A method, apparatus, storage medium, and computer device for recommending virtual rooms.

Abstract

This application provides a virtual room recommendation method, apparatus, storage medium, and computer device. When a first user refreshes the virtual room recommendation page, the method first obtains at least one second user who has interacted with the first user in a historical period but has not followed each other, forming a second user set. Then, it filters out the second users currently in the virtual room from the second user set, forming a recommended user set. Next, it determines at least one target recommended user from the recommended user set based on the interaction between each second user and the first user. Finally, it obtains the room identifier of the virtual room where each target recommended user is located and updates the virtual room recommendation page using each room identifier, so that the first user can reunite and interact with the target recommended user who is online at the same time, promoting communication and understanding, and bringing the relationship between the two users closer, thereby improving the user experience.

Description

Technical Field

[0001] This application relates to the field of Internet communication technology, and in particular to a virtual room recommendation method, apparatus, storage medium, and computer equipment. Background Technology

[0002] With the development of internet technology, social networking platforms have become a mainstream way of making friends in modern social life. Their advantage lies in the fact that users can interact with other users from different regions and cultural backgrounds anytime, anywhere. After multiple interactions with strangers and reaching a deeper understanding, users can add each other as friends through mutual following, easily expanding their social circle. During the interaction, users can engage in one-on-one communication via private messages, or join virtual rooms with different themes for multi-person themed interactions.

[0003] After logging in, users often interact with strangers for the first time through virtual rooms and other means. However, the relevant technologies can only recommend virtual rooms based on social trends and interests, which is relatively limited. It is difficult for users to expand their social circles by interacting with strangers multiple times to build closer relationships. Summary of the Invention

[0004] The purpose of this application is to at least address one of the aforementioned technical shortcomings, particularly the limitation of existing technologies that can only recommend virtual rooms based on social trends and interests, resulting in a relatively singular recommendation direction and making it difficult for users to expand their social circles by interacting with strangers multiple times to build closer relationships.

[0005] This application provides a virtual room recommendation method, characterized in that the method includes:

[0006] When it is detected that the first user refreshes the virtual room recommendation page, the second user set corresponding to the first user is obtained. The second user set includes at least one second user who has interacted with the first user in the historical period but has not followed each other.

[0007] The second user currently in the virtual room is selected from the second user set to form a recommended user set;

[0008] Based on the interaction behavior between each second user and the first user in the recommended user set, at least one target recommended user is determined from the recommended user set;

[0009] Obtain the room identifier of the virtual room where each target recommended user is located, and update the virtual room recommendation page using each room identifier.

[0010] Optionally, the step of filtering out the second user currently in the virtual room from the second user set to form a recommended user set includes:

[0011] Obtain the online second users from the second user set, and filter out the second users currently in the virtual room from the online second users to form a recommended user set.

[0012] Optionally, determining at least one target recommended user from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set includes:

[0013] Based on the interaction behavior between each second user and the first user in the recommended user set, determine the interaction score corresponding to each second user;

[0014] At least one target recommended user is determined from the set of recommended users based on each interaction score.

[0015] Optionally, determining the interaction score for each second user based on the interaction behavior between each second user and the first user in the recommended user set includes:

[0016] Feature extraction is performed on the interaction behaviors of each second user and the first user in the recommended user set for the same interaction category, to obtain the feature value of the interaction behavior corresponding to each second user;

[0017] The corresponding scoring coefficient is determined based on the interaction category;

[0018] The scoring coefficients are used to score the feature values ​​of each interactive behavior to obtain the interaction score for each second user.

[0019] Optionally, determining at least one target recommended user from the recommended user set based on each interaction score includes:

[0020] Sort the interaction scores of each second user from highest to lowest to obtain the ranking results;

[0021] Based on the preset selection rules and the sorting results, at least one target recommended user is selected from the recommended user set.

[0022] Optionally, updating the virtual room recommendation page using each room identifier includes:

[0023] The recommendation order of each room identifier is sorted according to the user behavior corresponding to each target recommended user, resulting in a room sorting list;

[0024] The virtual room recommendation page is updated based on the room sorting list.

[0025] Optionally, the method further includes:

[0026] When it is detected that the first user interacts with other users, it is determined whether the other user is the second user in the second user set;

[0027] If so, then update the interaction behavior between the other users and the first user;

[0028] If not, then if the other users do not follow the first user, add the other users to the second user set.

[0029] This application also provides a virtual room recommendation device, including:

[0030] The second user acquisition module is used to acquire the second user set corresponding to the first user when the first user refreshes the virtual room recommendation page. The second user set includes at least one second user who has interacted with the first user in the historical period but has not followed each other.

[0031] The second user filtering module is used to filter out the second users currently in the virtual room from the second user set to form a recommended user set;

[0032] The recommended user determination module is used to determine at least one target recommended user from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set;

[0033] The recommendation page update module is used to obtain the room identifier of the virtual room where each target recommended user is located, and update the virtual room recommendation page using each room identifier.

[0034] This application also provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the virtual room recommendation method as described in any of the above embodiments.

[0035] This application also provides a computer device, including: one or more processors, and memory;

[0036] The memory stores computer-readable instructions, which, when executed by the one or more processors, perform the steps of the virtual room recommendation method as described in any of the above embodiments.

[0037] As can be seen from the above technical solutions, the embodiments of this application have the following advantages:

[0038] This application provides a virtual room recommendation method, apparatus, storage medium, and computer device. When a first user refreshes the virtual room recommendation page, a set of second users corresponding to the first user can be obtained first. This set of second users includes at least one second user who has interacted with the first user in a historical period but has not followed each other, ensuring that the first user has an initial interactive impression of the second users corresponding to the recommended virtual rooms. After obtaining the set of second users corresponding to the first user, the second users currently in the virtual room can be filtered from the set of second users to form a recommended user set, so that the first user can interact with the second users who are online at the same time in real time. Then, based on this recommended user set... The interaction behavior between each second user and the first user determines at least one target recommended user from the recommended user set. This allows us to understand the level of interaction between the two users and determine the target recommended user based on this level of interaction. This deepens the relationship between the first user and the target recommended user, increasing the likelihood of them following each other and becoming friends. Finally, we can obtain the room identifier of the virtual room where each target recommended user is located and update the virtual room recommendation page using these room identifiers. This allows the first user to reunite with the target recommended user who is also online and interact with them, promoting communication and understanding, bringing the two users closer together, and thus improving the user experience. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A flowchart illustrating a virtual room recommendation method provided in an embodiment of this application;

[0041] Figure 2 This is a schematic diagram of the structure of a virtual room recommendation device provided in an embodiment of this application;

[0042] Figure 3 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0044] With the development of internet technology, social networking platforms have become a mainstream way of making friends in modern social life. Their advantage lies in the fact that users can interact with other users from different regions and cultural backgrounds anytime, anywhere. After multiple interactions with strangers and reaching a deeper understanding, users can add each other as friends through mutual following, easily expanding their social circle. During the interaction, users can engage in one-on-one communication via private messages, or join virtual rooms with different themes for multi-person themed interactions.

[0045] After logging in, users often interact with strangers for the first time through virtual rooms and other means. However, the relevant technologies can only recommend virtual rooms based on social trends and interests, which is relatively limited. It is difficult for users to expand their social circles by interacting with strangers multiple times to build closer relationships.

[0046] Based on this, this application proposes the following technical solution, as detailed below:

[0047] In one embodiment, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating a virtual room recommendation method provided in an embodiment of this application. The present application provides a virtual room recommendation method, specifically including the following:

[0048] S110: When it is detected that the first user refreshes the virtual room recommendation page, obtain the set of second users corresponding to the first user. The set of second users includes at least one second user who has interacted with the first user in the historical period but has not followed each other.

[0049] In this step, after the first user logs on to the social platform, they can refresh the virtual room recommendation page on the social platform at any time to get the latest recommendation page. When the social platform detects that the first user refreshes the virtual room recommendation page, it can obtain the second user set corresponding to the first user, so as to select the target recommended user from the second user set and refresh the virtual room recommendation page according to the target recommended user.

[0050] It should be noted that the second user set in this application includes at least one second user who has interacted with the first user during the historical period but has not followed each other. The historical period refers to the duration between any point in time in the historical period and the point in time when the first user refreshes the virtual room page. The first user can obtain the start time of the historical period each time the recommendation page is refreshed by setting the duration of the historical period. Here, the historical period can be a week, a month, or a quarter, depending on the first user's usage habits.

[0051] Specifically, when the first user refreshes the virtual room recommendation page on the social platform, the system can search the database for the second user set corresponding to the first user based on the first user's characteristic information. The database on the social platform stores the second user set corresponding to each user in advance, and the social platform can update the second user set corresponding to any user after any user has a new interactive behavior.

[0052] Furthermore, when obtaining the second user set corresponding to the first user, the characteristic information of the first user can be obtained first. The characteristic information here can be information used to identify the first user, such as username, user account, user identification code, etc. In other words, the characteristic information is unique. After obtaining the characteristic information of the first user, the characteristic information can be searched in the corresponding database on the social platform to obtain the corresponding second user set.

[0053] S120: Select the second user currently in the virtual room from the second user set to form a recommended user set.

[0054] In this step, after obtaining the set of second users corresponding to the first user through step S110, the second users in the set of second users can be filtered out to form a recommended user set, so that the first user can interact with the second users who are online at the same time.

[0055] It is understood that the virtual room in this application refers to a themed room on a social platform used for multiple users to interact. The themed room can be a game room, a music room, a pet room, or other themes. Different themed virtual rooms have different functions. When a user goes online, they can choose to create a new virtual room and wait for other users to join, or they can choose to enter a virtual room that has been created by other users. When all users in a virtual room leave the room, the virtual room will be disbanded.

[0056] For example, in the game room, users can choose to invite users of a specific game rank to team up and play games together. During the game, they can communicate strategically through the room's voice function. In the music room, users can freely choose songs and interact with other users through methods such as two or more people going on mic. In the pet room, users can interact through different sections such as photo sharing, story sharing, and Q&A mutual assistance.

[0057] Specifically, the online status of each second user in the second user set varies, specifically whether they are online or offline. Online second users can be in the lobby or in a virtual room on the social platform. When online second users are in the lobby, they can interact via private messages, etc. When online second users are in a virtual room, they can use the virtual room's microphone function for one-on-one or group interaction. Furthermore, the first user can filter out the second users currently in the virtual room to further engage with them through themed interactions within the virtual room, thereby strengthening the relationship between them.

[0058] S130: Determine at least one target recommended user from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set.

[0059] In this step, after obtaining the recommended user set through step S120, the interaction behavior between each second user and the first user in the recommended user set can be obtained from the database corresponding to the social platform, and at least one target recommended user can be determined from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set.

[0060] It is understandable that the first user and the second user can have various types of interactive behaviors. For example, the first user can interact with the second user through private messaging, or by liking and commenting on the second user's platform updates, or by entering a virtual room to go on stage or chat together. The types of interactive behaviors between the two users in this application can be added or removed according to the specific functions of the social platform, and no restrictions are imposed here.

[0061] Specifically, the interaction behavior between the first user and the second user can reveal the degree of interaction between them. Based on this interaction level, a target recommended user can be identified, thereby deepening the relationship between the first user and the target recommended user and increasing the likelihood of them following each other and becoming friends. Since the first user and the second user in the recommended user set have different interaction habits and use different interaction categories, the target recommended user identified from the recommended user set will also be different under different interaction categories.

[0062] Furthermore, when determining the target recommended user, the first user can pre-set the interaction category of the interaction behavior. This can be done by selecting one interaction category to obtain the corresponding interaction behavior, or by selecting interaction behaviors under multiple interaction categories. Then, based on the interaction behavior corresponding to each second user, at least one target recommended user can be determined from the recommended user set.

[0063] S140: Obtain the room identifier of the virtual room where each target recommended user is located, and update the virtual room recommendation page using each room identifier.

[0064] In this step, after determining at least one target recommended user through step S130, the room identifier of the virtual room where each target recommended user is located can be obtained, and the virtual room recommendation page can be updated using each room identifier. The first user can enter the corresponding virtual room through the room identifier.

[0065] It is understood that the room identifier in this application is the entrance channel for the first user to enter the virtual room. The room identifier includes the room ID and the user information of the second user in the virtual room. The room ID is a randomly generated string when the virtual room is created, which is used to identify the identity and location of the virtual room. The user information is used to inform the first user of the relevant information of the corresponding second user in the virtual room, so that the first user can select the virtual room he / she wants to enter based on the user information, and then meet and interact with the corresponding second user in the virtual room again. Through multiple interactions, the relationship between the two users is brought closer, thereby improving the user experience.

[0066] Specifically, after obtaining the room identifier of the virtual room where each target recommended user is located, the recommendation order of each room identifier can be arranged first, and then each room identifier can be filled into the corresponding recommendation area of ​​the recommendation page in sequence to complete the update of the virtual room recommendation page. It should be noted that the virtual room recommendation page can have different partition layouts, and the method of updating the virtual room recommendation page using each room identifier in this application is used under different partition layouts.

[0067] In the above embodiments, when it is detected that the first user refreshes the virtual room recommendation page, the second user set corresponding to the first user can be obtained first. The second user set includes at least one second user who has interacted with the first user in the historical period but has not followed each other. This ensures that the first user has an initial interactive impression of the second user corresponding to the recommended virtual room. After obtaining the second user set corresponding to the first user, the second users currently in the virtual room can be filtered from the second user set to form a recommended user set, so that the first user can interact with the second users who are online at the same time in real time. Then, based on the interaction behavior between each second user and the first user in the recommended user set, at least one target recommended user can be determined from the recommended user set. In this way, the interaction behavior between the first user and the second user can be used to understand the degree of interaction between the two users, and then the target recommended user can be determined based on the degree of interaction, thereby deepening the relationship chain between the first user and the target recommended user and increasing the possibility of following each other and becoming friends. Finally, the room identifier of the virtual room where each target recommended user is located can be obtained, and the virtual room recommendation page can be updated using each room identifier, so that the first user can meet and interact with the target recommended user who is online at the same time again, promote communication and understanding, bring the relationship chain between the two users closer, and thus improve the user experience.

[0068] In one embodiment, step S120, which involves filtering the second users currently in the virtual room from the second user set to form a recommended user set, may include:

[0069] S121: Obtain the online second users from the second user set, and filter out the second users currently in the virtual room from the online second users to form a recommended user set.

[0070] In this embodiment, when the first user goes online, the social platform can monitor the online status of each second user in the set of second users corresponding to the first user. When it detects that the first user refreshes the virtual room recommendation page, it can filter out the online second users based on the real-time online status of the set of second users, so that the first user can interact with the online second users in real time. Then, it can filter out the second users in the virtual room from the online second users, which serves as the basic basis for refreshing the virtual room recommendation page.

[0071] Furthermore, when the online status of a second user in the second user set changes, the virtual room recommendation page is also refreshed. The online status here can be the second user going online or offline, or the second user entering or leaving the virtual room. For example, if a second user in a virtual room leaves the virtual room, the social platform removes the second user from the recommended user set. Conversely, if a second user enters the virtual room, the social platform adds the second user to the recommended user set and refreshes the room recommendation page.

[0072] In one embodiment, step S130, which involves determining at least one target recommended user from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set, may include:

[0073] S131: Determine the interaction score for each second user based on the interaction behavior between each second user and the first user in the recommended user set.

[0074] S132: Determine at least one target recommended user from the set of recommended users based on each interaction score.

[0075] In this embodiment, the social platform can determine the interaction type of the target recommended user based on the interaction type set in advance by the first user, and obtain the interaction behavior between each second user and the first user corresponding to the interaction type, thereby determining the interaction score of each second user. Then, at least one target recommended user can be determined from the set of recommended users based on each interaction score.

[0076] In this application, the degree of interaction between the second user and the first user can be determined based on the interaction score. The higher the interaction score, the more interaction the second user has with the first user, the deeper the interaction, and the closer the relationship. The higher the interaction score, the less interaction the second user has with the first user, the shallower the interaction, and the more distant the relationship.

[0077] Furthermore, once the interaction score for each second user is determined, the interaction scores can be sorted from high to low. The interaction scores can then be filtered from the recommended user set to select the second users with higher interaction scores as target recommended users. In this way, the two users can reconnect and interact again based on their previous interactions, making the interaction process more harmonious and increasing the likelihood of them following each other and becoming friends.

[0078] In one embodiment, step S131, which determines the interaction score for each second user based on the interaction behavior between each second user and the first user in the recommended user set, may include:

[0079] S313: Extract features from the interaction behaviors of each second user and the first user in the recommended user set for the same interaction category, and obtain the feature value of the interaction behavior corresponding to each second user.

[0080] S312: Determine the corresponding scoring coefficient based on the interaction category.

[0081] S313: Use scoring coefficients to score the feature values ​​of each interactive behavior to obtain the interaction score for each second user.

[0082] In this embodiment, when determining the interaction score for each second user, feature extraction can be performed on the interaction behavior between each second user and the first user in the recommended user set to obtain the feature value of the interaction behavior for each second user. Then, the corresponding scoring coefficient can be determined according to the interaction category corresponding to the interaction behavior, so as to adjust the interaction scores between different second users to an appropriate range of values. Finally, the feature value of each interaction behavior can be scored using the scoring coefficient to obtain the interaction score for each second user.

[0083] Specifically, different methods are used to extract feature values ​​for different interaction categories. For example, when the interaction category is private messaging, the number of chat records can be used as a feature value. Here, the number of chat records can be the total number of interactions between the two parties or the number of responses from the first user alone. When the interaction category is room interaction, the duration of time both parties are on the microphone can be used as a feature value. Other methods that can achieve feature extraction for different interaction types in this application can all be considered as preferred solutions in this application, and no restrictions are imposed here.

[0084] Understandably, because the level of interaction between the first user and each of the second users is different, there may be a large difference in the amount of interaction behavior under the same type, which increases the scoring calculation pressure of the social platform. Users also cannot intuitively compare the level of interaction with each of the second users. Therefore, after extracting the feature values ​​corresponding to each second user, the scoring coefficient can be used to suppress the feature values ​​with larger magnitudes and adjust the interaction score to an appropriate range.

[0085] Furthermore, this application does not limit the number of interaction types corresponding to the interactive behavior. One, two, or all can be selected. When there are multiple interaction types corresponding to the interactive behavior in this application, the feature value of each interaction type of the second user can be extracted separately. Then, the feature value of each feature value of the second user is summed, and the summation result is used as the feature value of the interactive behavior.

[0086] In one embodiment, determining at least one target recommended user from the recommended user set based on each interaction score in step S132 may include:

[0087] S321: Sort the interaction scores of each second user from high to low to obtain the sorting results.

[0088] S322: Based on the preset selection rules and sorting results, select at least one target recommended user from the recommended user set.

[0089] In this embodiment, after obtaining the interaction score corresponding to each second user, the interaction scores of each second user can be sorted from high to low to obtain the sorting result, so as to determine the number of users to be selected according to the preset selection rules, and then filter at least one target recommended user from the recommended user set according to the number of selected users and the sorting result. The social platform selects the target recommended user in descending order of the sorting result by default.

[0090] Specifically, the preset selection rules in this application can be based on a score threshold or on the layout of the recommendation page. When selecting based on a score threshold, second users with low interaction scores and lacking recommendation value can be eliminated, and second users with interaction scores higher than the score threshold can be selected as target recommended users. When selecting based on the layout of the recommendation page, the number of locations that can be used to recommend virtual rooms can be determined based on the layout of the recommendation page, and second users matching the number of locations can be selected as target recommended users from high to low according to the sorting results.

[0091] For example, if a social platform's recommendation page can recommend ten virtual rooms, then the ten second users with the highest interaction scores can be selected from the set of recommended users as target recommended users. If the number of second users who meet the recommendation criteria is less than the number of recommendation positions on the recommendation page, then the remaining recommendation positions will be empty.

[0092] In one embodiment, updating the virtual room recommendation page using each room identifier in step S140 may include:

[0093] S141: Sort the recommendation order of each room identifier according to the user behavior corresponding to each target recommended user, and obtain the room sorting list.

[0094] S142: Update the virtual room recommendation page based on the room sorting list.

[0095] In this embodiment, after obtaining each room identifier, the recommendation order of each room identifier can be sorted according to the user behavior corresponding to each target recommended user to obtain a room sorting list. In other words, the recommendation order of each room identifier can be sorted according to the interaction score of each target recommended user to obtain a room sorting list, so as to update the virtual room recommendation page according to the room sorting list.

[0096] Furthermore, the recommendation order of each room icon is consistent with the interaction score ranking of each target recommended user, and the virtual room recommendation page has a reunion icon, indicating that the recommendation page is recommended to bring closer the relationship chain with the second user who has interacted but has not followed each other. Each room icon on the recommendation page is marked with a room ID and the user information of the second user in the virtual room. The first user can directly understand the information of the corresponding virtual room through the room icon so as to select the virtual room they want to enter.

[0097] Furthermore, when the first user enters the corresponding virtual room by clicking the room icon, the room pages of the first user and the second user in the virtual room will simultaneously display the interaction time, location, and behavior of the last encounter between the two users, as well as the follow button, in order to strengthen the relationship between the two users.

[0098] In one embodiment, the virtual room recommendation method may further include:

[0099] S150: When it is detected that the first user interacts with other users, determine whether the other user is the second user in the second user set.

[0100] S160: If so, update the interaction behavior between other users and the first user.

[0101] S170: If not, add other users to the second user set if they do not follow the first user.

[0102] In this embodiment, while the first user is online on the social platform, they can interact with other users who are not friends. Here, "non-friends" refers to users who do not follow each other. Interacting with other users can be interacting with the second user again, or it can be interacting with a stranger for the first time. If the other user is the second user in the second user set, the interaction behavior between the other user and the first user can be updated. If the other user is a stranger interacting for the first time, the other user can be added to the second user set.

[0103] Furthermore, after adding other users who interacted with the first user to the second user set, the interaction behavior between the first user and these other users can be stored. When the interaction behavior of the second user in the second user set corresponding to the first user changes, the social platform can synchronously update the interaction scores of each second user and refresh the virtual room recommendation page based on the updated interaction scores.

[0104] Furthermore, once the first user and the second user in the second user set follow each other and become friends, the second user can be removed from the second user set, and then the virtual room recommendation page can be refreshed. During the process of the first user and the second user following each other, the second user can follow the first user if the first user has already followed the second user, or the first user can follow the second user if the second user has already followed the first user.

[0105] The virtual room recommendation device provided in the embodiments of this application is described below. The virtual room recommendation device described below can be referred to in correspondence with the virtual room recommendation method described above.

[0106] In one embodiment, such as Figure 2 As shown, Figure 2 The present application provides a schematic diagram of a virtual room recommendation device according to an embodiment of the present application. The present application also provides a virtual room recommendation device, including a second user acquisition module 210, a second user filtering module 220, a recommended user determination module 230, and a recommendation page update module 240, specifically comprising the following:

[0107] The second user acquisition module 210 is used to acquire the second user set corresponding to the first user when the first user refreshes the virtual room recommendation page. The second user set includes at least one second user who has interacted with the first user in the historical period but has not followed each other.

[0108] The second user filtering module 220 is used to filter out the second users currently in the virtual room from the second user set to form a recommended user set.

[0109] The recommended user determination module 230 is used to determine at least one target recommended user from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set.

[0110] The recommendation page update module 240 is used to obtain the room identifier of the virtual room where each target recommended user is located, and to update the virtual room recommendation page using each room identifier.

[0111] In this embodiment, when the first user refreshes the virtual room recommendation page, the set of second users corresponding to the first user can be obtained first. This set of second users includes at least one second user who has interacted with the first user in the historical time period but has not followed each other. This ensures that the first user has an initial interactive impression of the second users corresponding to the recommended virtual room. After obtaining the set of second users corresponding to the first user, the second users currently in the virtual room can be filtered from the set of second users to form a set of recommended users. This allows the first user to interact with the second users who are online at the same time in real time. Then, based on the interaction behavior between each second user and the first user in the set of recommended users, at least one target recommended user can be determined from the set of recommended users. This allows the interaction behavior between the first user and the second user to understand the degree of interaction between the two users, and then the target recommended user can be determined based on the degree of interaction. This deepens the relationship chain between the first user and the target recommended user, increases the possibility of following each other and becoming friends. Finally, the room identifier of the virtual room where each target recommended user is located can be obtained, and the virtual room recommendation page can be updated using each room identifier. This allows the first user to reunite with the target recommended user who is online at the same time and interact with them, promotes communication and understanding, and brings the relationship chain between the two users closer, thereby improving the user experience.

[0112] In one embodiment, the second user screening module 220 may include:

[0113] The second user filtering submodule is used to obtain the online second users in the second user set, and filter out the second users currently in the virtual room from the online second users to form a recommended user set.

[0114] In one embodiment, the user recommendation module 230 may include:

[0115] The interaction score determination submodule is used to determine the interaction score for each second user based on the interaction behavior between each second user and the first user in the recommended user set.

[0116] The recommended user determination submodule is used to determine at least one target recommended user from the recommended user set based on each interaction score.

[0117] In one embodiment, the interactive score determination submodule may include:

[0118] The feature extraction unit is used to extract features from the interaction behaviors of each second user and the first user in the recommended user set for the same interaction category, and obtain the feature value of the interaction behavior corresponding to each second user.

[0119] The coefficient determination unit is used to determine the corresponding scoring coefficient based on the interaction category.

[0120] The score determination unit is used to score the feature values ​​of each interactive behavior using scoring coefficients to obtain the interaction score for each second user.

[0121] In one embodiment, recommending that the user determine the submodule may include:

[0122] The score sorting unit is used to sort the interaction scores of each second user from high to low to obtain the sorting result.

[0123] The recommended user determination unit is used to select at least one target recommended user from the recommended user set according to preset selection rules and sorting results.

[0124] In one embodiment, the recommendation page update module 240 may include:

[0125] The room sorting submodule is used to sort the recommendation order of each room identifier according to the user behavior corresponding to each target recommended user, and obtain the room sorting list.

[0126] The Recommendation Page Update submodule is used to update the virtual room recommendation page based on the room sorting list.

[0127] In one embodiment, the virtual room recommendation device may further include:

[0128] The user judgment module is used to determine whether other users are the second users in the second user set when the interaction behavior of the first user with other users is detected.

[0129] The interaction behavior update module is used to update the interaction behavior between other users and the first user if the condition is met.

[0130] The user set update module is used to add other users to the second user set if, otherwise, other users do not follow each other with the first user.

[0131] In one embodiment, this application also provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the virtual room recommendation method as described in any of the above embodiments.

[0132] In one embodiment, this application also provides a computer device storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the virtual room recommendation method as described in any of the above embodiments.

[0133] Indicatively, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the internal structure of a computer device 300 provided in an embodiment of this application. The computer device 300 can be provided as a server. (Refer to...) Figure 3 The computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by memory 301 for storing instructions, such as application programs, that can be executed by the processing component 302. The application programs stored in memory 301 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 302 is configured to execute instructions to perform the virtual room recommendation method of any of the above embodiments.

[0134] The computer device 300 may also include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate on an operating system stored in memory 301, such as Windows Server™, Mac OS X™, Unix™, Linux™, Free BSD™, or similar.

[0135] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0136] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0137] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0138] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A virtual room recommendation method, characterized in that, The method includes: When it is detected that the first user refreshes the virtual room recommendation page, the second user set corresponding to the first user is obtained. The second user set includes at least one second user who has interacted with the first user in the historical period but has not followed each other. The second user currently in the virtual room is selected from the second user set to form a recommended user set; Based on the interaction behavior between each second user and the first user in the recommended user set, at least one target recommended user is determined from the recommended user set; Obtain the room identifier of the virtual room where each target recommended user is located, and update the virtual room recommendation page using each room identifier; When it is detected that the first user interacts with other users, it is determined whether the other user is the second user in the second user set; If so, then update the interaction behavior between the other users and the first user; If not, then if the other users do not follow the first user, add the other users to the second user set.

2. The virtual room recommendation method according to claim 1, characterized in that, The step of selecting the second user currently in the virtual room from the second user set to form a recommended user set includes: Obtain the online second users from the second user set, and filter out the second users currently in the virtual room from the online second users to form a recommended user set.

3. The virtual room recommendation method according to claim 1, characterized in that, The step of determining at least one target recommended user from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set includes: Based on the interaction behavior between each second user and the first user in the recommended user set, determine the interaction score corresponding to each second user; At least one target recommended user is determined from the set of recommended users based on each interaction score.

4. The virtual room recommendation method according to claim 3, characterized in that, The step of determining the interaction score for each second user based on the interaction behavior between each second user and the first user in the recommended user set includes: Feature extraction is performed on the interaction behaviors of each second user and the first user in the recommended user set for the same interaction category, to obtain the feature value of the interaction behavior corresponding to each second user; The corresponding scoring coefficient is determined based on the interaction category; The scoring coefficients are used to score the feature values ​​of each interactive behavior to obtain the interaction score for each second user.

5. The virtual room recommendation method according to claim 3, characterized in that, The step of determining at least one target recommended user from the recommended user set based on each interaction score includes: Sort the interaction scores of each second user from highest to lowest to obtain the ranking results; Based on the preset selection rules and the sorting results, at least one target recommended user is selected from the recommended user set.

6. The virtual room recommendation method according to claim 1, characterized in that, The step of updating the virtual room recommendation page using each room identifier includes: The recommendation order of each room identifier is sorted according to the user behavior corresponding to each target recommended user, resulting in a room sorting list; The virtual room recommendation page is updated based on the room sorting list.

7. A virtual room recommendation device, characterized in that, include: The second user acquisition module is used to acquire the second user set corresponding to the first user when the first user refreshes the virtual room recommendation page. The second user set includes at least one second user who has interacted with the first user in the historical period but has not followed each other. The second user filtering module is used to filter out the second users currently in the virtual room from the second user set to form a recommended user set; The recommended user determination module is used to determine at least one target recommended user from the recommended user set based on the interaction behavior between each second user and the first user in the recommended user set; The recommendation page update module is used to obtain the room identifier of the virtual room where each target recommended user is located, and update the virtual room recommendation page using each room identifier; The user judgment module is used to determine whether the other user is the second user in the second user set when the first user is detected to be interacting with other users. The interaction behavior update module is used to update the interaction behavior between the other users and the first user if the condition is met. The user set update module is used to add the other users to the second user set if, no, the other users do not follow each other with the first user.

8. A storage medium, characterized in that: The storage medium stores computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the virtual room recommendation method as described in any one of claims 1 to 6.

9. A computer device, characterized in that, include: One or more processors, and memory; The memory stores computer-readable instructions that, when executed by the one or more processors, perform the steps of the virtual room recommendation method as described in any one of claims 1 to 6.

Images