storage warehouse to the production warehouse; excluding the excess goods entering the production warehouse and returning to the production warehouse; excluding the excess goods returning to the storage warehouse.

[0067] The process of specifically illustrating the commodity processing method based on the above-illustrated architecture includes:

[0068] When receiving a commodity processing instruction, the sales-end server 10 obtains basic information of the current commodity based on the commodity processing instruction; when determining that the basic information meets the preset requirements, determines to predict the production volume of the commodity; when determining that the current time triggers a dispatch wave and determining that commodity data exists in the previous dispatch wave, obtains the commodity data existing in the previous dispatch wave; processes based on the basic information and commodity data to obtain the target predicted sales volume of the commodity for the time period corresponding to the current dispatch wave; and dispatches the target predicted sales volume to the production storage warehouse 20 corresponding to the commodity.

[0069] The production storage warehouse 20 prepares to produce the goods of the commodity based on the target predicted sales volume to prepare the goods in advance, and produces the goods prepared for production according to the production time.

[0070] The processing warehouse 30 carries out outbound production and packaging of the commodities according to the actual orders.

[0071] In the embodiment of the present invention, the basic information and product data of the product are processed by a pre-built prediction model to determine the target predicted sales volume of the product in the corresponding time period of the current delivery wave, and the production storage warehouse prepares to produce the goods of the product based on the target predicted sales volume to prepare the goods in advance, and produces the goods based on the production time. In this way, the impact on the customer's shopping experience can be reduced while the production cost is controllable.

[0072] See also Figure 2 , is a flow chart of a commodity processing method shown in an embodiment of the present invention, the method comprising:

[0073] Step S201: Obtain basic information of the product.

[0074] In the specific implementation of step S201, the sales server obtains basic information of different commodities in real time.

[0075] It should be noted that the basic information includes the name of the product, the activities of the product in different periods, the price and sales volume in different regions during different periods, the peak sales period and the actual inventory of the product.

[0076] Among them, the peak sales period is determined based on historical order sales and time.

[0077] Step S202: Determine whether the basic information meets the preset requirements. If so, execute step S203. If not, do not predict the product, that is, remove the basic information of the product.

[0078] It should be noted that the specific implementation of step S202 includes the following steps:

[0079] Step S11: Determine whether the historical sales volume of the commodity in the preset time period in the basic information meets the preset quantity. If it is determined that the sales volume of the commodity in the preset time period meets the preset quantity, execute step S15. If it is determined that the sales volume of the commodity in the preset time period does not meet the preset quantity, no prediction is made for the commodity, that is, the basic information of the commodity is removed.

[0080] In the process of implementing step S11, for each commodity, the historical sales volume of the commodity within the preset time period is compared with the preset quantity. If it is determined that the sales volume of the commodity within the preset time period meets the preset quantity, step S15 is executed. If it is determined that the sales volume of the commodity within the preset time period does not meet the preset quantity, no prediction is made for the commodity, that is, the basic information of the commodity is removed.

[0081] It should be noted that the preset time is set according to actual conditions and refers to a cycle, and its unit can be hours, days, 7 days, 28 days, quarters, half a year, one year, etc.

[0082] The preset quantity is set in advance by the technicians based on the actual situation.

[0083] Step S12: Determine whether the popularity of the product in the basic information within the preset time period reaches a preset threshold. If it is determined that the popularity of the product within the preset time period reaches the preset threshold, execute step S15. If it is determined that the popularity of the product within the preset time period does not reach the preset threshold, no prediction is made for the product, that is, the basic information of the product is removed.

[0084] In the specific implementation of step S12, the popularity of the product within the preset time period is compared with the preset threshold to determine whether the product is a hot product. If it is determined that the popularity of the product within the preset time period reaches the preset threshold, it is determined to be a hot product, and step S15 is executed. If it is determined that the popularity of the product within the preset time period does not reach the preset threshold, it is determined that the product is not a hot product, and no prediction is made for the product, that is, the basic information of the product is removed.

[0085] It should be noted that the preset threshold is set in advance by the technicians based on the actual situation.

[0086] Step S13: Determine whether the category to which the product in the basic information belongs exists in the preset category. If it is determined that the product belongs to the preset category, execute step S15. If it is determined that the product does not belong to the preset category, do not predict the product, that is, remove the basic information of the product.

[0087] In the specific implementation of step S13, it is determined whether the category to which the product belongs exists in the preset category. If so, step S15 is executed. If not, no prediction is performed on the product, that is, the basic information of the product is removed.

[0088] Step S14: Determine whether the actual inventory quantity of the commodity in the basic information is the preset inventory quantity. If the actual inventory quantity of the commodity in the basic information is not the preset inventory quantity, execute step S15. If the actual inventory quantity of the commodity in the basic information is the preset inventory quantity, no prediction is made for the commodity, that is, the basic information of the commodity is removed.

[0089] It should be noted that the preset inventory quantity can be 0 or the maximum packaging code quantity, that is, the maximum inventory quantity.

[0090] In the process of implementing step S14, it is determined whether the actual inventory of the product in the basic information is 0 or the maximum packaging code quantity. If not, step S15 is executed. If so, no prediction is made for the product, that is, the basic information of the product is removed.

[0091] Step S15: Determine whether the basic information meets the preset requirements, and execute step S203.

[0092] It should be noted that the preset requirements not only include whether the historical sales volume shown in the above steps S11 to S13 meets the preset quantity, whether the popularity reaches the preset threshold, and whether the category to which the product belongs exists in the preset category, but may also include other conditions, which are not limited to this embodiment of the present invention.

[0093] Step S203: Determine a production volume forecast for the commodity.

[0094] Step S204: Determine whether the current time triggers the sending of waves. If it is determined that the current time triggers the sending of waves, execute step S205; if not, continue to execute step S201.

[0095] It should be noted that the sending waves are pre-configured according to actual conditions, for example, they can be 9 o'clock, 16 o'clock and 23 o'clock.

[0096] Step S205: Obtain the commodity data of the previous delivery wave.

[0097] In the specific implementation of step S205, the commodity data of the previous delivery wave is obtained from the storage warehouse.

[0098] It should be noted that the specific calculation process of commodity data includes the following steps:

[0099] Step S21: obtaining the actual sales volume of the product in the time period corresponding to the previous distribution wave.

[0100] In a specific implementation, the actual sales volume of the commodity in the time period corresponding to the previous distribution wave is obtained through the sales record of the sales end.

[0101] It should be noted that the time period corresponding to the dispatched wave is divided according to the actual situation. For example, the time period from 23:00 yesterday to 9:00 today is the time period corresponding to the dispatched wave at 9:00, and this time period does not include the 9:00 time point; the time period from 9:00 today to 16:00 today is the time period corresponding to the dispatched wave at 16:00, and this time period does not include the 16:00 time point; the time period from 16:00 today to 23:00 today is the time period corresponding to the dispatched wave at 16:00, and this time period does not include the 23:00 time point.

[0102] Step S22: Determine whether the actual sales volume is consistent with the target predicted sales volume. If it is determined that the actual sales volume is inconsistent with the target predicted sales volume, execute step S23; if it is determined that the actual sales volume is consistent with the target predicted sales volume, execute step S24.

[0103] In the specific implementation of step S22, the actual sales volume is compared with the target predicted sales volume to see if they are the same. If they are different, step S23 is executed; if they are the same, step S24 is executed.

[0104] Step S23: Calculating commodity data based on the actual sales volume and the target predicted sales volume.

[0105] In step S23, the commodity data includes excess data or missing data.

[0106] In the process of specifically implementing step S23, if it is determined that the actual sales volume is greater than the target predicted sales volume, the difference between the actual sales volume and the target predicted sales volume is calculated and used as missing data so that more production can be made in the next prediction; if it is determined that the actual sales volume is less than the target predicted sales volume, the difference between the actual sales volume and the target predicted sales volume is calculated and used as overweight data.

[0107] Optionally, when overweight data is obtained, the goods corresponding to the overweight data are returned to the production storage warehouse for storage.

[0108] Step S24: the value of the commodity data is 0.

[0109] In the process of specifically implementing step S24, if it is determined that the actual sales volume is equal to the target predicted sales volume, the value 0 is used as the commodity data.

[0110] Step S25: storing the commodity data.

[0111] In the specific implementation of step S25, the commodity data and its corresponding delivery wave, and the time period corresponding to the delivery wave are stored in the production storage warehouse.

[0112] Step S206: Processing is performed based on the basic information and product data to obtain the target predicted sales volume of the product for the time period corresponding to the current delivery wave.

[0113] It should be noted that the specific implementation of step S206 includes the following steps:

[0114] Step S31: input the basic information into a pre-built prediction model, process the basic information based on the prediction model, and output a first predicted sales volume of the commodity.

[0115] In step S31, the prediction model is trained based on the historical sample data set.

[0116] It should be noted that the process of building the prediction model based on the historical sample data set includes the following steps:

[0117] Step S41: Obtain a sample data set.

[0118] In step S41, the sample data includes historical sales data, historical price data, historical activity data, historical actual inventory of the commodity within a historical period, and category data of the same category as the commodity.

[0119] In the specific implementation of step S41, the historical sales data, historical price data, historical activity data, historical actual inventory of the commodity and category data of the same category as the commodity in the historical period are obtained; and they are divided into a training set and a test set.

[0120] Step S42: Perform training using the sample data set to obtain a trained prediction model.

[0121] In the process of implementing step S42, the initial model is trained using the training set in the sample data set to obtain a trained initial model, and then the trained initial model is tested using the test set until the difference between the output test result and the historical sales data is less than a predetermined value, and the current trained initial model is determined to be a prediction model.

[0122] It should be noted that the initial model can be a neural network model, a model built by a deep learning algorithm, or a model built by a machine learning algorithm, etc.

[0123] The preset value is set by the technician according to the actual situation.

[0124] In the process of implementing step S31, the prediction model processes the historical sales volume within a preset time period, the popularity within a preset time period, the category to which the product belongs, the peak sales period and the actual inventory of the product in the basic information, and the activity data of the product in the time period corresponding to the issuing wave to obtain the first predicted sales volume.

[0125] Step S32: Calculate the first predicted sales volume and commodity data to obtain a target predicted sales volume.

[0126] In the specific implementation of step S32, the sum of the first predicted sales volume and the commodity data is calculated to obtain the target predicted sales volume.

[0127] Step S207: Send the target predicted sales volume to the production storage warehouse, so that the production storage warehouse prepares to produce the goods of the goods based on the target predicted sales volume, and produces the goods based on the goods prepared to produce the goods.

[0128] In the embodiment of the present invention, the basic information and product data of the product are processed by a pre-built prediction model to determine the target predicted sales volume of the product in the corresponding time period of the current delivery wave, and the production storage warehouse prepares to produce the goods of the product based on the target predicted sales volume to prepare the goods in advance, and produces the goods based on the production time. In this way, the impact on the customer's shopping experience can be reduced while the production cost is controllable.

[0129] Based on the commodity processing method shown above, the embodiment of the present invention also discloses a flowchart of another commodity processing method, such as Figure 3 As shown, the method includes:

[0130] Step S301: The sales server obtains basic information of the product.

[0131] Step S302: Determine whether the basic information meets the preset requirements. If so, execute step S303. If not, do not predict the product, that is, remove the basic information of the product.

[0132] Step S303: Determine a production volume forecast for the commodity.

[0133] Step S304: Determine whether the current time triggers the sending of waves. If it is determined that the current time triggers the sending of waves, execute step S305; if not, continue to execute step S304.

[0134] Step S305: Obtain the commodity data of the previous delivery wave.

[0135] In the specific implementation of step S305, the commodity data of the previous delivery wave is obtained from the storage warehouse.

[0136] Step S306: Processing is performed based on the basic information and product data to obtain the target predicted sales volume of the product for the time period corresponding to the current delivery wave.

[0137] Step S307: Correct the target forecast sales volume to obtain a corrected target forecast sales volume.

[0138] In the specific implementation of step S307, the target forecast sales volume is processed according to the units entering the warehouse to obtain a revised target forecast sales volume.

[0139] For example, if the target forecast sales volume is 18 bags, if warehouse A enters the warehouse by bag, 18 / 7 is rounded to 2, and then 2*7 is calculated to get 14 bags. The revised target forecast sales volume is 14 bags.

[0140] Step S308: Send the revised target forecast sales volume to the production storage warehouse, so that the production storage warehouse prepares to produce the goods of the goods based on the target forecast sales volume, and produces the goods based on the goods prepared to produce the goods.

[0141] In an embodiment of the present invention, the basic information and product data of the product are processed by a pre-built forecast model to determine the target forecast sales volume for the time period corresponding to the current wave of product delivery; the target forecast sales volume is corrected to obtain the corrected target forecast sales volume. The production storage warehouse prepares to produce the goods of the product based on the corrected target forecast sales volume to prepare the goods in advance and to produce the goods based on the production time. This can reduce the impact on the customer's shopping experience while keeping the production cost controllable.

[0142] Based on the commodity processing method shown above, before the prediction model is used, Figure 4 As shown, the following steps are also included:

[0143] Step S401: when it is determined that the current time triggers a distribution wave, the actual sales volume and the target predicted sales volume of the commodity in the time period corresponding to the previous distribution wave are obtained.

[0144] Step S402: Calculate the prediction accuracy based on the actual sales volume of the product in the time period corresponding to the previous delivery wave and the target predicted sales volume.

[0145] In the specific implementation of step S402, the actual sales volume real_qtty of the commodity in the time period corresponding to the previous delivery wave and the target predicted sales volume pred are input into formula (1) for calculation to obtain the prediction accuracy P.

[0146] Formula 1:

[0147] P=1-(abs(90%pred-90%real_qtty)) / (90%real_qtty) (1)

[0148] Among them, P is the prediction accuracy, real_qtty is the actual sales volume, and pred is the target predicted sales volume.

[0149] Step S403: Determine whether the prediction accuracy is higher than or equal to the preset probability. If the prediction accuracy is higher than or equal to the preset probability, execute step S404; if the prediction accuracy is lower than the preset probability, execute step S405.

[0150] In the specific implementation of step S403, the prediction accuracy is compared with the preset probability. If the prediction accuracy is higher than or equal to the preset probability, step S404 is executed; if the prediction accuracy is lower than the preset probability, step S405 is executed.

[0151] It should be noted that the preset probability is set by technical personnel based on actual conditions.

[0152] Step S404: Determine whether the prediction model can be used.

[0153] It should be noted that it is determined that step S206 can be executed at this time.

[0154] Step S405: updating the prediction model to obtain an updated prediction model.

[0155] In the process of specifically implementing step S405, the prediction model is trained with the actual sales volume of the product in the time period corresponding to the previous wave, the target predicted sales volume, and the activities in which the product is located, until the prediction accuracy corresponding to the prediction result output by the trained prediction model is greater than the preset probability, and an updated prediction model is determined. At this time, the prediction model can be used to execute step S206.

[0156] In the embodiment of the present invention, when determining the current time triggering the next wave, the prediction accuracy is calculated by the actual sales volume of the commodity in the corresponding time period of the previous next wave and the target predicted sales volume. And the prediction accuracy is given to determine whether the current prediction model can be used directly. The prediction of subsequent commodity sales volume is more accurate.

[0157] Based on the commodity processing method shown in the above embodiment of the present invention, the embodiment of the present invention also discloses a schematic diagram of the architecture of a commodity processing device, such as Figure 5 The device shown comprises:

[0158] The first acquisition unit 501 is used to acquire basic information of the product;

[0159] A determination unit 502, configured to determine a production volume forecast for the commodity when it is determined that the basic information meets a preset requirement;

[0160] The second acquisition unit 503 is used to determine the current time triggering the distribution wave and obtain the commodity data of the previous distribution wave;

[0161] The processing unit 504 is used to process the basic information and the commodity data to obtain the target predicted sales volume of the commodity in the time period corresponding to the current delivery wave;

[0162] The sending unit 505 is used to send the target predicted sales volume to the production storage warehouse, so that the production storage warehouse prepares to produce the goods of the goods based on the target predicted sales volume, and produces the goods based on the goods prepared to produce the goods.

[0163] It should be noted that the specific principles and execution processes of each unit in the commodity processing device disclosed in the above-mentioned embodiment of the present application are the same as the commodity processing method shown in the above-mentioned implementation of the present application. Please refer to the corresponding parts of the commodity processing method disclosed in the above-mentioned embodiment of the present application, and no further details will be given here.

[0164] In the embodiment of the present invention, the basic information and product data of the product are processed by a pre-built prediction model to determine the target predicted sales volume of the product in the corresponding time period of the current delivery wave, and the production storage warehouse prepares to produce the goods of the product based on the target predicted sales volume to prepare the goods in advance, and produces the goods based on the production time. In this way, the impact on the customer's shopping experience can be reduced while the production cost is controllable.

[0165] Optionally, based on the commodity processing device shown in the above embodiment of the present invention, the determining unit 502 is specifically used to: determine whether the historical sales volume of the commodity in the basic information within a preset time period meets a preset quantity;

[0166] Determine whether the popularity of the product in the basic information reaches a preset threshold within a preset time period;

[0167] Determine whether the category to which the product in the basic information belongs exists in the preset category;

[0168] Determine whether the actual inventory quantity of the product in the basic information is the preset inventory quantity;

[0169] If it is determined that the sales volume of the commodity within the preset time period meets the preset quantity, the popularity of the commodity within the preset time period reaches the preset threshold, the commodity belongs to a preset category of commodities, or the actual inventory of the commodity in the basic information is not the preset inventory, it is determined that the basic information meets the preset requirements.

[0170] Optionally, based on the commodity processing device shown in the above embodiment of the present invention, the processing unit 504 includes a training unit 506, and the processing unit 504 is specifically used for:

[0171] Inputting the basic information into a pre-built prediction model, processing the basic information based on the prediction model, and outputting a first predicted sales volume of the commodity, wherein the prediction model is obtained through training by the training unit 506;

[0172] The first predicted sales volume and commodity data are calculated to obtain a target predicted sales volume.

[0173] Optionally, based on the commodity processing device shown in the above embodiment of the present invention, the training unit 506 is specifically used for:

[0174] Acquire a sample data set, wherein the sample data includes historical sales data, historical price data, historical activity data of the commodity in a historical period, and category data of the same category as the commodity;

[0175] The sample data set is used for training to obtain a trained prediction model.

[0176] Optionally, based on the commodity processing device shown in the above embodiment of the present invention, the processing unit 504 is further used to: when determining that the current time triggers the delivery wave, obtain the actual sales volume and target predicted sales volume of the commodity in the time period corresponding to the previous delivery wave;

[0177] Calculate the forecast accuracy based on the actual sales volume of the product in the corresponding time period of the previous delivery wave and the target forecast sales volume;

[0178] If the prediction accuracy is higher than or equal to the preset probability, it is determined that the prediction model can be used;

[0179] If the prediction accuracy is lower than the preset probability, the prediction model is updated to obtain an updated prediction model.

[0180] Optionally, based on the commodity processing device shown in the above embodiment of the present invention, the second acquisition unit 503 is further used to: acquire the actual sales volume of the commodity in the time period corresponding to the previous delivery wave;

[0181] If it is determined that the actual sales volume is inconsistent with the target predicted sales volume, calculating commodity data based on the actual sales volume and the target predicted sales volume, the commodity data including excess data or missing data;

[0182] The commodity data is stored.

[0183] Optionally, based on the commodity processing device shown in the above embodiment of the present invention, the processing unit 504 is further used for:

[0184] The target forecast sales volume is revised to obtain a revised target forecast sales volume.

[0185] The embodiment of the present invention also discloses an electronic device, which is used to run a database storage process, wherein the above-mentioned Figures 2 to 4 Publicly available product handling methods.

[0186] The embodiment of the present invention also discloses a computer storage medium, wherein the storage medium includes a storage database storage process, wherein when the database storage process is running, the device where the storage medium is located is controlled to execute the above Figures 2 to 4 Publicly available product handling methods.

[0187] In the context of the present disclosure, a computer storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0188] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0189] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0190] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A commodity processing method, characterized in that: Applied to a sales-end server, the sales-end server is connected to a production storage warehouse, and the method includes: Get basic information about the product; When it is determined that the basic information meets the preset requirements, determining a production volume forecast for the commodity; After determining the current time to trigger the distribution wave, obtain the product data of the previous distribution wave; Based on the basic information and product data, the target predicted sales volume of the product for the time period corresponding to the current delivery wave is obtained; The target predicted sales volume is sent to the production storage warehouse so that the production storage warehouse prepares to produce the goods of the goods based on the target predicted sales volume, and produces the goods based on the goods prepared to produce the goods.

2. The method according to claim 1, characterized in that Confirm that the basic information meets the preset requirements, including: Determine whether the historical sales volume of the commodity in the basic information within a preset time period meets the preset quantity; Determine whether the popularity of the product in the basic information reaches a preset threshold within a preset time period; Determine whether the category to which the product in the basic information belongs exists in the preset category; Determine whether the actual inventory quantity of the product in the basic information is the preset inventory quantity; If it is determined that the sales volume of the commodity within the preset time period meets the preset quantity, the popularity of the commodity within the preset time period reaches the preset threshold, and the commodity belongs to a preset category of commodities, the actual inventory quantity of the commodity in the basic information is not the preset inventory quantity, or it is determined that the basic information meets the preset requirements.

3. The method according to claim 1, characterized in that: The processing based on the basic information and the commodity data to obtain the target predicted sales volume of the commodity includes: Inputting the basic information into a pre-built prediction model, processing the basic information based on the prediction model, and outputting a first predicted sales volume of the commodity, wherein the prediction model is obtained by training based on a historical sample data set; The first predicted sales volume and commodity data are calculated to obtain a target predicted sales volume.

4. The method according to claim 1, characterized in that: The process of building a prediction model based on the historical sample data set includes: Acquire a sample data set, wherein the sample data includes historical sales data, historical price data, historical activity data of the commodity in a historical period, and category data of the same category as the commodity; The sample data set is used for training to obtain a trained prediction model.

5. The method according to claim 1, characterized in that Also includes: When determining that the current time triggers the distribution wave, the actual sales volume and the target predicted sales volume of the product in the corresponding time period of the previous distribution wave are obtained; Calculate the forecast accuracy based on the actual sales volume of the product in the corresponding time period of the previous delivery wave and the target forecast sales volume; If the prediction accuracy is higher than or equal to the preset probability, it is determined that the prediction model can be used; If the prediction accuracy is lower than the preset probability, the prediction model is updated to obtain an updated prediction model.

6. The method according to claim 1, characterized in that Also includes: Get the actual sales volume of the product in the corresponding time period of the previous delivery wave; If it is determined that the actual sales volume is inconsistent with the target predicted sales volume, calculating commodity data based on the actual sales volume and the target predicted sales volume, the commodity data including excess data or missing data; The commodity data is stored.

7. The method according to claim 1, characterized in that Also includes: The target forecast sales volume is revised to obtain a revised target forecast sales volume.

8. A commodity processing device, characterized in that: Applied to a sales-end server, the sales-end server is connected to a production storage warehouse, and the device includes: A first acquisition unit, used to acquire basic information of a product; A determination unit, configured to determine a production volume forecast for the commodity when it is determined that the basic information meets preset requirements; The second acquisition unit is used to determine the current time to trigger the distribution wave and obtain the commodity data of the previous distribution wave; A processing unit, configured to perform processing based on the basic information and the commodity data to obtain a target predicted sales volume for a time period corresponding to a current delivery wave of the commodity; The sending unit is used to send the target predicted sales volume to the production storage warehouse, so that the production storage warehouse prepares to produce the goods of the goods based on the target predicted sales volume, and produces the goods based on the goods prepared to produce the goods.

9. An electronic device, characterized in that: The electronic device is used to run a program, wherein the program, when running, executes the commodity processing method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The storage medium includes a storage program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the commodity processing method according to any one of claims 1 to 7.

Images