Method, device, electronic device and storage medium for determining recommendation words

Abstract

The present disclosure relates to a method, device, electronic device and storage medium for determining a recommendation word, including: receiving a search word, and displaying a first search result corresponding to the search word under a first attribute tag on a search result page; wherein the search result page includes multiple attribute tags, and the attribute of the first search result matches the first attribute tag; in response to a switching operation of the attribute tag, displaying a second search result corresponding to the search word under a second attribute tag on the search result page, and the attribute of the second search result matches the second attribute tag; in response to a triggering operation on a search box in the search result page, displaying a set of recommendation words on a search intermediate page, wherein the set of recommendation words is determined based on the search word and the second attribute tag, thereby improving the user's search experience.

Description

Technical Field

[0001] The present disclosure relates to the technical field of search keyword recommendation, and in particular to a method, device, electronic device and storage medium for determining a recommendation word. Background Art

[0002] In recent years, with the rapid development of science and technology, Internet applications have been widely used in various fields, big data has shown explosive growth, and massive amounts of data and information are scattered in cyberspace. When users need to obtain information and data, they usually use search engines to search for information and obtain the search information they want.

[0003] In the prior art, when a user clicks a search box or a magnifying glass on a search page, the user can enter a search intermediate page, which displays search recommendation words to the user, and the user can trigger the search recommendation words to search for related information.

[0004] However, in the prior art, the accuracy of the search recommendation words displayed to the user on the search intermediate page is low and cannot meet the user's search needs. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a method, device, electronic device and storage medium for determining recommended words to improve the user's search experience.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for determining a recommendation word, including:

[0007] Receiving a search term, and displaying a first search result corresponding to the search term under a first attribute tag on a search result page; wherein the search result page includes a plurality of attribute tags, and an attribute of the first search result matches the first attribute tag;

[0008] In response to the switching operation of the attribute label, displaying a second search result corresponding to the search term under a second attribute label on the search result page, wherein the attribute of the second search result matches the second attribute label;

[0009] In response to a triggering operation on a search box in the search results page, a recommended word set is displayed on a search intermediate page, wherein the recommended word set is determined based on the search words and the second attribute tag.

[0010] Optionally, the recommended word set is determined based on the search word and the second attribute tag, including:

[0011] determining an expansion word based on the second attribute tag;

[0012] The candidate recommended words and the extended words corresponding to the search words are concatenated and combined to generate target recommended words, so as to obtain the recommended word set.

[0013] Optionally, the recommended word set is determined based on a first recommended word set corresponding to the search word and a second recommended word set corresponding to the second attribute tag;

[0014] Based on the second attribute label, obtaining a first recommended word subset from the first recommended word set, and obtaining a second recommended word subset from the second recommended word set; wherein the recommended words in the first recommended word subset and the second recommended word subset match the second attribute label;

[0015] The recommended words in the first recommended word subset and the second recommended word subset are processed and concatenated to obtain the recommended word set.

[0016] Optionally, in response to a triggering operation on a search box in the search results page, displaying a set of recommended words on a search intermediate page includes:

[0017] In response to triggering the focus of the search box in the search results page, displaying a set of recommended words on a search intermediate page;

[0018] or,

[0019] In response to deleting the search term in the search box on the search results page, displaying a set of recommended terms on a search intermediate page;

[0020] or,

[0021] In response to triggering a target control corresponding to a search box in the search results page, a set of recommended words is displayed on a search intermediate page.

[0022] Optionally, the method further includes:

[0023] In response to a triggering operation on any target recommended word in the recommended word set, displaying a target search result matching the target recommended word and the second attribute tag on a search result page; or,

[0024] In response to a triggering operation on any target recommended word in the recommendation word set, a target search result matching the target recommended word is displayed on a search result page, wherein the target search result includes a third search result corresponding to the target search word under a different attribute label, and a search result in the third search result whose attribute label matches the second attribute label is displayed with a higher priority than a search result in the third search result whose attribute label does not match the second attribute label.

[0025] In a second aspect, the present disclosure provides another method for determining a recommendation word, including:

[0026] receiving a recommendation word set acquisition request sent by a client, wherein the recommendation word set acquisition request includes a second attribute tag and a search word, and the recommendation word set acquisition request is used to request acquisition of a recommendation word set;

[0027] Based on the second attribute tag and the search word, a recommended word set is obtained, wherein the recommended words in the recommended word set match the second attribute tag.

[0028] Optionally, acquiring a set of recommended words based on the second attribute tag and the search word includes:

[0029] Based on the second attribute tag and the search term, a set of recommended terms corresponding to the second attribute tag and the search term is obtained from a database.

[0030] Optionally, before acquiring a set of recommended words corresponding to the second attribute label and the search word from a database based on the second attribute label and the search word, the method further includes:

[0031] Acquire historical search terms including the search terms;

[0032] A set of recommended words matching the second attribute tag is filtered out from the historical search words.

[0033] Optionally, before acquiring, from a database, a set of recommended words corresponding to the second attribute label and the search word based on the second attribute label and the search word, the method further includes:

[0034] Obtain historical search results for the search term;

[0035] Obtain candidate recommendation words corresponding to the historical search results;

[0036] A set of recommended words matching the second attribute label is obtained from the candidate recommended words.

[0037] Optionally, the acquiring, based on the second attribute label, from the candidate recommendation words, a set of recommendation words matching the second attribute label includes:

[0038] Based on the interaction data of the second attribute label and the candidate recommendation words, a set of recommendation words matching the second attribute label is obtained from the candidate recommendation words.

[0039] Optionally, the acquiring, based on the second attribute label and the interaction data of the candidate recommendation words, a set of recommendation words matching the second attribute label from the candidate recommendation words includes:

[0040] Acquire a set of candidate recommendation words matching the second attribute label from the candidate recommendation words;

[0041] Determining recommendation parameters of candidate recommendation words in the candidate recommendation word set based on the interaction data of the candidate recommendation words;

[0042] Based on the recommendation parameters of the candidate recommendation words in the candidate recommendation word set, a recommendation word set is obtained from the candidate recommendation word set.

[0043] Optionally, the interactive data includes search frequency, search time period and / or browsing behavior.

[0044] In a third aspect, an embodiment of the present disclosure provides a device for determining a recommendation word, including:

[0045] A first search result display module, configured to receive a search term and display a first search result corresponding to the search term under a first attribute tag on a search result page; wherein the search result page includes a plurality of attribute tags, and an attribute of the first search result matches the first attribute tag;

[0046] A second search result display module, configured to display, in response to a switching operation of an attribute tag, a second search result corresponding to the search term under a second attribute tag on the search result page, wherein an attribute of the second search result matches the second attribute tag;

[0047] The recommended word set display module is used to display a recommended word set on a search intermediate page in response to a triggering operation on a search box in the search result page, wherein the recommended word set is determined based on the search word and the second attribute tag.

[0048] In a fourth aspect, an embodiment of the present disclosure provides another device for determining a recommendation word, including:

[0049] A request receiving module, configured to receive a recommendation word set acquisition request sent by a client, wherein the recommendation word set acquisition request includes a second attribute tag and a search word, and the recommendation word set acquisition request is used to request acquisition of a recommendation word set;

[0050] A recommendation word set acquisition module is used to acquire a recommendation word set based on the second attribute tag and the search word, wherein the recommendation words in the recommendation word set match the second attribute tag.

[0051] In a fifth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0052] one or more processors;

[0053] a storage device for storing one or more programs,

[0054] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of the first aspect or the second aspect.

[0055] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any one of the first aspect or the second aspect.

[0056] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0057] The recommended word determination method, device, electronic device and storage medium provided by the embodiments of the present disclosure are as follows: after a client receives a search word, a first search result corresponding to the search word under a first attribute tag is displayed on a search result page; in response to a switching operation of the attribute tag, a second search result corresponding to the search word under a second attribute tag is displayed on the search result page, and the attribute of the second search result matches the second attribute tag; in response to a triggering operation on a search box in the search result page, a recommended word set is displayed on a search intermediate page, wherein the recommended word set is determined based on the search word and the second attribute tag, so that when a user switches to a different attribute tag for searching, the recommended word set displayed to the user in the search result page is associated with the user's search needs, and the recommended word set is more relevant to the user's search word and the switched attribute tag. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0060] Figure 1 is a flowchart of a method for determining a recommendation word provided by an embodiment of the present disclosure;

[0061] Figures 2A to 2E is a schematic diagram of an interface structure of a recommendation word provided by an embodiment of the present disclosure;

[0062] Figure 3 is a flowchart of another method for determining a recommendation word provided by an embodiment of the present disclosure;

[0063] Figure 4 is a structural diagram of a device for determining a recommendation word provided by an embodiment of the present disclosure;

[0064] Figure 5 is a structural schematic diagram of another device for determining a recommendation word provided by an embodiment of the present disclosure;

[0065] Figure 6 It is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0066] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0068] When a user searches for content on a search engine, if the search results are not very relevant to the search keyword and do not meet the user's search needs, the user will return to the search homepage and switch search channels to obtain search results under different search channels. When the user returns to the search homepage and switches search channels, he needs to re-enter the search keyword in the corresponding search channel to complete the query.

[0069] In the prior art, corresponding to different search channels, when users modify search keywords in the search channel, the search recommendation words on the corresponding search intermediate page are similar, that is, the comprehensive search recommendation words in the global state by default, that is, the search recommendation words displayed to users by the search intermediate page cannot be associated with more relevant and focused recommendation word content according to user needs, thereby reducing the user's search experience.

[0070] Based on this, an embodiment of the present disclosure provides a method for determining a recommended word, including: receiving a search word, and displaying a first search result corresponding to the search word under a first attribute tag on a search results page; wherein the search results page includes multiple attribute tags, and the attribute of the first search result matches the first attribute tag; in response to a switching operation of the attribute tag, displaying a second search result corresponding to the search word under a second attribute tag on the search results page, and the attribute of the second search result matches the second attribute tag; in response to a triggering operation on a search box in the search results page, displaying a recommended word set on a search intermediate page, and the recommended word set is determined based on the search word and the second attribute tag, so that the recommended word set displayed on the search intermediate page is determined based on the search word and the second attribute tag, thereby improving the user's search experience.

[0071] The recommendation word determination method disclosed in the present invention is executed by an application client corresponding to the recommendation word determination method. The application client may be an application client on a tablet computer, a mobile phone, a wearable device, an in-vehicle device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a smart TV, a smart screen, a high-definition TV, a 4K TV, a smart speaker, or a smart projector.

[0072] like Figure 1 As shown, the method for determining the recommended words includes:

[0073] S10: Receive a search term, and display a first search result corresponding to the search term under a first attribute tag on a search result page.

[0074] The search result page includes a plurality of attribute tags, and the attribute of the first search result matches the first attribute tag.

[0075] Specifically, the attribute tags include attention, comprehensive, recommendation, video, short video, novel, music, entertainment, film and television, question and answer, etc.

[0076] When the user enters a search term in the search box, the application client displays the first search result corresponding to the search term under the recommendation tag on the search results page in response to the search term entered by the user in the search box.

[0077] For example, Figure 2A As shown, if the user enters the search term "XX Biography" in the search box 100 and triggers the search button, the first search result 300 corresponding to "XX Biography" under the comprehensive tag is displayed on the search result page 200, such as Figure 2B shown.

[0078] It should be noted that the above embodiment exemplarily indicates that the first attribute label is a comprehensive label. In a specific implementation, after receiving the search term, the first attribute label can be customized and the first search result corresponding to the search term under the corresponding first attribute label can be displayed on the search page. The present disclosure does not specifically limit this.

[0079] S20. In response to the switching operation of the attribute tag, a second search result corresponding to the search term under the second attribute tag is displayed on the search result page, and the attribute of the second search result matches the second attribute tag.

[0080] When the user triggers the attribute tag switching on the search result page 200, for example, the user triggers the attribute tag to switch from the comprehensive attribute tag to the music attribute tag, at this time, in response to the attribute tag switching operation, the second search result 400 corresponding to "XX Chuan" under the music attribute tag is displayed on the search result page 200. The second search result is as follows: Figure 2C As shown, the attributes of the second search result 400 match the second attribute tag.

[0081] It should be noted that the attribute of the second search result may be the file type of the second search result, or may be a label corresponding to the second search result, which is not specifically limited in the embodiments of the present disclosure.

[0082] S30. In response to a triggering operation on a search box in a search result page, a set of recommended words is displayed on a search intermediate page, where the set of recommended words is determined based on the search words and the second attribute tag.

[0083] When a user triggers the search box on the search results page, combined with Figure 2C , the user triggers the search box 500 in the search result page 200, and at this time, the recommended word set is displayed in the search middle page such as Figure 2D shown.

[0084] In a specific implementation, the triggering operation of the search box in the search results page can be to select the search box with focus, to perform a deletion operation on the search box, or to trigger a target control corresponding to the search box. The disclosed embodiment does not specifically limit the triggering operation of the search box.

[0085] The recommended word determination method provided by the embodiment of the present disclosure is that after the client receives the search word, the first search result corresponding to the search word under the first attribute tag is displayed on the search results page; in response to the switching operation of the attribute tag, the second search result corresponding to the search word under the second attribute tag is displayed on the search results page, and the attribute of the second search result matches the second attribute tag; in response to the triggering operation of the search box in the search results page, a recommended word set is displayed on the search middle page, wherein the recommended word set is determined based on the search word and the second attribute tag, so that when the user switches to different attribute tags for searching, the recommended word set displayed to the user in the search results page is associated according to the user's search needs (search words and attribute tags), thereby improving the accuracy of the search recommended words displayed to the user in the search middle page.

[0086] As an implementable method, the specific process of determining the recommended word set based on the search word and the second attribute tag includes:

[0087] Determining an expansion word based on the second attribute tag;

[0088] The candidate recommended words and the extended words corresponding to the search words are concatenated and combined to generate target recommended words, so as to obtain a recommended word set.

[0089] Exemplarily, if the input search term is "harem palace fighting TV series", the candidate recommendation terms determined based on the search term are exemplarily "XX Biography" and "Bu Bu XX". If the second attribute tag is video, the expansion terms corresponding to "XX Biography" are determined based on the video attribute tag as Chenghuan collection, Rongchong collection, etc., and the expansion terms corresponding to "Bu Bu XX" are determined based on the video attribute tag as Jiu Zi YY, Cihuan, etc. After determining the candidate recommendation terms corresponding to the search term and the expansion terms corresponding to the candidate recommendation terms, the target recommendation terms are determined based on the candidate recommendation terms and the expansion terms corresponding to the candidate recommendation terms as "XX Biography Rongchong Collection", "XX Inheritance Huan Collection", "Bu Bu XX Jiu Zi YY", "Bu Bu XX Cihuan", etc., and the recommendation term set is the determined target recommendation term.

[0090] It should be noted that, in the process of determining candidate recommendation words based on search terms, the determined candidate recommendation words are those that are related to the search terms. For example, if the search term is "harem palace fighting TV series", then the candidate recommendation words can be determined to be TV series with harem palace fighting themes or TV series with harem themes, etc., or they can be TV series with harem palace fighting themes or TV series with harem themes, etc.

[0091] In addition, in the process of determining the expansion word corresponding to the candidate recommendation word based on the attribute tag, the expansion word can be the same as the attribute tag, or a word associated with the attribute tag. For example, if the attribute tag is a video attribute tag, the expansion word includes: video, YY clip collection, etc. Based on the candidate recommendation word and the corresponding expansion word, the process of determining the target recommendation word can be to splice the candidate recommendation word and the corresponding expansion word to obtain the target recommendation word.

[0092] In the process of splicing and combining candidate recommendation words and expansion words, the splicing and combination process can be candidate recommendation words + expansion words, or expansion words + candidate recommendation words, or part of candidate recommendation words + expansion words, or part of candidate recommendation words + part of expansion words, etc. The embodiment of the present disclosure does not specifically limit the splicing and combination process.

[0093] As another possible implementation, the specific process of determining the recommended word set based on the first recommended word set corresponding to the search word and the second recommended word set corresponding to the second attribute tag includes:

[0094] Based on the second attribute tag, obtaining a first recommended word subset from the first recommended word set, and obtaining a second recommended word subset from the second recommended word set; wherein the recommended words in the first recommended word subset and the second recommended word subset match the second attribute tag;

[0095] The recommended words in the first recommended word subset and the second recommended word subset are processed and concatenated to obtain a recommended word set.

[0096] Exemplarily, if the input search term is "harem fighting TV series", the first recommended word set determined based on the search term is exemplarily "XX Biography", "Bu Bu XX", "YY Film and Television Soundtrack", and "ZZ Film and Television Soundtrack". If the second attribute tag is video, the first recommended word subset obtained from the first recommended word set based on the video attribute tag is "XX Biography" and "Bu Bu XX", and the second recommended word set determined based on the second attribute tag, i.e., the video attribute tag, includes "XX's collection", "Funny XX collection", "XX Biography", "Bu Bu XX", etc., then the second recommended word subset obtained from the second recommended word set based on the search term is "XX's collection", "XX Biography", and "Bu Bu XX". After determining the first recommended word subset and the second recommended word subset, the recommended word set is determined based on the first recommended word subset and the second recommended word subset, wherein the first recommended word subset is "XX Biography" and "Bu Bu XX", and the second recommended word subset is "XX's collection", "XX Biography" and "Bu Bu XX", then the determined recommended word set is "XX's collection", "XX Biography" and "Bu Bu XX".

[0097] It should be noted that in the above embodiment, after determining the first recommended word subset and the second recommended word subset, in the process of determining the recommended word set based on the first recommended word subset and the second recommended word subset, the union of the first recommended word subset and the second recommended word subset is selected to determine the recommended word set.

[0098] In addition, in the first recommended word set determined based on the search word, the first recommended word set includes the first recommended word under different attribute tags, and the second recommended word set determined based on the second attribute tag includes the second recommended word under the second attribute tag. Therefore, when obtaining the first recommended word subset from the first recommended word set based on the second attribute tag, the first recommended word subset whose attribute tag is the second attribute tag is obtained from the first recommended word set; when obtaining the second recommended word subset from the second recommended word set based on the search word, the second recommended word subset corresponding to the search word is obtained from the second recommended word set, thereby ensuring that the determined recommended word set is richer and more comprehensive.

[0099] The method for determining recommended words provided by the embodiments of the present disclosure first determines a first recommended word set based on search words, then obtains a first recommended word subset from the first recommended word set based on a second attribute tag, then determines a second recommended word set based on the second attribute tag, then obtains a second recommended word subset from the second recommended word set based on the search words, and finally determines a recommended word set based on the first recommended word subset and the second recommended word subset, thereby ensuring that the determined recommended word set is more comprehensive.

[0100] As an implementation method, in response to a triggering operation on a search box in a search result page, a set of recommended words is displayed on a search intermediate page, including:

[0101] In response to triggering the focus of the search box in the search results page, a set of recommended words is displayed on the search intermediate page.

[0102] Exemplary, combined Figure 2C and Figure 2D When the user places the focus on the search box on the search result page 200, in response to the triggering of the intersection of the search box in the search result page, the recommended word set is displayed on the search intermediate page, wherein the search intermediate page 600 is as follows Figure 2D As shown, the display method of the recommended word set 700 displayed on the search intermediate page 600 is shown in FIG. Figure 2D .

[0103] As another possible implementation, in response to a triggering operation on a search box in a search result page, a set of recommended words is displayed on a search intermediate page, including:

[0104] In response to deleting a search word in a search box on a search results page, a set of recommended words is displayed on a search intermediate page.

[0105] Exemplary, combined Figure 2C and Figure 2E When the user places the focus on the search box on the search results page 200 and deletes the search word in the search box, in response to deleting the search word in the search box on the search results page, a set of recommended words is displayed on the search intermediate page, wherein the search intermediate page 600' is as shown in FIG. Figure 2E As shown, the display method of the recommended word set 700' displayed on the search intermediate page 600' is shown in Figure 2E .

[0106] As another possible implementation, in response to a triggering operation on a search box in a search result page, a set of recommended words is displayed on a search intermediate page, including:

[0107] In response to triggering a target control corresponding to a search box in a search results page, a set of recommended words is displayed on a search intermediate page.

[0108] Exemplary, combined Figure 2C and Figure 2E When the user triggers the target control 800 corresponding to the search box on the search result page 200, in response to the triggering operation of the target control corresponding to the search box on the search result page, a set of recommended words is displayed on the search intermediate page, wherein the search intermediate page 600' is as shown in FIG. Figure 2E As shown, the display method of the recommended word set 700' displayed on the search intermediate page 600' is shown in Figure 2E .

[0109] It should be noted that the above embodiments exemplarily represent three methods of displaying a set of recommended words on a search intermediate page in response to a triggering operation on a search box on a search result page, and the embodiments of the present disclosure do not specifically limit this.

[0110] As an implementable embodiment, the method for determining a recommendation word further includes:

[0111] In response to a trigger operation on any target recommendation word in the recommendation word set, a target search result matching the target recommendation word and the second attribute tag is displayed on the search results page; or, in response to a trigger operation on any target recommendation word in the recommendation word set, a target search result matching the target recommendation word is displayed on the search results page, wherein the target search result includes a third search result corresponding to the target search word under a different attribute tag, and a search result in the third search result in which the attribute tag matches the second attribute tag is displayed with a higher priority than a search result in which the attribute tag does not match the second attribute tag.

[0112] As an implementable method, when the search box is triggered in the search result page under the video tag, the page jumps to the search intermediate page, and the user selects any target recommended word in the recommended word set displayed on the search intermediate page and clicks on the target recommended word. At this time, the search intermediate page jumps to the search result page, and the target search result is displayed on the search result page, wherein the target search result matches the target recommended word selected by the user in the recommended word set and the second attribute tag. Exemplarily, the recommended word set displayed on the search intermediate page includes "XX's collection", "XX Biography" and "Step by Step XX". The user selects "Step by Step XX" and clicks on the target recommended word. At this time, the search intermediate page jumps to the search result page, and the target search result is displayed on the search result page, and the target search result matches the target recommended word "Step by Step XX" and the video tag, that is, the video search result corresponding to the target recommended word "Step by Step XX" is displayed on the search result page.

[0113] As another possible implementation method, when the search box is triggered in the search results page under the video tag, the page jumps to the search intermediate page, and the user selects any target recommended word in the recommended word set displayed on the search intermediate page and clicks on the target recommended word. At this time, the search intermediate page jumps to the search results page, and the target search results are displayed on the search results page, wherein the target search results match the target recommended word selected by the user in the recommended word set, and the target search results include the third search results corresponding to the target search words under different attribute tags, and the search results in the third search results whose attribute tags match the second attribute tags have a higher priority than the search results in the third search results whose attribute tags do not match the second attribute tags. Exemplarily, the recommended word set displayed on the search intermediate page includes "XX's collection", "XX Biography" and "Step by Step XX". The user selects "BuBuXX" and clicks on the target recommendation word. At this time, the search page jumps to the search results page from the search middle page, and the target search results are displayed on the search results page. The target search results match the target recommendation word "BuBuXX", that is, the search results corresponding to the target recommendation word "BuBuXX" are displayed on the search results page. Since the search results displayed at this time include search results under different attribute tags, the search results matching the second attribute tag are set to have a higher display priority than the search results in the third search results whose attribute tags do not match the second attribute tags, it is ensured that the search results matching the second attribute tag can be displayed first, so that users can see the search results matching the second attribute tag first, thereby satisfying the user's search needs.

[0114] It should be noted that in the above embodiment, when the user performs a trigger operation in the search box on the search results page, the application client sends a recommendation word set acquisition request to the server. After the server obtains the recommendation word set acquisition request sent by the application client, the server obtains the recommendation word set corresponding to the recommendation word set acquisition request based on the second attribute tag and the search word included in the recommendation word set acquisition request, and sends the obtained recommendation word set to the application client. The application client displays the recommendation word set sent by the server on the search intermediate page.

[0115] The method for determining recommended words provided in the above embodiment is executed by the application client. The following will introduce the specific implementation steps of the method for determining recommended words executed by the server through a specific embodiment. Figure 3 As shown, the method for determining the recommended words includes:

[0116] S100: Receive a recommendation word set acquisition request sent by a client.

[0117] The recommended word set acquisition request includes a second attribute tag and a search word, and the recommended word set acquisition request is used to request to acquire a recommended word set.

[0118] When the user enters a search word in the search box and switches to the second attribute label, a search operation is triggered. The server receives a recommendation word set acquisition request sent by the client, and based on the second attribute label and recommended words included in the recommendation word set acquisition request, acquires a recommendation word set corresponding to the second attribute label and the recommended words.

[0119] Specifically, exemplary attribute tags in the recommendation word set acquisition request include attention, comprehensive, recommendation, video, short video, novel, music, entertainment, film and television, question and answer, etc.

[0120] S200: Acquire a set of recommended words based on the second attribute tag and the search word.

[0121] The recommended words in the recommended word set are matched with the second attribute tag.

[0122] Specifically, when the user performs a trigger operation in the search box on the search results page, the application client sends a recommendation word set acquisition request to the server. After obtaining the recommendation word set acquisition request sent by the application client, the server obtains the recommendation word set corresponding to the recommendation word set acquisition request based on the second attribute tag and search word included in the recommendation word set acquisition request, and sends the acquired recommendation word set to the application client. The application client displays the recommendation word set sent by the server on the search intermediate page.

[0123] The recommended word determination method provided by the embodiment of the present disclosure obtains a recommended word set based on the second attribute tag and search word included in the recommended word acquisition request after receiving the recommended word acquisition request sent by the client, so that when the user switches to different attribute tags for searching, the recommended word set displayed to the user in the search results page is associated with the user's search needs, and the recommended word set is more relevant to the user's search word and the switched attribute tag.

[0124] As an implementable method, based on the attribute tag and the search word, a set of recommended words is obtained, including:

[0125] Determine the expansion word based on the second attribute tag; concatenate and combine the candidate recommendation words and the expansion words corresponding to the search word to generate the target recommendation word, so as to obtain a recommendation word set.

[0126] In a specific implementation, when the server receives a recommendation word set acquisition request sent by the client, it first determines the candidate recommendation word based on the search word included in the recommendation word set acquisition request, and then determines the expansion word corresponding to the candidate recommendation word set based on the second attribute tag included in the recommendation word set acquisition request, and then determines the target recommendation word based on the candidate recommendation word and the corresponding expansion word, and finally determines the recommendation word set based on the target recommendation word.

[0127] Exemplarily, if the input search term is "harem palace fighting TV series", the candidate recommendation terms determined based on the search term are exemplarily "XX Biography" and "Bu Bu XX". If the second attribute tag is video, the expansion terms corresponding to "XX Biography" are determined based on the video attribute tag as Chenghuan collection, Rongchong collection, etc., and the expansion terms corresponding to "Bu Bu XX" are determined based on the video attribute tag as Jiu Zi YY, Cihuan, etc. After determining the candidate recommendation terms corresponding to the search term and the expansion terms corresponding to the candidate recommendation terms, the target recommendation terms are determined based on the candidate recommendation terms and the expansion terms corresponding to the candidate recommendation terms as "XX Biography Rongchong Collection", "XX Inheritance Huan Collection", "Bu Bu XX Jiu Zi YY", "Bu Bu XX Cihuan", etc., and the recommendation term set is the determined target recommendation term.

[0128] As another possible implementation method, based on the attribute tag and the search word, a set of recommended words is obtained, including:

[0129] Based on the second attribute label, a first recommended word subset is obtained from the first recommended word set, and a second recommended word subset is obtained from the second recommended word set; wherein the recommended words in the first recommended word subset and the second recommended word subset match the second attribute label; and the recommended words in the first recommended word subset and the second recommended word subset are processed and spliced ​​to obtain a recommended word set.

[0130] Exemplarily, if the input search term is "harem fighting TV series", the first recommended word set determined based on the search term is exemplarily "XX Biography", "Bu Bu XX", "YY Film and Television Soundtrack", and "ZZ Film and Television Soundtrack". If the second attribute tag is video, the first recommended word subset obtained from the first recommended word set based on the video attribute tag is "XX Biography" and "Bu Bu XX", and the second recommended word set determined based on the second attribute tag, i.e., the video attribute tag, includes "XX's collection", "Funny XX collection", "XX Biography", "Bu Bu XX", etc., then the second recommended word subset obtained from the second recommended word set based on the search term is "XX's collection", "XX Biography", and "Bu Bu XX". After determining the first recommended word subset and the second recommended word subset, the recommended word set is determined based on the first recommended word subset and the second recommended word subset, wherein the first recommended word subset is "XX Biography" and "Bu Bu XX", and the second recommended word subset is "XX's collection", "XX Biography" and "Bu Bu XX", then the determined recommended word set is "XX's collection", "XX Biography" and "Bu Bu XX".

[0131] As another possible implementation method, obtaining a set of recommended words based on the second attribute tag and the search word includes:

[0132] Based on the second attribute tag and the search term, a set of recommended terms corresponding to the second attribute tag and the search term is obtained from a database.

[0133] Specifically, when the server receives a recommendation word set acquisition request sent by the application client, the server obtains the recommendation word set corresponding to the second attribute tag and the search word from the database based on the second attribute tag and the search word included in the recommendation word set acquisition request sent by the client.

[0134] In a specific implementation, based on the second attribute tag and the search word, an implementation method of determining the recommended word set in the database before obtaining the recommended word set corresponding to the second attribute tag and the search word from the database includes:

[0135] Acquire historical search terms including the search term; and filter out a set of recommended terms matching the second attribute tag from the historical search terms.

[0136] Specifically, first, based on the search term, the search results based on the search term are obtained, then historical search terms including the search term are selected from the search results based on the search term, and finally, based on the second attribute tag, a set of recommended terms matching the second attribute tag is filtered out from the historical search terms and stored in the database.

[0137] In a specific implementation, based on the second attribute tag and the search word, another implementation method of determining the recommended word set in the database before obtaining the recommended word set corresponding to the second attribute tag and the search word from the database includes:

[0138] Obtain historical search results of the search term; obtain candidate recommended terms corresponding to the historical search results; and obtain a set of recommended terms that match the second attribute tag from the candidate recommended terms.

[0139] Specifically, first, based on the search term, historical search results based on the search term are obtained, then corresponding candidate recommendation terms are determined from the historical search results based on the search term, and finally, based on the second attribute tag, a set of recommendation terms matching the second attribute tag is obtained from the candidate recommendation terms and stored in the database.

[0140] As an implementable method, based on the second attribute tag, the specific process of obtaining a set of recommended words matching the second attribute tag from the candidate recommended words includes:

[0141] Based on the second attribute label and the interaction data of the candidate recommendation words, a set of recommendation words matching the second attribute label is obtained from the candidate recommendation words.

[0142] Specifically, based on the second attribute label, a set of candidate recommendation words matching the second attribute label is obtained from the candidate recommendation words.

[0143] Based on the interaction data of the candidate recommendation words, recommendation parameters of the candidate recommendation words in the candidate recommendation word set are determined.

[0144] Among them, interactive data includes search frequency, search time period and / or browsing behavior.

[0145] Specifically, search frequency refers to the number of searches based on the candidate recommendation term in the historical search data, search time period refers to the search time corresponding to the search based on the candidate recommendation term in the historical search data, and browsing behavior refers to the frequency of users browsing different historical search results in the historical search results based on the historical search results.

[0146] In the historical search data, the more times the candidate recommendation word is searched, the greater the proportion of the recommendation parameters of the candidate recommendation word in the candidate recommendation word set.

[0147] In the historical search data, if the number of searches based on the candidate recommendation word in a certain time period is greater, the recommendation parameter proportion of the candidate recommendation word in the candidate recommendation word set will be greater.

[0148] In the historical search data, if the user browses a certain historical search result more frequently or spends a longer time browsing it among the historical search results obtained based on the candidate recommendation word, then the candidate recommendation word included in the historical search result with a higher browsing frequency or a longer browsing time will account for a larger proportion of the recommendation parameters in the candidate recommendation word set.

[0149] Based on the recommendation parameters of the candidate recommendation words in the candidate recommendation word set, the candidate recommendation words are obtained from the candidate recommendation word set and the recommendation word set is formed.

[0150] After obtaining a set of candidate recommendation words that match the second attribute tag from the candidate recommendation words based on the second attribute tag, then determining recommendation parameters of the candidate recommendation words in the candidate recommendation word set based on the interaction data of the candidate recommendation words, and finally obtaining a recommendation word set from the candidate recommendation word set based on the recommendation parameters of the candidate recommendation words in the candidate recommendation word set.

[0151] Exemplarily, the second attribute label is variety show. At this time, based on the second attribute label, a set of candidate recommendation words matching the second attribute label are screened out from historical search words: "Everyday XX", "China Trend X", and "Immediate XX". The number of times the user triggers the search for the candidate search recommendation word "China Trend X" is 1 time, the number of times the user triggers the search for the candidate recommendation word "Everyday XX" is 3 times, the number of times the user triggers the search for the candidate recommendation word "Immediate XX" is 3 times, and the number of times the user triggers the search for the candidate recommendation word "Our X" is 3 times. It can be determined that the recommendation parameter of the candidate recommendation word "China Trend X" is A1, the recommendation parameter of the candidate recommendation word "Everyday XX" is A2, the recommendation parameter of the candidate recommendation word "Immediate XX" is A3, and the recommendation parameter of the candidate recommendation word "Our X" is A4, and A4=A3=A2>A1.

[0152] When the number of candidate recommendation words included in the recommendation word set displayed on the search middle page is set to 3, based on the recommendation parameters of the candidate recommendation words in the candidate recommendation word set, the first 3 candidate recommendation words with larger recommendation parameters are selected as the recommendation words in the recommendation word set, that is, the recommendation word set includes: our X, immediate XX, and every day XX.

[0153] It should be noted that in the above embodiment, the recommendation parameters of the candidate recommendation words are determined based on the search frequency of the candidate recommendation words. In other implementations, the recommendation parameters of the candidate recommendation words may also be determined based on the search time period and / or browsing behavior of the candidate recommendation words.

[0154] For example, when the second attribute label is food, and the user enters the search term "recipe" in the food attribute label, the search results obtained based on the search term "recipe" in the food attribute label are: 1. It takes more than 3 minutes to be ready, and it tastes better than fried dough sticks; 2. What do primary school students eat for breakfast? Simple and practical 7-day breakfast; 3. Cook millet porridge without boiling it directly with water; 4. Steamed egg, fresh and tender; 5. 10 ways to cook vegetarian dishes, and the candidate recommended words obtained include: fried dough sticks, breakfast, millet porridge, steamed egg, and fried vegetarian dishes.

[0155] The user triggered the search time for the candidate recommendation word "millet porridge" in the morning, the user triggered the search time for the candidate recommendation word "fried dough sticks" in the morning, the user triggered the search time for the candidate recommendation word "steamed egg" at noon, and the user triggered the search time for the candidate recommendation word "fried vegetables" at noon. It can be determined that the recommendation parameters of the candidate recommendation words "millet porridge" and "fried dough sticks" in the morning are greater than the recommendation parameters of the candidate recommendation words "steamed egg" and "fried vegetables" in the morning, and the recommendation parameters of the candidate recommendation words "millet porridge" and "fried dough sticks" at noon are less than the recommendation parameters of the candidate recommendation words "steamed egg" and "fried vegetables" at noon.

[0156] When the time when the user inputs the search word in the second attribute tag is morning, a recommended word set including millet porridge and fried dough sticks is obtained from the candidate recommended word set according to the recommendation parameters of the candidate recommended words.

[0157] In other possible implementations, the recommendation parameters of the candidate recommendation words can also be determined based on the search frequency and the search time period. For example, the search frequency accounts for 70%, and the search time accounts for 30%. When it is determined that the recommendation parameter of a candidate recommendation word under the search frequency is B1, and the recommendation parameter of the candidate recommendation word under the search time is C1, then the recommendation parameter of the candidate recommendation word is determined to be 0.7B1+0.3C1. By obtaining the recommendation parameters corresponding to each candidate recommendation word in turn, a preset number of candidate recommendation words with the highest recommendation parameters are selected as the recommendation word set.

[0158] Figure 4is a schematic diagram of a recommended word determination device provided by an embodiment of the present disclosure. Figure 4 As shown, the recommendation word determination device includes:

[0159] A first search result display module 410 is used to receive a search term and display a first search result corresponding to the search term under a first attribute tag on a search result page; wherein the search result page includes a plurality of attribute tags, and the attribute of the first search result matches the first attribute tag;

[0160] A second search result display module 420, for displaying a second search result corresponding to the search term under a second attribute tag on a search result page in response to a switching operation of the attribute tag, wherein the attribute of the second search result matches the second attribute tag;

[0161] The recommended word set display module 430 is used to display the recommended word set on the search intermediate page in response to a triggering operation on the search box in the search result page, where the recommended word set is determined based on the search word and the second attribute tag.

[0162] The recommended word determination device provided by the embodiment of the present disclosure is characterized in that a first search result display page receives a search word, and displays a first search result corresponding to the search word under a first attribute tag on the search result page; wherein the search result page includes multiple attribute tags, and the attribute of the first search result matches the first attribute tag; the second search result display page responds to the switching operation of the attribute tag and displays a second search result corresponding to the search word under a second attribute tag on the search result page, and the attribute of the second search result matches the second attribute tag; the recommended word set display module responds to the triggering operation of the search box in the search result page and displays a recommended word set on the search middle page; the recommended word set is determined based on the search word and the second attribute tag, so that when the user switches to different attribute tags for searching, the recommended word set displayed to the user in the search result page is associated according to the user's search needs, and the recommended word set is more relevant to the user's search word and the switched attribute tag.

[0163] Optionally, the recommendation word determination device is further used to implement:

[0164] Determining an expansion word based on the second attribute tag;

[0165] The candidate recommended words and the extended words corresponding to the search words are concatenated and combined to generate target recommended words, so as to obtain a recommended word set.

[0166] Optionally, the recommendation word determination device is further used to implement:

[0167] Based on the second attribute tag, obtaining a first recommended word subset from the first recommended word set, and obtaining a second recommended word subset from the second recommended word set; wherein the recommended words in the first recommended word subset and the second recommended word subset match the second attribute tag;

[0168] The recommended words in the first recommended word subset and the second recommended word subset are processed and concatenated to obtain a recommended word set.

[0169] Optionally, a specific implementation of the recommendation word set display module includes:

[0170] In response to triggering the focus of the search box in the search results page, displaying the recommended word set on the search intermediate page;

[0171] or,

[0172] In response to deleting the search term in the search box on the search results page, displaying a set of recommended terms on the search intermediate page;

[0173] or,

[0174] In response to triggering a target control corresponding to a search box in a search results page, a set of recommended words is displayed on a search intermediate page.

[0175] Optionally, also include:

[0176] A target search result, which is used to display a target search result matching the target recommendation word and the second attribute tag on a search result page in response to a trigger operation on any target recommendation word in the recommendation word set; or

[0177] In response to a triggering operation on any target recommended word in the recommended word set, a target search result matching the target recommended word is displayed on the search result page, wherein the target search result includes a third search result corresponding to the target search word under different attribute tags, and a search result in the third search result whose attribute tag matches the second attribute tag is displayed with a higher priority than a search result in the third search result whose attribute tag does not match the second attribute tag.

[0178] Figure 5 is a schematic diagram of the structure of another device for determining a recommendation word provided by an embodiment of the present disclosure. Figure 5 As shown, the recommendation word determination device includes:

[0179] The request receiving module 510 is used to receive a recommendation word set acquisition request sent by a client, wherein the recommendation word set acquisition request includes an attribute tag and a search word, and the recommendation word set acquisition request is used to request to acquire a recommendation word set;

[0180] The recommended word set acquisition module 520 is used to acquire a recommended word set based on the attribute tag and the search word, wherein the recommended words in the recommended word set match the second attribute tag.

[0181] In the recommended word determination device provided by the embodiment of the present disclosure, after the request receiving module receives the recommended word acquisition request sent by the client, the recommended word set acquisition module acquires the recommended word set based on the second attribute tag and the search word included in the recommended word acquisition request, so that when the user switches to different attribute tags for searching, the recommended word set displayed to the user in the search results page is associated according to the user's search needs, and the recommended word set is more relevant to the user's search word and the switched attribute tag.

[0182] Optionally, another possible implementation of the recommendation word set acquisition module includes:

[0183] Based on the second attribute tag and the search term, a set of recommended terms corresponding to the second attribute tag and the search term is obtained from a database.

[0184] Optionally, also include:

[0185] A historical search term acquisition module, used for historical search terms including search terms;

[0186] The recommended word set screening module is used to screen out the recommended word set matching the second attribute tag from the historical search words.

[0187] Optionally, also include:

[0188] A historical search result acquisition module is used to acquire historical search results of a search term;

[0189] A candidate recommendation word acquisition module is used to obtain candidate recommendation words corresponding to historical search results;

[0190] The recommendation word set matching module is used to obtain a recommendation word set matching the second attribute tag from the candidate recommendation words.

[0191] Optionally, a possible implementation of the recommendation word set matching module includes:

[0192] Based on the second attribute tag and the interactive data of the candidate recommendation words, a set of candidate recommendation words that match the second attribute tag is obtained from the candidate recommendation words.

[0193] Optionally, the recommendation word set matching module includes:

[0194] A candidate recommendation word set acquisition unit, used to acquire a candidate recommendation word set matching the second attribute tag from the candidate recommendation words;

[0195] A recommendation parameter determination unit, configured to determine a recommendation parameter of a candidate recommendation word in the candidate recommendation word set based on the interaction data of the candidate recommendation word;

[0196] The recommendation word set acquisition unit is used to acquire a recommendation word set from the candidate recommendation word set based on the recommendation parameters of the candidate recommendation words in the candidate recommendation word set.

[0197] Optionally, the interaction data includes search frequency, search time period and / or browsing behavior.

[0198] It is worth noting that in the embodiment of the above-mentioned device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0199] The device provided by the embodiment of the present invention can execute the method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0200] Figure 6 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure, such as Figure 6 As shown, the electronic device includes a processor 610, a memory 620, an input device 630, and an output device 640; the number of the processor 610 in the electronic device can be one or more. Figure 6 A processor 610 is taken as an example; the processor 610, the memory 620, the input device 630 and the output device 640 in the electronic device can be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0201] The memory 620 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the method in the embodiment of the present invention. The processor 610 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 620, that is, implements the method provided in the embodiment of the present invention.

[0202] The memory 620 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 620 may further include a memory remotely arranged relative to the processor 610, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0203] The input device 630 can be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device, and can include a keyboard, a mouse, etc. The output device 640 can include a display device such as a display screen.

[0204] The embodiment of the present disclosure also provides a storage medium containing computer executable instructions, and the computer executable instructions are used to implement the method provided by the embodiment of the present disclosure when executed by a computer processor.

[0205] Of course, the computer executable instructions of a storage medium including computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, but can also execute related operations in the method provided by any embodiment of the present invention.

[0206] The present disclosure further provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the method of the application program in the above embodiment.

[0207] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0208] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be 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 the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a recommendation word, characterized in that: include: Receiving a search term, and displaying a first search result corresponding to the search term under a first attribute tag on a search result page; wherein the search result page includes a plurality of attribute tags, and an attribute of the first search result matches the first attribute tag; In response to the switching operation of the attribute label, displaying a second search result corresponding to the search term under a second attribute label on the search result page, wherein the attribute of the second search result matches the second attribute label; In response to a triggering operation on a search box in the search results page, displaying a set of recommended words on a search intermediate page, wherein the set of recommended words is determined based on the search words and the second attribute tag; The recommended word set is determined based on the search word and the second attribute tag, including: Based on the second attribute tag, a first recommended word subset is obtained from a first recommended word set corresponding to the search word; a second recommended word subset is obtained from a second recommended word set corresponding to the second attribute tag; recommended words of the first recommended word subset and the second recommended word subset are matched with the second attribute tag; The recommended words in the first recommended word subset and the second recommended word subset are processed and concatenated to obtain the recommended word set.

2. The method according to claim 1, characterized in that The recommendation word set is determined based on the search word and the second attribute tag, and further includes: determining an expansion word based on the second attribute tag; The candidate recommended words and the extended words corresponding to the search words are concatenated and combined to generate target recommended words, so as to obtain the recommended word set.

3. The method according to claim 1, characterized in that The step of displaying a set of recommended words on a search intermediate page in response to a triggering operation on a search box in the search result page includes: In response to triggering the focus of the search box in the search results page, displaying a set of recommended words on a search intermediate page; or, In response to deleting the search term in the search box on the search results page, displaying a set of recommended terms on a search intermediate page; or, In response to triggering a target control corresponding to a search box in the search results page, a set of recommended words is displayed on a search intermediate page.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: In response to a triggering operation on any target recommended word in the recommended word set, displaying a target search result matching the target recommended word and the second attribute tag on a search result page; or, In response to a triggering operation on any target recommended word in the recommendation word set, a target search result matching the target recommended word is displayed on a search result page, wherein the target search result includes a third search result corresponding to the target search word under a different attribute label, and a search result in the third search result whose attribute label matches the second attribute label is displayed with a higher priority than a search result in the third search result whose attribute label does not match the second attribute label.

5. A method for determining a recommendation word, characterized in that: include: receiving a recommendation word set acquisition request sent by a client, wherein the recommendation word set acquisition request includes a second attribute tag and a search word, and the recommendation word set acquisition request is used to request acquisition of a recommendation word set; Based on the second attribute tag and the search word, obtaining a recommended word set, wherein the recommended words in the recommended word set match the second attribute tag; The acquiring of a set of recommended words based on the second attribute tag and the search word includes: Based on the second attribute tag, a first recommended word subset is obtained from a first recommended word set corresponding to the search word; a second recommended word subset is obtained from a second recommended word set corresponding to the second attribute tag; recommended words of the first recommended word subset and the second recommended word subset are matched with the second attribute tag; Processing and concatenating the recommended words in the first recommended word subset and the second recommended word subset to obtain the recommended word set; The receiving of the recommendation word set acquisition request sent by the client includes: when the user enters a search word in the search box and switches to the second attribute label, a search operation is triggered, and the server receives the recommendation word set acquisition request sent by the client.

6. The method according to claim 5, characterized in that The acquiring a set of recommended words based on the second attribute tag and the search word further includes: Based on the second attribute tag and the search term, a set of recommended terms corresponding to the second attribute tag and the search term is obtained from a database.

7. The method according to claim 6, characterized in that Before acquiring a set of recommended words corresponding to the second attribute tag and the search word from a database based on the second attribute tag and the search word, the method further includes: Acquire historical search terms including the search terms; A set of recommended words matching the second attribute tag is filtered out from the historical search words.

8. The method according to claim 6, characterized in that Before acquiring a set of recommended words corresponding to the second attribute tag and the search word from a database based on the second attribute tag and the search word, the method further includes: Obtain historical search results for the search term; Obtain candidate recommendation words corresponding to the historical search results; A set of recommended words matching the second attribute label is obtained from the candidate recommended words.

9. The method according to claim 8, characterized in that The acquiring, based on the second attribute label, a set of recommendation words matching the second attribute label from the candidate recommendation words includes: Based on the interaction data of the second attribute label and the candidate recommendation words, a set of recommendation words matching the second attribute label is obtained from the candidate recommendation words.

10. The method according to claim 9, characterized in that The step of acquiring a set of recommended words matching the second attribute label from the candidate recommended words based on the interaction data of the second attribute label and the candidate recommended words includes: Acquire a set of candidate recommendation words matching the second attribute label from the candidate recommendation words; Determining recommendation parameters of candidate recommendation words in the candidate recommendation word set based on the interaction data of the candidate recommendation words; Based on the recommendation parameters of the candidate recommendation words in the candidate recommendation word set, a recommendation word set is obtained from the candidate recommendation word set.

11. The method according to claim 10, characterized in that The interaction data includes search frequency, search time period and / or browsing behavior.

12. A device for determining a recommendation word, characterized in that: include: A first search result display module, configured to receive a search term and display a first search result corresponding to the search term under a first attribute tag on a search result page; wherein the search result page includes a plurality of attribute tags, and an attribute of the first search result matches the first attribute tag; A second search result display module, configured to display, in response to a switching operation of an attribute tag, a second search result corresponding to the search term under a second attribute tag on the search result page, wherein an attribute of the second search result matches the second attribute tag; A recommended word set display module, configured to display a recommended word set on a search intermediate page in response to a triggering operation on a search box in the search result page, wherein the recommended word set is determined based on the search word and the second attribute tag; The recommended word set is determined based on the search word and the second attribute tag, including: Based on the second attribute tag, a first recommended word subset is obtained from a first recommended word set corresponding to the search word; a second recommended word subset is obtained from a second recommended word set corresponding to the second attribute tag; recommended words of the first recommended word subset and the second recommended word subset are matched with the second attribute tag; The recommended words in the first recommended word subset and the second recommended word subset are processed and concatenated to obtain the recommended word set.

13. A device for determining a recommendation word, characterized in that: include: A request receiving module, configured to receive a recommendation word set acquisition request sent by a client, wherein the recommendation word set acquisition request includes a second attribute tag and a search word, and the recommendation word set acquisition request is used to request acquisition of a recommendation word set; a recommendation word set acquisition module, configured to acquire a recommendation word set based on the second attribute tag and the search word, wherein the recommendation words in the recommendation word set match the second attribute tag; The acquiring of a set of recommended words based on the second attribute tag and the search word includes: Based on the second attribute tag, a first recommended word subset is obtained from a first recommended word set corresponding to the search word; a second recommended word subset is obtained from a second recommended word set corresponding to the second attribute tag; recommended words of the first recommended word subset and the second recommended word subset are matched with the second attribute tag; Processing and concatenating the recommended words in the first recommended word subset and the second recommended word subset to obtain the recommended word set; The receiving of the recommendation word set acquisition request sent by the client includes: when the user enters a search word in the search box and switches to the second attribute label, a search operation is triggered, and the server receives the recommendation word set acquisition request sent by the client.

14. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4 or the method according to any one of claims 5 to 11.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 or the method according to any one of claims 5 to 11 is implemented.

Images