Recommendation method and device, equipment and medium

Abstract

The invention provides a recommendation method and device, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of intelligent recommendation and software application. According to the implementation scheme, the method comprises the steps of determining a first page category corresponding to a current display page from a plurality of candidate page categories based on page content of the current display page; at least one first search word corresponding to the first page category is determined from a candidate search word bank, at least one search word corresponding to each candidate page category in a plurality of candidate page categories is stored in the candidate search word bank, and at least one search word corresponding to each candidate page category in the plurality of candidate page categories is stored in the candidate search word bank; the at least one search word corresponding to each candidate page category is determined based on behavior information of a plurality of users for searching pages corresponding to the candidate page category; determining at least one recommended search term based on the at least one first search term; and displaying the at least one recommended search term in the current display page.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more particularly to the field of intelligent recommendation and software application technology, specifically to a recommendation method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0003] With the development of computer and big data technologies, people's daily behaviors, such as consumption, entertainment, learning, and travel, are all closely related to big data. In the operation of software platforms, it is often necessary to proactively recommend content to users.

[0004] The methods described in this section are not necessarily methods that had been previously conceived or adopted. Unless otherwise specified, no method described in this section should be assumed to be prior art simply because it is included in this section. Similarly, unless otherwise specified, the issues mentioned in this section should not be considered to be accepted in any prior art. Summary of the Invention

[0005] This disclosure provides a recommended method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0006] According to one aspect of this disclosure, a recommendation method is provided, comprising: determining a first page category corresponding to the currently displayed page from a plurality of candidate page categories based on the page content of the currently displayed page; determining at least one first search term corresponding to the first page category from a candidate search term library, wherein the candidate search term library stores at least one search term corresponding to each of the plurality of candidate page categories, and wherein the at least one search term corresponding to each candidate page category is determined based on behavioral information of multiple users searching for pages corresponding to the candidate page category; determining at least one recommended search term based on the at least one first search term; and displaying the at least one recommended search term on the currently displayed page.

[0007] According to another aspect of this disclosure, a recommendation apparatus is provided, comprising: a first determining unit configured to determine a first page category corresponding to the currently displayed page from a plurality of candidate page categories based on the page content of the currently displayed page; a second determining unit configured to determine at least one first search term corresponding to the first page category from a candidate search term library, wherein the candidate search term library stores at least one search term corresponding to each of the plurality of candidate page categories, and wherein the at least one search term corresponding to each candidate page category is determined based on behavioral information of multiple users searching for pages corresponding to the candidate page category; a third determining unit configured to determine at least one recommended search term based on the at least one first search term; and a display unit configured to display the at least one recommended search term on the currently displayed page.

[0008] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the recommended method described above.

[0009] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the recommended method described above.

[0010] According to another aspect of this disclosure, a computer program product is provided, including a computer program, wherein the computer program, when executed by a processor, is capable of implementing the above-described recommended method.

[0011] According to one or more embodiments of this disclosure, recommendation efficiency and accuracy can be improved.

[0012] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] The accompanying drawings exemplify embodiments and form part of the specification, serving together with the textual description to explain exemplary implementations of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0014] Figure 1 A schematic diagram of an exemplary system in which various methods described herein may be implemented, according to exemplary embodiments of the present disclosure;

[0015] Figure 2 A flowchart of a recommended method according to an exemplary embodiment of the present disclosure is shown;

[0016] Figure 3 A schematic diagram of a recommendation information display page according to an exemplary embodiment of the present disclosure is shown;

[0017] Figure 4 A schematic diagram of a recommendation process according to an exemplary embodiment of the present disclosure is shown;

[0018] Figure 5 A structural block diagram of a recommended apparatus according to an exemplary embodiment of the present disclosure is shown;

[0019] Figure 6 A structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0020] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] In this disclosure, unless otherwise stated, the use of terms such as "first," "second," etc., to describe various elements is not intended to limit the positional, temporal, or importance relationships of these elements; such terms are merely used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of that element, while in other cases, based on the context, they may refer to different instances.

[0022] The terminology used in the description of the various examples described in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context explicitly indicates otherwise, an element may be one or more unless the number of elements is specifically limited. Furthermore, the term "and / or" as used in this disclosure covers any one of the listed items and all possible combinations thereof.

[0023] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0024] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatus described herein can be implemented according to embodiments of this disclosure is shown. Reference Figure 1The system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.

[0025] In embodiments of this disclosure, server 120 may run one or more services or software applications that enable the execution of the recommended methods.

[0026] In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, such as to users of client devices 101, 102, 103, 104, 105, and / or 106 under a Software as a Service (SaaS) model.

[0027] exist Figure 1 In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 can sequentially interact with server 120 using one or more client applications to utilize the services provided by these components. It should be understood that various different system configurations are possible and may differ from system 100. Therefore, Figure 1 This is an example of a system used to implement the various methods described herein, and is not intended to be limiting.

[0028] Users can use client devices 101, 102, 103, 104, 105, and / or 106 to send recommendation requests or perform interactive operations on recommended content. The client devices can provide interfaces that allow users to interact with them. The client devices can also output information to the user through these interfaces. Although... Figure 1 Only six client devices are described, but those skilled in the art will understand that this disclosure can support any number of client devices.

[0029] Client devices 101, 102, 103, 104, 105, and / or 106 may include various categories of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptops), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices. These computer devices can run various categories and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as Google Chrome OS); or include various mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, and Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, internet-enabled gaming devices, etc. Client devices can run a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), short message service (SMS) applications, and can use various communication protocols.

[0030] Network 110 can be any type of network well known to those skilled in the art, and can use any of a variety of available protocols (including but not limited to TCP / IP, SNA, IPX, etc.) to support data communication. By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, a token ring network, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a blockchain network, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0031] Server 120 may include one or more general-purpose computers, special-purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices for servers). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0032] The computing unit in server 120 can run one or more operating systems, including any of the aforementioned operating systems and any commercially available server operating system. Server 120 can also run any of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0033] In some implementations, server 120 may include one or more applications to analyze and merge data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0034] In some implementations, server 120 can be a server for a distributed system or a server integrated with blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system, designed to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0035] System 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. Databases 130 may reside in various locations. For example, a database used by server 120 may be local to server 120, or it may be located away from server 120 and may communicate with server 120 via a network-based or dedicated connection. Databases 130 may be of different categories. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve data from and from the databases in response to commands.

[0036] In some embodiments, one or more of the databases 130 may also be used by an application to store application data. The databases used by the application may be different categories of databases, such as key-value stores, object stores, or regular stores supported by a file system.

[0037] Figure 1The system 100 can be configured and operated in various ways to enable the application of the various methods and apparatus described in this disclosure.

[0038] In related technologies, when displaying recommendation information to users on a front-end page, recommendations are typically based on the content of the currently displayed page, i.e., showing users recommended search terms related to the page content. This approach fails to consider the quality of the recommended search terms (e.g., search popularity), resulting in limited conversion rates.

[0039] Based on this, this disclosure provides a recommendation method that categorizes the content of the front-end display page. By maintaining a list of search terms corresponding to different page categories in a candidate search term library based on user behavior information, recommended search terms can be selected from the search term list corresponding to the first page category of the currently displayed page during the front-end recommendation process. By obtaining recommended search terms based on page content classification, it is possible to ensure that the recommended search terms are relevant to the currently displayed page while also ensuring that the recommended search terms are popular and high-quality search terms selected based on user behavior information, thereby improving the recommendation effect. At the same time, obtaining recommended search terms from the search term list stored in the search term library also simplifies the recommendation algorithm and improves recommendation efficiency.

[0040] Figure 2 A flowchart of a recommended method 200 according to an exemplary embodiment of this disclosure is shown. Figure 2 As shown, method 200 includes:

[0041] Step S201: Based on the page content of the currently displayed page, determine the first page category corresponding to the currently displayed page from multiple candidate page categories;

[0042] Step S202: Determine at least one first search term corresponding to the first page category from the candidate search term library, wherein the candidate search term library stores at least one search term corresponding to each of the plurality of candidate page categories, and wherein the at least one search term corresponding to each candidate page category is determined based on the behavior information of multiple users searching for the corresponding pages of the candidate page category;

[0043] Step S203: Based on the at least one first search term, determine at least one recommended search term; and

[0044] Step S204: Display the at least one recommended search term on the currently displayed page.

[0045] By applying the method 200 described above, recommended search terms can be selected from the search term list corresponding to the first page category of the currently displayed page during the front-end recommendation process. Since at least one search term corresponding to each candidate page category in the candidate search term library is determined based on the behavioral information of multiple users searching for pages corresponding to that candidate page category, at least one search term corresponding to each candidate page category corresponds to popular, high-quality search terms with high user search frequency. Obtaining recommended search terms based on page content classification ensures that the recommended search terms are relevant to the currently displayed page while also guaranteeing that the recommended search terms are popular, high-quality search terms selected based on user behavior information. This improves the conversion rate of current users searching based on recommended search terms, thereby enhancing the recommendation effect. Simultaneously, obtaining recommended search terms from the search term list stored in the search term library simplifies the recommendation algorithm and improves recommendation efficiency.

[0046] In some examples, the search terms are queries entered by the user during a real-time search. The search terms can be entered by the user in the form of natural language text, or they can be obtained by converting the user's voice input into text.

[0047] In some examples, multiple candidate page categories are predefined manually, such as movie and TV recommendations, fitness, skincare and beauty, food, travel, shopping, and education. By categorizing the content of the front-end display pages, it is easy to obtain recommended search terms related to the content of each page based on its category. This allows for efficient and accurate content recommendations to users, improving recommendation efficiency.

[0048] In some examples, multiple candidate page categories can also be determined using other methods, such as content topic analysis and clustering based on the page content of multiple sample pages. In this example, the number of clusters can be determined based on the storage and data processing capabilities of the hardware resources used to support the construction and maintenance of the candidate search terminology, so that the data volume of the candidate search terminology built based on multiple candidate page categories is compatible with the hardware resources.

[0049] In some examples, the currently displayed page can be a page that is being rendered and displayed. The page display device can initiate a request for recommended search terms while rendering the current page. Then, after determining at least one recommended search term, it can render the recommendation information display area in the current page based on this term, so as to display the recommended search terms to the user on the current display page. In one example, multiple recommended search terms can be displayed on the current display page, allowing users to select recommended search terms that interest them and trigger a search, thereby improving the conversion rate of the recommended content and enhancing the recommendation effect.

[0050] According to some embodiments, step S201, determining the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page, includes: determining a content summary of the currently displayed page based on the page content, wherein the length of the content summary does not exceed a length threshold; and determining the first page category based on the relevance of the content summary to the multiple candidate page categories. Therefore, by summarizing the page content, the page content category corresponding to the currently displayed page can be determined more easily and accurately, thereby improving the efficiency and accuracy of page content classification.

[0051] In some examples, each candidate page category has a category label that characterizes the content category features of that candidate page category (e.g., movie / TV recommendations, fitness, skincare / beauty, etc.). The first page category corresponding to the currently displayed page can then be determined based on the semantic relevance between the content summary of the currently displayed page and the category labels of each candidate page category. In some examples, the first page category can also be determined based on the semantic relevance between the content summary of the currently displayed page and at least one search term corresponding to each candidate page category. As long as the content summary of the currently displayed page can be used to indicate the content topic and determine the page category accordingly, this disclosure does not limit the specific method for determining the page category.

[0052] According to some embodiments, determining the content summary of the currently displayed page based on its content includes: inputting the page content of the currently displayed page into a language model to obtain the content summary output by the language model. This enables intelligent summarization using a language model, improving the efficiency and accuracy of page content classification.

[0053] In some examples, the language model can be a Generative Large Language Model (GLLM) trained on a large corpus. GLLMs are typically built on deep learning frameworks, possessing the ability to understand and generate human language. They can capture statistical patterns and semantic logic in language through self-supervised learning, thereby enabling complex tasks such as text generation, dialogue interaction, and knowledge reasoning. In some examples, the language model can be inputted with the content of the currently displayed page and a prompt instructing it to generate a summary of the page content. This allows for a convenient and efficient way to obtain the content summary of the currently displayed page.

[0054] According to some embodiments, determining the content summary of the currently displayed page based on its content includes: extracting at least one keyword from the currently displayed page to determine the content summary. This enables efficient and accurate page content classification based on the keyword extraction results of the currently displayed page.

[0055] In some examples, extracting at least one keyword from the currently displayed page can be achieved in various ways. For example, it could involve performing text content statistics on the page content, calculating the word frequency and inverse document frequency of each word to assess the importance of words in the document, and thus determining keywords that can characterize the content theme of the currently displayed page. Another example is keyword extraction based on word co-occurrence analysis. This disclosure does not limit the specific method of keyword extraction as long as keywords characterizing the content theme of the currently displayed page can be obtained by analyzing its content.

[0056] According to some embodiments, the page content of the currently displayed page includes the page address of the currently displayed page. Step S201, determining the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page, includes: determining the resource location information of the currently displayed page based on its page address; and determining the first page category based on the resource location information. Therefore, page content categories can be identified more easily and efficiently based on the resource location information of the currently displayed page, improving page classification efficiency.

[0057] In some examples, the resource location information of the currently displayed page can be a Uniform Resource Locator (URL) corresponding to the front-end page. A URL corresponds to a standardized naming system used in internet platforms to locate resources, specifying the exact location of resources such as web pages, files, images, and videos on the internet. A URL can include information such as protocol headers, domain names, paths, query conditions, and anchor points. In some examples, the resource location information can be a URL signature. A URL signature can be a digital signature obtained by converting page resource location information or page feature parameters into a fixed-length string. By using a fixed-length URL signature field to store the feature information of the front-end page, simple and efficient page feature recognition can be achieved based on this field. In some examples, the candidate search term library can store the mapping relationship between multiple candidate page categories and various URL signature field information. Therefore, based on the URL signature field information of the currently displayed page, the first page category corresponding to the currently displayed page and its corresponding first search term can be retrieved from the candidate search term library, improving recommendation efficiency.

[0058] In some examples, method 200 may further include a security verification step based on the page address of the currently displayed page, thereby ensuring the security of the page display by displaying recommended search terms if the page address of the currently displayed page is valid.

[0059] According to some embodiments, method 200 further includes: in response to determining that the currently displayed page was triggered by a current user's search based on a user's search term, obtaining the user's search term, wherein step S201, determining the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page, includes: determining the first page category from the multiple candidate page categories based on the page content of the currently displayed page and the user's search term. When a user searches based on a user's search term and browses a landing page in a search scenario, the page category can be identified more accurately by combining the user's search term.

[0060] In some examples, each candidate page category in the candidate search term library can correspond to a sequence of search terms. For instance, at least one search term corresponding to each candidate page category can be sorted according to statistical values ​​of user behavior information (such as search count, browsing duration, click count, etc.) corresponding to each search term. In this case, in step S203, recommended search terms can be selected from at least one first search term based on the sorting information to obtain recommendation information with higher search popularity, thereby improving the conversion rate of current users searching based on recommended search terms and enhancing the recommendation effect.

[0061] According to some embodiments, method 200 further includes: updating at least one search term corresponding to the first page category in the candidate search term library based on the user's behavioral information regarding the at least one recommended search term. It is understood that after a recommended search term is recommended to a user, the user's feedback behavior regarding the recommended search term can indicate the degree to which the recommended search term arouses the user's interest. By updating the candidate search term library based on the user's feedback behavior, the content of the candidate search term library can be made more in line with the user's interests, thereby improving the accuracy of recommendations.

[0062] According to some embodiments, the currently displayed page shows multiple recommended search terms. Updating at least one search term corresponding to the first page category in the candidate search term library based on the user's behavior information regarding the at least one recommended search term includes: in response to determining that the user's swiping or page-turning behavior regarding the multiple recommended search terms exceeds a preset number, deleting the first recommended search term displayed on the currently displayed page from the candidate search term library. By monitoring the user's swiping and page-turning behavior on the recommended term list, this behavior can be used to more directly indicate whether the user is satisfied with the first recommended term in the list, thereby updating the candidate search term library to make its content more in line with user interests and improving recommendation accuracy.

[0063] In some examples, updating the candidate search term library based on user behavior information can also include other aspects. For instance, the library can be updated based on whether a user clicks on a recommended search term (i.e., triggers the search process) or doesn't click on it. If a search term fails to elicit clicks from a user after being recommended to them for an extended period, it can be removed from the library. In one example, when at least one search term corresponding to each page category in the candidate search term library is an ordered sequence, the order of the search terms in that sequence can be adjusted based on user behavior information. This makes the top-ranked content in the candidate search term library more aligned with user interests, thereby improving recommendation accuracy.

[0064] According to some embodiments, the behavioral information of multiple users searching for pages corresponding to each candidate page category includes multiple historical search terms corresponding to that candidate page category. At least one search term corresponding to each candidate page category in the candidate search term library is determined using the following method: based on the search statistics of each of the multiple historical search terms corresponding to that candidate page category, at least one search term corresponding to that candidate page category is determined. The search statistics include at least one of cumulative search counts, search frequency, recent search time, or search duration. Therefore, a candidate search term library that can be used for recommendations can be determined based on the search statistics of historical search terms, making the content of the candidate search term library more aligned with user interests and improving recommendation accuracy.

[0065] In some examples, multiple historical search terms can be sorted based on their respective search statistics for each candidate page category. A certain number of search terms are then added to the candidate search term library based on the sorting results. The cumulative search count for each historical search term indicates the total number of times a user has searched for that term within a specific historical time period. Search frequency indicates the cumulative number of searches for that term. Recent search time indicates the time of the most recent search for that term. Search duration indicates the duration of the user's search for that term (e.g., the time spent browsing the corresponding search results). Based on these search statistics, the user's level of interest in each historical search term or its popularity can be indicated, making the content of the candidate search term library more aligned with user interests and improving recommendation accuracy.

[0066] According to some embodiments, determining at least one recommended search term based on the at least one first search term includes: determining at least one candidate search term based on the search statistics of each of the at least one first search term; and determining at least one recommended search term that meets semantic conditions based on the at least one candidate search term, wherein the semantic conditions include: the semantic similarity between the at least one recommended search term and the at least one candidate search term exceeds a preset threshold; and / or the at least one recommended search term and the at least one candidate search term include the same keywords. Therefore, semantic similarity can be considered in the process of determining recommended search terms, and recommended terms semantically related to the content of user interest (i.e., candidate search terms determined based on search statistics) can be mined. Typically, some search terms stored in the candidate search term library may be historical search terms filtered based on search statistics. By applying the above methods to mine search terms semantically related to historical search terms, it is possible to avoid recommending duplicate historical search terms to users while ensuring that recommended terms meet user interests, thereby improving recommendation accuracy.

[0067] According to some embodiments, method 200 further includes: obtaining a second page category preferred by the current user, wherein the second page category is determined based on page category information of the current user's historical browsing pages; and in response to determining that the second page category is different from the first page category, determining at least one second search term corresponding to the second page category from the candidate search term library, wherein step S203, based on the at least one first search term, determines at least one recommended search term including: based on the at least one first search term, determining at least one third search term; based on the at least one second search term, determining at least one fourth search term; and based on the at least one third search term and the at least one fourth search term, determining multiple recommended search terms. Thus, it is possible to combine the user's historical preferred page categories to determine recommended content, making the recommended content more in line with the user's interests and improving recommendation accuracy.

[0068] In some examples, the page categories preferred by each user can be pre-collected and stored based on each user's historical behavior information. This allows the second page category preferred by the current user to be directly obtained based on the current user's identification information during the front-end recommendation process, thereby improving recommendation efficiency.

[0069] In some examples, the display space for recommended search terms on the front-end page is limited. In such cases, the third search term corresponding to the first page category and the fourth search term corresponding to the second page category can be selected based on a pre-set quantity threshold or proportion. For example, if the front-end page can display 5 recommended search terms, 3 third search terms can be selected from the search term list corresponding to the first page category to recommend to the user, and 2 fourth search terms can be selected from the search term list corresponding to the second page category to recommend to the user. This ensures that the recommended information displayed on the front-end includes both content relevant to the currently displayed page and content that the user currently prefers, thereby improving the recommendation effect.

[0070] In some examples, when the list of search terms for the first or second page category is insufficient, more popular search terms can be retrieved and displayed as recommended search terms to the current user to improve the recommendation effect.

[0071] In some examples, the display position of recommended search terms on the front-end page can correspond to different display methods, such as being permanently displayed or being hidden as the page is scrolled.

[0072] According to some embodiments, method 200 further includes: updating the at least one recommended search term in response to determining that the interaction duration between the current user and the currently displayed page exceeds a duration threshold. Thus, when the user's interaction duration with the current page exceeds the threshold, the recommended information displayed on the front end can be further updated. It can be understood that when the user's interaction duration with the current page is long, it indicates that the user has not triggered a search process based on the recommended search terms after viewing them for a considerable period, meaning that the currently displayed recommended content may not match the user's interests. By updating the recommended information in a timely manner, new search terms can be recommended to the user to improve the recommendation effect.

[0073] According to some embodiments, updating the at least one recommended search term includes: determining the updated at least one recommended search term based on the current user's interaction behavior information on the currently displayed page. This allows for more accurate identification of user interests based on real-time user interaction behavior, and thus more accurate determination of recommended content.

[0074] In some examples, the content that a user is interested in can be identified based on the user's interaction behavior on the currently displayed page. For example, it could be to determine the page categories that the user is interested in, and then determine new recommended search terms based on the candidate search terms corresponding to the page categories that the user is interested in, so as to improve the accuracy of recommendations.

[0075] In some examples, the search terms corresponding to multiple candidate page categories in the candidate search term library described above, as well as the page categories preferred by each user, can be continuously updated based on the user's interaction behavior on the front-end page to ensure the accuracy of the database information, thereby enabling more accurate recommendations.

[0076] In some examples, users may navigate to other pages while browsing the front-end page. In such cases, the page category of the new displayed page can be identified after the front-end page is displayed. If the new displayed page belongs to the same category as the previous displayed page, there is no need to update the recommended search terms. When the page category of the new displayed page changes, the method 200 provided in this disclosure can be used to redetermine new recommended search terms.

[0077] Figure 3 A schematic diagram of a recommendation information display page according to an exemplary embodiment of this disclosure is shown. Figure 3 As shown, the display page includes an address bar 310, an area 320 for displaying recommended information, and an area 330 for displaying page content. Figure 3 As shown, area 320, used to display recommended information, can display multiple recommended search term tags. By displaying multiple recommended search terms below the address bar on the front-end page, users can easily trigger a search by clicking on the recommended search term tags, thereby improving the recommendation effect.

[0078] Figure 4 A schematic diagram of a recommendation process according to an exemplary embodiment of this disclosure is shown. Figure 4 As shown, the process of displaying recommended information (multiple recommended search terms) on the front-end page may include the following steps:

[0079] Step S1: In response to the user clicking a search result item, redirect to the target page. In this example, method 200 can be applied to search scenarios (such as search websites or search software platforms). When a user searches based on their search terms and clicks a search result item to redirect to the target page, recommended information can be displayed on the target page.

[0080] Step S2: Request recommendation information based on the target page's URL and the user's search terms. In this example, the step of determining recommendation information can be done by the backend server. The frontend display device can request recommendation information from the server based on the user's search terms and the target page that the user triggers to display on the frontend.

[0081] Step S3: Determine if the page address is valid. As mentioned earlier, by performing a security check based on the page address of the target page to be displayed, the recommended information can be displayed if the page address is valid, thus ensuring the security of the page display.

[0082] If the page address is valid, proceed to step S4 to return a list of recommended search terms based on the page category of the target page. In this step, the steps described above can be applied to identify the page category of the target page and, based on this, retrieve a list of search terms from the candidate search term library.

[0083] When the page address is invalid, step S5 can be executed to return empty data, that is, no recommendation information is displayed.

[0084] Step S6: Determine if the number of recommended search terms meets the requirements. As mentioned earlier, the display position of recommended search terms on the front-end page can be fixed. In this case, when the number of recommended search terms obtained based on page content classification meets the requirements, step S8 can be executed to directly display the recommendation information.

[0085] If the number of recommended search terms obtained based on page content categorization is insufficient, step S7 can be executed to further obtain popular search terms for recommendation, so as to ensure the recommendation effect.

[0086] According to one aspect of this disclosure, a recommended device is also provided. Figure 5 A structural block diagram of a recommended apparatus 500 according to an exemplary embodiment of the present disclosure is shown. Figure 5 As shown, the device 500 includes:

[0087] The first determining unit 501 is configured to determine the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page.

[0088] The second determining unit 502 is configured to determine at least one first search term corresponding to the first page category from a candidate search term library, wherein the candidate search term library stores at least one search term corresponding to each of the plurality of candidate page categories, and wherein the at least one search term corresponding to each candidate page category is determined based on the behavior information of multiple users searching for pages corresponding to the candidate page category;

[0089] The third determining unit 503 is configured to determine at least one recommended search term based on the at least one first search term; and

[0090] Display unit 504 is configured to display the at least one recommended search term on the currently displayed page.

[0091] According to some embodiments, the first determining unit 501 includes: a first determining subunit configured to determine a content summary of the currently displayed page based on the page content of the currently displayed page, wherein the length of the content summary does not exceed a length threshold; and a second determining subunit configured to determine the first page category based on the relevance of the content summary to the plurality of candidate page categories.

[0092] According to some embodiments, the first determining subunit is configured to: obtain the content summary output by the language model by inputting the page content of the currently displayed page into the language model.

[0093] According to some embodiments, the first determining subunit is configured to: determine the content summary by extracting at least one keyword included in the currently displayed page.

[0094] According to some embodiments, the page content of the currently displayed page includes the page address of the currently displayed page, and the first determining unit 501 includes: a third determining subunit configured to determine the resource location information of the currently displayed page based on the page address of the currently displayed page; and a fourth determining subunit configured to determine the first page category based on the resource location information.

[0095] According to some embodiments, the device 500 further includes: a first acquisition unit configured to acquire the user search term in response to determining that the currently displayed page was triggered by a current user's search based on a user search term, wherein the first determination unit 501 is configured to: determine the first page category from the plurality of candidate page categories based on the page content of the currently displayed page and the user search term.

[0096] According to some embodiments, the device 500 further includes: a second acquisition unit configured to acquire a second page category preferred by the current user, wherein the second page category is determined based on page category information of the current user's historical browsing pages; and a fourth determination unit configured to determine at least one second search term corresponding to the second page category from the candidate search term library in response to determining that the second page category is different from the first page category, wherein the third determination unit 503 includes: a fifth determination subunit configured to determine at least one third search term based on the at least one first search term; a sixth determination subunit configured to determine at least one fourth search term based on the at least one second search term; and a seventh determination subunit configured to determine a plurality of recommended search terms based on the at least one third search term and the at least one fourth search term.

[0097] According to some embodiments, the apparatus 500 further includes an updating unit configured to update the at least one recommended search term in response to determining that the duration of interaction between the current user and the currently displayed page exceeds a duration threshold.

[0098] According to some embodiments, the updating unit is configured to: determine the updated at least one recommended search term based on the current user's interaction behavior information on the currently displayed page.

[0099] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0100] According to another aspect of this disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the recommended method described above.

[0101] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is also provided, wherein the computer instructions are used to cause the computer to perform the recommended method described above.

[0102] According to another aspect of this disclosure, a computer program product is also provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the recommended method described above.

[0103] refer to Figure 6 The present invention describes a structural block diagram of an electronic device 600 that can serve as a server or client of the present disclosure, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0104] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0105] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, output unit 607, storage unit 608, and communication unit 609. Input unit 606 can be any type of device capable of inputting information to device 600. Input unit 606 can receive input numerical or character information and generate key signal inputs related to user settings and / or function control of the electronic device, and may include, but is not limited to, a mouse, keyboard, touchscreen, trackpad, trackball, joystick, microphone, and / or remote control. Output unit 607 can be any type of device capable of presenting information, and may include, but is not limited to, a monitor, speaker, video / audio output terminal, vibrator, and / or printer. Storage unit 608 may include, but is not limited to, a hard disk and an optical disk. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and / or chipsets, such as Bluetooth™ devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0106] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as the recommendation method. For example, in some embodiments, the recommendation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the recommendation method by any other suitable means (e.g., by means of firmware).

[0107] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0109] 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.

[0110] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0111] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0112] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0113] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0114] While embodiments or examples of this disclosure have been described with reference to the accompanying drawings, it should be understood that the methods, systems, and devices described above are merely exemplary embodiments or examples, and the scope of the invention is not limited by these embodiments or examples, but only by the granted claims and their equivalents. Various elements in the embodiments or examples may be omitted or replaced by their equivalents. Furthermore, the steps may be performed in a different order than that described in this disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, as the technology evolves, many elements described herein can be replaced by equivalents that appear after this disclosure.

Claims

1. A recommendation method, comprising: Based on the content of the currently displayed page, determine the first page category corresponding to the currently displayed page from multiple candidate page categories; Determine at least one first search term corresponding to the first page category from the candidate search term library, wherein the candidate search term library stores at least one search term corresponding to each of the plurality of candidate page categories, and wherein the at least one search term corresponding to each candidate page category is determined based on the behavior information of multiple users searching for the corresponding pages of the candidate page category; Based on the at least one first search term, at least one recommended search term is determined; and The at least one recommended search term is displayed on the currently displayed page.

2. The method of claim 1, further comprising: Based on the user's behavior information regarding the at least one recommended search term, update at least one search term corresponding to the first page category in the candidate search term library.

3. The method as described in claim 2, wherein, The currently displayed page shows multiple recommended search terms. Updating the at least one search term corresponding to the first page category in the candidate search term library based on the user's behavior information regarding the at least one recommended search term includes: In response to determining that the user's swiping or page-turning behavior for the multiple recommended search terms exceeds a preset number, the first recommended search term displayed on the current display page is deleted from the candidate search term library.

4. The method according to any one of claims 1-3, wherein, The behavioral information of multiple users searching for pages corresponding to each candidate page category includes multiple historical search terms corresponding to that candidate page category. At least one search term corresponding to each candidate page category in the candidate search term library is determined using the following method: Based on the search statistics of multiple historical search terms corresponding to the candidate page category, at least one search term corresponding to the candidate page category is determined, wherein the search statistics include at least one of cumulative search count, search frequency, recent search time, or search duration.

5. The method of claim 4, wherein, The determination of at least one recommended search term based on the at least one first search term includes: Based on the search statistics of each of the at least one first search term, at least one candidate search term is determined; and Based on the at least one candidate search term, at least one recommended search term that satisfies semantic conditions is determined, wherein the semantic conditions include: The semantic similarity between at least one recommended search term and at least one candidate search term exceeds a preset threshold; and / or The at least one recommended search term and the at least one candidate search term include the same keyword.

6. The method according to any one of claims 1-5, wherein, The step of determining the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page includes: Based on the page content of the currently displayed page, a content summary of the currently displayed page is determined, wherein the length of the content summary does not exceed a length threshold; and The first page category is determined based on the relevance between the content summary and the multiple candidate page categories.

7. The method of claim 6, wherein, The step of determining the content summary of the currently displayed page based on the page content includes: By inputting the page content of the currently displayed page into a language model, the content summary output by the language model is obtained.

8. The method of claim 6, wherein, The step of determining the content summary of the currently displayed page based on the page content includes: The content summary is determined by extracting at least one keyword from the currently displayed page.

9. The method according to any one of claims 1-5, wherein, The page content of the currently displayed page includes the page address of the currently displayed page, and determining the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page includes: Based on the page address of the currently displayed page, determine the resource location information of the currently displayed page; and The first page category is determined based on the resource location information.

10. The method of any one of claims 1-9, further comprising: In response to determining that the currently displayed page was triggered by the current user's search based on user search terms, the user search terms are obtained. The step of determining the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page includes: Based on the page content of the currently displayed page and the user's search terms, the first page category is determined from the plurality of candidate page categories.

11. The method according to any one of claims 1-10, further comprising: Obtain the second page category preferred by the current user, wherein the second page category is determined based on the page category information of the current user's historical browsing pages; and In response to determining that the second page category is different from the first page category, at least one second search term corresponding to the second page category is determined from the candidate search term library. The step of determining at least one recommended search term based on the at least one first search term includes: Based on the at least one first search term, at least one third search term is determined; Based on the at least one second search term, determine at least one fourth search term; and Multiple recommended search terms are determined based on the at least one third search term and the at least one fourth search term.

12. The method according to any one of claims 1-11, further comprising: In response to determining that the interaction duration between the current user and the currently displayed page exceeds a duration threshold, the at least one recommended search term is updated.

13. The method of claim 12, wherein, The update of the at least one recommended search term includes: Based on the current user's interaction behavior information on the currently displayed page, the updated at least one recommended search term is determined.

14. A recommended device, comprising: The first determining unit is configured to determine the first page category corresponding to the currently displayed page from multiple candidate page categories based on the page content of the currently displayed page; The second determining unit is configured to determine at least one first search term corresponding to the first page category from a candidate search term library, wherein the candidate search term library stores at least one search term corresponding to each of the plurality of candidate page categories, and wherein the at least one search term corresponding to each candidate page category is determined based on behavioral information of multiple users searching for pages corresponding to that candidate page category; The third determining unit is configured to determine at least one recommended search term based on the at least one first search term; and The display unit is configured to display the at least one recommended search term on the currently displayed page.

15. An electronic device comprising: At least one processor; as well as A memory that is communicatively connected to the at least one processor; in The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-13.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-13.

17. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the method according to any one of claims 1-13.

Images