CN115827978A - Information recommendation method, device, equipment and computer readable storage medium - Google Patents

Information recommendation method, device, equipment and computer readable storage medium Download PDF

Info

Publication number
CN115827978A
CN115827978A CN202211599477.7A CN202211599477A CN115827978A CN 115827978 A CN115827978 A CN 115827978A CN 202211599477 A CN202211599477 A CN 202211599477A CN 115827978 A CN115827978 A CN 115827978A
Authority
CN
China
Prior art keywords
materials
recommended
subset
target user
behavior
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211599477.7A
Other languages
Chinese (zh)
Inventor
刘广东
张鹏涛
韩梦凡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Weimeng Chuangke Network Technology China Co Ltd
Original Assignee
Weimeng Chuangke Network Technology China Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Weimeng Chuangke Network Technology China Co Ltd filed Critical Weimeng Chuangke Network Technology China Co Ltd
Priority to CN202211599477.7A priority Critical patent/CN115827978A/en
Publication of CN115827978A publication Critical patent/CN115827978A/en
Pending legal-status Critical Current

Links

Images

Abstract

The application provides an information recommendation method, device, equipment and a computer readable storage medium; the method comprises the following steps: obtaining search behavior data of a target user; determining a material set corresponding to the search behavior according to the search behavior data; determining the type of the operation behavior of a target user on the material corresponding to the search behavior in the material set; determining a material subset to be recommended corresponding to each type of operation behavior according to recommendation strategies corresponding to different types of operation behaviors; obtaining a set of materials to be recommended according to the priority of the subset of the materials to be recommended; and recommending the materials to the target user according to the set of the materials to be recommended. By the method and the device, the information recommended for the target user is more in line with the interest points of the target user, and the accuracy of information recommendation can be improved.

Description

Information recommendation method, device, equipment and computer readable storage medium
Technical Field
The present application relates to computer processing technologies, and in particular, to an information recommendation method, apparatus, device, and computer-readable storage medium.
Background
The recommendation system achieves the purpose of user growth by recommending materials which are interesting to users to the users, and is divided into two stages of recall and sequencing.
Disclosure of Invention
The application provides an information recommendation method, an information recommendation device and a computer-readable storage medium, which can analyze interest points of a user based on active behaviors of the user and improve the accuracy of information recommendation.
The technical scheme of the application is realized as follows:
the application provides an information recommendation method, which comprises the following steps: obtaining search behavior data of a target user, wherein the search behavior data is used for indicating the search behavior of the target user; determining a material set corresponding to the search behavior according to the search behavior data; determining the type of the operation behavior of a target user on the material corresponding to the search behavior in the material set; determining a material subset to be recommended corresponding to each type of operation behavior according to recommendation strategies corresponding to different types of operation behaviors; obtaining a set of materials to be recommended according to the priority of the subset of the materials to be recommended; and recommending the materials to the target user according to the set of the materials to be recommended.
In some possible embodiments, the operation behavior of the target user on the material corresponding to the search behavior is used to indicate the interest degree of the target user on the material corresponding to the search behavior; determining a material subset to be recommended corresponding to each type of operation behavior according to recommendation strategies corresponding to different types of operation behaviors, wherein the recommendation strategies comprise: determining a first subset of materials to be recommended according to content data of a search behavior based on a first operation behavior of a target user for materials corresponding to the search behavior; determining a second to-be-recommended material subset according to the content data of the material corresponding to the search behavior based on a second operation behavior of the target user for the material corresponding to the search behavior; the materials corresponding to the search behavior are obtained from a preset material library based on the content data of the search behavior; the interest degree of the target user indicated by the second operation behavior on the material corresponding to the search behavior is higher than that of the first operation behavior.
In some possible embodiments, determining the first subset of materials to be recommended according to the content data of the search action based on the first operation action of the target user on the materials corresponding to the search action includes: acquiring a first set of the first N hot content data with the highest search volume in the content data of the search behavior of a preset user, wherein N is an integer larger than 0; acquiring a second set of content data of the search behavior of the target user; taking intersection of the first set and the second set to obtain popular content data of the search behavior of the target user; calculating a first similarity between the hot content data and materials in a preset material library based on a similarity algorithm model according to the hot content data; and determining a first to-be-recommended material subset from a preset material library based on the first similarity.
In some possible embodiments, determining, based on a second operation behavior of the target user for the material corresponding to the search behavior, a second subset of the material to be recommended according to content data of the material corresponding to the search behavior includes: acquiring content data of materials corresponding to the search behavior; calculating a second similarity between the content data of the material corresponding to the search behavior and the material in the preset material library based on a similarity algorithm model according to the content data of the material corresponding to the search behavior; and determining a second to-be-recommended material subset from the preset material library based on the second similarity.
In some possible embodiments, obtaining a set of materials to be recommended according to the priority of the subset of materials to be recommended includes: determining a second subset of materials to be recommended as a set of materials to be recommended; and the second subset of the materials to be recommended is the subset of the materials to be recommended with the highest priority.
In some possible embodiments, obtaining a set of materials to be recommended according to the priority of the subset of materials to be recommended includes: determining whether the quantity of the materials in the second subset of the materials to be recommended is greater than or equal to a first threshold value; when the quantity of the materials in the second subset of the materials to be recommended is larger than or equal to a first threshold value, selecting the materials with the quantity of meeting the first threshold value from the second subset of the materials to be recommended as a set of the materials to be recommended; when the quantity of the materials in the second subset of the materials to be recommended is smaller than a first threshold value, combining the first subset of the materials to be recommended to the second subset of the materials to be recommended, and selecting the materials with the quantity meeting the first threshold value from the combined second subset of the materials to be recommended as a set of the materials to be recommended; the priority of the first subset of the materials to be recommended is the next level of the priority of the second subset of the materials to be recommended.
In some possible embodiments, before determining the subset of the material to be recommended corresponding to each type of the operation behavior according to the recommendation policy corresponding to the operation behaviors of different types, the method further includes: and performing data cleaning on the content data of the search behavior and/or the content data of the material corresponding to the search behavior to filter invalid contents in the content data of the search behavior and/or the content data of the material corresponding to the search behavior.
In a second aspect, the present application provides an information recommendation apparatus, including: the device comprises a first obtaining module, a second obtaining module and a searching module, wherein the first obtaining module is used for obtaining searching behavior data of a target user, and the searching behavior data is used for indicating searching behaviors of the target user; the first determining module is used for determining a material set corresponding to the searching behavior according to the searching behavior data; the second determining module is used for determining the type of the operation behavior of the target user on the material corresponding to the search behavior in the material set; the third determining module is used for determining a material subset to be recommended corresponding to each type of operation behavior according to the recommendation strategies corresponding to the different types of operation behaviors; the processing module is used for obtaining a set of materials to be recommended according to the priority of the subset of the materials to be recommended; and the recommending module is used for recommending the materials to the target user according to the material set to be recommended.
In some possible embodiments, the operation behavior of the target user on the material corresponding to the search behavior is used to indicate the interest degree of the target user on the material corresponding to the search behavior; the search sub-behavior is used for indicating the interest degree of the target user in the material corresponding to the search behavior; the third determining module is further used for determining a second subset of the materials to be recommended according to the content data of the materials corresponding to the searching behaviors based on a second operation behavior of the target user for the materials corresponding to the searching behaviors; the materials corresponding to the search behavior are obtained from a preset material library based on the content data of the search behavior; the interest degree of the target user indicated by the second operation behavior on the material corresponding to the search behavior is higher than that of the first operation behavior.
In some possible embodiments, the third determining module is further configured to obtain a first set of top N top-ranked content data with the highest search volume in content data of search behaviors of a preset user; n is an integer greater than 0; acquiring a second set of content data of the search behavior of the target user; taking intersection of the first set and the second set to obtain hot content data of the search behavior of the target user; calculating a first similarity between the popular content data of the search behavior of the target user and the materials in a preset material library based on a similarity algorithm model according to the popular content data; and determining a first to-be-recommended material subset from a preset material library based on the first similarity.
In some possible embodiments, the third determining module is further configured to obtain content data of a material corresponding to the search behavior; calculating a second similarity between the content data of the material corresponding to the search behavior and the material in the preset material library based on a similarity algorithm model according to the content data of the material corresponding to the search behavior; and determining a second to-be-recommended material subset from the preset material library based on the second similarity.
In some possible embodiments, the processing module is further configured to determine the second subset of materials to be recommended as the set of materials to be recommended; and the second subset of the materials to be recommended is the subset of the materials to be recommended with the highest priority.
In some possible embodiments, the processing module is further configured to determine whether the amount of the material in the second subset of materials to be recommended is greater than or equal to a first threshold; when the quantity of the materials in the second subset of the materials to be recommended is greater than or equal to a first threshold value, selecting the materials of which the quantity of the materials meets the first threshold value from the second subset of the materials to be recommended as a set of the materials to be recommended; when the quantity of the materials in the second subset of the materials to be recommended is smaller than a first threshold value, combining the first subset of the materials to be recommended to the second subset of the materials to be recommended, and selecting the materials with the quantity meeting the first threshold value from the combined second subset of the materials to be recommended as a set of the materials to be recommended; the priority of the first subset of the materials to be recommended is the next level of the priority of the second subset of the materials to be recommended.
In some possible embodiments, the apparatus further comprises: and the data cleaning module is used for performing data cleaning on the content data of the search behavior and/or the content data of the material corresponding to the search behavior so as to filter invalid contents in the content data of the search behavior and/or the content data of the material corresponding to the search behavior.
In a third aspect, the present application provides an information recommendation apparatus, including:
a memory for storing executable instructions;
a processor configured to implement the method provided by the first aspect of the present application when executing the executable instructions stored in the memory.
In a fourth aspect, the present application provides a computer-readable storage medium storing executable instructions for causing a processor to perform the method provided by the first aspect of the present application when the processor executes the executable instructions.
Compared with the prior art, the technical scheme provided by the application has the beneficial effects that:
according to the method and the device, the subsets of the materials to be recommended corresponding to different types are obtained according to different types of operation behaviors of the target user on the materials corresponding to the search behaviors, the sets of the materials to be recommended are obtained according to the priority of the subsets of the materials to be recommended and are recommended to the target user, therefore, the recommended materials determined through the active search behaviors of the target user are more in line with the interest points of the target user, meanwhile, the different interest degrees of the target user can be reflected according to different operation behaviors through layered processing based on the different types of operation behaviors, the probability that the recommended information is high-quality information in line with the interest points of the target user is higher, and the accuracy of information recommendation is improved.
Drawings
Fig. 1 is a flowchart illustrating an information recommendation method in the related art;
FIG. 2 is a schematic diagram of an architecture of an information recommendation system provided in an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a server provided in an embodiment of the present application;
fig. 4 is a schematic flowchart of an information recommendation method provided in an embodiment of the present application;
FIG. 5 is an alternative flow chart of an information recommendation method provided in an embodiment of the present application;
FIG. 6 is an alternative flow chart of an information recommendation method provided in an embodiment of the present application;
FIG. 7 is an alternative flow chart of an information recommendation method provided in an embodiment of the present application;
FIG. 8 is a schematic flowchart of an application of the information recommendation method provided in the embodiment of the present application to social application software;
fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
In the following description, references to the terms "first/second/third" are only to distinguish similar objects and do not denote a particular order, but rather the terms "first/second/third" may, where permissible, be interchanged with a particular order or sequence so that embodiments of the application described herein may be practiced in other than the order shown or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.
With the rapid development of science and technology, particularly the wide popularization of mobile communication networks and mobile terminals, various material contents exist on the networks, users can also produce and manufacture the material contents at any time and any place, different manufacturers provide platforms, on one hand, part of the material contents produced by the users are collected, on the other hand, high-quality material contents are screened in different modes, and corresponding material contents are pushed to the users based on different user interest types, so that the probability that the users click and view the pushed material content data is improved.
On each network platform, a large amount of material content is generally stored to form a material content database, and the material content data may include multimedia data in various formats, such as video data, audio data, image data, text data, and the like, which may be in different forms in different service scenes, such as live programs, short videos, songs, comics, audios, novels, news, articles, gourmet platforms, and the like. The platform side can actively release the multimedia data on the platform, for example, the platform side can purchase various multimedia data from the copyright side to be displayed on the platform. Alternatively, registered users on the platform can also produce various types of multimedia data through the electronic equipment and upload the produced multimedia data to the platform, and other users can also search and browse the multimedia data through the electronic equipment. The electronic device includes, but is not limited to, various user intelligent terminals such as a notebook computer, a tablet computer, a desktop computer, and a mobile terminal.
For different service scenes, there can be multimedia data in various different data forms, for example, in a live service scene, a user can use a camera to collect video data, and perform operations such as beautifying and connecting with a microphone on the video data, so as to generate a live program; in a short video service scene, a user can use a camera to collect video data, perform operations such as beautifying, clipping, adding special effects and the like on the video data so as to generate a short video, and in an information sharing communication service scene, the user can upload edited characters, images, videos and the like to generate blog information and the like. The multimedia data can be published on the corresponding platform, and other users can use intelligent devices such as terminals to obtain the data on the corresponding platform, or can share the data content and the like.
Recommendation systems are available for more accurately screening out contents that may be of interest to a user from massive data and then recommending the contents to the user. The recommendation system can achieve the purposes of pulling new and pulling life through materials which are interested by the user, and further achieves the growth of the user. Essentially, materials with high click rate are recommended to users, and the method is widely applied to the fields of e-commerce, search, advertisement and the like and is used for recommending personalized materials for the users. For example, in an advertisement scene, the personalized recommendation system can push materials with advertisements to a user through characteristics, preferences and the like of the user, if the user finally generates click conversion behavior, the user can consider an advertisement pushing result, and otherwise, the pushing fails.
The recommendation system generally comprises two stages of recalling and sorting, and the current recommendation system recall algorithm generally uses click data of a user as basic data for calculation, and determines whether the user has certain interest in recommendation information based on whether the user clicks the recommendation information, so that other similar data of the same type are recommended to the user. Referring to fig. 1, fig. 1 is a schematic flow chart of an information recommendation method in the related art, in which an information recommendation system first obtains click data of a user (S1), and obtains a preset interestingness rule and/or a preset calculation model (S2), and then determines a material similar to the content of the click data of the user from a material database and recommends the material to the user by using the preset interestingness rule and/or the preset calculation model (S3).
However, for the recommendation system, it is a primary objective to be able to more accurately capture the user interest and meet the personalized requirements of the user, and the recommendation information data clicked by the user is data recommended to the user by the platform through calculation, such as clicking, reading, and the like of the recommendation information by the user, belonging to information passively acquired by the user, and if only depending on the user interest point determined by the user's behavior in passively acquiring information, there is practically no subjective interest of the user, so that it is possible that the recommendation fails because the recommendation information is not information of interest of the user.
In order to solve the above problem, embodiments of the present application provide an information recommendation method, apparatus, device, and computer-readable storage medium, where the determined recommendation information is high-quality information that better conforms to a target user interest point, so as to improve effectiveness of information recommendation.
The information recommendation method provided by the embodiment of the application can be implemented by various electronic devices, for example, the information recommendation method can be implemented by a server alone, or can be implemented by a terminal and the server cooperatively. For example, the server alone executes a live broadcast recommendation method described below, or the terminal transmits a recommendation request message to the server, and the server executes an information recommendation method based on the received recommendation request message.
The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network service, cloud communication, middleware service, domain name service, security service, big data and artificial intelligence platforms and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, which is not specifically limited in this embodiment of the application.
Referring to fig. 2, fig. 2 is a schematic diagram of an architecture of an information recommendation system 200 provided in an embodiment of the present application, in which terminals (terminal 201-1 and terminal 201-2 are exemplarily shown) are connected to a server 203 through a network 202, and the network 202 may be a wide area network or a local area network, or a combination of both.
In some embodiments, the terminal or the server 200 may implement the information recommendation method provided by the embodiment of the present application by running a computer program. For example, the computer program may be a native program or a software module in an operating system; for example, the Application may be a native Application (APP), that is, a program that needs to be installed in an operating system to run, such as a live APP; the method can also be a live program, namely a live program which can be operated only by downloading to a browser environment; but also a live applet that can be embedded into any APP. In summary, the computer program may be any form of application program, module or plug-in, which is not specifically limited in this application embodiment.
Here, the terminal 201-1 is taken as a target user for explanation, and the terminal 201-1 displays an interface of APP on the current interface 210-1. Illustratively, the terminal 201-1 may also display on the current interface recommended materials to be presented to the target user based on the search behavior of the target user. The server 200 may receive content data of a search behavior sent by the terminal 201-1, where the search behavior includes multiple child behaviors, and then the server splits the child behaviors of the search behavior of the target user and recommends a set of materials to be recommended to the target user according to recommendation strategies corresponding to different search behaviors.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a server according to an embodiment of the present disclosure, and the server 203 shown in fig. 3 may include at least one processor 310, a memory 320, at least one network interface 330, and a user interface 340. The various components in device 300 are coupled together by a bus system 350. It is understood that the bus system 350 is used to enable connection communications between these components. The bus system 350 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 350 in FIG. 3.
The Processor 310 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.
The user interface 340 includes one or more output devices 341, including one or more speakers and/or one or more visual display screens, that enable presentation of media content. The user interface 304 also includes one or more input devices 342, including user interface components to facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.
The memory 320 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 320 may optionally include one or more storage devices physically located remote from processor 310.
The memory 320 includes volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. The nonvolatile memory may be a Read Only Memory (ROM), and the volatile memory may be a Random Access Memory (RAM). The memory 320 described in embodiments herein is intended to comprise any suitable type of memory.
In some embodiments, memory 320 is capable of storing data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as exemplified below.
An operating system 321 including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks;
a network communication module 322 for reaching other computing devices via one or more (wired or wireless) network interfaces 330, exemplary network interfaces 330 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), etc.;
a presentation module 323 for enabling presentation of information (e.g., user interfaces for operating peripherals and displaying content and information) via one or more output devices 342 (e.g., display screens, speakers, etc.) associated with the user interface 340;
an input processing module 324 for detecting one or more user inputs or interactions from one of the one or more input devices 342 and interpreting the detected inputs or interactions.
In some embodiments, the user recall means provided by the embodiments of the present application may be implemented in software, and fig. 3 shows the user recall means 325 stored in the memory 320, which may be software in the form of programs and plug-ins, etc., and includes the following software modules: the first obtaining module 3251, the first determining module 3252, the second determining module 3253, the third determining module 3254, the processing module 3255 and the recommending module 3256 are logical, and thus may be arbitrarily combined or further split according to the implemented functions. The functions of the respective modules will be explained below.
In other embodiments, the user recall Device provided in the embodiments of the present Application may be implemented in hardware, and for example, the user recall Device provided in the embodiments of the present Application may be a processor in the form of a hardware decoding processor, which is programmed to execute the user recall method provided in the embodiments of the present Application, for example, the processor in the form of the hardware decoding processor may be one or more Application Specific Integrated Circuits (ASICs), DSPs, programmable Logic Devices (PLDs), complex Programmable Logic Devices (CPLDs), field Programmable Gate Arrays (FPGAs), or other electronic components.
In other embodiments, the information recommendation Device provided in the embodiments of the present Application may be implemented in hardware, and for example, the information recommendation Device provided in the embodiments of the present Application may be a processor in the form of a hardware decoding processor, which is programmed to execute the information recommendation method provided in the embodiments of the present Application, for example, the processor in the form of the hardware decoding processor may be one or more Application Specific Integrated Circuits (ASICs), DSPs, programmable Logic Devices (PLDs), complex Programmable Logic Devices (CPLDs), field Programmable Gate Arrays (FPGAs), or other electronic components.
The information recommendation method provided by the embodiment of the present application will be described below in conjunction with an exemplary application and implementation of the information recommendation device provided by the embodiment of the present application.
Referring to fig. 4, fig. 4 is a schematic flowchart of an information recommendation method provided in an embodiment of the present application, and the following description will be made with reference to the steps shown in fig. 4.
S401, obtaining search behavior data of a target user;
wherein the search behavior data is used to indicate search behavior of the target user.
In some embodiments, the search behavior data of the target user may contain search terms of the target user, or may also include data of the time the target user searched for behavior, the location where the search behavior was conducted. Wherein the search terms are data actively input by the target user. The number of the search words may be one or more, for example, a single word or a plurality of words, or may also be a long sentence, and the like, and the content of the search word may be a word having a direct sentence meaning, or may also be some symbols having no meaning, such as some web-symbol languages, and the like. In addition, the search term may be in any language type, such as english, chinese, or a combination of multiple types of languages.
In some embodiments, the search behavior data may not be limited to only text information, but the search behavior data of the target user may also be image information. For example, for a platform supporting image retrieval, a target user may search for content associated with image information content by uploading image information to be searched, and at this time, the information recommendation device may acquire the image information, determine an associated material to be recommended based on the content of the image information, and recommend the material to be recommended to the target user.
S402, determining a material set corresponding to the search behavior according to the search behavior data.
It is to be understood that the material set corresponding to the search behavior may be a set of associated one or more materials determined from the material library based on the above-mentioned search term, image, and the like.
Illustratively, after a target user inputs a search term through a terminal, an information recommendation device retrieves materials with the search term from a material database according to the search term and sends the materials to the terminal, and the terminal displays the received materials through a display interface. The received materials can be any type of materials such as characters, pictures, videos and the like.
And S403, determining the type of the operation behavior of the target user on the material corresponding to the search behavior in the material set.
In some embodiments, the operation behavior of the target user on the material corresponding to the search behavior in the material collection is a further operation behavior on the searched material after the target user searches the corresponding material through the search behavior.
Illustratively, after the information recommendation device searches one or more materials including characters, pictures, videos and the like according to the search terms and issues the materials to the terminal, the target user can view the materials through a display interface of the terminal. The further operational behavior of the target user based on the retrieved material may include: clicking one or more materials to view, and carrying out operations of approval, collection, forwarding, comment and the like on the contents of the one or more materials.
It will be appreciated that recommendation systems typically analyze a user's points of interest based on the user's behavioral data, such as data that the user likes, as well as data types, such as styles, types of pictures, styles of videos, and so forth. And the target user can reflect the interest degree of the material content to a certain extent according to the different operation behaviors of the searched material based on the search word. For example, the number of the materials received by the terminal is multiple, and the target user clicks to view one or more of the materials, so that the target user has a higher probability of being interested in the materials viewed by clicking than the materials viewed only without clicking. Or for a plurality of materials which are clicked and viewed by the target user, the probability that the target user has a higher interest degree in one or more of the collected materials than the uncollected materials is necessarily higher. Or may also include any other operation behavior of the target user that can indicate different interest levels of the user, such as different time periods for the target user to view a plurality of materials, and so on.
S404, determining a material subset to be recommended corresponding to each type of operation behavior according to recommendation strategies corresponding to different types of operation behaviors;
in some embodiments, the operational behavior of the target user may correspond to only one item.
For example, for a material, such as a video content, the operation behavior may include that the target user clicks on the video or does not click on the video. At this time, based on the operation behavior of click-to-view, determining the subset of the materials to be recommended corresponding to the operation behavior may determine the subset of the materials to be recommended for the target user based on the content information of the video as a search mark, for example, some commentary videos of the video, a photo set of characters in the video, and the like. For the operation behavior which is not clicked to watch, the subset of the materials to be recommended corresponding to the operation behavior is determined, and the subset of the materials to be recommended can be determined for the target user based on data such as search words of the video searched by the target user and the like as a search mark.
In other embodiments, each operational behavior may correspond to multiple materials.
For example, also taking the material corresponding to the operation behavior as the video content, the operation behavior of the target user may include that the target user clicks to watch the videos or does not click to watch the videos, and meanwhile, because the durations of the plurality of videos are different, the operation behavior of the target user may also include that the target user watches the complete videos or the target user does not watch the complete video content. Or the time for the target user to watch each video and whether the video is subjected to operation behaviors such as praise, comment forwarding and the like. Firstly, aiming at the operation behavior of non-click watching, determining the subset of the materials to be recommended for the target user can be based on the search words of the videos searched by the target user as the search marks, and determining the subset of the materials to be recommended for the target user. Aiming at the operation behavior that the target user clicks and watches the video, the target user watches each video for different time lengths, or part of the target users of the video only watch the video and do not watch the complete video content. At this time, the subset of the materials to be recommended can be determined for the target user according to the video content of the target user watching the complete video content.
As can be understood, the target user may reflect, to a certain extent, whether the target user is interested in the material based on the type of the operation behavior of the material corresponding to the search behavior, and therefore, in this embodiment of the application, the operation behavior of the target user on the material corresponding to the search behavior may be used to indicate the interest degree of the target user on the material corresponding to the search behavior. Therefore, the recommended materials are determined for the target users by different strategies based on the interest degree of the target users, the determined subset of the materials to be recommended more conforms to the interest points of the target users, and the recommending effect can be improved.
For example, referring to fig. 5, fig. 5 is a schematic view of an optional flow chart of the information recommendation method provided in the embodiment of the application, based on fig. 5, the step S403 may include:
s501, determining a first subset of materials to be recommended according to content data of a search behavior based on a first operation behavior of a target user for materials corresponding to the search behavior;
the content data of the search behavior may be data input by the target user when obtaining the material corresponding to the search behavior based on the search behavior, such as the search word and the image.
S502, based on a second operation behavior of the target user for the material corresponding to the search behavior, determining a second recommended material subset according to the content data of the material corresponding to the search behavior.
And the interest degree of the target user indicated by the second operation behavior on the material corresponding to the search behavior is higher than that of the first operation behavior.
It can be understood that the first operation behavior and the second operation behavior described herein are only sub-behaviors used for distinguishing different operations of the target user on the material, and based on multiple types of operation behaviors, the embodiment of the present application may further include multiple types of sub-behaviors used for referring to different interest degrees of the target user on the material corresponding to the search behavior.
For example, the second operation behavior may refer to that the target user clicked on one or more of the materials after the search behavior, and the first operation behavior may refer to that the materials were not clicked on after the search behavior.
As can be appreciated, the likely level of interest is higher for a target user for a clicked-after-search material as compared to a non-clicked-after-search material. Therefore, the method and the device for recommending the materials are based on the division of the target user on different types of operation behaviors of the materials corresponding to the search behaviors to refer to the interest degrees of the target user on different materials, so that the recommended materials are determined for the target user by different strategies based on the interest degrees of the target user, the recommended materials are more in line with the interest points of the target user, and the recommending effect can be improved.
The material corresponding to the search behavior is obtained from a preset material library based on the content data corresponding to the search behavior, for example, the content data of the search behavior is a search word, and the material corresponding to the search behavior may be a material which is searched by the information recommendation device from the material library based on the search word and contains all or part of the content of the search word. The content data of the material corresponding to the search behavior indicates data of material content, for example, the material corresponding to the search behavior contains a video file, and the content data of the material may include data information of a duration, a style type, video content, and the like of the video file.
In an embodiment, referring to fig. 6, fig. 6 is an optional flowchart of the information recommendation method provided in the embodiment of the present application, and based on fig. 6, the step S501 may include:
s601, acquiring a first set of the top N hot content data with the highest search volume in the content data of the search behavior of the preset user;
it should be noted that the preset user may be each user to be recommended in the recommendation system, that is, each set of target users. For example, the target user is a user registered in the social software platform, the preset user may refer to all registered users of the platform, or the preset user may also be a part of the registered users of the platform determined by the recommendation system based on certain conditions.
The content data of the search behavior of the preset user is input data in the search behavior of the preset user, such as search words and the like. The first N hot content data with the highest search volume are the first N input data with the largest repetition times in the input data of all search behaviors in the search behaviors of the preset user. For example, when the preset user is all registered users of the platform, the acquired content data of the search behavior of the preset user may be content data of the search behavior of each registered user acquired by the information recommendation device, that is, a set of input data (search terms) in the search behavior of each registered user in the platform is acquired. At this time, the top N popular content data with the highest search volume are the search terms with the highest repetition volume in the search behaviors of all registered users in the platform.
Wherein, the value of N can be obtained according to data analysis. For example, when the user population is large, the total amount of the search terms is inevitably large, the required computing resources are also increased exponentially, all the search terms inevitably contain more invalid contents such as long-tail words, the number of search terms with small search quantity is small, and the influence range is small, so that the maximum computing effect is ensured under the condition of saving computing resources by selecting a reasonable threshold value to be online.
S602, acquiring a second set of content data of the search behavior of the target user;
in some embodiments, the second set of content data of the search behavior of the target user may be data of the search behavior of the target user within a predetermined time window.
It is understood that the larger the time span of the search behavior, the more content data of the search behavior of the corresponding target user may be, but the lower the interest level of the target user is reflected, for example, a tv drama searched by the target user one month ago may be seen by the target user during the month, so that the data of the search behavior has little effect on determining the interest level of the target user, and may even affect the final recommendation result. Therefore, the content data of the search behavior within the predetermined time window (for example, the last day, or three days, etc.) is acquired, the current interest point of the target user can be fitted to the maximum extent, and the accuracy of information recommendation is improved.
S603, taking intersection of the first set and the second set to obtain popular content data of the search behavior of the target user;
it can be understood that, taking the example that the target user acquires the relevant video content by inputting the search term, in the case that the target user only searches for the missing point, the probability shows that the target user has a small degree of interest in the video content found based on the search term at this time, or some target users may not have an explicit purpose of interest in the content. Therefore, in the embodiment of the application, the intersection is taken based on the first set of the search term records of the target user and the popular search terms of the whole user group, the interesting content of the target user is fitted as much as possible according to the interest probability of most people, the probability that the determined recommended material set is the interesting content of the target user can be improved under the condition that the basic data for analyzing the interest points of the target user is less, and the recommendation effect is improved.
S604, calculating a first similarity between the popular content data of the target user search behavior and the materials in a preset material library based on a similarity algorithm model according to the popular content data;
the similarity algorithm model may be any existing model, such as a system filtering algorithm. Or may be actually trained based on historical data of the target user. The selection of the similarity algorithm model in the embodiment of the present application is not specifically limited.
In some embodiments, the information recommendation device may obtain the vectorized representation of each hot search term by vectorizing each search term through a term vector algorithm for the N hot search terms, extracting the meaning of the search term in the complete search term through a semantic analysis model, simultaneously performing data cleaning, eliminating meaningless mood auxiliary words in the search terms, and the like. And then, after the intersection of the second set of the search terms of the target users and the N hot search terms is taken, the vectorized representation of the hot search terms of each target user can be obtained. The semantic analysis model may be an existing trained model, such as a language model (BERT) algorithm.
S605, determining a first to-be-recommended material subset from a preset material library based on the first similarity.
In some embodiments, the information recommendation device may acquire the first material to be recommended from a preset material library by setting a similarity threshold.
Illustratively, the information recommendation device determines all materials in a preset material library, which satisfy a similarity threshold with the hot search term of the target user, as a first subset of materials to be recommended.
In other embodiments, the information recommendation device may further obtain the first subset of materials to be recommended from a preset material library by setting a threshold of the quantity of the first set of materials to be recommended.
For example, the quantity threshold may be 50, and at this time, the information recommendation device may sort the materials in the preset material database based on the similarity value, and select the first 50 materials as the first set of materials to be recommended.
In some embodiments, referring to fig. 7, fig. 7 is an optional flowchart of the information recommendation method provided in the embodiment of the present application, and based on fig. 7, the step S502 may include:
s701, acquiring content data of a material corresponding to a search behavior;
it can be understood that the material corresponding to the search behavior is the material that the information recommendation device finds all or part of the search terms from the material library based on the search behavior data, such as the search terms. When the target user clicks one or more materials for viewing after searching, the materials are shown as materials which are likely to be interested by the target user, and therefore, materials of the type can be recommended for the target user based on the content corresponding to the materials.
S702, calculating a second similarity between the content data of the material corresponding to the search behavior and the material in the preset material library based on a similarity algorithm model according to the content data of the material corresponding to the search behavior;
the similarity algorithm may adopt any existing algorithm model, for example, the similarity algorithm may be the same as the above-mentioned similarity algorithm for calculating the similarity of the search term materials. The selection of the similarity algorithm in the embodiment of the present application is not specifically limited.
And S703, determining a second to-be-recommended material subset from the preset material library based on the second similarity.
In some embodiments, the information recommendation device may obtain the second material to be recommended from the preset material library by setting a similarity threshold.
Exemplarily, all the materials, which satisfy the similarity threshold value with the content data of the material corresponding to the search behavior, in the preset material library are determined as the second set of materials to be recommended.
In other embodiments, the server may further obtain a second subset of the materials to be recommended from the preset material library by setting a second threshold of the number of the sets of the materials to be recommended.
For example, the number threshold may be 50, and at this time, the materials in the preset material database may be sorted based on the similarity, and the top 50 materials are selected as the second set of materials to be recommended.
S405, obtaining a set of materials to be recommended according to the priority of the subset of the materials to be recommended;
it should be noted that the priority of the to-be-recommended material subset is actually the priority of the corresponding operation behavior, for example, the interest degree of the target user in the to-be-recommended material subset corresponding to the operation behavior of the search click is higher than the interest degree of the to-be-recommended material subset corresponding to the operation behavior of the search click, and therefore, the priority of the to-be-recommended material subset corresponding to the operation behavior of the search click is higher than the priority of the to-be-recommended material subset corresponding to the operation behavior of the search click.
It will be appreciated that the first to-be-recommended subset may be determined based on search behavior data, such as search terms, and that each target user may have one or more search terms. Therefore, for any target user, a first subset of the materials to be recommended can be determined based on the search terms. And for the target user with the second operation behavior, the interest degree of acquiring the corresponding second to-be-recommended material subset based on the second operation behavior is higher. Therefore, the second subset of materials to be recommended can be preferentially recommended to the target user as the set of materials to be recommended.
Based on this, in some embodiments, the obtaining the set of materials to be recommended according to the priority of the subset of materials to be recommended may include: and determining the second subset of the materials to be recommended as the set of the materials to be recommended.
And the second subset of materials to be recommended is the subset of materials to be recommended with the highest priority.
In addition, because there may be a case where the number of the materials in the second subset of the materials to be recommended is small, at this time, the first subset of the materials to be recommended and the second subset of the materials to be recommended may also be merged, and the merged first subset of the materials to be recommended and the merged second subset of the materials to be recommended are recommended to the target user together as the set of the materials to be recommended.
Based on this, in some embodiments, obtaining the set of materials to be recommended according to the priority of the subset of materials to be recommended may further include the following steps:
step 1, determining whether the quantity of materials in a second subset of materials to be recommended is greater than or equal to a first threshold value;
step 2, when the quantity of the materials in the second subset of the materials to be recommended is greater than or equal to a first threshold value, selecting the materials with the quantity meeting the first threshold value from the second subset of the materials to be recommended as a set of the materials to be recommended;
and 3, when the quantity of the materials in the second subset of the materials to be recommended is smaller than a first threshold value, combining the first subset of the materials to be recommended to the second subset of the materials to be recommended, and selecting the materials with the quantity meeting the first threshold value from the combined second subset of the materials to be recommended as the set of the materials to be recommended.
The priority of the first subset of the materials to be recommended is the next level of the priority of the second subset of the materials to be recommended.
In some embodiments, the first subset of materials to be recommended is merged to the second subset of materials to be recommended, all materials in the first subset of materials to be recommended may be merged to the second subset of materials to be recommended, and then materials with quantity meeting a first threshold value are selected from the merged second subset of materials to be recommended and recommended to the target user.
In other embodiments, the merging of the first subset of materials to be recommended to the second subset of materials to be recommended may also be to determine a difference between the quantity of materials in the second subset of materials to be recommended and a first threshold, and then select materials of which the quantity satisfies the difference from the first subset of materials to be recommended to merge into the second subset of materials to be recommended. For example, the items in the first subset of the to-be-recommended items may be sorted based on the first similarity determined when the first subset of the to-be-recommended items is determined, and then the item with the highest similarity is selected to make up the difference portion.
Illustratively, the value of the first threshold is 30, only 20 materials are in the current second set of materials to be recommended, the information recommendation device ranks the materials in the first subset of materials to be recommended based on the calculated first similarity, then selects 10 materials with the highest similarity to be added to the second subset of materials to be recommended, and then determines the merged second subset of materials to be recommended as the set of materials to be recommended.
And S406, recommending materials to the target user according to the combined material set to be recommended.
It can be understood that the second subset of materials to be recommended is a set of materials with the highest determined interest level of the target user, and therefore when materials are recommended to the target user, if the set of materials to be recommended is a set in which the first subset of materials to be recommended and the second subset of materials to be recommended are combined, the content of the materials in the second set of materials to be recommended can be preferentially displayed, the materials in the first subset of materials to be recommended are placed behind the materials in the second subset of materials to be recommended, and the materials in the set of materials to be recommended are recommended to the target user according to the order of the materials. Therefore, when the target user displays the recommended materials through the terminal, the materials with higher interest degree can be preferentially checked, and the effectiveness of information recommendation is improved.
In the embodiment of the application, the subsets of the materials to be recommended corresponding to different types are obtained according to different types of operation behaviors of the target user on the materials corresponding to the search behaviors, the set of the materials to be recommended is obtained according to the priority of the subsets of the materials to be recommended and recommended to the target user, and therefore the recommended materials determined by the active search behaviors of the target user better accord with the interest points of the target user, meanwhile, the different interest degrees of the target user can be reflected according to different operation behaviors by carrying out hierarchical processing on the basis of the different types of operation behaviors, the probability that the recommended information is high-quality information according with the interest points of the target user is ensured to be higher, and the accuracy of information recommendation is improved.
Next, an exemplary application of the embodiment of the present application in a practical application scenario will be described.
When the information recommendation method is applied to the social application software of the terminal, such as a microblog, at this time, the information recommended to the user may include a blog article, a picture, a video and the like issued by a blogger. An implementation process of the information recommendation method applied to the microblog can be seen in fig. 8, and fig. 8 is a schematic process diagram of the information recommendation method applied to the social application software provided by the embodiment of the application. The following will be explained with reference to the steps shown in fig. 8.
S801, acquiring search behavior data of a target user;
s802, determining a material set corresponding to the search behavior according to the search behavior data;
s803, determining the type of the operation behavior of the target user on the material corresponding to the search behavior in the material set, and executing steps S804 to S809 when the type of the operation behavior is the first operation behavior; when the type of the operation behavior is the second operation behavior, performing steps S810 to S814;
s804, acquiring a first set of the top N hot content data with the highest search volume in the content data of the search behavior of the preset user;
s805, acquiring a second set of content data of the search behavior of the target user;
s806, taking intersection of the first set and the second set to obtain popular content data of the search behavior of the target user;
s807, calculating a first similarity between hot content data of the target user and materials in a preset material library based on a similarity algorithm model;
s808, determining a first to-be-recommended material subset from a preset material library based on the first similarity;
s809, selecting materials of which the quantity meets a first threshold value from the first subset of materials to be recommended, and determining the materials to be recommended;
s810, acquiring content data of the material corresponding to the search behavior;
s811, calculating a second similarity between the content data of the material corresponding to the search behavior and the material in the preset material library based on the similarity algorithm model according to the content data of the material corresponding to the search behavior;
s812, determining a second to-be-recommended material subset from a preset material library based on the second similarity;
s813, determining whether the quantity of the materials in the second subset of the materials to be recommended is greater than or equal to a first threshold value; if the value is greater than or equal to the predetermined value, step S814 is executed; if less than the threshold value, go to step S814;
s813, selecting materials of which the material quantity meets a first threshold value from the second subset of materials to be recommended as a set of materials to be recommended;
s814, merging the first subset of materials to be recommended to the second subset of materials to be recommended, and selecting materials of which the material quantity meets a first threshold value from the merged second subset of materials to be recommended as a set of materials to be recommended;
and S815, recommending materials to the target user according to the material set to be recommended.
Thus, the information recommendation method is completed.
Continuing with the exemplary structure of the information recommendation device 325 implemented as software modules provided in the embodiments of the present application, in some embodiments, as shown in fig. 3, the software modules stored in the information recommendation device 325 of the memory 320 may include: a first obtaining module 3251, configured to obtain search behavior data of a target user, where the search behavior data is used to indicate a search behavior of the target user; the first determining module 3252 is configured to determine, according to the search behavior data, a material set corresponding to a search behavior; the second determining module 3253 is configured to determine the type of an operation behavior of the target user on the material corresponding to the search behavior in the material set; the third determining module 3254 is configured to determine, according to recommendation strategies corresponding to different types of operation behaviors, a subset of the material to be recommended, which corresponds to each type of operation behavior; the processing module 3255 is configured to obtain a set of materials to be recommended according to the priority of the subset of materials to be recommended; and the recommending module 3256 is used for recommending materials to the target user according to the set of materials to be recommended.
In some possible embodiments, the operation behavior of the target user on the material corresponding to the search behavior is used to indicate the interest degree of the target user on the material corresponding to the search behavior; the search sub-behavior is used for indicating the interest degree of the target user in the material corresponding to the search behavior; the third determining module 3254 is further configured to determine, based on a second operation behavior of the target user for the material corresponding to the search behavior, a second subset of the material to be recommended according to the content data of the material corresponding to the search behavior; the materials corresponding to the search behavior are obtained from a preset material library based on the content data of the search behavior; the interest degree of the target user indicated by the second operation behavior on the material corresponding to the search behavior is higher than that of the first operation behavior.
In some possible embodiments, the third determining module 3254 is further configured to obtain a first set of top N top-ranked content data with the highest search volume in the content data of the search behavior of the preset user; n is an integer greater than 0; acquiring a second set of content data of the search behavior of the target user; taking intersection of the first set and the second set to obtain hot content data of the search behavior of the target user; calculating a first similarity between the popular content data of the search behavior of the target user and the materials in a preset material library based on a similarity algorithm model according to the popular content data; and determining a first to-be-recommended material subset from a preset material library based on the first similarity.
In some possible embodiments, the third determining module 3254 is further configured to obtain content data of a material corresponding to the search behavior; calculating a second similarity between the content data of the material corresponding to the search behavior and the material in the preset material library based on a similarity algorithm model according to the content data of the material corresponding to the search behavior; and determining a second to-be-recommended material subset from the preset material library based on the second similarity.
In some possible embodiments, the processing module 3255 is further configured to determine the second subset of materials to be recommended as the set of materials to be recommended; and the second subset of the materials to be recommended is the subset of the materials to be recommended with the highest priority.
In some possible embodiments, the processing module 3255 is further configured to determine whether the amount of the material in the second subset of materials to be recommended is greater than or equal to a first threshold; when the quantity of the materials in the second subset of the materials to be recommended is greater than or equal to a first threshold value, selecting the materials of which the quantity of the materials meets the first threshold value from the second subset of the materials to be recommended as a set of the materials to be recommended; when the quantity of the materials in the second subset of the materials to be recommended is smaller than a first threshold value, combining the first subset of the materials to be recommended to the second subset of the materials to be recommended, and selecting the materials with the quantity meeting the first threshold value from the combined second subset of the materials to be recommended as a set of the materials to be recommended; the priority of the first subset of the materials to be recommended is the next level of the priority of the second subset of the materials to be recommended.
In some possible embodiments, the information recommendation apparatus further includes: and the data cleaning module is used for performing data cleaning on the content data of the search behavior and/or the content data of the material corresponding to the search behavior so as to filter invalid contents in the content data of the search behavior and/or the content data of the material corresponding to the search behavior.
Fig. 9 is a schematic structural diagram of a computer device 910 according to an embodiment of the present application, where the computer device 910 may have a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 911 (e.g., one or more processors) and a memory 912, and one or more storage media 913 (e.g., one or more mass storage devices) for storing an application 921 or data 922. Memory 912 and storage medium 913 may be, among other things, transient or persistent storage. The program stored on the storage medium 913 may include one or more modules (not shown), each of which may include a series of instruction operations for the computer device. Still further, the central processor 911 may be configured to communicate with the storage medium 913, and execute a series of instruction operations in the storage medium 913 on the computer device 910.
The computer device 910 may also include one or more power supplies 914, one or more wired or wireless network interfaces 915, one or more input-output interfaces 916, and/or one or more operating systems 917, such as Windows Server, mac OS XTM, uniTM, linuxTM, freeBSDTM, and so forth.
Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the information recommendation method described in the embodiment of the present application.
Embodiments of the present application provide a computer-readable storage medium storing executable instructions, which when executed by a processor, cause the processor to execute an information recommendation method provided by embodiments of the present application, for example, the information recommendation method shown in fig. 4.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EP ROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
In summary, according to different types of operation behaviors of a target user on materials corresponding to search behaviors, subsets of materials to be recommended corresponding to different types are obtained, and a set of the materials to be recommended is obtained according to priorities of the subsets of the materials to be recommended and recommended to the target user.
The above description is only an example of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims (10)

1. An information recommendation method, characterized in that the method comprises:
obtaining search behavior data of a target user, wherein the search behavior data is used for indicating the search behavior of the target user;
determining a material set corresponding to the search behavior according to the search behavior data;
determining the type of the operation behavior of the target user on the material corresponding to the search behavior in the material set;
determining a material subset to be recommended corresponding to each type of operation behavior according to recommendation strategies corresponding to different types of operation behaviors;
obtaining a set of materials to be recommended according to the priority of the subset of the materials to be recommended;
and recommending materials to the target user according to the set of materials to be recommended.
2. The method according to claim 1, wherein the operation behavior of the target user on the material corresponding to the search behavior is used to indicate the interest level of the target user on the material corresponding to the search behavior;
determining the material subset to be recommended corresponding to each type of operation behavior according to the recommendation strategies corresponding to the different types of operation behaviors, including:
determining a first subset of materials to be recommended according to content data of the search behavior based on a first operation behavior of the target user for the materials corresponding to the search behavior;
determining a second subset of materials to be recommended according to content data of the materials corresponding to the search behavior based on a second operation behavior of the target user for the materials corresponding to the search behavior;
the materials corresponding to the search behavior are obtained from a preset material library based on the content data of the search behavior; the interest degree of the target user indicated by the second operation behavior on the material corresponding to the search behavior is higher than the interest degree of the target user indicated by the first operation behavior on the material corresponding to the search behavior.
3. The method according to claim 2, wherein the determining a first subset of materials to be recommended according to content data of the search behavior based on the first operation behavior of the target user for the materials corresponding to the search behavior comprises:
acquiring a first set of the first N hot content data with the highest search volume in the content data of the search behavior of a preset user, wherein N is an integer larger than 0;
acquiring a second set of content data of the search behavior of the target user;
taking intersection of the first set and the second set to obtain popular content data of the search behavior of the target user;
calculating a first similarity between the popular content data of the search behavior of the target user and the materials in a preset material library based on a similarity algorithm model according to the popular content data;
and determining the first to-be-recommended material subset from the preset material library based on the first similarity.
4. The method according to claim 2, wherein the determining, based on a second operation behavior of the target user for the material corresponding to the search behavior, a second subset of the material to be recommended according to the content data of the material corresponding to the search behavior includes:
acquiring content data of the material corresponding to the search behavior;
calculating a second similarity between the content data of the material corresponding to the search behavior and the material in the preset material library based on a similarity algorithm model according to the content data of the material corresponding to the search behavior;
and determining the second subset of the materials to be recommended from the preset material library based on the second similarity.
5. The method according to claim 3 or 4, wherein the obtaining a set of materials to be recommended according to the priority of the subset of materials to be recommended comprises:
determining the second subset of materials to be recommended as the set of materials to be recommended; and the second subset of materials to be recommended is the subset of materials to be recommended with the highest priority.
6. The method according to claim 5, wherein the obtaining a set of materials to be recommended according to the priority of the subset of materials to be recommended comprises:
determining whether the quantity of the materials in the second subset of the materials to be recommended is greater than or equal to a first threshold value;
when the quantity of the materials in the second subset of the materials to be recommended is larger than or equal to the first threshold value, selecting the materials with the quantity of the materials meeting the first threshold value from the second subset of the materials to be recommended as the set of the materials to be recommended;
when the quantity of the materials in the second subset of the materials to be recommended is smaller than the first threshold value, merging the first subset of the materials to be recommended into the second subset of the materials to be recommended, and selecting the materials with the quantity meeting the first threshold value from the merged second subset of the materials to be recommended as the set of the materials to be recommended; the priority of the first subset of the materials to be recommended is the next level of the priority of the second subset of the materials to be recommended.
7. The method according to claim 2, wherein before determining the subset of the materials to be recommended corresponding to each type of the operation behaviors according to the recommendation strategies corresponding to the different types of the operation behaviors, the method further comprises:
and performing data cleaning on the content data of the search behavior and/or the content data of the material corresponding to the search behavior to filter invalid contents in the content data of the search behavior and/or the content data of the material corresponding to the search behavior.
8. An information recommendation apparatus, characterized in that the apparatus comprises:
the device comprises a first obtaining module, a second obtaining module and a third obtaining module, wherein the first obtaining module is used for obtaining search behavior data of a target user, and the search behavior data is used for indicating search behaviors of the target user;
the first determining module is used for determining a material set corresponding to the searching behavior according to the searching behavior data;
a second determining module, configured to determine a type of an operation behavior of the target user on the material corresponding to the search behavior in the material set;
the third determining module is used for determining a material subset to be recommended corresponding to each type of operation behavior according to the recommendation strategies corresponding to the different types of operation behaviors;
the processing module is used for obtaining a set of materials to be recommended according to the priority of the subset of the materials to be recommended;
and the recommending module is used for recommending materials to the target user according to the material set to be recommended.
9. An information recommendation apparatus characterized by comprising:
a memory for storing executable instructions;
a processor for implementing the method of any one of claims 1 to 7 when executing executable instructions or computer programs stored in the memory.
10. A computer-readable storage medium storing executable instructions or a computer program, wherein the executable instructions, when executed by a processor, implement the method of any one of claims 1 to 7.
CN202211599477.7A 2022-12-12 2022-12-12 Information recommendation method, device, equipment and computer readable storage medium Pending CN115827978A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211599477.7A CN115827978A (en) 2022-12-12 2022-12-12 Information recommendation method, device, equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211599477.7A CN115827978A (en) 2022-12-12 2022-12-12 Information recommendation method, device, equipment and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN115827978A true CN115827978A (en) 2023-03-21

Family

ID=85546970

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211599477.7A Pending CN115827978A (en) 2022-12-12 2022-12-12 Information recommendation method, device, equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN115827978A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117151828A (en) * 2023-10-30 2023-12-01 建信金融科技有限责任公司 Recommended article pool processing method, device, equipment and medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117151828A (en) * 2023-10-30 2023-12-01 建信金融科技有限责任公司 Recommended article pool processing method, device, equipment and medium
CN117151828B (en) * 2023-10-30 2024-01-30 建信金融科技有限责任公司 Recommended article pool processing method, device, equipment and medium

Similar Documents

Publication Publication Date Title
CN111444428B (en) Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium
CN112203122B (en) Similar video processing method and device based on artificial intelligence and electronic equipment
US10277696B2 (en) Method and system for processing data used by creative users to create media content
CN110781376A (en) Information recommendation method, device, equipment and storage medium
CN110688476A (en) Text recommendation method and device based on artificial intelligence
CN111818370B (en) Information recommendation method and device, electronic equipment and computer-readable storage medium
US20140074828A1 (en) Systems and methods for cataloging consumer preferences in creative content
US11755676B2 (en) Systems and methods for generating real-time recommendations
US20170155939A1 (en) Method and System for Processing Data Used By Creative Users to Create Media Content
RU2714594C1 (en) Method and system for determining parameter relevance for content items
CN112528147A (en) Content recommendation method and apparatus, training method, computing device, and storage medium
CN111125344A (en) Related word recommendation method and device
CN114265981A (en) Recommendation word determining method, device, equipment and storage medium
CN111506845A (en) Content display method, device and equipment based on media information stream and storage medium
US7917520B2 (en) Pre-cognitive delivery of in-context related information
CN115858910A (en) Object recommendation method and device based on artificial intelligence and electronic equipment
CN112825089B (en) Article recommendation method, device, equipment and storage medium
CN115203539A (en) Media content recommendation method, device, equipment and storage medium
CN115827978A (en) Information recommendation method, device, equipment and computer readable storage medium
CN112818195A (en) Data acquisition method, device and system and computer storage medium
KR101372942B1 (en) Social media contents sharing apparatus and method
JP2010181966A (en) Device and method for evaluating recommendation information
AU2018429394B2 (en) Media source measurement for incorporation into a censored media corpus
CN110659419B (en) Method and related device for determining target user
CN112015972A (en) Information recommendation method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination