Method and apparatus for real-time inventory adjustment, electronic device and computer readable medium

Abstract

Embodiments of the present disclosure disclose a real-time inventory adjustment method and device, electronic equipment and computer readable medium. A specific embodiment of the method comprises: obtaining historical item flow-related information of a target item at a plurality of preset time points; performing data update processing on the historical item acquisition quantity in the historical item flow-related information sequence to obtain an updated item flow-related information sequence; performing summation processing on each updated item acquisition quantity in the updated item flow-related information sequence to obtain an updated item flow quantity set; generating a reference item flow-related information sequence based on the updated item flow-related information sequence; inputting the reference item flow-related information sequence into a pre-trained value relationship prediction model to obtain a value relationship group set; and determining value transfer-related information based on item-related information, a valuable information set and the value relationship group set. The embodiment adjusts the inventory in real time, thereby avoiding waste of resources.

Description

Technical Field

[0001] Embodiments of this disclosure relate to the field of computer technology, and more particularly to methods, apparatus, electronic devices, and computer-readable media for real-time inventory adjustment. Background Technology

[0002] Real-time inventory adjustments have a significant impact on the market. Timely and accurate inventory adjustments can effectively prevent resource waste. Currently, inventory adjustments are typically made by sales personnel at fixed times or using fixed methods.

[0003] However, when adjusting inventory using the above methods, the following technical problems often arise:

[0004] First, adjusting inventory at fixed times and using fixed methods makes it difficult to adjust inventory based on the relationship between real-time goods turnover and real-time inventory levels, leading to frequent instances of excess inventory and wasting resources in various sectors.

[0005] Second, previous value relationship predictions did not take into account the introduction of demand information for goods, resulting in value relationship predictions that did not match actual demand for goods, and consequently, inventory surpluses.

[0006] Third, it is difficult to determine valuable information about dynamic changes based on real-time goods turnover and real-time inventory levels, thus making it difficult to flexibly adjust inventory. Summary of the Invention

[0007] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0008] Some embodiments of this disclosure propose methods, apparatuses, electronic devices, and computer-readable media for real-time inventory adjustment to address one or more of the technical problems mentioned in the background section above.

[0009] Firstly, some embodiments of this disclosure provide a method for real-time inventory adjustment. The method includes: acquiring historical item circulation information related to a target item at multiple preset time points within a preset time period, obtaining a sequence of historical item circulation information, wherein the historical item circulation information in the sequence includes a set of historical item acquisition quantities, which is a set of historical item acquisition quantities from a previous preset time point to the current preset time point; performing data update processing on the historical item acquisition quantities that satisfy a first preset condition in each set of historical item acquisition quantities included in the historical item circulation information sequence to generate updated item circulation information, obtaining an updated item circulation information sequence, wherein the updated item circulation information in the sequence includes updated item circulation information... The information includes an updated set of item acquisition quantities; the acquisition quantities of each updated item included in the updated item acquisition quantity set in each updated item circulation related information sequence are summed to generate an updated item circulation volume, resulting in an updated item circulation volume set; in response to determining that the updated item circulation volume included in each updated item circulation related information sequence satisfies a second preset condition, a reference item circulation related information sequence is generated based on the updated item circulation related information sequence; the reference item circulation related information sequence is input into a pre-trained value relationship prediction model to obtain a value relationship set; a set of valuable information and the item-related information of the target item are acquired; based on the item-related information, the set of valuable information, and the set of value relationship sets, value transfer related information is determined.

[0010] In some embodiments, the above-mentioned item demand information is obtained through the following steps:

[0011] Obtain initial item requirements information;

[0012] Input the initial item requirement information above into the following formula to obtain the item requirement information:

[0013]

[0014] Where F represents the above-mentioned item demand information, f represents the above-mentioned initial item demand information, α represents the preset fitting parameter, T1 represents the current time point, T represents the preset time point, and t represents the time interval between the above-mentioned current time point and the above-mentioned preset time point.

[0015] In some embodiments, the aforementioned item-related information includes attribute information, remaining inventory, and price-related information; and

[0016] Based on the aforementioned information about the items, the aforementioned set of valuable information, and the aforementioned set of value relationships, the relevant information for value transfer is determined, including:

[0017] The first product value is obtained by multiplying the above attribute information and the value relationship group corresponding to the current time point in the above value relationship group set.

[0018] The first product value set is obtained by multiplying the above-mentioned first product value set with each piece of valuable information in the above-mentioned valuable information set.

[0019] The difference between the remaining inventory and the value relationship group corresponding to the current time point is calculated to obtain the first difference.

[0020] The first difference and the price-related information mentioned above are multiplied to obtain the second product value;

[0021] The difference between each of the first product values ​​in the first product value set and the second product value is calculated to obtain the second difference value set.

[0022] The largest second difference in the aforementioned second difference set is determined as the target difference;

[0023] The first product value corresponding to the above target difference is determined as the target first product value;

[0024] The valuable information corresponding to the first product value of the above objectives is identified as value transfer related information.

[0025] Secondly, some embodiments of this disclosure provide a real-time inventory adjustment device, comprising: a first acquisition unit configured to acquire historical item circulation-related information of a target item at multiple preset time points within a preset time period, thereby obtaining a sequence of historical item circulation-related information, wherein the historical item circulation-related information in the above-mentioned historical item circulation-related information sequence includes a set of historical item acquisition quantities, which is a set of historical item acquisition quantities from the previous preset time point to the current preset time point; and a data update processing unit configured to perform data update processing on the historical item acquisition quantities that satisfy a first preset condition in each set of historical item acquisition quantities included in the above-mentioned historical item circulation-related information sequence to generate updated item circulation-related information, thereby obtaining an updated item circulation-related information sequence, wherein the updated item circulation-related information in the above-mentioned updated item circulation-related information sequence includes an updated item acquisition quantity set. The following units are configured: a summation processing unit, configured to sum the acquisition quantities of each updated item in the set of updated item acquisition quantities included in each updated item circulation-related information in the above-mentioned updated item circulation-related information sequence, to generate an updated item circulation volume and obtain an updated item circulation volume set; a generation unit, configured to generate a reference item circulation-related information sequence based on the above-mentioned updated item circulation-related information sequence in response to determining that the updated item circulation volume included in each updated item circulation-related information in the above-mentioned updated item circulation-related information sequence meets a second preset condition; an input unit, configured to input the above-mentioned reference item circulation-related information sequence into a pre-trained value relationship prediction model to obtain a value relationship set; a second acquisition unit, configured to acquire a set of valuable information and the item-related information of the target item; and a determination unit, configured to determine value transfer-related information based on the above-mentioned item-related information, the above-mentioned set of valuable information, and the above-mentioned value relationship set.

[0026] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0027] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0028] The above-described embodiments of this disclosure have the following beneficial effects: By adjusting inventory in real-time according to the relationship between real-time item turnover and real-time inventory, the frequency of inventory surplus is reduced, effectively avoiding waste of resources. Specifically, the reason for resource waste is that adjusting inventory at fixed times using fixed methods makes it difficult to adjust inventory based on the relationship between real-time item turnover and real-time inventory. Therefore, the real-time inventory adjustment method of some embodiments of this disclosure first obtains historical item turnover information related to the target item at multiple preset time points within a preset time period, resulting in a historical item turnover information sequence. This sequence includes a set of historical item acquisition quantities, which represents multiple historical item acquisition quantities from the previous preset time point to the current preset time point. Thus, future item turnover information can be predicted using historical item turnover information. Then, for each set of historical item acquisition quantities included in the aforementioned historical item circulation related information sequence, the historical item acquisition quantities that meet the first preset condition can be updated to generate updated item circulation related information, resulting in an updated item circulation related information sequence. This updated item circulation related information sequence includes an updated item acquisition quantity set. This allows for updating abnormal data (e.g., group-buying data) in the historical item acquisition quantity set, thereby predicting more realistic value relationship groups. Next, the updated item acquisition quantities in each updated item acquisition quantity set included in the aforementioned updated item circulation related information sequence can be summed to generate updated item circulation volume, resulting in an updated item circulation volume set. This allows for obtaining updated item circulation volumes at multiple preset time points after removing abnormal data. Then, in response to determining that the updated item circulation volumes included in each updated item circulation related information sequence satisfy the second preset condition, a reference item circulation related information sequence can be generated based on the aforementioned updated item circulation related information sequence. Therefore, even if a target item sells out ahead of schedule, the system can reconstruct the item circulation information within a preset time period assuming sufficient inventory. Then, the aforementioned reference item circulation information sequence can be input into a pre-trained value relationship prediction model to obtain a value relationship set. This allows for real-time prediction of the target item's circulation volume under different discounts. Finally, the system acquires a set of valuable information and the aforementioned item-related information for the target item; and based on this item-related information, the set of valuable information, and the set of value relationship sets, it determines value transfer information.Therefore, by adjusting inventory based on the relationship between real-time goods turnover and real-time inventory levels, the frequency of excess inventory is reduced, effectively avoiding waste of resources in various sectors. Attached Figure Description

[0029] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0030] Figure 1 This is a schematic diagram illustrating an application scenario of the real-time inventory adjustment method according to some embodiments of this disclosure;

[0031] Figure 2 This is a flowchart of some embodiments of the real-time inventory adjustment method according to this disclosure;

[0032] Figure 3 These are schematic diagrams illustrating the structure of some embodiments of the real-time inventory adjustment device according to this disclosure;

[0033] Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0034] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0035] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0036] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0037] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0038] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0039] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0040] Figure 1 This is a schematic diagram illustrating an application scenario of the real-time inventory adjustment method according to some embodiments of this disclosure.

[0041] exist Figure 1 In the application scenario, firstly, the computing device 101 can acquire historical item circulation information related to the target item at multiple preset time points within a preset time period, obtaining a historical item circulation information sequence 102. This sequence includes a set of historical item acquisition quantities, which represents multiple historical item acquisition quantities from the previous preset time point to the current preset time point. Then, the computing device 101 can update the historical item acquisition quantities that satisfy a first preset condition within each set of historical item acquisition quantities included in the historical item circulation information sequence 102 to generate updated item circulation information, resulting in an updated item circulation information sequence 103. This sequence includes an updated item acquisition quantity set. Next, the computing device 101 can sum the updated item acquisition quantities within each updated item acquisition quantity set included in each updated item circulation information sequence 103 to generate an updated item circulation volume, resulting in an updated item circulation volume set 104. Subsequently, in response to determining that the updated item circulation related information included in each of the updated item circulation related information sequences 103 meets a second preset condition, the computing device 101 generates a reference item circulation related information sequence 105 based on the updated item circulation related information sequence 103. Then, the computing device 101 inputs the reference item circulation related information sequence 105 into a pre-trained value relationship prediction model 106 to obtain a value relationship set 107. Next, the computing device 101 acquires a valuable information set 108 and the item-related information 109 of the target item. Finally, the computing device 101 determines value transfer related information 110 based on the item-related information 109, the valuable information set 108, and the value relationship set 107.

[0042] It should be noted that the aforementioned computing device 101 can be either 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 software, it can be installed within the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0043] It should be understood that Figure 1 The number of computing devices shown is merely illustrative. Any number of computing devices can be used depending on implementation needs.

[0044] Continue to refer to Figure 2 The diagram illustrates a flow 200 of some embodiments of a real-time inventory adjustment method according to the present disclosure. This real-time inventory adjustment method includes the following steps:

[0045] Step 201: Obtain historical item circulation information of the target item at multiple preset time points within a preset time period to obtain a sequence of historical item circulation information.

[0046] In some embodiments, the entity executing the real-time inventory adjustment method (e.g., Figure 1 The computing device 101 shown can acquire historical item circulation information of a target item at multiple preset time points within a preset time period, obtaining a sequence of historical item circulation information. The historical item circulation information in this sequence includes a set of historical item acquisition quantities. This set of historical item acquisition quantities represents the acquisition quantities of multiple historical items from the previous preset time point to the current preset time point.

[0047] It should be noted that "real-time" in this application refers to the hour (e.g., 8:00 AM or 9:00 AM, etc.). Smaller granular real-time is not applicable in the application scenario of this application because historical item flow information (e.g., sales volume) will not change significantly in a short period of time (e.g., 1 minute or 10 minutes).

[0048] As an example, the above-mentioned information related to the flow of historical items includes the set of historical item acquisition quantities, which can be multiple order information for the target item between 8:00 AM and 9:00 AM. The set of historical item acquisition quantities can be [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2 ...

[0049] Step 202: For each set of historical item acquisition quantities included in the historical item transfer information sequence, the historical item acquisition quantities that meet the first preset condition are updated to generate updated item transfer information, thus obtaining the updated item transfer information sequence.

[0050] In some embodiments, the executing entity may update the data of historical item acquisition quantities that meet a first preset condition within the set of historical item acquisition quantities included in each historical item transfer-related information sequence to generate updated item transfer-related information, thus obtaining an updated item transfer-related information sequence. The updated item transfer-related information in the updated item transfer-related information sequence includes an updated set of item acquisition quantities. The first preset condition may be that the number of historical item acquisitions exceeds a predetermined threshold.

[0051] In some optional implementations of certain embodiments, the execution entity performs data update processing on the historical item acquisition quantity that meets the first preset condition in the set of historical item acquisition quantities included in each historical item transfer related information sequence to generate updated item transfer related information. This may include the following steps:

[0052] The first step is to determine the mean and standard deviation of the acquisition quantity of each historical item in the set of historical item acquisition quantities, which includes the above-mentioned information on the circulation of historical items.

[0053] As an example, the set of historical item acquisition quantities could be [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2 ...9,9,9,9,9,9,9,9,9,9,9,9,100]. The mean and standard deviation of the above set of historical item acquisition quantities are approximately 3.45 and 10.96, respectively.

[0054] The second step is to generate a comparison update value based on the mean and standard deviation mentioned above.

[0055] As an example, the sum of the mean and three times the standard deviation can be used to obtain the updated value. For example, 3.45 + 3 * 10.96 = 36.32. 36.32 can be the updated value.

[0056] The third step is to use the above-mentioned comparison update value to replace the historical item acquisition quantity in the set of historical item acquisition quantities that is greater than the above-mentioned comparison update value, in order to obtain updated item transfer information.

[0057] As an example, the number 100 in the historical item acquisition quantity set is greater than 36.32. Therefore, the number 100 in the historical item acquisition quantity set is replaced with 36.32. This can remove abnormally large orders caused by group buying or some unknown factors, thus improving the accuracy of prediction. The updated item circulation information includes the set of updated item acquisition quantities, which can be [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2 ...

[0058] Step 203: Sum the quantities of each updated item acquired in the set of updated item acquisition quantities included in each updated item circulation related information sequence to generate the updated item circulation volume and obtain the updated item circulation volume set.

[0059] In some embodiments, the execution entity may sum up the quantities of each updated item acquired in the set of updated item acquisition quantities included in each updated item circulation-related information sequence to generate an updated item circulation volume and obtain an updated item circulation volume set.

[0060] As an example, summing the set of updated item acquisition quantities [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,2 ...9,9,9,9,9,9,9,9,9,9,36.32], which includes information related to updated item circulation, yields an updated item circulation quantity of 222.21.

[0061] Step 204: In response to determining that the updated item circulation volume included in each updated item circulation related information in the updated item circulation related information sequence meets the second preset condition, a reference item circulation related information sequence is generated based on the updated item circulation related information sequence.

[0062] In some embodiments, the execution entity may, in response to determining that the updated item circulation volume included in each of the updated item circulation related information sequences in the updated item circulation related information sequence meets a second preset condition, generate a reference item circulation related information sequence based on the updated item circulation related information sequence.

[0063] In some optional implementations of certain embodiments, the execution entity, in response to determining that the updated item circulation volume included in each updated item circulation-related information in the updated item circulation-related information sequence meets a second preset condition, generates a reference item circulation-related information sequence based on the updated item circulation-related information sequence, which may include the following steps:

[0064] The first step is to determine whether the updated item circulation volume included in each updated item circulation-related information sequence is equal to the preset historical inventory volume.

[0065] The second step is to determine whether there is at least one updated item turnover quantity with a value of 0 among the updated item turnover quantities included in each updated item turnover related information in the above-mentioned updated item turnover related information sequence, since the updated item turnover quantity included in each updated item turnover related information in the above-mentioned updated item turnover related information sequence is equal to the preset historical inventory quantity.

[0066] The third step is to determine the percentage of the total number of updated items in each updated item circulation information in the above-mentioned updated item circulation information sequence if at least one updated item circulation quantity is 0.

[0067] The fourth step is to sum up the non-zero values ​​of the updated item circulation quantities in each updated item circulation related information sequence to obtain the actual item circulation quantity.

[0068] Fifth, based on the above-mentioned updated item circulation information sequence, the above-mentioned item circulation volume ratio, and the above-mentioned actual item circulation volume, a reference item circulation information sequence is generated. For example, the above-mentioned actual item circulation volume could be the item circulation volume when the target item sells out very early on the same day.

[0069] As an example, the target item could be a perishable item, which is a special case. For instance, some high-quality items might sell out quickly, potentially very early in the day, meaning the sales data for that day wouldn't reflect true demand. If sales forecasts are based on these actual sales, the predicted sales will be affected, resulting in an underestimation. Therefore, a sell-out restoration is necessary. This can be done using the following method, with a preset time period of [8:00, 21:00), totaling 13 hours. Log records show that sales during [20:00, 21:00] account for 1 / 13 of the total daily sales. If the target item is sold out by 20:00, and the sales volume in the 12 hours before 20:00 was 120, then the formula for restoring sales during [20:00, 21:00] is: (120 / (12 / 13))*1 / 13=120*(1 / 12)=10. The total sales for the day were updated from 120 to 120 + 10 = 130. This allows us to reconstruct the item turnover information within a preset time period assuming sufficient inventory of the target item.

[0070] Step 205: Input the relevant information sequence of the reference item circulation into the pre-trained value relationship prediction model to obtain a set of value relationship groups.

[0071] In some embodiments, the executing entity can input the aforementioned reference item circulation-related information sequence into a pre-trained value relationship prediction model to obtain a set of value relationship groups. This set of value relationship groups can be a collection of multiple time points. One time point can predict one value relationship group. For example, the aforementioned value relationship group at 2 PM could be: {[No discount: Sales volume corresponding to no discount], [Discount of 10%: Sales volume corresponding to 10% discount], [Discount of 20%: Sales volume corresponding to 20% discount], [Discount of 30%: Sales volume corresponding to 30% discount], [Discount of 40%: Sales volume corresponding to 40% discount], [Discount of 50%: Sales volume corresponding to 50% discount], [Discount of 60%: Sales volume corresponding to 60% discount], [Discount of 70%: Sales volume corresponding to 70% discount], [Discount of 80%: Sales volume corresponding to 80% discount], [Discount of 90%: Sales volume corresponding to 90% discount]}}.

[0072] Optionally, the training sample features of the aforementioned pre-trained value relationship prediction model include: historical goods circulation information, holiday information, payment information, real-time goods circulation information, and goods demand information. Among them, the aforementioned real-time goods circulation information includes: goods circulation volume between the first preset time point and the second preset time point, cumulative goods circulation volume, and goods circulation volume ratio. The holiday information includes: weekday information, non-working day information, and holiday information.

[0073] As an example, the percentage of goods turnover can be the ratio of hourly goods turnover (e.g., sales volume) to the previous hour's goods turnover (e.g., sales volume). The time periods during which users perform value transfer operations (e.g., shopping) typically differ between weekdays and non-weekdays. For instance, on weekdays, working users can only perform value transfer operations after get off work, while on non-weekdays, they can usually complete these operations in the morning. Therefore, the distribution of real-time goods turnover (e.g., real-time sales volume) differs significantly between weekdays and non-weekdays, and can be used as a feature for model training. Goods demand information (e.g., goods freshness) is closely related to users performing value transfer operations; therefore, user demand can also be used as a feature for model training. The amount of data for fresh produce is usually not particularly large, making deep learning models unsuitable. LightGBM, which performs well on small datasets, can be chosen instead. LightGBM is a machine learning model that performs numerical predictions by non-linearly fitting data features.

[0074] Optionally, the above-mentioned item demand information is obtained through the following steps:

[0075] The first step is to obtain the initial item requirements information.

[0076] The second step is to input the initial item requirement information into the following formula to obtain the item requirement information:

[0077]

[0078] Where F represents the aforementioned item demand information. f represents the aforementioned initial item demand information. α represents the preset fitting parameters. T1 represents the current time point. T represents the preset time point. t represents the time interval between the aforementioned current time point and the aforementioned preset time point.

[0079] The above formula, as an inventive point of this disclosure, solves the second technical problem mentioned in the background art: "Previous value relationship predictions did not take into account the introduction of item demand information, thus making the value relationship predictions inconsistent with actual item demand, leading to inventory surplus." Factors leading to inventory surplus often include: previous value relationship predictions did not take into account the introduction of item demand information, thus making the value relationship predictions inconsistent with actual item demand. Solving these factors can improve inventory turnover efficiency. To achieve this effect, firstly, item demand information (e.g., item freshness) is considered when predicting value relationships. In practice, item demand information is closely related to customer traffic and the probability of users performing value transfers. The higher the freshness of an item, the greater the user demand for that item. The lower the freshness of an item, the smaller the user demand for that item. Item demand information is closely related to initial item demand information and time. As time goes on, item demand information gradually decreases. Simultaneously, when the initial item demand information is high, the item demand information at the current time point is also relatively high. By using initial item demand information, preset fitting parameters, and time interval values, the item demand information at the current point in time is determined in real time. Therefore, by incorporating item demand information for prediction, the predicted value relationships more accurately reflect actual item demand, thereby improving inventory turnover efficiency and effectively preventing inventory backlog.

[0080] Step 206: Obtain a set of valuable information and item-related information for the target item.

[0081] In some embodiments, the aforementioned executing entity may acquire a set of valuable information (e.g., discount information) and item-related information of the aforementioned target item.

[0082] Step 207: Based on the item-related information, the set of valuable information, and the set of value relationship groups, determine the value transfer-related information.

[0083] In some embodiments, the executing entity may determine value transfer-related information based on the aforementioned item-related information, the aforementioned set of valuable information, and the aforementioned set of value relationship groups. Value transfer-related information may be valuable information (e.g., discount information) that maximizes the target value (e.g., revenue).

[0084] In some optional implementations of certain embodiments, the execution entity determines value transfer-related information based on the aforementioned item-related information, the aforementioned set of valuable information, and the aforementioned set of value relationship groups. The item-related information includes attribute information (e.g., price), remaining inventory (e.g., remaining inventory for the day), and price-related information (e.g., unit cost of unsold items). This may include the following steps:

[0085] The first step is to perform a product operation on the above attribute information and the value relationship group corresponding to the current time point in the above value relationship group set to obtain the first product value.

[0086] The second step is to perform product calculation on the first product value set and each piece of valuable information in the valuable information set to obtain the first product value set.

[0087] The third step is to calculate the difference between the remaining inventory and the value relationship group corresponding to the current time point to obtain the first difference.

[0088] The fourth step is to multiply the first difference and the price-related information to obtain the second product value.

[0089] The fifth step is to calculate the difference between each of the first product values ​​in the first product value set and the second product value to obtain the second difference value set.

[0090] The sixth step is to determine the largest second difference in the aforementioned second difference set as the target difference. Constraints can be added when determining the target difference. For example, the sum of historical item circulation information generated on the current day and the value relationship group corresponding to the current time point must be greater than a predetermined threshold.

[0091] Step 7: Determine the first product value corresponding to the above target difference as the target first product value.

[0092] The eighth step is to identify the valuable information corresponding to the first product value of the above objectives as value transfer related information.

[0093] It should be noted that the obtained value transfer information (e.g., discount information) can use customer traffic as a constraint. Generally, larger discounts usually lead to larger customer traffic, and smaller discounts usually lead to smaller customer traffic. When the determined value transfer information leads to a decrease in customer traffic, it is necessary to comprehensively consider the impact of customer traffic and other factors, and adjust the value transfer information accordingly. This will allow us to obtain the optimal inventory adjustment strategy.

[0094] Optionally, the aforementioned implementing entity may also determine value transfer-related information based on item-related information, a set of valuable information, and a set of value relationship groups using the following formula:

[0095]

[0096] Where R represents value transfer related information, which can characterize the valuable information (e.g., discount information) that maximizes the target value (e.g., revenue). Max[] represents finding the maximum value. p represents attribute information. d represents the valuable information in the value relationship group corresponding to the current time point in the value relationship group set. pre represents the value transfer amount corresponding to the valuable information in the value relationship group corresponding to the current time point in the value relationship group set (e.g., sales volume for the remaining time of the day). s represents the remaining inventory. w represents price related information. dayhis represents the historical value transfer amount that has been generated on the current day (e.g., historical sales volume that has been generated on the current day). thr represents the preset value transfer amount threshold that a certain item needs to reach on the current day. Other constraints can be added according to the actual situation.

[0097] Step 207 above, as an inventive point of this disclosure, solves the third technical problem mentioned in the background art: "It is difficult to determine dynamically changing valuable information based on real-time item turnover and real-time inventory, thus making it difficult to flexibly adjust inventory." Factors leading to the difficulty in flexibly adjusting inventory often include: difficulty in determining dynamically changing valuable information based on real-time item turnover and real-time inventory. Solving these factors allows for flexible inventory adjustments. To achieve this, firstly, it is considered that the optimal valuable information is the information that maximizes revenue. Therefore, by using attribute information, a set of valuable information (e.g., 10 pieces of valuable information ranging from 10% to 90% off, without discounts), and a predicted value relationship set corresponding to the current time point, the maximum revenue under various discounts is obtained. Furthermore, considering the impact of cost on revenue, remaining inventory and price-related information (e.g., the unit cost of unsold items) are introduced. And based on the remaining inventory, the predicted value relationship set corresponding to the current time point, and the price-related information, the total cost of unsold items is obtained. By analyzing revenue from various discounts and the total cost of unsold items, we can identify the most valuable information relevant to value transfer. Therefore, based on real-time inventory turnover and inventory levels, we can determine dynamically changing valuable information, allowing for flexible inventory adjustments.

[0098] Optionally, the aforementioned executing entity may generate demand information for goods based on the aforementioned value transfer information. Then, this demand information is sent to a robot that performs inventory adjustments, allowing the robot to adjust the inventory accordingly.

[0099] Optionally, the aforementioned value transfer information can be sent to relevant terminal devices for real-time broadcasting. This can increase customer traffic, thereby increasing the turnover rate of goods and effectively reducing inventory accumulation.

[0100] The above-described embodiments of this disclosure have the following beneficial effects: By adjusting inventory in real-time according to the relationship between real-time item turnover and real-time inventory, the frequency of inventory surplus is reduced, effectively avoiding waste of resources. Specifically, the reason for resource waste is that adjusting inventory at fixed times using fixed methods makes it difficult to adjust inventory based on the relationship between real-time item turnover and real-time inventory. Therefore, the real-time inventory adjustment method of some embodiments of this disclosure first obtains historical item turnover information related to the target item at multiple preset time points within a preset time period, resulting in a historical item turnover information sequence. This sequence includes a set of historical item acquisition quantities, which represents multiple historical item acquisition quantities from the previous preset time point to the current preset time point. Thus, future item turnover information can be predicted using historical item turnover information. Then, for each set of historical item acquisition quantities included in the aforementioned historical item circulation related information sequence, the historical item acquisition quantities that meet the first preset condition can be updated to generate updated item circulation related information, resulting in an updated item circulation related information sequence. This updated item circulation related information sequence includes an updated item acquisition quantity set. This allows for updating abnormal data (e.g., group-buying data) in the historical item acquisition quantity set, thereby predicting more realistic value relationship groups. Next, the updated item acquisition quantities in each updated item acquisition quantity set included in the aforementioned updated item circulation related information sequence can be summed to generate updated item circulation volume, resulting in an updated item circulation volume set. This allows for obtaining updated item circulation volumes at multiple preset time points after removing abnormal data. Then, in response to determining that the updated item circulation volumes included in each updated item circulation related information sequence satisfy the second preset condition, a reference item circulation related information sequence can be generated based on the aforementioned updated item circulation related information sequence. Therefore, even if a target item sells out ahead of schedule, the system can reconstruct the item circulation information within a preset time period assuming sufficient inventory. Then, the aforementioned reference item circulation information sequence can be input into a pre-trained value relationship prediction model to obtain a set of value relationship groups. This allows for real-time prediction of the target item's circulation volume under different discounts. Finally, the system obtains a set of valuable information and the aforementioned item-related information for the target item; and based on this item-related information, the set of valuable information, and the set of value relationship groups, it determines value transfer information.Therefore, by adjusting inventory based on the relationship between real-time goods turnover and real-time inventory levels, the frequency of excess inventory is reduced, effectively avoiding waste of resources in various sectors.

[0101] Further reference Figure 3 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a real-time inventory adjustment device, which are similar to... Figure 2 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0102] like Figure 3 As shown, the real-time inventory adjustment device 300 in some embodiments includes: a first acquisition unit 301, a data update processing unit 302, a summation processing unit 303, a generation unit 304, an input unit 305, a second acquisition unit 306, and a determination unit 307. The first acquisition unit 301 is configured to acquire historical item circulation information related to a target item at multiple preset time points within a preset time period, obtaining a sequence of historical item circulation information related to the target item. The historical item circulation information related to the target item includes a set of historical item acquisition quantities, which represents multiple historical item acquisition quantities from the previous preset time point to the current preset time point. The data update processing unit 302 is configured to perform data update processing on the historical item acquisition quantities that meet a first preset condition in each set of historical item acquisition quantities included in the historical item circulation information related to the target item circulation information sequence to generate updated item circulation information related to the target item circulation, obtaining an updated item circulation information related to the target item circulation, wherein the updated item circulation information related to the target item circulation includes a set of updated item acquisition quantities. The summation processing unit 303 is configured to perform data update processing on the historical item acquisition quantities that meet a first preset condition in each set of historical item acquisition quantities included in the historical item circulation information related to the target item circulation information sequence, generating updated item circulation information related to the target item circulation, obtaining an updated item circulation information related to the target item circulation, obtaining a sequence of updated item circulation information related to the target item circulation, wherein the updated item circulation information related to the target item circulation includes a set of updated item acquisition quantities. The summation processing unit 303 is configured to perform data update processing on the historical item circulation information related to the target item circulation, obtaining a sequence of updated item circulation information related to the target item circulation, obtaining a sequence of updated item circulation information related to the target item circulation, wherein the updated item circulation information related to the target item circulation includes a set of updated item acquisition quantities. The update item circulation related information sequence includes summing the acquisition quantities of each updated item in the updated item acquisition quantity set to generate an updated item circulation volume, thus obtaining an updated item circulation volume set; the generation unit 304 is configured to generate a reference item circulation related information sequence based on the updated item circulation related information sequence in response to determining that the updated item circulation volume included in each updated item circulation related information sequence meets a second preset condition; the input unit 305 is configured to input the reference item circulation related information sequence into a pre-trained value relationship prediction model to obtain a value relationship set; the second acquisition unit 306 is configured to acquire a valuable information set and item-related information of the target item; the determination unit 307 is configured to determine value transfer related information based on the item-related information, the valuable information set, and the value relationship set.

[0103] It is understandable that the units described in the device 300 are related to the reference. Figure 2 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 300 and the units contained therein, and will not be repeated here.

[0104] The following is for reference. Figure 4 It illustrates electronic devices suitable for implementing some embodiments of the present disclosure (such as...). Figure 1 The diagram shows the structure of the computing device 101)400. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0105] like Figure 4 As shown, electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. RAM 403 also stores various programs and data required for the operation of electronic device 400. Processing device 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0106] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 4 Each box shown can represent a device or multiple devices as needed.

[0107] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from storage device 408, or installed from ROM 402. When the computer program is executed by processing device 401, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0108] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0109] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0110] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: acquire historical item circulation information related to a target item at multiple preset time points within a preset time period, obtaining a sequence of historical item circulation information, wherein the historical item circulation information in the aforementioned historical item circulation information sequence includes a set of historical item acquisition quantities, which is a set of historical item acquisition quantities from the previous preset time point to the current preset time point; perform data update processing on the historical item acquisition quantities that satisfy a first preset condition in each set of historical item acquisition quantities included in the aforementioned historical item circulation information sequence to generate updated item circulation information, obtaining an updated item circulation information sequence, wherein the updated item circulation information sequence contains updated item circulation information. The new item circulation information includes an updated item acquisition quantity set; the updated item acquisition quantities in each updated item acquisition quantity set included in the updated item circulation information sequence are summed to generate an updated item circulation volume, resulting in an updated item circulation volume set; in response to determining that the updated item circulation volume included in each updated item circulation information sequence meets a second preset condition, a reference item circulation information sequence is generated based on the updated item circulation information sequence; the reference item circulation information sequence is input into a pre-trained value relationship prediction model to obtain a value relationship set; a valuable information set and the item-related information of the target item are obtained; based on the item-related information, the valuable information set, and the value relationship set, value transfer information is determined.

[0111] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0113] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a first acquisition unit, a data update processing unit, a summation processing unit, a generation unit, an input unit, a second acquisition unit, and a determination unit. The names of these units do not necessarily limit the specific unit itself; for example, the first acquisition unit may also be described as "a unit that acquires historical item circulation information related to a target item at multiple preset time points within a preset time period, and obtains a sequence of historical item circulation information."

[0114] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0115] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for real-time inventory adjustment, comprising: The historical item circulation information of the target item at multiple preset time points within a preset time period is obtained to obtain a historical item circulation information sequence. The historical item circulation information sequence includes a set of historical item acquisition quantities, which is a set of historical item acquisition quantities from the previous preset time point to the current preset time point. For each set of historical item acquisition quantities included in the historical item transfer related information sequence, the historical item acquisition quantities that meet the first preset condition are updated to generate updated item transfer related information, thus obtaining an updated item transfer related information sequence, wherein the updated item transfer related information in the updated item transfer related information sequence includes an updated item acquisition quantity set; The quantities of each updated item acquired in the set of updated item acquisition quantities included in each updated item circulation-related information in the updated item circulation-related information sequence are summed to generate the updated item circulation volume, thus obtaining the updated item circulation volume set. In response to determining that the updated item circulation volume included in each updated item circulation related information in the updated item circulation related information sequence meets the second preset condition, a reference item circulation related information sequence is generated based on the updated item circulation related information sequence. The relevant information sequence of the reference item circulation is input into a pre-trained value relationship prediction model to obtain a set of value relationship groups; Obtain a set of valuable information and item-related information of the target item; Based on the item-related information, the set of valuable information, and the set of value relationship groups, value transfer-related information is determined.

2. The method of claim 1, wherein, The method further includes: Based on the value transfer information, generate the demand information for the goods; The demand information for the items is sent to the robot that adjusts the inventory, so that the robot can adjust the inventory accordingly.

3. The method of claim 2, wherein, The step of updating the data on the number of historical items acquired that meet the first preset condition in the set of historical item acquisition quantities included in each historical item transfer-related information sequence to generate updated item transfer-related information includes: Determine the mean and standard deviation of the acquisition quantity of each historical item in the set of historical item acquisition quantities, which includes the relevant information on the circulation of historical items; Based on the mean and the standard deviation, a comparative update value is generated; Using the comparison update value, replace the historical item acquisition quantity in the historical item acquisition quantity set included in the historical item circulation information with the historical item acquisition quantity that is greater than the comparison update value to obtain the updated item circulation information.

4. The method according to claim 3, wherein, In response to determining that the updated item circulation volume included in each updated item circulation-related information in the updated item circulation-related information sequence meets a second preset condition, a reference item circulation-related information sequence is generated based on the updated item circulation-related information sequence, including: Determine whether the updated item circulation volume included in each updated item circulation related information in the updated item circulation related information sequence is equal to the preset historical inventory volume; In response to the fact that the updated item circulation volume included in each updated item circulation related information in the updated item circulation related information sequence is equal to the preset historical inventory volume, it is determined whether there is at least one updated item circulation volume with a value of 0 among the updated item circulation volumes included in each updated item circulation related information in the updated item circulation related information sequence. In response to the fact that at least one updated item circulation volume with a value of 0 exists in the updated item circulation volume included in each updated item circulation related information in the updated item circulation related information sequence, the item circulation volume percentage of the updated item circulation volume included in each updated item circulation related information in the updated item circulation related information sequence is determined. The actual item circulation volume is obtained by summing the non-zero values ​​of the updated item circulation volume included in each updated item circulation related information sequence. Based on the updated item circulation related information sequence, the item circulation volume ratio, and the actual item circulation volume, a reference item circulation related information sequence is generated.

5. The method according to claim 4, wherein, The training sample features of the pre-trained value relationship prediction model include: historical goods circulation information, holiday information, payment information, real-time goods circulation information, and goods demand information. The real-time goods circulation information includes: the goods circulation volume between the first preset time point and the second preset time point, the cumulative goods circulation volume, and the proportion of goods circulation volume. The holiday information includes: weekday information, non-working day information, and holiday information.

6. A real-time inventory adjustment device, comprising: The first acquisition unit is configured to acquire historical item circulation information of the target item at multiple preset time points within a preset time period, and obtain a sequence of historical item circulation information. The historical item circulation information in the sequence of historical item circulation information includes a set of historical item acquisition quantities, which is a set of historical item acquisition quantities from the previous preset time point to the current preset time point. The data update processing unit is configured to perform data update processing on the historical item acquisition quantity that meets the first preset condition in the set of historical item acquisition quantities included in each historical item transfer related information sequence to generate updated item transfer related information, thereby obtaining an updated item transfer related information sequence, wherein the updated item transfer related information in the updated item transfer related information sequence includes an updated item acquisition quantity set; The summation processing unit is configured to sum the quantities of each updated item acquired in the set of updated item acquisition quantities included in each updated item flow-related information in the updated item flow-related information sequence, so as to generate the updated item flow volume and obtain the updated item flow volume set. The generation unit is configured to generate a reference item flow-related information sequence based on the updated item flow-related information sequence in response to determining that the updated item flow-related information volume included in each updated item flow-related information sequence in the updated item flow-related information sequence meets a second preset condition. The input unit is configured to input the reference item circulation-related information sequence into a pre-trained value relationship prediction model to obtain a set of value relationship groups. The second acquisition unit is configured to acquire a set of valuable information and item-related information of the target item; The determining unit is configured to determine value transfer-related information based on the item-related information, the set of valuable information, and the set of value relationship groups.

7. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 5.

Images