Information recommendation method, device, computer-readable medium, and server

Abstract

The present application discloses an information recommendation method, device, computer-readable medium, and server, the method comprising: obtaining a recommended operating position list according to an information recommendation request sent by a client, the recommended operating position list indicating the arrangement order of the operating positions of a plurality of recommended information; combining the recommended operating position list with a preset operating position list to generate a target operating position list, the preset operating position list including at least one preset operating position for displaying preset recommended information; obtaining a plurality of target recommended information according to the target operating position list; sending the target operating position list and the plurality of target recommended information to the client, so that the client recommends the plurality of target recommended information according to the target operating position list. The technical solution provided by the embodiment of the present application makes information recommendation more targeted, thereby improving the value of information recommendation; while retaining a portion of random recommended information, so that the recommended information can be diverse and extensive.

Description

Technical Field

[0001] The present application belongs to the field of Internet and computer technology, and specifically relates to an information recommendation method, device, computer-readable medium, and server. Background Art

[0002] With the development of internet technology, people can access a variety of information online every day. One of the ways to obtain information is through proactive recommendations from online platforms. Currently, these recommendations typically push real-time information to users. This information is often arranged in chronological order, making it difficult to reflect the value of the information. Furthermore, the recommended information is identical for all users, failing to consider the individual needs of each user. Therefore, the flexibility of existing information recommendation methods still needs to be improved.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0004] The purpose of this application is to provide an information recommendation method, device, computer-readable medium and server to solve the problem of low flexibility of information recommendation in related technologies.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0006] According to one aspect of an embodiment of the present application, there is provided an information recommendation method, comprising:

[0007] Obtaining a recommended operating position list according to the information recommendation request sent by the client, wherein the recommended operating position list indicates an arrangement order of the operating positions of the plurality of recommended information;

[0008] Combining the recommended operating position list with the preset operating position list to generate a target operating position list, wherein the preset operating position list includes at least one preset operating position for displaying preset recommendation information;

[0009] Acquire multiple target recommendation information according to the target operation position list;

[0010] The target operation position list and the plurality of target recommendation information are sent to the client, so that the client recommends the plurality of target recommendation information according to the target operation position list.

[0011] According to one aspect of an embodiment of the present application, there is provided an information recommendation device, including:

[0012] A recommendation list acquisition module, configured to acquire a recommended operation position list according to an information recommendation request sent by a client, wherein the recommended operation position list indicates an arrangement order of the operation positions of a plurality of recommended information;

[0013] a target list generating module, configured to combine the recommended operating position list with the preset operating position list to generate a target operating position list, wherein the preset operating position list includes at least one preset operating position for displaying preset recommendation information;

[0014] A recommendation information acquisition module, configured to acquire a plurality of target recommendation information according to the target operation position list;

[0015] An information recommendation module is configured to send the target operation position list and the plurality of target recommendation information to the client, so that the client recommends the plurality of target recommendation information according to the target operation position list.

[0016] In one embodiment of the present application, the recommendation list acquisition module includes:

[0017] A random list acquisition unit, configured to acquire a random recommended operating position list according to an information recommendation request sent by a client;

[0018] A verification unit, configured to verify each item of random recommendation information corresponding to the random recommendation operation position list;

[0019] The recommendation list generating unit is configured to delete the operating positions corresponding to the random recommendation information that fails verification from the random recommendation operating position list, retain the operating positions corresponding to the random recommendation information that passes verification, and generate the recommended operating position list.

[0020] In one embodiment of the present application, the verification unit is specifically configured to:

[0021] Determining whether the creator of the information corresponding to the random recommendation information is in the service blacklist of the current user;

[0022] If the creator of the information is not in the service blacklist, it is determined that the random recommendation information has passed the verification;

[0023] If the information creator is in the service blacklist, it is determined that the random recommendation information verification fails.

[0024] In one embodiment of the present application, the target list generation module includes:

[0025] A preferred operating position determining unit, configured to determine a preferred operating position in the recommended operating position list based on historical user behavior data;

[0026] The target list generating unit is configured to use the preset operating positions in the preset operating position list as the preferred operating positions in the recommended operating position list to generate a target operating position list.

[0027] In one embodiment of the present application, the target operation position list includes picture operation positions, topic operation positions, and random operation positions; and the recommendation information acquisition module includes:

[0028] A picture data acquisition unit, configured to, when the target operation position in the target operation position list is a picture operation position, acquire picture data corresponding to the picture operation position as target recommendation information;

[0029] An offline package data acquisition unit, configured to, when the target operation position in the target operation position list is a topic operation position, acquire offline package data corresponding to the topic operation position as target recommendation information, wherein the offline package data indicates a method for acquiring topic data corresponding to the topic operation position;

[0030] The random recommendation information acquiring unit is configured to acquire random recommendation information as target recommendation information when the target operation position in the target operation position list is a random operation position.

[0031] In one embodiment of the present application, the image operation position corresponds to image data of multiple images, and the topic operation position corresponds to offline package data of multiple topics; the information recommendation module includes:

[0032] A picture data filtering unit, configured to filter the multiple pictures corresponding to the topic operation position to obtain picture data of the target picture when the target operation position in the target operation position list is a picture operation position;

[0033] an offline package data filtering unit, configured to, when a target operation position in the target operation position list is a topic operation position, filter a plurality of topics corresponding to the topic operation position to obtain offline package data of the target topic;

[0034] An information recommendation unit is configured to send the image data of the target image and the offline package data of the target topic to the client, so that the client recommends the target image and the target topic according to the target operating position list.

[0035] In one embodiment of the present application, the offline package data includes an offline package identifier; and the information recommendation unit is specifically configured to:

[0036] Calling a corresponding remote call interface according to the offline package identifier corresponding to the topic operation position in the target operation position list, so that the remote call interface obtains the corresponding target topic data from the server;

[0037] The target topic data is displayed through the topic operation position to recommend the target topic.

[0038] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the information recommendation method in the above technical solution is implemented.

[0039] According to one aspect of an embodiment of the present application, a server is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the information recommendation method in the above technical solution by executing the executable instructions.

[0040] According to one aspect of an embodiment of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the information recommendation method described in the above technical solution.

[0041] In the technical solution provided in the embodiment of the present application, a target operation position list is generated by combining the recommended operation position list with the preset operation position list, so that the information recommended by the client contains specially selected preset recommendation information, making the information recommendation more targeted, thereby improving the value of the information recommendation; at the same time, a part of the random recommendation information is retained, so that the recommended information can be diverse and extensive.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0044] Figure 1 The following schematically shows an exemplary system architecture block diagram applying the technical solution of the present application.

[0045] Figure 2 The following schematically shows a flow chart of an information recommendation method provided by an embodiment of the present application.

[0046] Figure 3AThe flowchart of obtaining a list of recommended operating locations provided by one embodiment of the present application is schematically shown.

[0047] Figure 3B A schematic diagram of a target recommended operating position list provided in one embodiment of the present application is schematically shown.

[0048] Figure 4 The following schematically shows a flow chart of an information recommendation method provided by a specific embodiment of the present application.

[0049] Figure 5 The flowchart of a topic information recommendation method provided by a specific embodiment of the present application is schematically shown.

[0050] Figure 6 The following schematically shows a flow chart of pulling feed operation positions in a specific embodiment of the present application.

[0051] Figure 7 The flowchart of pulling pictures and topic operation positions in a specific embodiment of the present application is schematically shown.

[0052] Figure 8 The structural block diagram of the information recommendation device provided in an embodiment of the present application is schematically shown.

[0053] Figure 9 The following schematically shows a block diagram of a computer system structure suitable for implementing a server according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0055] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0056] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0057] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0058] Figure 1 The following schematically shows an exemplary system architecture block diagram applying the technical solution of the present application.

[0059] like Figure 1 As shown, system architecture 100 may include terminal device 110, network 120, and server 130. Terminal device 110 may include various electronic devices such as smartphones, tablet computers, laptop computers, and desktop computers. Server 130 may be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services. Network 120 may be a communication medium of various connection types capable of providing a communication link between terminal device 110 and server 130, such as a wired communication link or a wireless communication link.

[0060] Depending on implementation needs, the system architecture in the embodiments of the present application can have any number of terminal devices, networks, and servers. For example, server 130 can be a server group consisting of multiple server devices. In addition, the technical solutions provided in the embodiments of the present application can be applied to terminal device 110, server 130, or can be implemented by both terminal device 110 and server 130, and this application does not impose any special restrictions on this.

[0061] For example, a client is located in a terminal device 110. When information recommendation is required, the terminal device 110 initiates an information recommendation request to the server 130. The server 130 obtains a recommended operating position list based on the information recommendation request initiated by the terminal device 110. The recommended operating position list indicates the order in which the operating positions of the multiple recommended information are arranged. The server 130 then combines the recommended operating position list with the preset operating position list to generate a target operating position list, wherein the preset operating position list includes at least one preset operating position for displaying preset recommended information. The server 130 then obtains multiple target recommended information based on the target operating position list and sends the target operating position list and the multiple target recommended information to the client of the terminal device 110, so that the client can recommend the multiple target recommended information based on the target operating position list.

[0062] In one embodiment of the present application, the information recommendation method provided in the embodiment of the present application is executed by server 130. Server 130 feeds back a target operating location list and target recommendation information to terminal device 110 based on an information recommendation request sent by terminal device 110. Accordingly, the information recommendation device is generally provided in server 130. However, it will be readily understood by those skilled in the art that the information recommendation method provided in the embodiment of the present application may also be executed by terminal device 110, and accordingly, the information recommendation device may also be provided in terminal device 110, and this is not particularly limited in this exemplary embodiment.

[0063] The information recommendation provided by this application is described in detail below in conjunction with specific implementation methods.

[0064] Figure 2 The flowchart of the information recommendation method provided by an embodiment of the present application is schematically shown. The method can be implemented by a server, such as Figure 1 The method can also be implemented by a terminal device, such as Figure 1 The terminal device 110 shown in FIG. Figure 2 As shown, the information recommendation method provided in the embodiment of the present application includes steps 210 to 240, which are specifically as follows:

[0065] Step 210: Obtain a recommended operating position list according to the information recommendation request sent by the client, where the recommended operating position list indicates an arrangement order of the operating positions of the plurality of recommended information.

[0066] Specifically, the information recommendation request can be triggered by the user or generated by a scheduled task set by the client. For example, an information recommendation request is generated when the user opens the information recommendation page, or when the user performs a refresh operation, or the client sets a scheduled task to generate an information recommendation request every 10 minutes, etc.

[0067] The information recommendation request generated by the client is an instruction to the server to request a response of recommended information. After receiving the information recommendation request, the server obtains a list of recommended operation positions based on the information recommendation request. The recommended operation position list is a list of operation positions of recommended information arranged in a certain order. The operation position is equivalent to the card position or location on the display page where the recommended information is displayed. Recommended information is any form of content information that can be recommended, also generally referred to as a feed. For example, the recommended information can be an image, a topic, a video, an audio clip, etc.

[0068] In one embodiment of the present application, the recommended information corresponding to each operation position in the recommended operation position list may be randomly selected, one piece of recommended information corresponds to one operation position, and one operation position may correspond to multiple pieces of recommended information.

[0069] In one embodiment of the present application, Figure 3A As shown, the process of obtaining the recommended operating location list includes steps 310 to 330, which are as follows:

[0070] Step 310: Obtain a list of randomly recommended operating locations according to the information recommendation request sent by the client.

[0071] Specifically, the random recommended operation position list means that the recommended information corresponding to the operation position is randomly selected, that is, the operation position corresponds to random recommended information.

[0072] Step 320: Verify each item of random recommendation information corresponding to the random recommendation operation position list.

[0073] Specifically, after obtaining the list of randomly recommended operating positions, the attribute information of the randomly recommended information corresponding to each operating position in the randomly recommended operating position list can be determined, such as the creator, source, and type of the randomly recommended information. The type refers to the presentation format of the randomly recommended information, such as pictures, topics, audio, and video. Verifying the randomly recommended information is to determine whether the user has the authority to recommend the randomly recommended information to the current user corresponding to the information recommendation request, that is, to verify whether the current user allows the recommendation of the randomly recommended information.

[0074] In one embodiment of the present application, the process of verifying the random recommendation information includes: determining whether the information creator corresponding to the random recommendation information is in the service blacklist of the current user; if the information creator is not in the service blacklist, determining that the random recommendation information verification is passed; if the information creator is in the service blacklist, determining that the random recommendation information verification is failed.

[0075] Specifically, the verification is performed by verifying whether the creator of the random recommendation information is in the service blacklist corresponding to the current user. The service blacklist corresponding to the current user is generated according to the user's settings. Users in the service blacklist are determined to be users that the current user does not want to see, such as blacklist users set by the current user, users blocked by the current user, etc. If the creator of the information is not in the service blacklist, it is considered that the random recommendation information can be recommended to the current user, and the verification is determined to be passed; otherwise, if the creator of the information is in the service blacklist, it is determined that the random recommendation information verification has failed.

[0076] Step 330: Delete the operating positions corresponding to the random recommendation information that fails verification from the random recommended operating position list, retain the operating positions corresponding to the random recommendation information that passes verification, and generate a recommended operating position list.

[0077] Specifically, the random recommended operation position list will delete the corresponding operation position of the random recommended information that fails verification, and the remaining operation positions that pass verification will constitute the recommended operation position list. This prevents the recommended information corresponding to each operation position in the recommended operation list from coming from the current user's blacklist or blocked users, thereby improving the user experience when viewing recommended information.

[0078] Continue to refer Figure 2 In step 220, the recommended operation position list is combined with the preset operation position list to generate a target operation position list, where the preset operation position list includes at least one preset operation position for displaying preset recommendation information.

[0079] Specifically, the preset operation position list is a list composed of preset operation positions, which are operation positions used to display preset recommended information. Preset recommended information is usually pre-selected information with relatively high recommendation value, such as videos with large playback volumes, topics with a large number of participants, and pictures with high popularity. Combining the recommended operation position list with the preset operation position list means rearranging the operation positions in the two operation position lists to form a new target operation position list. In this way, the target operation position list includes both randomly selected recommended information and pre-selected recommended information, which not only ensures the breadth of recommended information but also reflects the value of the recommended information.

[0080] In one embodiment of the present application, the recommended operation position list is combined with the preset operation position list, and the preset operation positions in the preset operation position list can be uniformly arranged before the operation positions in the recommended operation position list, or the preset operation positions in the preset operation position list can be inserted between the operation positions in the recommended operation position list.

[0081] In one embodiment of the present application, the process of combining the recommended operation position list with the preset operation position list specifically includes: determining the preferred operation position in the recommended operation position list based on historical user behavior data; using the preset operation position in the preset operation position list as the preferred operation position in the recommended operation position list to generate a target operation position list.

[0082] Specifically, historical user behavior data refers to the historical behavior data of users when browsing recommended information, including browsing speed, browsing time, dwell time, number of clicks, clicked positions, and other data. This historical user behavior data can be used to analyze the preferred operational positions with the most valuable information recommendations. For example, the preferred operational position is the position that users click most frequently, the position where users dwell the longest, etc. There can be multiple preferred operational positions; generally, the number of preferred operational positions is the same as the number of preset operational positions.

[0083] After determining the preferred operating position in the recommended operating position list, the preferred operating position is changed to the preset operating position in the preset operating position list, that is, the preset operating position is inserted in the position of the preferred operating position. For example, the recommended operating position list includes operating position 1, operating position 2, operating position 3, operating position 4, and operating position 5, and the preset operating positions in the preset operating position list include preset operating position 1 and preset operating position 2. If the preferred operating positions are determined to be operating position 2 and operating position 3, the target operating position list formed will include operating position 1, preset operating position 1, preset operating position 2, operating position 4, and operating position 5.

[0084] Continue to refer Figure 2 , step 230, obtaining multiple target recommendation information according to the target operation position list.

[0085] Specifically, after obtaining the target operation position list, it is equivalent to determining each target recommendation information required for recommendation, and then the target recommendation information corresponding to each target operation position can be obtained according to the target operation position list.

[0086] In one embodiment of the present application, the preset operation position list includes picture operation positions and topic operation positions, and the target operation position list includes picture operation positions, topic operation positions and random operation positions. Random operation positions are the operation positions in the target operation position list except picture operation positions and topic operation positions. Generally, the number of picture operation positions and topic operation positions is small, and the number of random operation positions is large. For example, Figure 3BAs shown, both feed and recommendation feed represent random operation positions, and pictures / topics represent picture operation positions or topic operation positions. In the display interface of the terminal device, the picture operation position and topic operation position are set at the preferred operation position, that is, the position where the user has a greater probability of clicking, so that the recommended information at the picture operation position and topic operation position can be more likely to be discovered by the user. Furthermore, the interface at the picture operation position and topic operation position can be set to a display method that is different from the random operation position. For example, the random operation position has a light background, and the picture operation position and topic operation position have a dark background. This can further increase the probability of the recommended information at the picture operation position and topic operation position being quickly discovered by the user.

[0087] In one embodiment of the present application, when the type of target operation position is different, the target recommendation information obtained is also different. The method for obtaining the target recommendation information includes: when the target operation position in the target operation position list is a picture operation position, obtaining the picture data corresponding to the picture operation position as the target recommendation information; when the target operation position in the target operation position list is a topic operation position, obtaining the offline package data corresponding to the topic operation position as the target recommendation information, and the offline package data indicates the method for obtaining the topic data corresponding to the topic operation position; when the target operation position in the target operation position list is a random operation position, obtaining random recommendation information as the target recommendation information.

[0088] Specifically, since the target operation position list includes three types: picture operation position, topic operation position and random operation position, the recommended information is also divided into three categories: picture recommendation information, topic recommendation information and random recommendation information. The operation position corresponding to the picture recommendation information is the picture operation position, the operation position corresponding to the topic recommendation information is the topic operation position, and the operation position corresponding to the random recommendation information is the random operation position.

[0089] When the target operation position in the target operation position list is a picture operation position, it indicates that picture recommendation information should be obtained. Generally, the picture operation position is native, and the server stores the corresponding picture data, so the picture data is the target recommendation information corresponding to the picture operation position. Optionally, the picture operation position and its corresponding picture recommendation information have an association relationship, and the storage address or picture identifier of the corresponding picture recommendation information can be determined according to the picture operation position, and the server can obtain the corresponding picture data according to the storage address or picture identifier. When the target operation position in the target operation position list is a topic operation position, it indicates that topic recommendation information should be obtained. In an embodiment of the present application, the topic recommendation information does not adopt the form of directly storing topic data, but stores topic data in the form of an offline package. The offline package indicates the method of obtaining the topic data corresponding to the topic operation position. Each offline package has an identifier (ID). When the target operation position in the target operation position list is a topic operation position, the server will obtain the offline package data for indicating the topic recommendation information according to the topic operation position as the target recommendation information, and the offline package data includes the offline package ID. The offline package can be pre-configured and stored on the server or other management platform. When needed, the client obtains the offline package data from the offline package storage location using the offline package ID.

[0090] When the target operation position in the target operation position list is a random operation position, it means that random recommendation information should be obtained, and random recommendation information means randomly obtaining a piece of recommendation information. Figure 3B As shown, random recommendation information can also be divided into general recommendation information (feed) and special recommendation information (recommendation feed). General recommendation information (feed) can be randomly obtained recommendation information, and special recommendation information (recommendation feed) can be recommended information obtained according to certain rules, for example, the most popular information in the recommended information, the latest updated information, etc.

[0091] Continue to refer Figure 2 In step 240 , the target operation position list and the plurality of target recommendation information are sent to the client, so that the client recommends the plurality of target recommendation information according to the target operation position list.

[0092] Specifically, a list of target operating positions and multiple target recommendation information is sent to the client, and the client can recommend the target recommendation information based on the order of the target operating positions in the target operating position list. On the client's display page, the preset operating positions will have a more prominent UI (User Interface) design, so that users can prioritize the preset recommendation information for the preset operating positions when browsing the recommended information on the display page.

[0093] In the technical solution provided in the embodiment of the present application, a target operation position list is generated by combining the recommended operation position list with the preset operation position list, so that the information recommended by the client contains specially selected preset recommendation information, making the information recommendation more targeted, thereby improving the value of the information recommendation; at the same time, a part of the random recommendation information is retained, so that the recommended information can be diverse and extensive.

[0094] In one embodiment of the present application, Figure 4 As shown, the specific process of step 240 includes: when the target operation position in the target operation position list is a picture operation position, filtering multiple pictures corresponding to the topic operation position to obtain picture data of the target picture; when the target operation position in the target operation position list is a topic operation position, filtering multiple topics corresponding to the topic operation position to obtain offline package data of the target topic; sending the picture data of the target picture and the offline package data of the target topic to the client, so that the client recommends the target picture and the target topic according to the target operation position list.

[0095] Specifically, before sending the target recommendation information to the client, the target recommendation information is filtered. The filtering mainly removes the recommended information that the current user is not interested in or has already viewed, thereby avoiding recommending information that the user is not interested in or recommending duplicate information to the user. The information that the current user is not interested in or has already viewed can be determined based on the current user's historical behavior data.

[0096] The filtering of target recommendation information includes filtering of image recommendation information and filtering of topic recommendation information. For filtering of image recommendation information, when one image operation position corresponds to one image, no filtering operation is required. When one image operation position corresponds to multiple images, the image data of multiple images can be filtered, and the image data of images that the current user is not interested in or has browsed can be deleted, and the retained image data is the image data of the target image that ultimately needs to be recommended. Optionally, when there are multiple image operation positions, multiple image operation positions can be filtered, and the image operation positions corresponding to images that the current user is not interested in or has browsed can be deleted, and the image operation positions that the user is interested in or has not browsed can be retained.

[0097] Regarding the filtering of topic recommendation information, when a topic operation position corresponds to one topic, no filtering operation is required. When a topic operation position corresponds to multiple topics, the offline package data corresponding to the multiple topics can be filtered, and the offline package data corresponding to the topics that the current user is not interested in or has browsed can be deleted. The retained offline package data is the offline package data of the target topic that needs to be recommended in the end. Optionally, when there are multiple topic operation positions, multiple topic operation positions can be filtered, and the topic operation positions corresponding to the topics that the current user is not interested in or has browsed can be deleted, and the topic operation positions that the user is interested in or has not browsed can be retained.

[0098] Finally, the image data of the target image and the offline package data of the target topic are sent to the client. The client can then recommend the target image and target topic based on the target operation position list, thereby avoiding Axing recommending information that the current user is not interested in or has already browsed to the user, and improving the user's experience of browsing recommended information.

[0099] In one embodiment of the present application, when the client recommends information, for the picture operation position, since the server directly returns the corresponding picture data, the client can display the corresponding picture through the native picture operation position.

[0100] For the topic operation position, the server returns the offline package data corresponding to the topic recommendation information. The offline package data is the offline package ID, and the offline package ID indicates the call of the remote call interface (API). Therefore, the client calls the corresponding remote call interface according to the offline package identifier to obtain the corresponding target topic data from the server through the remote call interface; the target topic data is displayed through the topic operation position to recommend the target topic. That is, the client calls the specified offline package API by calling the offline package ID. The offline package API is a remote call (Remote Procedure Call Protocol, RPC) interface, and obtains the corresponding target topic data through the RPC interface. Finally, the target topic data is displayed in the topic operation position, thereby realizing the recommendation of the target topic.

[0101] When the client calls the offline package API, the offline package API initiates a request to the server to obtain offline package data. Based on the offline package data acquisition request, the server obtains the offline package data from the offline package data storage address such as the database or offline package platform, and then returns the offline package data to the offline package API. The client can then obtain the offline package data.

[0102] In one embodiment of the present application, when filtering offline package data, historical recommendation information that the user has marked as not interested or disliked can be matched with the offline package data, and the similarity between the two can be calculated. Based on the similarity, it is determined whether the offline package data is information that the user is not interested in or dislikes.

[0103] In one embodiment of the present application, when matching historical recommendation information with offline package data, the feature vectors of the historical recommendation information and the feature vectors of the offline package data are first extracted, and then the similarity (such as cosine similarity) between the two feature vectors is calculated. When the similarity is greater than a preset threshold, the historical recommendation information is considered to be similar to the offline package data, and the offline package data is considered to be information that the user is not interested in or dislikes.

[0104] In one embodiment of the present application, a feature vector of historical recommendation information or offline package data is extracted through a TextRank model. Taking the extraction of feature vectors of historical recommendation information as an example, in the TextRank model, the length of the window is set to k, and the historical recommendation information {w1, w2, w3, w4, w5, ..., wn} is processed, where wn represents the feature word in the historical recommendation information, and the window of the historical recommendation information is {w1, w2, .., wk}, {w2, w3, .., wk+1}, {w3, w4, .., wk+2}, ..., {wnk, wn(k1), .., wn}. Between any two nodes in a window, there is an edge with the number of times two feature words co-occur as the weight, and all feature words and their co-occurrence relationship constitute a weighted undirected graph, and then the importance of each feature word (the TextRank value of each feature word) is calculated using the following formula:

[0105]

[0106] Among them, WS(V i ) represents the i-th feature word V i The important value of d is the damping coefficient, In(V i ) represents the i-th feature word V i The co-occurring word set, Out(V j ) represents the jth feature word V j The set of co-occurring words, w ji Represents the i-th feature word V i and the jth feature word V j The co-occurrence weight of .

[0107] Optionally, the damping coefficient d may be 0.85, but is not limited to 0.85, and may be 0.8 or 0.9, etc., depending on the usage scenario.

[0108] Based on the word vector model Vec(wordi )=(v1,v2,...,v K ), the matched feature words are input into the word vector model in sequence to obtain the feature vector of the historical recommendation information:

[0109]

[0110] Among them, V represents the feature vector and n represents the number of feature words.

[0111] The following Figure 4-7 A specific embodiment is shown to illustrate the implementation process of the information recommendation method provided by this application.

[0112] like Figure 4 As shown, the information recommendation method provided by a specific embodiment of the present application includes:

[0113] S401. Requesting a plaza list. The client (client) initiates a plaza list request to the multimedia server (media_list_svr). A plaza list is a list of recommended information to be displayed on the recommendation information display page of the application software. Requesting a plaza list is equivalent to initiating an information recommendation request.

[0114] S402. Request a feed list. After receiving the plaza list request, the multimedia server (media_list_svr) requests a feed list from the application server (nnq_svr). A feed is recommended information, and a feed list is a list of recommended information arranged in a certain order. In this embodiment, the feed list is equivalent to a list of randomly recommended information, equivalent to a list of randomly recommended operating locations.

[0115] S403. Read feed_id and feed_model, and read the feed operation position from the database. The feed_id is the unique identifier corresponding to each recommendation information, and the feed_model is the display model corresponding to each recommendation information, including creator information, publication time, publication content, interactive content, number of interactions, and various statistics. The application software server (nnq_svr) reads feed_id and feed_model from the relational database (Redis) to obtain all random recommendation information. At the same time, the feed operation position is read from the database (DB), that is, a list of random recommendation operation positions is obtained.

[0116] S404. Request feed list response. After the application server (nnq_svr) obtains the feed_id, feed_model, and feed operation bit, it returns the data to the multimedia server (media_list_svr).

[0117] S405. Request for image & topic operation position. Based on the obtained operation position information, the multimedia server (media_list_svr) requests the information recommendation server (recommend_svr) to obtain the corresponding recommended information.

[0118] S406. Request image placement information. After receiving the request from the multimedia server (media_list_svr), the recommendation server (recommend_svr) retrieves the corresponding recommendation information based on the placement type. If it is a placement for an image, the recommendation server (recommend_svr) directly reads the corresponding image data from the database (DB) as the image recommendation information (i.e., the placement information for the image).

[0119] S407. Request topic operation position. If it is a topic operation position, the information recommendation server (recommend_svr) requests the topic server (discussion_svr) to obtain the topic recommendation information corresponding to the topic operation position.

[0120] S408. Read topic operation position information. The topic server (discussion_svr) reads the corresponding topic data from the database (DB) as topic recommendation information (ie, topic operation position information). In this embodiment, the topic data is offline package data.

[0121] S409. Request for topic operation position response. The topic server (discussion_svr) returns the operation position information read from the database (DB) to the information recommendation server (recommend_svr).

[0122] S410. Request for image and topic marketing position response. The information recommendation server (recommend_svr) returns the acquired image marketing position information and topic marketing position information to the multimedia server (media_list_svr).

[0123] S411. Request for Plaza List Response: The multimedia server (media_list_svr) returns the image and topic information to the client, which can then recommend information based on the returned data.

[0124] Figure 5 A flowchart showing only topic information recommendation is shown. Figure 5 As shown in the figure, the process specifically includes:

[0125] S501. Request a plaza list. The client (client) initiates a plaza list request to the multimedia server (media_list_svr). This step is the same as step S401 and can be referred to in the previous description.

[0126] S502. Requesting an operating position: The multimedia server (media_list_svr) requests topic operating position information from the topic server (discussion_svr).

[0127] S503. Request for operation position response: The topic server (discussion_svr) returns the topic operation position information to the multimedia server (media_list_svr).

[0128] S504. Request for Plaza List Response. The multimedia server (media_list_svr) returns the topic operation position information to the client (client), so that the client (client) can recommend topic information based on the topic operation position information. The returned topic operation position information includes the offline package data corresponding to the topic information.

[0129] S505. Requesting operation position details. The client (client) makes an API call based on the offline package data to request operation position details from the topic server (discussion_svr), that is, to obtain topic recommendation information corresponding to the topic operation position.

[0130] S506. Read the operation position information. The offline package is stored in the database (DB), and the topic server (discussion_svr) reads the operation position information (topic data) from the database (DB).

[0131] S507. Request operation bit response. The discussion server (discussion_svr) returns the acquired topic data to the client (client), and the client (client) can display the corresponding topic information.

[0132] Figure 6 The process of pulling the feed operation position in the specific embodiment of the present application is shown, that is, the specific process from step S402 to step S404 above. Figure 6 As shown, the process includes:

[0133] S601. The client pulls the feed list. The client executes the command cmd:8000 to request to pull the feed list.

[0134] S602. Determine whether you have permission to pull the list. The server obtains a list of random recommendation positions, which includes multiple random recommendation pieces. Each piece of random recommendation is verified to determine whether the creator of the random recommendation is a blacklisted user or a blocked user. This is determined using the blacklist service (im_svr) and the mute service (mute_svr). If not, the process ends; if so, proceed to step S603.

[0135] S603. Read the zset list set from Redis to obtain feed_ids, and read feed_models based on feed_ids. Read feed_id and feed_model from the relational database (Redis), where feed_ids refers to multiple feed_ids and feed_models refers to multiple feed_models.

[0136] S604. Insert feed content into the operation position. This step determines the preferred operation position, then uses the preset operation position as the preferred operation position and combines it with the recommended operation position to obtain the target operation position. The data for the preset operation position is stored in a database (DB). Data read from the database (DB) is first stored in a cache, and then read from the cache and inserted into the feed content operation position.

[0137] S605. Assemble feed information. This step assembles the recommendation information to form a corresponding recommendation model. The assembled content includes comment data, like data, user profile, and user information. Comment data is obtained through the comment service (comment_svr), like data is obtained through the like service (like_svr), user profile is obtained through the user profile service (sns_profile), and user information is obtained through the user information service (sns_user_tag).

[0138] S606. UGC translation: This step refers to recommending the assembled model as UCG (User Generated Content).

[0139] Figure 7 The flowchart of the picture and topic operation position pulling in the specific embodiment of the present application is shown, that is, the specific process of the above steps S405 to S410, as shown in FIG. Figure 7 As shown, the process includes:

[0140] Step 701: The client requests a list of applications for the plaza, where the application is moomoo. The request includes image and topic operation slots.

[0141] Step 702: The server loads the image operation position data. Since the image operation position is native and the image data is stored on the server, the server can directly load the image operation position data.

[0142] Step 703: Filter out uninteresting / already displayed picture operation positions. This step is to filter the picture data of the picture operation positions, including filtering the picture data of multiple pictures in one picture operation position, and filtering multiple picture operation positions.

[0143] Step 704: Determine whether the image operation position still exists. If so, display the native image operation position; if not, proceed to step 705.

[0144] Step 705: Load n topic operation positions. After processing the image operation position, the topic operation is loaded to process the topic operation position.

[0145] Step 706: Filter out uninteresting / displayed topic operation positions. This step is to filter the topic data of the topic operation position, including filtering the topic data of multiple topics in one topic operation position, and filtering multiple topic operation positions.

[0146] Step 707: The client displays the picture operation position.

[0147] Step 708: Reserve offline package slots. Since the topic data for the topic operation slots must be obtained through offline packages, the display of topic operation slots is slightly slower than that of image operation slots. While displaying image operation slots, reserve the topic operation slots, i.e., the offline package slots.

[0148] Step 709: The offline package platform loads the offline package. The client calls the offline package API interface using the offline package ID, and the offline package platform loads the corresponding offline package based on the calling instruction.

[0149] Step 710. The web end pulls the topic operation content. In this embodiment, the offline package platform and the web end are equivalent to the server end in the offline package calling process described above.

[0150] Step 711. The client performs topic operation position display.

[0151] It should be noted that although the steps of the method of the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all steps must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0152] The following introduces an embodiment of a device of the present application, which can be used to execute the information recommendation method in the above-mentioned embodiment of the present application. Figure 8 The structural block diagram of the information recommendation device provided by the embodiment of the present application is schematically shown. Figure 8 As shown, the information recommendation device provided in the embodiment of the present application includes:

[0153] A recommendation list acquisition module 810 is configured to acquire a recommended operation position list according to an information recommendation request sent by a client, wherein the recommended operation position list indicates an arrangement order of operation positions of a plurality of recommended information;

[0154] A target list generating module 820 is configured to combine the recommended operating position list with the preset operating position list to generate a target operating position list, wherein the preset operating position list includes at least one preset operating position for displaying preset recommendation information;

[0155] A recommendation information acquisition module 830 is configured to acquire a plurality of target recommendation information according to the target operation position list;

[0156] The information recommendation module 840 is configured to send the target operation position list and the plurality of target recommendation information to the client, so that the client recommends the plurality of target recommendation information according to the target operation position list.

[0157] In one embodiment of the present application, the recommendation list acquisition module 810 includes:

[0158] A random list acquisition unit, configured to acquire a random recommended operating position list according to an information recommendation request sent by a client;

[0159] A verification unit, configured to verify each item of random recommendation information corresponding to the random recommendation operation position list;

[0160] The recommendation list generating unit is configured to delete the operating positions corresponding to the random recommendation information that fails verification from the random recommendation operating position list, retain the operating positions corresponding to the random recommendation information that passes verification, and generate the recommended operating position list.

[0161] In one embodiment of the present application, the verification unit is specifically configured to:

[0162] Determining whether the creator of the information corresponding to the random recommendation information is in the service blacklist of the current user;

[0163] If the creator of the information is not in the service blacklist, it is determined that the random recommendation information has passed the verification;

[0164] If the information creator is in the service blacklist, it is determined that the random recommendation information verification fails.

[0165] In one embodiment of the present application, the target list generation module 820 includes:

[0166] A preferred operating position determining unit, configured to determine a preferred operating position in the recommended operating position list based on historical user behavior data;

[0167] The target list generating unit is configured to use the preset operating positions in the preset operating position list as the preferred operating positions in the recommended operating position list to generate a target operating position list.

[0168] In one embodiment of the present application, the target operation position list includes picture operation positions, topic operation positions, and random operation positions; the recommendation information acquisition module 830 includes:

[0169] A picture data acquisition unit, configured to, when the target operation position in the target operation position list is a picture operation position, acquire picture data corresponding to the picture operation position as target recommendation information;

[0170] An offline package data acquisition unit, configured to, when the target operation position in the target operation position list is a topic operation position, acquire offline package data corresponding to the topic operation position as target recommendation information, wherein the offline package data indicates a method for acquiring topic data corresponding to the topic operation position;

[0171] The random recommendation information acquiring unit is configured to acquire random recommendation information as target recommendation information when the target operation position in the target operation position list is a random operation position.

[0172] In one embodiment of the present application, the image operation position corresponds to image data of multiple images, and the image operation position corresponds to offline package data of multiple topics; the information recommendation module 840 includes:

[0173] A picture data filtering unit, configured to filter the multiple pictures corresponding to the topic operation position to obtain picture data of the target picture when the target operation position in the target operation position list is a picture operation position;

[0174] an offline package data filtering unit, configured to, when a target operation position in the target operation position list is a topic operation position, filter a plurality of topics corresponding to the topic operation position to obtain offline package data of the target topic;

[0175] An information recommendation unit is configured to send the image data of the target image and the offline package data of the target topic to the client, so that the client recommends the target image and the target topic according to the target operating position list.

[0176] In one embodiment of the present application, the offline package data includes an offline package identifier; and the information recommendation unit is specifically configured to:

[0177] Calling a corresponding remote call interface according to the offline package identifier corresponding to the topic operation position in the target operation position list, so that the remote call interface obtains the corresponding target topic data from the server;

[0178] The target topic data is displayed through the topic operation position to recommend the target topic.

[0179] The specific details of the information recommendation device provided in each embodiment of the present application have been described in detail in the corresponding method embodiments and will not be repeated here.

[0180] Figure 9 The following schematically shows a block diagram of a computer system structure of a server for implementing an embodiment of the present application.

[0181] It should be noted that Figure 9 The server computer system 900 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application.

[0182] like Figure 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 902 or the program loaded from the storage part 908 into the random access memory (RAM) 903. Various programs and data required for system operation are also stored in the random access memory 903. The CPU 901, the read-only memory 902, and the random access memory 903 are connected to each other via a bus 904. An input / output interface 905 (i.e., an I / O interface) is also connected to the bus 904.

[0183] The following components are connected to the input / output interface 905: an input section 906 including a keyboard, a mouse, and the like; an output section 907 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a local area network card or a modem. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, is installed in the drive 910 as needed so that a computer program read therefrom can be installed into the storage section 908 as needed.

[0184] In particular, according to an embodiment of the present application, the processes described in the various method flow charts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the methods shown in the flow charts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909 and / or installed from a removable medium 911. When the computer program is executed by the central processing unit 901, the various functions defined in the system of the present application are performed.

[0185] 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 embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0186] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0187] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. An information recommendation method, characterized in that: include: Obtain a list of randomly recommended operating positions based on the information recommendation request sent by the client; Verifying each item of random recommendation information corresponding to the random recommendation operation position list; Deleting the operating positions corresponding to the random recommendation information that failed the verification from the random recommended operating position list, retaining the operating positions corresponding to the random recommendation information that passed the verification, and generating a recommended operating position list, wherein the recommended operating position list indicates the arrangement order of the operating positions of the multiple recommended information; Determining a preferred operating location in the recommended operating location list based on historical user behavior data; generating a target operation position list by using a preset operation position in the preset operation position list as a preferred operation position in the recommended operation position list, wherein the preset operation position list includes at least one preset operation position for displaying preset recommendation information; the preset recommendation information includes pre-selected information with recommendation value; Acquire multiple target recommendation information according to the target operation position list; the target operation position list includes picture operation positions, topic operation positions and random operation positions; The target operation position list and the plurality of target recommendation information are sent to the client, so that the client recommends the plurality of target recommendation information according to the target operation position list.

2. The information recommendation method according to claim 1, characterized in that: Verify each item of random recommendation information corresponding to the random recommendation operation position list, including: Determine whether the creator of the information corresponding to the random recommended information is in the service blacklist of the current user; If the creator of the information is not in the service blacklist, it is determined that the random recommendation information has passed the verification; If the information creator is in the service blacklist, it is determined that the random recommendation information verification fails.

3. The information recommendation method according to claim 1, wherein: Acquire multiple target recommendation information based on the target operation position list, including: When the target operation position in the target operation position list is a picture operation position, obtaining picture data corresponding to the picture operation position as target recommendation information; When the target operation position in the target operation position list is a topic operation position, obtaining offline package data corresponding to the topic operation position as target recommendation information, wherein the offline package data indicates a method for obtaining topic data corresponding to the topic operation position; When the target operation position in the target operation position list is a random operation position, random recommendation information is obtained as target recommendation information.

4. The information recommendation method according to claim 3, characterized in that: The image operation position corresponds to image data of multiple images, and the topic operation position corresponds to offline package data of multiple topics; sending the target operation position list and the multiple target recommendation information to the client, so that the client recommends the multiple target recommendation information according to the target operation position list, including: When the target operation position in the target operation position list is a picture operation position, filtering multiple pictures corresponding to the picture operation position to obtain picture data of the target picture; When the target operation position in the target operation position list is a topic operation position, filtering multiple topics corresponding to the topic operation position to obtain offline package data of the target topic; The image data of the target image and the offline package data of the target topic are sent to the client, so that the client recommends the target image and the target topic according to the target operating position list.

5. The information recommendation method according to claim 4, characterized in that: The offline package data includes an offline package identifier; the client recommends the target topic according to the target operating position list, including: Calling a corresponding remote call interface according to the offline package identifier corresponding to the topic operation position in the target operation position list, so that the remote call interface obtains the corresponding target topic data from the server; The target topic data is displayed through the topic operation position to recommend the target topic.

6. An information recommendation device, characterized in that: include: A recommendation list acquisition module is configured to acquire a list of randomly recommended operating positions based on an information recommendation request sent by a client; verify each item of random recommended information corresponding to the list of randomly recommended operating positions; delete the operating positions corresponding to random recommended information that fails verification from the list of randomly recommended operating positions, retain the operating positions corresponding to random recommended information that passes verification, and generate a recommended operating position list, wherein the recommended operating position list indicates the order in which the operating positions of the multiple recommended information are arranged; a target list generation module, configured to determine a preferred operating position in the recommended operating position list based on historical user behavior data; generate a target operating position list by using a preset operating position in the preset operating position list as the preferred operating position in the recommended operating position list, wherein the preset operating position list includes at least one preset operating position for displaying preset recommendation information; the preset recommendation information includes pre-selected information with recommendation value; A recommendation information acquisition module, configured to acquire a plurality of target recommendation information according to the target operation position list; the target operation position list includes picture operation positions, topic operation positions, and random operation positions; An information recommendation module is configured to send the target operation position list and the plurality of target recommendation information to the client, so that the client recommends the plurality of target recommendation information according to the target operation position list.

7. A computer-readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the information recommendation method according to any one of claims 1 to 5 is implemented.

8. A server, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor executes the executable instructions so that the server executes the information recommendation method according to any one of claims 1 to 5.

Images