A server and a method of pushing recommended content

Abstract

The present disclosure relates to a server and a push method of recommended content, and relates to the technical field of data recommendation. The server comprises: obtaining a search keyword of an event, a search topic corresponding to the search keyword, and first sorting information of the search keyword; determining a preferred search topic of the event according to the first sorting information and the search topic corresponding to the search keyword; determining a target search keyword from the search keyword according to the preferred search topic; determining target recommended content corresponding to the target search keyword; and sending the target recommended content to a terminal. The embodiments of the present disclosure can accurately recommend content of interest to a user, and improve the recommendation effect and user experience.

Description

Technical Field

[0001] This disclosure relates to the field of data recommendation technology, and in particular to a server and a method for pushing recommended content. Background Technology

[0002] Following the incident, information on the internet exploded, making it difficult for users to select content they liked. Therefore, proactively recommending content that users might be interested in is crucial. Existing recommendation methods retrieve highly similar content based on user-input search terms and then recommend it to the user. However, relying solely on search terms for recommendations lacks specificity and may result in recommending media content that users are not interested in, leading to low recommendation accuracy. Summary of the Invention

[0003] To address, or at least partially address, the aforementioned technical problems, this disclosure provides a server and a method for pushing recommended content, which can accurately recommend content of interest to users, thereby improving recommendation effectiveness and user experience.

[0004] To achieve the above objectives, the technical solutions provided by the embodiments of this disclosure are as follows:

[0005] In a first aspect, this disclosure provides a server comprising:

[0006] The controller is configured to: obtain the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms;

[0007] Based on the first ranking information and the search topics corresponding to the search terms, determine the preferred search topics for the event;

[0008] Based on preferred search topics, identify target search terms from the search terms; determine the target recommended content corresponding to the target search terms;

[0009] Send the target recommended content to the terminal.

[0010] Secondly, this disclosure provides a method for pushing recommended content, the method comprising:

[0011] Retrieve the search terms for the event, the search topics corresponding to the search terms, and the first ranking information of the search terms;

[0012] Based on the first ranking information and the search topics corresponding to the search terms, determine the preferred search topics for the event;

[0013] Based on preferred search topics, identify target search terms from the search terms; determine the target recommended content corresponding to the target search terms;

[0014] Send the target recommended content to the terminal.

[0015] Thirdly, this disclosure provides a server, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, it implements the method for pushing recommended content as described in the second aspect or any of its optional embodiments.

[0016] Fourthly, this disclosure provides a computer-readable storage medium, comprising: storing a computer program on the computer-readable storage medium, wherein when the computer program is executed by a processor, it implements the method for pushing recommended content as described in the second aspect or any of its optional embodiments.

[0017] Fifthly, this disclosure provides a computer program product, including: when the computer program product is run on a computer, causing the computer to implement a method for pushing recommended content as described in the second aspect or any of its optional embodiments.

[0018] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0019] This disclosure provides a server and a method for pushing recommended content. The server obtains search terms for an event, the corresponding search topics, and first ranking information of the search terms through a controller. Then, based on the search topics and first ranking information, it determines the preferred search topic for the time. Next, based on the preferred search topic, it identifies the target search term from the search terms and the corresponding target recommended content, and then sends the target recommended content to the terminal. By accurately locating the user's preferred search topic based on the search topics and first ranking information, determining the target search term based on the preferred search topic, and then sending the corresponding target recommended content to the terminal, the server can push the target recommended content, thereby accurately recommending content of interest to the user and improving the recommendation effect and user experience. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0021] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the server operation scenario provided in the embodiments of this disclosure;

[0023] Figure 2 This is a block diagram showing the configuration of the control device in an embodiment of this disclosure;

[0024] Figure 3 A hardware configuration block diagram of a server provided in an embodiment of this disclosure;

[0025] Figure 4 This is a schematic diagram of the software configuration in the server provided in an embodiment of this disclosure;

[0026] Figure 5 This is a flowchart illustrating a method for pushing recommended content provided in an embodiment of this disclosure;

[0027] Figure 6 This is an illustration of the search terms provided in the embodiments of this disclosure. Figure 1 ;

[0028] Figure 7 This is an illustration of the search terms provided in the embodiments of this disclosure. Figure 2 ;

[0029] Figure 8 A schematic diagram illustrating the acquisition of a region identifier provided in an embodiment of this disclosure;

[0030] Figure 9 A schematic diagram illustrating the heat parameters of an event over a historical time period, as provided in the embodiments of this disclosure;

[0031] Figure 10 This is a schematic diagram of the structure of a server provided in an embodiment of the present disclosure. Detailed Implementation

[0032] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0033] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0034] The terms "first," "second," "third," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses. Those skilled in the art will understand the specific meaning of the above terms in this disclosure based on the specific circumstances. Additionally, in the description of this disclosure, unless otherwise stated, "a plurality of" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist; for example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0035] To recommend content that users may be interested in, existing recommendation methods retrieve content highly similar to the search terms entered by the user and then directly recommend it to the user. However, relying solely on search terms makes it difficult to pinpoint the user's interests, resulting in a lack of targeting and the recommendation of content that the user is not interested in. Consequently, the recommendation accuracy is low, the recommendation effect is poor, and the user experience is negatively impacted.

[0036] In addition, the existing recommendation method relies on operators to manually set the time to push notifications, which often results in the push of recommended content the day before the event. This may cause the best time to push notifications to be missed, greatly affecting the effectiveness of the push.

[0037] To address the aforementioned issues, this disclosure provides a server and a method for pushing recommended content. The server includes a controller. The server obtains search terms for an event, the corresponding search topics, and first ranking information for the search terms through the controller. Then, based on the search topics and the first ranking information, it determines the preferred search topic for the time period. Next, based on the preferred search topic, it identifies the target search term from the search terms and the corresponding target recommended content, and then sends the target recommended content to the terminal. By accurately locating the user's preferred search topic based on the search topics and the first ranking information of the search terms, determining the target search term based on the preferred search topic, and then obtaining the corresponding target recommended content based on the target search term and sending it to the terminal, the terminal can push the target recommended content, thereby accurately recommending content of interest to the user and improving the recommendation effect and user experience.

[0038] This disclosure also obtains the popularity parameters of events within a historical time period, and then analyzes and uses the time corresponding to the target popularity parameter that is greater than or equal to the preset popularity threshold as the target push time to realize automated push recommendation content. The push time is reasonable and can improve the recommendation effect.

[0039] like Figure 1 As shown, Figure 1 This is a schematic diagram illustrating an operational scenario of a server provided in an embodiment of this disclosure. The diagram includes a control device 100, a display device 200, a smart device 300, and a server 400. Users can operate the display device 200 through the control device 100 or the smart device 300.

[0040] In the recommendation scenario, server 400 periodically obtains search terms, corresponding search topics, and the initial ranking information of the search terms. In determining the target recommended content, it first identifies the user's preferred search topics based on the search topics and initial ranking information, then determines the target search terms based on those preferred topics, and finally determines the target recommended content corresponding to the target search terms, which is then sent to display device 200. By accurately identifying the user's focus through search terms, corresponding search topics, and initial ranking information, targeted and accurate recommendations of content that the user is interested in are achieved, improving recommendation effectiveness and user experience.

[0041] In some embodiments, a user can operate the display device 200 via a smart device 300 or a control device 100, and the display device 200 can communicate with the server 400. The smart device 300 (such as a mobile terminal, tablet computer, computer, laptop computer, etc.) can also be used to control the display device 200. For example, an application running on the smart device can be used to control the display device 200. In some embodiments, the control device 100 can be a remote control, and communication between the remote control and the terminal device includes infrared protocol communication or Bluetooth protocol communication, and other short-range communication methods, controlling the display device 200 wirelessly or via wired means. The user can control the display device 200 by inputting user commands through buttons on the remote control, voice input, control panel input, etc.

[0042] In some embodiments, the display device 200 may receive instructions not through the aforementioned smart device 300 or control device 100, but through touch or gestures.

[0043] In some embodiments, the display device 200 can also be controlled in ways other than the control device 100 and the smart device 300. For example, it can be controlled by directly receiving the user's voice commands through a module configured inside the display device 200 for acquiring voice commands, or it can be controlled by receiving the user's voice commands through a voice control device set outside the display device 200.

[0044] In some embodiments, the display device 200 may be allowed to communicate via a local area network (LAN), a wireless local area network (WLAN), and other networks. The server 400 may provide various content and interactive features to the display device 200. The server 400 may be a cluster or multiple clusters, and may include one or more types of servers. Alternatively, it may be a cloud server. The above is merely an example, and no limitation is made in this embodiment.

[0045] Figure 2 This is a block diagram showing the configuration of the control device in an embodiment of this disclosure. Figure 2 As shown, the control device 100 includes a controller 110, a communication interface 130, a user input / output interface 140, a memory, and a power supply. The control device 100 can receive user input commands and convert them into commands that the display device 200 can recognize and respond to, acting as an intermediary for interaction between the user and the display device 200. The communication interface 130 is used for external communication and includes at least one of a Wi-Fi chip, a Bluetooth module, NFC, or a replacement module. The user input / output interface 140 includes at least one of a microphone, a touchpad, a sensor, a button, or a replacement module.

[0046] Figure 3 This is a hardware configuration block diagram of a server provided in an embodiment of this disclosure. (See diagram below.) Figure 3As shown, server 400 includes at least one of the following: tuner / demodulator 210, communicator 220, detector 230, external device interface 240, controller 250, display 260, audio output interface 270, memory, power supply, and user interface 280. Controller 250 includes a central processing unit, video processor, audio processor, graphics processor, random access memory (RAM), read-only memory (ROM), and a first to nth interface for input / output. Display 260 may be at least one of liquid crystal display, OLED display, touch display, and projection display, and may also be a projection device and projection screen. Tuner / demodulator 210 receives broadcast television signals via wired or wireless reception and demodulates audio and video signals, such as Electronic Program Guide (EPG) data signals, from multiple wireless or wired broadcast television signals. Detector 230 is used to collect signals from the external environment or signals interacting with the external environment. The controller 250 and the tuner / demodulator 210 can be located in different separate devices; that is, the tuner / demodulator 210 can also be located in an external device of the main device containing the controller 250, such as an external set-top box. The external device interface 240 can include, but is not limited to, one or more of the following: High-definition multimedia interface (HDMI), analog or data high-definition component input interface (component), composite video input interface (CVBS), USB input interface (USB), RGB port, etc. It can also be a composite input / output interface formed by multiple of the above interfaces.

[0047] In some embodiments, the controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in memory. The controller 250 controls the overall operation of the display device 200. The user can input commands through a graphical user interface (GUI) displayed on the monitor 260, and the user input interface receives the user input commands through the GUI. Alternatively, the user can input user commands by inputting specific sounds or gestures, and the user input interface receives the user input commands by recognizing the sounds or gestures through sensors.

[0048] In some embodiments, a "user interface" is the medium through which an application or operating system interacts and exchanges information with a user, realizing the conversion between the internal form of information and a form acceptable to the user. A common form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed graphically. It can be an icon, window, control, or other interface element displayed on the monitor of an electronic device. Controls can include at least one of the following visual interface elements: icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, and web widgets (widgets).

[0049] In some embodiments, the controller includes at least one of a central processing unit (CPU), a video processor, an audio processor, a graphics processing unit (GPU), a RAM (random access memory), a ROM (read-only memory), a digital signal processor (DSP) for input / output, a first to an nth interface, a communication bus, etc.

[0050] A CPU (CPU) processor is used to execute operating system and application instructions stored in memory, as well as various interactive instructions received from external input, to execute various applications, data, and content, ultimately for the display and playback of various audio and video content. A CPU processor can include multiple processors, such as a main processor and one or more sub-processors.

[0051] This disclosure provides a server, the server comprising:

[0052] The controller 250 is configured to: acquire the search terms of the event, the search topics corresponding to the search terms, and the first sorting information of the search terms; determine the preferred search topic of the event based on the first sorting information and the search topics corresponding to the search terms; determine the target search term from the search terms based on the preferred search topic; determine the target recommended content corresponding to the target search term; and send the target recommended content to the terminal.

[0053] The server obtains the search terms for the event, the search topics corresponding to the search terms, and the first ranking information of the search terms through the controller. It combines the search topics and the first ranking information to determine the user's preferred search topics, then determines the target search terms based on the preferred search topics, and finally determines the target recommended content based on the target search terms. This achieves more accurate positioning of the target recommended content that the user is interested in, thus improving the recommendation effect.

[0054] In some embodiments, the search terms include a first search term corresponding to a primary search topic and a second search term corresponding to a secondary search topic; wherein, the secondary search topic is a search topic at other levels other than the primary search topic; the first sorting information includes a first sub-sorting information corresponding to the first search term and a second sub-sorting information corresponding to the second search term;

[0055] The controller 250, based on the first sorting information and the search topics corresponding to the search terms, determines the preferred search topic of the event, and is configured to: determine the first preference value of the primary search topic based on the first sub-sorting information; determine the second preference value of the secondary search topic based on the second sub-sorting information; calculate the total preference value of the search topics corresponding to the search terms based on the first preference value and the second preference value; and determine the preferred search topic from the search topics corresponding to the search terms based on the total preference value.

[0056] In some embodiments, the controller 250, which determines the target recommended content corresponding to the target search term, is configured to: perform word segmentation on the target search term to obtain multiple search words; match the multiple search words with a database to obtain target recommended keywords, wherein the database stores multiple recommended keywords, and different recommended keywords correspond to different recommended content; and determine the target recommended content corresponding to the target recommended keywords.

[0057] In some embodiments, the controller 250, which determines the target recommended content corresponding to the target recommended keyword, is configured to: determine the content to be recommended based on the target recommended keyword; after determining the second ranking information of the target search term, calculate the similarity between the target recommended keyword and the content to be recommended based on the second ranking information; and determine the target recommended content from the content to be recommended based on the similarity.

[0058] In some embodiments, after determining the target recommended content corresponding to the target search term, the controller 250 is further configured to: obtain historical search preference information of the event, which includes the popularity parameters of the event within a historical time period; determine the target recommendation time based on the popularity parameters of the event within the historical time period, and send the target recommended content and the target recommendation time to the terminal so that the terminal can push the target recommended content according to the target recommendation time.

[0059] In some embodiments, the controller 250 is configured to determine the target recommended time based on the popularity parameters of the event within a historical time period, wherein the target popularity parameter is greater than or equal to a preset popularity threshold, and the time corresponding to the target popularity parameter is used as the target recommended time.

[0060] In some embodiments, after determining the target popularity parameter based on the popularity parameter of the event within a historical time period, the controller 250 is further configured to: determine the duration of the event's popularity, where the duration of the popularity is the time it takes for the popularity parameter to rise from the first target popularity parameter to the maximum popularity parameter and then fall back to the last target popularity parameter; and use the time corresponding to the target popularity parameter and the duration of the popularity as the basis for determining the target recommended time.

[0061] In some embodiments, the controller 250 is further configured to: obtain a region identifier before obtaining the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms;

[0062] The controller 250, which obtains the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms, is configured to: obtain the search terms for the event corresponding to the region identifier, the search topics corresponding to the search terms, and the first sorting information of the search terms based on the region identifier.

[0063] In some embodiments, the type of search topic corresponding to the search term includes at least one of the following: movies, TV series, shopping, games, songs, advertisements, variety shows, and articles;

[0064] The controller 250, based on the first sorting information and the search topics corresponding to the search terms, determines the preferred search topics for the event, and is configured to: classify according to the type of the search topics corresponding to the search terms; and for the classified search topics, determine the preferred search topics for the event under different types.

[0065] Figure 4 This is a schematic diagram of the software configuration in the server provided in an embodiment of this disclosure, such as... Figure 4 As shown, the system is divided into four layers, from top to bottom: the Applications layer (referred to as the "Application Layer"), the Application Framework layer (referred to as the "Framework Layer"), the Android runtime and system library layer (referred to as the "System Runtime Library Layer"), and the kernel layer. The kernel layer contains at least one of the following drivers: audio driver, display driver, Bluetooth driver, camera driver, Wi-Fi driver, Universal Serial Bus (USB) driver, High Definition Multimedia Interface (HDMI) driver, sensor driver (such as fingerprint sensor, temperature sensor, pressure sensor, etc.), and power driver.

[0066] The method for pushing recommended content provided in this disclosure can be implemented using computer devices, including but not limited to servers, personal computers, laptops, tablets, smartphones, and in-vehicle devices. Computer devices include user devices and network devices. User devices include, but are not limited to, computers, smartphones, and tablets; network devices include, but are not limited to, a single network server, a server group consisting of multiple network servers, or a cloud computing system composed of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. The computer device can operate independently to implement this disclosure, or it can connect to a network and implement this disclosure through interaction with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the Internet, wide area networks, metropolitan area networks, local area networks, and virtual private networks (VPNs).

[0067] It should be noted that the scope of protection of the method for pushing recommended content according to the present disclosure is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting or replacing steps in the prior art based on the principles of this disclosure is included within the scope of protection of this disclosure.

[0068] like Figure 5 As shown, Figure 5 This is a flowchart illustrating a method for pushing recommended content provided in an embodiment of this disclosure. The method includes the following steps S501~S504:

[0069] S501. Obtain the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms.

[0070] The search terms corresponding to these search topics can be categorized into different types, such as movies, TV series, songs, shopping, advertisements, games, variety shows, and articles, which are not limited in this disclosure. It should be noted that some search terms may have no specific topic. This disclosure does not process search terms without a topic, and this will not be elaborated upon here.

[0071] In some embodiments, the server periodically triggers a task to obtain the search terms for the event, the search topics corresponding to the search terms, and the first ranking information of the search terms, such as... Figure 6 As shown, Figure 6 This is an illustration of the search terms provided in the embodiments of this disclosure. Figure 1For example, the server obtains search terms related to the event "Christmas," the corresponding search topics, and the top ranking information of the search terms based on Google Trends. Google Trends is a Google search product that analyzes billions of Google search results globally to inform users about the frequency and related statistics of a particular search keyword on Google over a given period. It should be noted that this disclosure does not specifically limit the source of the search terms, the corresponding search topics, and the top ranking information for the event.

[0072] In some embodiments, the server obtains a region identifier, which is used to identify the geographical location of the terminal. Based on the region identifier, the server obtains search terms for the events corresponding to that region identifier, the search topics corresponding to those search terms, and the first ranking information for the search terms.

[0073] For example, if the server obtains the region identifier as "Canada", then the result will be as follows: Figure 6 The search terms for the event "Christmas", the corresponding search topics, and the first ranking information of the search terms are shown; if the region identifier obtained by the server is "Japan", then as follows: Figure 7 As shown, Figure 7 This is an illustration of the search terms provided in the embodiments of this disclosure. Figure 2 This yields search terms related to "Christmas" in Japan, the corresponding search topics, and the top ranking of the search terms.

[0074] The server obtains different search terms, corresponding search topics, and the first ranking information of the search terms based on different region identifiers, and then pushes different recommended content to different regions accordingly, such as... Figure 8 As shown, Figure 8 This is a schematic diagram of obtaining a region identifier provided in an embodiment of this disclosure. In the diagram, server 400 obtains the region identifier "Japan" uploaded by terminal 201, and after performing subsequent steps, obtains target recommendation content 1 for "Japan" and sends it to terminal 201; server 400 obtains the region identifier "Canada" uploaded by terminal 202, and after performing subsequent steps, obtains target recommendation content 2 for "Canada" and sends it to terminal 202.

[0075] It should be noted that the search terms correspond to multi-level search topics, which can be divided into primary search topics and secondary search topics. Secondary search topics refer to topics at other levels besides the primary search topics, such as second-level search topics, third-level search topics, etc. Figure 6The search topic shown in Figure 7 can be understood as the primary search topic for the event "Christmas". Regarding secondary search topics, for example, the primary search topic "Q_superset_8" includes multiple secondary search topics: Django being rescued, Kill Bill, etc. The relevance of secondary search topics to the event is less than that of the primary search topic.

[0076] Search terms can be divided into primary search terms and secondary search terms. The primary search term corresponds to the first-level search topic, and the secondary search term corresponds to the second-level search topic. The first ranking information includes the first sub-ranking information of the primary search term and the second sub-ranking information of the secondary search term. Although secondary search topics have a lower relevance to the event, they need to be considered to enrich the target recommendation content.

[0077] In some embodiments, the search terms are obtained by acquiring the first-level search topic, the second-level search topic, and the third-level search topic, thereby accurately and comprehensively obtaining the topics related to the search terms and meeting the needs of determining recommended content.

[0078] S502. Determine the preferred search topic for the event based on the first sorting information and the search topic corresponding to the search term.

[0079] The number of preferred search topics can be one or more.

[0080] In some embodiments, search topics are categorized according to different search topic types, and then, for the same type of search topic, the preferred search topic for events under that type is determined based on the first ranking information of the search terms.

[0081] For example, the search topics corresponding to the search terms obtained in step S201 are categorized according to search topic types such as movies, TV series, songs, shopping, and advertisements, in order to... Figure 7 For example, search terms are divided into two categories: songs and no topic. The search topic type includes search terms such as "Happy Merry Christmas", "We wish you a Merry Christmas" and "Kissin' Christmas", and further calculates the preferred search topic for events under the "song" type. In some embodiments, the server calculates the preference value of the search topic corresponding to each search term according to the following formula (1):

[0082] (1)

[0083] Where p represents the preference value of the search topic corresponding to the search term; rank represents the index of the search term in the first ranking information; i is 0 or 1, i=1 when the search topic belongs to the category topic, and i=0 when the search topic does not belong to the category topic; N is the level of the search topic.

[0084] It should be noted that, in determining whether a search topic belongs to a category, this disclosure compares the search topic with the category. If the search topic contains keywords from the category, it is determined that the search topic belongs to the category. (Refer to...) Figure 6 As shown, the search term "Q Superset 8" corresponds to the search topic "movies of 2020," which contains the keyword "movie" from the category topic "movies." Therefore, it can be determined that the search topic "movies of 2020" belongs to the category topic. When the search topic does not contain the keyword of the category topic, different descriptions exist for the same category topic. This disclosure provides an implementation method where the server pre-sets a thesaurus of category topics and establishes a correspondence between synonymous category topics. For example, the synonymous category topic for the category topic "movies" could be "film," etc., and this disclosure does not limit this.

[0085] According to formula (1), for each search topic, the server first determines the first sub-sorting information rank_1 of the first search term corresponding to the first-level search topic, then determines whether the search topic belongs to the category topic, and then obtains the first preference value of the first-level search topic.

[0086] For example, refer to Figure 6 As shown, for the category topic "movies", the first sub-ranking information rank_1 of the first search term corresponding to the first-level search topic is: 1, 2, 3, 4, 5. All search topics in the figure belong to the category topic. Therefore, the first preference value of the first-level search topic is 1 / 1+1 / 2+1 / 3+1 / 4+1 / 5.

[0087] After calculating the first preference value of the primary search topic, the second preference value of the secondary search topic is determined according to the second sub-sorting information of the secondary search topic based on formula (1). It should be noted that the secondary search topic is not highly relevant to the event itself. In this embodiment, the preferred search topic can be determined directly based on the first preference value of the primary search topic to identify the search terms with the highest relevance to the event, thereby obtaining accurate recommended content. The total preference value of the search topic corresponding to the search term can also be calculated based on the first and second preference values. If the total preference value is greater than a preset threshold, the search topic is determined as the preferred search topic. The preferred search topic is determined by combining the primary search topic and the secondary search topic, thereby determining richer target recommended content. The preset threshold can be set to 1.

[0088] S503. Based on the preferred search topic, determine the target search term from the search terms; determine the target recommended content corresponding to the target search term.

[0089] In some embodiments, search terms corresponding to preferred search topics are identified as target search terms. These target search terms are then segmented into multiple search terms. Based on these multiple search terms, target recommended keywords are obtained by matching them against a database. The database stores multiple recommended keywords, with different recommended keywords corresponding to different recommended content. Further, the content to be recommended corresponding to the target recommended keywords is determined.

[0090] For example, refer to Figure 6 As shown, the target search terms include: "Q's Super Set 8", "Saving Christmas Diary", "Bad Mom's Christmas", "Film Set Construction", "Last Christmas". After word segmentation, the search terms are: "Q", "Super Set", "8"; "Saving", "Christmas", "Diary"; "Bad", "Mom", "Christmas Day"; "Film", "Set Construction"; "Last Year", "Christmas Day". Then, based on these multiple search terms, the target recommended keywords are matched from the database: "Q", "Christmas", "Movie". The recommended keyword "Q" in the database corresponds to multiple recommended content, such as "Q's representative works", "Movies directed by Q", "Q's news", etc. The recommended content corresponding to "Christmas" can be: "Christmas gifts", "Christmas movies", "Christmas recipes", "Christmas decorations", etc.

[0091] After determining the content to be recommended corresponding to the target recommendation keyword, it is not directly sent to the terminal to push to the user. It is also necessary to filter the content to be recommended to obtain the final target recommendation content. This disclosure provides an implementation method that determines the weight vector of each target recommendation keyword according to the position information of the target recommendation entry in the first sorting information, and then calculates the similarity between the target recommendation keyword and the content to be recommended according to the weight vector of the target recommendation keyword and the weight vector of the content to be recommended, as shown in formula (2):

[0092] (2)

[0093] in, A is the weight vector of the target recommended keywords, B is the weight vector of the content to be recommended, and n is the number of target recommended keywords.

[0094] If the similarity is greater than the similarity threshold, the content to be recommended is determined as the target recommended content.

[0095] This disclosure provides another implementation method: after determining the target recommended terms, the target recommended terms are reordered to determine the second ranking information of the target recommended terms. For each target recommended keyword, its position information in the second ranking information is determined as a weight vector. Then, the similarity between the target recommended keyword and the content to be recommended is calculated based on the weight vector and the weight vector of the content to be recommended. If the similarity is greater than the similarity threshold, the content to be recommended is determined as the target recommended content.

[0096] In some embodiments, the proportion of content to be recommended that is greater than a similarity threshold in the target recommended content can also be determined based on the similarity value, thereby quantifying the target recommended content and enabling more content to be recommended that is highly similar and of greater interest to the user to be pushed to the terminal.

[0097] S504: Send the target recommended content to the terminal.

[0098] In some embodiments, in order to accurately determine the timing of recommending content of interest to users, this disclosure provides an implementation method for determining the target recommendation time: First, obtain the historical search preference information of the event, which includes the popularity parameter of the event within a historical time period. The popularity parameter of the event within a historical time period refers to the popularity parameter of the event at each moment within the historical time period. The popularity parameter is obtained through statistical analysis based on user clicks, discussion volume, number of comments, etc., which will not be elaborated upon in this disclosure.

[0099] For example, Figure 9 This is a schematic diagram of the heat parameters of an event within a historical time period provided in an embodiment of this disclosure. The heat parameters are different at different times in the diagram.

[0100] Then, the target recommendation time is determined based on the popularity parameters of the event within the historical time period, and the target recommendation time is sent to the terminal so that the terminal can push the target recommendation content according to the target recommendation time.

[0101] In determining the target recommendation time based on the event's popularity parameters over a historical period, optionally, a target popularity parameter can be determined based on the event's popularity parameters over the historical period. If the target popularity parameter is greater than or equal to a preset popularity threshold, the time corresponding to the target popularity parameter is then used as the target recommendation time. It is important to emphasize that there are often multiple times within the historical period where the popularity parameter is greater than or equal to the preset popularity threshold; therefore, the time that occurs most frequently can be identified as the target recommendation time.

[0102] For example, refer to Figure 9As shown, the preset popularity threshold is set to 25%. After obtaining the popularity parameters of "Christmas" over the past five years, the time period with a popularity parameter greater than 25% is determined. If the period with a popularity parameter greater than 25% is from December 11th to January 1st, then December 11th is selected as the target recommendation time. If the period with a popularity parameter greater than 25% over the past five years is December 11th to January 1st, December 10th to January 1st, December 10th to January 1st, December 11th to January 1st, and December 11th to January 1st, and the period with the most occurrences is December 11th to January 1st, then December 11th to January 1st is selected as the target recommendation time.

[0103] Since the popularity parameters of an event are constantly changing over a historical period, this disclosure provides an implementation method to maximize the recommendation effect by pushing recommended content during the peak of the event's development. After determining the target popularity parameter, the duration of the event's popularity is determined based on the popularity parameters within the historical event period. This duration is defined as the time it takes for the event's popularity parameter to first rise from the target parameter to the maximum popularity parameter and then fall back to the last target popularity parameter. Then, the target recommendation time is determined based on the time corresponding to the target popularity parameter and the popularity duration.

[0104] For example, after obtaining the popularity parameters of "Christmas" in the past five years, the times when the target popularity parameter was first reached in the past five years were determined to be December 11, December 10, December 10, December 11, and December 11, respectively, and the duration of popularity in the past five years was determined to be 21 days, 22 days, 22 days, 21 days, and 21 days, respectively. Then the target recommendation time is determined to be December 11 and the 21 days after December 11.

[0105] The above embodiments determine the target recommendation time by using the popularity parameter of the event within a historical time period, so that the terminal can push the target recommendation content according to the target recommendation time, thereby accurately grasping the push timing, automatically triggering the push of the target recommendation content, improving push efficiency, and significantly improving the recommendation effect.

[0106] In summary, this disclosure provides a method for pushing recommended content, applied to a server. First, the server obtains search terms for an event, the corresponding search topics, and the first ranking information of the search terms. Then, based on the search topics and the first ranking information, it determines the preferred search topic for the time. Next, based on the preferred search topic, it identifies the target search term from the search terms and the corresponding target recommended content, and then sends this target recommended content to the terminal. By accurately locating the user's preferred search topic based on the search topics and the first ranking information of the search terms, and then determining the target search term based on the preferred search topic, and finally obtaining the corresponding target recommended content based on the target search term and sending it to the terminal, the terminal can push the target recommended content, thereby accurately recommending content of interest to the user and improving the recommendation effect and user experience.

[0107] In addition, this disclosure also obtains the popularity parameters of events within a historical time period, and then analyzes and uses the time corresponding to the target popularity parameter that is greater than or equal to the preset popularity threshold as the target push time to realize automated push recommendation content. The push time is reasonable and can improve the recommendation effect.

[0108] Figure 10 This is a schematic diagram of the structure of a server provided in an embodiment of the present disclosure, such as... Figure 10 As shown, the server includes a processor 1001, a memory 1002, and a computer program stored in the memory 1002 and executable on the processor 1001. When the computer program is executed by the processor 1001, it implements the various processes of the recommended content push method in the above method embodiments. Furthermore, it achieves the same technical effect, and to avoid repetition, it will not be described again here.

[0109] This disclosure provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the recommended content push method described in the above method embodiments and achieves the same technical effect. To avoid repetition, further details are omitted here.

[0110] The computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0111] This disclosure provides a computer program product that stores a computer program. When the computer program is executed by a processor, it implements the various processes of the recommended content push method in the above-described method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0112] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media containing computer-usable program code.

[0113] In this disclosure, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0114] In this disclosure, memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0115] In this disclosure, computer-readable media includes both permanent and non-permanent, removable and non-removable storage media. Storage media can store information using any method or technology; the information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient media, such as modulated data signals and carrier waves.

[0116] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0117] The above are merely specific embodiments of this disclosure, enabling those skilled in the art to understand or implement this disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A server, characterized in that, include: The controller is configured to: acquire the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms; The search terms include a first search term corresponding to a primary search topic and a second search term corresponding to a secondary search topic; wherein, the secondary search topic is a search topic at other levels besides the primary search topic; the first sorting information includes a first sub-sorting information corresponding to the first search term and a second sub-sorting information corresponding to the second search term; Based on the first sorting information and the search topic corresponding to the search term, determine the preferred search topic for the event; Obtain the historical search preference information of the event, which includes the popularity parameter of the event within a historical time period; The target recommendation time is determined based on the popularity parameters of the event within a historical time period; Based on the preferred search topic, determine the target search term from the search terms; determine the target recommended content corresponding to the target search term; The target recommendation time and the target recommendation content are sent to the terminal so that the terminal can push the target recommendation content according to the target recommendation time; The controller, based on the first sorting information and the search topic corresponding to the search term, determines the preferred search topic of the event, and is configured to: determine a first preference value of the first-level search topic based on the first sub-sorting information; determine a second preference value of the second-level search topic based on the second sub-sorting information; calculate a total preference value of the search topics corresponding to the search term based on the first preference value and the second preference value; and determine the preferred search topic from the search topics corresponding to the search term based on the total preference value.

2. The server according to claim 1, characterized in that, The controller, which determines the target recommended content corresponding to the target search term, is configured as follows: The target search term is segmented to obtain multiple search terms; Based on the multiple search terms, target recommended keywords are obtained by matching them from the database. The database stores multiple recommended keywords, and different recommended keywords correspond to different recommended content. Determine the target recommended content corresponding to the target recommended keywords.

3. The server according to claim 2, characterized in that, The controller, which determines the target recommended content corresponding to the target recommended keyword, is configured as follows: The content to be recommended is determined based on the target recommended keywords; After determining the second ranking information of the target search term, the similarity between the target recommended keyword and the content to be recommended is calculated based on the second ranking information; The target recommended content is determined from the content to be recommended based on the similarity.

4. The server according to claim 1, characterized in that, The controller, which determines the target recommendation time based on the popularity parameters of the event within a historical time period, is configured as follows: Based on the heat parameters of the event within a historical time period, a target heat parameter is determined, wherein the target heat parameter is greater than or equal to a preset heat threshold. The time corresponding to the target popularity parameter is used as the target recommendation time.

5. The server according to claim 4, characterized in that, The controller, after determining the target popularity parameter based on the popularity parameters of the event within a historical time period, is further configured as follows: Determine the duration of the event's popularity, which is the time it takes for the popularity parameter to rise from the initial target popularity parameter to the maximum popularity parameter and then drop back to the last target popularity parameter; The target recommended time is determined based on the time corresponding to the target popularity parameter and the duration of the popularity.

6. The server according to claim 1, characterized in that, Before acquiring the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms, the controller is further configured as follows: Obtain the region identifier; The controller, which acquires the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms, is configured as follows: Based on the region identifier, obtain the search terms for the event corresponding to the region identifier, the search topics corresponding to the search terms, and the first sorting information of the search terms.

7. The server according to claim 1, characterized in that, The search terms correspond to search topics that include at least one of the following: movies, TV series, shopping, games, songs, advertisements, variety shows, and articles; The controller, based on the first sorting information and the search topic corresponding to the search term, determines the preferred search topic for the event, which is configured as follows: Categorize according to the type of search topic corresponding to the search terms; For the categorized search topics, determine the preferred search topics for the events under different types.

8. A method for pushing recommended content, characterized in that, include: Obtain the search terms for the event, the search topics corresponding to the search terms, and the first sorting information of the search terms; The search terms include a first search term corresponding to a primary search topic and a second search term corresponding to a secondary search topic; wherein, the secondary search topic is a search topic at other levels besides the primary search topic; the first sorting information includes a first sub-sorting information corresponding to the first search term and a second sub-sorting information corresponding to the second search term; Based on the first sorting information and the search topic corresponding to the search term, determine the preferred search topic for the event; Obtain the historical search preference information of the event, which includes the popularity parameter of the event within a historical time period; The target recommendation time is determined based on the popularity parameters of the event within a historical time period; Based on the preferred search topic, determine the target search term from the search terms; determine the target recommended content corresponding to the target search term; The target recommendation time and the target recommendation content are sent to the terminal so that the terminal can push the target recommendation content according to the target recommendation time; The step of determining the preferred search topic of the event based on the first sorting information and the search topic corresponding to the search term includes: determining a first preference value of the primary search topic based on the first sub-sorting information; determining a second preference value of the secondary search topic based on the second sub-sorting information; calculating a total preference value of the search topics corresponding to the search term based on the first preference value and the second preference value; and determining the preferred search topic from the search topics corresponding to the search term based on the total preference value.

Images