Member commodity recommendation method, related device and system

Abstract

The invention discloses a member commodity recommendation method, a related device and a system, and relates to the technical field of commodity recommendation, the method comprises the following steps: receiving a member commodity acquisition request of a target user, the member commodity acquisition request being a request sent by a terminal when the target user accesses a purchase page on the terminal; obtaining user features of the target user and commodity attribute features of all member commodities in the candidate member commodity set; determining member commodities matched with the target user from the candidate member commodity set according to the user features of the target user and the commodity attribute features of the member commodities to obtain a recommended commodity list; setting a member commodity with the highest matching degree with the target user in the recommended commodity list as a default selected state to obtain a target recommended commodity list; and sending the target recommended commodity list to the terminal, so that the terminal displays the target recommended commodity list in a purchase page. According to the member commodity recommendation method disclosed by the invention, the member commodity matched with the user can be recommended to the user.

Description

Technical Field

[0001] The present application relates to the technical field of product recommendation, and in particular to a member product recommendation method, related devices and systems. Background Art

[0002] As the number of online video platform users continues to grow, membership subscriptions have become an important source of income for the platform. Membership subscriptions are one of the paid features of online video platforms. Users can enjoy more privileges and services by paying a certain fee to purchase membership products. However, there are many membership products, and users often find it difficult to make a choice.

[0003] To address the above issues, the current solution is to recommend pre-configured membership products of different durations (such as monthly, annual, and quarterly cards) to users. However, the pre-configured membership products often do not match the users (i.e., the recommended membership products are often not what the users need). Summary of the invention

[0004] In view of this, the present application provides a member product recommendation method, related device and system to solve the problem that the member products recommended by the current member product recommendation method do not match the user. The technical solution is as follows:

[0005] The first aspect of the present application provides a member product recommendation method, comprising:

[0006] Receiving a member commodity acquisition request from a target user, wherein the member commodity acquisition request is a request sent by the terminal when the target user accesses a member commodity purchase page on the terminal;

[0007] Acquire the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, wherein the user characteristics of the target user can characterize the consumption situation and preference of the target user, the candidate member commodity set includes multiple types of member rights, different types of member rights are different, each type of member rights includes multiple member rights with different validity periods, and each member commodity in the candidate member commodity set is a member right of one type with one validity period;

[0008] According to the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, member commodities matching the target user are determined from the candidate member commodity set to obtain a recommended commodity list consisting of member commodities matching the target user;

[0009] The member product in the recommended product list that has the highest matching degree with the target user is set to a default selected state, to obtain a target recommended product list;

[0010] The target recommended commodity list is sent to the terminal so that the terminal displays the target recommended commodity list on the member commodity purchase page.

[0011] In a possible implementation, the user characteristics of the target user include: basic personal characteristics of the target user and interaction characteristics between the target user and the member products in the candidate member product set, wherein the interaction characteristics can characterize the behavior of the target user on the member products in the candidate member product set.

[0012] In a possible implementation, determining a member product matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set includes:

[0013] Using the pre-trained product recommendation model, based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, determine the member product that matches the target user from the candidate member product set;

[0014] The product recommendation model is trained using user feature samples and product attribute feature samples as training samples, and member products that match the user to which the user feature samples belong as sample labels.

[0015] In a possible implementation, the pre-trained product recommendation model is used to determine the member product matching the target user from the candidate member product set based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, including:

[0016] Combining the user characteristics of the target user with the commodity attribute characteristics of each member commodity in the candidate member commodity set to obtain a combined characteristic;

[0017] Inputting the combined features into a pre-trained product recommendation model to obtain a recommendation score of each member product in the candidate member product set output by the product recommendation model, wherein the recommendation score of a member product can represent the degree of matching between the member product and the target user, and the recommendation score of the member product is in positive proportion to the matching degree;

[0018] According to the recommendation score of each member product in the candidate member product set, a member product matching the target user is determined from the candidate member product set.

[0019] In a possible implementation, determining a member product matching the target user from the candidate member product set according to the recommendation score of each member product in the candidate member product set includes:

[0020] Recommending member products with scores greater than a preset score threshold in the candidate member product set, and determining them as member products matching the target user;

[0021] Alternatively, the member products in the candidate member product set are sorted in descending order of recommendation score, and the first N member products are determined as member products matching the target user, where N is an integer greater than or equal to 1;

[0022] The step of setting the member product in the recommended product list that has the highest matching degree with the target user as a default selected state includes:

[0023] The member product with the highest recommended score in the recommended product list is set to be selected by default.

[0024] In a possible implementation manner, obtaining the user characteristics of the target user includes:

[0025] Acquire user data of the target user from a user database, wherein the user database includes user data of several users, and the user data of any user includes browsing behavior data, and / or click behavior data, and / or purchase behavior data of the user for member products;

[0026] Acquire user characteristics that can characterize the consumption situation and preferences of the target user based on the user data of the target user;

[0027] The member product recommendation method further includes:

[0028] Obtaining feedback data of the target user on the target recommended product list;

[0029] Add the target user's feedback data on the target recommended product list to the user data of the target user in the user database.

[0030] In a possible implementation, the user data of any user includes the user's purchase behavior data for member commodities, and the user's purchase behavior data for member commodities includes purchase order information generated by the user when purchasing member commodities, wherein the purchase order information generated by the user when purchasing member commodities is obtained by monitoring by an order monitoring module, and when the order service module generates a purchase order for the user's purchase behavior for member commodities and sends the purchase order information, the order monitoring module monitors the purchase order information;

[0031] According to the user data of the target user, a user feature capable of characterizing the consumption situation of the target user is obtained, including:

[0032] Based on the purchase order information in the user data of the target user, user characteristics that can characterize the consumption situation of the target user are determined, wherein the purchase order information includes the information of the purchased member products, the purchase time and the purchase amount, and the user characteristics that can characterize the consumption situation of the target user include some or all of the following characteristics: the total purchase amount of member products, the number of member product purchases, and the most recent purchase time of member products.

[0033] The second aspect of the present application provides a member product recommendation device, comprising: a user request receiving module, a feature acquisition module, a recommended product determination module, an optimal member product selection module and a recommended product feedback module;

[0034] The user request receiving module is used to receive a member commodity acquisition request from a target user, wherein the member commodity acquisition request is a request sent by the terminal when the target user accesses a member commodity purchase page on the terminal;

[0035] The feature acquisition module is used to acquire the user features of the target user and the commodity attribute features of each member commodity in the candidate member commodity set, wherein the user features of the target user can characterize the consumption situation and preference of the target user, the candidate member commodity set includes multiple types of member rights, different types of member rights are different, each type of member rights includes multiple types of member rights with different validity periods, and each member commodity in the candidate member commodity set is a member right of one type with one validity period;

[0036] The recommended product determination module is used to determine the member products matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, so as to obtain a recommended product list consisting of the member products matching the target user;

[0037] The optimal member product selection module is used to set the member product in the recommended product list that has the highest matching degree with the target user to a default selected state, thereby obtaining a target recommended product list;

[0038] The recommended product feedback module is used to send the target recommended product list to the terminal so that the terminal displays the target recommended product list on the member product purchase page.

[0039] A third aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0040] The memory is used to store computer programs;

[0041] The processor is used to execute the computer program so that the electronic device can implement the steps of any one of the member product recommendation methods described above.

[0042] In a fourth aspect, the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of any one of the above-mentioned member product recommendation methods.

[0043] In a fifth aspect of the present application, a computer program product includes computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the steps of any one of the above-mentioned member product recommendation methods.

[0044] A sixth aspect of the present application provides a member product recommendation system, including: a terminal and a server;

[0045] The terminal is used to send a member commodity acquisition request of the target user to the server when the target user visits the member commodity purchase page;

[0046] The server is used for, when receiving a member commodity acquisition request from the target user, acquiring the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, determining the member commodity matching the target user from the candidate member commodity set according to the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, so as to obtain a recommended commodity list consisting of the member commodities matching the target user, setting the member commodity in the recommended commodity list with the highest degree of matching with the target user as a default selected state, obtaining a target recommended commodity list, and sending the target recommended commodity list to the terminal so that the terminal displays the target recommended commodity list on the member commodity purchase page, wherein the user characteristics of the target user can characterize the consumption situation and preference of the target user, the candidate member commodity set includes multiple types of member rights, different types of member rights are different, each type of member rights includes multiple member rights with different validity periods, and each member commodity in the candidate member commodity set is a member right of one type with one validity period;

[0047] The terminal is used for displaying the target recommended commodity list on the member commodity purchase page when receiving the target recommended commodity list.

[0048] By means of the above technical solution, the commodity recommendation method provided by the present application can determine the member commodities recommended to the user according to the user characteristics of the user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, and then make the recommendation. At the same time, when recommending member commodities, the member commodity with the highest degree of matching with the user is selected by default. Since the commodity recommendation method provided by the present application takes into account the user characteristics and commodity attribute characteristics that characterize the user's consumption situation and preferences when recommending member commodities, it is able to recommend member commodities that match the user to the user. In addition, when recommending member commodities, the member commodity with the highest degree of matching with the user is selected by default, which can achieve focused and accurate recommendation of member commodities. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0050] Figure 1 A schematic diagram of the system architecture involved in this application;

[0051] Figure 2 A schematic diagram of a hardware structure of a terminal provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of a hardware structure of a server provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of a method for recommending member products according to an embodiment of the present invention;

[0054] Figure 5 A schematic diagram of displaying a recommended product list on a member product purchase page provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram of the product recommendation process provided in the embodiment of the present application;

[0056] Figure 7 This is a schematic diagram of the structure of the member product recommendation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0058] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0059] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0060] Before introducing the product recommendation method provided by this application, the system architecture involved in this application is first explained.

[0061] like Figure 1 As shown, the system architecture may include a terminal 100 and a server 200, wherein the server 200 may include one or more servers ( Figure 1 A server is included as an example for explanation).

[0062] The user can use the terminal 100 to interact with the server 200 through a network (wired network or wireless network) to receive or send messages, etc. Various client applications can be installed on the terminal 100, such as web browser applications, video playback software, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0063] Next, the product form of the terminal 100 will be described.

[0064] The terminal 100 mentioned above can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiments of the present application do not impose any restrictions on this.

[0065] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0066] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 The terminal 100 is merely an example and does not constitute a limitation on the terminal 100 , and may include more or less components than those shown in the figure, or may combine certain components, or may include different components.

[0067] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the terminal 100. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0068] The display unit 140 may be used to display information input by a user or information provided to a user, various menus of the terminal, an interactive interface, file display, and / or playback of any multimedia file.

[0069] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0070] The processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the terminal 100 and processes data, thereby controlling the terminal 100 as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on independent chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0071] The radio frequency unit 110 (optional) can be used to receive and send information or receive and send signals during a call. For example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the radio frequency unit 110 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LowNoiseAmplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (Global System of Mobile communication, GSM), General Packet Radio Service (General PacketRadio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0072] In the embodiment of the present application, the radio frequency unit 110 can send data to other devices, and can also receive data sent by other devices. It should be understood that the radio frequency unit 110 is optional, and can be replaced by other communication interfaces, such as a network port.

[0073] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0074] The terminal 100 also includes an external interface 180, which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to communicate with other devices, or to connect a charger to charge the terminal.

[0075] Although not shown, the terminal 100 may further include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which will not be described in detail herein.

[0076] Next, the product form of the server 200 will be described.

[0077] Figure 3 A structural diagram of the server 200 is provided. Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0078] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0079] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0080] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard drive (HDD), or a solid state drive (SSD).

[0081] The memory 204 may be used to store software codes related to the member product recommendation method. The processor 202 may call the software codes stored in the memory 204 or schedule other units to implement corresponding functions.

[0082] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0083] In view of the fact that the current member product recommendation method often recommends products that do not match the user (i.e., the recommended member products are often not what the user needs), the inventor of this case conducted research and, through continuous research, finally proposed a member product recommendation method with better effect, which can recommend member products that match the user to the user. Next, the member product recommendation method provided by this application is introduced through the following embodiments.

[0084] See also Figure 4 , shows a flow chart of a member product recommendation method provided in an embodiment of the present application, the member product recommendation method can be applied to a server, and the method includes:

[0085] Step S401: receiving a member product acquisition request from a target user.

[0086] The member product acquisition request is a request sent by the terminal when the target user visits the member product purchase page on the terminal.

[0087] When the target user visits the member commodity purchase page on the terminal, the terminal can obtain the user identification of the target user, and then send a member commodity acquisition request carrying the user identification of the target user.

[0088] Step S402: obtaining the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set.

[0089] When a member product acquisition request of a target user is received, user characteristics of the target user and product attribute characteristics of each member product in the candidate member product set are acquired.

[0090] Among them, the user characteristics of the target user can represent the consumption situation and preference of the target user, and the product attribute characteristics of any member product in the candidate member product set can represent the product attributes of the member product.

[0091] It should be noted that the candidate membership product set includes multiple types of membership rights (such as Basic VIP / Gold VIP / Platinum VIP / Star Diamond VIP), and different types of membership rights are different (for example, the membership rights of Basic VIP are that they can be used on mobile phones, tablets, and computers, and the same account allows the individual to use it on a maximum of 1 device, etc. The membership rights of Gold VIP are that the individual can watch popular videos first, and can be used on mobile phones, tablets, and computers, and the same account allows the individual to use it on a maximum of 5 devices, etc. Each type of membership right includes membership rights with multiple different validity periods (such as one month, one quarter, one year, etc.), and each membership product in the candidate membership product set is a membership right of one type with one validity period (such as Gold VIP monthly card).

[0092] Step S403: According to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, member products matching the target user are determined from the candidate member product set to obtain a recommended product list consisting of member products matching the target user.

[0093] There may be multiple member products that match the target user, that is, the recommended product list may include multiple member products that match the target user.

[0094] In this embodiment, the user characteristics of the target user include the basic personal characteristics of the target user and the interaction characteristics between the target user and the member commodities in the candidate member commodity set.

[0095] The basic personal characteristics of the target user may include, but are not limited to, the target user's gender, age, province or city, etc.

[0096] Among them, the interaction characteristics between the target user and the member products in the candidate member product set can characterize the behavior of the target user on the member products in the candidate member product set, such as the number of times the target user purchases the member products, the number of times the target user clicks on the member products, etc. Among them, the number of times the target user purchases the member products can be determined according to the purchase order of the member products. When the target user purchases the member products, a purchase order for the member products will be generated. The number of purchases of the member products can be obtained by counting the number of purchase orders for the member products (for example, if there are 5 purchase orders for a member product, the number of purchases of the member product is 5 times). The number of clicks of the member products by the target user can be obtained by counting the data obtained by the pingback service module on the terminal side. It should be noted that when the target user clicks on a member product, a part of data will be delivered to the pingback service module. This part of data includes the user ID of the target user and the information of the member product clicked by the target user. By counting the data obtained by the pingback service module, the number of clicks of the user on the member product can be obtained (for example, for a member product, the pingback service module receives a total of 5 data about the member product, and the number of clicks of the member product is 5 times).

[0097] Step S404: setting the member product in the recommended product list that has the highest matching degree with the target user as a default selected state to obtain a target recommended product list.

[0098] When users are faced with multiple member products, it is often difficult for them to make a purchase decision quickly. In view of this, this application sets the member product with the highest degree of match with the target user in the recommended product list as the default selected state to help users make purchase decisions more quickly. It should be noted that the member product with the highest degree of match with the target user in the recommended product list is the member product that is most suitable for the target user.

[0099] Step S405: Send the target recommended product list to the terminal so that the terminal displays the target recommended product list on the member product purchase page.

[0100] After obtaining the target recommended product list (setting the member product with the highest matching degree with the target user as the recommended product list in the default selected state), the target recommended product list is sent to the terminal. After obtaining the target recommended product list, the terminal displays the target recommended product list on the member product purchase page, such as Figure 5 As shown, in this way, the target users can get to know the membership products that are suitable for them.

[0101] The commodity recommendation method provided in the embodiment of the present application can determine the member commodities recommended to the user based on the user characteristics of the user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, and then make recommendations. At the same time, when recommending member commodities, the member commodities with the highest degree of matching with the user are selected by default. Because the commodity recommendation method provided in the embodiment of the present application takes into account the user characteristics and commodity attribute characteristics that characterize the user's consumption situation and preferences when recommending member commodities, it is possible to recommend member commodities that match the user to the user. In addition, when recommending member commodities, the member commodities with the highest degree of matching with the user are selected by default, which can achieve focused and accurate recommendations of member commodities. Furthermore, recommending member commodities that match the user to the user can improve the user experience, and selecting the member commodities with the highest degree of matching with the user by default can help users make purchase decisions more quickly, thereby improving the purchase conversion rate.

[0102] In another embodiment of the present application, the implementation process of "step S402: obtaining user characteristics of the target user and commodity attribute characteristics of each member commodity in the candidate member commodity set" in the above embodiment is introduced.

[0103] First, the implementation process of obtaining the user characteristics of the target users is introduced.

[0104] In a possible implementation, the process of obtaining the user characteristics of the target user may include:

[0105] Step a1: Obtain user data of the target user from the user database.

[0106] Among them, the user database includes user data of several users. The user data of any user can, but is not limited to, include part or all of the following data: the user's browsing behavior data for member products, the user's click behavior data for member products, the user's purchase behavior data for member products, etc.

[0107] The user data of each user (such as browsing behavior data, purchase behavior data, etc.) can be collected in advance, and the collected user data can be cleaned, deduplicated, formatted, etc. to remove abnormal values ​​and noise data to ensure data quality, and the processed user data is stored in the user database. It should be noted that when the processed user data is stored in the database, the corresponding user identification can be stored at the same time, that is, the user database stores several user identifications and the user data corresponding to the several user identifications.

[0108] When a member product acquisition request carrying the user ID of a target user is received, the user ID of the target user can be obtained, and then the user data corresponding to the user ID of the target user can be obtained from the user database to obtain the user data of the target user.

[0109] Step a2: extracting features that can characterize the consumption situation and preferences of the target user from the user data of the target user to obtain the user features of the target user.

[0110] In this embodiment, the user characteristics of the target user may include, but are not limited to, some or all of the following characteristics: the total purchase amount of member goods, the number of member goods purchased, the last purchase time of member goods, the browsing time of member goods, the number of member goods views, the number of member goods clicks, etc. Among them, the total purchase amount of member goods, the number of member goods purchased, the last purchase time of member goods, etc. can characterize the consumption of the target user, and the number of member goods purchased, the number of member goods views, the browsing time of member goods, the number of member goods clicks, etc. can characterize the user's preference. It can be understood that if a user purchases a member goods many times, it means that the user likes the member goods more, and if a user browses a member goods many times and clicks a member goods many times, it means that the user is more interested in the member goods, and if a user browses a member goods for a long time, it means that the user is more interested in the member goods. The user characteristics characterizing the consumption of the target user can be obtained by analyzing and counting the purchase behavior data of the target user, and the user characteristics characterizing the preference of the target user can be obtained by analyzing and counting the purchase behavior data, browsing behavior data, click behavior data, etc. of the target user.

[0111] The target user's purchase behavior data for member products may include purchase order information generated by the target user purchasing member products. It should be noted that the purchase order information generated by the target user purchasing member products can be obtained by monitoring the order monitoring module. When the order service module generates a purchase order for the target user's purchase behavior for member products and sends the purchase order information, the order monitoring module can monitor the purchase order information.

[0112] When obtaining user characteristics that can characterize the consumption of the target user based on the user data of the target user, the user characteristics that can characterize the consumption of the target user can be determined based on the purchase order information in the user data of the target user, such as the total purchase amount of member products, the number of member product purchases, and the most recent purchase time of member products. It should be noted that the purchase order information may include the information of the purchased member products, the purchase time, the purchase amount of the products, etc. The purchase amount of the products in all the purchase order information of the target user can be counted to obtain the total purchase amount of the member products. For each purchased member product, the total number of purchase order information of the member product can be counted to obtain the number of member product purchases of the member product. The most recent purchase time of the member product can be obtained based on the purchase time in the purchase order information of the target user.

[0113] In addition to the characteristics that characterize the target users' consumption and preferences, the user characteristics of the target users may also include other characteristics, such as the number of days the users are active, etc. The characteristics such as the number of days the users are active can be obtained by analyzing the time information in the target users' purchase behavior data, the time information in the click behavior data, and the time information in the browsing behavior data.

[0114] Next, the process of obtaining the product attribute characteristics of each member product in the candidate member product set is introduced.

[0115] The process of obtaining the product attribute characteristics of each member product in the candidate member product set may include:

[0116] Step b1: Obtain product data of each member product in the candidate member product set from the member product database.

[0117] Among them, the product data of any member product is the detailed information of the product, which may include but is not limited to part or all of the following data: price (such as original price, discounted price, etc.), validity period (for example, the validity period of a monthly card is 1 month, and the validity period of an annual card is 1 year), historical sales volume, etc.

[0118] The product data of various member products can be collected in advance, and the collected product data can be cleaned, deduplicated, formatted, etc. to remove outliers and noise data and ensure data quality. The processed product data is stored in the member product database.

[0119] Step b2: extracting product attribute features from the product data of each member product in the candidate member product set to obtain the product attribute features of each member product in the candidate member product set.

[0120] The attribute characteristics of any member product may include, but are not limited to, some or all of the following characteristics: price, validity period, historical sales volume, etc.

[0121] It should be noted that the product data of member products include attribute characteristics such as the price and validity period of the member products, as well as other data such as the listing time of the member products and the product transaction conversion rate. This embodiment extracts the attribute characteristics such as the price and validity period of the member products from the numerous data of the member products.

[0122] Through the above process, the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set can be obtained.

[0123] In another embodiment of the present application, the implementation process of "Step S403: determining the member products matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set to obtain a recommended product list consisting of the member products matching the target user" and "Step S404: setting the member product in the recommended product list that best matches the target user to the default selected state to obtain a target recommended product list" in the above embodiment is introduced.

[0124] In a possible implementation, based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, member products matching the target user are determined from the candidate member product set to obtain a recommended product list consisting of member products matching the target user. The implementation process may include: using a pre-trained product recommendation model, based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, member products matching the target user are determined from the candidate member product set to obtain a recommended product list consisting of member products matching the target user.

[0125] The product recommendation model is trained using the training data in the training data set. The training data set includes multiple training data, each of which includes a training sample and a sample label. The training sample includes a user feature sample and a product attribute feature sample (product attribute features of several member products), and the sample label is a member product that matches the user to which the user feature sample belongs. The training data of the product recommendation model in this embodiment can be constructed based on the user data in the user database and the product data in the product database. The product recommendation model in this embodiment can be a machine learning model, such as a random forest, a gradient boosting decision tree, a neural network, etc.

[0126] Specifically, using the pre-trained product recommendation model, based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, the process of determining the member product matching the target user from the candidate member product set may include:

[0127] Step c1: Combine the user characteristics of the target user with the product attribute characteristics of each member product in the candidate member product set to obtain a combined characteristic.

[0128] In a possible implementation, the user features of the target user may be combined with the product attribute features of each member product in the candidate member product set by feature splicing, that is, the user features of the target user may be spliced ​​with the product attribute features of each member product in the candidate member product set.

[0129] Step c2: input the combined features into a pre-trained product recommendation model to obtain a recommendation score for each member product in the candidate member product set output by the product recommendation model.

[0130] The combined features are input into a pre-trained product recommendation model, and the product recommendation model predicts and outputs the recommendation score of each member product in the candidate member product set based on the input combined features.

[0131] It should be noted that the recommendation score of any member product represents the degree of match between the member product and the target user. The recommendation score of any member product is directly proportional to the degree of match (the degree of match between the member product and the target user), that is, the higher the recommendation score, the higher the degree of match between the member product and the target user (the higher the recommendation score, the more suitable it is for the target user).

[0132] Step c3: Determine a member product that matches the target user from the candidate member product set according to the recommendation score of each member product in the candidate member product set.

[0133] There are several implementation methods for determining member products that match the target user from the candidate member product set based on the recommendation score of each member product in the candidate member product set. In one possible implementation method, member products with a recommendation score greater than a preset score threshold may be screened from the candidate member product set, and the screened member products with a recommendation score greater than the preset score threshold may be determined as member products that match the target user. In another possible implementation method, the member products in the candidate member product set may be sorted in descending order of the recommendation score, and the first N (N is an integer greater than or equal to 1, and the specific value of N may be set according to the actual application scenario) member products may be determined as member products that match the target user (of course, the member products in the candidate member product set may also be sorted in descending order of the recommendation score, and the last N member products may be determined as member products that match the target user).

[0134] After obtaining member products matching the target user, a recommended product list is formed by the member products matching the target user. Preferably, the member products in the recommended product list can be sorted in descending order according to the recommendation score, that is, member products with higher recommendation scores are ranked higher.

[0135] After obtaining the recommended product list, the member product in the recommended product list that has the highest matching degree with the target user may be set to a default selected state to obtain a target recommended product list.

[0136] Specifically, after obtaining the recommended product list, the member product with the highest recommended score in the recommended product list may be set to a default selected state to obtain a target recommended product list.

[0137] The member product with the highest recommendation score is the member product that best matches the target user, that is, the member product that is most suitable for the target user. Using the member product that is most suitable for the target user in the recommended product list as the default recommendation can help users make purchasing decisions more quickly, thereby improving the purchase conversion rate.

[0138] The above embodiment mentioned that the product recommendation model uses user feature samples and product attribute feature samples as training samples, and uses member products that match the user to which the user feature samples belong as sample labels for training. When training the product recommendation model, the user feature samples and product attribute feature samples can be first combined to obtain combined feature samples, and then the combined feature samples are input into the product recommendation model. The product recommendation model predicts the product recommendation score based on the input combined feature samples, and then determines the loss function based on the product recommendation score and the sample labels. Finally, the product recommendation model parameters are updated based on the loss function. The product recommendation model is iteratively trained for multiple times according to the above process until the training end condition is met. The training end condition can be, but is not limited to, model convergence, reaching a preset number of training iterations, etc.

[0139] In another embodiment of the present application, the member product recommendation method, in addition to steps S401 to S405 in the above embodiment, may also include the following process: obtaining the target user's feedback data on the target recommended product list; adding the target user's feedback data on the target recommended product list to the user data of the target user in the user database to update the user data.

[0140] Among them, the target user's feedback data on the target recommended product list can be but is not limited to one or more of the following data: the target user's browsing behavior data on the member products in the target recommended product list, the target user's click behavior data on the member products in the target recommended product list, the target user's purchase behavior data on the member products in the target recommended product list, etc.

[0141] The target user's feedback data on the target recommended product list is updated to the user database, so that the next time a member product acquisition request from the target user is received, the latest user features can be extracted from the target user's latest user data, and then the member products currently matching the target user can be determined based on the latest user features.

[0142] In addition, the member product data in the member product database can also be dynamically updated according to changes in the member products on sale.

[0143] By updating the user database and member product database according to changes in user behavior and member products on sale, it can be ensured that the user features extracted from the user data in the user database are the latest user features, and the product attribute features extracted from the product data in the product database are the latest product attribute features. Furthermore, based on the latest user features and the latest product attribute features, the member products that currently match the user can be determined (if the user data and product data change, the product recommendation results will also change accordingly), which can ensure the timeliness of product recommendations.

[0144] Optionally, in addition to updating the user data in the user database and the product data in the product database, a new training data set may be regularly or irregularly constructed based on the user data in the user database and the product data in the product database, and then the data recommendation model may be updated using the new training data set.

[0145] Based on the member product recommendation method provided in the above embodiment, Figure 6 Further explanation of the method of recommending products to members.

[0146] The server collects the user data of the users who visit the video platform and the product data of each member product on the video platform in advance, and constructs a user database from the collected user data, and constructs a product database from the product data of each member product. It should be noted that the user data in the user database and the product data in the product database can be updated regularly or irregularly.

[0147] A training data set is pre-built based on user data in the user database and product data in the product database. The training data in the training data set includes training samples (user feature samples and product attribute feature samples) and sample labels (member products that match the user to which the user feature samples belong). The product recommendation model is trained using the training data set.

[0148] When the target user visits the member product purchase page of the video platform on the terminal, the terminal obtains the user ID of the target user, and then sends a member product acquisition request carrying the user ID of the target user to the server to request to obtain recommended member products.

[0149] When the server obtains a member product acquisition request carrying the user identifier of the target user, it reads the user data of the target user from the user database according to the user identifier of the target user, and extracts features that can characterize the consumption situation and preference of the target user from the user data of the target user to obtain the user features of the target user, and reads the product data of each candidate member product from the product database, and extracts product attribute features from the product data of each candidate member product to obtain the product attribute features of each candidate member product.

[0150] After the server obtains the user characteristics of the target user and the product attribute characteristics of each candidate member product, the server combines the user characteristics of the target user with the product attribute characteristics of each candidate member product, inputs the combined characteristics into the training to obtain the product recommendation model, and obtains the recommendation score of each candidate member product output by the product recommendation model. After obtaining the recommendation score of each candidate member product, the server determines the member product that matches the target user according to the recommendation score of each candidate member product, so as to obtain a recommended product list consisting of the member products that match the target user. After obtaining the recommended product list, the member product in the recommended product list that has the highest degree of match with the target user (the highest recommendation score) is selected by default, and the recommended product list set to the default selected state is sent to the terminal.

[0151] After obtaining the recommended commodity list set to be selected by default, the terminal displays the member commodity purchase page, and displays the recommended commodity list set to be selected by default on the member commodity purchase page.

[0152] After the target user sees the recommended product list displayed on the product purchase page, the user will usually operate the member products in the recommended product list (such as purchasing, browsing, etc.). If the user purchases the recommended member product, the payment will be redirected to the third-party payment platform. The terminal obtains the user's operation behavior data, that is, the target user's feedback data on the recommended product list, and sends the target user's feedback data on the recommended product list to the server.

[0153] After the server obtains the target user's feedback data on the recommended product list, the server may add the target user's feedback data on the recommended product list to the user database.

[0154] Since the user data in the user database will be continuously updated, the product data in the product database may also be continuously updated. The server can regularly or irregularly build a new training data set based on the latest user data in the user database and the latest product data in the product database, and then use the new training data set to update the product recommendation model to ensure the timeliness of the product recommendation.

[0155] The member product recommendation method provided in the embodiment of the present application is introduced above, and the device corresponding to the member product recommendation method will be introduced below.

[0156] See also Figure 7 , Figure 7 This is a structural diagram of a member product recommendation device provided in an embodiment of the present application. The member product recommendation device may include: a user request receiving module 701, a feature acquisition module 702, a recommended product determination module 703, an optimal member product selection module 704 and a recommended product feedback module 707.

[0157] The user request receiving module 701 is used to receive a member commodity acquisition request from a target user.

[0158] The member product acquisition request is a request sent by the terminal when the target user visits the member product purchase page on the terminal.

[0159] The feature acquisition module 702 is used to acquire the user features of the target user and the product attribute features of each member product in the candidate member product set.

[0160] Among them, the user characteristics of the target user can characterize the consumption situation and preferences of the target user. The candidate member product set includes multiple types of member rights and interests. Different types of member rights and interests are different. Each type of member rights and interests includes multiple member rights and interests with different validity periods. Each member product in the candidate member product set is a member right and interest of one type with one validity period.

[0161] The recommended product determination module 703 is used to determine the member products matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, so as to obtain a recommended product list consisting of the member products matching the target user.

[0162] The optimal member product selection module 704 is used to set the member product that best matches the target user in the recommended product list to a default selected state, thereby obtaining a target recommended product list.

[0163] The recommended product feedback module 707 is used to feed back the target recommended product list to the terminal so that the terminal can display the target recommended product list on the member product purchase page.

[0164] In a possible implementation, the user characteristics of the target user include: basic personal characteristics of the target user and interaction characteristics between the target user and member products in the candidate member product set, wherein the interaction characteristics can characterize the behavior of the target user on the member products in the candidate member product set.

[0165] In a possible implementation, the recommended product determination module 703 is specifically used to determine the member product matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set:

[0166] Using the pre-trained product recommendation model, based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, the member products matching the target user are determined from the candidate member product set; wherein the product recommendation model is trained using user feature samples and product attribute feature samples as training samples, and using member products matching the user to which the user feature samples belong as sample labels.

[0167] In a possible implementation, the recommended product determination module 703 uses the pre-trained product recommendation model to determine the member products matching the target user from the candidate member product set based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set. Specifically, it is used to:

[0168] Combining the user characteristics of the target user with the product attribute characteristics of each member product in the candidate member product set to obtain a combined characteristic;

[0169] The combined features are input into the pre-trained product recommendation model to obtain the recommendation score of each member product in the candidate member product set output by the product recommendation model, wherein the recommendation score of a member product can represent the matching degree between the member product and the target user, and the recommendation score of the member product is in positive proportion to the matching degree;

[0170] According to the recommendation score of each member product in the candidate member product set, a member product matching the target user is determined from the candidate member product set.

[0171] In a possible implementation, when determining the member product matching the target user from the candidate member product set according to the recommendation score of each member product in the candidate member product set, the recommended product determination module 703 is specifically configured to:

[0172] Recommend member products with scores greater than a preset score threshold from the candidate member products collection and determine them as member products that match the target user;

[0173] Alternatively, the member products in the candidate member product set are sorted in descending order of recommendation score, and the first N member products are determined as member products matching the target user, where N is an integer greater than or equal to 1;

[0174] Set the member products in the recommended product list that have the highest degree of match with the target user to be selected by default, including:

[0175] Set the member product with the highest recommendation score in the recommended product list to be selected by default.

[0176] In a possible implementation, when acquiring the user features of the target user, the feature acquisition module 702 is specifically configured to:

[0177] Acquire user data of the target user from a user database, wherein the user database includes user data of several users, and the user data of any user includes browsing behavior data, and / or click behavior data, and / or purchase behavior data of the user for member products;

[0178] Based on the user data of the target user, obtain user characteristics that can characterize the target user's consumption behavior and preferences.

[0179] In a possible implementation, the member product recommendation device may further include: a user feedback data module and a user data update module.

[0180] User feedback data module, used to obtain target user's feedback data on the target recommended product list;

[0181] The user data updating module is used to add the target user's feedback data on the target recommended product list to the user data of the target user in the user database.

[0182] In one possible implementation, the user data of any user includes the user's purchasing behavior data for member products, and the user's purchasing behavior data for member products includes the purchase order information generated by the user's purchase of member products, wherein the purchase order information generated by the user's purchase of member products is obtained through monitoring by an order monitoring module, and when the order service module generates a purchase order for the user's purchasing behavior for member products and sends the purchase order information, the order monitoring module monitors the purchase order information.

[0183] When the feature acquisition module 702 acquires the user features that can characterize the consumption situation of the target user according to the user data of the target user, it is specifically used to:

[0184] Based on the purchase order information in the user data of the target user, determine the user characteristics that can characterize the consumption of the target user, where the purchase order information includes the information of the purchased member products, the purchase time and the purchase amount, etc. The user characteristics that can characterize the consumption of the target user include some or all of the following characteristics: the total purchase amount of member products, the number of member product purchases, and the most recent purchase time of member products.

[0185] The commodity recommendation device provided in the embodiment of the present application can determine the member commodities recommended to the user based on the user characteristics of the user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, and then make recommendations. At the same time, when recommending member commodities, the member commodities with the highest degree of matching with the user are selected by default. Since the commodity recommendation device provided in the embodiment of the present application takes into account the user characteristics and commodity attribute characteristics that characterize the user's consumption situation and preferences when recommending member commodities, it is possible to recommend member commodities that match the user to the user. In addition, when recommending member commodities, the member commodities with the highest degree of matching with the user are selected by default, which can achieve focused and accurate recommendations of member commodities. Furthermore, recommending member commodities that match the user to the user can improve the user experience, and selecting the member commodities with the highest degree of matching with the user by default can help users make purchase decisions faster, thereby improving the purchase conversion rate.

[0186] An embodiment of the present application also provides an electronic device, which may include: at least one processor, at least one communication interface, at least one memory and at least one communication bus.

[0187] In the embodiment of the present application, the number of the processor, the communication interface, the memory, and the communication bus is at least one, and the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0188] The processor may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application;

[0189] The memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;

[0190] The memory stores a program, and the processor can call the program stored in the memory, and the program is used to implement the steps of the member product recommendation method provided in the above embodiment.

[0191] An embodiment of the present application also provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of the member product recommendation method provided in the above embodiment.

[0192] The embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the steps of the member product recommendation method provided in the above embodiment.

[0193] The embodiment of the present application also provides a member commodity recommendation system, which may include: a terminal and a server.

[0194] The terminal is used to send a member commodity acquisition request of the target user to the server when the target user visits the member commodity purchase page.

[0195] The server is used to obtain the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set when receiving the member product acquisition request of the target user, determine the member products matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, so as to obtain a recommended product list consisting of member products matching the target user, set the member products in the recommended product list that have the highest degree of matching with the target user as the default selected state, obtain the target recommended product list, and feed back the target recommended product list to the terminal so that the terminal can display the target recommended product list in the member product purchase page. Among them, the user characteristics of the target user can characterize the consumption situation and preferences of the target user, the candidate member product set includes multiple types of member rights, different types of member rights are different, each type of member rights includes multiple member rights with different effective durations, and each member product in the candidate member product set is a member right of one type with one effective duration.

[0196] The terminal is used to display the target recommended commodity list on the member commodity purchase page when receiving the target recommended commodity list.

[0197] In a possible implementation, the user characteristics of the target user include: basic personal characteristics of the target user and interaction characteristics between the target user and member products in the candidate member product set, wherein the interaction characteristics can characterize the behavior of the target user on the member products in the candidate member product set.

[0198] In a possible implementation, when the server determines the member product matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, it is specifically configured to:

[0199] Using the pre-trained product recommendation model, based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, the member products matching the target user are determined from the candidate member product set; wherein the product recommendation model is trained using user feature samples and product attribute feature samples as training samples, and using member products matching the user to which the user feature samples belong as sample labels.

[0200] In a possible implementation, when the server uses the pre-trained product recommendation model to determine the member product matching the target user from the candidate member product set based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, it is specifically used to:

[0201] The user characteristics of the target user are combined with the product attribute characteristics of each member product in the candidate member product set to obtain the combined characteristics; the combined characteristics are input into the pre-trained product recommendation model to obtain the recommendation score of each member product in the candidate member product set output by the product recommendation model; according to the recommendation score of each member product in the candidate member product set, the member product matching the target user is determined from the candidate member product set. Among them, the recommendation score of a member product can represent the matching degree between the member product and the target user, and the recommendation score of the member product is in positive proportion to the matching degree.

[0202] In a possible implementation, when the server determines the member product matching the target user from the candidate member product set according to the recommendation score of each member product in the candidate member product set, it is specifically configured to:

[0203] The member products in the candidate member product set whose recommendation scores are greater than a preset score threshold are determined as the member products matching the target user; or, the member products in the candidate member product set are sorted in descending order of the recommendation scores, and the first N member products are determined as the member products matching the target user, where N is an integer greater than or equal to 1.

[0204] When the server sets the member product in the recommended product list that has the highest matching degree with the target user as the default selected state, it is specifically used to:

[0205] Set the member product with the highest recommendation score in the recommended product list to be selected by default.

[0206] In a possible implementation, when the server obtains the user characteristics of the target user, it is specifically used to:

[0207] Obtain user data of the target user from a user database, wherein the user database includes user data of several users, and the user data of any user includes browsing behavior data, and / or click behavior data, and / or purchase behavior data of the user for member products; based on the user data of the target user, obtain user characteristics that can characterize the consumption situation and preferences of the target user.

[0208] In a possible implementation, the server is further configured to obtain feedback data of the target user on the target recommended product list; and add the feedback data of the target user on the target recommended product list to the user data of the target user in the user database.

[0209] In one possible implementation, the user data of any user includes the user's purchasing behavior data for member products, and the user's purchasing behavior data for member products includes the purchase order information generated by the user's purchase of member products, wherein the purchase order information generated by the user's purchase of member products is obtained through monitoring by an order monitoring module, and when the order service module generates a purchase order for the user's purchasing behavior for member products and sends the purchase order information, the order monitoring module monitors the purchase order information.

[0210] When the server obtains the user characteristics that can characterize the consumption situation of the target user according to the user data of the target user, it is specifically used to:

[0211] Based on the purchase order information in the user data of the target user, determine the user characteristics that can characterize the consumption of the target user, where the purchase order information includes the information of the purchased member products, the purchase time and the purchase amount, etc. The user characteristics that can characterize the consumption of the target user include some or all of the following characteristics: the total purchase amount of member products, the number of member product purchases, and the most recent purchase time of member products.

[0212] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0213] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0214] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0215] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A member product recommendation method, characterized in that: include: Receiving a member commodity acquisition request from a target user, wherein the member commodity acquisition request is a request sent by the terminal when the target user accesses a member commodity purchase page on the terminal; Acquire the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, wherein the user characteristics of the target user can characterize the consumption situation and preference of the target user, the candidate member commodity set includes multiple types of member rights, different types of member rights are different, each type of member rights includes multiple member rights with different validity periods, and each member commodity in the candidate member commodity set is a member right of one type with one validity period; According to the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, member commodities matching the target user are determined from the candidate member commodity set to obtain a recommended commodity list consisting of member commodities matching the target user; The member product in the recommended product list that has the highest matching degree with the target user is set to a default selected state, to obtain a target recommended product list; The target recommended commodity list is sent to the terminal so that the terminal displays the target recommended commodity list on the member commodity purchase page.

2. The member product recommendation method according to claim 1, characterized in that: The user characteristics of the target user include: the basic personal characteristics of the target user and the interaction characteristics between the target user and the member products in the candidate member product set, wherein the interaction characteristics can characterize the behavior of the target user on the member products in the candidate member product set.

3. The member product recommendation method according to claim 1, characterized in that: The determining, from the candidate member product set, a member product matching the target user according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set comprises: Using the pre-trained product recommendation model, based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, determine the member product that matches the target user from the candidate member product set; The product recommendation model is trained using user feature samples and product attribute feature samples as training samples, and member products that match the user to which the user feature samples belong as sample labels.

4. The member product recommendation method according to claim 3, characterized in that: The method of using the pre-trained product recommendation model to determine the member products matching the target user from the candidate member product set based on the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set includes: Combining the user characteristics of the target user with the commodity attribute characteristics of each member commodity in the candidate member commodity set to obtain a combined characteristic; Inputting the combined features into a pre-trained product recommendation model to obtain a recommendation score of each member product in the candidate member product set output by the product recommendation model, wherein the recommendation score of a member product can represent the degree of matching between the member product and the target user, and the recommendation score of the member product is in positive proportion to the matching degree; According to the recommendation score of each member product in the candidate member product set, a member product matching the target user is determined from the candidate member product set.

5. The member product recommendation method according to claim 4, characterized in that: The determining, from the candidate member product set, a member product matching the target user according to the recommendation score of each member product in the candidate member product set comprises: Recommending member products with scores greater than a preset score threshold in the candidate member product set, and determining them as member products matching the target user; Alternatively, the member products in the candidate member product set are sorted in descending order of recommendation score, and the first N member products are determined as member products matching the target user, where N is an integer greater than or equal to 1; The step of setting the member product in the recommended product list that has the highest matching degree with the target user as a default selected state includes: The member product with the highest recommended score in the recommended product list is set to be selected by default.

6. The member product recommendation method according to claim 1, characterized in that: Obtaining user characteristics of the target user includes: Acquire user data of the target user from a user database, wherein the user database includes user data of several users, and the user data of any user includes browsing behavior data, and / or click behavior data, and / or purchase behavior data of the user for member products; Acquire user characteristics that can characterize the consumption situation and preferences of the target user based on the user data of the target user; The member product recommendation method further includes: Obtaining feedback data of the target user on the target recommended product list; Add the target user's feedback data on the target recommended product list to the user data of the target user in the user database.

7. The member product recommendation method according to claim 6, characterized in that: The user data of any user includes the user's purchase behavior data for member products, and the user's purchase behavior data for member products includes the purchase order information generated by the user when purchasing member products, wherein the purchase order information generated by the user when purchasing member products is obtained through monitoring by the order monitoring module. When the order service module generates a purchase order for the user's purchase behavior for member products and sends the purchase order information, the order monitoring module monitors the purchase order information; According to the user data of the target user, a user feature capable of characterizing the consumption situation of the target user is obtained, including: Based on the purchase order information in the user data of the target user, user characteristics that can characterize the consumption situation of the target user are determined, wherein the purchase order information includes the information of the purchased member products, the purchase time and the purchase amount, and the user characteristics that can characterize the consumption situation of the target user include some or all of the following characteristics: the total purchase amount of member products, the number of member product purchases, and the most recent purchase time of member products.

8. A member product recommendation device, characterized in that: include: User request receiving module, feature acquisition module, recommended product determination module, optimal member product selection module and recommended product feedback module; The user request receiving module is used to receive a member commodity acquisition request from a target user, wherein the member commodity acquisition request is a request sent by the terminal when the target user accesses a member commodity purchase page on the terminal; The feature acquisition module is used to acquire the user features of the target user and the commodity attribute features of each member commodity in the candidate member commodity set, wherein the user features of the target user can characterize the consumption situation and preference of the target user, the candidate member commodity set includes multiple types of member rights, different types of member rights are different, each type of member rights includes multiple types of member rights with different validity periods, and each member commodity in the candidate member commodity set is a member right of one type with one validity period; The recommended product determination module is used to determine the member products matching the target user from the candidate member product set according to the user characteristics of the target user and the product attribute characteristics of each member product in the candidate member product set, so as to obtain a recommended product list consisting of the member products matching the target user; The optimal member product selection module is used to set the member product in the recommended product list that has the highest matching degree with the target user to a default selected state, thereby obtaining a target recommended product list; The recommended product feedback module is used to send the target recommended product list to the terminal so that the terminal displays the target recommended product list on the member product purchase page.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the steps of the member product recommendation method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the steps of the member product recommendation method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the steps of the member product recommendation method as described in any one of claims 1 to 7.

12. A member product recommendation system, characterized in that: include: Terminals and servers; The terminal is used to send a member commodity acquisition request of the target user to the server when the target user visits the member commodity purchase page; The server is used for, when receiving a member commodity acquisition request from the target user, acquiring the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, determining the member commodity matching the target user from the candidate member commodity set according to the user characteristics of the target user and the commodity attribute characteristics of each member commodity in the candidate member commodity set, so as to obtain a recommended commodity list consisting of the member commodities matching the target user, setting the member commodity in the recommended commodity list with the highest degree of matching with the target user as a default selected state, obtaining a target recommended commodity list, and sending the target recommended commodity list to the terminal so that the terminal displays the target recommended commodity list on the member commodity purchase page, wherein the user characteristics of the target user can characterize the consumption situation and preference of the target user, the candidate member commodity set includes multiple types of member rights, different types of member rights are different, each type of member rights includes multiple member rights with different validity periods, and each member commodity in the candidate member commodity set is a member right of one type with one validity period; The terminal is used for displaying the target recommended commodity list on the member commodity purchase page when receiving the target recommended commodity list.

Images