Article detail page-based content recommendation method and device, equipment and storage medium

Abstract

The application relates to the fields of Internet and financial technology, and discloses a content recommendation method and device based on an article detail page, equipment and a storage medium. The method comprises the following steps: obtaining a target article browsed by a user, performing tag processing on the target article, and obtaining the content tags of the target article; obtaining preset product tags and service tags; matching the content tags with the product tags and the service tags respectively; if the content tags match the product tags, obtaining a target product corresponding to the product tags as recommendation content, and displaying the recommendation content in the form of an advertisement in the detail page of the target article; and if the content tags match the service tags, obtaining a target service corresponding to the service tags as recommendation content, and displaying the recommendation content in the form of an advertisement in the detail page of the target article. Through the above method, the accuracy of shopping advertisement recommendation, user experience, utilization rate of advertisement resources and conversion rate can be improved.

Description

Technical Field

[0001] This invention relates to the fields of internet and financial technology, and in particular to a method, apparatus, device, and storage medium for content recommendation based on article detail pages. Background Technology

[0002] With the rapid development of internet technology, functions such as shopping, social networking, interactive games, and resource transfer can be supported. In a shopping advertising recommendation platform application scenario, the article details page involves multiple components, including guiding users to learn about the author and interacting with the content (sharing, liking, commenting, etc.). Product advertisements can be embedded in the main text to guide users to make a purchase. Further recommendations of similar content can increase user dwell time and click-through rates on the platform, thereby improving user retention.

[0003] Traditional advertising recommendations require users to sift through massive amounts of information to find suitable product content. At the same time, the lack of contextualized marketing directly interrupts users' browsing behavior on mobile devices, which can easily cause user dissatisfaction and lead to the loss of platform users. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for content recommendation based on article detail pages, which can improve the accuracy of shopping advertisement recommendations, user experience, utilization rate of advertising resources, and conversion rate.

[0005] To solve the above-mentioned technical problems, one technical solution adopted by the present invention is: to provide a content recommendation method based on an article details page, comprising:

[0006] The system retrieves the target article that the user is currently browsing and tags the target article based on a preset content tag library to obtain the content tags of the target article.

[0007] Product tags are obtained from a pre-defined product tag library, and service tags are obtained from a pre-defined service tag library.

[0008] The content tags are matched with the product tags and the service tags respectively;

[0009] If the content tag matches the product tag, the target product corresponding to the product tag is obtained as recommended content, and the recommended content is displayed in the details page of the target article in the form of an advertisement;

[0010] If the content tag matches the service tag, the target service corresponding to the service tag is obtained as recommended content, and the recommended content is displayed in the details page of the target article in the form of an advertisement.

[0011] According to one embodiment of the present invention, matching the content tag with the product tag and the service tag respectively includes:

[0012] The content tags are associated with the product tags, and a first relevance is calculated between the content tags and the associated product tags.

[0013] Based on the calculation result of the first relevance, determine whether the content tag matches the associated mapped product tag;

[0014] If so, then the steps are performed to obtain the target product corresponding to the product tag as recommended content, and to display the recommended content in the details page of the target article in the form of an advertisement.

[0015] According to an embodiment of the present invention, after determining whether the content tag matches the associated mapped product tag based on the calculation result of the first relevance, the method further includes:

[0016] If not, the content tag and the service tag are associated and mapped, and a second relevance between the content tag and the associated service tag is calculated;

[0017] Based on the calculation result of the second relevance, it is determined whether the content tag matches the associated mapped service tag;

[0018] If so, then the steps are performed to obtain the target service corresponding to the service tag as recommended content, and to display the recommended content in the details page of the target article in the form of an advertisement.

[0019] According to an embodiment of the present invention, determining whether the content tag matches the associated mapped product tag based on the calculation result of the first relevance includes:

[0020] The calculation result of the first relevance is compared with the first preset value to determine whether the calculation result of the first relevance is higher than the first preset value;

[0021] If so, then determine that the content tag matches the associated mapped product tag;

[0022] If not, then it is determined that the content tag does not match the associated mapped product tag;

[0023] The step of determining whether the content tag matches the associated mapped service tag based on the calculation result of the second relevance includes:

[0024] The calculation result of the second relevance is compared with the second preset value to determine whether the calculation result of the second relevance is higher than the second preset value;

[0025] If so, then it is determined that the content tag matches the associated mapped service tag;

[0026] If not, then it is determined that the content tag does not match the associated mapped service tag.

[0027] According to one embodiment of the present invention, calculating the first relevance between the content tag and the associated mapped product tag includes:

[0028] Calculate the similarity between the content tag and the product tag;

[0029] Based on the similarity calculation results, target content tags that match the product tags are determined;

[0030] Calculate the proportion of the target content tag in the content tags to obtain the first relevance.

[0031] According to one embodiment of the present invention, after obtaining the target service corresponding to the service tag as recommended content and displaying the recommended content in the detail page of the target article in the form of an advertisement, the method further includes:

[0032] Call the coupon center interface to obtain the coupon configuration information, and determine whether the target service has pre-configured coupons based on the configuration information;

[0033] If so, determine whether the coupon is within its validity period;

[0034] If so, when allowing the user to claim the coupon, display the coupon's content information and the claiming portal.

[0035] According to one embodiment of the present invention, obtaining the target article that the user is browsing and tagging the target article based on a preset content tag library to obtain the content tags of the target article includes:

[0036] The system retrieves the target article that the user is currently browsing and performs word segmentation on the target article to obtain multiple short texts.

[0037] The short texts are classified to obtain comment text and non-comment text;

[0038] The comment text is preprocessed, and a text set is formed based on the preprocessed comment text and the non-comment text;

[0039] Calculate the similarity between each text in the text set and the content tags in the preset content tag library;

[0040] The content tags corresponding to the target article are determined based on the similarity calculation results.

[0041] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is: to provide a content recommendation device based on an article details page, comprising:

[0042] The tagging module is used to obtain the target article that the user is browsing, and to tag the target article based on a preset content tag library to obtain the content tags of the target article;

[0043] The acquisition module is used to acquire product tags based on a preset product tag library and service tags based on a preset service tag library.

[0044] A matching module is used to match the content tags with the product tags and the service tags, respectively;

[0045] The first recommendation module is used to obtain the target product corresponding to the product tag as recommended content if the content tag matches the product tag, and to display the recommended content in the details page of the target article in the form of an advertisement;

[0046] The second recommendation module is used to obtain the target service corresponding to the service tag as recommended content if the content tag matches the service tag, and to display the recommended content in the details page of the target article in the form of an advertisement.

[0047] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is to provide a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the content recommendation method based on the article details page.

[0048] To solve the above-mentioned technical problems, another technical solution adopted by the present invention is to provide a computer storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the above-mentioned content recommendation method based on article detail pages.

[0049] The beneficial effects of this invention are as follows: by acquiring the target article that the user is browsing and tagging the target article based on a preset content tag library to obtain the content tags of the target article; acquiring preset product tags and service tags; matching the content tags with the product tags and service tags respectively; determining recommended content based on the matching results, and using tags in the form of automatic tag matching to display matching products or services on the target article details page, it is possible to improve the accuracy of shopping advertisement recommendations, user experience, utilization rate of advertising resources, and conversion rate. Attached Figure Description

[0050] Figure 1 This is a flowchart illustrating the content recommendation method based on article detail pages according to the first embodiment of the present invention;

[0051] Figure 2 This is a flowchart illustrating step S103 in an embodiment of the present invention;

[0052] Figure 3 This is a flowchart illustrating the content recommendation method based on article detail pages according to the second embodiment of the present invention;

[0053] Figure 4 This is a schematic diagram of the structure of a content recommendation device based on an article details page according to an embodiment of the present invention;

[0054] Figure 5 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention;

[0055] Figure 6 This is a schematic diagram of the structure of a computer storage medium according to an embodiment of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0057] The terms "first," "second," and "third" used in this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this invention are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the figures). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0058] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0059] Figure 1 This is a flowchart illustrating the content recommendation method based on article detail pages according to the first embodiment of the present invention. It should be noted that if substantially the same result is achieved, the method of the present invention is not necessarily identical. Figure 1 The illustrated process sequence is limited. For example... Figure 1 As shown, the method includes the following steps:

[0060] Step S101: Obtain the target article that the user is browsing, and tag the target article based on the preset content tag library to obtain the content tags of the target article.

[0061] In step S101, the preset content tag library includes several content tags, including first-level, second-level, and third-level tags. The content tags related to the target article can be one or more. In one embodiment, after obtaining the target article, the AI ​​tagging interface can be called in real time to tag the title and body of the target article. In another embodiment, the target article currently being viewed by the user is obtained and segmented into multiple short texts; the short texts are then classified to obtain comment texts and non-comment texts; the comment texts are preprocessed, and a text set is formed based on the preprocessed comment texts and non-comment texts; the similarity between each text in the text set and the content tags in the preset content tag library is calculated; and the content tags corresponding to the target article are determined based on the similarity calculation results.

[0062] Comment text consists of short texts related to the comment. Preprocessing of the comment text involves filtering its quality based on content, retaining superior comment texts and removing inferior ones. Specifically, comments are categorized into featured comments, high-quality comments, medium-quality comments, spam comments, and non-compliant comments. Superior comment texts include featured, high-quality, and medium-quality comments, while inferior comment texts include spam and non-compliant comments. Featured comments are those automatically selected based on a set number of likes, or manually selected in the background. High-quality comments are those deemed highly relevant to the main text and relatively positive by an AI model based on semantic analysis. Medium-quality comments are ordinary comments. Spam comments are those made to complete tasks or maliciously inflate numbers, such as duplicate comments or using the same text. Non-compliant comments are inappropriate content that violates preset rules.

[0063] Step S102: Obtain product tags based on the preset product tag library, and obtain service tags based on the preset service tag library.

[0064] In step S102, the preset product tag library is created by the business party. The business party extracts product tags based on the products, and the product tag library is composed of multiple product tags. In this embodiment, the products can be financial insurance, such as non-motor insurance products, such as accident insurance, home insurance, and health insurance. The preset service tag library is also created by the business party. The business party extracts service tags based on service functions, and the service tag library is composed of multiple service tags. In this embodiment, the services can be car services, such as car washing and refueling.

[0065] Step S103: Match the content tags with the product tags and service tags respectively.

[0066] In step S103, the lowest-level tag, i.e., the third-level tag, is extracted from the content tag. The extracted lowest-level tag is then matched with one of the product tag and the service tag. If the extracted lowest-level tag does not match the product tag / service tag, it is then matched with the other of the product tag and the service tag. In this embodiment, the matching order between the content tag and the product tag, and between the content tag and the service tag, is not limited. If one of the content tag and the product tag or the service tag matches successfully, there is no need to perform the matching of the other of the content tag and the product tag or the service tag.

[0067] Further, please see Figure 2 Step S103 further includes the following steps:

[0068] Step S201: Associate and map the content tags with the product tags, and calculate the first relevance between the content tags and the associated product tags.

[0069] In step S201, if there are multiple content tags, each content tag is associated with a product tag and the first relevance between each content tag and the associated product tag is calculated. Specifically, the similarity between the content tag and the product tag is calculated; the target content tag that matches the product tag is determined based on the similarity calculation result; the proportion of the target content tag in the content tags is calculated to obtain the first relevance.

[0070] Step S202: Determine whether the content tag matches the associated mapped product tag based on the calculation result of the first relevance.

[0071] In step S202, the calculated result of the first relevance is compared with a first preset value to determine whether the calculated result of the first relevance is higher than the first preset value. If yes, it is determined that the content tag matches the associated mapped product tag; if no, it is determined that the content tag does not match the associated mapped product tag. The first preset value can be adjusted according to the actual situation, for example, 90%.

[0072] Step S203: If yes, then execute the step of obtaining the target product corresponding to the product tag as recommended content, and displaying the recommended content as an advertisement on the details page of the target article.

[0073] In step S203, if the first relevance is higher than the first preset value, that is, the first relevance is greater than the first preset value, then the content tag matches the associated mapped product tag, and step S104 is executed.

[0074] Step S204: If not, perform association mapping between content tags and service tags, and calculate the second relevance between content tags and the associated service tags.

[0075] In step S204, if the first relevance is not higher than the first preset value, i.e., the first relevance is less than or equal to the first preset value, then the content tag does not match the associated mapped product tag, and the content tag needs to be matched with the service tag respectively, i.e., steps S204-S205.

[0076] Specifically, if there are multiple content tags, each content tag is associated with a service tag, and a second relevance is calculated between each content tag and its associated service tag. More specifically, the similarity between content tags and service tags is calculated; based on the similarity calculation results, a target content tag matching the service tag is determined; and the proportion of the target content tag among the content tags is calculated to obtain the second relevance.

[0077] Step S205: Determine whether the content tag matches the associated mapped service tag based on the calculation result of the second relevance.

[0078] In step S205, the calculated result of the second relevance is compared with a second preset value to determine whether the calculated result of the second relevance is higher than the second preset value. If yes, it is determined that the content tag matches the associated mapped service tag; if no, it is determined that the content tag does not match the associated mapped service tag. The second preset value can be adjusted according to the actual situation, for example, 90%.

[0079] Step S206: If yes, then execute the step of obtaining the target service corresponding to the service tag as recommended content, and displaying the recommended content as an advertisement on the details page of the target article.

[0080] In step S206, if the second relevance is higher than the second preset value, that is, the second relevance is greater than the second preset value, then the content tag matches the associated mapped service tag, and step S105 is executed.

[0081] Step S104: If the content tag matches the product tag, then obtain the target product corresponding to the product tag as recommended content, and display the recommended content as an advertisement on the details page of the target article.

[0082] In step S104, if the content tag matches the product tag, the product matching result corresponding to the product tag is obtained, such as the product ID code. Then, the product details interface is retrieved through the product ID code to obtain the product information display. Taking financial insurance as an example, the product information may include: product name and title, applicable age group, coverage amount, coverage period, product ranking, price, and redirect links, etc. At the same time, by tracking data points, the purchase behavior initiated by the user after browsing the product content is recorded, and it can be ultimately tracked whether the user makes a purchase directly after browsing or indirectly within 7 days after browsing.

[0083] Step S105: If the content tag matches the service tag, then obtain the target service corresponding to the service tag as recommended content, and display the recommended content as an advertisement on the details page of the target article.

[0084] In step S105, if the content tag matches the service tag, the service matching result corresponding to the service tag is obtained, such as the service ID. Then, the service details interface is retrieved through the service ID to obtain the display of service information, including: service title, subtitle, icon and jump link, etc.

[0085] The content recommendation method based on article detail pages in the first embodiment of the present invention obtains the target article that the user is currently browsing, and tags the target article based on a preset content tag library to obtain content tags for the target article; obtains preset product tags and service tags; matches the content tags with the product tags and service tags respectively; determines the recommended content based on the matching results, and uses tags in the form of automatic tag matching to display matching products or services on the target article detail page, which can improve the accuracy of shopping advertisement recommendations, user experience, utilization rate of advertising resources, and conversion rate.

[0086] Figure 3 This is a flowchart illustrating the content recommendation method based on article detail pages according to the second embodiment of the present invention. It should be noted that if substantially the same result is achieved, the method of the present invention does not necessarily require further elaboration. Figure 3 The illustrated process sequence is limited. For example... Figure 3 As shown, the method includes the following steps:

[0087] Step S301: Obtain the target article that the user is browsing, and tag the target article based on the preset content tag library to obtain the content tags of the target article.

[0088] In this embodiment, Figure 3 Step S301 and Figure 1 The steps in step S101 are similar and will not be repeated here for the sake of simplicity.

[0089] Step S302: Obtain product tags based on the preset product tag library, and obtain service tags based on the preset service tag library.

[0090] In this embodiment, Figure 3 Step S302 and Figure 1 Step S102 is similar and will not be repeated here for the sake of simplicity.

[0091] Step S303: Match the content tags with the product tags and service tags respectively.

[0092] In this embodiment, Figure 3 Step S303 and Figure 1 Step S103 is similar and will not be repeated here for the sake of simplicity.

[0093] Step S304: If the content tag matches the product tag, then obtain the target product corresponding to the product tag as recommended content, and display the recommended content as an advertisement on the details page of the target article.

[0094] In this embodiment, Figure 3 Step S304 and Figure 1 Step S104 is similar and will not be repeated here for the sake of simplicity.

[0095] Step S305: If the content tag matches the service tag, then obtain the target service corresponding to the service tag as recommended content, and display the recommended content as an advertisement on the details page of the target article.

[0096] In this embodiment, Figure 3 Step S305 and Figure 1 Step S105 is similar and will not be repeated here for the sake of simplicity.

[0097] Step S306: Call the coupon center interface to obtain the coupon configuration information, and determine whether the target service has pre-configured coupons based on the configuration information.

[0098] Step S307: If yes, then determine whether the coupon is within its validity period.

[0099] In step S307, if the target service has pre-configured coupons, the validity period of the coupons is obtained, and it is determined whether the coupons are within the validity period. If the target service has not pre-configured coupons or has pre-configured coupons but the coupons are not within the validity period, the coupon entry will not be displayed.

[0100] Step S308: If so, when allowing users to claim coupons, display the coupon details and claim entry point.

[0101] In step S308, if the coupon is within its validity period, it is also necessary to determine whether the current user is eligible to receive the coupon. If so, the user is allowed to receive the coupon, and the coupon content information and the entry point for receiving the coupon are displayed. The coupon content information includes: the coupon icon, the coupon name, and the receiving status.

[0102] The content recommendation method based on article detail pages in the second embodiment of the present invention, based on the first embodiment, improves user experience, advertising resource utilization and conversion rate by displaying coupon content information and redemption entry when coupons are pre-configured in the target service and are within their validity period. This can guide users to initiate transaction behavior, thereby increasing the platform's revenue and user stickiness.

[0103] Figure 4 This is a schematic diagram of the structure of a content recommendation device based on an article details page according to an embodiment of the present invention. Figure 4 As shown, the device 40 includes a marking processing module 41, an acquisition module 42, a matching module 43, a first recommendation module 44, and a second recommendation module 45.

[0104] The tagging module 41 is used to obtain the target article that the user is browsing, and to tag the target article based on a preset content tag library to obtain the content tags of the target article;

[0105] The acquisition module 42 is used to acquire product tags based on a preset product tag library and service tags based on a preset service tag library.

[0106] Matching module 43 is used to match content tags with product tags and service tags respectively;

[0107] The first recommendation module 44 is used to obtain the target product corresponding to the product tag as recommended content if the content tag matches the product tag, and to display the recommended content in the form of an advertisement on the details page of the target article;

[0108] The second recommendation module 45 is used to obtain the target service corresponding to the service tag as recommended content if the content tag matches the service tag, and to display the recommended content in the form of an advertisement on the details page of the target article.

[0109] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Figure 5 As shown, the computer device 50 includes a processor 51 and a memory 52 coupled to the processor 51.

[0110] The memory 52 stores program instructions for implementing the content recommendation method based on article detail pages as described in any of the above embodiments.

[0111] Processor 51 is used to execute program instructions stored in memory 52 to recommend content.

[0112] The processor 51 can also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip with signal processing capabilities. The processor 51 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0113] See Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer storage medium according to an embodiment of the present invention. The computer storage medium of this embodiment stores a program file 61 capable of implementing all the above methods. This program file 61 can be stored in the computer storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0114] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0115] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] The above are merely embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An article detail page based content recommendation method, characterized in that, The method comprises the following steps: acquiring a target article being browsed by a user, and tagging the target article based on a preset content label library to obtain a content label of the target article, including: acquiring the target article being browsed by the user and performing word segmentation on the target article to obtain a plurality of short texts; performing classification processing on the short texts to obtain comment texts and non-comment texts; preprocessing the comment texts, and forming a text set based on the preprocessed comment texts and the non-comment texts; calculating the similarity between each text in the text set and a content label in a preset content label library; and determining the content label corresponding to the target article according to the similarity calculation result; acquiring a product label based on a preset product label library and a service label based on a preset service label library; matching the content label with the product label and the service label, including: performing associated mapping processing on the content label and the product label, and calculating the first correlation degree between the content label and the associated mapped product label; determining whether the content label matches the associated mapped product label according to the calculation result of the first correlation degree; if yes, acquiring a target product corresponding to the product label as recommended content, and displaying the recommended content in the form of an advertisement in the detail page of the target article; if the content label matches the product label, acquiring a target product corresponding to the product label as recommended content, and displaying the recommended content in the form of an advertisement in the detail page of the target article; if the content label matches the service label, acquiring a target service corresponding to the service label as recommended content, and displaying the recommended content in the form of an advertisement in the detail page of the target article, wherein, after displaying the recommended content, the purchase behavior of the user for the recommended content is tracked through data burying to monitor the advertising recommendation effect, including tracking whether the user directly transacts after browsing or indirectly transacts within a preset time.

2. The content recommendation method according to claim 1, characterized by, After determining whether the content label matches the associated mapped product label according to the calculation result of the first correlation degree, the method further comprises the following steps: if no, performing associated mapping processing on the content label and the service label, and calculating the second correlation degree between the content label and the associated mapped service label; determining whether the content label matches the associated mapped service label according to the calculation result of the second correlation degree; if yes, acquiring a target service corresponding to the service label as recommended content, and displaying the recommended content in the form of an advertisement in the detail page of the target article.

3. The content recommendation method according to claim 2, characterized by, The step of determining whether the content label matches the associated mapped product label according to the calculation result of the first correlation degree comprises the following steps: comparing the calculation result of the first correlation degree with a first preset value to determine whether the calculation result of the first correlation degree is higher than the first preset value; if yes, it is determined that the content label matches the associated mapped product label; If not, it is determined that the content label does not match the product label in the associated mapping; The step of determining whether the content label matches the service label in the associated mapping according to the calculation result of the second correlation degree includes: Comparing the calculation result of the second correlation degree with a second preset value to determine whether the calculation result of the second correlation degree is higher than the second preset value; If yes, it is determined that the content label matches the service label in the associated mapping; If not, it is determined that the content label does not match the service label in the associated mapping.

4. The content recommendation method of claim 1, wherein, The step of calculating the first correlation degree between the content label and the product label in the associated mapping includes: Calculating the similarity between the content label and the product label; Determining a target content label that matches the product label according to the similarity calculation result; Calculating the proportion of the target content label in the content label to obtain the first correlation degree.

5. The content recommendation method of claim 1, wherein, After the step of obtaining the target service corresponding to the service label as the recommended content and displaying the recommended content in the form of an advertisement in the detail page of the target article, the method further includes: Calling a coupon center interface to obtain configuration information of a coupon, and determining whether the target service is preconfigured with the coupon according to the configuration information; If yes, it is determined whether the coupon is within a valid period; If yes, the content information and the acquisition portal of the coupon are displayed when the user is allowed to acquire the coupon.

6. An article detail page-based content recommendation apparatus, characterized by comprising: The method includes: A labeling processing module is configured to obtain a target article being browsed by a user, and perform labeling processing on the target article based on a preset content label library to obtain a content label of the target article, including: obtaining a target article being browsed by a user and performing word segmentation processing on the target article to obtain a plurality of short texts; performing classification processing on the short texts to obtain review texts and non-review texts; preprocessing the review texts, and composing a text set based on the preprocessed review texts and the non-review texts; calculating the similarity between each text in the text set and a content label in a preset content label library; and determining a content label corresponding to the target article according to the similarity calculation result; A obtaining module is configured to obtain a product label based on a preset product label library, and obtain a service label based on a preset service label library; A matching module is configured to match the content label with the product label and the service label, including: performing associated mapping processing on the content label and the product label, and calculating a first correlation degree between the content label and the product label in the associated mapping; determining whether the content label matches the product label in the associated mapping according to the calculation result of the first correlation degree; if yes, performing the steps of obtaining a target product corresponding to the product label as the recommended content, and displaying the recommended content in the form of an advertisement in the detail page of the target article; The first recommendation module is configured to, if the content label matches the product label, obtain a target product corresponding to the product label as recommendation content, and display the recommendation content in the form of an advertisement in a detail page of the target article. The second recommendation module is configured to, if the content label matches the service label, obtain a target service corresponding to the service label as recommendation content, and display the recommendation content in the form of an advertisement in a detail page of the target article. After the recommendation content is displayed, a user's purchase behavior with respect to the recommendation content is tracked through data burying to monitor the advertising recommendation effect, including tracking whether the user directly transacts after browsing or indirectly transacts within a preset time.

7. A computer device comprising: The memory, the processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the article detail page-based content recommendation method of any one of claims 1-5 when executing the computer program.

8. A computer storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the article detail page-based content recommendation method of any one of claims 1-5.

Images