Information recommendation method and device
By using behavioral data identification models in the e-commerce interface to identify user behavior, and combining machine learning algorithms to provide recommendation information for the same or different categories as the main object, the independence of information flow and product details interface recommendation scenarios is solved, and users are improved Stickiness and recommended accuracy.
Patent Information
- Application Number
- CN202011009804.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-09-23
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2040-09-23
AI Technical Summary
The lack of correlation between the information flow and product details interface recommendation scenarios in the existing e-commerce field, resulting in users needing to frequently switch interfaces during browsing, reducing user stickiness and experience quality.
By obtaining the user's operation information in the preset interface, using the pre-trained behavioral data identification model to determine the user's browsing behavior data, combining machine learning algorithms to identify the user's recommendation information, and displaying the same or different categories as the main object in the interface Objects, breaking through the independent limitations between information flow and product details interface.
It reduces the number of times users switch between different interfaces, improves user stickiness and browsing depth, and enhances the accuracy and user experience of recommendations.
Smart Images

Figure CN113763086B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of computer technology, and more particularly to an information recommendation method and device. Background Art
[0002] With the rapid development of mobile internet, shopping apps are emerging in large numbers, and user traffic is a key area of competition among companies. In the field of e-commerce, user stickiness is increased by the dimension of product display location. Specifically, in shopping apps, different types of product recommendations in the homepage information flow and similar product recommendations in the product details interface have gradually become standard. The homepage information flow scenario is designed to capture user interests. The more accurately the product of interest is determined, the more it can increase the user's browsing time and scroll depth. The display of similar products in the product details interface is designed to display products in the same category as the current product, providing users with more choices. The more accurately the brand or product model that users are interested in is displayed, the more convenient it is for users to compare similar products, thereby increasing the conversion rate of products. Currently, the information flow scenario and the recommendation scenario in the product details interface are completely independent and have no connection. Summary of the Invention
[0003] The embodiments of the present application provide an information recommendation method and device.
[0004] In a first aspect, an embodiment of the present application provides an information recommendation method, comprising: in response to determining that a preset interface is entered based on a first preset operation of a user, obtaining operation information within a preset time length before the user performs the first preset operation; determining the user's behavior data of browsing the preset interface based on the operation information; determining the user's recommended information based on the behavior data, and displaying the recommended information in the preset interface, wherein the objects represented by the recommended information include objects of the same category as the main object displayed on the preset interface and objects of different categories from the main object.
[0005] In some embodiments, the behavioral data includes first behavioral data characterizing that the user has a clear browsing object and second behavioral data characterizing that the user does not have a clear browsing object; the above-mentioned determination of the behavioral data of the user browsing the preset interface based on the operation information includes: in response to determining that the operation information includes the second preset operation, inputting the operation information into a pre-trained behavioral data recognition model to obtain a first array characterizing a first proportion of the first behavioral data and a second proportion of the second behavioral data.
[0006] In some embodiments, the above-mentioned determination of the user's behavior data of browsing the preset interface based on the operation information also includes: in response to determining that the operation information does not include the second preset operation, determining the entrance to the preset interface; in response to determining that the entrance is an entrance in the interface obtained based on the user's third preset operation, determining a second preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data.
[0007] In some embodiments, the above-mentioned determination of the user's behavior data of browsing the preset interface based on the operation information also includes: in response to determining that the entrance is an entrance in the preset recommendation interface, determining a third preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data.
[0008] In some embodiments, the above-mentioned determination of the user's recommended information based on the behavioral data includes: determining an object of the same category as the main object based on a first proportion of the first behavioral data and the preset display area information in the preset interface; and determining an object of a different category from the main object based on a second proportion of the second behavioral data and the preset display area information.
[0009] In some embodiments, the behavior data recognition model is trained in the following manner: obtaining a training sample set, wherein the training samples in the training sample set include: sample operation information and sample labels in units of preset time length; using a machine learning algorithm, using the sample operation information in the training samples as the input of the initial behavior data recognition model, and using the sample labels corresponding to the input sample operation information as the expected output, to train the behavior data recognition model.
[0010] In some embodiments, the above-mentioned acquisition of the training sample set includes: acquiring log information; dividing the log information into units of preset time length to obtain multiple sample operation information; for each sample operation information in the multiple sample operation information, based on the number of categories of objects included in the sample operation information, and the number of views of each category in the sample operation information, determining the sample label of the sample operation information.
[0011] In the second aspect, an embodiment of the present application provides an information recommendation device, including: a first acquisition unit, configured to, in response to determining that a preset interface is entered based on a first preset operation of a user, obtain operation information within a preset time length before the user performs the first preset operation; a first determination unit, configured to determine the user's behavior data of browsing the preset interface based on the operation information; a second determination unit, configured to determine the user's recommended information based on the behavior data, and display the recommended information in the preset interface, wherein the objects represented by the recommended information include objects of the same category as the main object displayed on the preset interface and objects of different categories from the main object.
[0012] In some embodiments, the behavioral data includes first behavioral data characterizing that the user has a clear browsing object and second behavioral data characterizing that the user does not have a clear browsing object; the first determination unit is further configured to input the operation information into a pre-trained behavioral data recognition model in response to determining that the operation information includes a second preset operation, to obtain a first array characterizing a first proportion of the first behavioral data and a second proportion of the second behavioral data.
[0013] In some embodiments, the first determination unit is further configured to determine the entrance to the preset interface in response to determining that the operation information does not include the second preset operation; and determine the second preset array representing the first proportion of the first behavior data and the second proportion of the second behavior data in response to determining that the entrance is an entrance in the interface obtained based on the user's third preset operation.
[0014] In some embodiments, the first determining unit is further configured to determine a third preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data in response to determining that the entry is an entry in a preset recommendation interface.
[0015] In some embodiments, the second determination unit is further configured to determine an object of the same category as the main object based on the first proportion of the first behavior data and the preset display area information in the preset interface; and to determine an object of a different category from the main object based on the second proportion of the second behavior data and the preset display area information.
[0016] In some embodiments, the behavior data recognition model is trained in the following manner: a second acquisition unit is configured to acquire a training sample set, wherein the training samples in the training sample set include: sample operation information and sample labels in units of preset time length; a training unit is configured to adopt a machine learning algorithm, with the sample operation information in the training sample as the input of the initial behavior data recognition model, and with the sample label corresponding to the input sample operation information as the expected output, to train the behavior data recognition model.
[0017] In some embodiments, the second acquisition unit is further configured to acquire log information; divide the log information into units of preset time length to obtain multiple sample operation information; for each sample operation information in the multiple sample operation information, based on the number of categories of objects included in the sample operation information and the number of views of each category in the sample operation information, determine the sample label of the sample operation information.
[0018] In a third aspect, an embodiment of the present application provides a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the first aspect is implemented.
[0019] In a fourth aspect, an embodiment of the present application provides an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation manner of the first aspect.
[0020] The information recommendation method and device provided in the embodiments of the present application, by responding to determining that a preset interface is entered based on a first preset operation of the user, obtains operation information within a preset time length before the user performs the preset operation; determines the user's behavior data of browsing the preset interface based on the operation information; determines the user's recommendation information based on the behavior data, and displays the recommendation information in the preset interface, wherein the objects represented by the recommendation information include objects of the same category as the main object displayed on the preset interface and objects of different categories from the main object, thereby breaking through the independent limitation between the recommendation scene and the information flow scene of the product details interface. In the preset interface, objects of the same category as the main object corresponding to the recommendation scene of the product details interface can be displayed, and objects of different categories from the main object corresponding to the information flow scene can also be displayed, thereby reducing the number of times the user switches back and forth between interfaces during use and improving user stickiness. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:
[0022] Figure 1 is an exemplary system architecture diagram in which an embodiment of the present application may be applied;
[0023] Figure 2 is a flow chart of an embodiment of the information recommendation method according to the present application;
[0024] Figure 3 is a schematic diagram of an application scenario of the information recommendation method according to this embodiment;
[0025] Figure 4 is a flowchart of another embodiment of the information recommendation method according to the present application;
[0026] Figure 5 is a structural diagram of an embodiment of an information recommendation device according to the present application;
[0027] Figure 6 It is a structural diagram of a computer system suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION
[0028] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the relevant invention are shown in the accompanying drawings.
[0029] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0030] Figure 1 An exemplary architecture 100 to which the information recommendation method and apparatus of the present application can be applied is shown.
[0031] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.
[0032] Terminal devices 101, 102, and 103 can be hardware devices or software that support network connection for data interaction and data processing. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices that support network connection, information interaction, display, processing, and other functions, including but not limited to smartphones, tablet computers, e-book readers, laptop computers, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules, for example, to provide distributed services, or they can be implemented as a single software or software module. No specific limitations are given here.
[0033] Server 105 can be a server that provides various services, such as a background processing server that recommends information in response to determining that a user has entered a preset interface based on a first preset operation on terminal devices 101, 102, or 103. The background processing server can obtain operation information within a preset time period before the user performs the preset operation; determine user behavior data for browsing the preset interface based on the operation information; determine recommended information for the user based on the behavior data, and display the recommended information on the preset interface of the terminal device. As an example, server 105 can be a cloud server.
[0034] It should be noted that the server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software or software modules (e.g., software or software modules for providing distributed services), or as a single software or software module. No specific limitations are given here.
[0035] It should also be noted that the information recommendation method provided in the embodiments of the present disclosure can be executed by a server, a terminal device, or a server and a terminal device in cooperation with each other. Accordingly, the various components (e.g., various units, subunits, modules, and submodules) of the information recommendation apparatus can be entirely located in the server, entirely located in the terminal device, or separately located in the server and the terminal device.
[0036] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the system is merely illustrative. Any number of terminal devices, networks, and servers may be provided as needed. When the electronic device on which the information recommendation method is running does not need to transmit data to other electronic devices, the system architecture may only include the electronic device (e.g., server or terminal device) on which the information recommendation method is running.
[0037] Continue to refer Figure 2 , shows a process 200 of an embodiment of an information recommendation method, comprising the following steps:
[0038] Step 201 : In response to determining that a preset interface is entered based on a first preset operation of the user, operation information within a preset time period before the user performs the first preset operation is obtained.
[0039] In this embodiment, the execution subject of the information recommendation method (for example Figure 1 The terminal device or server in the system may respond to determining that a preset interface is entered based on a first preset operation of the user, and obtain operation information within a preset time length before the user performs the preset operation remotely or locally through a wired connection or a wireless connection.
[0040] The user may be a user of a shopping application. During the use of the shopping application, the user performs a first preset operation (e.g., a click operation, a search operation) to enter a preset interface. The preset interface may be, for example, a product details interface that primarily displays a primary object. For example, for a certain model of mobile phone, the corresponding preset interface includes information such as pictures, videos, prices, and configuration parameters of the mobile phone model.
[0041] Operation information refers to any operations performed on a shopping app within a preset time period before a user performs a first preset operation, including but not limited to click operations, search operations, swipe operations, purchase operations, and communication operations with merchants. The preset time period can be set based on actual circumstances, for example, 30 minutes.
[0042] As an example, the execution entity may obtain the user's operation behavior in real time while using a shopping application and store the operation information to obtain the corresponding operation information. As another example, the execution entity may obtain the operation information from a log recording the user's operation information when using the shopping application.
[0043] Step 202: Determine the user's behavior data of browsing the preset interface based on the operation information.
[0044] In this embodiment, the execution entity may obtain the operation information according to step 201 and determine the behavior data of the user browsing the preset interface.
[0045] Behavioral data includes first behavioral data indicating that the user has a clear browsing target and second behavioral data indicating that the user does not have a clear browsing target. When the user's behavioral data is the first behavioral data, it indicates that the user entered the preset interface with a clear purpose, namely, the primary object displayed in the preset interface or an object of the same category as the object. When the user's behavioral data is the second behavioral data, it indicates that the user entered the preset interface with an unclear purpose, not targeting the primary object displayed in the preset interface or an object of the same category as the object, but rather randomly browsing the interface.
[0046] In many cases, users do not browse the preset interface purely based on the first behavior data or the second behavior data, but based on the two purposes mentioned above, except that the proportion of the first behavior data representing the user's clear purpose and the second behavior data representing the user's no clear purpose are different. In this embodiment, the proportion of the user's first behavior data and the second behavior data can be represented in the form of an array. For example, if the array representing the user's behavior data is (0.7, 0.3), it means that the proportion of the first behavior data is 0.7 and the proportion of the second behavior data is 0.3.
[0047] As an example, the above-mentioned execution entity can determine the object category corresponding to each of all operations based on all operations in the operation information; determine the user's behavior data based on the number of all object categories corresponding to the operation information and the number of views of the user on each object category. Specifically, when the number of all object categories corresponding to the operation information is smaller, the more views the user has on one of the object categories, indicating that the user's purpose is clearer, the proportion of the first behavior data is larger, and the proportion of the second behavior data is smaller; conversely, when the number of all object categories corresponding to the operation information is larger, or the number of views the user has on each object category is similar, and there is no category with a more prominent view, it indicates that the user's purpose is less clear and more random, the smaller the proportion of the first behavior data is, and the larger the proportion of the second behavior data is.
[0048] The execution entity may be provided with a correspondence table representing the correspondence between the number of object categories, the number of views of each object category and the array representing the user's behavior data, and the user's behavior data may be determined through the correspondence table.
[0049] In some optional implementations of this embodiment, the execution entity performs step 202 as follows:
[0050] First, in response to determining that the operation information includes a second preset operation, the operation information is input into a pre-trained behavior data recognition model to obtain a first array representing a first proportion of the first behavior data and a second proportion of the second behavior data.
[0051] The second preset operation is a user clicking on an object or selecting a category in the interface displayed by a shopping application. When the operation information includes a click operation, the execution entity inputs the operation information into a pre-trained behavior data recognition model to obtain a first array representing a first percentage of the first behavior data and a second percentage of the second behavior data. The behavior data recognition model represents the correspondence between the operation information and the first array and may employ a neural network model with feature extraction and information processing capabilities, such as a recurrent neural network model.
[0052] The behavior data recognition model is trained in the following manner: a training sample set is obtained, wherein the training samples in the training sample set include: sample operation information and sample labels in units of preset time length, and the sample labels represent the user's behavior data; a machine learning algorithm is used, and the sample operation information in the training samples is used as the input of the initial behavior data recognition model, and the sample labels corresponding to the input sample operation information are used as the expected output, to train the behavior data recognition model.
[0053] Among them, the training sample set is obtained in the following manner: obtaining log information; dividing the log information into units of preset time length to obtain multiple sample operation information; for each sample operation information in the multiple sample operation information, determining the sample label of the sample operation information based on the number of categories of objects included in the sample operation information and the number of views of each category in the sample operation information.
[0054] Specifically, when the number of categories of all objects corresponding to the sample operation information is smaller, the user's browsing volume for objects in one category is more, which indicates that the user's purpose is clearer, the proportion of the first behavior data is larger, and the proportion of the second behavior data is smaller; conversely, when the number of categories of all objects corresponding to the sample operation information is larger, or the user's browsing volume for each object category is similar, and there is no category with a more prominent browsing volume, it indicates that the user's purpose is less clear and more random, the proportion of the first behavior data is smaller, and the proportion of the second behavior data is larger.
[0055] Second, in response to determining that the operation information does not include the second preset operation, an entry to the preset interface is determined.
[0056] Third, in response to determining that the entry is an entry in the interface obtained based on the user's third preset operation, a second preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data is determined.
[0057] The third preset operation is a user search operation. When there is no user click operation in the operation information, and the user's entry to the preset interface is an entry in the interface obtained based on the user's search operation, the user's behavior data can be represented by a second preset array. The first proportion of the first behavior data in the second preset array is much greater than the second proportion of the second behavior data. For example, the second preset array can be (1, 0).
[0058] Fourth, in response to determining that the entry is an entry in a preset recommendation interface, a third preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data is determined.
[0059] The preset recommendation interface is an interface that recommends items to the user based on the user's interest. For example, the homepage of a shopping app generally has a "Guess You Like" display area that displays items of interest to the user. The homepage can serve as the preset recommendation interface.
[0060] When the operation information does not include the second preset operation, and the entry to the preset interface is an entry in the preset recommendation interface, the user's behavior data is represented by a third preset array. In the third preset array, the first proportion of the first behavior data and the second proportion of the second behavior data are equal. As an example, the third preset array can be (0.5, 0.5).
[0061] By distinguishing different situations as described above and determining the user's behavior data in different ways, the practicality and accuracy of this embodiment can be improved.
[0062] Step 203: Determine the user's recommended information based on the behavior data, and display the recommended information in a preset interface.
[0063] In this embodiment, the execution entity may determine the user's recommended information based on the behavioral data determined in step 202 and display the recommended information in a preset interface. The objects represented by the recommended information may include objects of the same category as the main object displayed in the preset interface and objects of different categories from the main object.
[0064] In the default interface, the main object's image, video, price, and other information are generally displayed in the majority of the display area. Beyond the main object's display area, there are other default display areas. These default display areas can display objects of the same or different categories as the main object.
[0065] In some optional implementations of this embodiment, the above-mentioned execution entity determines an object of the same category as the main object based on the first proportion of the first behavior data and the preset display area information in the preset interface; and determines an object of a different category from the main object based on the second proportion of the second behavior data and the preset display area information.
[0066] As an example, the first proportion of the user's first behavior data is 0.7, the second proportion of the second behavior data is 0.3, and the number of preset display areas is 10. Then, among the 10 preset display areas, 7 (0.7*10) preset display areas display objects of the same category as the main object, and 3 (0.3*10) preset display areas display objects of a different category from the main object.
[0067] Continue to see Figure 3 , Figure 3 This is a schematic diagram of an application scenario of the information recommendation method according to this embodiment. Figure 3In the application scenario, user 301 browses a shopping application through a terminal device 302. During the browsing process of user 301, the user clicks on the entrance of the product details interface (preset interface) with a certain model of mobile phone as the main object on the homepage. Server 303 detects the operation process of user 301 and determines that user 301 is about to enter the product details interface of the mobile phone. In response to determining that user 301 enters the product details interface, server 303 obtains the operation information within a preset time length before user 301 performs the click operation from database 304; based on the operation information, the behavior data of user 301 browsing the preset interface is determined, wherein the behavior data includes first behavior data representing that the user has a clear browsing object, which accounts for 0.7, and second behavior data representing that the user does not have a clear browsing object, which accounts for 0.3. Further, server 303 determines the recommended information of user 301 based on the determined behavior data, and displays the recommended information in the preset interface, wherein the objects represented by the recommended information include objects of the same category as the main object displayed on the preset interface (other models of mobile phones) and objects of different categories from the main object (including laptops, digital cameras).
[0068] The method provided by the above-mentioned embodiments of the present disclosure obtains operation information within a preset time length before the user performs the preset operation in response to determining that a preset interface is entered based on the user's first preset operation; determines the user's behavior data of browsing the preset interface based on the operation information; determines the user's recommendation information based on the behavior data, and displays the recommendation information in the preset interface, wherein the objects represented by the recommendation information include objects of the same category as the main object displayed on the preset interface and objects of different categories from the main object, thereby breaking through the independent limitation between the recommendation scene and the information flow scene of the product details interface. In the preset interface, objects of the same category as the main object corresponding to the recommendation scene of the product details interface can be displayed, and objects of different categories from the main object corresponding to the information flow scene can also be displayed, thereby reducing the number of times the user switches back and forth between interfaces during use and improving user stickiness.
[0069] Continue to refer Figure 4 , shows a schematic process 400 of another embodiment of the information recommendation method according to the present application, comprising the following steps:
[0070] Step 401 : In response to determining that a preset interface is entered based on a first preset operation of the user, operation information within a preset time period before the user performs the first preset operation is obtained.
[0071] Step 402 : In response to determining that the operation information includes a second preset operation, the operation information is input into a pre-trained behavior data recognition model to obtain a first array representing a first proportion of the first behavior data and a second proportion of the second behavior data.
[0072] Step 403: In response to determining that the operation information does not include the second preset operation, determining an entry to the preset interface.
[0073] Step 404 : In response to determining that the entry is an entry in the interface obtained based on the third preset operation of the user, a second preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data is determined.
[0074] Step 405 : In response to determining that the entry is an entry in a preset recommendation interface, a third preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data is determined.
[0075] Step 406: Determine objects of the same category as the main object based on the first proportion of the first behavior data and the preset display area information in the preset interface; and determine objects of different categories from the main object based on the second proportion and the preset display area information.
[0076] Step 407: Display the recommended information in the preset interface.
[0077] It can be seen from this embodiment that Figure 2 Compared with the corresponding embodiment, the process 400 of the information recommendation method in this embodiment specifically illustrates that different methods are adopted to determine the user's behavior data according to different scenarios, thereby improving the accuracy of the information recommendation in this embodiment.
[0078] Continue to refer Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an information recommendation device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0079] like Figure 5 As shown, the information recommendation device includes: a first acquisition unit 501 is configured to, in response to determining that a preset interface is entered based on a first preset operation of a user, obtain operation information within a preset time length before the user performs the first preset operation; a first determination unit 502 is configured to determine the behavior data of the user browsing the preset interface based on the operation information; a second determination unit 503 is configured to determine the user's recommended information based on the behavior data, and display the recommended information in the preset interface, wherein the objects represented by the recommended information include objects of the same category as the main object displayed on the preset interface and objects of different categories from the main object.
[0080] In some embodiments, the behavioral data includes first behavioral data characterizing that the user has a clear browsing object and second behavioral data characterizing that the user does not have a clear browsing object; the first determination unit 502 is further configured to input the operation information into a pre-trained behavioral data recognition model in response to determining that the operation information includes a second preset operation, to obtain a first array characterizing a first proportion of the first behavioral data and a second proportion of the second behavioral data.
[0081] In some embodiments, the first determination unit 502 is further configured to determine an entrance to a preset interface in response to determining that the operation information does not include a second preset operation; and to determine a second preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data in response to determining that the entrance is an entrance in an interface obtained based on the user's third preset operation.
[0082] In some embodiments, the first determining unit 502 is further configured to determine a third preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data in response to determining that the entry is an entry in a preset recommendation interface.
[0083] In some embodiments, the second determination unit 503 is further configured to determine objects of the same category as the main object based on the first proportion of the first behavior data and the preset display area information in the preset interface; and determine objects of a different category from the main object based on the second proportion and the preset display area information.
[0084] In some embodiments, the behavior data recognition model is trained in the following manner: a second acquisition unit (not shown in the figure) is configured to acquire a training sample set, wherein the training samples in the training sample set include: sample operation information and sample labels in units of preset time length; a training unit (not shown in the figure) is configured to adopt a machine learning algorithm, with the sample operation information in the training sample as the input of the initial behavior data recognition model, and with the sample label corresponding to the input sample operation information as the expected output, to train the behavior data recognition model.
[0085] In some embodiments, the second acquisition unit is further configured to acquire log information; divide the log information into units of preset time length to obtain multiple sample operation information; for each sample operation information in the multiple sample operation information, based on the number of categories of objects included in the sample operation information and the number of views of each category in the sample operation information, determine the sample label of the sample operation information.
[0086] In this embodiment, the first acquisition unit in the information recommendation device responds to determining that a preset interface is entered based on the user's first preset operation, and obtains operation information within a preset time length before the user performs the first preset operation; the first determination unit determines the user's behavior data of browsing the preset interface based on the operation information; the second determination unit determines the user's recommendation information based on the behavior data, and displays the recommendation information in the preset interface, wherein the objects represented by the recommendation information include objects of the same category as the main object displayed on the preset interface and objects of different categories from the main object, thereby breaking through the independent restrictions between the recommendation scene and the information flow scene of the product details interface. In the preset interface, objects of the same category as the main object corresponding to the recommendation scene of the product details interface can be displayed, and objects of different categories from the main object corresponding to the information flow scene can also be displayed, which reduces the number of times the user switches back and forth between interfaces during use and improves user stickiness.
[0087] Reference below Figure 6 , which shows a device suitable for implementing the embodiments of the present application (eg Figure 1 Schematic diagram of the structure of the computer system 600 of the devices 101, 102, 103, 105 shown. Figure 6 The device shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.
[0088] like Figure 6 As shown, the computer system 600 includes a processor (e.g., CPU, central processing unit) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the system 600 are also stored in the RAM 603. The processor 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0089] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, and the like; an output section 607 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or a modem. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 610 as needed, so that computer programs read therefrom can be installed into the storage section 608 as needed.
[0090] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the processor 601, the above-mentioned functions defined in the method of the present application are performed.
[0091] It should be noted that the computer-readable medium of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, or any suitable combination thereof.
[0092] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the client computer, partially on the client computer, as a stand-alone software package, partially on the client computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the client computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0093] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the devices, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.
[0094] The units involved in the embodiments described in the present application can be implemented by software or by hardware. The described units can also be set in a processor. For example, they can be described as: a processor comprising a first acquisition unit, a first determination unit, and a second determination unit. Among them, the names of these units do not constitute a limitation on the units themselves under certain circumstances. For example, the first determination unit can also be described as "a unit that determines the behavior data of the user browsing the preset interface based on the operation information."
[0095] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the device, the computer device: in response to determining that a preset interface is entered based on a first preset operation of the user, obtains operation information within a preset time length before the user performs the first preset operation; based on the operation information, determines the user's behavior data of browsing the preset interface; based on the behavior data, determines the user's recommended information, and displays the recommended information in the preset interface, wherein the objects represented by the recommended information include objects of the same category as the main object displayed on the preset interface and objects of different categories from the main object.
[0096] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.
Claims
1. An information recommendation method, comprising: In response to determining that a preset interface is entered based on a first preset operation of the user, obtaining operation information within a preset time length before the user performs the first preset operation; Determining, according to the operation information, the behavior data of the user browsing the preset interface, comprising: in response to determining that the operation information includes a second preset operation, inputting the operation information into a pre-trained behavior data recognition model to obtain a first array of a first proportion of first behavior data and a second proportion of second behavior data, wherein the behavior data includes first behavior data representing that the user has a clear browsing object and second behavior data representing that the user has no clear browsing object; Determine the recommended information of the user according to the behavior data, and display the recommended information in the preset interface, wherein the objects represented by the recommended information include objects of the same category as the main object displayed in the preset interface and objects of different categories from the main object; Wherein, determining the recommended information of the user according to the behavior data includes: According to the first proportion of the first behavior data and the preset display area information in the preset interface, determine the object of the same category as the main object; according to the second proportion of the second behavior data and the preset display area information, determine the object of a different category from the main object.
2. The method according to claim 1, wherein: The determining, according to the operation information, the behavior data of the user browsing the preset interface further includes: In response to determining that the operation information does not include the second preset operation, determining an entry to enter the preset interface; In response to determining that the entry is an entry in an interface obtained based on a third preset operation of the user, a second preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data is determined.
3. The method according to claim 2, wherein: The determining, according to the operation information, the behavior data of the user browsing the preset interface further includes: In response to determining that the entry is an entry in a preset recommendation interface, a third preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data is determined.
4. The method according to claim 1, wherein: The behavior data recognition model is trained in the following way: Acquire a training sample set, wherein the training samples in the training sample set include: sample operation information and sample labels in units of preset time length; A machine learning algorithm is adopted, sample operation information in training samples is used as input of an initial behavior data recognition model, and sample labels corresponding to the input sample operation information are used as expected outputs, so as to train and obtain the behavior data recognition model.
5. The method according to claim 4, wherein: The step of obtaining a training sample set includes: Get log information; Dividing the log information into units of the preset time length to obtain a plurality of sample operation information; For each sample operation information in the plurality of sample operation information, a sample label of the sample operation information is determined based on the number of categories of objects included in the sample operation information and the number of views of each category in the sample operation information.
6. An information recommendation device, comprising: A first acquisition unit is configured to, in response to determining that a preset interface is entered based on a first preset operation of a user, acquire operation information within a preset time length before the user performs the first preset operation; A first determining unit is configured to determine the behavior data of the user browsing the preset interface according to the operation information, including: in response to determining that the operation information includes a second preset operation, inputting the operation information into a pre-trained behavior data recognition model to obtain a first array of a first proportion of first behavior data and a second proportion of second behavior data, wherein the behavior data includes first behavior data representing that the user has a clear browsing object and second behavior data representing that the user has no clear browsing object; a second determining unit configured to determine the recommended information of the user according to the behavior data, and display the recommended information in the preset interface, wherein the objects represented by the recommended information include objects of the same category as the main object displayed in the preset interface and objects of different categories from the main object; Among them, the second determination unit is further configured to: determine an object of the same category as the main object based on a first proportion of the first behavior data and the preset display area information in the preset interface; determine an object of a different category from the main object based on a second proportion of the second behavior data and the preset display area information.
7. The device according to claim 6, wherein: The first determining unit is further configured to determine an entry to the preset interface in response to determining that the operation information does not include the second preset operation; In response to determining that the entry is an entry in an interface obtained based on a third preset operation of the user, a second preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data is determined.
8. The device according to claim 7, wherein: The first determination unit is further configured to determine a third preset array representing a first proportion of the first behavior data and a second proportion of the second behavior data in response to determining that the entry is an entry in a preset recommendation interface.
9. The device according to claim 6, wherein: The behavior data recognition model is trained in the following way: The second acquisition unit is configured to acquire a training sample set, wherein the training samples in the training sample set include: sample operation information and sample labels in units of preset time length; the training unit is configured to adopt a machine learning algorithm, use the sample operation information in the training samples as the input of the initial behavior data recognition model, and use the sample labels corresponding to the input sample operation information as the expected output, to train and obtain the behavior data recognition model.
10. The device according to claim 9, wherein: The second acquisition unit is further configured to acquire log information; divide the log information into units of the preset time length to obtain multiple sample operation information; and for each sample operation information in the multiple sample operation information, determine a sample label of the sample operation information based on the number of categories of objects included in the sample operation information and the number of views of each category in the sample operation information.
11. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
12. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Information recommendation method, apparatus, and server based on user data in an online forum
US20190197416A1
