Content recommendation method and apparatus, electronic device, and readable medium

Abstract

The present application discloses a content recommendation method and apparatus, an electronic device, and a readable medium. In the method, first, a target object class is determined on the basis of historical interaction behaviors; and then a recommended media stream corresponding to the target object class is displayed on a media stream page, the recommended media stream comprising a recommended object corresponding to the target object class.

Description

Content recommendation method, device, electronic device and readable medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese invention patent application with application number 202311023454.6, entitled "A content recommendation method, device, electronic device and readable medium" and filing date August 14, 2023, and incorporates the entirety of that application into this document by reference. Technical Field

[0003] The present application relates to the field of computer technology, and in particular to a content recommendation method, device, electronic device, and readable medium. Background Art

[0004] With the development of the internet, more and more information is being disseminated online, leading to severe information overload. To address this issue, we need to understand user intent as accurately as possible and recommend the content they need to see.

[0005] Currently, recommendation algorithms typically predict user preferences and inclinations based on user information, and then recommend content that the user may be interested in based on the predicted preferences and inclinations. User information may include, for example, user-disclosed information such as gender and age.

[0006] It can be seen that the current recommendation algorithm is unable to provide accurate content recommendations to users.

[0007] Summary of the Invention

[0008] In order to solve the above technical problems, the present application provides a content recommendation method, device, electronic device and readable medium.

[0009] In order to achieve the above objectives, the technical solutions provided by this application are as follows:

[0010] In a first aspect, the present application provides a content recommendation method, which may include:

[0011] Determine the target object category based on historical interaction behavior;

[0012] The recommended media stream corresponding to the target object category is displayed on the media stream page, and the recommended media stream includes the recommended object corresponding to the target object category.

[0013] In a possible implementation, displaying the recommended media stream corresponding to the target object category on the media stream page may include:

[0014] If it is determined that the historical interaction behavior meets the first condition, then the recommended media stream is displayed on the media stream page, and the first condition includes at least one of the following conditions: the number of times the first type of behavior is performed within the first time period reaches a first number threshold, the number of times the second type of behavior is performed within the second time period reaches a second number threshold, the number of times the second type of behavior is performed within the second time period reaches the second number threshold and the third type of behavior is performed on the result of performing the second type of behavior, wherein the first type of behavior, the second type of behavior and the third type of behavior all belong to historical interaction behaviors corresponding to the object category.

[0015] In another possible implementation, displaying the recommended media stream corresponding to the target object category on the media stream page may include:

[0016] If it is determined that a marketing activity related to the historical interaction behavior exists under the target object category, the recommended media stream is displayed on the media stream page, and each of the recommended objects included in the recommended media stream participates in the marketing activity.

[0017] As an example, if the historical interaction behavior is directed at a first-level entity, then the marketing activities related to the historical interaction behavior include the marketing activities of the first-level entity and / or the marketing activities of the second-level entity belonging to the first-level entity; or, if the historical interaction behavior is directed at the second-level entity, then the marketing activities related to the historical interaction behavior include the marketing activities of the second-level entity.

[0018] In a possible implementation, the method may further include:

[0019] In response to performing a first operation on a target object in the media stream page, an object details page of the target object is displayed, and the target object belongs to the recommended object.

[0020] In another possible implementation, the method may further include:

[0021] In response to performing a second operation in the media stream page, a channel page corresponding to the target object category is displayed.

[0022] As an example, the second operation corresponds to a target object, and the target object is displayed at the top of the channel page, or the target object is displayed in an independent unit of the channel page, and the independent unit is used to carry a preset number of objects among the recommended objects in the channel page, and the target object belongs to the recommended objects.

[0023] In a possible implementation, displaying the recommended media stream corresponding to the target object category on the media stream page may include:

[0024] If it is determined that the target object category meets the second condition, the recommended media stream is displayed on the media stream page, and the second condition includes at least one of the following conditions: an interactive behavior belonging to the target object category is performed within a third time period, which belongs to the time range corresponding to the target object category, and the number of interactive behaviors belonging to the target object category performed within a fourth time period reaches a third number threshold, and the third time period and the fourth time period are both preset durations that are earlier than the display time of the recommended media stream.

[0025] In a second aspect, the present application further provides a content recommendation device, which may include:

[0026] A determination unit, used to determine the target object category based on historical interaction behaviors;

[0027] The display unit is configured to display a recommended media stream corresponding to the target object category on a media stream page, wherein the recommended media stream includes recommended objects corresponding to the target object category.

[0028] In a possible implementation, the display unit is specifically configured to:

[0029] If it is determined that the historical interaction behavior meets the first condition, then the recommended media stream is displayed on the media stream page, and the first condition includes at least one of the following conditions: the number of times the first type of behavior is performed within the first time period reaches a first number threshold, the number of times the second type of behavior is performed within the second time period reaches a second number threshold, the number of times the second type of behavior is performed within the second time period reaches the second number threshold and the third type of behavior is performed on the result of performing the second type of behavior, wherein the first type of behavior, the second type of behavior and the third type of behavior all belong to historical interaction behaviors corresponding to the object category.

[0030] In another possible implementation, the display unit is specifically configured to:

[0031] If it is determined that a marketing activity related to the historical interaction behavior exists under the target object category, the recommended media stream is displayed on the media stream page, and each of the recommended objects included in the recommended media stream participates in the marketing activity.

[0032] As an example, if the historical interaction behavior is directed at a first-level entity, then the marketing activities related to the historical interaction behavior include the marketing activities of the first-level entity and / or the marketing activities of the second-level entity belonging to the first-level entity; or, if the historical interaction behavior is directed at the second-level entity, then the marketing activities related to the historical interaction behavior include the marketing activities of the second-level entity.

[0033] In a possible implementation, the display unit is further configured to:

[0034] In response to performing a first operation on a target object in the media stream page, an object details page of the target object is displayed, and the target object belongs to the recommended object.

[0035] In another possible implementation, the display unit is further configured to:

[0036] In response to performing a second operation in the media stream page, a channel page corresponding to the target object category is displayed.

[0037] As an example, the second operation corresponds to a target object, and the target object is displayed at the top of the channel page, or the target object is displayed in an independent unit of the channel page, and the independent unit is used to carry a preset number of objects among the recommended objects in the channel page, and the target object belongs to the recommended objects.

[0038] In a possible implementation, the display unit is specifically configured to:

[0039] If it is determined that the target object category meets the second condition, the recommended media stream is displayed on the media stream page, and the second condition includes at least one of the following conditions: an interactive behavior belonging to the target object category is performed within a third time period, which belongs to the time range corresponding to the target object category, and the number of interactive behaviors belonging to the target object category performed within a fourth time period reaches a third number threshold, and the third time period and the fourth time period are both preset durations that are earlier than the display time of the recommended media stream.

[0040] It should be noted that the specific implementation method of the device and the technical effects achieved can be found in the relevant description of the method provided in the first aspect or any implementation method of the first aspect.

[0041] In a third aspect, the present application further provides an electronic device, the electronic device comprising: a processor and a memory;

[0042] The memory is used to store instructions or programs;

[0043] The processor is used to execute the instructions or programs in the memory so that the electronic device executes the method provided by the first aspect or any one of the implementations of the first aspect.

[0044] In a fourth aspect, the present application also provides a readable medium, which stores instructions or programs. When the instructions or programs are run on a processor, the processor executes the method provided in the first aspect or any one of the implementations of the first aspect.

[0045] In a fifth aspect, the present application further provides a computer program product, which includes instructions, and when executed by a processor, implements the method provided in the first aspect or any one of the implementations of the first aspect.

[0046] In the technical solution provided by this application, users will perform some historical interactive behaviors when using the client, such as searching, watching, liking, and collecting. In order to recommend content to the user more accurately on the client, this application provides a content recommendation method. In this method, the target object category is first determined based on the historical interactive behavior; then the recommended media stream corresponding to the target object category is displayed on the media stream page. The recommended media stream includes the recommended objects corresponding to the target object category, thereby achieving the purpose of content recommendation for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] FIG1 is a flow chart of a memory recommendation method provided in an embodiment of the present application;

[0049] FIG2 is a schematic diagram of a display page in a first possible implementation manner provided in an embodiment of the present application;

[0050] FIG3 is a schematic diagram of another display page in the first possible implementation manner provided in an embodiment of the present application;

[0051] FIG4 is a schematic diagram of a display page in a second possible implementation manner provided in an embodiment of the present application;

[0052] FIG5 is a schematic diagram of another display page in the second possible implementation manner provided in an embodiment of the present application;

[0053] FIG6 is a schematic diagram of a display page in a third possible implementation manner provided in an embodiment of the present application;

[0054] FIG7 is a schematic diagram of another display page in the third possible implementation manner provided in an embodiment of the present application;

[0055] FIG8 is another schematic diagram of a display page in the third possible implementation method provided in an embodiment of the present application

[0056] FIG9 is a schematic structural diagram of a memory recommendation device 900 provided in an embodiment of the present application;

[0057] FIG10 is a schematic structural diagram of an electronic device 1000 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] To facilitate people's lives and work, various clients have emerged, providing users with a variety of services. For example, various short video clients have emerged to enrich daily life; online conferencing clients have emerged to facilitate work; and various online shopping clients have emerged to facilitate shopping. With the explosive growth of information dissemination online, to avoid overloading unwanted content with unwanted content, which could reduce users' "favorability" towards the client, clients often proactively filter information for users, recommending content they believe they might be interested in, thereby improving the user experience.

[0059] Currently, clients typically recommend content based on user information. For example, this information predicts a user's preferences and inclinations, and then recommends content that the user might be interested in. However, user information only provides basic user attributes, such as gender and age, and doesn't truly reflect the content the user actually wants to access on the client. Consequently, the recommended content is often poorly relevant to the user's recent preferences on the client.

[0060] Based on this, an embodiment of the present application provides a content recommendation method, in which a target object category is first determined based on historical interaction behavior; then a recommended media stream corresponding to the target object category is displayed on a media stream page, and the recommended media stream includes the recommended object corresponding to the target object category, thereby achieving the purpose of content recommendation for the user. In this way, considering that the user's behavior during the use of the client (referred to as historical interaction behavior in the embodiment of the present application, for example, including but not limited to: searching, watching, liking or collecting) can better represent the content that the user wants to obtain on the client, in order to overcome the current problem of inaccurate content recommendation based on user information to predict the user's preferences and tendencies and recommend content to the user accordingly, the method perceives the historical interaction behavior performed by the user on the client and generates a recommended media stream corresponding to the target object category according to the target object category corresponding to the historical interaction behavior. Since the recommended media stream is generated based on the user's actual historical interaction behavior, the content carried by the recommended media stream is displayed to the user through the media stream page on the client, so that the user can see the content he wants to browse using the client, thereby improving the user's experience of using the client.

[0061] It should be noted that the subject implementing the content recommendation method may be the content recommendation device provided in the embodiments of the present application. The content recommendation device may be carried in an electronic device or a functional module of an electronic device. The electronic device may be a terminal device installed with the client, or the electronic device may be a server providing services to the client. Alternatively, it can be understood as: a client having the corresponding function of the content recommendation method, or a server having the corresponding function of the content recommendation method to which the client is connected.

[0062] FIG1 is a flow chart of a content recommendation method provided by an embodiment of the present application. The method can be applied to a content recommendation device, such as the content recommendation device 900 shown in FIG9 below. As shown in FIG1 , the method can include the following steps S101 to S102:

[0063] S101, determining the target object category based on historical interaction behaviors.

[0064] Historical interaction behavior refers to the operations performed by users while using the client that can represent the content they want to obtain.

[0065] As an example, historical interaction behaviors representing a user's desire to obtain content can be time-sensitive. For example, when a user uses a client, they may "watch," "follow," "like," or "favorite" content related to the desired content. Another example is when a user uses a client, they may "search" on the client based on their needs. In this example, the content recommendation device can periodically execute the method shown in FIG1 to recommend content that the user desires to obtain from the client.

[0066] As another example, a user's desire to obtain content, as represented by historical interaction behavior, may have long-term attributes. For example, when using a client, a user may voluntarily "register," "enter their birthday," "join as a member," or "purchase a membership." In this example, the content recommendation device can monitor whether a recommended time range matching this historical interaction behavior has been reached. Only when the recommended time range is reached will the method shown in FIG1 be executed to recommend content to the user that is subject to the user's long-term attributes, such as new member benefits, birthday benefits, or anniversary benefits.

[0067] Object categories refer to the categories of different services provided on the client.

[0068] As an example, the object category may correspond to a first-level category. For example, the object category may include: food, hotels, homestays, clothes, or travel, etc.

[0069] As another example, the object category may correspond to a secondary category. The secondary category may be understood as a subcategory of the primary category, which is a refinement of the primary category. For example, the object category may include barbecue, hot pot, or stir-fry.

[0070] In some implementations, if the user performs historical interaction behavior on the client, the target object category corresponding to the historical interaction behavior can be determined based on S101. For example, if the user "follows" hot pot restaurant A on the client, then the target object category determined based on S101 can be food or hot pot; for example, if the user "searches" for hotels on the client, then the target object category determined based on S101 can be hotels, homestays, or selected hotels.

[0071] It can be seen that, based on S101, the target object category corresponding to the historical interaction behavior performed by the user on the client is determined, which determines the direction for subsequent accurate content recommendation.

[0072] S102: Display a recommended media stream corresponding to a target object category on a media stream page. The recommended media stream includes recommended objects corresponding to the target object category.

[0073] Media stream refers to any form of stream that can carry content, such as a feed stream. When a user uses the client, the page displayed to the user by the client for the user to browse is a media stream page. The recommended media stream can be, for example, a media stream displayed on a media stream page, carrying the recommended content in the method provided in the embodiment of the present application. The recommended media stream can, for example, carry relevant information of a preset number (such as 3) of recommended objects. It should be noted that, in the embodiment of the present application, the recommended media stream can be understood as the content carried by the recommended media stream, that is, S102 can be understood as: displaying the content carried by the recommended media stream on the media stream page.

[0074] In an embodiment of the present application, each recommended object in the recommended objects can be considered as an entity. For example, a recommended object can correspond to a brand, a store, or a product. Among them, a brand can include at least one store, and a store can include at least one product. Each recommended object can have its own object details page (also called a point of interest (POI) details page), and the object details page displays relevant information about the recommended object to facilitate users to understand the corresponding recommended object.

[0075] In a first possible implementation, the method may be applicable to a scenario in which a user is directed to push content based on the historical interactive behaviors that the user has performed on the target object category on the client. In this scenario, S102 may include, for example: if it is determined that the historical interactive behaviors that the user has performed on the target object category meet the first condition, then, generating a recommended media stream, and displaying the recommended media stream on the media stream page. The first condition may, for example, include at least one of the following conditions: the number of times the first type of behavior is performed within a first time period reaches a first number threshold; the number of times the second type of behavior is performed within a second time period reaches a second number threshold; the number of times the second type of behavior is performed within a second time period reaches a second number threshold and a third type of behavior is performed on the result of performing the second type of behavior. The above-mentioned first type of behavior, second type of behavior, and third type of behavior all belong to historical interactive behaviors performed on object categories.

[0076] As an example, the first type of behavior may include at least one of the following: viewing an object details page, liking an object details page, adding an object details page to favorites, or following an object details page. When the number of times a user performs the first type of behavior (viewing, liking, or viewing + liking) on ​​an object details page under a target object category (such as food) within a first time period (such as 2 hours) reaches a first threshold (such as 5 times), the user's historical interaction behavior with the target object category is considered to meet the first condition, thereby generating a recommended media stream corresponding to the target object category. It should be noted that, for more accurate content recommendations, multiple first type behaviors on the same object details page within the first time period can be counted as one first type behavior.

[0077] As another example, the second type of behavior may include at least one of the following: searching for products, searching for stores (also known as shops), or searching for brands (also known as merchants). When the number of times a user performs the second type of behavior for a target object category within a second time period reaches a second threshold, the user's historical interaction behavior with the target object category is considered to meet the first condition, and a recommended media stream corresponding to the target object category is generated. The second threshold can be, for example, 1. In this case, if the user has searched for products, stores, or brands within a certain object category within the second time period, a recommended media stream corresponding to the search behavior is generated.

[0078] As another example, the second type of behavior may include at least one of the following: searching for products, searching for stores, or searching for brands. When the number of times a user performs the second type of behavior for the same object category within a second time period reaches a second threshold, in order to further confirm whether the user's search results are the content the user wants to obtain, it may also be determined whether the user performs a third type of behavior on the results of performing the second type of behavior. If the user performs the third type of behavior on the results of performing the second type of behavior, the search results are considered to be the content the user wants to obtain, and thus a corresponding recommended media stream is generated. If the user does not perform the third type of behavior on the results of performing the second type of behavior, the search results are considered not to be the content the user wants to obtain, and thus no corresponding recommended media stream is generated. The third type of behavior may, for example, include at least one of the following: browsing the search results for a time greater than or equal to a preset time length (e.g., 5 seconds), performing operations such as viewing, collecting, following, or adding to a shopping cart on at least one of the search results. Taking the second numerical threshold equal to 1 and the second time period of 1 hour as an example, when the user has searched for products, stores or brands in a certain object category within 1 hour and browsed the search results for more than 5 seconds, a recommended media stream corresponding to the search behavior is generated.

[0079] It should be noted that for the first condition related to the second category of behavior, in order to improve the user experience of the client, the second category of behavior can exclude explicit searches. For example, the user's search for Quanjude Roast Duck is not counted as the second category of behavior.

[0080] It should be noted that, in the above three examples, the first time period and the second time period may be the same or different, and the first number threshold and the second number threshold may be the same or different, and may be flexibly set based on demand.

[0081] It can be seen that once the user's historical interaction behavior with respect to the target object category meets at least one of the above conditions, the target object category is determined for the user, thereby generating a recommended media stream corresponding to the target object category, making accurate targeted recommendations possible in the embodiments of the present application.

[0082] In a second possible implementation, the method can be applied to a scenario where a targeted push is provided to a user when a marketing activity related to a historical interactive behavior exists under a target object category on the client. In this scenario, S102 may include, for example: if it is determined that a marketing activity related to a historical interactive behavior exists under a target object category, a recommended media stream is generated, and the recommended media stream is displayed on a media stream page, and the recommended object in the recommended media stream is recommended to participate in the marketing activity. If the historical interactive behavior is directed to a first-level entity, the marketing activity related to the historical interactive behavior may include the marketing activity of the first-level entity and / or the marketing activity of a second-level entity belonging to the first-level entity; if the historical interactive behavior is directed to a second-level entity, the marketing activity related to the historical interactive behavior may include the marketing activity of the second-level entity.

[0083] In this implementation, historical interactive behaviors may include, for example, at least one of the following behaviors: collecting brands, following brands, collecting stores, following stores, collecting products, or following products. Marketing activities may include, for example, but are not limited to, flash sales, full-discount sales, or discounts.

[0084] For example, if the first-level entity is a brand, then the second-level entity can be a store of that brand. Historical interaction behavior is specific to the first-level entity, meaning that the user has followed or favorited the brand and believes it is content they desire. Once the brand or one of its stores has a marketing campaign, a recommended media stream corresponding to the campaign can be generated to promptly notify users who have followed or favorited the brand. A store's marketing campaign includes marketing campaigns for some or all products within the store.

[0085] As another example, if the first-level entity refers to a store, then the second-level entity can refer to the store's products. The historical interaction behavior is for the first-level entity, that is, the user follows or collects the store and believes that the store is the content that the user wants to obtain. Once the store or one or more of its products have a marketing campaign, in order to promptly notify the user who follows or collects the store, a recommended media stream corresponding to the marketing campaign can be generated. In addition, if the brand to which the store belongs also has marketing campaigns in other stores in the user's area (such as a city, street, or business district), a recommended media stream corresponding to the marketing campaign can also be generated.

[0086] As another example, if the second-level entity is a product, and the historical interaction behavior is specific to the second-level entity, that is, the user has followed or favorited the product and believes that the product is content that the user wants to obtain, once the product has a marketing campaign, in order to promptly notify users who follow or favorite the product, a recommendation media stream corresponding to the marketing campaign can be generated. In addition, if the product has marketing campaigns in multiple stores in the user's area (such as a city, street, or business district), the generated recommendation media stream can include details of the product's marketing campaigns in multiple stores.

[0087] It should be noted that the first-level entity and the second-level entity may correspond to different entities based on different scenarios. For example, the first-level entity may refer to a commodity, and the second-level entity may correspond to the accessories or parts of the commodity; for another example, the first-level entity may refer to a brand alliance, and the second-level entity may correspond to the brand under the brand alliance. This embodiment of the present application does not make specific limitations.

[0088] It can be seen that once an entity that a user follows or collects has a marketing activity, a recommended media stream corresponding to the target object category to which the entity belongs is generated, making accurate targeted recommendations possible in the embodiments of the present application.

[0089] In a third possible implementation, this method can be applied to scenarios where push notifications are targeted to users of the client at a user granularity. In this scenario, based on S102, the recommended media stream is displayed on the media stream page, thereby focusing on historical interaction behaviors with long-term attributes based on user granularity, recommending content with higher user recognition, and further improving the user experience of the client.

[0090] In addition, in the embodiment of the present application, the conditions for generating recommended media streams can be set based on different needs. For example, before S102, it is determined whether the user is an active paying user or a churned user. If so, a recommended media stream is generated for the user. If not, based on this implementation of the embodiment of the present application, no recommended media stream is generated and no content is recommended to the user.

[0091] In addition, in the embodiment of the present application, the display conditions for whether to display the generated recommended media stream in S102 can be set based on different needs. For example, in S102, it is determined whether the content carried in the generated recommended media stream belongs to the same area (for example, the same city) as the user. If so, the "display" of the recommended media stream in S102 is executed. If not, even if the recommended media stream in S102 is generated, the action of "displaying" the recommended media stream is not executed.

[0092] In some implementations, after a recommended media stream is generated, a frequency control condition and / or a negative feedback condition may be used to determine whether the content carried by the recommended media stream is to be displayed on the media stream page of the user's client. If only the frequency control condition is considered without the negative feedback condition, then when the recommended media stream satisfies the frequency control condition, the content carried by the recommended media stream is determined to be displayed on the media stream page of the user's client. Alternatively, if only the negative feedback condition is considered without the frequency control condition, then when the recommended media stream satisfies the negative feedback condition, the content carried by the recommended media stream is determined to be displayed on the media stream page of the user's client. If both the negative feedback condition and the frequency control condition are considered, then when the recommended media stream satisfies both the negative feedback condition and the frequency control condition, the content carried by the recommended media stream is determined to be displayed on the media stream page of the user's client.

[0093] The frequency control condition indicates the number of times content is allowed to be recommended to a user on the client within a preset period (e.g., one day). The frequency control condition can be the same or different for different types of users, and the user type can be determined based on user stratification. For example, for the first possible implementation, two content recommendations (hereinafter referred to as "targeted cards") for the first possible implementation are allowed per day for each high-paying or churned user, and one targeted card recommendation is allowed per day for each non-high-paying or non-churned user. For example, for the second possible implementation, two targeted card recommendations for the second possible implementation are allowed per day for each high-paying or churned user, and one targeted card recommendation is allowed per day for each non-high-paying or non-churned user. It should be noted that the frequency control condition may also include the maximum number of recommendations for other cards that share the frequency control condition with the targeted card. For example, the number of recommendations for all life service-related cards for a user per day does not exceed N (e.g., N = 100). In addition to targeted cards, life service-related content recommendations may also include, but are not limited to, store cards or same-city and different-city cards. If the number of content recommendations to be made exceeds the frequency control condition, then corresponding priorities can be set for various types of content recommendations, and the recommended content displayed to the user can be determined according to the priority. For example, the priority of the store card can be set higher than the directional card, and the priority of the directional card can be set higher than the same-city-different-city card. When the user has a store card, a directional card, and a same-city-different-city card to be recommended at the same time, and is limited to the frequency control condition, only two cards can be selected to recommend to the user, then the store card and directional card with higher priority can be selected to recommend to the user. For the multiple types of directional cards that may be included in the directional card, the priority of each type of directional card can also be set based on the strength of the user's desire to obtain related content. For example, the directional card includes post-search directional cards and post-view directional cards. Since the search can better represent the user's desire to obtain related content, the priority of the post-search directional card can be set higher than the post-view directional card.

[0094] The negative feedback condition is used to indicate the maximum number of times (e.g., 5) that a user may provide negative feedback, such as disliking or ignoring, historically recommended content on the client. For example, if a user on the client receives the maximum number of negative feedbacks for content recommended under the object category of food, the content recommended to the user under that object category is deemed to not meet the negative feedback condition, and all food-related cards will no longer be recommended to the user. Even if a recommended media stream corresponding to food has been generated based on S102, the recommended media stream will no longer be displayed on the media stream page.

[0095] As an example, when the content recommendation device determines that the generated recommended media stream meets the frequency control condition and / or the negative feedback condition, in response to the user refreshing the media stream page of the client, the content corresponding to the recommended media stream is displayed on the media stream page. It should be noted that the media stream page can be any page on the client that can be viewed by the user, such as a recommendation page (also called a home page) or a local city page.

[0096] As another example, after generating a recommended media stream, the content recommendation device determines that the target object category meets a second condition and displays the recommended media stream on the media stream page. The second condition may include at least one of the following: performing an interactive behavior belonging to the target object category within a third time period, which falls within the time range corresponding to the target object category; performing an interactive behavior belonging to the target object category within a fourth time period, which reaches a third threshold; and both the third and fourth time periods are preset durations prior to the time at which the recommended media stream is displayed. In one embodiment, if an interactive behavior belonging to the target object category is performed within the third time period (e.g., 10 minutes), it is determined that the user desires to obtain further recommended content related to the target object category, and the recommended media stream corresponding to the target object category is displayed to the user. In another embodiment, the content recommendation device may maintain a correspondence between target object categories and time ranges. For example, the time ranges corresponding to the food object category include 7:00 AM to 10:00 AM, 12:00 PM to 2:00 PM, and 6:00 PM to 9:00 PM. Thus, if the current time falls within the time range corresponding to the target object category, the recommended media stream corresponding to the target object category is displayed to the user. In another case, if the number of interactive behaviors belonging to the target object category executed within a fourth time period (e.g., 30 minutes) reaches a third threshold (e.g., 3 times), it is determined that the user wants to obtain further recommended content related to the target object category, and thus the recommended media stream corresponding to the target object category is displayed to the user. In this way, by setting the display timing of the recommended media stream, better content recommendations can be made to the user, further improving the user's experience with the client.

[0097] Corresponding to the first possible implementation method mentioned above, in the directional card displayed on the media stream page of the client, the post-view directional card and the post-search directional card are shown in Figures 2 and 3 respectively. The directional card may include: (1) candidate, (2) title, (3) content, (4) btn (i.e., Button, a button instance in Flash, also called an action item), and (5) click interaction. (1) may include the selection of the hit object category, such as the first-level category and / or second-level category candidate set in the channel, which can be used as the theme card; the object category corresponding to travel and accommodation supports the issuance of cards in different places, and all object categories support the issuance of cards in the same city. (2) can include the reason for recommendation and the main title. The reason for recommendation can be, for example, related recommendations. For the post-view directional card, the main title can be: Guess what you want to see + place name + object category name + "recommendation", as shown in Figure 2, for example, it can be: Guess what you want to see Beijing food recommendations; for the post-search directional card, the main title can be: Guess what you want to find + place name + object category name + "recommendation", as shown in Figure 3, for example, it can be: Guess what you want to find Beijing food recommendations. It should be noted that the specific main title copy can be determined according to the mapping relationship table. The mapping relationship table can be represented as the mapping relationship between the first-level category and / or the second-level category of the POI card channel. (3) refers to the specific content of the recommendation, which can block the POI details page that the user has viewed, and sort out a preset number (such as 3) of POIs that meet the object category according to the recommendation algorithm (referring to a recommended store in the figure) and display them (on the same POI card line). Each POI can include: POI header image, POI name, category, regional location, average price per person, distance information or product information, etc. (4) may include: two buttons: Browse More and Not Interested. Clicking "Browse More" enters the corresponding channel page and loads the labels of the first-level category and / or second-level category in the channel. Clicking "Not Interested" generates a negative feedback (only the main page has the "Not Interested" button and the accumulation of negative feedback conditions, and the same-city page does not have the "Not Interested" button and the accumulation of negative feedback conditions). (5) may include: clicking on a specific store to enter the POI details page of the store; clicking on the background or "Browse More" to enter the channel page and load the corresponding category; clicking on the "Back" button on the channel page to return to the directional card shown in Figure 2 or Figure 3.

[0098] Corresponding to the second possible implementation method mentioned above, the directional card displayed on the media stream page of the client may include: (1) candidates, (2) content. Corresponding to (1), it may include: a) card issuance based on the scenario of the merchant that the user follows, b) card issuance based on the store that the user has collected, and c) card issuance based on the goods that the user has collected. In a), for the goods, it is necessary to select the goods that are undergoing marketing activities when the card is issued. For the store, it is necessary to issue the card to the store according to the algorithm, but it is necessary to ensure that the goods corresponding to the store have corresponding marketing activities; in b), for the goods, it is necessary to select the goods that are undergoing marketing activities when the card is issued. For the store, it is necessary to be a store that the user has collected; in c), for the goods, it is necessary to select the goods that the user has collected. For the store, it is necessary to issue the card to the store according to the algorithm, but it is necessary to ensure that the goods corresponding to the store have corresponding marketing activities. For (2), the card issuance strategy of single card and multiple cards can be determined according to the algorithm. For the case of follow-up relationship, user collection of store or user collection of goods, a single card can be issued; for the case of follow-up relationship or user collection of store, multiple cards can be issued.

[0099] For single-item cards, using a marketing campaign as an example, the content of a targeted card can include: recommendation reason, title, store information, product title, price, service tag, hot sale tag, product image, flash sale countdown, button, and click-through interaction. For recommendation reasons, for cards based on user follow-up, this can include: merchant avatar + account nickname + merchants you follow (click to enter the showcase); for cards based on user favorited stores, this can include: stores you've favorited (not clickable); for cards based on user favorited items, this can include: items you've favorited (not clickable). For example, the title could be: "Limited-time flash sale in progress." For store information, if geolocation permissions are available and there are multiple stores, if the recommended store is the nearest, the display could be: "Nearest xx km | Store name + xx store general"; if the recommended store is not the nearest, the display could be: "xx km | Store name + xx store general"; if the recommended store is a single store, the display could be: "xx km | Store name" In another case, if the geographic location cannot be obtained, when there are multiple stores, the display can be: "Store Information + Common to XX Stores"; when there is only a single store, the display can be: "Store Name." Store information can also include distance information. If the distance is less than 100 meters (m), the display can be: "Within 100 meters." If the distance is within 1 kilometer, the distance is displayed in meters. If the distance is 1 kilometer or greater, the distance is displayed in kilometers (km). The km can be rounded to one decimal place. For prices, the display can include: "Original Price," "Strike-through Price," "Cost," or "Discount." For service tags, the order can be consistent with the online order. For hot-selling tags, they can be displayed in the same row as service tags. For flash sale countdowns, they have priority over hot-selling tags and can only be displayed if the flash sale end time is less than a preset time (e.g., 24 hours). For click interactions, the display can include: clicking on the image, product area, or "Product Details" button to enter the product details page; clicking on the "Buy Now" button to enter the order page. See Figure 4 for details.

[0100] For multiple cards, using a marketing campaign as an example, the content of a targeted card can include: recommendation reason, title, product, store information, product title, price, service tag, hot sale tag, product image, flash sale countdown, button, and click interaction. For recommendation reasons, for cards based on user attention, this can include: merchant avatar + account nickname + merchants you follow (click to enter the showcase); for cards based on user favorited stores, this can include: stores you've favorited (not clickable); for cards based on user favorited products, this can include: products you've favorited (not clickable). Regarding titles, in one case, if all items are flash sale items, there can be only one title: "Limited-time flash sale in progress"; in another case, if only some items are flash sale items, the flash sale items can be pinned to the top with the title "Limited-time flash sale in progress" and non-flash sale items can be displayed with the title "Other products in the same store recommended." For products, a card can only be issued if multiple products belong to the same store and are all on flash sale. For store information, if geolocation permissions are available and there are multiple stores, if the recommended store is the nearest, the display might be: "Nearest xx km | Store Name + xx Store General." If the recommended store is not the nearest, the display might be: "xx km | Store Name + xx Store General." If there is only a single store, the display might be: "xx km | Store Name." Alternatively, if geolocation permissions are unavailable, if there are multiple stores, the display might be: "Store Information + XX Store General." If there is only a single store, the display might be: "Store Name." Store information can also include distance information. If the distance is less than 100 meters, the display might be: "Within 100 meters." If the distance is within 1 kilometer, the display might be in meters. If the distance is 1 kilometer or more, the display might be in kilometers. km can retain one decimal place. For prices, the display might include: "Original Price," "Strike-through Price," "Cost," or "Discount" (e.g., xx off after flash sale, total savings of yy). Service tags can be displayed in the same order as online. Best Seller tags can be displayed on the same line as service tags. For flash sale countdowns, prioritized over hot sale tags, they can be displayed only when the remaining time for the flash sale is less than a preset duration (e.g., 24 hours). Click interactions can include: clicking the "All Products" button to enter the product showcase, and then clicking "Not Interested" to generate negative feedback. See Figure 5 for details.

[0101] Corresponding to the third possible implementation method mentioned above, the directional card displayed on the media stream page of the client, taking the user as a new user and the directional card as a new user coupon recommendation card as an example, as shown in Figure 6, can include: (1) a background image, which can be configured based on the desired design effect, and can also be called an atmosphere image; (2) coupon information: the title can be, for example: Exclusive for new users | Instant discount of x yuan on orders (x yuan is the face value of the new user coupon), a limited-time offer is used to indicate the countdown for the availability of the coupon (for example, it can be: expires in xx:yy:zz, xx is hours, yy is minutes, zz is seconds), and, a critical state where the card is not issued (for example, within 10 seconds of the deadline). If the coupon expires within 5 minutes, the card will not be issued; or if the new user identity is invalid, the card will not be issued); (3) Title: xx recommendation (xx can be a first-level category), which is displayed after the algorithm determines the category. If there is a mixed arrangement of categories, the title can be unified as: limited-time recommendation; (4) The title of the category is linked to the label of the new user channel. For example, food recommendations are anchored to the nearby food channel, and for example, mixed arrangements are not anchored to any channel; (5) Product card. Since there are two types of products in the new user area, a switch can be designed in the background according to the different coupon usage situations. When the switch is turned on, all products are visible, and when the switch is turned off, only regular products are visible. For all products, the product display logic on independent cards can be as follows: First, the POI in the product card is positioned and inserted, ensuring that the POI of the same product on the targeted card and the POI in the new user zone are consistent. Second, when displaying products in the targeted card, consideration is given to overlaying the display during flash sales (overlaying the flash sale atmosphere image on the product image, and displaying the post-coupon price). Third, if an abnormal situation causes the new user coupon to fail to be issued, the countdown can be omitted, while other information is displayed normally. For exclusive products among all products, the information displayed on the targeted card may include: basic information, marketing information, and a button (BTN). Basic information may include: product image + (store POI + product name) and distance (distribution is restricted to the same city). Marketing information may include: new user price, original price (for example, it may include the struck-through price and / or the regular price); BTN may include: buy now. For regular products, the information may include: ranking and regular product information. Ranking can be understood as the top n recommended products in the new user channel being displayed on independent cards, with products mixed.The information in regular products may include: basic information, marketing information and btn. Basic information may include: product picture + (store POI + product name), usage rules, sales volume, etc.; marketing information may include: new user coupon label + minus x yuan (x yuan is the face value of the new user coupon), price after coupon (can be accurate to two decimal places; if the last two decimal places are 0, it can be not displayed), strike-through price (new user pre-coupon price), and subsidy amount (the difference between original price and new user price); btn may include: get coupon and buy (the function is to guide, whether clicked or not, it will be processed as getting coupon), large card button (universal), not interested (click to close the directional card and enter the next browsing page (such as video)) and more new user goodies (click to enter the new user channel or product details page).

[0102] Corresponding to the third possible implementation described above, the method may further include: in response to a user performing a first action on a target object on a media stream page displaying a recommended media stream, jumping to an object details page corresponding to the target object, wherein the target object is a recommended object. As shown in FIG7 , clicking “Snap Up” on a single item in a targeted card can jump to the item details page for that item, facilitating the user to further learn about and purchase the item. Alternatively, in response to a user performing a second action on a media stream page displaying a recommended media stream, jumping to a channel page corresponding to the target object category, wherein the second action corresponds to the target object, and the target object is displayed at the top of the channel page, or the target object is displayed in a separate unit (also referred to as a separate card) on the channel page, the separate unit being configured to carry a preset number (e.g., 2) of recommended objects on the channel page. As shown in FIG8 , clicking “Snap Up” on a single item in a targeted card can also jump to a new user channel page, where the clicked item can be displayed at the top of the channel page, or the clicked item can be displayed in a separate card, facilitating the user to further learn about and purchase the item.

[0103] In addition, corresponding to the third possible implementation method, the frequency control of a single product in the directional card is connected to the algorithm logic of the existing independent card. For the follow-up page, when clicking on a single product, the jump design can include the following two situations. In one case, jump to the new user channel page, and the designed switch is displayed on the follow-up page. When the switch is turned on, the directional card can display all products, and the new user channel page is displayed normally. When the switch is turned off, the directional card only displays regular products, and the exclusive product area is blocked on the new user channel page (only for independent card channels); for the pull-up method, the clicked product bar enters the new user channel page, and the product bar is displayed in the first place; in the other case, jump to the product details page to facilitate direct transactions. For example, click "More Newcomer Hot Products" to jump to the new user channel page to continue.

[0104] It can be seen that in the embodiment of the present application, considering that some historical interactive behaviors performed by the user in the process of using the client can best reflect the needs of the user, in order to recommend content to the user more accurately on the client, the target object category is first determined based on the historical interactive behaviors; then the recommended media stream corresponding to the target object category is displayed on the media stream page, and the recommended media stream includes the recommended objects corresponding to the target object category, thereby achieving the purpose of recommending content to the user. It can be seen that this method overcomes the current problem of inaccurate content recommendation based on predicting the user's hobbies and tendencies based on user information and recommending content to the user accordingly. By sensing the user's historical interactive behaviors on the client and generating a recommended media stream corresponding to the target object category according to the target object category corresponding to the historical interactive behaviors, since the recommended media stream is generated based on the user's actual historical interactive behaviors, the content carried by the recommended media stream is displayed to the user through the client, so that the user can see the content he wants to browse using the client, thereby improving the user's experience of using the client.

[0105] Accordingly, the embodiment of the present application further provides a content recommendation device 900. As shown in FIG9 , the device 900 may include:

[0106] A determination unit 901 is configured to determine a target object category based on historical interaction behaviors;

[0107] The display unit 902 is configured to display the recommended media stream corresponding to the target object category on a media stream page, where the recommended media stream includes the recommended objects corresponding to the target object category.

[0108] In a possible implementation, the display unit 902 is specifically configured to:

[0109] If it is determined that the historical interaction behavior meets the first condition, then the recommended media stream is displayed on the media stream page, and the first condition includes at least one of the following conditions: the number of times the first type of behavior is performed within the first time period reaches a first number threshold, the number of times the second type of behavior is performed within the second time period reaches a second number threshold, the number of times the second type of behavior is performed within the second time period reaches the second number threshold and the third type of behavior is performed on the result of performing the second type of behavior, wherein the first type of behavior, the second type of behavior and the third type of behavior all belong to historical interaction behaviors corresponding to the object category.

[0110] In another possible implementation, the display unit 902 is specifically configured to:

[0111] If it is determined that a marketing activity related to the historical interaction behavior exists under the target object category, the recommended media stream is displayed on the media stream page, and each of the recommended objects included in the recommended media stream participates in the marketing activity.

[0112] As an example, if the historical interaction behavior is directed at a first-level entity, then the marketing activities related to the historical interaction behavior include the marketing activities of the first-level entity and / or the marketing activities of the second-level entity belonging to the first-level entity; or, if the historical interaction behavior is directed at the second-level entity, then the marketing activities related to the historical interaction behavior include the marketing activities of the second-level entity.

[0113] In a possible implementation, the display unit 902 is further configured to:

[0114] In response to performing a first operation on a target object in the media stream page, an object details page of the target object is displayed, and the target object belongs to the recommended object.

[0115] In another possible implementation, the display unit 902 is further configured to:

[0116] In response to performing a second operation in the media stream page, a channel page corresponding to the target object category is displayed.

[0117] As an example, the second operation corresponds to a target object, and the target object is displayed at the top of the channel page, or the target object is displayed in an independent unit of the channel page, and the independent unit is used to carry a preset number of objects among the recommended objects in the channel page, and the target object belongs to the recommended objects.

[0118] In a possible implementation, the display unit 902 is specifically configured to:

[0119] If it is determined that the target object category meets the second condition, the recommended media stream is displayed on the media stream page, and the second condition includes at least one of the following conditions: an interactive behavior belonging to the target object category is performed within a third time period, which belongs to the time range corresponding to the target object category, and the number of interactive behaviors belonging to the target object category performed within a fourth time period reaches a third number threshold, and the third time period and the fourth time period are both preset durations that are earlier than the display time of the recommended media stream.

[0120] It should be noted that the specific implementation of the device 900 and the technical effects achieved can be found in the relevant description of the method shown in FIG1 .

[0121] It should be noted that in the embodiments of the present application, the above-mentioned “user information”, “historical interactive behavior”, “recommended media stream”, etc. do not involve user sensitive information. The “user information”, “historical interactive behavior” and other information are all obtained and used after user authorization, and are all determined after user authorization. In one example, before obtaining the above-mentioned “historical interactive behavior”, the corresponding interface displays prompt information related to obtaining data use authorization. The prompt information is based on relevant laws and regulations and informs the user of the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure in an appropriate manner, so that the user can determine whether to agree to the authorization based on the prompt information. It can be understood that the above-mentioned notification and the process of obtaining user authorization are only illustrative and do not constitute a limitation on the implementation method of the present disclosure. Other methods that meet relevant laws and regulations can also be applied to the implementation method of the present disclosure.

[0122] In addition, an embodiment of the present application also provides an electronic device, which includes a processor and a memory: the memory is used to store instructions or programs; the processor is used to execute the instructions or programs in the memory, so that the electronic device executes any implementation method of the method provided in the embodiment of the present application.

[0123] Referring to FIG10 , a schematic diagram of the structure of an electronic device 1000 suitable for implementing an embodiment of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in FIG10 is merely an example and should not limit the functionality and scope of use of the embodiments of the present disclosure.

[0124] As shown in FIG10 , the electronic device 1000 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 into a random access memory (RAM) 1003. Various programs and data required for the operation of the electronic device 1000 are also stored in the RAM 1003. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0125] Typically, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device 1000 to communicate with other devices wirelessly or by wire to exchange data. Although FIG. 10 illustrates the electronic device 1000 with various devices, it should be understood that not all of the devices shown are required to be implemented or present. More or fewer devices may alternatively be implemented or present.

[0126] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0127] The electronic device provided by the embodiment of the present disclosure and the method provided by the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0128] An embodiment of the present application further provides a computer-readable medium, in which instructions or computer programs are stored. When the instructions or computer programs are executed on a device, the device executes any implementation of the method provided in the embodiment of the present application.

[0129] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0130] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0131] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0132] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device can perform the method.

[0133] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0134] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods, devices and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0135] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit / module does not, in some cases, limit the unit itself.

[0136] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0137] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0138] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems or devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0139] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0140] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0141] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0142] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A content recommendation method, the method comprising: Determine the target object category based on historical interaction behaviors; The recommended media stream corresponding to the target object category is displayed on the media stream page, and the recommended media stream includes the recommended object corresponding to the target object category.

2. The method according to claim 1, wherein displaying the recommended media stream corresponding to the target object category on the media stream page comprises: If it is determined that the historical interaction behavior satisfies a first condition, then the recommended media stream is displayed on the media stream page, and the first condition includes at least one of the following conditions: the number of times the first type of behavior is performed within a first time period reaches a first number threshold, the number of times the second type of behavior is performed within a second time period reaches a second number threshold, the number of times the second type of behavior is performed within the second time period reaches a second number threshold and a third type of behavior is performed on the result of executing the second type of behavior, wherein the first type of behavior, the second type of behavior and the third type of behavior all belong to historical interaction behaviors corresponding to the object category.

3. The method according to claim 1, wherein displaying the recommended media stream corresponding to the target object category on the media stream page comprises: If it is determined that there is a marketing activity related to the historical interaction behavior under the target object category, the recommended media stream is displayed on the media stream page, and each of the recommended objects included in the recommended media stream participates in the marketing activity.

4. The method according to claim 3, wherein: The historical interaction behavior is directed to a first-level entity, and the marketing activities related to the historical interaction behavior include the marketing activities of the first-level entity and / or the marketing activities of a second-level entity belonging to the first-level entity; Alternatively, the historical interaction behavior is directed to the second-level entity, and the marketing activities related to the historical interaction behavior include the marketing activities of the second-level entity.

5. The method according to claim 1, further comprising: In response to performing a first operation on a target object in the media stream page, an object details page of the target object is displayed, and the target object belongs to the recommended object.

6. The method according to claim 1, further comprising: In response to performing a second operation in the media stream page, a channel page corresponding to the target object category is displayed.

7. According to the method described in claim 6, the second operation corresponds to a target object, and the target object is displayed at the top of the channel page, or the target object is displayed in an independent unit of the channel page, and the independent unit is used to carry a preset number of objects in the recommended number in the channel page, and the target object belongs to the recommended objects.

8. The method according to any one of claims 1 to 7, wherein displaying the recommended media stream corresponding to the target object category on the media stream page comprises: If it is determined that the target object category satisfies the second condition, the recommended media stream is displayed on the media stream page, and the second condition includes at least one of the following conditions: an interactive behavior belonging to the target object category is performed within a third time period, and the time range corresponds to the target object category; the number of interactive behaviors belonging to the target object category performed within a fourth time period reaches a third number threshold; and the third time period and the fourth time period are both earlier than the time period displayed. The preset duration of the recommended media stream display moment.

9. A content recommendation device, comprising: A determination unit, used to determine the target object category based on historical interaction behaviors; The display unit is used to display the recommended media stream corresponding to the target object category on the media stream page, wherein the recommended media stream includes the recommended object corresponding to the target object category.

10. An electronic device, comprising: Processor and memory; The memory is used to store instructions or programs; The processor is used to execute the instructions or programs in the memory so that the electronic device executes the method according to any one of claims 1 to 8.

11. A readable medium storing instructions or programs, which, when executed on a processor, enable the processor to execute the method according to any one of claims 1 to 8.

12. A computer program product comprising instructions, which when executed by a processor implement the method of any one of claims 1 to 8.

Images