Recommendation information distribution method and device, program product and electronic equipment

Abstract

The invention provides a recommendation information distribution method and device, a program product and electronic equipment, and relates to the technical field of computers. The method comprises the following steps: receiving a recommendation information distribution request, and determining a target recommendation scene carried in the recommendation information distribution request; pulling a distribution rule belonging to the target recommendation scene; wherein each distribution rule comprises a distribution type, recommendation content and a recommendation plate in the target recommendation scene; and based on the distribution type, distributing the recommendation content to the recommendation plate. According to the method, the processing process of the target recommendation scene is isolated from the recommendation module, namely, the service system for processing the service customization demand is independent from the recommendation system, so that the reconstruction and maintenance cost of the recommendation system is reduced on the basis of realizing personalized information distribution.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a recommendation information distribution method, device, program product and electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims, and no description herein is admitted to be prior art by inclusion in this section.

[0003] At present, in the related art, when distributing recommendation information, personalized recommendation information is generally distributed to users based on the historical behavior data of the users.

[0004] In order to better distribute personalized recommendation information to users, it is generally necessary to combine multiple business customization requirements such as cold start exploration of new content, accelerated distribution of real-time hot content, and commercial realization. However, in the related technology, when meeting the personalized recommendation information distribution needs of users, the business customization needs of users are generally coupled to the existing recommendation system business code. This method leads to the rapid expansion of the recommendation system logic. If new business customization needs are encountered, the recommendation system logic needs to be rebuilt. Summary of the invention

[0005] The present disclosure provides a recommendation information distribution method, a recommendation information distribution device, a computer program product and an electronic device, so as to at least to some extent solve the problem of achieving personalized information distribution without the need to reconstruct and transform the existing recommendation system.

[0006] According to a first aspect of the present disclosure, a method for distributing recommendation information is provided, the method comprising:

[0007] receiving a recommendation information distribution request, and determining a target recommendation scenario carried in the recommendation information distribution request;

[0008] Pulling distribution rules belonging to the target recommendation scenario; wherein each of the distribution rules includes a distribution type, recommended content, and a recommended section under the target recommendation scenario;

[0009] Based on the distribution type, the recommended content is distributed to the recommendation section.

[0010] In one implementation, the pulling of distribution rules belonging to the target recommendation scenario includes:

[0011] Determine a pre-configured first distribution rule and a second distribution rule that is constructed on a regular basis; wherein the first distribution rule and the second distribution rule include a recommendation scenario, a distribution type, a recommended content, and a recommended section under the recommendation scenario;

[0012] Aggregating target distribution rules belonging to the same recommendation scenario in the first distribution rule and the second distribution rule to obtain an aggregate rule;

[0013] Pull the summary rules belonging to the target recommendation scenario.

[0014] In one implementation, the first distribution rule is preconfigured according to preset rule attributes.

[0015] In one implementation, the second distribution rule also includes a recommendation weight; the recommendation weight is configured based on the ranking of the current recommendation information of the recommended content in the recommendation section.

[0016] In one embodiment, the distribution type includes a specific intervention type;

[0017] The distributing the recommended content to the recommendation section based on the distribution type includes:

[0018] If the distribution type included in the distribution rule is the specific intervention type, determining a specific distribution location included in the distribution rule;

[0019] The recommended content is distributed to the specific distribution location of the recommendation section.

[0020] In one embodiment, the distribution type is a non-intervention type; the non-intervention type includes a recall type;

[0021] The distributing the recommended content to the recommendation section based on the distribution type includes:

[0022] If the distribution type included in the distribution rule is the recall type, determining current recommendation information belonging to the recommendation section;

[0023] The recommended content is inserted into the current recommendation information.

[0024] In one embodiment, the distribution type is a non-intervention type; the non-intervention type includes a sorting type;

[0025] The distributing the recommended content to the recommendation section based on the distribution type includes:

[0026] If the distribution type included in the distribution rule is the sorting type, determining the recommendation weight included in the distribution rule, and determining the current recommendation sorting of the recommended content in the recommendation section;

[0027] The recommendation ranking of the recommended content in the recommendation section is adjusted based on the recommendation weight and the current recommendation ranking.

[0028] In one embodiment, the distribution type is a non-intervention type; the non-intervention type includes a filtering type;

[0029] The distributing the recommended content to the recommendation section based on the distribution type includes:

[0030] If the distribution type included in the distribution rule is the filtering type, the recommended content included in the current recommendation information belonging to the recommendation section is deleted.

[0031] In one embodiment, the method further comprises:

[0032] The erroneous recommendation information is determined, and the erroneous distribution rule belonging to the erroneous recommendation information in the first distribution rule or the second distribution rule is deleted.

[0033] According to a second aspect of the present disclosure, a recommendation information distribution device is provided, the device comprising:

[0034] A request module, configured to receive a recommendation information distribution request and determine a target recommendation scenario carried in the recommendation information distribution request;

[0035] A rule extraction module, used to extract distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes a distribution type, recommended content, and a recommended section under the target recommendation scenario;

[0036] A distribution module is used to distribute the recommended content to the recommendation section based on the distribution type.

[0037] In one embodiment, the rule pulling module is used to:

[0038] Determine a pre-configured first distribution rule and a second distribution rule that is constructed on a regular basis; wherein the first distribution rule and the second distribution rule include a recommendation scenario, a distribution type, a recommended content, and a recommended section under the recommendation scenario;

[0039] Aggregating target distribution rules belonging to the same recommendation scenario in the first distribution rule and the second distribution rule to obtain an aggregate rule;

[0040] Pull the summary rules belonging to the target recommendation scenario.

[0041] In one implementation, the first distribution rule is preconfigured according to preset rule attributes.

[0042] In one implementation, the second distribution rule also includes a recommendation weight; the recommendation weight is configured based on the ranking of the current recommendation information of the recommended content in the recommendation section.

[0043] In one embodiment, the distribution type includes a specific intervention type; and the distribution module is configured to:

[0044] If the distribution type included in the distribution rule is the specific intervention type, determining a specific distribution location included in the distribution rule;

[0045] The recommended content is distributed to the specific distribution location of the recommendation section.

[0046] In one embodiment, the distribution type is a non-intervention type; the non-intervention type includes a recall type; and the distribution module is used to:

[0047] If the distribution type included in the distribution rule is the recall type, determining current recommendation information belonging to the recommendation section;

[0048] The recommended content is inserted into the current recommendation information.

[0049] In one implementation, the distribution type is a non-intervention type; the non-intervention type includes a sorting type; the distribution module is used to:

[0050] If the distribution type included in the distribution rule is the sorting type, determining the recommendation weight included in the distribution rule, and determining the current recommendation sorting of the recommended content in the recommendation section;

[0051] The recommendation ranking of the recommended content in the recommendation section is adjusted based on the recommendation weight and the current recommendation ranking.

[0052] In one implementation, the distribution type is a non-intervention type; the non-intervention type includes a filtering type; the distribution module is used to:

[0053] If the distribution type included in the distribution rule is the filtering type, the recommended content included in the current recommendation information belonging to the recommendation section is deleted.

[0054] In one embodiment, the device further includes a rule updating module, configured to:

[0055] The erroneous recommendation information is determined, and the erroneous distribution rule belonging to the erroneous recommendation information in the first distribution rule or the second distribution rule is deleted.

[0056] According to a third aspect of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method of the first aspect and possible implementation methods thereof are implemented.

[0057] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method of the above-mentioned first aspect and its possible implementation methods by executing the executable instructions.

[0058] The technical solution disclosed in this disclosure has the following beneficial effects:

[0059] In an embodiment of the present disclosure, a recommendation information distribution request can be received, and a target recommendation scenario carried in the recommendation information distribution request can be determined; distribution rules belonging to the target recommendation scenario can be pulled; wherein each distribution rule includes a distribution type, recommended content, and a recommendation section under the target recommendation scenario; based on the distribution type, the recommended content is distributed to the recommendation section. Specifically, when a recommendation information distribution request is determined, that is, a new business customization requirement, the distribution rules for the recommended content can be directly determined based on the target recommendation scenario carried in the request, so that the recommended content is distributed to the recommendation section according to the distribution type in the distribution rule, without occasionally incorporating the business customization requirement into the business logic, that is, without reconstructing, modifying, and updating the existing promotion system, thereby reducing the maintenance cost of the system. In other words, the present disclosure isolates the processing process of the target recommendation scenario from the recommendation module, that is, the business system that handles the business customization requirement is independent of the recommendation system, thereby realizing personalized information distribution and reducing the reconstruction and maintenance cost of the recommendation system.

[0060] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by practicing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A schematic diagram of an application scenario in this exemplary embodiment is shown;

[0063] Figure 2 A system architecture diagram in this exemplary embodiment is shown;

[0064] Figure 3 A flowchart showing a method for distributing recommendation information in this exemplary embodiment is shown;

[0065] Figure 4 A schematic diagram showing a method of determining a preset rule attribute in this exemplary embodiment is shown;

[0066] Figure 5 A schematic diagram showing a method of storing a second distribution rule in this exemplary embodiment is shown;

[0067] Figure 6 A schematic diagram showing a request return protocol for regulating engine PID in this exemplary embodiment;

[0068] Figure 7 A schematic diagram showing the structure of a recommendation information distribution device in this exemplary embodiment is shown;

[0069] Figure 8 A schematic structural diagram of an electronic device in this exemplary embodiment is shown. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure. In the absence of conflict, the embodiments in the present disclosure and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0071] The term "comprising" and any variations thereof in the specification and claims of the present disclosure are intended to cover non-exclusive protection. For example, a process, method, system, product or device comprising 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.

[0072] In the embodiments of the present disclosure, one or more, "many" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, 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" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or plural.

[0073] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order, sequence, size, and priority. For example, the first distribution rule and the second distribution rule in the embodiment of the present disclosure are only used to distinguish different distribution rules. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0074] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, which are schematic diagrams of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the accompanying drawings may be functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in hardware modules or integrated circuits, or in networks, processors or microcontrollers. The implementation method can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein. The features, structures or characteristics described in the present disclosure may be combined in one or more implementations in any suitable manner. In the following description, many specific details are provided to provide a full description of the implementation methods of the present disclosure. However, those skilled in the art should be aware that one or more specific details may be omitted when implementing the technical solution of the present disclosure, or one or more specific details may be replaced by other methods, components, devices, steps, etc. It should be noted that in the embodiments of the present disclosure, the collection, dissemination, and use of data (such as songs and videos) are in compliance with relevant national laws and regulations. SUMMARY OF THE INVENTION

[0076] In the related technologies, the mainstream music traffic distribution system in the industry performs personalized recommendation distribution based on the user's historical behavior. However, in order to cope with business customization requirements such as cold-start exploration of new content, accelerated distribution of real-time hot content, and commercial monetization needs, a mechanism that can adjust the recommendation traffic distribution strategy in real time is urgently needed.

[0077] However, the current mainstream general deployment capability in the industry is to build an intervention and operation platform, that is, to enhance content distribution and mandatory filtering for specific users, specific groups, and all users. Although the aforementioned method can solve some specific business demands, it cannot meet the needs of general real-time traffic distribution strategy adjustment, and couples the processing of business customization requirements to the business code, resulting in poor scalability and maintainability of the original recommendation system corresponding to the business code.

[0078] In view of one or more of the above problems, an exemplary embodiment of the present disclosure provides a method for distributing recommendation information, which can receive a recommendation information distribution request, determine the target recommendation scenario carried in the recommendation information distribution request; pull the distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes a distribution type, recommended content, and a recommendation section under the target recommendation scenario; based on the distribution type, the recommended content is distributed to the recommendation section. Specifically, when the recommendation information distribution request is determined, that is, a new business customization requirement, the distribution rules for the recommended content can be directly determined based on the target recommendation scenario carried in the request, so that the recommended content is distributed to the recommendation section according to the distribution type in the distribution rule, without occasionally incorporating the business customization requirement into the business logic, that is, without reconstructing, transforming and updating the existing promotion system, thereby reducing the maintenance cost of the system. In other words, the present disclosure isolates the processing process of the target recommendation scenario from the recommendation module, that is, the business system for processing the business customization requirement is independent of the recommendation system, thereby realizing personalized information distribution and reducing the reconstruction and maintenance cost of the recommendation system.

[0079] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0080] Application Scenario Overview

[0081] In order to better understand the technical solutions provided by the embodiments of the present disclosure, the following briefly introduces the application scenarios to which the technical solutions provided by the embodiments of the present disclosure are applicable. It should be noted that the application scenarios introduced below are only used to illustrate the embodiments of the present disclosure and are not intended to limit the present disclosure. In specific implementation, the technical solutions provided by the embodiments of the present disclosure can be flexibly applied according to actual needs.

[0082] In order to more clearly introduce the contents of the embodiments of the present disclosure, some key terms are introduced below:

[0083] Cold start: Cold start can be understood as the situation where a new product faces certain difficulties in the initial promotion and sales process due to lack of traffic and data accumulation when it is first released on a preset platform. For example, if the new product is a song, then cold start can be understood as the situation where a new product faces certain difficulties in the initial promotion and sales process due to lack of traffic and data accumulation when it is first released on a preset platform.

[0084] Traffic distribution: In a broad sense, it can be understood as displaying specific content to users. The specific content is, for example, video content, music content, film and television content, etc. In the disclosed embodiment, it can be understood as the process of using a recommendation system to recommend personalized specific content to users. For example, if the specific content is music content, traffic distribution can be understood as displaying music content to users. In other words, song 1 is recommended to user 1, user 2, ..., user n, where n is a positive integer. For example, when the cold start of a new product is a business customization requirement, traffic distribution can be performed on the new song to effectively promote the new song.

[0085] Intervention rule execution process: In a broad sense, it can be understood as an intervention process outside the rules for various functional systems with preset rules, such as recommendation systems, etc. Optionally, when the promotion system is recommending content, it can support intervention functions such as forcing different content for different groups and forcing different distribution restrictions for different groups. For example, forcing content for different groups, blacklisting content for different groups, etc.

[0086] Main recommendation rule execution process: It can be understood as a personalized recommendation process common to all businesses. This process generally includes three sub-processes: recall, fine sorting, and mixed sorting. Of course, a coarse sorting sub-process can also be added between recall and fine sorting.

[0087] In the embodiments of the present disclosure, the recommendation information distribution technology can be applied to business scenarios where various software needs to distribute information, such as audio, video, audio and video, images, etc. For example, software that provides music as video background music (Background Music, BGM) needs to distribute music, or software that provides music playback function needs to distribute music. This is not limited in the embodiments of the present disclosure.

[0088] See also Figure 1 As shown, Figure 1 This is an application scenario to which the technical solution of the embodiment of the present disclosure can be applied. In the scenario diagram, multiple distribution devices 101, electronic devices 102 and distributed devices 103 are included. Among them, the distribution device 101 and the distributed device 103 can be multiple devices. Figure 1Only one is shown in the figure, that is, one piece of information can be distributed to multiple distributed devices 103, and the electronic device 102 can execute the distribution requirements of multiple distribution devices.

[0089] It should be noted that in the disclosed embodiment, the functions of the distributed device 103 and the distributing device 101 may change as the corresponding user identities change. For example, in the first time period, user 1 has a need to distribute information, then the device corresponding to user 1, or the device associated with it (for example, the device used by user 1's work partner or team members) can be called the distributing device 101. In the second time period, user 1 is distributed information distributed by user 2, then the device corresponding to user 1 or the device associated with it can be called the distributed device 103.

[0090] The distribution device 101 , the electronic device 102 and the distributed device 103 may be directly or indirectly connected to each other through one or more networks 104 .

[0091] In the embodiment of the present disclosure, the user to whom information is to be distributed, for the sake of ease of description, may also be referred to as a distribution user, can perform corresponding operations on the information platform corresponding to the distribution device 101, such as selection operations, input operations, or drag operations, and then the distribution device 101 can determine the recommendation information distribution request, and send the recommendation information distribution request to the electronic device 102, and the electronic device 102 can receive the recommendation information distribution request, determine the target recommendation scenario carried in the recommendation information distribution request; pull the distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes a distribution type, recommended content, and a recommendation section under the target recommendation scenario; based on the distribution type, the recommended content is distributed to the recommendation section, so that the electronic device 102 can send the recommended content finally determined by the recommendation section to the distributed device 103, so as to display it to the distributed user corresponding to the distributed device, that is, the user who receives the distribution information.

[0092] in, Figure 1 The distribution devices 101 and distributed devices 103 may be mobile phones, tablet computers (PADs), personal computers (PCs), smart TVs, smart watches, smart speakers, smart car devices, wearable devices, etc., but are not limited to these. These devices may have functions of supporting information distribution and information display, for example, these devices support functions such as playing, collecting, liking, commenting, and forwarding songs.

[0093] as well as, Figure 1The electronic device 102 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It may also be a cloud server or a cloud server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, but is not limited to these.

[0094] Of course, the method provided in the embodiment of the present disclosure is not limited to Figure 1 The application scenarios shown may also be used in other possible application scenarios, such as application scenarios where only electronic devices implement the recommendation information distribution method, which is not limited by the embodiments of the present disclosure.

[0095] See also Figure 2 As shown, Figure 2 The system architecture diagram of the operating environment of this exemplary embodiment is shown. The system architecture may include a distribution device 201, a server 202, and a distributed device 203. The distribution device 201 includes a sending unit 2011 for sending information and a receiving unit 2012 for receiving information. The server 202 includes a service customization unit 2021 and a recommendation unit 2022. The distributed device 203 includes a sending unit 2031 for sending information and a receiving unit 2032 for receiving information.

[0096] In the disclosed embodiment, the business customization unit 2021 includes a request module, a rule pulling module and a distribution module. The request module is used to receive the recommendation information distribution request sent by the sending unit 2011 of the distribution device 201, and determine the target recommendation scenario carried in the recommendation information distribution request; the rule pulling module is used to pull the distribution rules belonging to the target recommendation scenario; each distribution rule includes the distribution type, recommended content and the recommendation section under the target recommendation scenario; the distribution module is used to distribute the recommended content to the recommendation section based on the distribution type. The recommendation unit 2022 is used to send the recommended content determined by the recommendation section to the distributed device 203.

[0097] It can be seen that in the embodiment of the present disclosure, the server 202 decouples the business customization unit 2021 and the recommendation unit 2022 for realizing business customization needs, thereby executing various dynamic regulation needs when distributing information based on the business customization unit 2021, without affecting the conventional recommendation system, thereby avoiding the reconstruction of the conventional recommendation system, and on the basis of meeting the personalized needs of information distribution, it also enhances the maintainability and scalability of the information distribution system including the business customization unit 2021 and the recommendation unit 2022 deployed corresponding to the entire server.

[0098] Exemplary Methods

[0099] To further illustrate the technical solution provided by the embodiments of the present disclosure, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of the present disclosure provide method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiments of the present disclosure. The method may be executed in the order of the method shown in the embodiments or drawings or in parallel during the actual processing process or when the device is executed.

[0100] See also Figure 3 , Figure 3 FIG. 1 is a flow chart of a method for distributing recommendation information in an embodiment of the present disclosure. The method flow can be executed by an electronic device, for example, and the electronic device can be Figure 1 The electronic device 102 or Figure 2 The specific implementation process of the method is as follows:

[0101] Step 301: receiving a recommendation information distribution request, and determining a target recommendation scenario carried in the recommendation information distribution request.

[0102] In an embodiment of the present disclosure, the electronic device may receive a recommendation information distribution request sent by a distribution device, and determine a target recommendation scenario carried in the recommendation information distribution request.

[0103] In the disclosed embodiment, when the holder or associated person of the distribution device wishes to distribute a certain piece of information, a recommendation information distribution request can be triggered based on the distribution device. For example, when user A, the holder of terminal device 1, wishes to distribute song 1 by traffic, user A can perform corresponding operations based on the traffic distribution corresponding to terminal device 1, i.e., on the platform for recommending song 1, thereby triggering a recommendation information distribution request.

[0104] In the disclosed embodiment, the electronic device can parse the recommendation information distribution request to obtain the target recommendation scene carried in the recommendation information distribution request. Optionally, the target recommendation scene is, for example, song discovery, hot recommendation, language recommendation, style (music genre) recommendation, specific scene, emotion recommendation, theme recommendation, etc. Among them, the specific scene is, for example, early morning, lunch break, night, study, travel, walk, shopping mall, etc., which is not limited in the disclosed embodiment.

[0105] Step 302: Pull distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes a distribution type, recommended content, and a recommendation section under the target recommendation scenario.

[0106] In the disclosed embodiment, the electronic device may extract the distribution rules belonging to the target recommendation scenario by adopting but not limited to the following steps:

[0107] Step A: Determine a pre-configured first distribution rule and a timed second distribution rule; wherein the first distribution rule and the second distribution rule include a recommendation scenario, a distribution type, a recommended content, and a recommended section under the recommendation scenario.

[0108] In an embodiment of the present disclosure, the electronic device may first determine a pre-configured first distribution rule. In other words, the electronic device may determine the first distribution rule stored in a local database, or the first distribution rule stored in an external database associated with the local database, or may determine all first distribution rules stored in the local database and the external database. This is not limited in the embodiment of the present disclosure.

[0109] In the embodiment of the present disclosure, the first distribution rules stored in the local database or the external database are all pre-configured according to preset rule attributes. In other words, the first distribution rules stored in the local database and the external database are all pre-created.

[0110] In an optional implementation, the preset rule attributes include at least one of a scene (source), a channel (channel), a weighting action (action), a weighting parameter (action_val), a weighting content list (resouce_list), a weighting start time (begin_tm), and a weighting end time (end_tm).

[0111] For example, please refer to Table 1, which is a schematic table of a first distribution rule in an embodiment of the present disclosure.

[0112]

[0113] Table 1

[0114] In the embodiment of the present disclosure, the preset rule attributes may be pre-configured by the user based on the corresponding device, for example, the specific contents of "scene (source), channel (channel), weight adjustment action (action), weight adjustment parameter (action_val), weight adjustment content list (resouce_list), weight adjustment start time (begin_tm) and weight adjustment end time (end_tm)" may be determined directly on the platform displayed on the device based on at least one of input operation, selection operation, click operation, drag operation and sliding operation. _val), weight adjustment content list (resouce_list), weight adjustment start time (begin_tm) and weight adjustment end time (end_tm)". Other contents that are not manually set can be directly determined based on the preset fixed information. Of course, the specific contents of "scene (source), channel (channel), weight adjustment action (action), weight adjustment parameter (action_val), weight adjustment content list (resouce_list), weight adjustment start time (begin_tm) and weight adjustment end time (end_tm)" are all determined by the preset fixed information, which is not limited in the embodiments of the present disclosure.

[0115] For example, see Figure 4 , Figure 4 A schematic diagram of determining the attributes of a preset rule in an embodiment of the present disclosure. In an embodiment of the present disclosure, a user can click on the functional area corresponding to the "rights adjustment start time" in the platform, and then a floating input box will appear on the current page, so that the user can enter the corresponding information, such as Figure 4 "2024 / 6 / 3" shown in .

[0116] In the disclosed embodiment, after the electronic device obtains the preset rule attribute, it can automatically generate the corresponding first distribution rule according to the structure shown in Table 1, thereby completing the creation of the first distribution rule, and storing the created first distribution rule in the database.

[0117] In an embodiment of the present disclosure, the electronic device may determine a second distribution rule from a local database and / or an external database. The local database and / or the external database is, for example, a MySQL library. Optionally, the second distribution rule constructed periodically includes a recommendation scenario, a distribution type, a recommended content, and a recommended section under the recommendation scenario. Optionally, the second distribution rule constructed periodically includes a recommendation scenario, a distribution type, a recommended content, a recommended section under the recommendation scenario, and a recommendation weight; wherein the recommendation weight is configured based on the ranking of the recommended content in the current recommended information in the recommendation section.

[0118] In the disclosed embodiment, the second distribution rule determined by the electronic device is also pre-created. A method for creating the second distribution rule is described below. In one implementation, the electronic device can distribute the posterior data of songs according to various recommendation channels of each recommendation scene, generate multiple dynamic rules after segmentation according to experience, and use each of the multiple dynamic rules as a second distribution rule.

[0119] In other words, the second distribution rule is determined based on the distribution of songs in a preset time period before the current moment. For example, if the posterior data of songs 111 and 222 in the hot_recall channel of the daily_song scene rank top 20% in the posterior data of all distributed songs, a second distribution rule is generated, that is, in the hot_recall channel of the daily_song scene within the current 2 hours, for songs 111 and 222, a rank_boost weight adjustment of 1.5 is performed.

[0120] In the embodiment of the present disclosure, considering that the second distribution rule constructed in real time is stored in the MySQL library, there may be a situation where the universality and scalability of external queries are poor. In order to improve the universality and scalability of external queries of the second distribution rule stored in the MySQL library, the dynamic allocator proportional integral differential control (Proportion Integration Differentiation, PID) can be used to provide rule query services to the outside. Optionally, when the dynamic allocator PID provides a unified rule query and retrieval capability based on the second distribution rule stored in the MySQL library, in order to improve the overall query performance, a layer of memory caching and structural conversion can be performed within the PID, thereby achieving a balance between performance and timeliness. Optionally, the specific structure of the second distribution rule stored in the dynamic allocator PID is as follows: Figure 5 shown.

[0121] In the disclosed embodiments, various recommendation channels can be understood as channels corresponding to the recommendation-related behaviors performed by users, such as collection channels, hot channels, forwarding channels, sharing channels, and sharing channels. Among them, hot channels can also include hot channels for selection lists, hot channels for favorite singers, or hot channels for favorite albums, and sharing channels can also include sharing channels for feature codes corresponding to songs (such as bar codes, QR codes, or special codes composed of text and symbols, etc.), sharing channels for links corresponding to songs, or sharing channels for playback interfaces corresponding to songs, etc.

[0122] Step B: Aggregate the target distribution rules belonging to the same recommendation scenario in the first distribution rule and the second distribution rule to obtain an aggregate rule;

[0123] In the embodiment of the present disclosure, after the electronic device obtains a pre-configured first distribution rule and a timed constructed second distribution rule, it can filter out target distribution rules belonging to the same recommendation scenario from the pre-configured first distribution rule and the timed constructed second distribution rule, and then aggregate the target distribution rules to obtain an aggregate rule.

[0124] For example, the first distribution rule determined by the electronic device includes the first distribution rule 1, the first distribution rule 2, and the first distribution rule 3, and the first distribution rule 1 includes the recommended scenario M, the first distribution rule 2 includes the recommended scenario P, and the first distribution rule 3 includes the recommended scenario W; the second distribution rule determined by the electronic device includes the second distribution rule 1, the second distribution rule 2, and the second distribution rule 3, and the second distribution rule 1 includes the recommended scenario P, the second distribution rule 2 includes the recommended scenario W, and the second distribution rule 3 includes the recommended scenario N; then, the electronic device can determine the first distribution rule 2 and the second distribution rule 1, as well as the first distribution rule 3 and the second distribution rule 2 belonging to the same recommended scenario, thereby taking the first distribution rule 2 and the second distribution rule 1 as the target distribution rule 1, and taking the first distribution rule 3 and the second distribution rule 2 as the target distribution rule 2, and then aggregating the target distribution rule 1 and the target distribution rule 2 to obtain an aggregate rule.

[0125] Step C: Pull the summary rules belonging to the target recommendation scenario.

[0126] In the disclosed embodiment, after the electronic device obtains the summary rule, it can pull the summary rule belonging to the target recommendation scenario. For example, taking the previous summary rule including target distribution rule 1 and target distribution rule 2 as an example, the target recommendation is often W, then the summary rule belonging to the target recommendation scenario is determined to be target distribution rule 2.

[0127] That is to say, in the embodiment of the present disclosure, the final summary rules may be: forced insertion processing of songs in the scene collection channel, recall + sorting processing of the song list of the scene hot spot channel, downgrading of songs in the scene collection channel song list, filtering processing of the scene hot spot channel song list, etc.

[0128] It can be seen that in the embodiment of the present disclosure, the electronic device can quickly obtain a summary rule that includes a pre-configured first distribution rule and a timed second distribution rule, and belongs to a target recommendation scenario, so that the recommended content, i.e., the information to be distributed, can be efficiently distributed, thereby improving the user experience corresponding to the information to be distributed.

[0129] Step 303: Based on the distribution type, the recommended content is distributed to the recommendation section.

[0130] In the disclosed embodiment, after the electronic device determines the summary rules for distributing traffic to the recommended content, it is also necessary to better distribute the recommended content to the recommendation section according to the distribution method of the recommended content, that is, the distribution type.

[0131] In the embodiment of the present disclosure, when the electronic device executes step 303, it can be executed in two parts, for example, divided into main recommendation rule execution and upper-layer rule intervention execution.

[0132] In one embodiment, if the distribution type includes a specific intervention type, it is determined to be executed by the upper-level rule intervention, and the specific implementation process of step 303 is: if the distribution type included in the distribution rule is a specific intervention type, determine the specific distribution location included in the distribution rule; distribute the recommended content to the specific distribution location of the recommendation section.

[0133] In the embodiment of the present disclosure, if it is determined that the distribution type included in the distribution rule is a specific intervention type, the business scenario recommendation layer requests the dynamic allocation engine PID to pull the action=interve of the corresponding scenario and meet the rules of the effective time. The overall general request return protocol structure is as follows: Figure 6 shown.

[0134] In the disclosed embodiment, after obtaining the rule, the electronic device can perform forced insertion of the main recommendation process result delivery list for resouce_list and the corresponding action_val (paired with resouce_list).

[0135] For example, source = daily_song, channel = xx, action = interve, action_val = 1, 2, 4, resource_list = 111, 222, 333, then the upper-level rule intervention is to insert song 111, song 222, and song 333 into the positions 1, 2, and 4 of the sent result for the daily_song scene, respectively. 1, 2, and 4 represent the position identifiers corresponding to different positions in the channel, respectively.

[0136] In one implementation, if the distribution type is a non-intervention type, it is determined that the main recommendation rule is executed. If it is determined that the distribution type included in the distribution rule is a non-specific intervention type, the business scenario recommendation layer requests the dynamic allocation engine PID to pull the action of the corresponding scenario! =interve and meet the rules of the effective time. The overall general request return protocol structure is as follows Figure 6 shown.

[0137] In one embodiment, if the distribution type is a non-intervention type, and the non-intervention type includes a recall type, the specific implementation process of step 303 is: if the distribution type included in the distribution rule is a recall type, determine the current recommendation information belonging to the recommendation section; insert the recommended content into the current recommendation information.

[0138] Optionally, if the recommended content is a song, and the non-intervention type is a recall type, that is, the action = recall_boost type distribution rule, then for the result of the recall path being equal to the channel, that is, the current recommended information, the song content in resouce_list is forcibly inserted to obtain the final recommended information, and the recommended information is distributed to each distributed user.

[0139] In one embodiment, if the distribution type is a non-intervention type; and the non-intervention type includes a sorting type; then the specific implementation process of step 303 is: if the distribution type included in the distribution rule is a sorting type, determine the recommendation weight included in the distribution rule, and determine the current recommendation sorting of the recommended content in the recommendation section; adjust the recommendation sorting of the recommended content in the recommendation section based on the recommendation weight and the current recommendation sorting.

[0140] Optionally, if the recommended content is a song, and the non-intervention type is a ranking type, that is, a distribution rule of action = rank_boost type, then the songs in the resource_list after the fine ranking and scoring are completed can be sorted.

[0141] rank_score = rank_score * action_val, and sort the results based on the overall adjustment to obtain the final recommendation information, and distribute the recommendation information to each distributed user.

[0142] For example, source = daily_song, channel = hot_recall, action = rank_boost, action_val = 1.5, resouce_list = 111, 222, 333. In the main recommendation process of daily_song, the rank_scores of songs 111, 222 and 333 will be multiplied by 1.5 in the final sorted song list to become the new rank_score for queue re-arrangement.

[0143] In one implementation, if the distribution type is a non-intervention type, and the non-intervention type includes a filtering type, then the specific implementation process of step 303 is as follows: if the distribution type included in the distribution rule is a filtering type, the recommended content included in the current recommendation information belonging to the recommendation section is deleted.

[0144] For example, if the recommended content is a song, and the non-intervention type is a filtering type, that is, a distribution rule of action=filter type, then the main recommendation result is filtered to hit resouce_list.

[0145] In one implementation, the erroneous recommendation information is determined, and the erroneous distribution rule belonging to the erroneous recommendation information in the first distribution rule or the second distribution rule is deleted.

[0146] It can be seen that in the embodiments of the present disclosure, some manually configured rules and timed dynamic rules may cause erroneous recommendation information that does not meet expectations online (for example, called badcase). The erroneous distribution rules that generate erroneous recommendation information can be deleted, that is, the erroneous distribution rules can be urgently taken offline to avoid the occurrence of incorrect recommendation content and improve the user experience.

[0147] Exemplary Devices

[0148] The exemplary embodiment of the present disclosure also provides a recommendation information distribution device. Figure 7 As shown, the recommendation information distribution device 700 includes the following program modules:

[0149] The request module 701 is used to receive a recommendation information distribution request and determine a target recommendation scenario carried in the recommendation information distribution request;

[0150] A rule extraction module 702 is used to extract distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes a distribution type, recommended content, and a recommended section under the target recommendation scenario;

[0151] The distribution module 703 is used to distribute the recommended content to the recommendation section based on the distribution type.

[0152] In one implementation, the rule pulling module 702 is used to:

[0153] Determine a pre-configured first distribution rule and a second distribution rule that is constructed on a regular basis; wherein the first distribution rule and the second distribution rule include a recommendation scenario, a distribution type, a recommended content, and a recommended section under the recommendation scenario;

[0154] Aggregating target distribution rules belonging to the same recommendation scenario in the first distribution rule and the second distribution rule to obtain an aggregate rule;

[0155] Pull the summary rules belonging to the target recommendation scenario.

[0156] In one implementation, the first distribution rule is preconfigured according to preset rule attributes.

[0157] In one implementation, the second distribution rule also includes a recommendation weight; the recommendation weight is configured based on the ranking of the current recommendation information of the recommended content in the recommendation section.

[0158] In one implementation, the distribution type includes a specific intervention type; the distribution module 703 is used to:

[0159] If the distribution type included in the distribution rule is the specific intervention type, determining a specific distribution location included in the distribution rule;

[0160] The recommended content is distributed to the specific distribution location of the recommendation section.

[0161] In one implementation, the distribution type is a non-intervention type; the non-intervention type includes a recall type; the distribution module 703 is used to:

[0162] If the distribution type included in the distribution rule is the recall type, determining current recommendation information belonging to the recommendation section;

[0163] The recommended content is inserted into the current recommendation information.

[0164] In one implementation, the distribution type is a non-intervention type; the non-intervention type includes a sorting type; the distribution module 703 is used to:

[0165] If the distribution type included in the distribution rule is the sorting type, determining the recommendation weight included in the distribution rule, and determining the current recommendation sorting of the recommended content in the recommendation section;

[0166] The recommendation ranking of the recommended content in the recommendation section is adjusted based on the recommendation weight and the current recommendation ranking.

[0167] In one implementation, the distribution type is a non-intervention type; the non-intervention type includes a filtering type; the distribution module 703 is used to:

[0168] If the distribution type included in the distribution rule is the filtering type, the recommended content included in the current recommendation information belonging to the recommendation section is deleted.

[0169] In one embodiment, the device further includes a rule updating module, configured to:

[0170] The erroneous recommendation information is determined, and the erroneous distribution rule belonging to the erroneous recommendation information in the first distribution rule or the second distribution rule is deleted.

[0171] The specific details of each part of the above-mentioned device have been described in detail in the implementation method of the method part. The undisclosed details can be found in the implementation method of the method part, so they will not be repeated here.

[0172] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0173] Exemplary Program Products

[0174] The exemplary embodiments of the present disclosure also provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the above-mentioned recommendation information distribution method is implemented.

[0175] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid-state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory, and the like.

[0176] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0177] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, etc. The program code can be executed entirely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (e.g., an Internet connection provided by an operator).

[0178] The computer program may be carried or transmitted via electrical, magnetic, optical, electromagnetic, infrared, or other signals. The electronic device may convert the signal carrying the computer program into a digital signal, thereby running the computer program. When the computer program runs on an electronic device, its code is used to enable the electronic device to execute (more specifically, the processor of the electronic device may execute) the method steps of various exemplary embodiments of the present disclosure, such as the above-mentioned recommendation information distribution method, which includes the following steps:

[0179] Step 301: Receive a recommendation information distribution request and determine the target recommendation scenario carried in the recommendation information distribution request; Step 302: Pull the distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes the distribution type, recommended content and the recommendation section under the target recommendation scenario; Step 303 distributes the recommended content to the recommendation section based on the distribution type.

[0180] By implementing the above method steps through a computer program, a recommendation information distribution request can be received, and the target recommendation scenario carried in the recommendation information distribution request can be determined; the distribution rules belonging to the target recommendation scenario can be pulled; wherein each distribution rule includes a distribution type, recommended content, and a recommendation section under the target recommendation scenario; based on the distribution type, the recommended content is distributed to the recommendation section. Specifically, when the recommendation information distribution request is determined, that is, a new business customization requirement, the distribution rules for the recommended content can be directly determined based on the target recommendation scenario carried in the request, so that the recommended content is distributed to the recommendation section according to the distribution type in the distribution rule, without occasionally incorporating the business customization requirement into the business logic, that is, without reconstructing, transforming and updating the existing promotion system, etc., thereby reducing the maintenance cost of the system. In other words, the present disclosure isolates the processing process of the target recommendation scenario from the recommendation module, that is, the business system that processes the business customization requirement is independent of the recommendation system, thereby realizing personalized information distribution and reducing the reconstruction and maintenance cost of the recommendation system.

[0181] Exemplary Electronic Devices

[0182] The exemplary embodiments of the present disclosure also provide an electronic device. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions.

[0183] Reference below Figure 8 , the electronic device is exemplarily described in the form of a general-purpose computing device. It should be understood that Figure 8 The electronic device 800 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0184] like Figure 8 As shown, the electronic device 800 may include: a processor 810 , a memory 820 , a bus 830 , an I / O (input / output) interface 840 , a network adapter 850 , and a display 880 .

[0185] The memory 820 may include a volatile memory, such as a RAM 821, a cache unit 822, and may also include a non-volatile memory, such as a ROM 823. The memory 820 may also include one or more program modules 824, such program modules 824 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 824 may include each module in the above-mentioned device.

[0186] The processor 810 may include one or more processing units. For example, the processor 810 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0187] The processor 810 can be used to execute executable instructions stored in the memory 820, such as the above-mentioned recommendation information distribution method, which includes the following steps: Step 301: Receive a recommendation information distribution request, and determine the target recommendation scenario carried in the recommendation information distribution request; Step 302: Pull the distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes a distribution type, recommended content, and a recommendation section under the target recommendation scenario; Step 303 distributes the recommended content to the recommendation section based on the distribution type.

[0188] By executing the above method steps through the processor 810, a recommendation information distribution request can be received, and the target recommendation scenario carried in the recommendation information distribution request can be determined; the distribution rules belonging to the target recommendation scenario can be pulled; wherein each distribution rule includes a distribution type, recommended content, and a recommendation section under the target recommendation scenario; based on the distribution type, the recommended content is distributed to the recommendation section. Specifically, when the recommendation information distribution request is determined, that is, a new business customization requirement, the distribution rules for the recommended content can be directly determined based on the target recommendation scenario carried in the request, so that the recommended content is distributed to the recommendation section according to the distribution type in the distribution rule, without occasionally incorporating the business customization requirement into the business logic, that is, without reconstructing, transforming and updating the existing promotion system, etc., thereby reducing the maintenance cost of the system. In other words, the present disclosure isolates the processing process of the target recommendation scenario from the recommendation module, that is, the business system that processes the business customization requirement is independent of the recommendation system, thereby realizing personalized information distribution and reducing the reconstruction and maintenance cost of the recommendation system.

[0189] The bus 830 is used to realize the connection between different components of the electronic device 800, and may include a data bus, an address bus, and a control bus.

[0190] The electronic device 800 can communicate with one or more external devices 900 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 840 .

[0191] The electronic device 800 can communicate with one or more networks through the network adapter 850. For example, the network adapter 850 can provide mobile communication solutions such as 3G / 4G / 5G, or wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 850 can communicate with other modules of the electronic device 800 through the bus 830.

[0192] The electronic device 800 can display a graphical user interface, such as related content of song recommendations, through the display 880.

[0193] although Figure 8 Not shown, other hardware and / or software modules may also be provided in the electronic device 800, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0194] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, an apparatus, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software, such as being respectively referred to as a "circuit", "module" or "system".

[0195] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

Claims

1. A method for distributing recommendation information, characterized in that: The method comprises: receiving a recommendation information distribution request, and determining a target recommendation scenario carried in the recommendation information distribution request; Pulling distribution rules belonging to the target recommendation scenario; wherein each of the distribution rules includes a distribution type, recommended content, and a recommended section under the target recommendation scenario; Based on the distribution type, the recommended content is distributed to the recommendation section.

2. The method according to claim 1, characterized in that The pulling of distribution rules belonging to the target recommendation scenario includes: Determine a pre-configured first distribution rule and a second distribution rule that is constructed on a regular basis; wherein the first distribution rule and the second distribution rule include a recommendation scenario, a distribution type, a recommended content, and a recommended section under the recommendation scenario; Aggregating target distribution rules belonging to the same recommendation scenario in the first distribution rule and the second distribution rule to obtain an aggregate rule; Pull the summary rules belonging to the target recommendation scenario.

3. The method according to claim 2, characterized in that The first distribution rule is pre-configured according to preset rule attributes.

4. The method according to claim 2, characterized in that The second distribution rule also includes a recommendation weight; the recommendation weight is configured based on the ranking of the current recommended information of the recommended content in the recommendation section.

5. The method according to claim 1, characterized in that: The distribution types described include specific intervention types; The distributing the recommended content to the recommendation section based on the distribution type includes: If the distribution type included in the distribution rule is the specific intervention type, determining a specific distribution location included in the distribution rule; The recommended content is distributed to the specific distribution location of the recommendation section.

6. The method according to claim 1, characterized in that The distribution type is a non-intervention type; the non-intervention type includes a recall type; The distributing the recommended content to the recommendation section based on the distribution type includes: If the distribution type included in the distribution rule is the recall type, determining current recommendation information belonging to the recommendation section; The recommended content is inserted into the current recommendation information.

7. The method according to claim 1, characterized in that The distribution type is a non-intervention type; the non-intervention type includes a sorting type; The distributing the recommended content to the recommendation section based on the distribution type includes: If the distribution type included in the distribution rule is the sorting type, determining the recommendation weight included in the distribution rule, and determining the current recommendation sorting of the recommended content in the recommendation section; The recommendation ranking of the recommended content in the recommendation section is adjusted based on the recommendation weight and the current recommendation ranking.

8. A recommendation information distribution device, characterized in that: The device comprises: A request module, configured to receive a recommendation information distribution request and determine a target recommendation scenario carried in the recommendation information distribution request; A rule extraction module, used to extract distribution rules belonging to the target recommendation scenario; wherein each distribution rule includes a distribution type, recommended content, and a recommended section under the target recommendation scenario; A distribution module is used to distribute the recommended content to the recommendation section based on the distribution type.

9. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer program product having a computer program stored thereon, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images