Information recommendation method and device

Abstract

The embodiment of the present disclosure provides an information recommendation method and device, the method comprises: obtaining a search demand feature of a user, and determining a target entity matched with the search demand feature and a target entity category of the target entity from an entity library; determining at least one attribute information corresponding to the target entity based on the target entity category, wherein the entity library comprises a plurality of entities and at least one attribute information corresponding to each entity category of each entity; generating a recommendation word based on the at least one attribute information corresponding to the target entity, and sending the recommendation word to a terminal of the user, improving the accuracy of the determined recommendation word, after obtaining the recommendation word, sending the recommendation word to the terminal of the user, realizing accurate personalized recommendation, so that the user can select a required keyword from the recommendation word, without manually inputting the keyword, thereby reducing the search cost of the user.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to an information recommendation method and device. Background Technology

[0002] With the advent of the information age, users can search on relevant websites to obtain the information they need. When a user initiates a search, they need to enter keywords on the website's search page. To make the user's input faster, search terms can be recommended. Users can choose the desired keywords from the recommended search terms, eliminating the need to manually enter keywords and thus reducing the user's search costs.

[0003] However, the inventors discovered that the current search recommendations may not be what users need; that is, the accuracy of the recommended search terms is low, and they have not reduced the user's search costs. Summary of the Invention

[0004] This disclosure provides an information recommendation method and apparatus to overcome the problem of low accuracy of existing recommended search terms.

[0005] In a first aspect, embodiments of this disclosure provide an information recommendation method, including:

[0006] Obtain the user's search demand characteristics, and determine the target entities that match the search demand characteristics and the target entity categories of the target entities from the entity database;

[0007] Based on the target entity category, at least one attribute information corresponding to the target entity is determined, wherein the entity library includes multiple entities and at least one attribute information corresponding to each entity category of each entity;

[0008] Recommended words are generated based on at least one attribute information corresponding to the target entity, and the recommended words are sent to the user's terminal.

[0009] Secondly, embodiments of this disclosure provide an information recommendation method applied to a terminal, comprising:

[0010] In response to the first triggering operation, a recommendation keyword push request is sent to the server;

[0011] The server retrieves and displays the recommended words sent by the server; wherein the recommended words are generated by the server after determining the user's search demand characteristics based on the recommended word push request, identifying target entities that match the search demand characteristics from the entity database, and generating them based on at least one attribute information corresponding to the target entities.

[0012] Thirdly, embodiments of this disclosure provide an information recommendation device, including:

[0013] The entity determination module is used to acquire the user's search demand characteristics and determine the target entity that matches the search demand characteristics and the target entity category of the target entity from the entity database;

[0014] An attribute determination module is used to determine at least one attribute information corresponding to the target entity based on the target entity category, wherein the entity library includes multiple entities and at least one attribute information corresponding to each entity category of each entity;

[0015] The first transceiver module is used to generate recommendation words based on at least one attribute information corresponding to the target entity, and send the recommendation words to the user's terminal.

[0016] Fourthly, embodiments of this disclosure provide an information recommendation device applied to a terminal, comprising:

[0017] The second transceiver module is used to send a recommendation word push request to the server in response to the first trigger operation;

[0018] The display module is used to obtain and display the recommended words sent by the server; wherein the recommended words are generated by the server after determining the user's search demand characteristics based on the recommended word push request, determining the target entity that matches the search demand characteristics from the entity database, and based on at least one attribute information corresponding to the target entity.

[0019] Fifthly, embodiments of this disclosure provide an electronic device, including at least one processor and a memory.

[0020] The memory stores computer-executed instructions.

[0021] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the information recommendation method as described in the first aspect and various possible designs of the first aspect.

[0022] In a sixth aspect, embodiments of this disclosure provide an electronic device, including at least one processor and a memory.

[0023] The memory stores computer-executed instructions.

[0024] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the information recommendation method as described in the second aspect above and various possible designs of the second aspect.

[0025] In a seventh aspect, embodiments of this disclosure provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the information recommendation method described in the first aspect and various possible designs of the first aspect.

[0026] Eighthly, embodiments of this disclosure provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the information recommendation method described in the second aspect above and various possible designs of the second aspect.

[0027] This disclosure provides an information recommendation method and apparatus. The method includes acquiring a user's search demand characteristics and determining target entities and target entity categories matching the search demand characteristics from an entity database; determining at least one attribute information corresponding to the target entity based on the target entity category, wherein the entity database includes multiple entities and at least one attribute information corresponding to each entity category of each entity; generating recommendation words based on the at least one attribute information corresponding to the target entity; and sending the recommendation words to the user's terminal. This disclosure improves the accuracy of the determined recommendation words by searching the entity database for target entities and target entity categories matching the user's search demand characteristics when determining the user's search recommendation words, i.e., determining the target entities and target entity categories matching the user's characteristics, i.e., search demand, based on user characteristics. Generating corresponding recommendation words based on the attribute information corresponding to the target entity category of the target entity, i.e., generating recommendation words that meet the user's search needs, and sending the recommendation words to the user's terminal after obtaining them, achieves accurate personalized recommendations. This allows users to select desired keywords from the recommendation words without manually entering keywords, thereby reducing the user's search cost. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 Example of a search page provided for embodiments of this disclosure Figure 1 ;

[0030] Figure 2 A schematic diagram of an information recommendation system provided in an embodiment of this disclosure;

[0031] Figure 3Flowchart of the information recommendation method provided in the embodiments of this disclosure Figure 1 ;

[0032] Figure 4 Flowchart of the information recommendation method provided in the embodiments of this disclosure Figure 2 ;

[0033] Figure 5 A schematic diagram of the entity objects provided in the embodiments of this disclosure;

[0034] Figure 6 Flowchart of the information recommendation method provided in the embodiments of this disclosure Figure 3 ;

[0035] Figure 7 Example of a search page provided for embodiments of this disclosure Figure 2 ;

[0036] Figure 8 Structural framework of the information recommendation device provided in the embodiments of this disclosure Figure 1 ;

[0037] Figure 9 Structural framework of the information recommendation device provided in the embodiments of this disclosure Figure 2 ;

[0038] Figure 10 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0040] See Figure 1 , Figure 1 This is an example diagram of a search page in existing technology. When a user initiates a search, they can... Figure 1 When users enter keywords into the search box on a search page, the system can recommend search terms to speed up the process. These terms can be popular search terms, allowing users to choose the desired keywords without manually entering them, thus reducing search costs. However, if the recommended search terms are not what the user needs, meaning their accuracy is low, the system may not actually reduce search costs.

[0041] Therefore, to address the aforementioned problems, the technical concept of this invention is to determine the user's corresponding search demand characteristics, i.e., search demand, when the user accesses the site, and then search the entity database for entities and entity categories that match these search demand characteristics, thereby obtaining target entities and target entity categories. The invention also retrieves the attribute information corresponding to the target entity category from the entity database, and determines the corresponding recommended words based on this attribute information. This yields feature words that match the user's characteristics, i.e., search demand, thus achieving accurate determination of recommended words, improving the accuracy of recommended search terms, and realizing personalized recommendations. Furthermore, after creating and generating the entity database, it can be continuously updated and expanded, thereby recommending more and better recommended words to the user.

[0042] See Figure 2 , Figure 2 This is a schematic diagram of an information recommendation system provided in an embodiment of this disclosure. The display system includes a user terminal 101 and an information recommendation device 102. The user terminal 101 acquires the recommended words generated by the information recommendation device 102 and displays the recommended words so that the user currently using the user terminal can select the desired recommended words, i.e., search terms, from the recommended words.

[0043] The information recommendation device 102 is a server, terminal, or other electronic device capable of processing data. The user terminal 101 is a mobile terminal, computer, or other device capable of displaying web pages.

[0044] refer to Figure 3 , Figure 3 Flowchart of the information recommendation method provided in the embodiments of this disclosure Figure 1 The method in this embodiment can be applied to... Figure 2 In the information recommendation device, the information recommendation method includes:

[0045] S301. Obtain the user's search demand characteristics, and determine the target entity and the target entity category of the target entity that match the search demand characteristics from the entity library, wherein the entity library includes multiple entities and at least one attribute information corresponding to each entity category of each entity.

[0046] In this embodiment of the disclosure, when a user needs to perform a search, the user's search request characteristics are obtained, i.e., the user's search request is determined, and entities matching the search request are searched from the entity database, i.e., entities that conform to the user's characteristics are determined from the target entity database and identified as target entities. Since an entity includes entities of at least one entity category, it is also necessary to determine the entity category that matches the search request and identify it as the target entity category, so that the required entity can be determined based on the target entity category and the target entity.

[0047] The entity library includes multiple entities, and each entity has at least one entity category. For example, the entity library includes two entities, Xiaoming and Xiaohong. Xiaoming's entity category includes painter and singer, which means that there exists a Xiaoming who is a painter and a Xiaoming who is a singer.

[0048] Each entity category in the entity database corresponds to at least one attribute information, which is used to describe the corresponding entity, that is, to represent the entity's attributes and characteristics.

[0049] Optionally, attribute information includes necessary attribute information and basic attribute information. Necessary attribute information represents the essential attributes of an entity, that is, attributes that will not change, such as the entity's height, nationality, place of birth, etc. Basic attribute information represents the entity's basic attributes, which can more vividly and richly represent the entity object. Basic attribute information generally represents attributes that change over time. For example, when the entity is a singer, its corresponding basic attribute information includes attributes such as musical works and awards received.

[0050] The attribute information includes the attribute name and / or the attribute value corresponding to the attribute name. For example, the painter Xiaoming's height is 1.8 meters. Accordingly, Xiaoming is an entity, painter is its corresponding entity category, height is an attribute name, and 1.8 meters is an attribute value.

[0051] The entity category is determined by relevant classification rules, such as primary and secondary classifications. Relevant R&D personnel can classify according to actual needs, and the attribute names included in the attribute information can also be set according to actual needs. There are no restrictions on either.

[0052] S302. Determine at least one attribute information corresponding to the target entity based on the target entity category.

[0053] In this embodiment of the disclosure, after determining the entity and entity category required by the user, i.e. the target entity and the target entity category, the attribute information corresponding to the target entity and the target entity category is determined from the entity library, and is used as at least one attribute information corresponding to the target entity, so as to use the at least one attribute information to determine the search term required by the user, i.e., to determine the corresponding recommended term.

[0054] S303. Generate recommended words based on at least one attribute information corresponding to the target entity, and send the recommended words to the user's terminal.

[0055] In this embodiment of the disclosure, after obtaining at least one attribute information corresponding to the target entity that matches the user's characteristics, the at least one attribute information is used to generate recommended words, i.e. recommended search terms, and the recommended words are pushed to the user so that the user can select the recommended words they need from the recommended words, thereby reducing the user's search cost.

[0056] As described above, when determining a user's search terms, the system searches the entity database for target entities and their categories that match the user's search needs. In other words, it determines the target entities and their categories that match the user's characteristics, i.e., their search needs. Based on the attribute information corresponding to the target entity's category, it generates corresponding recommended terms that satisfy the user's search needs, improving the accuracy of the determined recommended terms. After obtaining these recommended terms, they are sent to the user's terminal, achieving accurate personalized recommendations. This allows the user to select the desired keywords from the recommended terms without manually entering them, thus reducing the user's search cost.

[0057] refer to Figure 4 , Figure 4 Flowchart of the information recommendation method provided in the embodiments of this disclosure Figure 2 This embodiment describes in detail the process of quickly updating the entity database, and the recommended methods include:

[0058] S401. Obtain the entity to be processed and determine the entity category corresponding to the entity to be processed.

[0059] In this embodiment of the disclosure, when a new entity is obtained, it indicates that the entity library can be automatically updated using the new entity. The new entity is then taken as the entity to be processed, and the entity category to which the entity to be processed belongs is obtained, i.e., the corresponding entity category.

[0060] Optionally, when obtaining new entities, they can be input or sent by relevant personnel, or they can be determined automatically, for example, by crawling web page information. Correspondingly, the entity category corresponding to the entity to be processed can also be input by relevant personnel or determined automatically; there are no restrictions on this.

[0061] S402. Obtain the attribute information corresponding to the entity category of the entity to be processed from the entity library, and determine it as the attribute information to be processed.

[0062] S403. Determine the attribute information corresponding to the entity to be processed based on the attribute information to be processed, and update the entity database based on the attribute information corresponding to the entity to be processed.

[0063] In this embodiment, upon obtaining the entity to be processed and its corresponding entity category, all attribute information corresponding to the entity category of the entity to be processed is retrieved from the entity database and used as the attribute information to be processed. This attribute information is then used to automatically determine the attribute information corresponding to the entity to be processed, eliminating the need for manual determination. After obtaining the attribute information corresponding to the entity to be processed, it is added to the entity database to achieve automatic updates. For example, if the new entity is "Xiao Li" and its corresponding entity category is "Singer," then all attribute information corresponding to the entity category "Singer" is searched in the entity database and determined as the attribute information corresponding to "Singer Xiao Li."

[0064] Optionally, in this embodiment of the disclosure, determining the attribute information corresponding to the entity to be processed based on the attribute information to be processed includes:

[0065] Use the attribute name in the attribute information to be processed as the attribute name corresponding to the entity to be processed.

[0066] Specifically, after obtaining the attribute information corresponding to the entity category of the entity to be processed, i.e., the attribute information to be processed, for each attribute name in the attribute information to be processed, that attribute name is used as the attribute name corresponding to the entity to be processed, that is, the attribute name is assigned to the entity to be processed. For example, if the attribute name corresponding to a singer includes musical works, then the musical works are also used as the attribute name corresponding to the singer Xiao Li.

[0067] In this embodiment, after obtaining the attribute name corresponding to the entity to be processed, the entity to be processed and its corresponding attribute name can be added to the entity database for subsequent determination of the attribute value corresponding to the attribute name using relevant data (e.g., webpage), thereby achieving automatic addition and updating of the attribute information of the entity to be processed. Alternatively, before adding the entity to be processed and its corresponding attribute name to the entity database, relevant data (e.g., webpage, user input / sent data) can be obtained to determine the attribute value corresponding to the attribute name, thereby determining the attribute information of the entity to be processed, and then adding the entity to be processed and its corresponding attribute information to the entity database.

[0068] Alternatively, when expanding the entity database with new entities, to avoid unnecessary expansion, only entities corresponding to popular types can be added to the entity database. The specific process includes: obtaining the entity category corresponding to the entity to be processed and obtaining the hot search category. When the entity category corresponding to the entity to be processed belongs to the hot search category, the entity database is updated according to the attribute information corresponding to the entity to be processed.

[0069] The trending search category can be the trending search type corresponding to a specific website, i.e., the popular search type. It is obtained by clustering analysis of the search behavior (e.g., search behavior information) of users visiting the website. Specifically, the trending search category can be determined based on the search behavior of users visiting the website on a given day, or it can be determined based on the search behavior of users visiting the website within a certain time period. There are no restrictions on this.

[0070] For example, if the hot search category is "pop stars", then when the entity category corresponding to the entity to be processed is "pop stars", the attribute information corresponding to the entity category corresponding to the entity to be processed is obtained from the entity database and identified as the attribute information to be processed. This attribute information is then used to determine the attribute information corresponding to the entity to be processed, and the entity database is updated based on the attribute information corresponding to the entity to be processed.

[0071] Optionally, since the attribute information of an entity may change, the entities in the entity database can also be updated. The specific process is as follows:

[0072] The system retrieves the webpage to be processed and determines the attribute information to be updated corresponding to the entity category of the entity to be updated, where the entity to be updated is an entity in the entity database. The entity database is then updated based on the attribute information to be updated corresponding to the entity category of the entity to be updated.

[0073] Specifically, upon obtaining a webpage (i.e., the webpage to be processed), the entities included in the webpage and their corresponding entity categories are acquired and identified as entities to be updated. By analyzing the webpage, attribute information corresponding to the entity categories of the entities to be updated is extracted and used as the attribute information to be updated. This attribute information is then used to update the attribute information of the corresponding entity categories in the entity database, achieving automatic updates to the entity database and ensuring the accuracy of the attribute information.

[0074] Optionally, when updating attribute information in the entity database, if the attribute value for the entity to be updated does not exist in the attribute value corresponding to the entity to be updated in the entity database, then the attribute value from the attribute information to be updated is added to the entity name corresponding to the entity to be updated in the entity database. For example, if the entity to be updated is Xiao Yang, and its corresponding entity category is movie actor, and the information to be updated for movie actor Xiao Li includes the movie "Movie 1", then it is determined whether the attribute value corresponding to the attribute name "Movie 1" for movie actor Xiao Li in the entity database includes "Movie 1". If it does, then there is no need to update the attribute value corresponding to the attribute name; if it does not, then "Movie 1" is used as the new attribute value corresponding to the attribute name.

[0075] Optionally, when updating attribute information in the entity database, if the attribute value corresponding to the entity to be updated in the entity database is inconsistent with the attribute value in the attribute information to be updated, then the attribute value corresponding to the entity to be updated in the entity database will be updated to the attribute value in the attribute information to be updated. For example, if the entity to be updated is Xiao Yang, and its corresponding entity category is "movie actor," and the determined update information for movie actor Xiao Li includes the number of movie works being 5, then the number of movie works corresponding to movie actor Xiao Li in the entity database will be retrieved. If the number of movie works corresponding to movie actor Xiao Li in the entity database is not 5, then the number of movie works will be modified to 5.

[0076] Of course, when updating attribute information in the entity database, other rules can also be followed. For example, if the attribute information of the entity to be updated corresponding to the entity category in the entity database does not include the attribute information to be updated, then the attribute information to be updated can be directly used as the new attribute information of the entity to be updated in the entity database.

[0077] Alternatively, to ensure the accuracy of attribute information in the entity database, the web pages to be processed can be retrieved periodically to update the entity database, thereby ensuring the accuracy and timeliness of the search terms recommended to users.

[0078] Furthermore, optionally, the webpage to be processed can be a webpage obtained through user search, or a webpage from a relevant website or system. The specific determination process involves: obtaining historical search terms and the corresponding interactive webpages; and / or obtaining target webpages from the target system. The interactive webpages and / or target webpages are then used as the webpages to be processed.

[0079] Specifically, when a user visits a website to obtain information, they typically enter a search term in the search box on the search page. The website's backend server (e.g., an information recommendation device) then responds to this search term (i.e., a historical search term) and pushes the corresponding webpage to the user. This webpage includes content related to the search term. If the user wants to view specific content, they can click the link to that specific content's page. The backend server responds to this click and pushes the page linked to that page to the user for viewing. This page is the interactive webpage corresponding to the search term. Alternatively, the webpage to be processed can also be a related website, i.e., a webpage displayed in the system.

[0080] Among them, historical search terms refer to the search terms entered by the user within a preset time period before the current moment.

[0081] It is important to understand that when a user enters a search term in the search box, the search term generally includes entities, and the entities in the search term can be used as the entities to be updated.

[0082] In any disclosed embodiment, optionally, when creating an entity library, entries can be used for creation, the specific process of which is as follows:

[0083] Retrieve multiple terms and the information corresponding to each term.

[0084] For each term, an initial entity is determined based on the term, and the entity category of the initial entity and at least one attribute information corresponding to each entity category are determined based on the information corresponding to the term.

[0085] An entity library is generated based on the initial entity and at least one attribute information corresponding to each entity category of the initial entity.

[0086] Specifically, upon acquiring terms, for each term, it is determined whether the term is an entity. If the term is an entity, it is used as the initial entity. Based on the information corresponding to the term, the entity category and attribute information corresponding to that entity category are determined, thus obtaining the attribute information for the initial entity. After obtaining each initial entity and its corresponding attribute information, these are combined to generate the desired entity library, resulting in a multi-relationship graph.

[0087] When obtaining entries and their corresponding information, one can collect entries and their corresponding information from third-party websites.

[0088] The information corresponding to an entry includes definition information, initial category, initial attribute information, and other information describing the entry.

[0089] The semantic information is used to distinguish between entries with the same name. For example, the entries include "Xiao Yang" and "Xiao Yang," but one "Xiao Yang" is defined as a tennis player, while the other is defined as a singer. The semantic information differentiates the two "Xiao Yang" entries. The initial category indicates the initial category corresponding to the entry. For example, the initial categories corresponding to "Xiao Yang" include singer and tennis player. The initial attribute information includes basic information about the entry, such as Xiao Yang's nationality. Other information describing the entry can include descriptive details, such as Xiao Yang's personal experiences.

[0090] Accordingly, the entity category corresponding to the entity in the term is determined based on the initial category in the term. For example, the entity categories corresponding to Xiao Yang include tennis player and singer. The attribute information corresponding to each entity category can be determined based on the initial attribute information in the term and other information describing the term. For example, the attribute information corresponding to singer Xiao Yang can be obtained using the initial attribute information corresponding to singer Xiao Yang and other information describing the term.

[0091] Optionally, since there are relationships between the initial entities, for example, Figure 5 Zhang San and Xiao Hong are both initial entities, and there is a relationship between them. Therefore, the initial entity objects with relationships can be associated and combined to construct a multi-relationship graph of entities.

[0092] Alternatively, the collected terms and their corresponding information can be stored in a database.

[0093] Specifically, when storing the collected terms and their corresponding information in the database, the information can be stored in a structured manner to facilitate the subsequent use of the terms and their corresponding information.

[0094] In addition, necessary labels can be attached to the initial entity, that is, the entity category corresponding to the initial entity can be determined.

[0095] Alternatively, the attribute information corresponding to the initial entities can be aligned, i.e., the initial entities can be unified. For example, if the initial entities include A and B, based on the attribute information corresponding to A and B, it can be determined that A and B refer to the same entity object, i.e., the same thing. Therefore, A and B can be aligned to achieve entity unification. After unifying the entity database, the sparsity of the entity database can be reduced.

[0096] The process of aligning the initial entities is an existing process and will not be described in detail here.

[0097] S404. Obtain the user's search demand characteristics, and determine the target entities that match the search demand characteristics and the target entity categories of the target entities from the entity database.

[0098] In this embodiment of the disclosure, upon receiving a recommendation term push request sent by the user's corresponding terminal, search behavior information corresponding to the user identifier in the recommendation term push request is obtained to acquire the user's corresponding search behavior information. The search behavior information includes one or more combinations of the following: the first search term entered by the user, the order of the first search terms, the interaction results corresponding to the first search term, and the web pages visited by the user. Feature word extraction and feature dimension analysis are performed on the user's search behavior information to obtain the user's search demand characteristics, wherein the search demand characteristics include search feature words and search categories.

[0099] Specifically, upon receiving a recommendation term push request from a user's terminal, it indicates the need to determine the corresponding recommendation terms for that user, i.e., to push the search terms to that user. The system then extracts the user's identifier from the recommendation term push request and searches for the search behavior information corresponding to that identifier, thus obtaining the user's search behavior information. After obtaining the user's search behavior information, feature word extraction and feature dimension analysis are performed to determine the user's search demand characteristics, i.e., to identify the user's search needs. This information is then used to determine recommendation terms that match the user's characteristics, i.e., their search needs.

[0100] The user's search behavior information includes the user's search behavior information within a historical preset time period and / or the search behavior information whose corresponding search session identifier is the current search session identifier.

[0101] Accordingly, when the user's search behavior information includes the user's search behavior information within a historical preset time period, the first search term represents the search term entered by the user within that historical preset time period. The order of the first search terms is obtained by sorting the first search terms according to the input time (e.g., from late to early). The interaction results corresponding to the first search term represent the webpages displayed when the user entered the first search term. The webpages visited by the user represent the search terms entered by the user within the historical preset time period.

[0102] Accordingly, when the recommendation term push request includes the current search session identifier, the user's corresponding search behavior information includes search behavior information where the user's corresponding search session identifier is the current search session identifier. The first search term represents the search term entered by the user during the current search session, and the order of the first search terms is obtained by sorting the first search terms according to the input time (e.g., from latest to earliest). The interaction results corresponding to the first search term represent the webpages displayed when the user entered the first search term. The webpages visited by the user represent the search terms entered by the user during the current search session.

[0103] The process of extracting feature words and analyzing feature dimensions from user search behavior information is similar to the existing feature word extraction and feature dimension analysis process, and will not be elaborated here.

[0104] S405. Determine at least one attribute information corresponding to the target entity based on the target entity category, wherein the entity library includes multiple entities and at least one attribute information corresponding to each entity category of each entity.

[0105] In this embodiment of the disclosure, after obtaining the user's search demand characteristics, i.e., obtaining the user's corresponding search terminology and search category, indicating that the user's search demand has been determined, entities matching the search terminology are identified from the entity database and used as target entities. Then, from the various entity categories of the target entities in the entity database, entity categories matching the search category are identified and used as target entity categories.

[0106] Specifically, when identifying entities matching search terms from entity classes, one can search for entities identical to the search term and designate them as target entities, or one can search for entities with high similarity to the search term and designate them as target entities. Similarly, following the process of identifying entities matching search terms from entity classes, one can identify entity categories matching the search category from the entity database.

[0107] S406. Generate recommended words based on at least one attribute information corresponding to the target entity, and send the recommended words to the user's terminal.

[0108] In this embodiment of the disclosure, the target entity and at least one attribute information corresponding to the target entity are combined to obtain multiple candidate recommendation words. The multiple candidate recommendation words are sorted, and a recommendation word is selected from the sorted candidate recommendation words.

[0109] Specifically, after obtaining the attribute information corresponding to the target entity, the target entity is combined with each attribute information to generate one or more candidate recommendation words. When there are multiple candidate recommendation words, these multiple candidate recommendation words are sorted to obtain sorted candidate recommendation words. In descending order, a preset number of candidate recommendation words are selected from the sorted candidate recommendation words and determined as recommendation words, that is, the candidate recommendation words that the user is most likely to be interested in are determined as recommendation words.

[0110] Specifically, when there are many candidate keywords, presenting all of them to the user could lead to significant time constraints, causing inconvenience. To reduce this time, only keywords of interest to the user can be displayed. Furthermore, multiple candidate keywords are sorted according to a preset ranking rule, and the highest-ranking keywords are selected from the sorted list to provide the most relevant recommendations.

[0111] The preset sorting rules can be based on the user's search terms, visited web pages, or other frequently visited web pages and search terms entered by the user some time before the current moment to determine the attributes the user is interested in. Of course, relevant personnel can set preset sorting rules according to actual needs; for example, static attributes may be ranked lower.

[0112] In this embodiment of the disclosure, after the entity library is generated, it can be continuously expanded and updated so that when generating recommended terms, the expanded and updated entity library is used to determine the search terms recommended to the user, i.e., recommended terms, thereby providing the user with a massive set of high-quality candidates and a richer set of search terms to meet the user's search needs.

[0113] In this embodiment, a new entity, i.e. the entity category corresponding to the entity to be processed, is determined. An entity category with the same entity category as the entity to be processed is searched in the entity database. The attribute name corresponding to the same entity category is used as the attribute name of the entity to be processed. This realizes the automatic determination of the attributes of the entity to be processed without the need for manual editing of the relevant attributes of the entity to be processed. Furthermore, the entity database is updated using the attributes of the entity to be processed, realizing the automatic update and expansion of the entity database, effectively improving the update efficiency of the entity database, and providing a more massive candidate set for subsequent determination of recommended words.

[0114] refer to Figure 6 , Figure 6 Flowchart of the information recommendation method provided in the embodiments of this disclosure Figure 3 The method in this embodiment can be applied to... Figure 2 In the terminals mentioned above, the information recommendation methods include:

[0115] S601. In response to the first trigger operation, a recommendation word push request is sent to the server.

[0116] In this embodiment of the disclosure, when a user inputs a first trigger operation, indicating that a corresponding search term needs to be recommended to the user, then in response to the first trigger operation, a corresponding recommendation term push request is sent to the server, so that when the server receives the recommendation term push request, it determines a recommendation term that matches the user's characteristics.

[0117] Optionally, the first triggering action can be the user opening a webpage, website, application, or the user entering search terms in the search box on the webpage.

[0118] Terminals include mobile devices (e.g., mobile phones, tablets, etc.) and terminal equipment (e.g., computers).

[0119] S602. Obtain the recommended words sent by the server and display the recommended words. The recommended words are generated by the server after determining the user's search needs based on the recommended word push request, identifying target entities matching the search needs from the entity database, and based on at least one attribute information corresponding to the target entity.

[0120] In this embodiment of the disclosure, the server determines recommended terms that match the user's search needs (i.e., characteristics) based on the recommendation term request sent by the terminal, and pushes the recommended terms to the terminal. Upon receiving the recommended terms from the server, the terminal displays the recommended terms so that the user can select the desired terms from them.

[0121] Optionally, if a first interface is provided via a terminal, and the first interface includes a search bar, then displaying recommended words may include: displaying recommended words in a drop-down box corresponding to the search bar, or displaying recommended words within the search bar.

[0122] Alternatively, upon receiving a second trigger action applied to the first button or search bar, a search intermediate page is displayed, and recommended terms are shown in a first preset position on the search intermediate page.

[0123] Specifically, when displaying received recommended terms, the recommended term can be shown in the drop-down box corresponding to the search bar on the first page of the terminal interface (e.g., ...). Figure 7 (As shown), this allows users to select the desired recommended terms from a drop-down menu. Alternatively, recommended terms can be displayed directly within the search bar, allowing users to directly use those terms for their searches.

[0124] Specifically, when the corresponding trigger operation is entered on the first button or search bar on the first interface, i.e., the second trigger operation, the user is redirected to another page, i.e. the search intermediate page, to display recommended words in the first preset position in the search intermediate page.

[0125] The first button can be a designated button on the first interface, such as the search button, or any other button; there are no restrictions on it.

[0126] The second triggering operation can be a click, touch, or other similar action.

[0127] The first preset position can be set according to actual needs. For example, the first preset position can be inside the search bar on the search middle page, below the search bar, the bottom area, the middle area, or the top area of ​​the search middle page. There are no restrictions on it.

[0128] Alternatively, when within the same search session, recommended terms can be displayed in the dropdown menu corresponding to the search bar, or within the search bar itself. Alternatively, upon receiving a second trigger action applied to the first button or the search bar, a search intermediary page can be displayed, and recommended terms can be displayed in a first preset position within that page.

[0129] Optionally, if a second interface is provided via the terminal, the recommended words can be displayed by: in response to the first triggering operation, displaying the recommended words at a second preset position in the second interface.

[0130] Specifically, it can also be displayed based on the first trigger operation input by the user. That is, when the first trigger operation input by the user is received, it is displayed in the second preset position on the currently displayed page of the terminal, that is, on the second page.

[0131] The second preset position can be set according to actual needs. For example, the second preset position can be the bottom area, middle area, or top area of ​​the second page. There are no restrictions on it.

[0132] Alternatively, the second page can be a feed page.

[0133] In this embodiment, upon receiving a first trigger operation input by the user, a recommendation word push request corresponding to the user is generated and sent to the server. The server then generates recommendation words that match the user's search needs, i.e., characteristics, based on the recommendation word push request and the entity database. The recommended words sent by the server are retrieved and displayed for the user to select, eliminating the need for the user to input search terms, thus reducing the user's search cost and improving the efficiency of information retrieval.

[0134] Corresponding to the information recommendation method in the above embodiments, Figure 8 Structural framework of the information recommendation device provided in the embodiments of this disclosure Figure 1 For ease of explanation, only the parts relevant to embodiments of this disclosure are shown.

[0135] Reference Figure 8 Information recommendation devices include:

[0136] The entity determination module 801 is used to obtain the user's search demand characteristics and determine the target entity and the target entity category of the target entity that match the search demand characteristics from the entity library. The entity library includes multiple entities and at least one attribute information corresponding to each entity category of each entity.

[0137] The attribute determination module 802 is used to determine at least one attribute information corresponding to the target entity based on the target entity category.

[0138] The first transceiver module 803 is used to generate recommendation words based on at least one attribute information corresponding to the target entity, and send the recommendation words to the user's terminal.

[0139] In one embodiment of this disclosure, the information recommendation device further includes a processing module, which is used to:

[0140] Obtain the entity to be processed and determine the entity category corresponding to the entity to be processed.

[0141] Retrieve the attribute information corresponding to the entity category of the entity to be processed from the entity database, and identify it as the attribute information to be processed.

[0142] The attribute information corresponding to the entity to be processed is determined based on the attribute information to be processed, and the entity database is updated based on the attribute information corresponding to the entity to be processed.

[0143] In one embodiment of this disclosure, the attribute information includes the attribute name.

[0144] The processing module is also used for:

[0145] Use the attribute name in the attribute information to be processed as the attribute name corresponding to the entity to be processed.

[0146] In one embodiment of this disclosure, the processing module is further configured to:

[0147] Obtain the webpage to be processed, and determine the attribute information to be updated corresponding to the entity category of the entity to be updated based on the webpage, where the entity to be updated is the entity in the entity database.

[0148] The entity database is updated based on the attribute information to be updated corresponding to the entity category of the entity to be updated.

[0149] In one embodiment of this disclosure, the processing module is further configured to:

[0150] Retrieve historical search terms and their corresponding interactive web pages. And / or, retrieve the target web page from the target system.

[0151] Treat interactive web pages and / or target web pages as web pages to be processed.

[0152] In one embodiment of this disclosure, the entity determination module 801 is further configured to: obtain the user's search request characteristics, including:

[0153] When a recommendation word push request is received from the user's corresponding terminal, the search behavior information corresponding to the user identifier in the recommendation word push request is obtained to obtain the user's corresponding search behavior information. The search behavior information includes one or more of the following combinations: the first search term entered by the user, the order of the first search terms, the interaction results corresponding to the first search term, and the web pages visited by the user.

[0154] By extracting feature words and analyzing feature dimensions from user search behavior information, we can obtain the user's search demand characteristics, which include search feature words and search categories.

[0155] In one embodiment of this disclosure, the entity determination module 801 is further configured to:

[0156] Identify entities from the entity database that match the search keywords and use them as target entities.

[0157] Identify the entity category that matches the search category from the various entity categories of the target entity in the entity database, and use that as the target entity category.

[0158] In one embodiment of this disclosure, the recommendation word push request includes the current search session identifier.

[0159] The user's search behavior information includes the user's search behavior information within a historical preset time period and / or the search behavior information whose corresponding search session identifier is the current search session identifier.

[0160] In one embodiment of this disclosure, the processing module is further configured to:

[0161] Retrieve multiple terms and the information corresponding to each term.

[0162] For each term, an initial entity is determined based on the term, and the entity category of the initial entity and at least one attribute information corresponding to each entity category are determined based on the information corresponding to the term.

[0163] An entity library is generated based on the initial entity and at least one attribute information corresponding to each entity category of the initial entity.

[0164] In one embodiment of this disclosure, the first transceiver module 803 is further configured to: generate recommendation words based on at least one attribute information corresponding to the target entity, including:

[0165] Multiple candidate recommendation words are obtained by combining the target entity and at least one attribute information corresponding to the target entity.

[0166] Sort multiple candidate recommendation words and select a recommendation word from the sorted candidate recommendation words.

[0167] Corresponding to the information recommendation method in the above embodiments, Figure 9 This is a structural block diagram of the information recommendation device provided in the embodiments of this disclosure. For ease of explanation, only the parts relevant to the embodiments of this disclosure are shown.

[0168] Reference Figure 9 Information recommendation devices include:

[0169] The second transceiver module 901 is used to send a recommendation word push request to the server in response to the first trigger operation.

[0170] Display module 902 is used to obtain and display the recommended words sent by the server. The recommended words are generated by the server after determining the user's search needs based on the recommendation word push request, identifying target entities matching the search needs from the entity database, and based on at least one attribute information corresponding to the target entity.

[0171] In one embodiment of this disclosure, a first interface is provided via a terminal, the first interface including a search bar and a first button; then the display module 902 is further configured to:

[0172] Display recommended terms in the dropdown menu corresponding to the search bar, or display recommended terms within the search bar itself.

[0173] or,

[0174] Upon receiving a second trigger action applied to the first button or the search bar, a search intermediate page is displayed, and recommended terms are shown in the first preset position on the search intermediate page.

[0175] In one embodiment of this disclosure, if a second interface is provided via a terminal, the display module 902 is further configured to:

[0176] In response to the first trigger operation, the recommended words are displayed in the second preset position on the second interface.

[0177] The device provided in this embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0178] refer to Figure 10 The diagram illustrates a structural schematic of an electronic device 1000 suitable for implementing embodiments of the present disclosure. The electronic device 1000 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants (PDAs), portable Android devices (PADs), portable media players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0179] like Figure 10As shown, the electronic device 1000 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 10010 into a random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the operation of the electronic device 1000. The processing unit 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0180] Typically, the following devices can be connected to the I / O interface 1005: input devices 1006 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1007 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1009 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the electronic device 1000 to exchange data wirelessly or via wired communication with other devices. Although Figure 10 An electronic device 1000 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0181] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1009, or installed from a storage device 1009, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, it performs the functions defined in the methods of embodiments of this disclosure.

[0182] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0183] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0184] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0185] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0186] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0187] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0188] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0189] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0190] In a first aspect, according to one or more embodiments of this disclosure, an information recommendation method is provided, comprising:

[0191] The system acquires the user's search demand characteristics and determines the target entities that match the search demand characteristics and the target entity categories of the target entities from the entity database. The entity database includes multiple entities and at least one attribute information corresponding to each entity category of each entity.

[0192] Determine at least one attribute information corresponding to the target entity based on the target entity category;

[0193] Recommended words are generated based on at least one attribute information corresponding to the target entity, and the recommended words are sent to the user's terminal.

[0194] According to one or more embodiments of this disclosure, the method further includes:

[0195] Obtain the entity to be processed and determine the entity category corresponding to the entity to be processed;

[0196] Obtain the attribute information corresponding to the entity category of the entity to be processed from the entity database, and determine it as the attribute information to be processed;

[0197] The attribute information corresponding to the entity to be processed is determined based on the attribute information to be processed, and the entity database is updated based on the attribute information corresponding to the entity to be processed.

[0198] According to one or more embodiments of this disclosure, the attribute information includes an attribute name;

[0199] Determining the attribute information corresponding to the entity to be processed based on the attribute information to be processed includes:

[0200] The attribute name in the attribute information to be processed is used as the attribute name corresponding to the entity to be processed.

[0201] According to one or more embodiments of this disclosure, the method further includes:

[0202] Obtain the webpage to be processed, and determine the attribute information to be updated corresponding to the entity category of the entity to be updated based on the webpage to be processed, wherein the entity to be updated is an entity in the entity library;

[0203] The entity database is updated based on the attribute information to be updated corresponding to the entity category of the entity to be updated.

[0204] According to one or more embodiments of this disclosure, the method further includes:

[0205] Obtain historical search terms and the corresponding interactive web pages; and / or, obtain target web pages in the target system;

[0206] The interactive webpage and / or the target webpage are used as the webpage to be processed.

[0207] According to one or more embodiments of this disclosure, obtaining user search demand characteristics includes:

[0208] When a recommendation word push request is received from the terminal corresponding to the user, search behavior information corresponding to the user identifier in the recommendation word push request is obtained to obtain the search behavior information corresponding to the user. The search behavior information includes one or more of the following combinations: the first search word entered by the user, the order of the first search words, the interaction results corresponding to the first search word, and the webpage visited by the user.

[0209] Feature words are extracted and feature dimensions are analyzed from the user's search behavior information to obtain the user's search demand features, wherein the search demand features include search feature words and search categories.

[0210] According to one or more embodiments of this disclosure, determining target entities that match the search requirement features and the target entity categories of the target entities from an entity database includes:

[0211] The entity that matches the search feature word is determined from the entity library and used as the target entity;

[0212] The entity category that matches the search category is determined from the various entity categories of the target entity in the entity library, and this entity category is taken as the target entity category.

[0213] According to one or more embodiments of this disclosure, the recommendation word push request includes a current search session identifier;

[0214] The user's search behavior information includes the user's search behavior information within a historical preset time period and / or the search behavior information whose corresponding search session identifier is the current search session identifier.

[0215] According to one or more embodiments of this disclosure, the method further includes:

[0216] Obtain multiple terms and information corresponding to each term;

[0217] For each term, an initial entity is determined based on the term, and the entity category of the initial entity and at least one attribute information corresponding to each entity category are determined based on the information corresponding to the term.

[0218] An entity library is generated based on the initial entity and at least one attribute information corresponding to each entity category of the initial entity.

[0219] According to one or more embodiments of this disclosure, generating recommendation words based on at least one attribute information corresponding to the target entity includes:

[0220] The target entity and at least one attribute information corresponding to the target entity are combined to obtain multiple candidate recommendation words;

[0221] The plurality of candidate recommendation words are sorted, and the recommendation word is selected from the sorted candidate recommendation words.

[0222] Secondly, according to one or more embodiments of this disclosure, an information recommendation method is provided, which is applied to a terminal, the method comprising:

[0223] In response to the first triggering operation, a recommendation keyword push request is sent to the server;

[0224] The server retrieves and displays the recommended words sent by the server; wherein the recommended words are generated by the server after determining the user's search demand characteristics based on the recommended word push request, identifying target entities that match the search demand characteristics from the entity database, and generating them based on at least one attribute information corresponding to the target entities.

[0225] According to one or more embodiments of this disclosure, if a first interface is provided through the terminal, the first interface including a search bar and a first button, then the recommended words are displayed, including:

[0226] The recommended words are displayed in the drop-down box corresponding to the search bar, or the recommended words are displayed in the search bar.

[0227] or,

[0228] Upon receiving a second trigger operation applied to the first button or the search bar, a search intermediate page is displayed, and the recommended term is displayed at a first preset position on the search intermediate page.

[0229] According to one or more embodiments of this disclosure, if a second interface is provided through the terminal, the recommended words are displayed, including:

[0230] In response to the first trigger operation, the recommended words are displayed at a second preset position in the second interface.

[0231] Thirdly, according to one or more embodiments of this disclosure, an information recommendation device is provided, comprising:

[0232] An entity determination module is used to acquire the user's search demand characteristics and determine the target entity that matches the search demand characteristics and the target entity category of the target entity from the entity library. The entity library includes multiple entities and at least one attribute information corresponding to each entity category of each entity.

[0233] An attribute determination module is used to determine at least one attribute information corresponding to the target entity based on the target entity category;

[0234] The first transceiver module is used to generate recommendation words based on at least one attribute information corresponding to the target entity, and send the recommendation words to the user's terminal.

[0235] According to one or more embodiments of this disclosure, the information recommendation device further includes a processing module, which is used to:

[0236] Obtain the entity to be processed and determine the entity category corresponding to the entity to be processed;

[0237] Obtain the attribute information corresponding to the entity category of the entity to be processed from the entity database, and determine it as the attribute information to be processed;

[0238] The attribute information corresponding to the entity to be processed is determined based on the attribute information to be processed, and the entity database is updated based on the attribute information corresponding to the entity to be processed.

[0239] According to one or more embodiments of this disclosure, the attribute information includes an attribute name;

[0240] The processing module is also used for:

[0241] The attribute name in the attribute information to be processed is used as the attribute name corresponding to the entity to be processed.

[0242] According to one or more embodiments of this disclosure, the processing module is further configured to:

[0243] Obtain the webpage to be processed, and determine the attribute information to be updated corresponding to the entity category of the entity to be updated based on the webpage to be processed, wherein the entity to be updated is an entity in the entity library;

[0244] The entity database is updated based on the attribute information to be updated corresponding to the entity category of the entity to be updated.

[0245] According to one or more embodiments of this disclosure, the processing module is further configured to:

[0246] Obtain historical search terms and the corresponding interactive web pages; and / or, obtain target web pages in the target system;

[0247] The interactive webpage and / or the target webpage are used as the webpage to be processed.

[0248] According to one or more embodiments of this disclosure, the entity determination module is further configured to: obtain user search request characteristics, including:

[0249] When a recommendation word push request is received from the terminal corresponding to the user, search behavior information corresponding to the user identifier in the recommendation word push request is obtained to obtain the search behavior information corresponding to the user. The search behavior information includes one or more of the following combinations: the first search word entered by the user, the order of the first search words, the interaction results corresponding to the first search word, and the webpage visited by the user.

[0250] Feature words are extracted and feature dimensions are analyzed from the user's search behavior information to obtain the user's search demand features, wherein the search demand features include search feature words and search categories.

[0251] According to one or more embodiments of this disclosure, the entity determination module is further configured to:

[0252] The entity that matches the search feature word is determined from the entity library and used as the target entity;

[0253] The entity category that matches the search category is determined from the various entity categories of the target entity in the entity library, and this entity category is taken as the target entity category.

[0254] According to one or more embodiments of this disclosure, the recommendation word push request includes a current search session identifier;

[0255] The user's search behavior information includes the user's search behavior information within a historical preset time period and / or the search behavior information whose corresponding search session identifier is the current search session identifier.

[0256] According to one or more embodiments of this disclosure, the processing module is further configured to:

[0257] Obtain multiple terms and information corresponding to each term;

[0258] For each term, an initial entity is determined based on the term, and the entity category of the initial entity and at least one attribute information corresponding to each entity category are determined based on the information corresponding to the term.

[0259] An entity library is generated based on the initial entity and at least one attribute information corresponding to each entity category of the initial entity.

[0260] According to one or more embodiments of this disclosure, the first transceiver module is further configured to: generate recommendation words based on at least one attribute information corresponding to the target entity, including:

[0261] The target entity and at least one attribute information corresponding to the target entity are combined to obtain multiple candidate recommendation words;

[0262] The plurality of candidate recommendation words are sorted, and the recommendation word is selected from the sorted candidate recommendation words.

[0263] Fourthly, according to one or more embodiments of this disclosure, an information recommendation device is provided, which is applied to a terminal, including:

[0264] The second transceiver module is used to send a recommendation word push request to the server in response to the first trigger operation;

[0265] The display module is used to obtain and display the recommended words sent by the server; wherein the recommended words are generated by the server after determining the user's search demand characteristics based on the recommended word push request, determining the target entity that matches the search demand characteristics from the entity database, and based on at least one attribute information corresponding to the target entity.

[0266] According to one or more embodiments of this disclosure, if a first interface is provided through the terminal, the first interface including a search bar and a first button, then the display module is further configured to:

[0267] The recommended words are displayed in the drop-down box corresponding to the search bar, or the recommended words are displayed in the search bar.

[0268] or,

[0269] Upon receiving a second trigger operation applied to the first button or the search bar, a search intermediate page is displayed, and the recommended term is displayed at a first preset position on the search intermediate page.

[0270] According to one or more embodiments of this disclosure, if a second interface is provided through the terminal, the display module is further configured to:

[0271] In response to the first trigger operation, the recommended words are displayed at a second preset position in the second interface.

[0272] The attribute information is matched to obtain the attribute information corresponding to the target entity object.

[0273] In one embodiment of this disclosure, if the user information includes search behavior information of the currently accessing user, then the processing module is further configured to:

[0274] Fifthly, according to one or more embodiments of the present disclosure, an electronic device is provided, comprising: at least one processor and a memory;

[0275] The memory stores computer-executed instructions;

[0276] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the information recommendation method as described in the first aspect and various possible designs of the first aspect.

[0277] In a sixth aspect, according to one or more embodiments of the present disclosure, an electronic device is provided, comprising: at least one processor and a memory;

[0278] The memory stores computer-executed instructions;

[0279] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the information recommendation method as described in the second aspect above and various possible designs of the second aspect.

[0280] In a seventh aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, which, when executed by a processor, implement the information recommendation method as described in the first aspect and various possible designs of the first aspect.

[0281] Eighthly, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, which, when executed by a processor, implement the information recommendation method as described in the second aspect above and various possible designs of the second aspect.

[0282] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0283] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0284] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An information recommendation method, characterized in that, include: The system acquires user search demand characteristics and determines target entities and target entity categories that match these characteristics from an entity database. The entity database includes multiple entities, each entity's corresponding entity category, and at least one attribute information associated with each entity category, enabling the same entity to be associated with different attribute information across different entity categories. The search demand characteristics include search terms and search categories. The attribute information includes attribute names and / or attribute values ​​corresponding to those names. The attribute information includes essential attribute information and basic attribute information. Essential attributes are those that do not change, while basic attributes are those that change over time. Based on the target entity category, determine at least one attribute information corresponding to the target entity and also corresponding to the target entity category; Recommended words are generated based on at least one attribute information corresponding to the target entity, and the recommended words are sent to the user's terminal; Determining target entities that match the search query features from the entity database, and the target entity categories of the target entities, includes: The entity that matches the search feature word is determined from the entity library and used as the target entity; The entity category that matches the search category is determined from the various entity categories of the target entity in the entity library, and this entity category is taken as the target entity category.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the entity to be processed and determine the entity category corresponding to the entity to be processed; Obtain the attribute information corresponding to the entity category of the entity to be processed from the entity database, and determine it as the attribute information to be processed; The attribute information corresponding to the entity to be processed is determined based on the attribute information to be processed, and the entity database is updated based on the attribute information corresponding to the entity to be processed.

3. The method according to claim 2, characterized in that, Determining the attribute information corresponding to the entity to be processed based on the attribute information to be processed includes: The attribute name in the attribute information to be processed is used as the attribute name corresponding to the entity to be processed.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the webpage to be processed, and determine the attribute information to be updated corresponding to the entity category of the entity to be updated based on the webpage to be processed, wherein the entity to be updated is an entity in the entity library; The entity database is updated based on the attribute information to be updated corresponding to the entity category of the entity to be updated.

5. The method according to claim 4, characterized in that, The method further includes: Obtain historical search terms and the corresponding interactive web pages; and / or, obtain target web pages in the target system; The interactive webpage and / or the target webpage are used as the webpage to be processed.

6. The method according to claim 1, characterized in that, Obtain user search query characteristics, including: When a recommendation word push request is received from the terminal corresponding to the user, search behavior information corresponding to the user identifier in the recommendation word push request is obtained to obtain the search behavior information corresponding to the user. The search behavior information includes one or more of the following combinations: the first search word entered by the user, the order of the first search words, the interaction results corresponding to the first search word, and the webpage visited by the user. Feature words and feature dimensions are extracted from the user's search behavior information to obtain the user's search demand characteristics.

7. The method according to claim 1, characterized in that, The recommended term push request includes the current search session identifier; The user's search behavior information includes the user's search behavior information within a historical preset time period and / or the search behavior information whose corresponding search session identifier is the current search session identifier.

8. The method according to claim 1, characterized in that, The method further includes: Obtain multiple terms and information corresponding to each term; For each term, an initial entity is determined based on the term, and the entity category of the initial entity and at least one attribute information corresponding to each entity category are determined based on the information corresponding to the term. An entity library is generated based on the initial entity and at least one attribute information corresponding to each entity category of the initial entity.

9. The method according to claim 1, characterized in that, Recommendation words are generated based on at least one attribute information corresponding to the target entity, including: The target entity and at least one attribute information corresponding to the target entity are combined to obtain multiple candidate recommendation words; The plurality of candidate recommendation words are sorted, and the recommendation word is selected from the sorted candidate recommendation words.

10. An information recommendation method, characterized in that, Applied to terminals, including: In response to the first triggering operation, a recommendation keyword push request is sent to the server; The system retrieves and displays recommended terms sent by the server. The recommended terms are generated by the server after determining the user's search needs based on the recommended term push request, identifying entities matching the search terms, and using these entities as target entities. The server then selects entity categories matching the search category from the target entity categories in the entity database and uses these categories as the target entity category. The system also generates the recommended terms based on at least one attribute information corresponding to the target entity category. The search needs include search terms and search categories. The attribute information includes attribute names and / or attribute values ​​corresponding to those names. The attribute information includes necessary attribute information and basic attribute information. Necessary attributes are attributes that do not change, while basic attributes are attributes that change over time. The entity database includes multiple entities and their corresponding entity categories, as well as at least one attribute information corresponding to each entity category, so that the same entity can be associated with different attribute information under different entity categories.

11. The method according to claim 10, characterized in that, The terminal provides a first interface, which includes a search bar and a first button, and then displays the recommended words, including: The recommended words are displayed in the drop-down box corresponding to the search bar, or the recommended words are displayed in the search bar. or, Upon receiving a second trigger operation applied to the first button or the search bar, a search intermediate page is displayed, and the recommended term is displayed at a first preset position on the search intermediate page.

12. The method according to claim 10, characterized in that, The recommended words are displayed through a second interface provided by the terminal, including: In response to the first trigger operation, the recommended words are displayed at a second preset position in the second interface.

13. An information recommendation device, characterized in that, include: An entity determination module is used to acquire the user's search demand features and determine the target entities and target entity categories that match the search demand features from an entity database. The entity database includes multiple entities, each entity's corresponding entity category, and at least one attribute information corresponding to each entity category, so that the same entity can be associated with different attribute information under different entity categories. The search demand features include search terminology and search category. The attribute information includes attribute names and / or attribute values ​​corresponding to those names. The attribute information includes necessary attribute information and basic attribute information. Necessary attributes are attributes that do not change, while basic attributes are attributes that change over time. An attribute determination module is used to determine at least one attribute information corresponding to the target entity and the target entity category based on the target entity category. The first transceiver module is used to generate recommendation words based on at least one attribute information corresponding to the target entity, and send the recommendation words to the user's terminal; The entity determination module is specifically used to determine the entity that matches the search feature word from the entity library and use it as the target entity; The entity category that matches the search category is determined from the various entity categories of the target entity in the entity library, and this entity category is taken as the target entity category.

14. An information recommendation device, characterized in that, Applied to terminals, including: The second transceiver module is used to send a recommendation word push request to the server in response to the first trigger operation; The display module is used to acquire and display the recommended words sent by the server. The recommended words are generated by the server after determining the user's search needs based on the recommended word push request, identifying entities matching the search features, and using these entities as target entities. The server then selects entity categories matching the search category from the target entity categories in the entity library and uses these categories as the target entity category. The generated entity category is based on at least one attribute information corresponding to the target entity category. The search needs include search features and search categories. The attribute information includes attribute names and / or attribute values ​​corresponding to those names. The attribute information includes necessary attribute information and basic attribute information. Necessary attributes are attributes that do not change, while basic attributes are attributes that change over time. The entity library includes multiple entities and their corresponding entity categories, as well as at least one attribute information corresponding to each entity category, so that the same entity can be associated with different attribute information under different entity categories.

15. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the information recommendation method as described in any one of claims 1 to 9 or 10 to 12.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the information recommendation method as described in any one of claims 1 to 9 or 10 to 12.

17. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program is used to implement the information recommendation method as described in any one of claims 1 to 9 or 10 to 12.

Images