Article recommendation method and device

Abstract

The invention discloses an article recommendation method and device, and relates to the technical field of electronic commerce and medicine supply chains. A specific embodiment of the method comprises the following steps: in response to a system recommendation function triggered by a user, determining a target shop browsed by the user and an operation article of the user for the target shop; similar articles and matched articles corresponding to the operation articles are determined; determining at least one display keyword according to the similar articles and the matched articles; determining a search keyword from the at least one display keyword; and determining a recommended article corresponding to the user from a plurality of alternative articles sold by the target shop by using the search keyword. According to the embodiment, the article that the user wants to purchase is intelligently recommended, the complexity of shopping operation of the user in a store can be reduced, and the shopping experience of the user is improved.

Description

Technical Field

[0001] This invention relates to the fields of e-commerce and pharmaceutical supply chain technology, and in particular to a method and apparatus for recommending items. Background Technology

[0002] With the increasing convenience of online shopping, more and more users are using it to meet their needs. In the online shopping process, users first select a target store, then browse its various items to find what they need. Alternatively, users can enter keywords into the store's search box and find the desired items from the returned list. However, this in-store shopping process is complex and cumbersome, resulting in a poor shopping experience. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and apparatus for recommending items, which intelligently recommends items that users want to buy, thereby reducing the complexity of in-store shopping operations and improving the user's shopping experience.

[0004] In a first aspect, embodiments of the present invention provide a method for recommending items, including:

[0005] In response to a user triggering the system recommendation function, determine the target store the user is browsing and the items the user interacts with in the target store;

[0006] Identify similar and matching items for the item being manipulated;

[0007] Based on similar items and matching items, determine at least one display keyword;

[0008] Determine the search keywords from at least one of the displayed keywords;

[0009] By using search keywords, the system identifies the recommended item for the user from multiple alternative items sold in the target store.

[0010] Optionally, at least one display keyword is determined based on similar items and matching items, including:

[0011] Identify the target item from similar and matching items;

[0012] Get at least one item attribute corresponding to the target item;

[0013] The item attributes corresponding to the target item are determined as the display keywords.

[0014] Optionally, the items that can be operated include: adding items to the cart and browsing items;

[0015] Identify similar items to the item being manipulated, including:

[0016] Based on the similarity relationship between items, determine the first similar item corresponding to the added item;

[0017] And / or,

[0018] Based on the similarity between items, determine the second most similar item corresponding to the browsed item.

[0019] Optionally, the items that can be operated include: adding items to the cart and browsing items;

[0020] Determine the items that correspond to the items being manipulated, including:

[0021] Based on the item pairing relationships, determine the first matching item corresponding to the added item;

[0022] And / or,

[0023] Based on the item pairing relationships, determine the second matching item corresponding to the item being viewed.

[0024] Optionally, after determining the recommended item for the user from multiple alternative items sold in the target store using search keywords, the process also includes:

[0025] If the number of recommended items is less than the quantity threshold, similar stores are identified based on the target store's business scope.

[0026] By using search keywords, supplementary items can be identified from multiple items sold in similar stores, so that the terminal can display the recommended items and supplementary items in the recommended items list.

[0027] Optionally, after determining the recommended item for the user from multiple alternative items sold in the target store using search keywords, the process also includes:

[0028] Determine the user's profile information and the item information for each recommended item;

[0029] Based on the portrait information and the item information of each recommended item, determine the recommendation value corresponding to each recommended item;

[0030] Based on the recommendation value of each recommended item, a ranking value is determined for each recommended item, so that the terminal can display a list of recommended items according to the ranking value of each recommended item.

[0031] Secondly, embodiments of the present invention provide an item recommendation device, comprising:

[0032] The function trigger module is used to respond to the user triggering the system recommendation function, and to determine the target store that the user is browsing and the items that the user is interacting with in the target store;

[0033] The item identification module is used to identify similar items and matching items corresponding to the item being operated on;

[0034] The first determination module is used to determine at least one display keyword based on similar items and matching items;

[0035] The second determining module is used to determine the search keyword from at least one displayed keyword;

[0036] The search module is used to identify recommended items for users from multiple alternative items sold in a target store using search keywords.

[0037] Thirdly, embodiments of the present invention provide an electronic device, comprising:

[0038] One or more processors;

[0039] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the methods of any of the above embodiments.

[0040] Fourthly, embodiments of the present invention provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method of any of the above embodiments.

[0041] Fifthly, embodiments of the present invention provide a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method of any of the above embodiments.

[0042] One embodiment of the above invention has the following advantages or beneficial effects: It identifies similar and complementary items corresponding to the items a user selects from a target store. Based on the similar and complementary items, it determines at least one display keyword, and then determines a search keyword from the display keywords. Finally, using the search keyword, it determines the recommended item for the user from multiple alternative items sold in the target store. The solution of this invention intelligently recommends items that the user wants to buy, reducing the complexity of the user's in-store shopping operations and improving the user's shopping experience.

[0043] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0044] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein:

[0045] Figure 1 This is a schematic diagram of the flow of an item recommendation method provided in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the flow of an item recommendation method provided in another embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the flow of an item recommendation method provided in another embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of the flow of an item recommendation method provided in another embodiment of the present invention;

[0049] Figure 5a This is a schematic diagram of a drug browsing page provided in one embodiment of the present invention;

[0050] Figure 5b This is a schematic diagram of a drug add-to-cart page provided in one embodiment of the present invention;

[0051] Figure 5c This is a schematic diagram of a keyword display page provided in one embodiment of the present invention;

[0052] Figure 6 This is a schematic diagram of the structure of an item recommendation device provided in one embodiment of the present invention;

[0053] Figure 7 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0054] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0055] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of this invention comply with the relevant provisions of national laws and regulations.

[0056] Figure 1 This is a schematic diagram illustrating the flow of an item recommendation method according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0057] Step 101: In response to the user triggering the system recommendation function, determine the target store the user is browsing and the items the user interacts with in the target store.

[0058] Users can trigger the system's recommendation function by clicking preset buttons, entering preset pages, etc. The items to be operated on are those related to the shopping actions initiated by the user while browsing the target store. Shopping actions can include: adding to cart, adding to favorites, following, and browsing. The items to be operated on are the items sold by the target store. Items to be operated on can include: items added to cart, items added to favorites, items followed, and items browsed. Step 102: Determine similar items and matching items corresponding to the items to be operated on.

[0059] Similar items are those that have the same or similar attributes as the item being operated on. Item attributes may include: item name, item purpose, main function, item category, item manufacturer, item origin, item material, etc.

[0060] Accessory items and functional items are frequently purchased by users simultaneously. The probability of users purchasing accessory items and functional items together exceeds the preset probability. For example, shoe insoles are accessory items for leather shoes, and thermometers are accessory items for fever-reducing medication.

[0061] Similar items and complementary items can be items sold in the target store or items sold in other stores on the shopping platform.

[0062] Step 103: Determine at least one display keyword based on similar and matching items.

[0063] It can retrieve the item attributes of similar items and their paired items. It combines the item attributes of similar items and their paired items to generate an attribute set. From this attribute set, it randomly or manually selects at least one display keyword.

[0064] Step 104: Determine the search keywords from at least one display keyword.

[0065] Search keywords can be determined manually or randomly from at least one set of displayed keywords. Alternatively, at least one set of displayed keywords can be sent to the terminal. The terminal displays a list of displayed keywords. This list showcases the various displayed keywords. The user selects at least one search keyword from the list of displayed keywords using a selection command.

[0066] It can also determine the match value between each displayed keyword and the user, and select displayed keywords with a match value greater than a preset value as search keywords. The match value is used to represent the degree of user interest in the displayed keywords.

[0067] Step 105: Using search keywords, determine the recommended item for the user from multiple alternative items sold in the target store.

[0068] The alternative items can be items sold in the target store that belong to the same category as similar or complementary items. Alternative items can also be all items sold in the target store. Alternative items can also be items sold in pre-defined target stores. Using the search keywords as the user's input, the system's existing search program determines the recommended items for the user from multiple alternative items.

[0069] The solution of this invention is applied to a server. After determining at least one recommended item, the server sends the at least one recommended item to the terminal. The terminal displays a list of recommended items consisting of at least one recommended item. Based on the list of recommended items, the user can perform operations such as browsing, adding to cart, and placing orders.

[0070] In this embodiment of the invention, similar items and complementary items corresponding to the items the user selects from a target store are determined. Based on the similar and complementary items, at least one display keyword is determined, and then a search keyword is determined from the display keywords. Finally, using the search keyword, recommended items for the user are determined from multiple alternative items sold in the target store. This embodiment of the invention can intelligently recommend items that the user wants to buy, reducing the complexity of the user's in-store shopping operations and improving the user's shopping experience.

[0071] The solution presented in this invention addresses the problem of complex and repetitive searches when users purchase multiple items from online stores. By leveraging user actions such as adding items to their cart or browsing within the target store, the system intelligently recommends items the user desires, reducing the complexity and frequency of in-store searches and optimizing the user's shopping experience.

[0072] In one embodiment of the present invention, determining at least one display keyword based on similar items and matching items includes: determining a target item from similar items and matching items; obtaining at least one item attribute corresponding to the target item; and determining the item attribute corresponding to the target item as a display keyword.

[0073] Similar items and matching items are sent to the terminal. The terminal displays a list of candidate items. This list displays each similar item and each matching item. The user selects the target item from the list using a selection command. At least one item attribute corresponding to the target item is obtained, and this attribute is used as the display keyword.

[0074] In one embodiment of the present invention, the operation of an item includes: adding an item to a shopping list and browsing an item; determining similar items corresponding to the operation of the item includes: determining a first similar item corresponding to the item to be added to the shopping list based on the similarity relationship between the items; and / or, determining a second similar item corresponding to the item to be browsed based on the similarity relationship between the items.

[0075] The item similarity relationship includes multiple similar item records. Each similar item record takes the following form: Similar Item 1 identifier, Similar Item 2 identifier, Similar Item 3 identifier, Similar Item 4 identifier, and so on. The target similar item record corresponding to the added-to-purchase or browsed item is identified. The target similar item record includes the item identifier of the added-to-purchase or browsed item. Other items in the target similar item record besides the added-to-purchase or browsed items are identified as similar items.

[0076] Item similarity relationships can be configured and maintained manually. Alternatively, algorithms or large models can be used to obtain initial similar item records, which can then be manually reviewed, filtered, and configured to generate item similarity relationships. Similar item records can be stored in a cache to speed up the process of determining the similar items corresponding to the item being operated on.

[0077] In one embodiment of the present invention, the operation of an item includes: adding an item and browsing an item; determining the matching item corresponding to the operation item includes: determining a first matching item corresponding to the added item based on the item matching relationship; and / or, determining a second matching item corresponding to the browsed item based on the item matching relationship.

[0078] The item pairing relationship includes multiple pairing item records. Each pairing item record has the following format: Pairing Item 1 identifier, Pairing Item 2 identifier, Pairing Item 3 identifier, Pairing Item 4 identifier, and so on. Identify the target pairing item record corresponding to the added-to-purchase or browsed item. The target pairing item record includes the item identifier of the added-to-purchase or browsed item. Other items in the target pairing item record besides the added-to-purchase or browsed items are identified as pairing items.

[0079] Item pairing relationships can be configured and maintained manually. Alternatively, algorithms or large models can be used to obtain initial item pairing records. These initial records are then manually reviewed, filtered, and configured to determine the item pairing relationships. These pairing records can be cached to speed up the process of determining the pairing items corresponding to the items being manipulated.

[0080] If a user adds an item to their cart, an add-to-cart record is generated. The format of the add-to-cart record is as follows: User ID_Item ID, Store ID_User ID_Item ID. Add-to-cart records are saved in the add-to-cart cache. Each time a user changes an item they added, the latest add-to-cart record is updated in the add-to-cart cache. By saving add-to-cart records in the add-to-cart cache, the system can quickly retrieve the user's added items when the user triggers the system's recommendation function.

[0081] If a user browses an item, a browsing history is generated. The format of the browsing history is as follows: User ID_Item ID, Store ID_User ID_Item ID. The browsing history is saved in the browsing cache. Each time a user browses an item, a new browsing history is generated and saved to the browsing cache. The system periodically clears expired browsing history from the browsing cache. By saving the browsing history to the browsing cache, the system can quickly retrieve the items browsed by the user when the system triggers the recommendation function.

[0082] Figure 2 This is a schematic diagram of the flow of an item recommendation method provided in another embodiment of the present invention. Figure 2 As shown, the method includes:

[0083] Step 201: In response to the user triggering the system recommendation function, determine the target store that the user is browsing and the items the user interacts with in the target store.

[0084] The system recommendation function is an in-store recommendation feature targeting specific stores. The target store is the store the user is currently browsing. The items the user interacts with in relation to the target store are the items related to the user's shopping actions within that store. Shopping actions can include: adding to cart, adding to favorites, following, and browsing. The items interacted with can include: items added to cart, items added to favorites, items followed, and items browsed.

[0085] Step 202: Determine the similar items and matching items corresponding to the item being operated on.

[0086] Step 203: Determine at least one display keyword based on similar items and matching items.

[0087] Step 204: Determine the search keywords from at least one display keyword.

[0088] Step 205: Using search keywords, determine the recommended item for the user from multiple alternative items sold in the target store.

[0089] Step 206: In response to the number of recommended items being less than the quantity threshold, identify similar stores based on the target store's business scope.

[0090] The quantity threshold can be set according to specific needs, such as 8, 15, etc. The business scope refers to the area to which the items sold in the store belong, such as food, medicine, clothing, bags, etc.

[0091] Similar stores can be identified as follows: Randomly select stores with the same or similar business scope as the target store as similar stores. Select multiple stores with the same or similar business scope as candidate stores; determine the similar stores from the candidate stores based on their weights. The store weights can be determined by factors such as the store's reputation score, user reviews, and the distance between the shipping location and the user's delivery location.

[0092] Step 207: Using search keywords, identify supplementary items from multiple items sold in similar stores, so that the terminal can display the recommended items and supplementary items in the recommended items list.

[0093] The number of items to replenish can be determined based on a quantity threshold and the number of recommended items. For example, the number of items to replenish equals the quantity threshold minus the number of recommended items.

[0094] In the solution of this invention embodiment, if the target store does not sell the recommended item, or the number of recommended items in the target store is small, supplementary items can be found from nearby stores, and both the recommended item and the supplementary item can be recommended to the user. This allows the user to have a wider range of items to choose from, making it easier for the user to select the items they need.

[0095] Figure 3 This is a schematic diagram of the flow of an item recommendation method provided in another embodiment of the present invention. Figure 3 As shown, the method includes:

[0096] Step 301: In response to the user triggering the system recommendation function, determine the target store that the user is browsing and the items the user interacts with in the target store.

[0097] Step 302: Determine the similar items and matching items corresponding to the item being operated on.

[0098] Step 303: Determine at least one display keyword based on similar items and matching items.

[0099] Step 304: Determine the search keywords from at least one display keyword.

[0100] Step 305: Using search keywords, determine the recommended item for the user from multiple alternative items sold in the target store.

[0101] Step 306: Determine the user's profile information and the item information for each recommended item.

[0102] Step 307: Determine the recommendation value for each recommended item based on the portrait information and the item information of each recommended item.

[0103] The recommendation score represents the probability that a user will purchase an item. It can also represent the degree of interest a user has in an item. User profile information and item information for each recommended item can be input into the recommendation model to obtain the recommendation score for each item. The higher the recommendation score, the higher the probability that a user will purchase the recommended item.

[0104] Step 308: Determine the ranking value of each recommended item based on its recommendation value, so that the terminal can display the list of recommended items according to the ranking value of each recommended item.

[0105] After the server identifies at least one recommended item, it sends that item to the terminal. The terminal then displays a list of recommended items, consisting of at least one item. Users can then browse and place orders based on this list.

[0106] In this embodiment of the invention, items with higher recommendation values ​​are more likely to be purchased by users. The ranking value is inversely proportional to the recommendation value. Items with higher recommendation values ​​are assigned smaller ranking values ​​so that they appear earlier in the recommended item list. Placing items with a higher probability of purchase or greater user interest at the top of the recommended item list improves the user shopping experience and increases item conversion rates.

[0107] Figure 4 This is a schematic diagram of the flow of an item recommendation method provided in another embodiment of the present invention. Figure 4 As shown, a user enters an online store. The user browses items and adds items to their cart. When the user clicks the store's search function, the system retrieves a set of similar items and matching items. Based on the similar and matching items, at least one display keyword is determined. Based on the user's click, a search keyword is determined from the at least one display keyword. Recommended items sold in the store are retrieved based on the search keyword. The recommended item list is displayed on the front end.

[0108] To facilitate understanding of the solutions in the embodiments of the present invention, the solutions of the present invention will be applied to the user's drug purchase process for explanation below. In the solutions of the embodiments of the present invention, the operational items may include: browsing drugs and adding drugs to the cart. Similar items are similar drugs browsed and added to the cart. Complementary items are complementary drugs browsed and added to the cart.

[0109] After a user browses a certain medicine, it may not be the medicine the user wants to buy. Therefore, a process for handling similar medicines needs to be added. Based on the similarity relationship between items, similar medicines should be identified.

[0110] After a user adds a certain medicine to their cart, they may need to search for complementary medicines to obtain. Therefore, a process for handling complementary medicine purchases needs to be added. This process involves determining the complementary medicines based on item pairing relationships.

[0111] Users trigger the system's recommendation function by clicking the "In-Store Search" button. The service checks the add-to-cart cache to see if the user has added any medicine to their cart in the target store. If medicine has been added, the service retrieves the set of items that were bundled with the added item. If no medicine has been added, the service checks the browsed item cache to determine if any medicine has been viewed. If medicine has been viewed, the service identifies similar medicines.

[0112] Similar or complementary drug names are displayed as keywords. Users click on a displayed keyword and select a search keyword from at least one of them. The server searches for items in the target store based on the search keyword, retrieves recommended items, and pushes these recommended items to the front end. The front end redirects to the target store's item search results page, displaying a list of recommended items for the user to choose from.

[0113] If no items have been added to the cart or browsed, the sales volume of each item in the target store is determined. Based on the sales volume of each item, a list of best-selling items in the store is generated. This list of best-selling items is then displayed to the user.

[0114] Figure 5a This is a schematic diagram of a drug browsing page provided in one embodiment of the present invention. Figure 5a As shown, users can browse medicines and perform actions such as asking questions and adding them to their cart on the medicine browsing page.

[0115] Figure 5b This is a schematic diagram of a drug add-to-purchase page provided in one embodiment of the present invention. Figure 5b As shown, users can add medicines to their shopping cart and perform other operations such as editing and checkout within the cart.

[0116] The system maintains item similarity and item combination relationships. By integrating offline store and item information resources from the instant retail business, it generates various similar or combined drug relationships based on stores and a professional knowledge base. Item similarity and item combination relationships can be stored in the database and then pushed to the system cache for convenient and quick querying by users.

[0117] Figure 5c This is a schematic diagram of a keyword display page provided in one embodiment of the present invention. For example... Figure 5cAs shown, for example, if a user adds XX units to their cart, the system searches for similar items and compatible items for that XX unit based on the item similarity and combination relationships maintained in the system. The names of the found similar items and compatible items are then used as display keywords.

[0118] When a user clicks on a displayed keyword, they select a search keyword from at least one of the displayed keywords. The front end redirects to the store's item search results page, displaying a list of items for the user to choose from. The user can then select items and complete the purchase process in their shopping cart.

[0119] The solution of this invention intelligently recommends similar items or complementary items that the user wants to search for in real time based on the user's browsing and adding to cart operations, reducing the complexity of the user manually entering search conditions and improving the convenience of the user's shopping.

[0120] Figure 6 This is a schematic diagram of the structure of an item recommendation device provided in one embodiment of the present invention. Figure 6 As shown, the device includes:

[0121] The function trigger module 601 is used to respond to the user triggering the system recommendation function, and to determine the target store that the user is browsing and the items that the user is operating on in the target store;

[0122] The item determination module 602 is used to determine similar items and matching items corresponding to the operated item;

[0123] The first determining module 603 is used to determine at least one display keyword based on similar items and matching items;

[0124] The second determining module 604 is used to determine the search keyword from at least one displayed keyword;

[0125] Search module 605 is used to determine the recommended item for the user from multiple alternative items sold in the target store using search keywords.

[0126] Optionally, the second determining module 604 is specifically used for:

[0127] Identify the target item from similar and matching items;

[0128] Get at least one item attribute corresponding to the target item;

[0129] The item attributes corresponding to the target item are determined as the display keywords.

[0130] Optionally, the items that can be operated include: adding items to the cart and browsing items;

[0131] Item identification module 602 is specifically used for:

[0132] Based on the similarity relationship between items, determine the first similar item corresponding to the added item;

[0133] And / or,

[0134] Based on the similarity between items, determine the second most similar item corresponding to the browsed item.

[0135] Optionally, the items that can be operated include: adding items to the cart and browsing items;

[0136] Item identification module 602 is specifically used for:

[0137] Based on the item pairing relationships, determine the first matching item corresponding to the added item;

[0138] And / or,

[0139] Based on the item pairing relationships, determine the second matching item corresponding to the item being viewed.

[0140] Optionally, the search module 605 is also used for:

[0141] If the number of recommended items is less than the quantity threshold, similar stores are identified based on the target store's business scope.

[0142] By using search keywords, supplementary items can be identified from multiple items sold in similar stores, so that the terminal can display the recommended items and supplementary items in the recommended items list.

[0143] Optionally, the search module 605 is also used for:

[0144] Determine the user's profile information and the item information for each recommended item;

[0145] Based on the portrait information and the item information of each recommended item, determine the recommendation value corresponding to each recommended item;

[0146] Based on the recommendation value of each recommended item, a ranking value is determined for each recommended item, so that the terminal can display a list of recommended items according to the ranking value of each recommended item.

[0147] This invention provides an electronic device, comprising:

[0148] One or more processors;

[0149] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the methods of any of the above embodiments.

[0150] This invention provides a computer program product, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0151] The following is for reference. Figure 7 It shows a schematic diagram of the structure of a computer system 700 suitable for implementing a terminal device of the present invention. Figure 7 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0152] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 702 or programs loaded from storage section 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the system 700. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0153] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0154] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs the functions defined above in the system of this invention.

[0155] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0157] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be located in a processor, and for example, can be described as: a function triggering module, an item determination module, a first determination module, a second determination module, and a search module. The names of these modules do not necessarily limit the module itself; for example, the function triggering module can also be described as "a module that, in response to a user triggering a system recommendation function, determines the target store the user is browsing and the items the user interacts with in the target store."

[0158] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0159] In response to a user triggering the system recommendation function, determine the target store the user is browsing and the items the user interacts with in the target store;

[0160] Identify similar and matching items for the item being manipulated;

[0161] Based on similar items and matching items, determine at least one display keyword;

[0162] Determine the search keywords from at least one of the displayed keywords;

[0163] By using search keywords, the system identifies the recommended item for the user from multiple alternative items sold in the target store.

[0164] According to the technical solution of this invention, similar items and complementary items corresponding to the items a user selects from a target store are determined. Based on the similar items and complementary items, at least one display keyword is determined, and then a search keyword is determined from the display keywords. Finally, using the search keyword, recommended items corresponding to the user are determined from multiple alternative items sold in the target store. The solution of this invention can intelligently recommend items that users want to buy, reduce the complexity of in-store shopping operations, and improve the user's shopping experience.

[0165] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for recommending items, characterized in that, include: In response to a user triggering the system recommendation function, determine the target store that the user is browsing and the items that the user is interacting with in the target store; Identify similar items and matching items corresponding to the items being manipulated; Based on the similar items and the matching items, determine at least one display keyword; From the at least one displayed keyword, determine the search keyword; Using the search keywords, the recommended item for the user is determined from multiple alternative items sold in the target store.

2. The method according to claim 1, characterized in that, The step of determining at least one display keyword based on the similar items and the matching items includes: The target item is determined from the similar items and the matching items; Obtain at least one item attribute corresponding to the target item; The item attribute corresponding to the target item is determined as the display keyword.

3. The method according to claim 1, characterized in that, The operational items include: items added to the shopping cart and items browsed; Determining similar items corresponding to the operated item includes: Based on the similarity relationship of the items, determine the first similar item corresponding to the added item; And / or, Based on the similarity relationship between the items, determine the second similar item corresponding to the browsed item.

4. The method according to claim 1, characterized in that, The operational items include: items added to the shopping cart and items browsed; Determining the matching items corresponding to the operated item includes: Based on the item pairing relationships, determine the first matching item corresponding to the added item; And / or, Based on the item pairing relationships, determine the second matching item corresponding to the browsed item.

5. The method according to claim 1, characterized in that, After determining the recommended item for the user from multiple alternative items sold by the target store using the search keywords, the process further includes: In response to the fact that the number of recommended items is less than a quantity threshold, similar stores are determined based on the business scope of the target store; Using the search keywords, supplementary items are identified from multiple items sold in similar stores, so that the terminal displays the recommended items and the supplementary items in the recommended items list.

6. The method according to claim 1, characterized in that, After determining the recommended item for the user from multiple alternative items sold by the target store using the search keywords, the process further includes: Determine the user's profile information and the item information of each of the recommended items; Based on the portrait information and the item information of each of the recommended items, determine the recommendation value corresponding to each of the recommended items; Based on the recommendation value corresponding to each of the recommended items, a sorting value corresponding to each of the recommended items is determined, so that the terminal can display a list of recommended items according to the sorting value corresponding to each of the recommended items.

7. An item recommendation device, characterized in that, include: The function triggering module is used to respond to the user triggering the system recommendation function, and to determine the target store that the user is browsing and the items that the user is operating on in the target store; The item determination module is used to determine similar items and matching items corresponding to the operated item; The first determining module is used to determine at least one display keyword based on the similar items and the matching items; The second determining module is used to determine the search keyword from the at least one displayed keyword; The search module is used to determine the recommended item for the user from multiple alternative items sold by the target store using the search keywords.

8. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images