Method and device for item recommendation, electronic device, storage medium

Abstract

The application relates to the technical field of information recommendation, and discloses a method for recommending an article, which comprises the following steps: acquiring an article consumption list corresponding to a user to be recommended; determining, as target articles, merchant inventory articles which are the same as each historical purchase article in a preset popular article database; determining the popular articles corresponding to the target articles as candidate popular articles, and acquiring the similarity between the candidate popular articles and the merchant inventory articles; determining, from each candidate popular article, a popular article to be recommended according to the similarity between the candidate popular articles and the merchant inventory articles; and recommending the popular article to be recommended to the user to be recommended. In this way, the candidate popular articles are directly determined from the popular article database according to the historical purchase articles, the similarity between the candidate popular articles and the merchant inventory articles is determined, the article to be recommended can be quickly obtained, and the efficiency of article recommendation is improved. The application further discloses an apparatus for recommending an article, an electronic device, and a storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information recommendation, for example to a method and device for item recommendation, an electronic device, and a storage medium. BACKGROUND

[0002] With more and more items on shopping websites, the cost for users to find suitable items is increasing. For shopping websites, since bulk purchasing can reduce costs, concentrating on selling some popular items can obtain greater profits, so it is necessary to recommend suitable popular items to users when the users have shopping needs.

[0003] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art:

[0004] In the related art, popular items are recommended to users after filtering out the items meeting the user's needs from all inventory items, but filtering out popular items after screening out items meeting the user's needs will result in slow item recommendation to users, and low efficiency of item recommendation to users. SUMMARY

[0005] The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. The summary is not an extensive overview of the disclosure, nor is it intended to identify key / critical elements of the embodiments or to delineate the scope of the embodiments. The sole purpose of the summary is to present some concepts of the embodiments in a simplified form as a prelude to the more detailed description that is presented later.

[0006] The embodiments of the present disclosure provide a method and device for item recommendation, an electronic device, and a storage medium, so as to improve the efficiency of item recommendation to users.

[0007] In some embodiments, the method for item recommendation comprises: obtaining a consumed item list corresponding to a to-be-recommended user; the consumed item list comprises a plurality of historical purchase items; determining, as target items, merchant inventory items in a preset popular item database that are identical to each of the historical purchase items; the popular item database stores merchant inventory items, popular items corresponding to the merchant inventory items, and similarities between the popular items and the merchant inventory items; determining, as candidate popular items, popular items corresponding to the target items, and obtaining similarities between the candidate popular items and the merchant inventory items; determining, from each of the candidate popular items, a to-be-recommended popular item according to the similarity between the candidate popular item and the merchant inventory item; and recommending the to-be-recommended popular item to the to-be-recommended user.

[0008] In some embodiments, the obtaining the consumed item list corresponding to the user to be recommended comprises: obtaining a historical shopping record corresponding to the user to be recommended; and determining the consumed item list according to the historical shopping record.

[0009] In some embodiments, the determining the consumed item list according to the historical shopping record comprises: in a case where there is a purchase item record in the historical shopping record, counting items in the purchase item record to obtain the consumed item list; or in a case where there is no purchase item record in the historical shopping record, determining a target user from a preset alternative user database; determining a consumed item list corresponding to the target user as the consumed item list corresponding to the user to be recommended; and the alternative user database stores a plurality of alternative users, and each alternative user corresponds to a consumed item list.

[0010] In some embodiments, the determining the target user from the preset alternative user database comprises: respectively obtaining a user similarity between the user to be recommended and each alternative user; and determining an alternative user with the highest user similarity to the user to be recommended as the target user.

[0011] In some embodiments, the determining the recommended popular item from each alternative popular item according to the similarity between the alternative popular item and the merchant inventory item comprises: for each alternative popular item, performing the following operation: accumulating the similarity between the alternative popular item and each merchant inventory item to obtain a recommendation score corresponding to the alternative popular item; and determining the recommended popular item from each alternative popular item according to the recommendation score corresponding to each alternative popular item.

[0012] In some embodiments, the determining the recommended popular item from each alternative popular item according to the recommendation score corresponding to each alternative popular item comprises: sorting each alternative popular item in a descending order of the recommendation score; and determining alternative popular items with a front preset number of sorting orders as the recommended popular items.

[0013] In some embodiments, after the recommended popular item is recommended to the user to be recommended, the method further comprises: updating the popular item database every preset time period.

[0014] In some embodiments, the device for item recommendation comprises: an acquisition module configured to acquire a list of consumed items corresponding to a user to be recommended; the list of consumed items comprises a plurality of historical purchase items; a first determination module configured to determine, as target items, merchant inventory items in a preset popular item database that are identical to each of the historical purchase items; the popular item database stores merchant inventory items, popular items corresponding to the merchant inventory items, and similarities between the popular items and the merchant inventory items; a second determination module configured to determine popular items corresponding to the target items as candidate popular items, and acquire similarities between the candidate popular items and the merchant inventory items; a third determination module configured to determine, from each of the candidate popular items, a popular item to be recommended according to the similarity between the candidate popular item and the merchant inventory item; and a recommendation module configured to recommend the popular item to be recommended to the user to be recommended.

[0015] In some embodiments, the electronic device comprises a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for item recommendation when running the program instructions.

[0016] In some embodiments, the storage medium stores program instructions, and the program instructions execute the above-mentioned method for item recommendation when running.

[0017] The method and device for item recommendation, the electronic device, and the storage medium provided by the embodiments of the present disclosure can achieve the following technical effects: since the popular item database pre-stores merchant inventory items, popular items corresponding to the merchant inventory items, and similarities between the popular items and the merchant inventory items, the similarities between the historical purchase items and the popular items do not need to be calculated again by determining, from a preset popular item database, candidate popular items according to the historical purchase items and the similarities between the candidate popular items and each of the merchant inventory items. The item to be recommended can be obtained more quickly, and thus the efficiency of item recommendation can be improved.

[0018] The general description above and the following description below are exemplary and explanatory only and are not intended to be limiting. BRIEF DESCRIPTION OF DRAWINGS

[0019] One or more embodiments are illustrated by way of example in the figures that are not intended to be limiting of the embodiments. Like numbers refer to like elements throughout the drawings, which are not necessarily to scale, with:

[0020] Figure 1 is a schematic diagram of a method for item recommendation provided by the embodiments of the present disclosure;

[0021] Figure 2 is a schematic diagram of another method for item recommendation provided by an embodiment of the present disclosure;

[0022] Figure 3 is a schematic diagram of another method for item recommendation provided by an embodiment of the present disclosure;

[0023] Figure 4 is a schematic diagram of another method for item recommendation provided by an embodiment of the present disclosure;

[0024] Figure 5 is a schematic diagram of an apparatus for item recommendation provided by an embodiment of the present disclosure;

[0025] Figure 6 is a schematic diagram of a structure of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to enable persons skilled in the art to more fully understand the features and technical contents of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, which are used only for reference and are not intended to limit the embodiments of the present disclosure. In the following technical description, in order to facilitate explanation, a plurality of details are provided to provide a full understanding of the disclosed embodiments. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be simplified to facilitate the drawings.

[0027] The terms "first", "second", and the like in the specification and claims of the embodiments of the present disclosure and the above drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0028] Unless otherwise specified, the term "a plurality of" means two or more.

[0029] In the embodiments of the present disclosure, the character " / " represents an "or" relationship between the objects before and after it. For example, A / B represents: A or B.

[0030] The term "and / or" is a description of the association relationship between objects, which means that there can be three relationships. For example, A and / or B means: A or B, or, A and B, the three relationships.

[0031] The term "corresponding" can refer to an association relationship or a binding relationship, A corresponding to B means that there is an association relationship or a binding relationship between A and B.

[0032] The technical solutions in the embodiments of the present application can be applied to electronic devices such as servers, computers, tablet computers, or smart phones.

[0033] In the embodiments of the present application, the similarity between the hot item and the merchant inventory item is calculated in advance, and the merchant inventory item, the hot item corresponding to the merchant inventory item, and the similarity are stored in the hot item database. By determining the candidate hot item and the similarity between the candidate hot item and each merchant inventory item from the preset hot item database according to the historical purchase item, the similarity between the historical purchase item and the hot item does not need to be calculated again, and the to-be-recommended item can be obtained more quickly, thereby improving the efficiency of item recommendation.

[0034] In combination with Figure 1 The embodiments of the present application provide a method for item recommendation, which comprises the following steps:

[0035] In step S101, the electronic device obtains a consumed item list corresponding to a to-be-recommended user; the consumed item list includes a plurality of historical purchase items.

[0036] In step S102, the electronic device determines a merchant inventory item in a preset hot item database as a target item, which is the same as each historical purchase item; the hot item database stores the merchant inventory item, the hot item corresponding to the merchant inventory item, and the similarity between the hot item and the merchant inventory item.

[0037] In step S103, the electronic device determines the hot item corresponding to the target item as a candidate hot item, and obtains the similarity between the candidate hot item and the merchant inventory item.

[0038] In step S104, the electronic device determines a to-be-recommended hot item from each candidate hot item according to the similarity between the candidate hot item and the merchant inventory item.

[0039] In step S105, the electronic device recommends the to-be-recommended hot item to the to-be-recommended user.

[0040] The method for item recommendation provided by the embodiments of the present application has the following advantages: the merchant inventory item, the hot item corresponding to the merchant inventory item, and the similarity between the hot item and the merchant inventory item are stored in the hot item database in advance. By determining the candidate hot item and the similarity between the candidate hot item and each merchant inventory item from the preset hot item database according to the historical purchase item, the similarity between the historical purchase item and the hot item does not need to be calculated again, and the to-be-recommended item can be obtained more quickly, thereby improving the efficiency of item recommendation.

[0041] Further, the electronic device obtains the consumed item list corresponding to the user to be recommended, including: the electronic device obtains the historical shopping record corresponding to the user to be recommended, and determines the consumed item list according to the historical shopping record.

[0042] Further, the electronic device determines the consumed item list according to the historical shopping record, including: the electronic device, in a case where the purchase item record exists in the historical shopping record, counts the items in the purchase item record to obtain the consumed item list. Or, the electronic device, in a case where the purchase item record does not exist in the historical shopping record, determines a target user from a preset candidate user database. The consumed item list corresponding to the target user is determined as the consumed item list corresponding to the user to be recommended.

[0043] Optionally, the electronic device determines the target user from the preset candidate user database, including: the electronic device respectively obtains the user similarity between the user to be recommended and each candidate user in the preset candidate user database, and determines the candidate user with the highest user similarity as the target user. The candidate user database stores a plurality of candidate users, and each candidate user corresponds to a consumed item list.

[0044] Further, the electronic device obtains the user similarity between the user to be recommended and the candidate user, including: obtaining the attribute vector corresponding to the user to be recommended and the attribute vector corresponding to the candidate user; and calculating the attribute vector corresponding to the user to be recommended and the attribute vector corresponding to the candidate user according to a preset algorithm to obtain the user similarity. The attribute vector corresponding to the user to be recommended is used to represent the attributes of the user, such as interest, gender, age, and registered region. The attribute vector corresponding to the candidate user is used to represent the attributes of the candidate user, such as interest, gender, age, and registered region.

[0045] Further, the electronic device obtains the user similarity according to the preset algorithm by calculating the attribute vector corresponding to the user to be recommended and the attribute vector corresponding to the candidate user, including: calculating to obtain the user similarity. Wherein, Cos(θ) is the user similarity, A is the attribute vector corresponding to the user to be recommended, and B is the attribute vector corresponding to the candidate user.

[0046] In some embodiments, Table 1 is an example table of a candidate user database provided by an embodiment of the present disclosure. As shown in Table 1, the consumed item list corresponding to the candidate user aa is list 1. The consumed item list corresponding to the candidate user bb is list 2. The consumed item list corresponding to the candidate user cc is list 3. The consumed item list corresponding to the candidate user dd is list 4. For example, in a case where the user similarity between the candidate user cc and the user to be recommended is the largest, the list 3 corresponding to the candidate user cc is determined as the consumed item list corresponding to the user to be recommended.

[0047] Alternative user List of consumed items Alternative user aa List 1 Alternative user bb List 2 Alternative user cc List 3 Alternative user dd List 4

[0048] Table 1

[0049] Optionally, the preset candidate user database further stores an average user, and the electronic device determines the target user from the preset candidate user database, including: determining the average user in the preset candidate user database as the target user. The average user is a user portrait corresponding to an active user group, and the active user group is a user group composed of users exceeding a preset active degree. The preset active degree is 2 times of monthly consumption.

[0050] Further, the consumed item list corresponding to the average user is determined by: obtaining purchase item records of each user in a user group corresponding to the average user, and counting the purchase item records of each user to obtain a total consumption corresponding to each purchase item. Each purchase item is sorted in descending order of the total consumption, and a preset number of purchase items before sorting are counted to obtain the consumed item list corresponding to the average user.

[0051] In combination Figure 2 As shown in the figure, the embodiment of the present disclosure provides a method for item recommendation, which comprises:

[0052] Step S201, the electronic device obtains the historical shopping record corresponding to the user to be recommended.

[0053] Step S202, the electronic device determines the consumed item list corresponding to the user to be recommended according to the historical shopping record; the consumed item list includes a plurality of historical purchase items.

[0054] Step S203, the electronic device determines the merchant inventory item same as each historical purchase item in the preset popular item database as the target item; the popular item database stores the merchant inventory item, the popular item corresponding to the merchant inventory item, and the similarity between the popular item and the merchant inventory item.

[0055] Step S204, the electronic device determines the popular item corresponding to the target item as the candidate popular item, and obtains the similarity between the candidate popular item and the merchant inventory item.

[0056] Step S205, the electronic device determines the popular item to be recommended from each candidate popular item according to the similarity between the candidate popular item and the merchant inventory item.

[0057] Step S206, the electronic device recommends the popular item to be recommended to the user to be recommended.

[0058] The method for item recommendation provided by the embodiment of the present disclosure can determine the items purchased by the user to be recommended by querying the historical shopping records of the user to be recommended, thereby determining the list of consumed items. Since the popular item database pre-stores the merchant inventory items, the popular items corresponding to the merchant inventory items, and the similarity between the popular items and the merchant inventory items, the candidate popular items and the similarity between the candidate popular items and each merchant inventory item can be determined directly from the preset popular item database according to the historical purchase items. There is no need to calculate the similarity between the historical purchase items and the popular items, the items to be recommended can be quickly obtained, and the efficiency of item recommendation can be improved.

[0059] Further, the electronic device determines the popular item corresponding to the target item as a candidate popular item by matching the popular item corresponding to the target item in the popular item database, and determines the matched popular item as the candidate popular item.

[0060] Further, the similarity between the candidate popular item and the merchant inventory item is obtained by searching the similarity between the candidate popular item and each merchant inventory item in the popular item database.

[0061] In some embodiments, Table 2 is an example table of a popular item database provided by the embodiment of the present disclosure. As shown in Table 2, the merchant inventory items include item C, item D, item E, item F, and item G. The popular items corresponding to item C include item C1 and item C2. The similarity between item C and item C1 is 0.88, the similarity between item C and item C2 is 0.8, the similarity between item D and item C1 is 0.66, the similarity between item D and item C2 is 0.7, the similarity between item E and item C1 is 0.55, the similarity between item E and item C2 is 0.6, the similarity between item F and item C1 is 0.65, the similarity between item F and item C2 is 0.7, the similarity between item G and item C1 is 0.84, and the similarity between item G and item C2 is 0.9.

[0062]

[0063]

[0064] Table 2

[0065] Further, the to-be-recommended hot item is determined from the candidate hot items according to the similarity between the candidate hot items and the merchant inventory items, including: for each candidate hot item, accumulating the similarity between the candidate hot item and each merchant inventory item to obtain a recommendation score corresponding to the candidate hot item; and determining the to-be-recommended hot item from the candidate hot items according to the recommendation score corresponding to each candidate hot item.

[0066] In combination with Table 2, in some embodiments, the historical purchase items of the to-be-recommended user include item C, item D, item N and item M, and the merchant inventory items include item C, item D, item E, item F and item G. The target items are the merchant inventory items that are the same as the historical purchase items, and the target items are item C and item D. The hot items corresponding to the target item "item C" matched in the hot item database are item C1 and item C2, and the hot items corresponding to the target item "item D" are item D1 and item D2. The matched hot items item C1 and item C2, item D1 and item D2 are determined as candidate hot items. The similarity between item C1 and each merchant inventory item found in the hot item database includes: the similarity between item C and item C1 is 0.88, the similarity between item D and item C1 is 0.66, the similarity between item E and item C1 is 0.55, the similarity between item F and item C1 is 0.65, and the similarity between item G and item C1 is 0.84. The similarity between item C1 and each merchant inventory item is accumulated to obtain a recommendation score corresponding to item C1, which is 3.58. Similarly, the recommendation score corresponding to item C2 is 3.7. The recommendation score corresponding to item D1 is 3.75. The recommendation score corresponding to item D2 is 3.65.

[0067] Further, the to-be-recommended hot item is determined from the candidate hot items according to the recommendation score corresponding to each candidate hot item, including: sorting the candidate hot items in descending order of the recommendation score; and determining the candidate hot items in the top pre-set number of the sorting order as the to-be-recommended hot items. The pre-set number is 5.

[0068] In combination with Table 2, in some embodiments, the historical purchase items of the to-be-recommended user include item C, item D, item N and item M, and the merchant inventory items include item C, item D, item E, item F and item G. The target items are the merchant inventory items that are the same as the historical purchase items, and the target items are item C and item D. The hot items corresponding to the target item "item C" matched in the hot item database are item C1 and item C2, and the hot items corresponding to the target item "item D" are item D1 and item D2. The matched hot items item C1 and item C2, item D1 and item D2 are determined as candidate hot items. The similarity between item C1 and each merchant inventory item found in the hot item database includes: the similarity between item C and item C1 is 0.88, the similarity between item D and item C1 is 0.66, the similarity between item E and item C1 is 0.55, the similarity between item F and item C1 is 0.65, and the similarity between item G and item C1 is 0.84. The similarity between item C1 and each merchant inventory item is accumulated to obtain a recommendation score corresponding to item C1, which is 3.58. Similarly, the recommendation score corresponding to item C2 is 3.7. The recommendation score corresponding to item D1 is 3.75. The recommendation score corresponding to item D2 is 3.65. Figure 3 The method provided by the embodiments of the present disclosure for item recommendation includes:

[0069] In step S301, the electronic device obtains a consumed item list corresponding to a to-be-recommended user; the consumed item list includes a plurality of historical purchase items.

[0070] In step S302, the electronic device determines, as target items, the merchant inventory items that are the same as each historical purchase item in the preset popular item database; the popular item database stores merchant inventory items, popular items corresponding to the merchant inventory items, and similarities between the popular items and the merchant inventory items.

[0071] In step S303, the electronic device determines, as candidate popular items, the popular items corresponding to the target items, and obtains similarities between the candidate popular items and the merchant inventory items.

[0072] In step S304, the electronic device performs the following operation on each candidate popular item: adding the similarities between the candidate popular item and each merchant inventory item to obtain a recommendation score corresponding to the candidate popular item.

[0073] In step S305, the electronic device determines, from the candidate popular items, a popular item to be recommended according to the recommendation scores corresponding to the candidate popular items.

[0074] In step S306, the electronic device recommends the popular item to be recommended to the user to be recommended.

[0075] The method for item recommendation provided in the embodiments of the present disclosure has the following advantages: since the popular item database pre-stores merchant inventory items, popular items corresponding to the merchant inventory items, and similarities between the popular items and the merchant inventory items, and directly determines, from the preset popular item database, candidate popular items according to historical purchase items and similarities between the candidate popular items and each merchant inventory item, it is not necessary to calculate the similarities between the historical purchase items and the popular items, and the item to be recommended can be quickly obtained, thereby improving the efficiency of item recommendation.

[0076] Optionally, after the popular item to be recommended is recommended to the user to be recommended, the method further includes: updating the popular item database every preset time period. The preset time period is one week.

[0077] Further, updating the popular item database every preset time period includes: obtaining a hot search item list in a preset application APP, determining, as candidate added items, the first preset number of hot search items in the hot search item list, obtaining similarities between the candidate added items and each merchant inventory item, determining, as popular items, the second preset number of candidate added items that are most similar to each inventory item, and adding the determined popular items and the similarities between the popular items and each merchant inventory item to the popular item database. In this way, the popular item database can be updated every preset time period, the hottest item can be obtained in real time to recommend items to the user to be recommended, and the experience of the user to be recommended in item recommendation is improved.

[0078] In combination Figure 4 As shown in the embodiments of the present disclosure, a method for item recommendation is provided, which comprises the following steps:

[0079] In step S401, the electronic device acquires a list of consumed items corresponding to a user to be recommended in response to a recommendation request sent by the user to be recommended, wherein the list of consumed items comprises a plurality of historical purchase items.

[0080] In step S402, the electronic device determines, as target items, the merchant inventory items in a preset popular item database that are identical to each of the historical purchase items, wherein the popular item database stores the merchant inventory items, the popular items corresponding to the merchant inventory items, and the similarity between the popular items and the merchant inventory items.

[0081] In step S403, the electronic device determines, as candidate popular items, the popular items corresponding to the target items, and acquires the similarity between the candidate popular items and the merchant inventory items.

[0082] In step S404, the electronic device determines, from each of the candidate popular items, a popular item to be recommended according to the similarity between the candidate popular items and the merchant inventory items.

[0083] In step S405, the electronic device recommends the popular item to be recommended to the user to be recommended.

[0084] In step S406, the electronic device updates the popular item database every preset time period.

[0085] The method for item recommendation provided by the embodiments of the present disclosure can directly determine, from the preset popular item database, the candidate popular items and the similarity between the candidate popular items and each of the merchant inventory items according to the historical purchase items after receiving the recommendation request initiated by the user to be recommended, without the need to calculate the similarity between the historical purchase items and the popular items, so as to quickly acquire the item to be recommended, thereby improving the efficiency of item recommendation. Meanwhile, the popular item database is updated every preset time period, so that the similarity between the popular items and the merchant inventory items can be calculated in advance and stored in the popular item database, which facilitates the item recommendation by the user to be recommended, and realizes the personalized item recommendation for the user by using the recommendation technology.

[0086] In combination Figure 5As shown, the embodiment of the present disclosure provides a device for item recommendation, which comprises an acquisition module 501, a first determination module 502, a second determination module 503, a third determination module 504 and a recommendation module 505. The acquisition module 501 is configured to acquire a consumed item list corresponding to a to-be-recommended user, and send the consumed item list to the first determination module; the consumed item list comprises a plurality of historical purchase items. The first determination module 502 is configured to receive the consumed item list sent by the acquisition module, determine a merchant inventory item same as each historical purchase item in a preset popular item database as a target item, and send the target item to the second determination module. The popular item database stores a merchant inventory item, a popular item corresponding to the merchant inventory item, and a similarity between the popular item and the merchant inventory item. The second determination module 503 is configured to receive the target item sent by the first determination module, determine a popular item corresponding to the target item as a candidate popular item, and acquire a similarity between the candidate popular item and the merchant inventory item, and send the similarity between the candidate popular item and the merchant inventory item to the third determination module. The third determination module 504 is configured to receive the similarity between the candidate popular item and the merchant inventory item sent by the second determination module, determine a to-be-recommended popular item from each candidate popular item according to the similarity between the candidate popular item and the merchant inventory item, and send the to-be-recommended popular item to the recommendation module. The recommendation module 505 is configured to receive the to-be-recommended popular item sent by the third determination module, and recommend the to-be-recommended popular item to the to-be-recommended user.

[0087] By using the device for item recommendation provided by the embodiment of the present disclosure, the acquisition module acquires a consumed item list corresponding to a to-be-recommended user; the consumed item list comprises a plurality of historical purchase items. The first determination module determines a merchant inventory item same as each historical purchase item in a preset popular item database as a target item; the popular item database stores a merchant inventory item, a popular item corresponding to the merchant inventory item, and a similarity between the popular item and the merchant inventory item. The second determination module determines a popular item corresponding to the target item as a candidate popular item, and acquires a similarity between the candidate popular item and the merchant inventory item. The third determination module determines a to-be-recommended popular item from each candidate popular item according to the similarity between the candidate popular item and the merchant inventory item. The recommendation module recommends the to-be-recommended popular item to the to-be-recommended user. Since the popular item database pre-stores a popular item corresponding to a merchant inventory item and a similarity between the popular item and the merchant inventory item, by determining a candidate popular item from the preset popular item database according to a historical purchase item and a similarity between the candidate popular item and each merchant inventory item, it is not necessary to calculate a similarity between the historical purchase item and the popular item, the to-be-recommended item can be quickly acquired, and thus the efficiency of item recommendation can be improved.

[0088] Further, the acquisition module is configured to acquire the consumed item list corresponding to the user to be recommended by: acquiring a historical shopping record corresponding to the user to be recommended, and determining the consumed item list according to the historical shopping record.

[0089] Further, the determination of the consumed item list according to the historical shopping record comprises: in the case that there is a purchase item record in the historical shopping record, counting the items in the purchase item record to obtain the consumed item list. Or, in the case that there is no purchase item record in the historical shopping record, determining a target user from a preset candidate user database, and determining the consumed item list corresponding to the target user as the consumed item list corresponding to the user to be recommended. The candidate user database stores a plurality of candidate users, and each candidate user corresponds to a consumed item list.

[0090] Further, the determination of the target user from the preset candidate user database comprises: respectively acquiring a user similarity between the user to be recommended and each candidate user, and determining the candidate user with the highest user similarity to the user to be recommended as the target user.

[0091] Further, the third determination module is configured to determine the popular item to be recommended from the candidate popular items according to the similarity between the candidate popular items and the merchant inventory items by: performing the following operation on each candidate popular item: accumulating the similarity between the candidate popular item and each merchant inventory item to obtain a recommendation score corresponding to the candidate popular item. The popular item to be recommended is determined from the candidate popular items according to the recommendation score corresponding to each candidate popular item.

[0092] Further, the recommendation module is configured to determine the popular item to be recommended from the candidate popular items according to the recommendation score corresponding to each candidate popular item by: sorting the candidate popular items in descending order of the recommendation score; and determining the candidate popular items in the first preset number of the sorting order as the popular item to be recommended.

[0093] Further, the device for item recommendation further comprises a recommendation module, which is configured to update the popular item database every preset time period after the popular item to be recommended is recommended to the user to be recommended.

[0094] In combination Figure 6As shown, the electronic device provided by the embodiment of the present disclosure includes a processor 600 and a memory 601. Optionally, the electronic device can further include a communication interface 602 and a bus 603. The processor 600, the communication interface 602 and the memory 601 can complete mutual communication through the bus 603. The communication interface 602 can be used for information transmission. The processor 600 can invoke the logic instructions in the memory 601 to execute the method for item recommendation of the above-mentioned embodiment.

[0095] By using the electronic device provided by the embodiment of the present disclosure, the list of consumed items corresponding to the user to be recommended is obtained; the list of consumed items includes a plurality of historical purchase items; the merchant inventory items identical to each historical purchase item in a preset popular item database are determined as target items; the merchant inventory items, the popular items corresponding to the merchant inventory items, and the similarity between the popular items and the merchant inventory items are stored in the popular item database; the popular items corresponding to the target items are determined as candidate popular items, and the similarity between the candidate popular items and the merchant inventory items is obtained; the popular item to be recommended is determined from each candidate popular item according to the similarity between the candidate popular items and the merchant inventory items; and the popular item to be recommended is recommended to the user to be recommended. Since the popular items corresponding to the merchant inventory items and the similarity between the popular items and the merchant inventory items are stored in the popular item database in advance, the candidate popular items and the similarity between the candidate popular items and each merchant inventory item are directly determined from the preset popular item database according to the historical purchase items, and the similarity between the historical purchase items and the popular items does not need to be calculated, the item to be recommended can be quickly obtained, and thus the efficiency of item recommendation can be improved.

[0096] In addition, the logic instructions in the memory 601 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer readable storage medium.

[0097] Optionally, the electronic device includes a server, a user terminal, and the like. Optionally, the user terminal includes a computer, a tablet computer, a smart phone, and the like.

[0098] Optionally, in the case of the electronic device being a server, the server sends the popular item to be recommended to the user terminal, and triggers the user terminal to display the popular item to be recommended to the user to be recommended.

[0099] Optionally, in the case of the electronic device being a user terminal, the popular item to be recommended is displayed to the user to be recommended through the display interface of the user terminal.

[0100] The memory 601 can be used to store software programs, computer executable programs, such as program instructions / modules corresponding to the method in the embodiments of the present disclosure. The processor 600 executes the function application and data processing, that is, implements the method for item recommendation in the above embodiments, by running the program instructions / modules stored in the memory 601.

[0101] The memory 601 can include a program storage area and a data storage area. The program storage area can store an operating system and at least one application required by a function; the data storage area can store data created according to the use of the terminal device, and the like. In addition, the memory 601 can include a high-speed random access memory, and can also include a non-volatile memory.

[0102] The embodiments of the present disclosure provide a storage medium, which stores program instructions. When the program instructions are executed, the above method for item recommendation is executed.

[0103] The embodiments of the present disclosure provide a computer program product, which includes a computer program stored on a computer readable storage medium. The computer program includes program instructions, which, when executed by a computer, cause the computer to execute the above method for item recommendation.

[0104] The above computer readable storage medium can be a transitory computer readable storage medium or a non-transitory computer readable storage medium.

[0105] The technical solutions of the embodiments of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present disclosure. The aforementioned storage medium can be a non-transitory storage medium, including a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes, or can be a transitory storage medium.

[0106] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0107] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0108] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to apparatuses, devices, etc.), can be implemented in other manners. For example, the described apparatus embodiments can be implemented only in a form of a logical function, and can be implemented by using a manner such as software (for example, application program) or the like. In some embodiments, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or indirect coupling between different units, or the coupling or direct coupling or indirect coupling between the displayed or discussed communication connections can be in a form of electrical, mechanical or other forms.

[0109] The flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the system, method and computer program product according to the embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment or a part of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions noted in the blocks can occur in an order different from that noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the drawings, the operations or steps corresponding to different blocks can also occur in an order different from that disclosed in the descriptions, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. Each block in the block diagrams and / or flowcharts, and the combination of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for item recommendation, characterized by, The method comprises the following steps: acquiring a historical shopping record corresponding to the user to be recommended; in a case where there is a purchase item record in the historical shopping record, counting the items in the purchase item record to obtain a consumed item list; the consumed item list comprises a plurality of historical purchase items; in a case where there is no purchase item record in the historical shopping record, determining a target user from a preset alternative user database; determining a consumed item list corresponding to the target user as a consumed item list corresponding to the user to be recommended; wherein the preset alternative user database stores an average user, and the target user is determined from the preset alternative user database by determining the average user in the preset alternative user database as the target user; the average user is a user portrait corresponding to an active user group, and the active user group is a user group composed of users exceeding a preset active degree; determining a target item from a merchant inventory item in the preset popular item database which is the same as each of the historical purchase items; the popular item database stores a merchant inventory item, a popular item corresponding to the merchant inventory item, and a similarity between the popular item and the merchant inventory item; determining a popular item corresponding to the target item as an alternative popular item, and finding a similarity between the alternative popular item and each merchant inventory item in the popular item database; determining a recommended popular item from each of the alternative popular items according to the similarity between the alternative popular item and the merchant inventory item; recommending the recommended popular item to the user to be recommended.

2. The method of claim 1, wherein: the alternative user database further stores a plurality of alternative users and a consumed item list corresponding to each alternative user.

3. The method of claim 2, wherein, Determining a target user from a preset alternative user database further comprises: respectively acquiring a user similarity between the user to be recommended and each alternative user; determining an alternative user with the highest user similarity to the user to be recommended as the target user.

4. The method of claim 1, wherein, Determining a recommended popular item from each of the alternative popular items according to the similarity between the alternative popular item and the merchant inventory item comprises: for each alternative popular item, adding the similarity between the alternative popular item and each merchant inventory item to obtain a recommendation score corresponding to the alternative popular item; determining a recommended popular item from each of the alternative popular items according to the recommendation score corresponding to each alternative popular item.

5. The method of claim 4, wherein, Determining a recommended popular item from each of the alternative popular items according to the recommendation score corresponding to each alternative popular item comprises: sorting each alternative popular item in descending order of the recommendation score; determining alternative popular items in the top pre-set number of the sorting order as the recommended popular items.

6. The method of claim 1, wherein, After recommending the recommended popular item to the user to be recommended, the method further comprises: updating the popular item database every pre-set time period.

7. An apparatus for item recommendation, the apparatus comprising: The method comprises the following steps: The acquisition module is configured to acquire a historical shopping record corresponding to the user to be recommended; in a case where a purchase item record exists in the historical shopping record, counting items in the purchase item record to obtain the consumed item list; the consumed item list includes a plurality of historical purchase items; in a case where a purchase item record does not exist in the historical shopping record, determining a target user from a preset alternative user database; The consumed item list corresponding to the target user is determined as the consumed item list corresponding to the user to be recommended. The preset alternative user database stores an average user, and the target user is determined from the preset alternative user database, including: determining the average user in the preset alternative user database as the target user; the average user is a user portrait corresponding to an active user group, and the active user group is a user group composed of users exceeding a preset active degree. The first determination module is configured to determine, as target items, merchant inventory items identical to each of the historical purchase items in a preset popular item database; the popular item database stores merchant inventory items, popular items corresponding to the merchant inventory items, and similarities between the popular items and the merchant inventory items. The second determination module is configured to determine popular items corresponding to the target items as alternative popular items, and find similarities between the alternative popular items and each of the merchant inventory items in the popular item database. The third determination module is configured to determine, from each of the alternative popular items, a recommended popular item according to the similarity between the alternative popular item and the merchant inventory item. The recommendation module is configured to recommend the recommended popular item to the user to be recommended.

8. An electronic device comprising a processor and a memory having stored thereon program instructions, wherein, The processor is configured to execute the method for item recommendation according to any one of claims 1 to 6 when running the program instruction.

9. A storage medium storing program instructions, characterized in that, The program instruction, when running, executes the method for item recommendation according to any one of claims 1 to 6.

Images