Method, device, equipment and medium for recommending portal pages

Abstract

The embodiments of this specification disclose a portal page recommendation method, apparatus, device and medium, including: when a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag; based on the associated tag, querying the portal page for recommended content containing the associated tag; based on the weight value of the associated tag, determining a recommendation value of the recommended content; and recommending to the designated user based on the recommendation value of the recommended content.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to a portal page recommendation method, device, equipment, and medium. Background Art

[0002] Most of the current manufacturers of internal enterprise portals are faced with the problem of how to present the portal content. For example, human resources personnel may pay more attention to the various dynamics of the company's employees, while financial specialists may be more concerned about daily income and expenditure.

[0003] Most of the portal products from existing manufacturers create different portal pages for different roles to push different content. This method has two problems: First, although setting up separate portal pages for different roles or personnel has greater freedom, the operation complexity is also increased, and too many pages need to be configured during implementation; second, when a person has multiple roles, it is necessary to switch the portal pages corresponding to different roles to see the content that each role wants to see, which does not provide a good user experience. Summary of the Invention

[0004] One or more embodiments of this specification provide a portal page recommendation method, apparatus, device, and medium, which are used to solve the technical problems raised in the background art.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of this specification provide a portal page recommendation method, including:

[0007] When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag;

[0008] According to the associated tag, searching the portal page for recommended content containing the associated tag;

[0009] Determining a recommendation value of the recommended content according to the weight value of the associated tag;

[0010] Recommend the recommended content to the designated user according to the recommendation value of the recommended content.

[0011] Furthermore, before the designated user enters the portal page, the method further includes:

[0012] Obtaining relevant behaviors of the designated user and setting corresponding content tags for the content of the portal page;

[0013] The determining of the associated tag corresponding to the designated user specifically includes:

[0014] When the designated user triggers the relevant behavior on the portal page, determining the trigger content corresponding to the relevant behavior;

[0015] A first content tag corresponding to the triggering content is determined, and the first content tag is recorded as the associated tag.

[0016] Furthermore, determining the weight value corresponding to the associated tag specifically includes:

[0017] The weight value corresponding to the associated tag is determined according to the preset weight of the related behavior and the preset weight of the associated tag.

[0018] Furthermore, determining the recommendation value of the recommended content according to the weight value of the associated tag specifically includes:

[0019] Determining the relevance of the associated tags in the recommended content;

[0020] The recommendation value of the recommended content is determined according to the relevance of the associated tags and the weight values of the associated tags.

[0021] Furthermore, after determining the recommendation value of the recommended content according to the weight value of the associated tag, the method further includes:

[0022] If it is determined that the recommended content is associated with the position of the designated user, the recommendation value of the recommended content is increased by a preset value.

[0023] Furthermore, the method further comprises:

[0024] Determining the keyword preset by the designated user;

[0025] When a designated user enters the portal page, determining specific content containing the keyword and setting a preset recommendation value for the specific content;

[0026] The recommending to the designated user according to the recommendation value of the recommended content specifically includes:

[0027] Recommending the recommended content to the designated user based on the recommendation value of the recommended content and the preset recommendation value of the specific content.

[0028] Furthermore, the related behaviors include one or more of browsing, sharing and collecting.

[0029] One or more embodiments of this specification provide a portal page recommendation device, the device comprising:

[0030] a tag determining unit, which determines, when a designated user enters a portal page, an associated tag corresponding to the designated user and a weight value corresponding to the associated tag;

[0031] a recommended content query unit, which queries the portal page for recommended content containing the associated tag according to the associated tag;

[0032] a recommendation value determination unit, which determines the recommendation value of the recommended content according to the weight value of the associated tag;

[0033] A recommendation unit is configured to recommend the recommended content to the designated user according to the recommendation value of the recommended content.

[0034] One or more embodiments of this specification provide a portal page recommendation device, including:

[0035] at least one processor; and,

[0036] a memory communicatively connected to the at least one processor; wherein,

[0037] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0038] When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag;

[0039] According to the associated tag, searching the portal page for recommended content containing the associated tag;

[0040] Determining a recommendation value of the recommended content according to the weight value of the associated tag;

[0041] Recommend the recommended content to the designated user according to the recommendation value of the recommended content.

[0042] One or more embodiments of this specification provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to:

[0043] When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag;

[0044] According to the associated tag, searching the portal page for recommended content containing the associated tag;

[0045] Determining a recommendation value of the recommended content according to the weight value of the associated tag;

[0046] Recommend the recommended content to the designated user according to the recommendation value of the recommended content.

[0047] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:

[0048] The embodiments of this specification utilize a portal page recommendation method to calculate the recommendation degree of content on the portal page, thereby achieving precise recommendation accuracy and maximizing push notifications. Furthermore, the embodiments of this specification can set a different recommendation degree for each piece of content for each person, and then display the content from highest to lowest recommendation degree when each person visits the portal page, thereby achieving precise and accurate content recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some of the embodiments described in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without inventive work. In the drawings:

[0050] Figure 1 A flowchart of a portal page recommendation method provided in one or more embodiments of this specification;

[0051] Figure 2 A schematic diagram of the structure of a portal page recommendation device provided in one or more embodiments of this specification;

[0052] Figure 3 A schematic diagram of the structure of a portal page recommendation device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0053] The embodiments of this specification provide a portal page recommendation method, apparatus, device, and medium.

[0054] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0055] Figure 1 This is a flow chart of a portal page recommendation method provided in one or more embodiments of this specification. The process can be executed by a portal page recommendation system. Certain input parameters or intermediate results in the process allow for manual intervention and adjustment to help improve accuracy.

[0056] The method steps of the embodiment of this specification are as follows:

[0057] S102: When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag.

[0058] In an embodiment of the present specification, before a designated user enters a portal page, data related to the designated user may be collected, and based on the data related to the designated user, corresponding content may be recommended to the designated user. Associated tags and weights corresponding to the associated tags may be determined based on the data related to the designated user.

[0059] In an embodiment of the present specification, before a designated user enters a portal page, the relevant behavior of the designated user is obtained, and the associated tag corresponding to the designated user is determined. Specifically, it can be as follows: when the designated user triggers the relevant behavior on the portal page, the trigger content corresponding to the relevant behavior is determined; the first content tag corresponding to the trigger content is determined, and the first content tag is recorded as the associated tag. For example, the designated user browses or forwards relevant content; corresponding content tags can also be set for the content of the portal page, for example, content A on the portal page can be set with content tags a and b. The associated tags can be tags contained in the relevant content browsed or forwarded by the designated user. For example, the designated user browsed content B before entering the portal page, and content B contains tag b. Tag b is the associated tag corresponding to the designated user.

[0060] In an embodiment of the present specification, the weight value corresponding to the associated tag is determined, specifically by: determining the weight value corresponding to the associated tag according to the preset weight of the related behavior and the preset weight of the associated tag, that is, the preset weight of the related behavior and the preset weight of the associated tag can be multiplied to obtain the weight value corresponding to the associated tag. For example, the related behaviors include browsing and forwarding, the weight of browsing is 5, and the weight of forwarding is 10. The associated tags include keywords and classification information, the weight of keywords is 20, and the weight of classification is 5. If content C has keyword C1 and classification C2, and the user is specified to browse content C, then the weight value of C1 is 5×20=100, and the weight value of C2 is 5×5=25.

[0061] It should be noted that, in the embodiments of this specification, the relevant behaviors include one or more of browsing, sharing, and collecting.

[0062] S104: According to the associated tag, search the portal page for recommended content containing the associated tag.

[0063] In the embodiments of this specification, the content on the portal page can be updated content or content that has been viewed or forwarded by a specified user. When searching the portal page, the tags of each content on the portal page can be searched based on the associated tags, and the content containing the associated tags can be set as recommended content to the specified user (recommended content).

[0064] S106: Determine a recommendation value of the recommended content according to the weight value of the associated tag.

[0065] In the embodiment of the present specification, when the recommended content includes multiple associated tags, the recommendation value of the recommended content can be determined by accumulation, that is, the weight values of the multiple associated tags can be added together to determine the recommendation value of the recommended content.

[0066] In an embodiment of the present specification, when determining the recommendation value of the recommended content based on the weight value of the associated tag, the relevance of the associated tag in the recommended content can also be determined. The relevance can be the number of times the same associated tag appears in the same recommended content to determine the relevance of the associated tag; finally, the recommendation value of the recommended content is determined based on the relevance of the associated tag and the weight value of the associated tag.

[0067] In the embodiment of the present specification, after determining the recommendation value of the recommended content according to the weight value of the associated tag, if it is determined that the recommended content is associated with the position of the designated user, the recommendation value of the recommended content is increased by a preset value.

[0068] S108: Recommend the recommended content to the designated user according to the recommendation value of the recommended content.

[0069] In the embodiment of the present specification, the recommended contents may be sorted according to their recommendation values and recommended to designated users.

[0070] In an embodiment of the present specification, in order to achieve personalized recommendations for a specified user, the keywords pre-set by the specified user can be determined. The keywords can be set by the specified user and are keywords that the specified user is interested in. When the specified user enters the portal page, the specific content containing the keywords is determined, and the specific content is set to a preset recommendation value. The preset recommendation value can be based on the number of times the specified user's preset keywords appear. For example, if the specified user's preset keywords appear once in the same content, the weight value can be set to 100. If the specified user's preset keywords appear twice, the weight value can be set to 120.

[0071] In the embodiment of the present specification, when recommending to the designated user according to the recommendation value of the recommended content, the recommendation may be made to the designated user according to the recommendation value of the recommended content and the preset recommendation value of the specific content.

[0072] It should be noted that the embodiments of this specification utilize a portal page recommendation method to calculate the recommendation degree of portal page content, thereby achieving precise recommendation accuracy and maximizing push notifications. Furthermore, the embodiments of this specification can set a different recommendation degree for each piece of content for each person, and then display the content from highest to lowest recommendation degree when each person visits the portal page, thereby achieving precise and accurate content recommendations.

[0073] It should be noted that the content recommendation degree measurement in the embodiments of this specification has the following major dimensions:

[0074] 1. The user's role / position within the enterprise (portal system)

[0075] 2. Contents that must be paid attention to by different roles / positions according to corporate rules and regulations

[0076] 3. Feature extraction of personal daily browsing and collection content

[0077] 4. Personally expressed preferences

[0078] The system structure of the embodiment of this specification may include: a portal application module, a content management module, and a full-text search engine. The portal application module may be responsible for presenting content, and at the same time, for collecting user browsing, sharing, and collection behaviors; the content management module may be responsible for editing, publishing, and storing content, and at the same time, for entering key information that the enterprise must know; the full-text search engine may be responsible for creating content indexes and content retrieval. In the embodiment of this specification, the system provides a unified portal page. In addition to the traditional content presentation blocks, the page also includes one or more intelligent recommendation blocks. The content displayed in this block is the content pushed by content recommendation ranking as mentioned in the embodiment of this specification.

[0079] In the portal application module of the embodiment of this specification, user browsing, sharing, and favorite behaviors can be collected through front-end tracking. At the same time, users can select keywords of interest on the settings page. In the content management module, for each content, the content keywords, summary, and classification information must be set when it is published. At the same time, the business organization, associated position, and whether the content is required to be paid attention to by a certain role / position of the enterprise are determined. In the embodiment of this specification, the browsing content weight can be 5, the sharing weight can be 10, and the favorite weight can be 20; the keyword weight can be 20, the summary weight can be 10, and the classification weight can be 5; the product of the weight of the behavior and the content is the final weight value; the weight of the user's position / role can be 50; if there is content that must be paid attention to, it has the highest weight and has a single vote. For example, content C1 has keyword W1, summary A1, and classification CA1; if user U1 browses C1, the weight of W1 is 5×20=100, the weight of A1 is 5×10=50, and the weight of CA1 is 5×5=25. The system will accumulate and store the weights of the user's keywords, summary, and classification.

[0080] When user U1 opens the portal homepage, the system obtains the weights of each keyword, abstract, and category for the user, and obtains the full-text search engine related to the keyword, abstract, and category according to the weight order for query. Then, the score field in the query result (the relevance mentioned above) and the weight of each word are multiplied to obtain the recommendation degree R of the content for the query condition. The recommendation degree of each query condition is added together to obtain the recommendation degree of the content. The query can be performed through ES (elastic ES performs a full-text search using a search learning scoring algorithm. When performing a search, each associated tag will have a score. For example, if a piece of content C2 contains both keyword W1 and summary A1, and the score for C2 found by searching W1 is 1.5, and the score for C2 found by searching A1 is 2.1, then C2's recommendation is: 100 (W1's weight) × 1.5 + 50 (A1's weight) × 2.1 = 255. If C2 is also assigned to the position of U1, then C2's total recommendation is 255 + 50 = 305. If the content is required by the enterprise, the recommendation is 999999. The system ranks the content based on the recommendation scores derived from this calculation.

[0081] It should be noted that the above method can solve the problem that users need to customize their own portal pages, helping users focus on content related to their work or that they are more interested in.

[0082] Figure 2This is a schematic structural diagram of a portal page recommendation device provided in one or more embodiments of this specification. The device includes: a tag determination unit 202 , a recommended content query unit 204 , a recommendation value determination unit 206 and a recommendation unit 208 .

[0083] The tag determination unit 202 determines, when a designated user enters a portal page, an associated tag corresponding to the designated user and a weight value corresponding to the associated tag;

[0084] The recommended content query unit 204 queries the portal page for recommended content containing the associated tag according to the associated tag;

[0085] A recommendation value determination unit 206 determines a recommendation value of the recommended content according to the weight value of the associated tag;

[0086] The recommendation unit 208 recommends the recommended content to the designated user according to the recommendation value of the recommended content.

[0087] Figure 3 A schematic diagram of a structure of a portal page recommendation device provided for one or more embodiments of this specification includes:

[0088] at least one processor; and,

[0089] a memory communicatively connected to the at least one processor; wherein,

[0090] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0091] When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag;

[0092] According to the associated tag, searching the portal page for recommended content containing the associated tag;

[0093] Determining a recommendation value of the recommended content according to the weight value of the associated tag;

[0094] Recommend the recommended content to the designated user according to the recommendation value of the recommended content.

[0095] One or more embodiments of this specification provide a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to:

[0096] When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag;

[0097] According to the associated tag, searching the portal page for recommended content containing the associated tag;

[0098] Determining a recommendation value of the recommended content according to the weight value of the associated tag;

[0099] Recommend the recommended content to the designated user according to the recommendation value of the recommended content.

[0100] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0101] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A portal page recommendation method, characterized in that: The method comprises: When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag; According to the associated tag, searching the portal page for recommended content containing the associated tag; Determining a recommendation value of the recommended content according to the weight value of the associated tag; Recommending the recommended content to the designated user according to the recommendation value of the recommended content; Before the designated user enters the portal page, the method further includes: Obtaining relevant behaviors of the designated user and setting corresponding content tags for the content of the portal page; The determining of the associated tag corresponding to the designated user specifically includes: When the designated user triggers the relevant behavior on the portal page, determining the trigger content corresponding to the relevant behavior; Determining a first content tag corresponding to the triggering content, and recording the first content tag as the associated tag; Determining the weight value corresponding to the associated tag specifically includes: Determining a weight value corresponding to the associated tag according to the preset weight of the related behavior and the preset weight of the associated tag; The relevant behaviors include one or more of browsing, sharing and collecting; Determining the recommendation value of the recommended content according to the weight value of the associated tag specifically includes: Determining the relevance of the associated tags in the recommended content; determining a recommendation value of the recommended content according to the relevance of the associated tags and the weight values of the associated tags; After determining the recommendation value of the recommended content according to the weight value of the associated tag, the method further includes: If it is determined that the recommended content is associated with the position of the designated user, increasing the recommendation value of the recommended content by a preset value; The method further comprises: Determining the keyword preset by the designated user; When a designated user enters the portal page, determining specific content containing the keyword and setting a preset recommendation value for the specific content; The recommending to the designated user according to the recommendation value of the recommended content specifically includes: Recommending the recommended content to the designated user based on the recommendation value of the recommended content and the preset recommendation value of the specific content.

2. A portal page recommendation device, characterized in that: The device comprises: a tag determining unit, which determines, when a designated user enters a portal page, an associated tag corresponding to the designated user and a weight value corresponding to the associated tag; a recommended content query unit, which queries the portal page for recommended content containing the associated tag according to the associated tag; a recommendation value determination unit, which determines the recommendation value of the recommended content according to the weight value of the associated tag; A recommendation unit, which recommends the recommended content to the designated user according to the recommendation value of the recommended content; Before the designated user enters the portal page, the process also includes: Obtaining relevant behaviors of the designated user and setting corresponding content tags for the content of the portal page; Determining the associated tag corresponding to the designated user specifically includes: When the designated user triggers the relevant behavior on the portal page, determining the trigger content corresponding to the relevant behavior; Determining a first content tag corresponding to the triggering content, and recording the first content tag as the associated tag; Determining the weight value corresponding to the associated tag specifically includes: Determining a weight value corresponding to the associated tag according to the preset weight of the related behavior and the preset weight of the associated tag; The relevant behaviors include one or more of browsing, sharing and collecting; Determining the recommendation value of the recommended content according to the weight value of the associated tag specifically includes: Determining the relevance of the associated tags in the recommended content; determining a recommendation value of the recommended content according to the relevance of the associated tags and the weight values of the associated tags; After determining the recommendation value of the recommended content according to the weight value of the associated tag, the method further includes: If it is determined that the recommended content is associated with the position of the designated user, increasing the recommendation value of the recommended content by a preset value; Also includes: Determining the keyword preset by the designated user; When a designated user enters the portal page, determining specific content containing the keyword and setting a preset recommendation value for the specific content; The recommending to the designated user according to the recommendation value of the recommended content specifically includes: Recommending the recommended content to the designated user based on the recommendation value of the recommended content and the preset recommendation value of the specific content.

3. A portal page recommendation device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag; According to the associated tag, searching the portal page for recommended content containing the associated tag; Determining a recommendation value of the recommended content according to the weight value of the associated tag; Recommending the recommended content to the designated user according to the recommendation value of the recommended content; Before the designated user enters the portal page, the process also includes: Obtaining relevant behaviors of the designated user and setting corresponding content tags for the content of the portal page; The determining of the associated tag corresponding to the designated user specifically includes: When the designated user triggers the relevant behavior on the portal page, determining the trigger content corresponding to the relevant behavior; Determining a first content tag corresponding to the triggering content, and recording the first content tag as the associated tag; Determining the weight value corresponding to the associated tag specifically includes: Determining a weight value corresponding to the associated tag according to the preset weight of the related behavior and the preset weight of the associated tag; The relevant behaviors include one or more of browsing, sharing and collecting; Determining the recommendation value of the recommended content according to the weight value of the associated tag specifically includes: Determining the relevance of the associated tags in the recommended content; determining a recommendation value of the recommended content according to the relevance of the associated tags and the weight values of the associated tags; After determining the recommendation value of the recommended content according to the weight value of the associated tag, the method further includes: If it is determined that the recommended content is associated with the position of the designated user, increasing the recommendation value of the recommended content by a preset value; Also includes: Determining the keyword preset by the designated user; When a designated user enters the portal page, determining specific content containing the keyword and setting a preset recommendation value for the specific content; The recommending to the designated user according to the recommendation value of the recommended content specifically includes: Recommending the recommended content to the designated user based on the recommendation value of the recommended content and the preset recommendation value of the specific content.

4. A non-volatile computer storage medium, characterized in that Computer-executable instructions are stored, and the computer-executable instructions are configured to: When a designated user enters a portal page, determining an associated tag corresponding to the designated user and a weight value corresponding to the associated tag; According to the associated tag, searching the portal page for recommended content containing the associated tag; Determining a recommendation value of the recommended content according to the weight value of the associated tag; Recommending the recommended content to the designated user according to the recommendation value of the recommended content; Before the designated user enters the portal page, the process also includes: Obtaining relevant behaviors of the designated user and setting corresponding content tags for the content of the portal page; Determining the associated tag corresponding to the designated user specifically includes: When the designated user triggers the relevant behavior on the portal page, determining the trigger content corresponding to the relevant behavior; Determining a first content tag corresponding to the triggering content, and recording the first content tag as the associated tag; Determining the weight value corresponding to the associated tag specifically includes: Determining a weight value corresponding to the associated tag according to the preset weight of the related behavior and the preset weight of the associated tag; The relevant behaviors include one or more of browsing, sharing and collecting; Determining the recommendation value of the recommended content according to the weight value of the associated tag specifically includes: Determining the relevance of the associated tags in the recommended content; determining a recommendation value of the recommended content according to the relevance of the associated tags and the weight values of the associated tags; After determining the recommendation value of the recommended content according to the weight value of the associated tag, the method further includes: If it is determined that the recommended content is associated with the position of the designated user, increasing the recommendation value of the recommended content by a preset value; Also includes: Determining the keyword preset by the designated user; When a designated user enters the portal page, determining specific content containing the keyword and setting a preset recommendation value for the specific content; The recommending to the designated user according to the recommendation value of the recommended content specifically includes: Recommending the recommended content to the designated user based on the recommendation value of the recommended content and the preset recommendation value of the specific content.

Images