Vertical data construction method, device, electronic device and storage medium

Abstract

The present disclosure is about a method, device, electronic device and storage medium for constructing vertical category data, which solves the problem of poor real-time performance and low accuracy of constructed vertical category data in related technologies. The method includes: obtaining first vertical category data corresponding to a target vertical category identifier from a metadata database table, the metadata database table is used to store vertical category data corresponding to multiple vertical category identifiers, the multiple vertical category identifiers include a target vertical category identifier, and the first vertical category data includes multiple user accounts; when a to-be-processed user account that meets a first preset condition is generated, according to the to-be-processed user account and the multiple user accounts included in the first vertical category data, a target user account that meets a second preset condition in a live broadcast state is determined; second vertical category data including the target user account is constructed, the second vertical category data corresponds to the target vertical category identifier; when a retrieval instruction for the target vertical category identifier sent by the electronic device is received, the user account to be pushed to the electronic device is determined from the second vertical category data.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to methods, devices, electronic devices and storage media for constructing vertical data. Background Art

[0002] In the related art, vertical category data constructed based on user account data with the same or similar attributes (such as anchor user account data) is stored in a metadata database table. When the user account data in a certain vertical category data needs to be updated (such as adding or deleting anchor account data), it is necessary to first modify the user account data in the metadata database table, and then run the modified metadata database table, so that the updated vertical category data of the vertical category can be obtained according to the updated user account data, and then it can be effectively used, such as selecting data from the vertical category data of a certain vertical category for pushing to the user account.

[0003] In the above method of updating user account data, since the metadata database table takes a long time to take effect, the updated user account data cannot be applied to the vertical data in a timely manner, resulting in poor real-time performance and low accuracy of the vertical data. Summary of the invention

[0004] The present disclosure provides a method, device, electronic device and storage medium for constructing vertical data, so as to at least solve the problems of poor real-time performance and low accuracy of vertical data constructed in related technologies. The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, a method for constructing vertical category data is provided, the method comprising: obtaining first vertical category data corresponding to a target vertical category identifier from a metadata database table, the metadata database table being used to store vertical category data corresponding to multiple vertical category identifiers, the multiple vertical category identifiers including a target vertical category identifier, and the first vertical category data including multiple user accounts; when a user account to be processed that meets a first preset condition is generated, determining a target user account that meets a second preset condition in a live broadcast state based on the user account to be processed and the multiple user accounts included in the first vertical category data; constructing second vertical category data containing the target user account, the second vertical category data corresponding to the target vertical category identifier; when a retrieval instruction for the target vertical category identifier sent by an electronic device is received, determining the user account to be pushed to the electronic device from the second vertical category data.

[0006] In a possible implementation, when a user account to be processed that meets the first preset condition is generated, including: when a user account to be deleted whose vertical category identifier is changed from a target vertical category identifier to another vertical category identifier is generated, and / or when a user account to be added whose vertical category identifier is to be changed to a target vertical category identifier is generated; according to the user account to be processed and the multiple user accounts included in the first vertical category data, determining a target user account that meets the second preset condition in the live broadcast state includes:

[0007] The user account to be added is added to the multiple user accounts, and / or the user account to be deleted is deleted from the multiple user accounts to obtain a first category of user accounts; based on the first category of user accounts, a target user account that meets the second preset condition in the live broadcast state is determined.

[0008] In another possible implementation, based on the first category of user accounts, a target user account that meets the second preset condition in the live broadcast state is determined, including: from the user accounts in the live broadcast state, determining the user account whose live broadcast content matches the target vertical category identifier to obtain the second category of user accounts; determining a first candidate user account that meets the second preset condition from the first category of user accounts, and determining a second candidate user account that meets the second preset condition from the second category of user accounts; determining the target user account based on the first candidate user account and the second candidate user account.

[0009] In another possible implementation, determining the target user account based on the first candidate user account and the second candidate user account includes: when there are duplicate user accounts between the first candidate user account and the second candidate user account, determining the duplicate user account as the target user account; when there are no duplicate user accounts between the first candidate user account and the second candidate user account, determining the first candidate user account or the second candidate user account as the target user account.

[0010] In another possible implementation, each user account corresponds to at least one of the number of virtual resources, the total number of associated user accounts, and the current number of online viewers; the second preset condition is that at least one of the number of virtual resources, the total number of associated user accounts, and the current number of online viewers meets the threshold condition.

[0011] In another possible implementation, each target user account corresponds to an account identifier and at least one live broadcast room identifier; constructing second vertical category data containing the target user account includes: associating the account identifier and live broadcast room identifier corresponding to each target user account with the target vertical category identifier, to obtain the second vertical category data including the target user account and indexed by the target vertical category identifier.

[0012] In another possible implementation, the method further includes: when the second vertical category data has been constructed and the target user account is updated, updating the second vertical category data according to the updated target user account.

[0013] In another possible implementation, when a retrieval instruction for a target vertical category identifier is received from an electronic device, a user account to be pushed to the electronic device is determined from the second vertical category data, including: when a retrieval instruction for multiple target vertical category identifiers is received from an electronic device, the account characteristics of the user account corresponding to the electronic device are obtained, and the correlation between the account characteristics and each target vertical category identifier is determined; according to the correlation between the account characteristics and each target vertical category identifier, the push priority of each target vertical category identifier is determined; from the second vertical category data corresponding to each target vertical category identifier, the user account to be pushed corresponding to the target vertical category identifier is determined; according to the push priority of each target vertical category identifier and the user account to be pushed corresponding to each target vertical category identifier, the user account is pushed to the electronic device.

[0014] In another possible implementation, the above method also includes: when a third type of user account is generated whose vertical category identifier is to be changed to a new vertical category identifier and is in a live broadcast state, third vertical category data containing the third type of user account is constructed according to the third type of user account, the third vertical category data corresponds to the new vertical category identifier, and the new vertical category identifier is not included in the multiple vertical category identifiers; when a retrieval instruction for the new vertical category identifier sent by the electronic device is received, the user account to be pushed to the electronic device is determined from the third vertical category data.

[0015] According to a second aspect of an embodiment of the present disclosure, a vertical category data construction device is provided, which includes: an acquisition unit, configured to execute acquisition of first vertical category data corresponding to a target vertical category identifier from a metadata database table, the metadata database table being used to store vertical category data corresponding to multiple vertical category identifiers, the multiple vertical category identifiers including the target vertical category identifier, and the first vertical category data including multiple user accounts; a determination unit, configured to execute, when a user account to be processed that meets a first preset condition is generated, determine the target user account that meets a second preset condition in a live broadcast state based on the user account to be processed and multiple user accounts of the first vertical category data; a construction unit, configured to execute construction of second vertical category data containing the target user account, the second vertical category data corresponding to the target vertical category identifier; a push unit, configured to execute, when a retrieval instruction for the target vertical category identifier sent by the electronic device is received, determine the user account to be pushed to the electronic device from the second vertical category data.

[0016] In a possible implementation, when a user account to be processed that meets the first preset condition is generated, it includes: when a user account to be deleted is generated whose vertical category identifier is changed from a target vertical category identifier to another vertical category identifier, and / or, when a user account to be added is generated whose vertical category identifier is to be changed to a target vertical category identifier; a determination unit is configured to specifically execute: adding the user account to be added to multiple user accounts, and / or, deleting the user account to be deleted from multiple user accounts to obtain a first type of user account; based on the first type of user account, determining a target user account that meets the second preset condition in the live broadcast state.

[0017] In another possible implementation, the determination unit is configured to specifically perform: determine, from user accounts in live broadcast state, user accounts whose live broadcast content matches the target vertical category identifier to obtain a second category of user accounts; determine a first candidate user account that meets the second preset condition from the first category of user accounts, and determine a second candidate user account that meets the second preset condition from the second category of user accounts; determine the target user account based on the first candidate user account and the second candidate user account.

[0018] In another possible implementation, the determination unit is configured to specifically perform: when there are duplicate user accounts between the first candidate user account and the second candidate user account, determining the duplicate user account as the target user account; when there are no duplicate user accounts between the first candidate user account and the second candidate user account, determining the first candidate user account or the second candidate user account as the target user account.

[0019] In another possible implementation, each user account corresponds to at least one of the number of virtual resources, the total number of associated user accounts, and the current number of online viewers; the second preset condition is that at least one of the number of virtual resources, the total number of associated user accounts, and the current number of online viewers meets the threshold condition.

[0020] In another possible implementation, each target user account corresponds to an account identifier and at least one live broadcast room identifier; the construction unit is configured to specifically execute: associating the account identifier and live broadcast room identifier corresponding to each target user account with the target vertical category identifier to obtain second vertical category data including the target user account and indexed by the target vertical category identifier.

[0021] In another possible implementation, the determination unit is further configured to specifically execute: when the second vertical category data has been constructed and the target user account is updated, updating the second vertical category data according to the updated target user account.

[0022] In another possible implementation, the push unit is configured to specifically perform the following: when receiving a retrieval instruction for multiple target vertical category identifiers sent by the electronic device, obtaining the account characteristics of the user account corresponding to the electronic device, and determining the correlation between the account characteristics and each target vertical category identifier; determining the push priority of each target vertical category identifier based on the correlation between the account characteristics and each target vertical category identifier; determining the user account to be pushed corresponding to the target vertical category identifier from the second vertical category data corresponding to each target vertical category identifier; and pushing the user account to the electronic device based on the push priority of each target vertical category identifier and the user account to be pushed corresponding to each target vertical category identifier.

[0023] In another possible implementation, the device is further configured to execute: when a third type of user account whose vertical category identifier is to be changed to a new vertical category identifier and is in a live broadcast state is generated, third vertical category data including the third type of user account is constructed according to the third type of user account, the third vertical category data corresponds to the new vertical category identifier, and the new vertical category identifier is not included in the multiple vertical category identifiers;

[0024] When a search instruction for a new vertical category identifier is received from an electronic device, a user account to be pushed to the electronic device is determined from the third vertical category data.

[0025] According to the third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor and a memory for storing processor executable instructions; wherein the processor is configured to execute executable instructions to implement a vertical data construction method as in the first aspect and any possible implementation manner thereof.

[0026] According to the fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute a vertical category data construction method such as the first aspect and any possible implementation manner thereof; or when instructions in the computer-readable storage medium are executed by a vertical category data construction device, the vertical category data construction device is enabled to execute a vertical category data construction method such as the first aspect and any possible implementation manner thereof.

[0027] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program or instructions, and the computer program or instructions are executed by a processor as the vertical data construction method of the first aspect and any possible implementation manner thereof.

[0028] The technical solution provided by the embodiment of the present disclosure brings at least the following beneficial effects: the target vertical category identifier obtained from the metadata database table corresponds to multiple user accounts of the first vertical category data. And according to the first preset condition, the user account to be processed that meets the vertical category data construction requirements is obtained; then, by the above-mentioned user account to be processed and multiple user accounts, the target user account in the live broadcast state and meeting the second preset condition is determined, thereby constructing the second vertical category data of the target vertical category identifier to which the target user account belongs, so that when a search instruction for the target vertical category identifier is received, the constructed second vertical category data is pushed.

[0029] Through the vertical category data construction method of the present application, it is possible to construct vertical category data in real time according to the needs, that is, when the to-be-processed user account data that meets the first preset condition is generated, the vertical category data, that is, the second vertical category data, can be constructed in real time, and the latest constructed vertical category data is always used as the data source of the user account pushed to the electronic device. It can be seen that this vertical category data construction method has high real-time and flexibility. Due to its high real-time and flexibility, user accounts can be pushed to electronic devices more accurately. For example, when an electronic device retrieves a food anchor, the anchor to be pushed to the electronic device is selected from the latest food vertical category, so it can avoid pushing the anchor whose attributes have changed to the electronic device.

[0030] In addition, since the user accounts in the latest constructed vertical data are all in live broadcast status, the user accounts pushed to electronic devices must be users who are currently broadcasting live, which can improve the user experience.

[0031] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0033] Figure 1 is a schematic diagram of an electronic device according to an exemplary embodiment;

[0034] Figure 2 is a flowchart of a method for constructing vertical data according to an exemplary embodiment;

[0035] Figure 3 is a schematic diagram of a vertical data construction process according to an exemplary embodiment;

[0036] Figure 4 is a schematic diagram of another vertical data construction process according to an exemplary embodiment;

[0037] Figure 5 is a schematic diagram showing a vertical data index according to an exemplary embodiment;

[0038] Figure 6 It is a block diagram of a vertical data construction device according to an exemplary embodiment. DETAILED DESCRIPTION

[0039] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0041] Before introducing in detail the vertical data construction method provided by the embodiment of the present disclosure, a brief introduction is first given to the implementation environment and application scenarios involved in the embodiment of the present disclosure.

[0042] First, the application scenarios involved in the present disclosure are briefly introduced.

[0043] In the related art, vertical data constructed based on user account data with the same or similar attributes are stored in a metadata database table. When the user account data in a vertical data category needs to be updated (such as adding or deleting anchor account data), it is necessary to first modify the user account data in the metadata database table, and then run the modified metadata database table, so that the updated vertical data of the vertical category can be obtained based on the updated user account data, and then it can be effectively utilized. Among them, the metadata database table can be a Hive table, which is a data warehouse tool that can map structured data files to a database table and provide complete query functions.

[0044] Vertical category refers to a vertical field. In this disclosure, vertical category data is a limitation of groups belonging to the same vertical field, or it can be understood that a vertical category data includes user account data in a vertical field, or in other words, a vertical category data includes user account data with the same or similar attributes.

[0045] In the above method of updating user account data, since the metadata database table takes a long time to take effect, the updated user account data cannot be applied to the vertical data in a timely manner, resulting in poor real-time performance and low accuracy of the vertical data.

[0046] In response to the above problems, the present disclosure provides a method for constructing vertical category data, wherein the target vertical category identifier obtained from the metadata database table corresponds to multiple user accounts of the first vertical category data. And according to the first preset condition, the user account to be processed that meets the vertical category data construction requirements is obtained; then, by determining the target user account in the live broadcast state and meeting the second preset condition through the above-mentioned user account to be processed and multiple user accounts, the second vertical category data of the target vertical category identifier to which the target user account belongs is constructed, so that when a search instruction for the target vertical category identifier is received, the constructed second vertical category data can be pushed.

[0047] Through the vertical category data construction method provided by the present disclosure, when a pending user account that needs to be processed and needs to be constructed for vertical category data is generated, the pending user account and multiple user accounts with the same target vertical category identifier in the metadata database table are directly processed to obtain the second vertical category data that meets the real-time construction requirements, so that the pushed second vertical category data can more accurately meet the user account requirements, avoiding the problem in the related art that when the vertical category data is obtained by updating the user account in the metadata database table, the vertical category data is pushed before it is updated due to the long update time when the vertical category data changes, thereby causing the pushed vertical category data to be inaccurate. Therefore, the present disclosure constructs vertical category data, i.e., the second vertical category data, in real time according to the vertical category construction requirements generated in real time, that is, when a pending user account that meets the first preset condition is generated, and the latest constructed vertical category data is always used as the data source of the user account pushed to the electronic device. It can be seen that this vertical category data construction method has high real-time and flexibility.

[0048] Due to its high real-time and flexibility, it can push user accounts to electronic devices more accurately. For example, when an electronic device searches for a food anchor, it selects the anchor to be pushed to the electronic device from the latest food vertical category, thus avoiding pushing anchors whose vertical category attributes have changed to the electronic device.

[0049] In addition, since the user accounts in the latest constructed vertical data are all in live broadcast status, the user accounts pushed to electronic devices must be users who are currently broadcasting live, which can improve the user experience.

[0050] Next, the implementation environment (implementation architecture) involved in the present disclosure is briefly introduced below.

[0051] The vertical data construction method provided in the embodiments of the present disclosure can be applied to electronic devices. The electronic device can be a terminal device or a server. Among them, the terminal device can be a smart phone, a tablet computer, a handheld computer, a vehicle terminal, a desktop computer, and a laptop computer. The server can be any server or server cluster, and the present disclosure does not limit this.

[0052] In addition, it should be noted that the user information involved in this disclosure (including but not limited to user device information, user personal information, etc.) is all information authorized by the user account or fully authorized by all parties.

[0053] Figure 1 is a schematic diagram of an electronic device provided by the present disclosure. Figure 1 The electronic device 10 may include at least one processor 101 and a memory 103 for storing processor executable instructions. The processor 101 is configured to execute instructions in the memory 103 to implement the vertical data construction method in the following embodiment.

[0054] In addition, the electronic device 10 may further include a communication bus 102 and at least one communication interface 104 .

[0055] The processor 101 may be a central processing unit (CPU), a microprocessing unit, an ASIC, or one or more integrated circuits for controlling the execution of the program of the disclosed solution.

[0056] The communication bus 102 may include a pathway for transmitting information between the above-mentioned components.

[0057] The communication interface 104 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0058] The memory 103 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processing unit through a bus. The memory may also be integrated with the processing unit.

[0059] The memory 103 is used to store instructions for executing the solution of the present disclosure, and the execution is controlled by the processor 101. The processor 101 is used to execute the instructions stored in the memory 103, thereby realizing the functions of the method of the present disclosure.

[0060] In a specific implementation, as an embodiment, the processor 101 may include one or more CPUs, such as Figure 1 CPU0 and CPU1 in.

[0061] In a specific implementation, as an embodiment, the electronic device 10 may include multiple processors, such as Figure 1 1 and 107. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0062] For ease of understanding, the vertical data construction method provided by the present disclosure is specifically introduced below with reference to the accompanying drawings.

[0063] Figure 2 is a flowchart of a method for constructing vertical data according to an exemplary embodiment. Figure 2 As shown, the vertical data construction method is used in an electronic device, comprising the following steps:

[0064] Step S21: Obtain the first vertical category data corresponding to the target vertical category identifier from the metadata database table.

[0065] Among them, the metadata database table is used to store vertical category data corresponding to multiple vertical category identifiers, the multiple vertical category identifiers include a target vertical category identifier, and the first vertical category data includes multiple user accounts.

[0066] Exemplarily, the vertical category identifiers may be food, literature, music, etc., and the vertical category data may include multiple user accounts corresponding to the vertical category identifiers such as food, literature, music, etc. Its user account may publish a media resource user account, such as a host user account.

[0067] It should be noted that the first vertical category data can be referred to as the original vertical category data obtained from the metadata database table.

[0068] Step S22: When a user account to be processed that meets the first preset condition is generated, a target user account that meets the second preset condition in the live broadcast state is determined based on the user account to be processed and multiple user accounts of the first vertical category data.

[0069] The above-mentioned “user accounts to be processed that meet the first preset condition” can be understood as user accounts to be processed that are screened in real time according to the first preset condition and can meet the vertical category construction requirements.

[0070] In some implementations, the second preset condition is that at least one of the number of virtual resources, the total number of associated user accounts, and the number of current online viewers meets a threshold condition. In this implementation, the second preset condition is set according to different parameters in the user account, ensuring the diversity and flexibility of the second preset condition setting method.

[0071] The number of virtual resources refers to the number of likes, comments, favorites, and gifts of the user account. The total number of associated user accounts can be understood as the number of user accounts that have an interactive relationship with the user account, such as the total number of fans.

[0072] Exemplarily, the number of virtual resources corresponding to the live broadcast room in the user account is greater than or equal to the first threshold; and / or the number of fans included in the live broadcast room in the user account is greater than or equal to the second threshold; and / or the number of online viewers included in the live broadcast room in the user account is greater than or equal to the third threshold. The first threshold, the second threshold, and the third threshold may be pre-stored in the electronic device, or may be set according to the user account requirements, or may be set according to the user account acquisition situation in the acquired live broadcast state.

[0073] In some implementations, the live broadcast status is also referred to as live online, online, online, or live broadcast, etc.

[0074] Step S23: Construct a second vertical category data including the target user account.

[0075] Among them, the second vertical category data corresponds to the target vertical category identifier. That is, the second vertical category data including the target user account is established under the target vertical category identifier.

[0076] Step S24: When a search instruction for a target vertical category identifier is received from an electronic device, a user account to be pushed to the electronic device is determined from the second vertical category data.

[0077] In this embodiment, when a pending user account that meets the first preset condition is generated, the pending user account and multiple user accounts with the target vertical category identifier in the metadata database table are directly processed to obtain the second vertical category data that meets the real-time construction requirements, so that the pushed second vertical category data can more accurately meet the user account requirements, avoiding the problem in the related art that when the vertical category data is obtained by updating the user account in the metadata database table, the vertical category data is pushed before it is updated due to the long update time when the vertical category data changes, thereby causing the pushed vertical category data to be inaccurate. Therefore, the present disclosure is based on the real-time generated vertical category construction requirements, that is, when a pending user account that meets the first preset condition is generated, the vertical category data, that is, the second vertical category data, is constructed in real time, and the latest constructed vertical category data is always used as the data source of the user account pushed to the electronic device. It can be seen that this vertical category data construction method has high real-time and flexibility.

[0078] Due to its high real-time and flexibility, it can push user accounts to electronic devices more accurately. For example, when an electronic device searches for a food anchor, it selects the anchor to be pushed to the electronic device from the latest food vertical category, thus avoiding pushing anchors whose attributes have changed to the electronic device.

[0079] In addition, since the user accounts in the latest constructed vertical data are all in live broadcast status, the user accounts pushed to electronic devices must be users who are currently broadcasting live, which can improve the user experience.

[0080] In this implementation, in actual application scenarios, the real-time vertical category construction needs can be attributed to two situations: First, in the previously constructed vertical category data (i.e., the first vertical category data), the vertical category attributes of certain user accounts have changed. For example, the food anchor in the food vertical category has become a music anchor. Such user accounts are user accounts to be deleted. Second, the latest user account belonging to a vertical category is generated, but the previously constructed vertical category data (i.e., the first vertical category data) does not include the latest user account belonging to the vertical category. For example, the food vertical category does not include the latest food anchor. Such users are user accounts to be added. Through this implementation, the above two types of real-time vertical category construction needs are used as trigger conditions for constructing vertical category data.

[0081] Based on this, as a possible implementation method, the acquisition of the user account to be processed that meets the first preset condition in the above step S22 can be achieved through the following three methods.

[0082] Method 1: When the electronic device detects that the vertical category identifier of a user account is changed from the target vertical category identifier to another vertical category identifier, the user account whose vertical category identifier is changed from the target vertical category identifier to another vertical category identifier is treated as the user account to be deleted, that is, the user account to be deleted is determined as the user account to be processed.

[0083] Method 2: When the electronic device detects that the vertical category identifier of the user account is to be changed to the target vertical category identifier, the user account whose vertical category identifier is to be changed to the target vertical category identifier is used as the user account to be added, that is, the user account to be added is determined as the user account to be processed.

[0084] Method 3: The electronic device detects both the user account to be processed in the above method 1 and the user account to be added in the above method 2; and determines the user account to be deleted and the user account to be added as the user accounts to be processed.

[0085] The user account to be added is a user account that is defined to match the target vertical category identifier, and the user account to be deleted is a user account that is defined to not match the target vertical category identifier. The user account to be added and the user account to be deleted can be user accounts with vertical category data construction requirements set according to the requirements of user accounts using electronic devices.

[0086] For example, the user account to be added can be the user account of the most recently registered anchor account or the user account of the anchor account whose vertical category identification has changed, such as the vertical category identification corresponding to a certain anchor account has changed from "food category" to "music category". The user account to be deleted can be the user account of the most recently cancelled anchor account or the user account of the anchor account whose vertical category identification has changed, such as the vertical category identification corresponding to a certain anchor account has changed from "music category" to "animation category".

[0087] In some implementations, the user accounts to be added can be understood as user accounts that are expected to participate in the construction of a certain vertical category of vertical data according to data construction requirements. Correspondingly, the user accounts to be deleted can be understood as user accounts that are expected to be excluded when the vertical category data of a certain vertical category is constructed according to data construction requirements.

[0088] Based on the three implementation methods of the above-mentioned methods 1 to 3, the above-mentioned step S22 can be specifically implemented by the following steps:

[0089] Step S221: adding the user account to be added to the multiple user accounts, and / or deleting the user account to be deleted from the multiple user accounts, to obtain a first type of user account.

[0090] In some embodiments, all user accounts to be added are stored in a whitelist user account package, all user accounts to be deleted are stored in a blacklist user account package, user accounts matching the target vertical category identifier are obtained from a Hive table, and user accounts matching the target vertical category identifier are stored in a source user account package, that is, the first vertical category data can be called a source user account package.

[0091] For example, Figure 3 As shown in , the source user account package obtained from the Hive table is merged with the whitelist user account package (i.e., the two are taken as a union), and the duplicate user accounts in the source user account package and the whitelist user account package are deduplicated to ensure the uniqueness of the duplicate user accounts. The user accounts in the user account package obtained above that are duplicated with the blacklist user account package are then deleted, thereby obtaining the first type of user accounts.

[0092] Combined with the above-mentioned methods 1 to 3, step S221 realizes the acquisition of the first category of user accounts. On the one hand, the user accounts to be added and the user accounts to be deleted are dynamically generated user accounts for updating vertical category data. The first category of user accounts is determined based on the dynamically generated user accounts to be added and the user accounts to be deleted, which ensures the dynamic and real-time nature of the first category of user accounts, thereby ensuring the real-time and accuracy of the constructed second vertical category data; on the other hand, when there are user accounts matching the target vertical category identifier in the Hive table, the user accounts matching the target vertical category identifier in the Hive table are used as static user accounts, and the static user accounts are combined with the dynamically generated user accounts to be added and the user accounts to be deleted to jointly determine the first category of user accounts, thereby ensuring the accuracy of the acquired first category of user accounts, thereby ensuring the accuracy of the constructed second vertical category data.

[0093] In another embodiment, based on the three implementation methods of methods one to three mentioned above, the first category of user accounts can also be determined through the following implementation method to adapt to the application scenario where there is no user account matching the target vertical category identifier in the metadata database table: remove the user accounts that are duplicated with the user accounts to be deleted from the user accounts to be added to obtain the first category of user accounts.

[0094] The above-mentioned method of obtaining the first category of user accounts is to obtain the first category of user accounts based on the user accounts to be processed, for the application scenario where the constructed first vertical category data does not exist in the metadata table. On the one hand, the user accounts to be added and the user accounts to be deleted are dynamically generated user accounts with vertical category data construction requirements, and the first category of user accounts are determined based on the dynamically generated user accounts to be added and the user accounts to be deleted, which ensures the dynamic and real-time nature of the first category of user accounts, thereby ensuring the real-time and accuracy of the construction of the second vertical category data; on the other hand, when there is no user account matching the target vertical category identifier in the metadata table, the first category of user accounts are directly determined based on the dynamically generated user accounts to be added and the user accounts to be deleted, so that the obtained first category of user accounts are more in line with the application scenario of reconstructing new vertical category data, which improves the accuracy of the first category of user accounts, thereby improving the accuracy of the reconstructed target vertical category data.

[0095] Step S222: Determine, based on the first type of user accounts, a target user account that meets the second preset condition in the live broadcast state.

[0096] As an implementation manner, the above step S222 can be specifically implemented through the following steps.

[0097] Step S222A, from the user accounts in the live broadcast state, determine the user accounts whose live broadcast content matches the target vertical category identifier, and obtain the second category user accounts.

[0098] In some implementations, based on the correlation between the live broadcast content and the target vertical category identifier, the second category of user accounts are screened out from the user accounts in the live broadcast state.

[0099] In some embodiments, Figure 4 As shown, by refreshing the crowd tag in real time (the crowd tag can be understood as the identifier of the user feature of the user account), the user accounts to be added and the user accounts to be deleted are obtained in real time, and the first category of user accounts are screened out according to the user accounts to be added and the user accounts to be deleted, and the first category of user accounts are stored in the storage system. At the same time, instructions are sent through the Remote Procedure Call Protocol (RPC) to retrieve and filter the live content corresponding to the live broadcast room in the live broadcast state, form the second category of user accounts, and store the second category of user accounts in the storage system. When the first category of user accounts and / or the second category of user accounts are needed, they can be directly obtained from the storage system.

[0100] Step S222B: determine a first candidate user account that meets a second preset condition from the first category of user accounts, and determine a second candidate user account that meets the second preset condition from the second category of user accounts.

[0101] In some implementations, according to the second preset condition, the first category of user accounts and the second category of user accounts are filtered respectively to generate a first candidate user account and a second candidate user account respectively.

[0102] Step S222C: determining a target user account based on the first candidate user account and the second candidate user account.

[0103] As an implementation mode, step S222C may be specifically implemented through the following steps.

[0104] Step 1: When there is a duplicate user account between the first candidate user account and the second candidate user account, the duplicate user account is determined as a target user account.

[0105] In some embodiments, Figure 3 As shown, the first candidate user account is also referred to as the filtering result corresponding to the first type of user account, and the second candidate user account is also referred to as the filtering result corresponding to the second type of user account. When the filtering result corresponding to the first type of user account is repeated with the filtering result corresponding to the second type of user account, the repeated user account is determined as the target user account.

[0106] Step 2: When there is no duplicate user account between the first candidate user account and the second candidate user account, the first candidate user account or the second candidate user account is determined as the target user account.

[0107] Exemplarily, when there is no duplication between the filtering results corresponding to the first type of user accounts and the filtering results corresponding to the second type of user accounts, the filtering results corresponding to the second type of user accounts or the filtering results corresponding to the first type of user accounts are determined as the target user accounts.

[0108] Among them, the filtering results corresponding to the first type of user accounts and the filtering results corresponding to the second type of user accounts are not repeated, which may include the following situations.

[0109] The first one is based on the fact that the filtering result corresponding to the first type of user account is an empty set, that is, there is no user account in its filtering result, and the filtering result corresponding to the second type of user account is a non-empty set, that is, there is a user account in its filtering result, the filtering result corresponding to the second type of user account is determined as the target user account.

[0110] The second type is based on the fact that the filtering result corresponding to the second type of user account is an empty set, that is, there is no user account in the filtering result, and the filtering result corresponding to the first type of user account is a non-empty set, that is, there is a user account in the filtering result, the filtering result corresponding to the first type of user account is determined as the target user account.

[0111] The third method is to determine the filtering result corresponding to the first type of user account as the target user account based on the fact that both the filtering results corresponding to the first type of user account and the filtering results corresponding to the second type of user account are non-empty sets, and the two types of non-empty set filtering results have no intersection.

[0112] In this implementation, first, the accounts that match the target vertical category identifier are screened out from the user accounts that are currently broadcasting live, that is, the second category accounts; then, according to the construction requirements (that is, the second preset condition), the first category accounts and the second category accounts are screened / filtered respectively to obtain the first candidate account and the second candidate account. Finally, the target user account is determined based on the first candidate account and the second candidate account. The above second preset condition reflects the vertical category construction requirements from another perspective. Based on this implementation method, the target user accounts that are expected to be built into a certain vertical category can be screened out according to the vertical category construction requirements, thereby ensuring that the constructed vertical category data is more accurate.

[0113] In one embodiment, each target user account corresponds to an account identifier and a live broadcast room identifier of at least one live broadcast room. Based on this, step S23 is specifically implemented in the following manner to realize the construction of the second vertical category data.

[0114] Step S231, associate the account identifier and live broadcast room identifier corresponding to each target user account with the target vertical category identifier to obtain the second vertical category data including the target user account and indexed by the target vertical category identifier.

[0115] In this implementation, the account identifier in the target user account and the live broadcast room identifier corresponding to the account identifier are associated with the target vertical category identifier, so that the constructed target vertical category identifier includes the live broadcast room identifier and the account identifier corresponding to the live broadcast room.

[0116] Through the vertical category data constructed as above, when the target vertical category identifier is indexed by the user account of an electronic device, the live broadcast room identifier and the corresponding account identifier associated with the target vertical category identifier can be automatically recommended to the electronic device to ensure the practicality of the constructed vertical category data.

[0117] In one implementation, after executing step S23, the following steps may also be performed:

[0118] Step S25, when the second vertical category data has been constructed and the target user account is updated, the second vertical category data is updated according to the updated target user account.

[0119] When the second vertical data has been built and the target user account is updated, the following scenarios can be used:

[0120] Scenario 1: The second vertical category data has been constructed. When a new target user account is detected to be added to the second vertical category data, it is determined that the target user account has been updated. For this scenario, it is only necessary to add a new target user account to the second vertical category data to update the second vertical category data.

[0121] Scenario 2: The second vertical category data has been constructed. When a user account that needs to be deleted is detected in the original target user account, it is determined that the target user account has been updated. For this scenario, it is only necessary to delete the user account that needs to be deleted from the original target user account of the second vertical category data to update the second vertical category data.

[0122] In this embodiment, when the second vertical category data has been constructed, when it is detected that the target user account is updated, such as a new target user account is generated, the second vertical category data can be directly updated according to the updated target user account without rebuilding the second vertical category data.

[0123] As an implementation manner, the above step S24 can be specifically implemented by the following steps:

[0124] Step S241, when receiving a search instruction for multiple target vertical category identifiers sent by an electronic device, obtaining account features of a user account corresponding to the electronic device, and determining the correlation between the account features and each target vertical category identifier;

[0125] Step S242, determining the push priority of each target vertical category identifier according to the correlation between the account characteristics and each target vertical category identifier;

[0126] Step S243, determining the user account to be pushed corresponding to the target vertical category identifier from the second vertical category data corresponding to each target vertical category identifier;

[0127] Step S244, push the user account to the electronic device according to the push priority of each target vertical category identifier and the user account to be pushed corresponding to each target vertical category identifier.

[0128] It should be noted that the above step S243 is used for application scenarios where push is required to the specified target user account in the target vertical category identifier. However, for application scenarios where push is required to all target user accounts in the target vertical category identifier, the above step S243 can be ignored. In other words, the user accounts to be pushed corresponding to the target vertical category identifier determined above can be all target user accounts or some of the target user accounts.

[0129] In this implementation, when multiple target vertical category identifiers need to be pushed to a user account, the account features of the user account are matched with each target vertical category identifier to determine the relevance between the account features and each target vertical category identifier. Based on the relevance, the push priority of each target vertical category identifier is determined, and then each target account identifier is pushed in sequence according to the priority.

[0130] In the above-mentioned recommended method of pushing multiple target vertical category identifiers to the same user account, each target vertical category identifier is pushed according to the correlation between the account characteristics and each target vertical category identifier, thereby ensuring that the pushed vertical category data better meets the needs of the user account.

[0131] For example, Figure 5 As shown, the server needs to push multiple target vertical category identifiers to the user account, where the multiple target vertical category identifiers are games, talents, and appearance. The server will send instructions based on RPC to recall the second target account data or vertical category data corresponding to each target vertical category identifier to sort the multiple target vertical category identifiers according to the account characteristics of the user account. If the account feature has the greatest correlation with the game, the account feature has the least correlation with appearance. When pushing to the user account, it is pushed according to the index sequence in the order of games, talents, and appearance. The index sequence can be a transition from a forward index to a reverse index. As Figure 5 The inverted index is game: each live broadcast room ID corresponding to the game; talent: each live broadcast room ID corresponding to talent; appearance: each live broadcast room ID corresponding to appearance. The forward index is a live broadcast room ID corresponding to a game: game; a live broadcast room ID corresponding to a talent: talent; a live broadcast room ID corresponding to appearance: appearance.

[0132] In one embodiment, the third vertical category data is constructed according to the following steps to target application scenarios in which the target vertical category identifier is not obtained in the metadata database table. For example, in order to classify the user group more finely, a new vertical category identifier will be defined. For example, there was originally only a music category, and later new vertical category identifiers such as pop music and jazz music appeared; however, the metadata database table does not include vertical category data corresponding to the new vertical category identifier, that is, vertical category data has not been constructed for the new vertical category identifier.

[0133] Step S31, when a third type of user account whose vertical category identifier is to be changed to a new vertical category identifier and is in a live broadcast state is generated, third vertical category data including the third type of user account is constructed according to the third type of user account, the third vertical category data corresponds to the new vertical category identifier, and the new vertical category identifier is not included in the multiple vertical category identifiers;

[0134] Step S32, when a search instruction for a new vertical category identifier is received from an electronic device, a user account to be pushed to the electronic device is determined from the third vertical category data.

[0135] Among them, the third type of user accounts may be user accounts to be added and / or user accounts to be deleted.

[0136] Specifically, for the application scenario in which there is no original vertical category data corresponding to the target vertical category identifier in the metadata database table, the data to be processed and the first type of user account are obtained. The user accounts to be processed include user accounts to be added and / or user accounts to be deleted generated in real time, so as to meet the real-time construction requirements. For example, the user account to be added can be a whitelist account set according to requirements, and the user account to be deleted can be a blacklist account set according to requirements. Through this implementation, when no user account matching the target vertical category identifier is detected, the vertical category data to be constructed is determined directly based on the dynamic account data, which is more in line with the application scenario of constructing new vertical category data and improves the accuracy of the constructed vertical category data.

[0137] In order to achieve the above functions, the vertical data construction device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0138] The present disclosure also provides a Figure 6 The vertical data construction device 600 shown includes: an acquisition unit 601, a determination unit 602, a construction unit 603, and a push unit 604.

[0139] The acquisition unit 601 is configured to execute the acquisition of the first vertical category data corresponding to the target vertical category identifier from the metadata database table, the metadata database table is used to store vertical category data corresponding to multiple vertical category identifiers, the multiple vertical category identifiers include the target vertical category identifier, and the first vertical category data includes multiple user accounts; the determination unit 602 is configured to execute when a pending user account that meets the first preset condition is generated, based on the pending user account and the multiple user accounts included in the first vertical category data, determine the target user account that meets the second preset condition in the live broadcast state; the construction unit 603 is configured to execute the construction of the second vertical category data containing the target user account, the second vertical category data corresponds to the target vertical category identifier; the push unit 604 is configured to execute when a retrieval instruction for the target vertical category identifier sent by the electronic device is received, Determine the user account to be pushed to the electronic device from the second vertical category data.

[0140] In a possible implementation, when a user account to be processed that meets the first preset condition is generated, including: when a user account to be deleted is generated whose vertical category identifier is changed from a target vertical category identifier to another vertical category identifier, and / or, when a user account to be added is generated whose vertical category identifier is to be changed to a target vertical category identifier; the determination unit 602 is configured to specifically execute: adding the user account to be added to multiple user accounts, and / or, deleting the user account to be deleted from multiple user accounts to obtain a first type of user account; based on the first type of user account, determining a target user account that meets the second preset condition in the live broadcast state.

[0141] In another possible implementation, the determination unit 602 is configured to specifically perform: determining, from user accounts in a live broadcast state, user accounts whose live broadcast content matches the target vertical category identifier, to obtain a second category of user accounts; determining a first candidate user account that meets a second preset condition from the first category of user accounts, and determining a second candidate user account that meets the second preset condition from the second category of user accounts; and determining the target user account based on the first candidate user account and the second candidate user account.

[0142] In another possible implementation, the determination unit 602 is configured to specifically perform: when there are duplicate user accounts between the first candidate user account and the second candidate user account, determining the duplicate user account as the target user account; when there are no duplicate user accounts between the first candidate user account and the second candidate user account, determining the first candidate user account or the second candidate user account as the target user account.

[0143] In another possible implementation, each user account corresponds to at least one of the number of virtual resources, the total number of associated user accounts, and the current number of online viewers; the second preset condition is that at least one of the number of virtual resources, the total number of associated user accounts, and the current number of online viewers meets the threshold condition.

[0144] In another possible implementation, each target user account corresponds to an account identifier and a live broadcast room identifier of at least one live broadcast room; the construction unit 603 is configured to specifically execute: associating the account identifier and live broadcast room identifier corresponding to each target user account with the target vertical category identifier, and obtaining second vertical category data including the target user account and indexed by the target vertical category identifier.

[0145] In another possible implementation, the determination unit 602 is further configured to specifically execute: when the second vertical category data has been constructed and the target user account is updated, updating the second vertical category data according to the updated target user account.

[0146] In another possible implementation, the push unit 604 is configured to specifically perform the following: when receiving a retrieval instruction for multiple target vertical category identifiers sent by the electronic device, obtaining the account characteristics of the user account corresponding to the electronic device, and determining the correlation between the account characteristics and each target vertical category identifier; determining the push priority of each target vertical category identifier based on the correlation between the account characteristics and each target vertical category identifier; determining the user account to be pushed corresponding to the target vertical category identifier from the second vertical category data corresponding to each target vertical category identifier; and pushing the user account to the electronic device based on the push priority of each target vertical category identifier and the user account to be pushed corresponding to each target vertical category identifier.

[0147] In another possible implementation, the device is further configured to execute: when a third type of user account whose vertical category identifier is to be changed to a new vertical category identifier and is in a live broadcast state is generated, third vertical category data including the third type of user account is constructed according to the third type of user account, the third vertical category data corresponds to the new vertical category identifier, and the new vertical category identifier is not included in the multiple vertical category identifiers;

[0148] When a search instruction for a new vertical category identifier is received from an electronic device, a user account to be pushed to the electronic device is determined from the third vertical category data.

[0149] The present disclosure also provides an electronic device. Figure 1 The example includes: a processor 101 and a memory 103 for storing executable instructions of the processor 101; wherein the processor 101 is configured to execute executable instructions to implement a vertical data construction method as in any possible implementation method described above. And the same technical effect can be achieved, and to avoid repetition, it will not be described here.

[0150] The disclosed embodiment also provides a computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by a processor of a vertical data construction device or an electronic device, the vertical data construction device or the electronic device can execute a vertical data construction method as described in any of the above possible implementations. And the same technical effect can be achieved, so it will not be repeated here to avoid repetition.

[0151] The embodiment of the present disclosure also provides a computer program product, including a computer program or an instruction, which is executed by a processor as a vertical data construction method of any possible implementation method described above. And the same technical effect can be achieved, so it will not be repeated here to avoid repetition.

[0152] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0153] It should be understood that the present disclosure is not limited to the exact structures that have been 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 disclosure is limited only by the appended claims.

Claims

1. A method for constructing vertical data, characterized in that: The method comprises: Acquire first vertical category data corresponding to the target vertical category identifier from a metadata database table, where the metadata database table is used to store vertical category data corresponding to multiple vertical category identifiers, where the multiple vertical category identifiers include the target vertical category identifier, and the first vertical category data includes multiple user accounts; When a user account to be processed that meets the first preset condition is generated, a target user account that meets the second preset condition in the live broadcast state is determined based on the user account to be processed and the multiple user accounts included in the first vertical category data, including: when a user account to be deleted is generated whose vertical category identifier is changed from the target vertical category identifier to other vertical category identifiers, and / or when a user account to be added is generated whose vertical category identifier is to be changed to the target vertical category identifier, the user account to be added is added to the multiple user accounts, and / or the user account to be deleted is deleted from the multiple user accounts to obtain a first type of user account; based on the first type of user account, the target user account that meets the second preset condition in the live broadcast state is determined; each of the user accounts corresponds to at least one of the number of virtual resources, the total number of associated user accounts, and the number of current online viewers; the second preset condition is: at least one of the number of virtual resources, the total number of associated user accounts, and the number of current online viewers meets the threshold condition; Constructing second vertical category data including the target user account, wherein the second vertical category data corresponds to the target vertical category identifier; When a search instruction for the target vertical category identifier is received from the electronic device, the user account to be pushed to the electronic device is determined from the second vertical category data.

2. The vertical data construction method according to claim 1 is characterized in that: The step of determining the target user account that meets the second preset condition in the live broadcast state according to the first type of user account includes: From the user accounts in the live broadcast state, determine the user accounts whose live broadcast content matches the target vertical category identifier to obtain the second category of user accounts; Determining a first candidate user account that meets the second preset condition from the first category of user accounts, and determining a second candidate user account that meets the second preset condition from the second category of user accounts; The target user account is determined according to the first candidate user account and the second candidate user account.

3. The vertical data construction method according to claim 2 is characterized in that: The determining the target user account according to the first candidate user account and the second candidate user account includes: In the case where there is a duplicate user account between the first candidate user account and the second candidate user account, determining the duplicate user account as the target user account; In the case that there is no duplicate user account between the first candidate user account and the second candidate user account, the first candidate user account or the second candidate user account is determined as the target user account.

4. The method for constructing vertical data according to claim 1, characterized in that: Each of the target user accounts corresponds to an account identifier and a live broadcast room identifier of at least one live broadcast room; The constructing of the second vertical category data containing the target user account includes: The account identifier and the live broadcast room identifier corresponding to each of the target user accounts are associated with the target vertical category identifier to obtain the second vertical category data including the target user account and indexed by the target vertical category identifier.

5. The method for constructing vertical data according to claim 1, characterized in that: The method further comprises: When the second vertical category data has been constructed and the target user account is updated, the second vertical category data is updated according to the updated target user account.

6. The method for constructing vertical data according to any one of claims 1 to 5, characterized in that: The step of determining, from the second vertical category data, a user account to be pushed to the electronic device when receiving a search instruction for the target vertical category identifier sent by the electronic device comprises: When receiving a search instruction for a plurality of target vertical category identifiers sent by an electronic device, obtaining account features of a user account corresponding to the electronic device, and determining a correlation between the account features and each of the target vertical category identifiers; Determine the push priority of each target vertical category identifier according to the correlation between the account feature and each target vertical category identifier; Determine the user account to be pushed corresponding to the target vertical category identifier from the second vertical category data corresponding to each of the target vertical category identifiers; The user account is pushed to the electronic device according to the push priority of each of the target vertical category identifiers and the user account to be pushed corresponding to each of the target vertical category identifiers.

7. The method for constructing vertical data according to claim 1, characterized in that: The method further comprises: When a third type of user account is generated whose vertical category identifier is to be changed to a new vertical category identifier and is in a live broadcast state, third vertical category data including the third type of user account is constructed according to the third type of user account, the third vertical category data corresponds to the new vertical category identifier, and the new vertical category identifier is not included in the multiple vertical category identifiers; When a search instruction for the new vertical category identifier is received from the electronic device, a user account to be pushed to the electronic device is determined from the third vertical category data.

8. A vertical data construction device, characterized in that: The device comprises: An acquiring unit is configured to acquire first vertical category data corresponding to a target vertical category identifier from a metadata database table, wherein the metadata database table is used to store vertical category data corresponding to multiple vertical category identifiers, wherein the multiple vertical category identifiers include the target vertical category identifier, and the first vertical category data includes multiple user accounts; A determination unit is configured to execute, when a user account to be processed that meets a first preset condition is generated, determine a target user account that meets a second preset condition in a live broadcast state according to the user account to be processed and the multiple user accounts included in the first vertical category data, including: when a user account to be deleted is generated whose vertical category identifier is changed from the target vertical category identifier to another vertical category identifier, and / or when a user account to be added is generated whose vertical category identifier is to be changed to the target vertical category identifier, add the user account to be added to the multiple user accounts, and / or delete the user account to be deleted from the multiple user accounts to obtain a first type of user account; determine the target user account that meets the second preset condition in a live broadcast state according to the first type of user account; each of the user accounts corresponds to at least one of the number of virtual resources, the total number of associated user accounts, and the number of current online viewers; the second preset condition is: at least one of the number of virtual resources, the total number of associated user accounts, and the number of current online viewers meets the threshold condition; A construction unit is configured to execute construction of second vertical category data containing the target user account, where the second vertical category data corresponds to the target vertical category identifier; The push unit is configured to execute, when receiving a retrieval instruction for the target vertical category identifier sent by the electronic device, determine the user account to be pushed to the electronic device from the second vertical category data.

9. The vertical data construction device according to claim 8, characterized in that: The determining unit is configured to specifically execute: From the user accounts in the live broadcast state, determine the user accounts whose live broadcast content matches the target vertical category identifier to obtain the second category of user accounts; Determining a first candidate user account that meets the second preset condition from the first category of user accounts, and determining a second candidate user account that meets the second preset condition from the second category of user accounts; The target user account is determined according to the first candidate user account and the second candidate user account.

10. The vertical data construction device according to claim 9, characterized in that: The determining unit is configured to specifically execute: In the case where there is a duplicate user account between the first candidate user account and the second candidate user account, determining the duplicate user account as the target user account; In the case that there is no duplicate user account between the first candidate user account and the second candidate user account, the first candidate user account or the second candidate user account is determined as the target user account.

11. The vertical data construction device according to claim 8, characterized in that: Each of the target user accounts corresponds to an account identifier and a live broadcast room identifier of at least one live broadcast room; the construction unit is configured to specifically perform: The account identifier and the live broadcast room identifier corresponding to each of the target user accounts are associated with the target vertical category identifier to obtain the second vertical category data including the target user account and indexed by the target vertical category identifier.

12. The vertical data construction device according to claim 8, characterized in that: The determining unit is further configured to specifically execute: When the second vertical category data has been constructed and the target user account is updated, the second vertical category data is updated according to the updated target user account.

13. The vertical data construction device according to any one of claims 8 to 12, characterized in that: The push unit is configured to specifically perform: When receiving a search instruction for a plurality of target vertical category identifiers sent by an electronic device, obtaining account features of a user account corresponding to the electronic device, and determining a correlation between the account features and each of the target vertical category identifiers; Determine the push priority of each target vertical category identifier according to the correlation between the account feature and each target vertical category identifier; Determine the user account to be pushed corresponding to the target vertical category identifier from the second vertical category data corresponding to each of the target vertical category identifiers; The user account is pushed to the electronic device according to the push priority of each of the target vertical category identifiers and the user account to be pushed corresponding to each of the target vertical category identifiers.

14. The vertical data construction device according to claim 8, characterized in that: The apparatus is also configured to perform: When a third type of user account is generated whose vertical category identifier is to be changed to a new vertical category identifier and is in a live broadcast state, third vertical category data including the third type of user account is constructed according to the third type of user account, the third vertical category data corresponds to the new vertical category identifier, and the new vertical category identifier is not included in the multiple vertical category identifiers; When a search instruction for the new vertical category identifier is received from the electronic device, a user account to be pushed to the electronic device is determined from the third vertical category data.

15. An electronic device, characterized in that: include: A processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the executable instructions to implement the method according to any one of claims 1 to 7.

16. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the vertical category data construction method as described in any one of claims 1 to 7.

Images