A server and a search word recommendation method

Abstract

The application provides a server and a search word recommendation method. The method comprises the following steps: receiving a page data request sent by a display device, determining historical search words and popular words in response to the page data request; receiving a query request for querying repeated words sent by the display device, determining repeated words of the historical search words and the popular words and associated media asset identification codes associated with the repeated words in response to the query request; obtaining a tag set corresponding to the associated media asset identification codes, and replacing the repeated words in the historical search words with associated words of different repeated words in the tag set to obtain replaced historical search words, or replacing the repeated words in the popular words with the associated words to obtain replaced popular words; and feeding back the replaced historical search words and / or the replaced popular words to the display device. The method can replace the repeated words, recommend associated words associated with the repeated words to the user, and solve the problems of poor diversity and high repetition rate of the recommended search words.

Description

Technical Field

[0001] This application relates to the field of server technology, and in particular to a method for recommending servers and search terms. Background Technology

[0002] Smart TVs and other display devices can recommend movies, TV series, and other media resources to users. When a user turns on the TV and accesses the search function, if the user wants to watch or search for a specific media resource, the TV will present an initial search page. The initial search page aims to provide users with a convenient entry point for information retrieval. Users can quickly locate media resources of interest by entering the first letter or full spelling, or by clicking on search terms provided on the initial search page.

[0003] Currently, the search terms displayed on the initial search page mainly include users' historical search terms and current trending terms. Historical search terms are based on individual user search behavior and reflect their personalized interests and preferences, while trending terms represent hot topics of common interest to a broad user base. For example, trending terms can be used to recommend media resources that are currently attracting attention or are playing frequently. However, the number of both types of search terms displayed on the initial search page is limited to maintain the page's simplicity and focus. If independent recommendation logic were used for the two types of search terms, duplicate terms might occur.

[0004] In other words, since the recommendation logics for the two types of search terms are independent of each other, they are likely to select some of the same popular or high-frequency words in their respective recommendation processes. This will reduce the number of unique words in the two types of search terms, resulting in the appearance of two completely or partially identical search terms on the initial search page, which will affect the user experience. Summary of the Invention

[0005] Some embodiments of this application provide a method for recommending servers and search terms to solve the problems of poor diversity and high repetition rate of recommended search terms in the initial search page.

[0006] In a first aspect, some embodiments of this application provide a server, including:

[0007] The communication module is configured to establish a communication connection with the display device;

[0008] The control module is configured as follows:

[0009] Receive page data requests sent by the display device, and in response to the page data requests, determine historical search terms and popular terms;

[0010] The system receives a query request from the display device for querying duplicate words, and in response to the query request, determines the duplicate words between the historical search words and the popular words, as well as the associated media asset identifier code associated with the duplicate words.

[0011] Obtain the tag set corresponding to the associated media asset identifier code, and replace the repeated words in the historical search terms with the associated words of different repeated words in the tag set to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

[0012] The replaced historical search terms and / or replaced popular terms are fed back to the display device, so that the display device responds to the page data request and controls the display to show the initial search page based on the replaced historical search terms and / or replaced popular terms.

[0013] The above technical solution has the following advantages or beneficial effects: by replacing duplicate words, the server can recommend related words associated with the duplicate words to users, thus solving the problem of poor diversity and high repetition rate of the search terms recommended on the initial search page.

[0014] In some embodiments, the control module determines duplicate words between the historical search terms and the popular terms, specifically configured as follows:

[0015] Obtain a first quantity corresponding to the historical search terms and a second quantity corresponding to the popular terms; the first quantity is less than the second quantity; the popular terms are sorted in descending order of media asset recommendation popularity;

[0016] Identify words that exist in the historical search terms and also in the popular terms to generate the duplicate terms.

[0017] The above technical solution has the following advantages or beneficial effects: the number of historical search terms is usually less than the number of popular terms. Therefore, finding terms that match a larger dataset (second set) within a smaller dataset (first set) reduces the number of comparisons, thereby improving search efficiency. By identifying and recording duplicate terms and their associated media asset identifiers, users can avoid seeing too many duplicate or irrelevant media assets on the initial search page, and this also facilitates the replacement of duplicate terms in subsequent steps.

[0018] In some embodiments, the control module replaces the repeated words in the historical search terms with related words of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms, specifically configured as follows:

[0019] Identify the target individuals associated with the associated media asset identifiers in the associated vocabulary;

[0020] When the associated words are associated with the target person, determine the name of the target person corresponding to the target person;

[0021] Replace the repeated words in the historical search terms with the target person's name to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

[0022] The above technical solution has the following advantages or beneficial effects: replacing duplicate words with the target person's name can attract users' attention, thereby increasing the likelihood of users clicking on the replaced words and thus improving the click-through rate. Replacing duplicate words with the target person's name takes into account users' personal preferences, making the search results closer to users' personal interests. At the same time, it can reduce redundant information in the search results, allowing users to see more diverse media resources, thereby solving the problem of poor diversity and high repetition rate of recommended search terms on the initial search page.

[0023] In some embodiments, the control module replaces the repeated words in the historical search terms with related words of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms, specifically configured as follows:

[0024] If the target person associated with the associated media asset identifier code does not exist in the associated vocabulary, the associated media asset associated with the associated media asset identifier code in the associated vocabulary is identified; the associated media asset is a series or derivative series of media assets corresponding to the associated media asset identifier code.

[0025] When the associated words are associated with the associated media assets, extract the associated words corresponding to the associated media assets;

[0026] Replace the repeated words in the historical search terms with the associated terms to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

[0027] The above technical solution has the following advantages or beneficial effects: by replacing repeated words with other relevant words in the series or derivative works, it takes into account the user's possible interest in the entire series or derivative works, rather than just a single media asset. By replacing repeated popular words, redundant information in search results can be reduced, thereby improving the diversity of recommended search terms.

[0028] In some embodiments, the control module replaces the repeated words in the historical search terms with related words of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms, specifically configured as follows:

[0029] If there is no target person associated with the associated media asset identifier code in the associated vocabulary and no associated media asset is associated with the associated media asset identifier code, then identify similar media assets associated with the associated media asset identifier code in the associated vocabulary.

[0030] When the associated words are associated with similar media assets, extract the similar words corresponding to the similar media assets;

[0031] Replace the repeated words in the historical search terms with the similar words to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

[0032] The above technical solution has the following advantages or beneficial effects: by replacing repeated words with other relevant words from similar works, it considers the user's potential interest in a specific theme, rather than just a single media asset, thus providing a personalized search experience. Replacing repeated popular words reduces redundant information in search results, thereby improving the diversity of recommended search terms.

[0033] In some embodiments, the control module is further configured to: prior to the step of determining historical search terms.

[0034] The display device receives historical search terms sent by the display device, which are generated by the display device according to the following steps: the display device obtains the search letters input by the user based on user information, and generates related words corresponding to the search letters; in response to the user's selection instruction for a target related word in the related words, the display device generates media asset results corresponding to the target related word; in response to the user's confirmation instruction for a target media asset result in the media asset results, the display device generates the historical search terms based on the name of the target media asset result.

[0035] The above technical solution has the following advantages or beneficial effects: By generating related keywords associated with the search letters, it can help users find the media assets they want more quickly, reducing the step of users entering complete search terms. By recording user choices and saving the names of target media asset results as historical search terms, it helps to better learn user search habits, thereby optimizing search recommendations and improving the efficiency and accuracy of media asset searches.

[0036] In some embodiments, the control module determines historical search terms, specifically configured as follows:

[0037] Retrieve historical search terms associated with the user information;

[0038] Obtain the media asset query time corresponding to the historical search terms; the media asset query time is the time when the target media asset result corresponding to the historical search terms is determined based on the historical search terms;

[0039] The historical search terms are sorted in descending order according to the media asset query time to obtain the historical search terms in descending order.

[0040] The historical search terms are output based on the historical search terms sorted in descending order.

[0041] The above technical solution has the following advantages or beneficial effects: the historical search terms entered by the user when searching for media assets are an ordered set, which includes the terms that the user has searched in the past, and these terms are sorted according to the time of the query. Based on the historical search terms entered by the user when searching for media assets, it can be used for functions such as personalized recommendation, search optimization, and user behavior analysis, and provide a data foundation for subsequent search term recommendations.

[0042] In some embodiments, the control module is further configured to: Before determining the popular keywords step, the control module is also configured to:

[0043] Obtain the dimensional information of the media asset; the dimensional information includes at least the title and media asset identifier code of the media asset;

[0044] Media asset association terms are generated based on the dimensional information; the media asset association terms are words generated after extracting the media asset according to the title.

[0045] Obtain the list of media assets associated with the media asset association terms, and determine the highest media asset popularity value and target media asset identifier code corresponding to the target media asset with the highest media asset popularity value in the list.

[0046] The above technical solution has the following advantages or beneficial effects: by obtaining the list of media assets associated with media asset related terms, the user's search scope can be expanded, providing the user with more potentially related media asset options. By identifying the target media asset with the highest media asset popularity value and recording its highest media asset popularity value and target media asset identification code, it is helpful to recommend the most popular and relevant media assets to the user, which can not only improve the efficiency of media asset search, but also enhance the accuracy of personalized recommendations.

[0047] In some embodiments, the control module determines popular keywords, specifically configured as follows:

[0048] Calculate the search popularity value of the associated media asset terms;

[0049] Assign a first weight to the highest media asset popularity value and a second weight to the search popularity value;

[0050] The comprehensive popularity value of the media asset associated terms is calculated based on the highest media asset popularity value, the first weight, the search popularity value, and the second weight;

[0051] The media asset association terms are sorted in descending order according to the overall popularity value.

[0052] Popular keywords are generated based on the results sorted in descending order.

[0053] The above technical solution has the following advantages or beneficial effects: The server can sort media asset-related keywords in descending order based on the calculated comprehensive popularity value. By sorting in descending order, the most popular words can be placed at the top, forming hot keywords. By recording hot keywords and their corresponding media asset identifiers, relevant media assets can be quickly located. Then, hot keywords can be generated based on the hot keywords and their corresponding media asset identifiers, providing a data foundation for subsequent search term recommendations.

[0054] Secondly, some embodiments of this application provide a method for recommending search terms, the method comprising:

[0055] Receive page data requests sent by the display device, and in response to the page data requests, determine historical search terms and popular terms;

[0056] The system receives a query request from the display device for querying duplicate words, and in response to the query request, determines the duplicate words between the historical search words and the popular words, as well as the associated media asset identifier code associated with the duplicate words.

[0057] Obtain the tag set corresponding to the associated media asset identifier code, and replace the repeated words in the historical search terms with the associated words of different repeated words in the tag set to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

[0058] The replaced historical search terms and / or replaced popular terms are fed back to the display device, so that the display device responds to the page data request and controls the display to show the initial search page based on the replaced historical search terms and / or replaced popular terms.

[0059] The above technical solution has the following advantages or beneficial effects: by replacing duplicate words, the server recommends related words associated with the duplicate words to users, thus solving the problem of poor diversity and high repetition rate of the search terms recommended on the initial search page.

[0060] As can be seen from the above technical solutions, some embodiments of this application provide a server and a method for recommending search terms. The method includes: receiving a page data request sent by a display device; in response to the page data request, determining historical search terms and popular terms; receiving a query request sent by the display device for querying duplicate terms; in response to the query request, determining duplicate terms between historical search terms and popular terms, as well as associated media asset identifiers associated with the duplicate terms; obtaining a tag set corresponding to the associated media asset identifiers, and replacing the duplicate terms in the historical search terms with associated terms of different duplicate terms in the tag set to obtain the replaced historical search terms, or replacing the duplicate terms in the popular terms to obtain the replaced popular terms; and feeding back the replaced historical search terms and / or the replaced popular terms to the display device, so that the display device responds to the page data request and controls the display to display an initial search page based on the replaced historical search terms and / or the replaced popular terms. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in some embodiments of this application or in the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a schematic diagram illustrating an operational scenario between a display device and a control device provided in some embodiments of this application;

[0063] Figure 2 This is a schematic diagram illustrating a scenario where a display device presents an initial search page, as shown in some embodiments of this application.

[0064] Figure 3 This is a schematic diagram illustrating a scenario in a first application where historical search terms and popular terms overlap, as shown in some embodiments of this application.

[0065] Figure 4 This is a schematic diagram illustrating a scenario where historical search terms and popular terms overlap in a second application, as shown in some embodiments of this application.

[0066] Figure 5 This is a schematic diagram illustrating a scenario in a third application where historical search terms and popular terms overlap, as shown in some embodiments of this application.

[0067] Figure 6 A schematic flowchart illustrating a server-side method for recommending search terms, provided in some embodiments of this application;

[0068] Figure 7A schematic diagram illustrating a scenario where a display device generates historical search terms according to some embodiments of this application;

[0069] Figure 8 A timing diagram illustrating a server-side method for recommending search terms, provided in some embodiments of this application;

[0070] Figure 9 This is a schematic diagram illustrating a scenario where a server determines the highest media asset popularity value and the target media asset identifier code corresponding to the target media asset with the highest media asset popularity value, as provided in some embodiments of this application.

[0071] Figure 10 This is a schematic diagram illustrating a scenario where historical search terms and popular terms do not overlap, as provided in some embodiments of this application. Detailed Implementation

[0072] The embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described below do not represent all embodiments consistent with this application. They are merely examples of systems and methods consistent with some aspects of this application as detailed in the claims.

[0073] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.

[0074] The terms "first," "second," "third," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar or related objects or entities, and do not necessarily imply a specific order or sequence, unless otherwise specified. It should be understood that such terms are interchangeable where appropriate.

[0075] The terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device that includes a range of components is not necessarily limited to all of the components that are clearly listed, but may include other components that are not clearly listed or that are inherent to such product or device.

[0076] The term "module" refers to any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0077] In this embodiment, the display device 200 generally refers to a device with screen display and data processing capabilities. For example, the display device 200 includes, but is not limited to, smart TVs, mobile terminals, computers, monitors, advertising screens, wearable devices, virtual reality devices, augmented reality devices, etc.

[0078] Figure 1 This is a schematic diagram illustrating an operational scenario between a display device and a control device provided in some embodiments of this application. For example... Figure 1 As shown, a user can operate the display device 200 via touch operation, a mobile terminal 300, and a control device 100. The control device 100 receives user input commands and converts them into control commands that the display device 200 can recognize and respond to. For example, the control device 100 can be a remote control, a stylus, a gamepad, etc.

[0079] The mobile terminal 300 can function as a control device for human-computer interaction between the user and the display device 200. It can also function as a communication device for establishing a communication connection with the display device 200 and exchanging data. In some embodiments, the mobile terminal 300 can have software applications installed on it and communicate with the display device 200 via network communication protocols to achieve one-to-one control and data communication. Furthermore, it can transmit audio and video content displayed on the mobile terminal 300 to the display device 200 for synchronized display.

[0080] In some embodiments, the mobile terminal 300 or other electronic devices may also simulate the functions of the control device 100 by running an application that controls the display device 200.

[0081] like Figure 1 The diagram also shows that the display device 200 communicates with the server 400 via various communication methods. This allows the display device 200 to communicate via a local area network (LAN), a wireless local area network (WLAN), and other networks.

[0082] Display device 200 can provide broadcast television reception function, and can also be equipped with intelligent network television function that provides computer support, including but not limited to network television, smart television, Internet Protocol television (IPTV), etc.

[0083] In some embodiments, the display device 200 may include at least one of a tuner 210, a communication device 220, a detector 230, a device interface 240, a controller 250, a display 260, an audio output device 270, a memory, a power supply, and a user input interface.

[0084] In some embodiments, detector 230 is used to acquire signals from the external environment or to interact with the outside world. For example, detector 230 includes a light receiver, a sensor for acquiring ambient light intensity; or, detector 230 includes an image acquisition device, such as a camera, which can be used to acquire external environmental scenes, user attributes, or user interaction gestures; or, detector 230 includes a sound acquisition device, such as a microphone, for receiving external sounds.

[0085] In some embodiments, the display 260 includes display function components for presenting images and driving components for driving image display. The display 260 is used to receive and display image signals output from the controller 250. For example, the display 260 can be used to display video content, image content, menu control interface components, and user control UI interfaces, etc.

[0086] In some embodiments, the communication device 220 is a component used to communicate with external devices or the server 400 according to various communication protocol types. The display device 200 may have multiple communication devices 220 depending on the supported communication methods. For example, when the display device 200 supports wireless network communication, it may have a communication device 220 with WiFi functionality. When the display device 200 supports Bluetooth connectivity, it needs to have a communication device 220 with Bluetooth functionality.

[0087] The communication device 220 enables the display device 200 to communicate with external devices or the server 400 via wireless or wired connections. Wired connections utilize data cables, interfaces, or other components to connect the display device 200 to external devices. Wireless connections utilize wireless signals or wireless networks. The display device 200 can directly establish a connection with external devices or indirectly through gateways, routers, or other connection devices.

[0088] In some embodiments, the controller 250 may include at least one of a central processing unit, a video processor, an audio processor, a graphics processor, and a power processor, and a first to an nth interface for input / output. 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.

[0089] In some embodiments, the controller 250 and the tuner 210 may be located in different separate devices, that is, the tuner 210 may also be located in an external device of the main device where the controller 250 is located, such as an external set-top box.

[0090] In some embodiments, a user can input user commands through a graphical user interface (GUI) displayed on a display 260, and the user input interface receives user input commands through the graphical user interface (GUI).

[0091] In some embodiments, the audio output device 270 can be a built-in speaker of the display device 200 or an external audio output device connected to the display device 200. For the external audio output device connected to the display device 200, the display device 200 may also be provided with an external audio output terminal, through which the audio output device can be connected to the display device 200 to output sound from the display device 200.

[0092] In some embodiments, the user input interface 280 can be used to receive instructions from user input.

[0093] To enable user interaction, in some embodiments, the display device 200 may run an operating system. The operating system is a computer program used to manage and control the hardware and software resources of the display device 200. The operating system can control the display device to provide a user interface; for example, the operating system can directly control the display device to provide a user interface, or it can provide a user interface by running an application. The operating system also allows users to interact with the display device 200.

[0094] It should be noted that the operating system can be a native operating system based on a specific operating platform, a third-party operating system that is deeply customized based on a specific operating platform, or an independent operating system specifically developed for display devices.

[0095] The above examples are merely simple classifications of operating system functions and do not limit the specific form of the operating system of the display device 200 in this application embodiment. Depending on factors such as the function of the display device and the type of the operating system, the number of levels and the specific level types contained in the operating system can be expressed in other forms.

[0096] The above embodiments illustrate the hardware / software architecture and functional implementation of a display device 200. The display device 200 is an intelligent device capable of presenting a user interface and supporting user interaction. Taking a smart TV as an example, a smart TV is a display device based on Internet application technology, possessing an open operating system and chip, an open application platform, and enabling two-way human-computer interaction. A smart TV can integrate multiple functions such as audio-visual entertainment and data to meet diverse and personalized user needs. For example, users can watch various movies, TV series, variety shows, etc., through a smart TV.

[0097] Taking the recommendation of movies, TV series and other media resources by smart TVs as an example, when a user turns on the TV and enters the search function, if the user wants to watch or search for a certain media resource, the TV will present the user with an initial search page. Figure 2 This application provides schematic diagrams illustrating scenarios where a display device presents an initial search page, as shown in some embodiments. Figure 2 As shown, in some embodiments, the initial search page is designed to provide users with a convenient information retrieval entry point. Users can quickly locate media resources of interest by entering the first letter or full spelling, or by clicking on search terms provided on the initial search page.

[0098] Currently, the search terms displayed on the initial search page mainly include users' historical search terms and current trending terms. Historical search terms are based on individual user search behavior and reflect their personalized interests and preferences, while trending terms represent hot topics of common interest to a broad user base. For example, trending terms can be used to recommend media resources that are currently attracting attention or are playing frequently. However, the number of both types of search terms displayed on the initial search page is limited to maintain the page's simplicity and focus. If independent recommendation logic were used for the two types of search terms, duplicate terms might occur.

[0099] For example, Figure 3 This is a schematic diagram illustrating a scenario in a first application where historical search terms and popular terms overlap, as shown in some embodiments of this application. Figure 4 This is a schematic diagram illustrating a scenario where historical search terms and popular terms overlap in a second application, as shown in some embodiments of this application. Figure 5 This is a schematic diagram illustrating a scenario in a third application where historical search terms and popular terms overlap, as shown in some embodiments of this application. Figures 3-5 Since the historical search terms and popular terms recommendation logics are independent of each other, they may select some of the same popular or high-frequency terms in their respective filtering and sorting processes. This will result in the initial search page presenting users with a lack of diversity and richness of search terms, and there may even be cases where completely identical or partially identical terms are repeated, which will affect the user experience.

[0100] For example, Figure 3 In the first application, as shown in the dotted box in the image, there are two duplicate words between the historical search terms and the popular terms. Figure 4 In the second application, there were three repeated words in the historical search terms and popular search terms. Figure 5 In the third application, there are also 3 repeated words in the historical search terms and popular terms. As a result, the diversity of search terms recommended on the initial search page is poor and the repetition rate is high.

[0101] In other words, since the recommendation logics for the two types of search terms are independent of each other, they are likely to select some of the same popular or high-frequency words in their respective recommendation processes. This will reduce the number of unique words in the two types of search terms, resulting in the appearance of two completely or partially identical search terms on the initial search page, which will affect the user experience.

[0102] Based on the above scenario, in order to solve the problem of poor diversity of recommended search terms in the initial search page, some embodiments of this application provide a server 400, which includes a communication module 410 and a control module 420. The communication module 410 is configured to establish a communication connection with the display device 200, and the control module 420, by running an application program, enables the server 400 to execute the search term recommendation method.

[0103] To facilitate understanding of the technical solutions in some embodiments of this application, the steps are described in detail below with reference to some specific embodiments and accompanying drawings. Figure 6 This application provides a schematic flowchart of a server-side method for recommending search terms, as illustrated in some embodiments. Figure 6 As shown, in some embodiments, when the server 400 performs the search term recommendation method, it may include the following steps:

[0104] Step S1: Receive a page data request sent by the display device 200, and in response to the page data request, determine historical search terms and popular terms.

[0105] In some embodiments, when a user triggers access to the initial search page via click, touch, or other input methods, the display device 200 can receive and respond to the control instruction and obtain the currently logged-in user's personal information from the user account information. For example, user information may include, but is not limited to, user identification codes (such as user IDs), historical search records, etc. Simultaneously, the display device 200 can read pre-set configuration parameters, which can define the number of historical search terms (such as a first number) and the number of popular terms (such as a second number) to be displayed on the initial search page. The first and second numbers can be flexibly adjusted according to user preferences or page layout, etc.

[0106] By acquiring user information and page configuration parameters, the display device 200 can configure the initial search page in a targeted manner according to the user's search habits, and improve the user experience by comprehensively considering the user's search habits and the current media asset flow trend through historical search terms and popular terms.

[0107] In some embodiments, before determining the historical search terms, the server 400 may also receive historical search terms sent by the display device 200. The historical search terms are generated by the display device 200 according to the following steps: the display device 200 obtains the search letters entered by the user based on user information and generates related words corresponding to the search letters; in response to the user's selection instruction for the target related word in the related words, it generates media asset results corresponding to the target related word; in response to the user's determination instruction for the target media asset result in the media asset results, it generates historical search terms based on the name of the target media asset result.

[0108] In some embodiments, the dataset compiled from historical search terms can be referred to as the first dataset, which includes historical search terms entered by the user when searching for media assets. For example, it may include search terms entered by the user when searching for media assets such as videos in the past. The dataset compiled from popular terms can be referred to as the second dataset, which may include popular terms corresponding to the recommended media assets on the initial search page. For example, popular terms may be the names of media assets that have recently gained popularity, and popular terms may be sorted in descending order of the media assets' recommended popularity, such as by comprehensively evaluating their popularity based on metrics such as click-through rate and viewing time, and then sorting them in descending order.

[0109] For example, Figure 7 This is a schematic diagram illustrating a scenario where a display device generates historical search terms, as provided in some embodiments of this application. Figure 8 This is a timing diagram illustrating a server-side method for recommending search terms, provided in some embodiments of this application. Figure 7 and Figure 8 To implement the search term recommendation function, the server 400 can be equipped with a collection module, a search module, and a recommendation module. The collection module can collect the user's historical search records, the search module can be used to search for popular terms of the current media asset and related media assets corresponding to the popular terms, and the recommendation module can be used to recommend the content displayed on the initial search page, such as historical search terms and popular terms displayed on the initial search page.

[0110] In some embodiments, the display device 200 can acquire user information and collect the search letters entered by each user. For example, after a user enters the letters CXQD, the display device 200 can generate related keywords corresponding to CXQD, helping the user quickly find the search results they might want. Related keywords may include phrases such as "spring, summer, autumn, winter," "spring, summer, autumn, winter, all four seasons," "spring, summer, autumn, winter," "autumn, spring, summer, autumn, winter," "spring, summer, autumn, winter," and "spring, summer, autumn, winter, winter, issue 1." After generating related keywords, the user can select a target related keyword from the list and move the focus to that keyword. In response to the user's selection of a target related keyword (such as...), the display device 200 can generate related keywords. Figure 7When a user selects the target media asset (Spring of Spring, Summer, Autumn, Winter), the display device 200 can search for media asset results corresponding to that target keyword, such as "Spring of Spring Season 1" and "Spring of Spring Season 2". After the media asset results are generated, the user can select their preferred target media asset result. In response to the user's confirmation command for the target media asset result (such as "Spring of Spring Season 1"), the display device 200 will set "Spring of Spring Season 1" as the latest historical search term.

[0111] In some embodiments, the display device 200 can send historical search terms to the server 400. The acquisition module in the server 400 can receive these historical search terms. By generating related keywords associated with the search letters, users can find the media assets they want more quickly, reducing the need for them to input complete search terms. Recording user choices and saving the names of target media asset results as historical search terms helps to better learn user search habits, optimize search recommendations, and improve the efficiency and accuracy of media asset searches.

[0112] After collecting historical search terms, server 400 can generate a first set based on the historical search terms. In some embodiments, this can be done by the collection module. When generating the first set, the collection module first determines the media asset query time corresponding to the historical search terms. The media asset query time is the time when the target media asset result corresponding to the historical search terms is determined based on the historical search terms. Then, the historical search terms are sorted in descending order according to the media asset query time, and the historical search terms are written into the first set according to the descending order. This completes the process of generating the first set.

[0113] For example, for a user's historical search terms, the query time of each historical search term can be determined. For instance, this could be the click and confirmation time of the target media asset result corresponding to a target related term based on a historical search result. These results are then sorted in descending order of query time, meaning the most recently queried terms are listed first, and earlier queried terms are listed later. The historical search terms are then written into a specific set, forming the first set. This first set is an ordered set containing terms the user has previously searched, sorted by query time. Based on this first set, personalized recommendations, search optimization, user behavior analysis, and other functions can be used, providing a data foundation for subsequent search term recommendations.

[0114] See also Figure 8In some embodiments, before generating the second set, the server 400 may also generate popular keywords by the search module. The search module first obtains the dimensional information of the media assets, which includes at least the title and media asset identification code (such as media asset ID) of the media assets; then, it generates media asset association words based on the dimensional information. The media asset association words are words generated after extracting the media assets according to their titles. Then, it obtains a list of media assets associated with the media asset association words, and determines the highest media asset popularity value and target media asset identification code corresponding to the target media asset with the highest media asset popularity value in the media asset list.

[0115] For example, after generating the first set, the search module can generate media asset association terms based on dimensions such as the title, category, and tags of the media assets. These association terms can be generated by extracting keywords or phrases from the media asset titles. For instance, when the media asset is "Little Pig Wonder Season 1," the corresponding association terms include "Little Pig Wonder Season 1" and "Little Pig Wonder"; when the media asset is "Nirvana in Fire 2," the corresponding association terms include "Nirvana in Fire," "Nirvana in Fire 2," and "Nirvana in Fire 2"; when the media asset is "Avengers: Endgame," the corresponding association terms include "Avengers," "Endgame," "Avengers 4," and "Avengers 4 Endgame." After the media asset association terms are determined, the search module can obtain a list of media assets associated with the association terms and find the media asset identifier code and popularity value corresponding to the most popular media asset.

[0116] For example, Figure 9 This application provides schematic diagrams illustrating scenarios where a server determines the highest media asset popularity value and target media asset identifier code corresponding to the target media asset with the highest media asset popularity value, as shown in some embodiments. Figure 9 As shown, taking the media asset association keyword "Little Pig*Q" as an example, this keyword is associated with 3 media assets. The media asset list includes "Little Pig*Q Season 1" (media asset identifier code 1, popularity value 0.3), "Little Pig*Q Season 2" (media asset identifier code 2, popularity value 0.4), and "Little Pig*Q Season 3" (identifier code 3, popularity value 0.5). The media asset with the highest popularity value is 0.5. Therefore, the hottest media asset, i.e., the target media asset, is "Little Pig*Q Season 3", which has a corresponding media asset identifier code of 3 and a media asset popularity value of 0.5. For example, taking the media asset association keyword "Little Pig Wonder Season 1" as an example, this keyword is associated with two media assets: the media asset list includes "Little Pig Wonder Season 1" (media asset identifier code 4, popularity value 0.3) and "Little Pig Wonder Season 1" (media asset identifier code 5, popularity value 0.2). The media asset with the highest popularity value is 0.3. Therefore, the hottest media asset, i.e. the target media asset, is "Little Pig Wonder Season 1", which has a corresponding media asset identifier code of 4 and a media asset popularity value of 0.3.

[0117] In this way, by obtaining a list of media assets associated with related keywords, the user's search scope can be expanded, providing the user with more potentially relevant media asset options. By identifying the target media asset with the highest media asset popularity value and recording its highest media asset popularity value and target media asset identifier, it is helpful to recommend the most popular and relevant media assets to the user. This not only improves the efficiency of media asset search but also enhances the accuracy of personalized recommendations.

[0118] Based on the highest media asset popularity value associated with the aforementioned media asset related terms and the search popularity value of the media asset related terms, the comprehensive popularity value of the media asset related terms can be obtained, and then the second set can be obtained based on the comprehensive popularity value.

[0119] To obtain popular keywords, server 400 can calculate the search popularity value of media asset associated words, assign a first weight to the highest media asset popularity value, assign a second weight to the search popularity value, and then calculate the comprehensive popularity value of media asset associated words based on the highest media asset popularity value, the first weight, the search popularity value, and the second weight. The media asset associated words are then sorted in descending order according to the comprehensive popularity value to generate popular keywords. In addition, the media asset identification codes corresponding to the popular keywords are recorded. Finally, a second set is generated based on the popular keywords and the corresponding media asset identification codes.

[0120] For example, when calculating the search popularity value of media asset associated terms, various factors can be considered, such as search frequency, user click-through rate, and browsing time, to measure users' interest and attention to specific terms. For instance, when calculating the search popularity value of "Little Pig * Qi," given that the number of times it was searched by users is N1 and the number of times users clicked on the corresponding media asset results after searching is N2, the search popularity value can be calculated by normalizing the search count, such as 0.7. Similarly, when calculating the search popularity value of "Little Pig * Qi Season 1," given that the number of times it was searched by users is N3 and the number of times users searched for Tina and the corresponding media asset results is N4, the search popularity value can be calculated by normalizing the search count, such as 0.4, where N is a positive number. It is understandable that the search popularity value can reflect the relative popularity or attention of media asset associated terms. After the search popularity value is calculated, a weight can be assigned to the highest media asset popularity value and search popularity value corresponding to the previously calculated target media asset. The weight can be adjusted according to actual needs, such as the popularity and popularity of the media asset. This application does not make any specific limitations.

[0121] For example, a weight of 0.5 can be assigned to the highest media asset popularity value, and a weight of 0.5 can be assigned to the search popularity value as well. Then, the overall popularity value of media asset associated keywords can be calculated as follows:

[0122] The comprehensive popularity value of Little Pig *Qi = 0.5 (the first weight) * 0.5 (the highest media asset popularity value) + 0.5 (the second weight) * 0.7 (the search popularity value) = 0.6 (the comprehensive popularity value);

[0123] The comprehensive popularity value of the first season of Little Pig *Qi = 0.5 (the first weight) * 0.3 (the highest media asset popularity value) + 0.5 (the second weight) * 0.4 (the search popularity value) = 0.35 (the comprehensive popularity value).

[0124] After calculating the comprehensive popularity value, the search module can sort the media asset associated words in descending order according to the calculated comprehensive popularity value. Through the descending order, the most popular words can be ranked at the front to form popular words. By recording the popular words and their corresponding media asset identification codes, the relevant media assets can be quickly located, and then a second set can be generated based on the popular words and the corresponding media asset identification codes. For example, the second set can be {Fan *Ge, identification code 1; Ao *Man, identification code 2; Ze *Ao *Man, identification code 3; Baby *Jiu, identification code 4; Run *Ba, identification code 5...}, providing a data basis for subsequent search term recommendations.

[0125] At this point, the server 400 has completed the steps of obtaining historical search terms and popular words. It can be understood that the first quantity is the quantity corresponding to the historical search terms, and the second quantity is the quantity corresponding to the popular words. In the initial stage of user search, the first quantity is usually less than the second quantity. As the number and frequency of user searches increase, at a certain point, it may reach the situation where the first quantity is equal to the second quantity, or the two are approximately equal. In some scenarios, as the user search frequency accumulates continuously, it is also possible for the first quantity to be greater than the second quantity. That is to say, the relationship between the first quantity and the second quantity is not absolute and is related to the user usage scenario. After step S1 is executed, the following step S2 can be included.

[0126] Step S2: Receive a query request sent by the display device 200 for querying duplicate words. In response to the query request, determine the duplicate words between the historical search terms and the popular words, and the associated media asset identification codes associated with the duplicate words.

[0127] In some embodiments, after obtaining the historical search terms and the popular words, the server 400 can receive a query request sent by the display device 200 for querying duplicate words. In response to this query request, the server 400 can determine the duplicate words between the historical search terms and the popular words, that is, find out the common words between the two, and record the associated media asset identification codes associated with the duplicate words for subsequent processing such as replacing the duplicate words.

[0128] In order to identify duplicate words between historical search terms and popular terms, in some embodiments, server 400 may obtain a first number of historical search terms and a second number of popular terms, wherein the first number is less than the second number, popular terms are sorted in descending order of media asset recommendation popularity, and words that exist in both historical search terms and popular terms are identified to generate duplicate words.

[0129] For example, taking the first quantity as less than the second quantity, that is, the number of historical search terms is less than the number of popular terms, after obtaining the historical search terms and popular terms, the search module can respond to the query request and compare the historical search terms and popular terms to identify terms that exist in both historical search terms and popular terms, so as to find terms that are both popular and related to the user's personal search history.

[0130] It should be noted that the number of historical search terms is usually less than the number of popular terms. Therefore, finding terms that match the larger dataset (second set) within a smaller dataset (first set) reduces the number of comparisons, thus improving search efficiency. Identifying and recording duplicate terms and their associated media asset identifiers avoids users seeing too many duplicate or irrelevant media assets on the initial search page and facilitates the replacement of duplicate terms in subsequent steps. After step S2 is completed, step S3 can be executed.

[0131] Step S3: The server 400 obtains the tag set corresponding to the associated media asset identifier code, and replaces the repeated words in the historical search terms with the related words of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms.

[0132] In some embodiments, if the server 400 detects the existence of duplicate words, it can obtain the tag set corresponding to the associated media asset identifier code, and replace the duplicate words in the historical search terms with the associated words of different duplicate words in the tag set to obtain the replaced historical search terms, or replace the duplicate words in the popular terms to obtain the replaced popular terms. For example, an associated word can be selected for the duplicate words, and the duplicate words can be replaced with the associated word based on the associated media asset identifier code.

[0133] In some embodiments, there are multiple ways to replace duplicate words. For example, duplicate historical search terms can be replaced individually, or duplicate popular terms can be replaced individually, or both duplicate historical search terms and popular terms can be replaced simultaneously.

[0134] Exemplarily, if the repeated words between the historical search terms and the popular terms include Term A and Term B, then Term C and Term D that do not exist in either the first set or the second set can be used to replace Term A and Term B. For example, Term C and Term D can be used to replace Term A and Term B in the historical search terms, or Term C and Term D can be used to replace Term A and Term B in the popular search terms, or Term C can be used to replace Term A in the historical search terms and Term D can be used to replace Term B in the popular terms, etc. The specific replacement method can be combined with the actual scenario, and the present application does not make specific limitations thereon.

[0135] In some embodiments, the server 400 can at least provide the following several replacement strategies, which will be introduced in detail below.

[0136] In some embodiments, the associated terms include the names of the target persons who play the media assets corresponding to the repeated words. When the server 400 replaces the repeated words in the historical search terms with the associated terms of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms, it first identifies the target persons associated with the associated media asset identification codes in the associated terms. When there are associated target persons in the associated terms, it determines the names of the target persons corresponding to the target persons, and then uses the names of the target persons to replace the repeated words in the historical search terms to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms.

[0137] Exemplarily, each associated media asset identification code can uniquely correspond to a certain media asset, such as a certain episode of a certain TV drama or a certain movie. If the associated media asset identification code corresponding to the repeated word has a leading actor or actress, a second male lead or a second female lead played by a popular actor, then the repeated word can be replaced with the name of the target person corresponding to the role. For example, if the repeated word is Lang* Bang, then its associated term can be Hu*. In this way, using the name of the target person to replace the repeated word can attract the user's attention, thereby increasing the possibility of the user clicking on the replaced word, and thus improving the click-through rate. Replacing the repeated word with the name of the target person takes into account the user's personal preferences, making the search results closer to the user's personal interests, and at the same time can reduce the redundant information in the search results, enabling the user to see more diverse media assets, thereby solving the problem that the recommended search terms on the initial search page have poor diversity and high repetition rate.

[0138] In other embodiments, associated words include related words corresponding to repeated words. When the server 400 replaces repeated words in historical search words with related words of different repeated words in the tag set to obtain replaced historical search words, or replaces repeated words in popular words to obtain replaced popular words, it may execute the following process: When there is no target person associated with the associated media asset identifier code in the associated words, the associated media asset associated with the associated media asset identifier code in the associated words is identified; the associated media asset is a series or derivative series of media assets corresponding to the associated media asset identifier code; when there is associated media asset in the associated words, the associated words corresponding to the associated media asset are extracted, and then the associated words are used to replace repeated words in historical search words to obtain replaced historical search words, or, the repeated words in popular words are replaced to obtain replaced popular words.

[0139] For example, when the associated media asset identifier does not contain the target person, if the associated media asset identifier corresponding to the repeated words contains related works in a series or derivative series, the repeated words can be randomly replaced with related words corresponding to the series or derivative series media assets. For example, if the repeated word is "morphing *gang," then its related words could be "big *bee." In this way, by replacing the repeated words with other relevant words from the series or derivative works, the user's potential interest in the entire series or derivative works is considered, rather than just a single media asset, thus providing a personalized search experience. By replacing repeated popular words, redundant information in search results can be reduced, thereby improving the diversity of recommended search terms.

[0140] In some embodiments, the associated vocabulary includes similar words. When the server 400 replaces the repeated words in the historical search vocabulary with associated words of different repeated words in the tag set to obtain the replaced historical search vocabulary, or replaces the repeated words in the popular vocabulary to obtain the replaced popular vocabulary, the following process can be executed: When there is no target person associated with the associated media asset identifier code and no associated media asset in the associated vocabulary, similar media assets associated with the associated media asset identifier code are identified in the associated vocabulary. When there are associated similar media assets in the associated vocabulary, the similar words corresponding to the similar media assets are extracted, and then the repeated words in the historical search vocabulary are replaced with the similar words to obtain the replaced historical search vocabulary, or the repeated words in the popular vocabulary are replaced to obtain the replaced popular vocabulary.

[0141] For example, when the associated media asset identifier code contains neither a target person nor related keywords, server 400 can search for media assets with similar themes corresponding to the associated media asset identifier code and replace duplicate keywords with related keywords for similar themes. For example, if the duplicate keyword is "Interstellar Travel," then its related keywords could be "Fire Rescue." In this way, by replacing duplicate keywords with other relevant keywords from similar themes, the system considers the user's potential interest in a specific theme, rather than just a single media asset, thus providing a personalized search experience. By replacing duplicate popular keywords, redundant information in search results can be reduced, thereby improving the diversity of recommended search terms.

[0142] In some embodiments, the above replacement process can be executed by the search module. After the duplicate word replacement is completed, the search module can transmit the historical search terms and popular terms that do not have duplicates to the display device 200, and then the display device 200 displays these two types of non-duplicate search terms, such as historical search terms and popular terms. Figure 10 As shown.

[0143] In other words, server 400 can replace duplicate words with other related words based on the identified associated media asset identifier code, thereby preventing users from seeing the same search results. After the replacement process, server 400 sends the unique historical search terms and popular terms to display device 200, so that display device 200 displays the unique historical search terms and popular terms on the initial search page. By introducing the replaced terms, it recommends more search terms, thus solving the problem of poor diversity and high repetition rate of recommended search terms on the initial search page. After step S3 is completed, step S4 can be executed.

[0144] Step S4: Feed back the replaced historical search terms and / or replaced popular terms to the display device 200, so that the display device 200 responds to the page data request and controls the display 260 to display the initial search page based on the replaced historical search terms and / or replaced popular terms.

[0145] In some embodiments, after the display device 200 obtains the replaced historical search terms and / or the replaced popular terms, it can control the display 260 to display the initial search page, and display the replaced historical search terms and popular terms within the initial search page.

[0146] In some embodiments, the display device 200 may sequentially display the user's historical search terms (arranged in descending order of media asset query time) and popular terms (arranged in descending order of search term recommendation popularity) on the initial search page according to a preset first quantity and a second quantity. In this way, by replacing duplicate terms, not only can the problem of duplicate historical search terms and popular terms be solved and redundancy on the initial search page be avoided, but new search terms can also be introduced, thereby recommending related terms associated with the duplicate terms to the user and improving the diversity of search terms on the initial search page.

[0147] As can be seen from the above technical solutions, the above embodiments provide a server 400. The server 400 receives page data requests sent by a display device, and in response to the page data requests, determines historical search terms and popular terms; receives query requests sent by the display device for querying duplicate terms, and in response to the query requests, determines duplicate terms between historical search terms and popular terms, as well as associated media asset identifiers associated with the duplicate terms; obtains a tag set corresponding to the associated media asset identifiers, and replaces the duplicate terms in the historical search terms with associated terms of different duplicate terms in the tag set to obtain the replaced historical search terms, or replaces the duplicate terms in the popular terms to obtain the replaced popular terms; and feeds back the replaced historical search terms and / or the replaced popular terms to the display device, so that the display device responds to the page data requests and controls the display to display the initial search page according to the replaced historical search terms and / or the replaced popular terms. By replacing duplicate terms, the server 400 can not only solve the problem of duplicate historical search terms and popular terms and avoid redundancy in the initial search page, but also introduce new search terms, thereby recommending associated terms related to the duplicate terms to users and improving the diversity of search terms in the initial search page.

[0148] Based on the server 400 described above, some embodiments of this application also provide a method for recommending search terms, which can be applied to the server 400 in the above embodiments. In some embodiments, the method may include the following:

[0149] Receive page data requests sent by the display device, and in response to the page data requests, determine historical search terms and popular terms;

[0150] The system receives a query request from the display device for querying duplicate words, and in response to the query request, determines the duplicate words between the historical search words and the popular words, as well as the associated media asset identifier code associated with the duplicate words.

[0151] Obtain the tag set corresponding to the associated media asset identifier code, and replace the repeated words in the historical search terms with the associated words of different repeated words in the tag set to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

[0152] The replaced historical search terms and / or replaced popular terms are fed back to the display device, so that the display device responds to the page data request and controls the display to show the initial search page based on the replaced historical search terms and / or replaced popular terms.

[0153] As can be seen from the above technical solutions, the above embodiments provide a method for recommending search terms. The method can not only solve the problem of duplicate historical search terms and popular terms and avoid redundancy in the initial search page by replacing duplicate words, but also introduce new search terms and recommend related words associated with duplicate words to users, thereby improving the diversity of search terms in the initial search page.

[0154] The same or similar parts between the various embodiments in this specification can be referred to each other, and will not be repeated here.

[0155] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or certain parts of the embodiments of the present invention.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0157] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, thereby enabling those skilled in the art to better utilize the described embodiments and various different variations of embodiments suitable for specific use considerations.

Claims

1. A server, characterized in that, include: The communication module is configured to establish a communication connection with the display device; The control module is configured as follows: Receive page data requests sent by the display device, and in response to the page data requests, determine historical search terms and popular terms; The system receives a query request from the display device for querying duplicate words, and in response to the query request, determines the duplicate words between the historical search words and the popular words, as well as the associated media asset identifier code associated with the duplicate words. Obtain the tag set corresponding to the associated media asset identifier code, and replace the repeated words in the historical search terms with the associated words of different repeated words in the tag set to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms. The replaced historical search terms and / or replaced popular terms are fed back to the display device, so that the display device responds to the page data request and controls the display to show the initial search page based on the replaced historical search terms and / or replaced popular terms.

2. The server according to claim 1, characterized in that, The control module identifies duplicate words between the historical search terms and the popular terms, specifically configured as follows: Obtain a first quantity corresponding to the historical search terms and a second quantity corresponding to the popular terms; the first quantity is less than the second quantity; the popular terms are sorted in descending order of media asset recommendation popularity; Identify words that exist in the historical search terms and also in the popular terms to generate the duplicate terms.

3. The server according to claim 1, characterized in that, The control module replaces the repeated words in the historical search terms with related words of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms, specifically configured as follows: Identify the target individuals associated with the associated media asset identifiers in the associated vocabulary; When the associated words are associated with the target person, determine the name of the target person corresponding to the target person; Replace the repeated words in the historical search terms with the target person's name to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

4. The server according to claim 3, characterized in that, The control module replaces the repeated words in the historical search terms with related words of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms, specifically configured as follows: If the target person associated with the associated media asset identifier code does not exist in the associated vocabulary, the associated media asset associated with the associated media asset identifier code in the associated vocabulary is identified; the associated media asset is a series or derivative series of media assets corresponding to the associated media asset identifier code. When the associated words are associated with the associated media assets, extract the associated words corresponding to the associated media assets; Replace the repeated words in the historical search terms with the associated terms to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

5. The server according to claim 4, characterized in that, The control module replaces the repeated words in the historical search terms with related words of different repeated words in the tag set to obtain the replaced historical search terms, or replaces the repeated words in the popular terms to obtain the replaced popular terms, specifically configured as follows: If there is no target person associated with the associated media asset identifier code in the associated vocabulary and no associated media asset is associated with the associated media asset identifier code, then identify similar media assets associated with the associated media asset identifier code in the associated vocabulary. When the associated words are associated with similar media assets, extract the similar words corresponding to the similar media assets; Replace the repeated words in the historical search terms with the similar words to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms.

6. The server according to claim 1, characterized in that, Before determining the historical search terms, the control module is further configured to: The display device receives historical search terms sent by the display device, which are generated by the display device according to the following steps: the display device obtains the search letters input by the user based on user information, and generates related words corresponding to the search letters; in response to the user's selection instruction for a target related word in the related words, the display device generates media asset results corresponding to the target related word; in response to the user's confirmation instruction for a target media asset result in the media asset results, the display device generates the historical search terms based on the name of the target media asset result.

7. The server according to claim 6, characterized in that, The control module determines historical search terms, specifically configured as follows: Retrieve historical search terms associated with the user information; Obtain the media asset query time corresponding to the historical search terms; the media asset query time is the time when the target media asset result corresponding to the historical search terms is determined based on the historical search terms; The historical search terms are sorted in descending order according to the media asset query time to obtain the historical search terms in descending order. The historical search terms are output based on the historical search terms sorted in descending order.

8. The server according to claim 1, characterized in that, Before determining the popular keywords, the control module is further configured to: Obtain the dimensional information of the media asset; the dimensional information includes at least the title and media asset identifier code of the media asset; Media asset association terms are generated based on the dimensional information; the media asset association terms are words generated after extracting the media asset according to the title. Obtain the list of media assets associated with the media asset association terms, and determine the highest media asset popularity value and target media asset identifier code corresponding to the target media asset with the highest media asset popularity value in the list.

9. The server according to claim 8, characterized in that, The control module identifies popular keywords, specifically configured as follows: Calculate the search popularity value of the associated keywords for the media assets; Assign a first weight to the highest media asset popularity value and a second weight to the search popularity value; The comprehensive popularity value of the media asset associated terms is calculated based on the highest media asset popularity value, the first weight, the search popularity value, and the second weight; The media asset association terms are sorted in descending order according to the overall popularity value. Popular keywords are generated based on the results sorted in descending order.

10. A method for recommending search terms, characterized in that, The method includes: Receive page data requests sent by the display device, and in response to the page data requests, determine historical search terms and popular terms; The system receives a query request from the display device for querying duplicate words, and in response to the query request, determines the duplicate words between the historical search words and the popular words, as well as the associated media asset identifier code associated with the duplicate words. Obtain the tag set corresponding to the associated media asset identifier code, and replace the repeated words in the historical search terms with the associated words of different repeated words in the tag set to obtain the replaced historical search terms, or replace the repeated words in the popular terms to obtain the replaced popular terms. The replaced historical search terms and / or replaced popular terms are fed back to the display device, so that the display device responds to the page data request and controls the display to show the initial search page based on the replaced historical search terms and / or replaced popular terms.

Images