Item recommendation method and apparatus, electronic device, and storage medium

Abstract

The application discloses an article recommendation method and device, an electronic device and a storage medium. On the one hand, the article recommendation method provided by the application can recommend articles for users when the users fill in the consignments, reduce the time for the users to fill in the waybills, and correct the sending fluctuation values of each candidate article by the average sending amount of the candidate articles when the target article is determined, so that the global fluctuation value which can more accurately represent the change of the sending amount with time is obtained, the problem that the sending fluctuation value of the small sample candidate article cannot accurately represent the change of the sending amount with time is solved, and the target article obtained is more accurate. On the other hand, the target article to be recommended can be determined without the information of a specific user, so that the cold start of the consignment article filling can be realized.

Description

Technical Field

[0001] This application relates to the field of product recommendation technology, specifically to a product recommendation method, apparatus, electronic device, and storage medium. Background Technology

[0002] To make things easier for users, express delivery and logistics companies have added an online waybill filling function to their self-developed software, which reduces the time users need to fill in waybills by hand and also reduces the probability of users making spelling mistakes when writing by hand.

[0003] However, although users can fill out waybills using electronic devices such as smartphones and personal computers, they still need to type the name of the item to be shipped, which is very time-consuming. Summary of the Invention

[0004] This application provides a method, apparatus, electronic device, and storage medium for recommending items, aiming to solve the problem of low recognition accuracy in current item recommendation methods.

[0005] Firstly, this application provides a method for recommending items, including:

[0006] Obtain logistics information;

[0007] Based on the shipping time and shipping quantity of each candidate item in the logistics information, determine the shipping fluctuation value of each candidate item;

[0008] The global fluctuation value of each candidate item is determined based on the shipment fluctuation value of each candidate item and the average shipment volume of candidate items in the logistics information.

[0009] Based on the global fluctuation value of each candidate item, a target item to be recommended is selected from the candidate items.

[0010] In one possible implementation of this application, determining the shipping fluctuation value of each candidate item based on the shipping time and shipping quantity of each candidate item in the logistics information includes:

[0011] Based on the shipping time of each candidate item in the logistics information, the shipping volume of each candidate item is divided to obtain the target shipping volume and the historical shipping volume of each candidate item.

[0012] The shipment fluctuation value of each candidate item is calculated based on the target shipment volume and the historical shipment volume of each candidate item.

[0013] In one possible implementation of this application, determining the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment volume of candidate items in the logistics information includes:

[0014] Count the quantity of each candidate item in the logistics information;

[0015] Based on the total number of shipments for each candidate item and the quantity of the item, the average number of shipments for the candidate items in the logistics information is calculated.

[0016] The fluctuation correction coefficient for each candidate item is calculated based on the average shipment volume of the candidate items, the target shipment volume of each candidate item, and the historical shipment volume of each candidate item.

[0017] Based on the fluctuation correction coefficient, the shipping fluctuation value of each candidate item is weighted to obtain the global fluctuation value of each candidate item.

[0018] In one possible implementation of this application, selecting the target item to be recommended from the candidate items based on the global fluctuation value of each candidate item includes:

[0019] The global fluctuation value of each candidate item is compared with a preset score threshold to obtain candidate items whose global fluctuation value is greater than the preset score threshold;

[0020] Candidate items with global fluctuation values ​​greater than a preset score threshold are set as target items to be recommended.

[0021] In one possible implementation of this application, before determining the shipping fluctuation value of each candidate item based on the shipping time and shipping quantity of each candidate item in the logistics information, the method further includes:

[0022] Based on the shipping time of the first item in the logistics information, the number of shipments of the first item in each preset historical time period is counted.

[0023] The average rate of change in the number of shipments of the first item is calculated based on the number of shipments in each preset historical time period and the time intervals corresponding to each preset historical time period.

[0024] The first item whose average rate of change in shipment volume is less than a preset rate of change threshold is set as a candidate item.

[0025] In one possible implementation of this application, setting a first item whose average rate of change in shipment volume is less than a preset rate of change threshold as a candidate item includes:

[0026] From the shipping records of the target users to be recommended, obtain a second item whose total historical shipping volume is less than a first preset threshold.

[0027] Determine the user group to which the target user belongs;

[0028] From the shipping records of the user group, obtain the third item whose average shipping volume for the same period in history is less than the second preset number of times threshold.

[0029] The second and third items are removed from the first items, and the first item whose average change rate of shipment volume after removal is less than a preset change rate threshold is selected as a candidate item.

[0030] In one possible implementation of this application, after determining the target item to be recommended based on the shipment fluctuation value and shipment growth rate of each candidate item, the method further includes:

[0031] Receive the selection instruction from the target user to be recommended, and obtain the item corresponding to the selection instruction from the target items;

[0032] Enter the item corresponding to the selection instruction into the preset area of ​​the preset waybill.

[0033] Secondly, this application provides an item recommendation device, comprising:

[0034] The acquisition unit is used to acquire logistics information;

[0035] The first determining unit is used to determine the shipping fluctuation value of each candidate item based on the shipping time and shipping quantity of each candidate item in the logistics information;

[0036] The second determining unit is used to determine the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment quantity of candidate items in the logistics information.

[0037] The selection unit is used to select a target item to be recommended from the candidate items based on the global fluctuation value of each candidate item.

[0038] In one possible implementation of this application, the first determining unit is further configured to:

[0039] Based on the shipping time of each candidate item in the logistics information, the shipping volume of each candidate item is divided to obtain the target shipping volume and the historical shipping volume of each candidate item.

[0040] The shipment fluctuation value of each candidate item is calculated based on the target shipment volume and the historical shipment volume of each candidate item.

[0041] In one possible implementation of this application, the second determining unit is further configured to:

[0042] Count the quantity of each candidate item in the logistics information;

[0043] Based on the total number of shipments for each candidate item and the quantity of the item, the average number of shipments for the candidate items in the logistics information is calculated.

[0044] The fluctuation correction coefficient for each candidate item is calculated based on the average shipment volume of the candidate items, the target shipment volume of each candidate item, and the historical shipment volume of each candidate item.

[0045] Based on the fluctuation correction coefficient, the shipping fluctuation value of each candidate item is weighted to obtain the global fluctuation value of each candidate item.

[0046] In one possible implementation of this application, the selection unit is further configured to:

[0047] The global fluctuation value of each candidate item is compared with a preset score threshold to obtain candidate items whose global fluctuation value is greater than the preset score threshold;

[0048] Candidate items with global fluctuation values ​​greater than a preset score threshold are set as target items to be recommended.

[0049] In one possible implementation of this application, the first determining unit is further configured to:

[0050] Based on the shipping time of the first item in the logistics information, the number of shipments of the first item in each preset historical time period is counted.

[0051] The average rate of change in the number of shipments of the first item is calculated based on the number of shipments in each preset historical time period and the time intervals corresponding to each preset historical time period.

[0052] The first item whose average rate of change in shipment volume is less than a preset rate of change threshold is set as a candidate item.

[0053] In one possible implementation of this application, the first determining unit is further configured to:

[0054] From the shipping records of the target users to be recommended, obtain a second item whose total historical shipping volume is less than a first preset threshold.

[0055] Determine the user group to which the target user belongs;

[0056] From the shipping records of the user group, obtain the third item whose average shipping volume for the same period in history is less than the second preset number of times threshold.

[0057] The second and third items are removed from the first items, and the first item whose average change rate of shipment volume after removal is less than a preset change rate threshold is selected as a candidate item.

[0058] In one possible implementation of this application, the selection unit is further configured to:

[0059] Receive the selection instruction from the target user to be recommended, and obtain the item corresponding to the selection instruction from the target items;

[0060] Enter the item corresponding to the selection instruction into the preset area of ​​the preset waybill.

[0061] Thirdly, this application also provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor invokes the computer program in the memory, it executes the steps in any of the article recommendation methods provided in this application.

[0062] Fourthly, this application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the article recommendation methods provided in this application.

[0063] In summary, the item recommendation method provided in this application includes: obtaining logistics information; determining the shipping fluctuation value of each candidate item based on the shipping time and shipping quantity of each candidate item in the logistics information; determining the global fluctuation value of each candidate item based on the shipping fluctuation value of each candidate item and the average shipping quantity of candidate items in the logistics information; and selecting a target item to be recommended from the candidate items based on the global fluctuation value of each candidate item.

[0064] As can be seen, on the one hand, the item recommendation method provided in this application can recommend items for users to ship when they fill in the shipping form, reducing the time users spend filling in the waybill. Furthermore, when determining the target item for recommendation, the shipping fluctuation value of each candidate item is corrected by the average shipping volume of candidate items, resulting in a more accurate global fluctuation value that represents the change in shipping volume over time. This solves the problem that the shipping fluctuation value of a small sample of candidate items cannot accurately represent the change in shipping volume over time, thus making the target item more accurate. On the other hand, this application embodiment does not require information about a specific user to determine the target item to be recommended, thus enabling a cold start for shipping item filling. Attached Figure Description

[0065] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0066] Figure 1 This is a schematic diagram illustrating an application scenario of the item recommendation method provided in the embodiments of this application;

[0067] Figure 2 This is a flowchart illustrating one of the item recommendation methods provided in the embodiments of this application;

[0068] Figure 3 This is a schematic diagram of a process for obtaining candidate items provided in an embodiment of this application;

[0069] Figure 4 This is another flowchart illustrating the item recommendation method provided in the embodiments of this application;

[0070] Figure 5 This is a schematic diagram of an embodiment of the item recommendation device provided in this application.

[0071] Figure 6 This is a schematic diagram of an embodiment of the electronic device provided in this application. Detailed Implementation

[0072] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0073] In the description of the embodiments of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0074] To enable any person skilled in the art to implement and use this application, the following description is provided. In this description, details are set forth for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be implemented without using these specific details. In other instances, well-known processes will not be described in detail to avoid obscuring the description of the embodiments of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in the embodiments of this application.

[0075] This application provides a method, apparatus, electronic device, and storage medium for recommending items. The item recommendation apparatus can be integrated into an electronic device, which may be a server or a terminal, etc.

[0076] The execution subject of the item recommendation method in this application embodiment can be the item recommendation device provided in this application embodiment, or different types of electronic devices such as server equipment, physical host, or user equipment (UE) that integrate the item recommendation device. The item recommendation device can be implemented in hardware or software. The UE can be a terminal device such as a smartphone, tablet computer, laptop computer, handheld computer, desktop computer, or personal digital assistant (PDA).

[0077] The electronic device can operate independently or as a cluster of devices.

[0078] See Figure 1 , Figure 1 This is a schematic diagram of a scenario for the item recommendation system provided in an embodiment of this application. The item recommendation system may include an electronic device 101, which integrates an item recommendation device.

[0079] In addition, such as Figure 1 As shown, the item recommendation system may also include a memory 102 for storing data, such as text data.

[0080] It should be noted that, Figure 1 The illustrated scenario of the item recommendation system is merely an example. The item recommendation system and scenario described in this application are intended to more clearly illustrate the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of item recommendation systems and the emergence of new business scenarios, the technical solutions provided in this invention are also applicable to similar technical problems.

[0081] The following describes the item recommendation method provided in this application embodiment. In this application embodiment, an electronic device is used as the execution subject. For simplicity and ease of description, this execution subject will be omitted in subsequent method embodiments. The item recommendation method includes: obtaining logistics information; determining the shipment fluctuation value of each candidate item based on the shipment time and shipment quantity of each candidate item in the logistics information; determining the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment quantity of candidate items in the logistics information; and selecting a target item to be recommended from the candidate items based on the global fluctuation value of each candidate item.

[0082] Reference Figure 2 , Figure 2 This is a flowchart illustrating an item recommendation method provided in an embodiment of this application. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here. Specifically, the item recommendation method may include the following steps 201-204, wherein:

[0083] 201. Obtain logistics information.

[0084] In this embodiment, the item recommendation method can be applied to express delivery and logistics software. When a user fills out a waybill, the method automatically recommends items to be shipped, reducing the time spent filling out the waybill and improving the user experience. For example, when a user opens an app for sending a package via a smartphone, personal computer, or other terminal, selects the electronic waybill to be filled out, and enters the item shipping form page, the electronic device can use the item recommendation method provided in this embodiment to determine the recommended items and display them on the item shipping form page for the user to choose from. The user does not need to manually fill out the waybill; instead, they can complete the electronic order by selecting via touchscreen or other methods.

[0085] Logistics information can refer to information generated when an item is shipped. For example, an electronic device can obtain logistics information based on historical waybill data; that is, the electronic device uses the information contained in the historical waybill data as logistics information. In this case, the logistics information may include the time information corresponding to each historical waybill. Historical waybills can refer to all waybills generated within a historical period. For example, the month preceding the current time can be considered as the aforementioned historical period, and all waybills generated within that month can be considered as historical waybills.

[0086] The data of historical waybills can be stored in the backend database of the express logistics software. When executing step 201, the electronic device can read the backend database of the express logistics software, obtain the historical waybills, and use the information contained in the historical waybill data as logistics information.

[0087] In some embodiments, logistics information may include the consigned item information for each historical waybill, as well as the dispatch time information for each historical waybill. Referring to Table 1, which illustrates one scenario for logistics information, assuming there are a total of 6 historical waybills, the logistics information may include the following:

[0088]

[0089] Table 1

[0090] In addition, logistics information can also include courier product information corresponding to each historical waybill. Courier product information can be understood as courier type information, which is set by the courier company. For example, courier product information may include courier type information such as "express delivery" or "same-day delivery".

[0091] 202. Determine the shipment fluctuation value of each candidate item based on the shipment time and shipment quantity of each candidate item in the logistics information.

[0092] Candidate items can include all the shipped items in the logistics information. For example, when the electronic device uses information contained in historical waybill data as logistics information, candidate items can include all the shipped items corresponding to the historical waybill. For instance, when the logistics information is contained in Table 1, candidate items include apples, fish, and oranges, a total of three types of shipped items.

[0093] The shipment volume can refer to the number of shipments. The shipment volume for each candidate item can refer to the number of shipments for each candidate item. For example, the shipment volume for each candidate item in the logistics information can include the number of shipments per day for each candidate item within the historical time period corresponding to the logistics information, which can be obtained from the number of historical waybills corresponding to each candidate item within each day. For example, if the logistics information is contained in Table 1, and assuming the historical time corresponding to the logistics information is January 1st and January 2nd, for the candidate item "Apple," its corresponding historical waybill count is 3, and the shipment time for all 3 historical waybills is January 1st. Therefore, the shipment volume for the candidate item "Apple" is: 3 on January 1st and 0 on January 2nd. As another example, for the candidate item "Orange," its corresponding historical waybill count is 1 on January 1st and 1 on January 2nd. Therefore, the shipment volume for the candidate item "Fish" is: 1 on January 1st and 1 on January 2nd. For ease of understanding, unless otherwise specified below, the shipment volume of each candidate item is assumed to include the number of shipments per day for each candidate item within the historical time period corresponding to the logistics information.

[0094] The shipping time for each candidate item can refer to the time each candidate item was shipped. For example, the shipping time for each candidate item in the logistics information can include the shipping time information contained in the historical waybills corresponding to each candidate item. For instance, when the logistics information is the information contained in Table 1, for the candidate item "apple," its corresponding historical waybills are historical waybills 1, 4, and 5, so the shipping time for the candidate item "apple" can be January 1st. As another example, for the candidate item "orange," its corresponding historical waybills are historical waybills 3 and 6, so the shipping time for the candidate item "orange" includes January 1st and January 2nd.

[0095] The shipment fluctuation value for each candidate item is calculated based on its own information, representing the change in shipment volume over time. It indicates the magnitude of the change in shipment volume for each candidate item over time, using its own total shipment volume as a benchmark. For example, the shipment fluctuation value for each candidate item can represent the change in recent shipment volume compared to historical shipment volume, using its own total shipment volume as a benchmark. For instance, a larger shipment fluctuation value indicates a greater change in recent shipment volume compared to historical shipment volume, considering only its own shipment volume, suggesting a recent surge in shipment volume for the corresponding candidate item. Conversely, a smaller shipment fluctuation value indicates a smaller change in recent shipment volume compared to historical shipment volume, suggesting a recent sharp decrease in shipment volume for the corresponding candidate item.

[0096] In some embodiments, for each candidate item, the electronic device can divide the shipment volume according to the shipment time to obtain the recent shipment volume and the historical shipment volume. For example, if the historical time corresponding to the logistics information is one month before the current time, the shipment volume within half a month before the current time can be used as the recent shipment volume, and the remaining shipment volume can be used as the historical shipment volume. Assuming the current time is February 1, the electronic device can use the daily shipment volume from January 1 to January 15 as the historical shipment volume, and the daily shipment volume from January 16 to January 31 as the recent shipment volume. Then, the electronic device calculates a first total value of the recent shipment volume and a second total value of the historical shipment volume, and takes the difference between the first and second total values ​​as a ratio to the sum of the first and second total values ​​to obtain the ratio of the change in shipment volume over time to the total shipment volume within the historical event. This ratio is used as the shipment fluctuation value of the candidate item. The difference in total value for each candidate item can be used to represent the recent increase / decrease in shipment volume, while the sum of total values ​​for each candidate item can be used to represent the total shipment volume of the candidate items. Therefore, the step "determining the shipment fluctuation value of each candidate item based on the shipment time and shipment volume of each candidate item in the logistics information" can be performed in the following manner:

[0097] (1.1) Based on the shipping time of each candidate item in the logistics information, the shipping volume of each candidate item is divided to obtain the target shipping volume and the historical shipping volume of each candidate item.

[0098] The target shipment volume can refer to the recent shipment volume. For an explanation of the recent shipment volume, please refer to the above text; details will not be repeated here. Similarly, for an explanation of the historical shipment volume, please refer to the above text.

[0099] (1.2) The shipment fluctuation value of each candidate item is calculated based on the target shipment volume of each candidate item and the historical shipment volume of each candidate item.

[0100] The method for calculating the shipment fluctuation value can be found above, and will not be elaborated further here.

[0101] It is evident that the shipment fluctuation value calculated using this method will be greater than the shipment fluctuation value calculated when the shipment volume of the corresponding candidate item surges in the recent period, or when the shipment volume of the corresponding candidate item does not change significantly in the recent period. It can be used to characterize the magnitude of the change in the shipment volume of each candidate item over time, using its own total shipment volume as a benchmark.

[0102] Furthermore, to ensure that the shipment fluctuation value of each candidate item is positive for subsequent calculations, the shipment fluctuation value of each candidate item can be calculated using formula (1):

[0103]

[0104] Among them, S i This refers to the shipment fluctuation value of the i-th candidate item. This refers to the first total value of the i-th candidate item. This refers to the second total value of the i-th candidate item. For ease of understanding, unless otherwise stated below, it is assumed that the shipment fluctuation value is calculated by formula (1), but this should not be construed as a limitation on the embodiments of this application.

[0105] It's important to note that the difference between the first and second total values—that is, the recent increase / decrease in shipment volume—is not directly used as the shipment fluctuation value. For candidate items with a large difference in total value, if their corresponding total shipment volume is not considered, the shipment fluctuation value cannot accurately represent the degree of change in the recent shipment volume of the candidate item. For ease of understanding, let's take candidate items A1 and A2 as examples. Assume A1's first total value is 278 and its second total value is 221, while A2's first total value is 50 and its second total value is 5. It's clear that the difference for A1 is greater than the difference for A2. However, it's evident from the first and second total values ​​of A1 and A2 that A2's recent shipment volume has surged. If the difference between the first and second total values ​​were used as the shipment fluctuation value, it would be judged that, compared to A2, A1's recent shipment volume has surged.

[0106] 203. Determine the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment volume of candidate items in the logistics information.

[0107] The average shipment quantity of candidate items refers to the average shipment value of all candidate items. For example, for each candidate item, the electronic device can sum the corresponding shipment quantities to obtain the total shipment quantity for each candidate item (equivalent to the sum of the first and second total values ​​for each candidate item). Then, it sums the total shipment quantities for each candidate item to obtain the total shipment quantity for all candidate items. The ratio between the total shipment quantity of all candidate items and the number of candidate items is used as the average shipment quantity of candidate items. Taking Table 1 as an example, the total shipment quantity for candidate item "apple" is 3, the total shipment quantity for candidate item "fish" is 1, and the total shipment quantity for candidate item "orange" is 2. After summing, the total shipment quantity for all candidate items is 6, and the number of candidate items is 3. Therefore, for Table 1, the average shipment quantity of candidate items is 2.

[0108] The average shipment volume of candidate items is used to address the inaccuracy of shipment fluctuation values ​​for small-sample candidate items. Small-sample candidate items refer to those with a relatively small total shipment volume, i.e., those with a small sum of the first and second total values. Because the total shipment volume corresponding to small-sample candidate items is relatively small, the shipment fluctuation value calculated according to formula (1) is inaccurate even if... Smaller, but Similarly, it is relatively small, therefore the calculated S i It might actually be too large. To make it easier to understand, let's take candidate items B1 and B2 as examples. Assume B1 has a first total value of 1 and a second total value of 0, and B2 has a first total value of 50 and a second total value of 5. Then, for candidate item B1, the calculated S1 is e, and for candidate item B2, the calculated S2 is... S1 is greater than S2. The electronic device will determine that the number of shipments in B1 has surged recently compared to B2. However, it can be seen from the total values ​​of B1 and B2 that the number of shipments in B2 has surged recently, while the number of shipments in B1 has not changed much recently. If the shipment fluctuation value calculated directly according to formula (1) is used to determine the items to be recommended, then the candidate items that have not surged will be recommended to the user.

[0109] The global fluctuation value is a more accurate fluctuation value obtained by correcting the shipment fluctuation value by the average shipment volume of candidate items. It can be understood as expanding the total shipment volume of each candidate item by the average shipment volume of candidate items, so as to avoid the value used to represent the change of shipment volume over time for each candidate item after a small sample of candidate items.

[0110] In some embodiments, a coefficient for correcting the shipment fluctuation value can be calculated using the average shipment volume of candidate items, the target shipment volume of each candidate item, and the historical shipment volume of each candidate item. Then, the global fluctuation value is calculated based on the obtained coefficient and the shipment fluctuation value. In this case, the step "determining the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment volume of candidate items in the logistics information" can be performed through the following steps:

[0111] (2.1) Count the number of each candidate item in the logistics information.

[0112] The quantity of each candidate item can be found in the explanation above. For example, in Table 1, the quantity of items in the corresponding logistics information is 3.

[0113] (2.2) Based on the total number of shipments of each candidate item and the number of items, the average number of shipments of the candidate items in the logistics information is calculated.

[0114] The total shipment volume for each candidate item refers to the sum of the total shipment volumes for each candidate item after calculating the first and second total values ​​for each candidate item as described above. Taking Table 1 as an example, the total shipment volume for each candidate item in the corresponding logistics information in Table 1 is 6.

[0115] By comparing the total number of shipments for each candidate item with the number of items, we can obtain the average number of shipments for each candidate item.

[0116] (2.3) The fluctuation correction coefficient of each candidate item is calculated based on the average number of shipments of the candidate items, the target number of shipments of each candidate item and the historical number of shipments of each candidate item.

[0117] For example, when the electronic device performs step (2.3), it can calculate the first total value and the second total value corresponding to each candidate item according to the target shipment volume and the historical shipment volume, respectively, using the method described above. Then, it can calculate the sum of the total values ​​corresponding to each candidate item and the difference in total values, and calculate the fluctuation correction coefficient using formula (2):

[0118]

[0119] Among them, T i It refers to the fluctuation correction coefficient for the i-th candidate item. This refers to the first total value of the i-th candidate item. refers to the second total value of the i-th candidate item, and avg refers to the average number of shipments of the candidate items. For ease of understanding, unless otherwise stated below, it is assumed that the fluctuation correction coefficient is calculated by formula (2), but this should not be construed as a limitation on the embodiments of this application.

[0120] As can be seen, by using formula (2), the total number of shipments of candidate items can be expanded by the average number of shipments of candidate items, and the proportion of the recent increase / decrease in the total number of shipments can be calculated. Then, the magnitude of the recent increase / decrease in the number of shipments can be judged. The larger the fluctuation correction coefficient, the greater the magnitude of the recent increase / decrease in the number of shipments. The smaller the fluctuation correction coefficient, the smaller the magnitude of the recent increase / decrease in the number of shipments. This avoids the problem of inaccurate recommendations due to the small number of shipments of small sample candidate items.

[0121] In some embodiments, a preset expansion value can be added to the denominator of equation (2) to obtain a global fluctuation value. This is to further expand the total number of shipments for each candidate item when multiple small sample candidate items are included in each candidate item, so as to avoid the problem that the average number of shipments for candidate items is still small, which leads to inaccurate recommendations.

[0122]

[0123] Among them, T i It refers to the fluctuation correction coefficient for the i-th candidate item. This refers to the first total value of the i-th candidate item. is the second total value of the i-th candidate item, avg is the average number of shipments of candidate items, and W is a preset expansion value that can be set according to the needs of the actual scenario.

[0124] (2.4) Based on the fluctuation correction coefficient, the shipment fluctuation value of each candidate item is weighted to obtain the global fluctuation value of each candidate item.

[0125] For example, the global fluctuation value of each candidate item can be calculated using equation (4):

[0126] G i =S i T i Equation (4)

[0127] Among them, G i S refers to the global fluctuation value of the i-th candidate item. i T refers to the shipment fluctuation value of the i-th candidate item. i It refers to the fluctuation correction coefficient of the i-th candidate item.

[0128] 204. Based on the global fluctuation value of each candidate item, select the target item to be recommended from the candidate items.

[0129] The target items to be recommended can be understood as currently popular items to be sent.

[0130] In some embodiments, the electronic device may select the candidate item with the largest global fluctuation value and use that candidate item as the target item.

[0131] In other embodiments, the electronic device can compare the global fluctuation value of each candidate item with a preset fluctuation threshold, and select the candidate item whose global fluctuation value is greater than the fluctuation threshold as the target item. The preset fluctuation threshold is used to evaluate the magnitude of the global fluctuation value, and its specific value can be set according to the needs of the actual scenario.

[0132] Therefore, the step "selecting the target item to be recommended from the candidate items based on the global fluctuation value of each candidate item" may include:

[0133] (3.1) Compare the global fluctuation value of each candidate item with a preset score threshold to obtain candidate items whose global fluctuation value is greater than the preset score threshold.

[0134] The preset score threshold is the fluctuation threshold mentioned above, which will not be elaborated further.

[0135] (3.2) Set the candidate items whose global fluctuation value is greater than the preset score threshold as the target items to be recommended.

[0136] As can be seen, the method in steps 201-204 not only improves the accuracy of recommendations, but also addresses the cold start problem of item selection during parcel dispatch, as it does not require access to the historical data of specific users to select target items. This means it can recommend candidate items that the user has not yet filled in. For example, for candidate items with seasonal attributes, such as zongzi (sticky rice dumplings) and mooncakes, they can be identified as target items for recommendation before the specific season, thus solving the user cold start problem.

[0137] In summary, the item recommendation method provided in this application includes: obtaining logistics information; determining the shipping fluctuation value of each candidate item based on the shipping time and shipping quantity of each candidate item in the logistics information; determining the global fluctuation value of each candidate item based on the shipping fluctuation value of each candidate item and the average shipping quantity of candidate items in the logistics information; and selecting a target item to be recommended from the candidate items based on the global fluctuation value of each candidate item.

[0138] As can be seen, on the one hand, the item recommendation method provided in this application can recommend items for users to ship when they fill in the shipping form, reducing the time users spend filling in the waybill. Furthermore, when determining the target item for recommendation, the shipping fluctuation value of each candidate item is corrected by the average shipping volume of candidate items, resulting in a more accurate global fluctuation value that represents the change in shipping volume over time. This solves the problem that the shipping fluctuation value of a small sample of candidate items cannot accurately represent the change in shipping volume over time, thus making the target item more accurate. On the other hand, this application embodiment does not require information about a specific user to determine the target item to be recommended, thus enabling a cold start for shipping item filling.

[0139] In some embodiments, the electronic device may first filter the consigned items contained in the logistics information, selecting those items less prone to sudden changes in shipment volume as candidate items. (Reference) Figure 3 At this point, before the step "determine the shipment fluctuation value of each candidate item based on the shipment time and shipment volume of each candidate item in the logistics information", the method further includes:

[0140] 301. Based on the shipping time of the first item in the logistics information, count the number of shipments of the first item in each preset historical time period.

[0141] For example, the time range corresponding to logistics information can be divided according to a preset time interval to obtain each preset historical time period. For instance, if the electronic device uses historical waybill information within one month prior to the current time as logistics information, that is, the time range corresponding to the logistics information is one month, and the preset time interval is 5 days, then one month can be divided into multiple preset historical time periods, each preset historical time period corresponding to 5 days in that month.

[0142] In steps 301-303, the first item refers to all the consigned items included in the logistics information. Taking Table 1 as an example, for the logistics information in Table 1, the first item includes "apples", "fish", and "oranges".

[0143] For details on the shipping time of the first item, please refer to the shipping time of the candidate items; further details will not be provided here.

[0144] The shipment volume of the first item within a preset historical time period refers to the number of times the first item was shipped within that preset historical time period. Taking Table 1 as an example, assuming that the time range corresponding to the logistics information in Table 1 is divided into two preset historical time periods, "January 1st" and "January 2nd", then for the first item "apple", the shipment volume within the preset time period "January 1st" includes the number of times "apple" was shipped on January 1st; for the first item "fish", the shipment volume within the preset time period "January 1st" includes the number of times "fish" was shipped on January 1st; and for the first item "orange", the shipment volume within the preset time period "January 1st" includes the number of times "orange" was shipped on January 1st.

[0145] 302. Based on the number of shipments in each preset historical time period and the time interval corresponding to each preset historical time period, calculate the average rate of change of the number of shipments of the first item.

[0146] The time intervals corresponding to each preset historical time period refer to the preset time intervals mentioned above, that is, the time range included in each preset historical time period.

[0147] For example, the electronic device can calculate the rate of change of the number of shipments corresponding to each pair of adjacent preset historical event segments based on the number of shipments in each pair of adjacent preset historical event segments and the time interval. Then, it averages all the rates of change of the number of shipments corresponding to each preset historical time period to obtain the average rate of change of the number of shipments of the first item. For ease of understanding, the following specific example is given as an example, but it should not be construed as a limitation on the embodiments of this application: Assume there are three preset historical time periods a, b, and c, and the number of shipments of the first item in preset historical time periods a, b, and c are 10, 20, and 30, respectively, and the time interval corresponding to the preset historical time periods is 5 days. After calculation, the rate of change of the number of shipments corresponding to each pair of adjacent preset historical event segments is the rate of change of the number of shipments between a and b, which is 2 / day, and the rate of change of the number of shipments between b and c, which is 2 / day. After averaging, the average rate of change of the number of shipments of the first item is 2 / day.

[0148] 303. The first item whose average rate of change in shipment volume is less than the preset rate of change threshold is set as a candidate item.

[0149] The preset change rate threshold is used to evaluate the magnitude of the average change rate of the number of shipments, and the specific value can be set according to the actual needs of the scenario.

[0150] If the average rate of change of shipment volume is greater than or equal to the preset rate of change threshold, it indicates that the shipment volume of the corresponding first item frequently changes abruptly. Since the item recommendation method provided in this application embodiment determines the target item based on the change of shipment volume, the first item whose shipment volume frequently changes abruptly cannot be judged by the item recommendation method provided in this application embodiment and needs to be screened out to avoid recommendation errors and reduce the amount of calculation.

[0151] In some embodiments, the first item with a low probability of being sent by the user to be recommended can be further filtered out based on the sending records of the user to be recommended and the sending records of the user group to which the user to be recommended belongs, in order to reduce the amount of computation. In this case, the step "setting the first item whose average rate of change in sending volume is less than a preset rate of change threshold as a candidate item" may include:

[0152] (4.1) Obtain a second item from the shipping records of the target user to be recommended, where the total number of historical shipments is less than a first preset threshold.

[0153] The target users to be recommended are users who open the express delivery and logistics software. For details, please refer to the explanation in step 201.

[0154] Shipping records can contain a user's historical shipping behavior data, such as waybill data created by the user. Therefore, the target user's shipping records contain historical waybill information created by the target user. This historical waybill information can refer to all waybills created by the target user, or it can refer to waybills created by the target user within a period of time prior to the current time.

[0155] The shipping records can be stored in the backend database of the express logistics software. When performing step (4.1), the electronic device can query the backend database based on the target user's user identity to obtain the target user's shipping records.

[0156] Among them, the user identity identifier is used to distinguish the identities of different users, which may refer to the login name used by the user when logging into the express delivery and logistics software, etc.

[0157] The total number of historical shipments refers to the total number of shipments in the shipment record. When performing step (4.1), the electronic device can query each historical waybill in the shipment record to obtain the consigned item corresponding to each historical waybill in the shipment record. Then, it can count the total number of shipments of different consigned items in the target user's shipment record to obtain the total number of historical shipments of each different consigned item.

[0158] The first preset number of times threshold is used to assess the total number of historical shipments. The specific value can be set according to the actual needs of the scenario, for example, it can be set to 1. Taking the first preset number of times threshold as 1 as an example, if the total number of historical shipments is less than the first preset number of times threshold, it means that the target user has never shipped the corresponding consignment item. Even if the global fluctuation value is large and the current shipment volume surges, the target user may not choose to ship the consignment item, so the consignment item can be filtered out.

[0159] (4.2) Determine the user group to which the target user belongs.

[0160] A group refers to a collection of users categorized based on attributes such as age, occupation, gender, and region. For example, users can be divided into multiple preset groups based on their city settings within the express delivery software. Then, the user group containing the target user can be retrieved from these preset groups based on the target user's user identifier. For ease of understanding, unless otherwise stated below, preset groups are assumed to be based on geographical location.

[0161] (4.3) Obtain a third item from the mailing records of the user group whose average mailing volume in the same period of history is less than the second preset number of times threshold.

[0162] The description of the mailing record can be found above, and will not be repeated here. When performing step (4.3), the electronic device can obtain all users in the user group and extract the historical mailing behavior data of all users in the user group to obtain the third item.

[0163] The average number of shipments in the same period of history can refer to the average number of shipments of corresponding items in the same period of several historical years.

[0164] The second preset threshold is used to assess the average number of shipments during the same historical period. The specific value can be set according to the actual needs of the scenario. If the average number of shipments during the same historical period is less than the second preset threshold, it means that in the region corresponding to the user group, and in the same historical period at the current time, the number of shipments for the corresponding item is low. Even if the item is seasonal, it is not a popular item for shipment in this region, so it can be filtered out.

[0165] (4.4) The second item and the third item are screened out from the first item, and the first item whose average change rate of the number of shipments after screening is less than a preset change rate threshold is selected as a candidate item.

[0166] The reason for selecting candidate items based on the average rate of change in shipment volume can be found in step 303, and will not be elaborated further.

[0167] In some embodiments, after obtaining the target item to be recommended, the electronic device can listen for whether it receives a selection instruction from the target user. Upon receiving a selection instruction, the electronic device fills in the corresponding area of ​​the waybill with the item selected from the target items. (Reference) Figure 4 At this point, after the step "determine the target item to be recommended based on the shipment fluctuation value and shipment growth rate of each candidate item", the method further includes:

[0168] 401. Receive the selection instruction from the target user to be recommended, and obtain the item corresponding to the selection instruction among the target items.

[0169] For a description of the target users, please refer to step (4.1), which will not be elaborated here.

[0170] The selection command can refer to a command such as a touch screen or voice. This application embodiment does not limit this. For example, a user can select a certain item from the target items by touching the screen to issue a selection command carrying the information of that item.

[0171] 402. Input the item corresponding to the selection instruction into the preset area of ​​the preset waybill.

[0172] Among them, the preset waybill can refer to a newly created, unfilled waybill by the target user.

[0173] The preset area can refer to the area in the preset waybill used to fill in the items to be shipped.

[0174] To better implement the item recommendation method in the embodiments of this application, based on the item recommendation method, the embodiments of this application also provide an item recommendation device, such as... Figure 5 The diagram shown is a schematic representation of one embodiment of the item recommendation device in this application. The item recommendation device 500 includes:

[0175] Acquisition unit 501 is used to acquire logistics information;

[0176] The first determining unit 502 is used to determine the shipping fluctuation value of each candidate item based on the shipping time and shipping quantity of each candidate item in the logistics information.

[0177] The second determining unit 503 is used to determine the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment quantity of candidate items in the logistics information.

[0178] Selection unit 504 is used to select a target item to be recommended from the candidate items based on the global fluctuation value of each candidate item.

[0179] In one possible implementation of this application, the first determining unit 502 is further configured to:

[0180] Based on the shipping time of each candidate item in the logistics information, the shipping volume of each candidate item is divided to obtain the target shipping volume and the historical shipping volume of each candidate item.

[0181] The shipment fluctuation value of each candidate item is calculated based on the target shipment volume and the historical shipment volume of each candidate item.

[0182] In one possible implementation of this application, the second determining unit 503 is further configured to:

[0183] Count the quantity of each candidate item in the logistics information;

[0184] Based on the total number of shipments for each candidate item and the quantity of the item, the average number of shipments for the candidate items in the logistics information is calculated.

[0185] The fluctuation correction coefficient for each candidate item is calculated based on the average shipment volume of the candidate items, the target shipment volume of each candidate item, and the historical shipment volume of each candidate item.

[0186] Based on the fluctuation correction coefficient, the shipping fluctuation value of each candidate item is weighted to obtain the global fluctuation value of each candidate item.

[0187] In one possible implementation of this application, the selection unit 504 is further configured to:

[0188] The global fluctuation value of each candidate item is compared with a preset score threshold to obtain candidate items whose global fluctuation value is greater than the preset score threshold;

[0189] Candidate items with global fluctuation values ​​greater than a preset score threshold are set as target items to be recommended.

[0190] In one possible implementation of this application, the first determining unit 502 is further configured to:

[0191] Based on the shipping time of the first item in the logistics information, the number of shipments of the first item in each preset historical time period is counted.

[0192] The average rate of change in the number of shipments of the first item is calculated based on the number of shipments in each preset historical time period and the time intervals corresponding to each preset historical time period.

[0193] The first item whose average rate of change in shipment volume is less than a preset rate of change threshold is set as a candidate item.

[0194] In one possible implementation of this application, the first determining unit 502 is further configured to:

[0195] From the shipping records of the target users to be recommended, obtain a second item whose total historical shipping volume is less than a first preset threshold.

[0196] Determine the user group to which the target user belongs;

[0197] From the shipping records of the user group, obtain the third item whose average shipping volume for the same period in history is less than the second preset number of times threshold.

[0198] The second and third items are removed from the first items, and the first item whose average change rate of shipment volume after removal is less than a preset change rate threshold is selected as a candidate item.

[0199] In one possible implementation of this application, the selection unit 504 is further configured to:

[0200] Receive the selection instruction from the target user to be recommended, and obtain the item corresponding to the selection instruction from the target items;

[0201] Enter the item corresponding to the selection instruction into the preset area of ​​the preset waybill.

[0202] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0203] Since the item recommendation device can perform the steps in the item recommendation method in any embodiment, it can achieve the beneficial effects that the item recommendation method in any embodiment of this application can achieve, as detailed in the preceding description, and will not be repeated here.

[0204] Furthermore, in order to better implement the item recommendation method in the embodiments of this application, the item recommendation method...

[0205] Based on this, embodiments of this application also provide an electronic device, see below. Figure 6 , Figure 6 This illustration shows a structural diagram of an electronic device according to an embodiment of this application. Specifically, the electronic device provided in this embodiment includes a processor 601. The processor 601 is used to execute a computer program stored in a memory 602 to implement each step of the item recommendation method in any embodiment; or, the processor 601 is used to execute a computer program stored in a memory 602 to implement, for example... Figure 5 The functions of each unit in the corresponding embodiment.

[0206] For example, a computer program may be divided into one or more modules / units, one or more of which are stored in memory 602 and executed by processor 601 to complete the embodiments of this application. One or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a computer device.

[0207] The electronic device may include, but is not limited to, processor 601 and memory 602. Those skilled in the art will understand that the illustrations are merely examples of an electronic device and do not constitute a limitation on the device. It may include more or fewer components than illustrated, or combine certain components, or use different components.

[0208] Processor 601 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting various parts of the electronic device through various interfaces and lines.

[0209] The memory 602 can be used to store computer programs and / or modules. The processor 601 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 602 and by calling data stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as audio data, video data, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0210] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the item recommendation device, electronic device and its corresponding units described above can be referred to the description of the item recommendation method in any embodiment, and will not be repeated here.

[0211] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions, or by instructions controlling related hardware. These instructions can be stored in a storage medium and loaded and executed by a processor.

[0212] Therefore, this application provides a storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the item recommendation method in any embodiment of this application. For specific operations, please refer to the description of the item recommendation method in any embodiment, which will not be repeated here.

[0213] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0214] Since the instructions stored in the storage medium can execute the steps of the item recommendation method in any embodiment of this application, the beneficial effects that the item recommendation method in any embodiment of this application can achieve can be realized, as detailed in the preceding description, and will not be repeated here.

[0215] The foregoing has provided a detailed description of a method, apparatus, storage medium, and electronic device for recommending items according to the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for recommending items, characterized in that, include: Obtain logistics information; Based on the shipping time and shipping quantity of each candidate item in the logistics information, determine the shipping fluctuation value of each candidate item; The shipment fluctuation value is a value calculated based on the information related to each candidate item itself, which is the value of the shipment volume changing over time. The global fluctuation value of each candidate item is determined based on the shipment fluctuation value of each candidate item and the average shipment volume of candidate items in the logistics information. Based on the global fluctuation value of each candidate item, a target item to be recommended is selected from the candidate items; Receive the selection instruction from the target user to be recommended, and obtain the item corresponding to the selection instruction from the target items; Enter the item corresponding to the selection instruction into the preset area of ​​the preset waybill.

2. The item recommendation method according to claim 1, characterized in that, The step of determining the shipping fluctuation value of each candidate item based on the shipping time and shipping volume of each candidate item in the logistics information includes: Based on the shipping time of each candidate item in the logistics information, the shipping volume of each candidate item is divided to obtain the target shipping volume and the historical shipping volume of each candidate item. The shipment fluctuation value of each candidate item is calculated based on the target shipment volume and the historical shipment volume of each candidate item.

3. The item recommendation method according to claim 2, characterized in that, The step of determining the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment volume of candidate items in the logistics information includes: Count the quantity of each candidate item in the logistics information; Based on the total number of shipments for each candidate item and the quantity of the item, the average number of shipments for the candidate items in the logistics information is calculated. The fluctuation correction coefficient for each candidate item is calculated based on the average shipment volume of the candidate items, the target shipment volume of each candidate item, and the historical shipment volume of each candidate item. Based on the fluctuation correction coefficient, the shipping fluctuation value of each candidate item is weighted to obtain the global fluctuation value of each candidate item.

4. The item recommendation method according to claim 1, characterized in that, The step of selecting a target item to be recommended from the candidate items based on the global fluctuation value of each candidate item includes: The global fluctuation value of each candidate item is compared with a preset score threshold to obtain candidate items whose global fluctuation value is greater than the preset score threshold; Candidate items with global fluctuation values ​​greater than a preset score threshold are set as target items to be recommended.

5. The item recommendation method according to claim 1, characterized in that, Before determining the shipment fluctuation value of each candidate item based on the shipment time and shipment volume of each candidate item in the logistics information, the method further includes: Based on the shipping time of the first item in the logistics information, the number of shipments of the first item in each preset historical time period is counted. The average rate of change in the number of shipments of the first item is calculated based on the number of shipments in each preset historical time period and the time intervals corresponding to each preset historical time period. The first item whose average rate of change in shipment volume is less than a preset rate of change threshold is set as a candidate item.

6. The item recommendation method according to claim 5, characterized in that, The step of setting the first item whose average rate of change in shipment volume is less than a preset rate of change threshold as a candidate item includes: From the shipping records of the target users to be recommended, obtain a second item whose total historical shipping volume is less than a first preset threshold. Determine the user group to which the target user belongs; From the shipping records of the user group, obtain the third item whose average shipping volume for the same period in history is less than the second preset number of times threshold. The second and third items are removed from the first items, and the first item whose average change rate of shipment volume after removal is less than a preset change rate threshold is selected as a candidate item.

7. An item recommendation device, characterized in that, include: The acquisition unit is used to acquire logistics information; The first determining unit is used to determine the shipping fluctuation value of each candidate item based on the shipping time and shipping quantity of each candidate item in the logistics information; The shipment fluctuation value is a value calculated based on the information related to each candidate item itself, which is the value of the shipment volume changing over time. The second determining unit is used to determine the global fluctuation value of each candidate item based on the shipment fluctuation value of each candidate item and the average shipment quantity of candidate items in the logistics information. The selection unit is used to select a target item to be recommended from the candidate items based on the global fluctuation value of each candidate item, receive the selection instruction from the target user to be recommended, obtain the item corresponding to the selection instruction among the target items, and input the item corresponding to the selection instruction into the preset area of ​​the preset waybill.

8. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the article recommendation method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the item recommendation method according to any one of claims 1 to 6.

Images