Content pushing method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a content pushing method and device, equipment and a storage medium, and relates to the technical field of computers, and the method can comprise the steps: obtaining a target operation information table of a target account for historical pushing content; wherein the target operation information table comprises each piece of target operation information in a preset historical time period; based on an operation attribute field of each piece of target operation information, a content type field of each piece of target operation information and an attribute weight corresponding to each candidate operation attribute, determining at least one preference content type corresponding to the target account from each candidate content type; and performing content pushing on the target account based on each preference content type. By adopting the technical scheme of the embodiment of the invention, the accuracy of the content pushed to the user by the APP can be improved, so that the waste of pushed resources can be reduced, and the pushing efficiency is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular to a content push method, device, equipment and storage medium. Background Art

[0002] With the rapid development of Internet technology and the popularization of mobile terminals, a large number of applications (Application, APP) that can be used in mobile terminals have emerged, which have provided great convenience to our daily life and work. For example, some APPs can push hot news, cultural and tourism projects, and entertainment information to users.

[0003] However, in the process of implementing the present invention, it is found that there are at least the following problems in the prior art: the content pushed by the APP to users is regularly and uniformly configured by the APP operator, and all users see the same pushed content. This overly single content push form affects the accuracy of the content pushed by the APP to users, resulting in a waste of push resources and low push efficiency. Summary of the invention

[0004] The embodiments of the present invention provide a content push method, apparatus, device and storage medium, which can improve the accuracy of content pushed by an APP to a user, thereby reducing the waste of push resources and improving push efficiency.

[0005] In the first aspect, an embodiment of the present invention provides a content push method, which may include: obtaining a target operation information table for a target account for historical pushed content; wherein the target operation information table includes each target operation information within a preset historical time period; based on the operation attribute field of each target operation information, the content type field of each target operation information, and the attribute weights corresponding to each candidate operation attribute, determining at least one preferred content type corresponding to the target account from each candidate content type; and pushing content to the target account based on each preferred content type.

[0006] In a second aspect, an embodiment of the present invention further provides a content push device, which may include: an acquisition module, a determination module, and a content push module;

[0007] Specifically, the acquisition module is used to obtain a target operation information table of the target account for historical push content; wherein the target operation information table includes each target operation information within a preset historical time period;

[0008] A determination module, configured to determine at least one preferred content type corresponding to the target account from each candidate content type based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute;

[0009] The content push module is used to push content to target accounts based on preferred content types.

[0010] In a third aspect, an embodiment of the present invention provides a content push device, the content push device comprising:

[0011] One or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the content push method provided by any embodiment of the present invention.

[0012] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a content push method as provided in any embodiment of the present invention.

[0013] The embodiments of the above invention have the following advantages or beneficial effects:

[0014] In the technical solution provided by the embodiment of the present invention, before pushing content to the target account used by the user in the APP, the target operation information table for the historical push content of the target account can be obtained first. The target operation information table includes each target operation information within a preset historical time period, and a target operation information can record the relevant information of an operation performed by the corresponding user of the target account on a certain historical push content during the use of the APP. Specifically, a target operation information may include an operation attribute field and a content type field. The operation attribute field can represent which attribute operation the user has performed on the historical push content, and the content type field can represent the content type to which the historical push content belongs. Generally, when a user prefers to browse a certain type of push content, the push content of this type may be operated. In addition, when the user has different preferences for different types of push content, different attributes of operations may be performed on different types of push content. Based on this, the embodiment of the present invention can determine in advance the attribute weights corresponding to each candidate operation attribute according to the association between each candidate operation attribute and the user's preference degree. Furthermore, after obtaining each piece of target operation information, at least one preferred content type corresponding to the target account can be determined from each candidate content type based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute, and then the content is pushed to the target account based on each preferred content type. It can be seen that in the technical solution provided in the embodiment of the present invention, the operation attribute field and the content type field in each piece of target operation information of the target account can be analyzed to determine several content types (i.e., the preferred content types in the embodiment of the present invention) that the corresponding user of the target account may prefer. Then, based on each preferred content type, the content is pushed to the target account, and the pushed content will be closer to the preferences of the corresponding user of the target account. Therefore, the accuracy of the content pushed by the APP to the user can be improved, thereby reducing invalid pushes, thereby reducing the waste of push resources, and improving push efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of a content push method provided by an embodiment of the present invention;

[0016] Figure 2 It is a flowchart of another content push method provided by an embodiment of the present invention;

[0017] Figure 3 It is a flowchart of another content push method provided by an embodiment of the present invention;

[0018] Figure 4 It is a flowchart of another content push method provided by an embodiment of the present invention;

[0019] Figure 5 It is a flowchart of another content push method provided by an embodiment of the present invention;

[0020] Figure 6 It is a structural schematic diagram of a content push device provided by an embodiment of the present invention;

[0021] Figure 7 It is a structural diagram of a content push device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0023] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0024] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0025] It should be noted that, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0026] In the description of the embodiments of the present invention, unless otherwise specified, “plurality” or “each” means two or more than two.

[0027] Figure 1 A flowchart of a content push method provided in an embodiment of the present invention, which can be applied to an application scenario of pushing content to a user through an APP. The method can be executed by a content push device provided in an embodiment of the present invention, which can be implemented in software and / or hardware and integrated in a content push device.

[0028] The content push method provided by the embodiment of the present invention can be applied to a content push system including a client and a server. Specifically, the content push device that executes the method can be configured on the server, and correspondingly, the content push device integrated with the content push device can be a corresponding device on the server, such as a server of a server.

[0029] The client is also the APP end. The corresponding device of the client can be different types of mobile terminals such as mobile phones, tablet computers, wearable electronic devices, virtual reality devices, etc. The mobile terminal can be installed with an APP that pushes content to users (for example, a life APP). It should be noted that the APP involved in the following description of the embodiments of the present invention refers to an APP used to push content to users.

[0030] like Figure 1 As shown, the content push method provided by the embodiment of the present invention specifically includes the following steps:

[0031] S110: Obtain a target operation information table of the target account for historical push content.

[0032] The target account is used to uniquely represent the identity of the user. For example, the target account can be the registration information entered by the user when logging into the APP for the first time. The target account can be used together with the key set by the user as the login credential when the user logs into the APP.

[0033] The target operation information table may include each piece of target operation information within a preset historical time period.

[0034] The preset historical time period may be a time period before the current moment. For example, the preset historical time period may be 7 consecutive days before the current moment.

[0035] Specifically, a target operation information can record the relevant information of an operation performed by the corresponding user of the target account on a certain historical push content during the use of the APP. The user's operation on the historical push content can represent the user's preference for various types of push content. Therefore, in the embodiment of the present invention, the target operation information table for the historical push content of the target account can be obtained, and the possible preferred content type of the target account can be determined based on each target operation information in the target operation information table.

[0036] It should be noted that in the embodiments of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When used, the user's personal information is de-identified and / or anonymized and / or encrypted. For example, in an embodiment of the present invention, in order to determine the user's preferred content type, the user's operation information during the use of the APP will be collected. The operation information we collect does not include relevant information of the user's target account, but distinguishes different target accounts through account identifiers. Among them, the account identifier can be a string randomly generated by the server, which has no actual physical meaning, so it does not involve user privacy, and a specific individual cannot be re-identified through the account identifier.

[0037] S120, based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute, determine at least one preferred content type corresponding to the target account from each candidate content type.

[0038] The target operation information may include an operation attribute field and a content type field. It is understandable that in actual applications, the target operation information may also include other information, which is not limited in the embodiment of the present invention. For example, the target operation information may also include the content code and content acquisition address of the historical push content operated by the user.

[0039] The content code can be a digital number or other string that uniquely represents a push content. In an embodiment of the present invention, the content code in the target operation information can be used to record which historical push content the user has operated on. The content acquisition address can be a web page address or other link address. Exemplarily, if the user operates on a historical push content, and the historical push content is an article, the server can record the acquisition address of the article in the target operation information. When the client needs to re-present the article, the article can be obtained through the acquisition address. The operation attribute field can represent which attribute the user has operated on the historical push content. Exemplarily, in an embodiment of the present invention, each candidate operation attribute can include multiple operation attributes such as likes, favorites, shares, and comments. Specifically, each candidate operation attribute can be determined according to the operation functions supported by the APP. The content type field can represent the content type to which the historical push content operated by the user belongs. Exemplarily, in an embodiment of the present invention, each candidate content type can include multiple content types such as hot news, cultural and tourism projects, and entertainment information.

[0040] Generally, when a user prefers a candidate content type, the push content of the candidate content type may be operated. Exemplarily, when a user prefers to browse the push content of hot news, the user may like, collect, share, or comment on the push content of hot news pushed by the APP during the use of the APP; and when the user does not prefer to browse the push content of entertainment information, that is, the user is not interested in the push content of entertainment information, the user may quickly swipe through the push content of this type during the use of the APP and not operate the push content of this type. Therefore, the more the number of target operation information corresponding to a candidate content type in each target operation information, the higher the possibility that the user prefers the candidate content type. Based on this, in an embodiment of the present invention, the number of target operation information corresponding to each candidate content type can be counted according to the content type field in each target operation information, and then the number of target operation information corresponding to each candidate content type is referred to to determine the several content types (i.e., the preferred content type in the embodiment of the present invention) that the user corresponding to the target account may prefer from each candidate content type.

[0041] In addition, when the user has different preferences for different candidate content types, different attributes of the push content corresponding to different candidate content types may be operated. For example, if the user prefers to browse the push content of hot news, but the preference is not high, the user may like this type of push content during the use of the APP; if the user prefers to browse the push content of entertainment information, but the preference is average, the user may share or comment on this type of push content during the use of the APP to achieve interaction with other users; if the user prefers to browse the push content of cultural and tourism projects, and the preference is very high, the user may collect this type of push content during the use of the APP, so that the collection of this type of push content can be repeatedly viewed. Therefore, in the embodiment of the present invention, the attribute weights corresponding to each candidate operation attribute can be determined in advance according to the association between each candidate operation attribute and the user's preference degree. When determining the preferred content types corresponding to the target account, the server can not only refer to the content type field in each target operation information, but also refer to the operation attribute field of each target operation information, and determine the preferred content types corresponding to the target account in combination with the attribute weights corresponding to each candidate operation attribute. In this way, the accuracy of the determined preferred content type can be improved, so that the content pushed by the APP is closer to the preferences of the corresponding user of the target account.

[0042] In a possible implementation, in an embodiment of the present invention, based on the association between the above-mentioned candidate operation attributes and the user preference degree, it can be determined that the attribute weight corresponding to the collection operation is higher than the attribute weight corresponding to the sharing operation and the comment operation, and the attribute weight corresponding to the sharing operation and the comment operation is higher than the attribute weight corresponding to the like operation. In addition, the sum of the attribute weights of the candidate operation attributes is 1.

[0043] It is understandable that the association between each candidate operation attribute and the user's preference level described in the embodiment of the present invention is only an example. In actual applications, when users use different APPs, they may express their preference levels differently, that is, for different APPs, the association between each candidate operation attribute and the user's preference level may be different. Therefore, in actual applications, the operator of the APP can analyze the association between each candidate operation attribute and the user's preference level in the APP in combination with the usage scenarios of the APP, so as to reasonably set the attribute weights corresponding to each candidate operation attribute, and the embodiment of the present invention does not limit this.

[0044] S130: Push content to target accounts based on preferred content types.

[0045] Exemplarily, a preset content library may be stored in the server, which includes a large number of contents of various candidate content types, and the APP operator may regularly update the preset content library. When the server needs to push content to the target account, it can determine at least one piece of content to be pushed corresponding to each preferred content type of the target account from the preset content library, and then push each determined piece of content to be pushed to the target account. For example, if the preferred content types of the target account are hot news and cultural and tourism project categories, the server can filter out multiple pieces of hot news and cultural and tourism project content from the preset content library, and push the filtered multiple pieces of content to be pushed to the target account.

[0046] Optionally, in order to improve the efficiency of the server in selecting the content to be pushed from the preset content library and save the computing resources of the server, in an embodiment of the present invention, the push content partitions corresponding to each candidate content type can be stored in the preset content library. In this way, when the server needs to push content to the target account, it can quickly determine the content to be pushed from each storage partition corresponding to each preferred content type of the target account.

[0047] Optionally, the content push method provided by the embodiment of the present invention may further include: creating a periodic task with a preset time interval as the execution interval; wherein the task content of the periodic task includes: obtaining the target operation information table of the target account, and based on the operation attribute field of each target operation information, the content type field of each target operation information, and the attribute weights corresponding to each candidate operation attribute, determining each preferred content type corresponding to the target account from each candidate content type.

[0048] Exemplarily, an embodiment of the present invention may use XXL-JOB (an open source distributed task scheduling platform) as a scheduled task scheduling manager to manage periodic tasks. XXL-JOB can support dynamic modification of task status, for example, tasks can be started and tasks being executed can be terminated by modifying the task status, and the modification of the task status can take effect immediately. Specifically, after the server creates a periodic task, the periodic task can be added to XXL-JOB, and XXL-JOB can execute the periodic task regularly with a preset duration as the execution interval. Exemplarily, the preset duration can be 1 day, 3 days, 7 days or 1 month, which can be set by the operator of the APP according to actual needs. Of course, in actual applications, other types of scheduled task scheduling managers can also be used to manage periodic tasks, and the embodiments of the present invention are not limited to this.

[0049] In a possible implementation, each time the server executes a periodic task, it can generate a piece of user preference type information of the target account based on each preferred content type obtained by executing the task, and can add the piece of user preference type information to the user preference type information table.

[0050] Exemplarily, the key fields in the user preference type information table are shown in Table 1:

[0051] Table 1

[0052] Field Name Data Types Field Description content_label varchar (variable-length character string) Preferred content type user_id varchar Account ID start_time datetime Start time end_time datetime End time

[0053] As shown in Table 1, each piece of user preference type information in the user preference type information table may include four fields: preference content type, account identifier, start time, and end time. Among them, the account identifier field is used to record the preference content type of the target account recorded by the user preference type information; the preference content type field is used to record the specific preference content type; the start time field may indicate the start time of the preset historical time period corresponding to the data source (target operation information table) referenced by the user preference type information, and the end time field may indicate the end time of the preset historical time period corresponding to the data source referenced by the user preference type information.

[0054] It is understandable that in actual applications, the user preference type information table may also include other fields, such as fields corresponding to auto-increment primary key, record creation time, record update time, record creator, and record updater information, and the embodiments of the present invention do not limit this.

[0055] Since the preferred content types of the same user may change. Therefore, in an embodiment of the present invention, the server can periodically analyze the target operation information table of the target account at intervals of a preset time, and dynamically update the preferred content types corresponding to the target account according to the analysis results. When it is necessary to push content to the target account, the server can obtain the latest user preference type information of the target account, and determine the content to be pushed based on the preferred content types recorded in the latest user preference type information. In this way, the determined content to be pushed will be closer to the current needs of the user corresponding to the target account, which can further improve the accuracy of the content pushed by the APP to the user.

[0056] Optionally, obtaining the target operation information table of the target account may include: obtaining the source operation information table of each candidate account for historical pushed content; for each candidate account, taking the current candidate account as the target account, and based on the account identification field of each source operation information and the operation time field of each source operation information, determining the target operation information table of the target account from the source operation information table.

[0057] The candidate accounts may be all accounts successfully registered in the APP. The source operation information table includes each source operation information, and each source operation information includes each target operation information of each candidate account.

[0058] The account ID field can be used to record the account ID of the candidate account that operates the historical push content. For example, the account ID can be a unique string generated by the server for the registered account based on a predetermined random number generation rule when the user registers an account in the APP. The operation time field can be used to record the time when the user operates the historical push content.

[0059] For example, when executing a periodic task, the server can first filter out source operation information within a preset historical time period from each piece of source operation information based on the operation time field in each piece of source operation information. Then, based on the account identification field in each piece of source operation information within the preset historical time period, each piece of source operation information of each candidate account within the preset historical time period can be determined respectively, and each piece of source operation information of the current candidate account (i.e., the target account) within the preset historical time period is used as each piece of target operation information of the current candidate account.

[0060] In a possible implementation, when a user browses the pushed content in the APP, if he likes, comments, collects or shares a certain pushed content, the client will call the operation record interface of the server and transmit the operation data such as the operation attribute, content type, operation time and account ID of the operation to the server. The server can generate an operation record based on the received operation data, and can store the generated operation record in the source operation information table.

[0061] It should be noted that, in actual applications, a user may perform multiple operations on the same push content. In the embodiment of the present invention, the server may generate corresponding operation records for the multiple operations of the user.

[0062] Exemplarily, the key fields in the source operation information table are shown in Table 2:

[0063] Table 2

[0064] Field Name Data Types Field Description user_id varchar Account ID user_action int (integer type) Operational properties data_type varchar Content Type content_type int Content Format operation_time datetime Operation time

[0065] As shown in Table 2, each source operation information in the source operation information table may include an account identification field, an operation attribute field, a content type field, a content format field, and an operation time field. It is understandable that in actual applications, the source operation information may also include other fields, such as fields corresponding to information such as an auto-increment primary key, a record creation time, a record update time, a record creator, and a record updater, which are not limited in the embodiment of the present invention.

[0066] In an embodiment of the present invention, the server can filter out the target operation information table of each candidate account from the source operation information table by executing a periodic task, and can analyze each target operation information table to dynamically update the preferred content type of each candidate account. When it is necessary to push content to a candidate account, the server can quickly push content based on the latest preferred content type of the candidate account. It can be seen that in an embodiment of the present invention, the server performs the operation of pushing content to the target account and the operation of determining the preferred content type of the target account, and these two operations are independent of each other. In this way, when the server pushes content to the target account, it can directly call the user preference type information table of the target account, without having to re-analyze each target operation information table when pushing content, which can improve the efficiency of determining the content to be pushed and further enhance the user experience.

[0067] In the content push method provided by the embodiment of the present invention, before pushing content to the target account used by the user in the APP, the target operation information table for the historical push content of the target account can be obtained first. The target operation information table includes each target operation information within a preset historical time period, and a target operation information can record the relevant information of an operation performed by the corresponding user of the target account on a certain historical push content during the use of the APP. Specifically, a target operation information may include an operation attribute field and a content type field. The operation attribute field can represent which attribute operation the user has performed on the historical push content, and the content type field can represent the content type to which the historical push content belongs. Generally, when a user prefers to browse a certain type of push content, the push content of this type may be operated. In addition, when the user has different preferences for different types of push content, different attributes of operations may be performed on different types of push content. Based on this, the embodiment of the present invention can determine the attribute weights corresponding to each candidate operation attribute in advance according to the association between each candidate operation attribute and the user's preference degree. Furthermore, after obtaining each piece of target operation information, at least one preferred content type corresponding to the target account can be determined from each candidate content type based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute, and then the content is pushed to the target account based on each preferred content type. It can be seen that in the technical solution provided in the embodiment of the present invention, the operation attribute field and the content type field in each piece of target operation information of the target account can be analyzed to determine several content types (i.e., the preferred content types in the embodiment of the present invention) that the corresponding user of the target account may prefer. Then, based on each preferred content type, the content is pushed to the target account, and the pushed content will be closer to the preferences of the corresponding user of the target account. Therefore, the accuracy of the content pushed by the APP to the user can be improved, thereby reducing invalid pushes, thereby reducing the waste of push resources, and improving push efficiency.

[0068] In addition, the existing overly simplistic content push format will affect the user experience and usage time of the user during the use of the APP. However, the number of APPs is currently increasing, and the total time that users use each APP is limited. Therefore, how to improve the user's usage time and user experience of a specific APP within the limited usage time has become a problem that needs to be solved urgently. In the embodiment of the present invention, content push can be performed based on the user's preferred content type, so that the user's interest in browsing the APP can be increased, thereby improving the user's user experience and usage time during the use of the APP.

[0069] Reference Figure 2, is a flow chart of another content push method provided by an embodiment of the present invention. The method in this embodiment can be combined with various optional solutions in the content push method provided by the previous embodiment, and the content push method provided by the previous embodiment is further optimized. Figure 2 As shown, the specific steps include:

[0070] S210: Obtain a target operation information table of the target account for historical push content.

[0071] S220: Based on the operation attribute field of each piece of target operation information and the content type field of each piece of target operation information, respectively determine the initial evaluation parameters of the target account for each candidate operation attribute under each candidate content type.

[0072] The initial evaluation parameter is used to characterize the number of target operation information of each candidate operation attribute under each candidate content type in each target operation information. The higher the initial evaluation parameter, the more operations the target account has performed on the pushed content of the candidate content type. Conversely, the lower the initial evaluation parameter, the fewer operations the target account has performed on the pushed content of the candidate content type.

[0073] In the embodiment of the present invention, after acquiring the target operation information table, the server may analyze the operation attribute field and the content type field of each piece of target operation information, and count the candidate operation attributes and candidate content types corresponding to each piece of target operation information.

[0074] For example, if the candidate operation attributes include collection attribute and like attribute, if the user corresponding to the target account is user A, then collection(A) can be used to represent the statistical results of collection attribute in each target operation information of user A; and thumpup(A) can be used to represent the statistical results of like attribute in each target operation information of user A. If there are n types of candidate content types, then clabel i It can represent the statistical results of the collection attributes of the i-th candidate content type, (clabel i ,cnum i ) indicates that the number of contents of the i-th candidate content type collected by the user is cnum i Then, the statistical result of the collection attribute is collection(A)={(clabel1, cnum1), (clabel2, cnum2)…, (clabel i ,cnum i )…,(clabel n ,cnum n )}. tlabeli It can represent the statistical results of the like attribute for the i-th candidate content type, (tlabel i ,tnum i ) can represent the number of contents of the i-th candidate content type liked by the user is tnum i Then, the statistical result of the like attribute is thumpup(A)={(tlabel1, tnum1), (tlabel2, tnum2)…, (tlabel i ,tnum i )…,(tlabel n ,tnum n )}. In the embodiment of the present invention, cnum i As the initial evaluation parameter of the collection attribute under the i-th candidate content type, tnum i As the initial evaluation parameter of the like attribute under the i-th candidate content type.

[0075] S230: Based on the initial evaluation parameters of each candidate operation attribute under each candidate content type and the attribute weights corresponding to each candidate operation attribute, respectively determine the weighted evaluation parameters of the target account for each candidate content type.

[0076] For example, still taking the example that each candidate operation attribute includes a collection attribute and a like attribute, if w1 represents the attribute weight of the collection attribute, w2 represents the attribute weight of the like attribute, and preference(A) represents the weighted evaluation parameter of the i-th candidate content type of user A corresponding to the target account, then preference(A) can be determined by expression (1):

[0077] preference(A)=w1*cnum i +w2*tnum i (1)

[0078] Among them, 0≤w1≤1, 0≤w2≤1, w1+w2=1.

[0079] It should be noted that, in the embodiment of the present invention, cnum i and tnum i The value of cnum can be 0. i When tnum is 0, it means that user A has not collected the content of the i-th candidate content type in the preset historical time period; i When it is 0, it indicates that user A has not performed a "like" operation on the content of the i-th candidate content type within the preset historical time period.

[0080] S240: Determine preferred content types corresponding to the target account from candidate content types based on the weighted evaluation parameters.

[0081] The larger the weighted evaluation parameter of a candidate content type, the more likely the user is to be interested in the content of the candidate content type; conversely, the smaller the weighted evaluation parameter of a candidate content type, the less likely the user is to be interested in the content of the candidate content type. Therefore, in the embodiment of the present invention, after the server determines the weighted evaluation parameter of each candidate content type, it can determine the preferred content types corresponding to the target account from each candidate content type according to the size of each weighted evaluation parameter.

[0082] Optionally, based on each weighted evaluation parameter, determining each preferred content type corresponding to the target account from each candidate content type may include: sorting each candidate content type based on each weighted evaluation parameter to obtain a sorting result; based on the sorting result and a preset number, determining each preferred content type corresponding to the target account from each candidate content type.

[0083] The preset number may be a number determined in advance by an operator according to actual needs. For example, the preset number may be 3.

[0084] For example, if m represents the preset number, after the server determines the weighted evaluation parameters of each candidate content type, it can sort the candidate content types according to the size of each weighted evaluation parameter. Specifically, the sorting rule is that the candidate content types with larger weighted evaluation parameters are sorted first, and the candidate content types with smaller weighted evaluation parameters are sorted last. After obtaining the sorting result, the server can determine the m candidate content types at the top as the preferred content types corresponding to the target account.

[0085] S250: Push content to target accounts based on preferred content types.

[0086] In an embodiment of the present invention, on the basis of the above-mentioned embodiment, the operation attribute field and the content type field in each target operation information of the target account can be analyzed to statistically calculate the initial evaluation parameters of the target account for each candidate operation attribute under each candidate content type. Afterwards, the initial evaluation parameters of each candidate operation attribute under each candidate content type can be weighted in combination with the attribute weights of each candidate operation attribute to determine the weighted evaluation parameters of the target account for each candidate content type. Among them, the size of the weighted evaluation parameter of the candidate content type can indicate the possibility that the user is interested in the content of the candidate content type. It can be seen that in an embodiment of the present invention, by statistically analyzing each target operation information of the target account, an indicator for measuring the degree of preference of the user for each preferred content type, namely the weighted evaluation parameter, can be determined. Then, by selecting each preferred content type from each candidate content type according to the size of each weighted evaluation parameter, the accuracy of the determined preferred content type can be further improved, thereby further improving the accuracy of the content pushed by the APP to the user.

[0087] It should be noted that the content push method proposed in the embodiment of the present invention and the aforementioned embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, reference can be made to the aforementioned embodiment, and the beneficial effects of the aforementioned embodiment are also applicable to this embodiment.

[0088] Reference Figure 3 , which is a flow chart of another content push method provided by an embodiment of the present invention. The method in this embodiment can be combined with various optional solutions in the content push method provided by the previous embodiment to further optimize the content push method provided by the previous embodiment. Figure 3 As shown, the specific steps include:

[0089] S310: Obtain a target operation information table of the target account for historical push content.

[0090] S320: Based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute, determine at least one preferred content type corresponding to the target account from each candidate content type.

[0091] S330: When receiving a content acquisition request initiated by a client, determine a target account based on the login credentials carried in the content acquisition request.

[0092] Among them, the content acquisition request can be a request initiated by the client to the server by calling the content push interface provided by the server in response to the target account's access instruction to the APP. Exemplarily, the user can trigger the access instruction by clicking on the APP control in the display interface of the mobile terminal. The content acquisition request can carry the login credential (token) of the client calling the content push interface, and the server can obtain the login information of the target account that initiated the content acquisition request based on the token, and the login information may include an account identifier. The server can identify which target account initiated the content acquisition request based on the account identifier, so that the latest user preference type information of the target account can be obtained from the user preference type information table of the corresponding target account based on the account identifier, and the latest preferred content types of the target account can be determined based on the latest user preference type information.

[0093] Optional, such as Figure 4 As shown, Figure 3 The S330 in can be replaced by S3301-S3302:

[0094] S3301. When receiving a content acquisition request initiated by a client, the content acquisition request is intercepted by an interceptor, and request parameters carried in the content acquisition request are obtained.

[0095] S3302. Determine whether there is a security vulnerability based on the request parameters. If it is determined that there is no security vulnerability, determine the target account based on the login credentials carried in the content acquisition request.

[0096] Exemplarily, the server can concatenate the various fields in the request parameters into a string of a unified format, and then determine whether the string contains Structured Query Language (SQL) keywords. If the SQL keyword is included, it indicates that a SQL injection vulnerability has occurred, and the server can refuse to process the content acquisition request initiated by the client to achieve security protection; if the SQL keyword is not included, it indicates that no SQL injection vulnerability has occurred, and the server can normally process the content acquisition request initiated by the client. It is understandable that in actual applications, the server can also identify other types of security vulnerabilities, such as unauthorized vulnerabilities, which is not limited in the embodiments of the present invention.

[0097] S340: Based on the display parameter field carried in the content acquisition request and the preferred content types corresponding to the target account, determine at least one piece of content to be pushed from a preset content library.

[0098] The display parameter field may be a field in the request parameters, and may represent the amount of content that can be presented in the display page of the client.

[0099] In an embodiment of the present invention, the client can present each content to be pushed by real-time acquisition and real-time rendering. Exemplarily, when the server needs to determine the content to be pushed of each preferred content type from the preset content library, it can first determine several pieces of content to be pushed corresponding to the display parameter field, and return these pieces of content to be pushed to the client. After the client obtains these pieces of content to be pushed, it can render and present these pieces of content to be pushed. After the user browses these pieces of content to be pushed in the APP, he can perform trigger operations such as sliding or refreshing in the display interface of the APP, and the client can initiate a content update request to the server in response to the trigger operation. After receiving the content update request, the server can re-determine the pieces of content to be pushed corresponding to the display parameter field and return them to the client, and the client can render and update the display page according to the newly obtained pieces of content to be pushed.

[0100] For example, if the display parameter field indicates that the number of contents that can be presented in the display page of the client is 10, the server can return 10 contents to be pushed to the client each time.

[0101] Optional, such as Figure 4 As shown, Figure 3 The S340 in can be replaced by S3401-S3402:

[0102] S3401: Determine at least one candidate push content from a preset content library based on a first access permission field carried in a content acquisition request and a stored second access permission field.

[0103] S3402: Based on the display parameter field and the preferred content types, select the content to be pushed from the candidate push content.

[0104] The first access permission field is used to indicate the access permission of the target account stored on the client, and the second access permission field is used to indicate the access permission of the target account stored on the server.

[0105] Exemplarily, if the server determines based on the first access permission field that the content to be pushed accessible to the client includes content to be pushed A, content to be pushed B, and content to be pushed C, and determines based on the second access permission field that the content to be pushed accessible to the client includes content to be pushed A and content to be pushed B, then the server can determine content to be pushed A and content to be pushed B as candidate push content.

[0106] In an embodiment of the present invention, the access rights of the target account can be set according to the level of the target account, and the access rights of target accounts of different levels can be different. However, in actual applications, after the server updates the access rights of the target account, the client may not update the access rights of the target account in time due to factors such as network delay. Therefore, in an embodiment of the present invention, when the access rights of the client and the server are different, each content to be pushed can be determined based on the second access right field stored by the server. In this way, it can be ensured that the client can access the pushed content corresponding to the latest access rights of the target account.

[0107] Optionally, pushing content to the target account based on each preferred content type may also include: determining the format weight of the target account for each candidate content format based on the content format field of each target operation information; and pushing content to the target account based on each preferred content type and each format weight.

[0108] The content format field may be used to record the content format of the historical push content operated by the user. For example, each candidate content format may include articles and videos.

[0109] For example, if the target operation information table in the preset historical time period includes 1000 target operation information, and 200 of the 1000 target operation information correspond to articles, and 800 of the target operation information correspond to videos, then the format weight of the article can be 0.2, and the format weight of the video can be 0.8. For example, if the server returns 10 pieces of content to be pushed to the client each time, then 2 of the 10 pieces of content to be pushed can be articles, and 8 of the 10 pieces of content to be pushed can be videos.

[0110] In the embodiment of the present invention, the target account's format weight for each candidate content format can be determined based on the content format field of each target operation information. When determining the content to be pushed, the target account's preferred content types and format weights can be combined. In this way, the determined content to be pushed will be closer to the preferences of the corresponding user of the target account, thereby further improving the accuracy of the content pushed by the APP.

[0111] In addition, since the server has not collected the user's target operation information when the user first starts using the APP, it is unable to analyze the user's preferred content type based on the target operation information table. At this time, if the server receives a content acquisition request, it cannot obtain the user preference type information table. Therefore, in an embodiment of the present invention, the operator of the APP can determine some default push content in advance, and these default push contents can cover various candidate content types. When the user is in the initial stage of using the APP, when the server obtains the content acquisition request initiated by the client, if the user preference type information table of the target account is not obtained, the default push content can be sent to the client first, and the client will render the default push content for the user to browse.

[0112] S350: Return each content to be pushed to the client.

[0113] Exemplarily, if the content format of the content to be pushed is an article, the server can return the article code, title, introduction, release time, source, and article acquisition address and other content information of the content to be pushed to the client, and the client can render and present it according to the content information. If the content format of the content to be pushed is a video, the server can return the video header image, title, release time, source, and video acquisition address and other content information of the content to be pushed to the client, and the client can render and present it according to the content information. It can be understood that in actual applications, the type of content information returned by the server to the client can be set by the operator of the APP according to needs, and the embodiments of the present invention do not limit this.

[0114] In an embodiment of the present invention, based on the aforementioned embodiment, after receiving a content acquisition request initiated by a client, the server determines a target account based on the login credentials carried in the content acquisition request, and then determines at least one content to be pushed from a preset content library according to each preferred content type corresponding to the target account, and returns each content to be pushed to the client. It can be seen that in an embodiment of the present invention, there is no need for operators to manually configure the content to be pushed for each candidate account, and intelligent content push to users can be achieved. In addition, an embodiment of the present invention uses real-time acquisition and real-time rendering to return each content to be pushed to the client, which can improve the client's processing speed of the content to be pushed, so that the presentation effect of the content to be pushed is better.

[0115] It should be noted that the content push method proposed in the embodiment of the present invention and the aforementioned embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, reference can be made to the aforementioned embodiment, and the beneficial effects of the aforementioned embodiment are also applicable to this embodiment.

[0116] In order to more clearly describe the technical solution of the embodiment of the present invention, refer to Figure 5 , is a flow chart of another content push method provided by an embodiment of the present invention. Figure 5 As shown, the content push method specifically includes the following steps:

[0117] S510: The client transmits the operation data to the server in response to the user's operation on the pushed content in the APP.

[0118] S520: The server generates an operation record according to the received operation data, and stores the generated operation record in the source operation information table.

[0119] S530. The server executes periodic tasks through XXL-JOB, periodically analyzes the source operation information table, determines the user preference type information of each candidate account, and updates the user preference type information of each candidate account determined each time to the user preference type information table of each candidate account.

[0120] S540: The client invokes a content push interface provided by the server to initiate a content acquisition request to the server.

[0121] S550. The server determines the account ID of the target account based on the login credentials carried in the content acquisition request, obtains the latest user preference type information from the user preference type information table of the target account according to the account ID of the target account, and determines the preferred content types corresponding to the target account according to the latest user preference type information.

[0122] S560: The server determines at least one piece of content to be pushed from the preset content library based on the display parameter field carried in the content acquisition request and the preferred content types corresponding to the target account, and returns the content information of each piece of content to be pushed to the client.

[0123] S570: The client renders and displays the content according to the content information of each content to be pushed.

[0124] The content push method provided in the embodiment of the present invention belongs to the same inventive concept as the content push methods in the aforementioned embodiments. For details not described in detail in this embodiment, reference can be made to the embodiments of the aforementioned content push method.

[0125] Figure 6 This is a schematic diagram of the structure of a content push device provided by an embodiment of the present invention. The device includes: an acquisition module 610 , a determination module 620 , and a content push module 630 .

[0126] Exemplarily, the acquisition module 610 may execute S110 in the above method embodiment, the determination module 620 may execute S120 in the above method embodiment, and the content push module 630 may execute S130 in the above method embodiment.

[0127] Specifically, the acquisition module 610 is used to obtain a target operation information table of the target account for historical push content; wherein the target operation information table includes each target operation information within a preset historical time period;

[0128] A determination module 620, configured to determine at least one preferred content type corresponding to the target account from each candidate content type based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute;

[0129] The content push module 630 is used to push content to the target account based on each preferred content type.

[0130] Optionally, in a possible implementation manner, the determining module 620 is specifically configured to:

[0131] Based on the operation attribute field of each piece of target operation information and the content type field of each piece of target operation information, the initial evaluation parameters of the target account for each candidate operation attribute under each candidate content type are determined respectively; based on the initial evaluation parameters of each candidate operation attribute under each candidate content type and the attribute weights corresponding to each candidate operation attribute, the weighted evaluation parameters of the target account for each candidate content type are determined respectively; based on each weighted evaluation parameter, each preferred content type corresponding to the target account is determined from each candidate content type.

[0132] Optionally, in another possible implementation, the determining module 620 is further configured to:

[0133] The candidate content types are sorted based on the weighted evaluation parameters to obtain a sorting result; based on the sorting result and a preset number, the preferred content types corresponding to the target account are determined from the candidate content types.

[0134] Optionally, in another possible implementation manner, the content push device provided by the embodiment of the present invention may further include a task creation module;

[0135] The task creation module is used to create periodic tasks with a preset execution interval;

[0136] Among them, the task content of the periodic task includes: obtaining the target operation information table of the target account, and based on the operation attribute field of each target operation information, the content type field of each target operation information, and the attribute weights corresponding to each candidate operation attribute, determining the preferred content types corresponding to the target account from each candidate content type.

[0137] Optionally, in another possible implementation, the task content of the periodic task may specifically include:

[0138] Obtain a source operation information table for each candidate account for historical push content; wherein the source operation information table includes each piece of source operation information; for each candidate account, use the current candidate account as the target account, and based on the account identification field of each piece of source operation information and the operation time field of each piece of source operation information, determine the target operation information table of the target account from the source operation information table.

[0139] Optionally, in another possible implementation, the content push module 630 is specifically configured to:

[0140] When receiving a content acquisition request initiated by a client, the target account is determined based on the login credentials carried in the content acquisition request; at least one content to be pushed is determined from the preset content library based on the display parameter field carried in the content acquisition request and the preferred content types corresponding to the target account; and each content to be pushed is returned to the client.

[0141] Optionally, in another possible implementation, the content push module 630 is further configured to:

[0142] Based on the first access permission field carried in the content acquisition request and the stored second access permission field, at least one candidate push content is determined from the preset content library; based on the display parameter field and the preferred content types, the content to be pushed is screened from the candidate push contents.

[0143] Optionally, in another possible implementation, the content push module 630 is further configured to:

[0144] Based on the content format field of each target operation information, the format weight of the target account for each candidate content format is determined respectively; based on each preferred content type and each format weight, content is pushed to the target account.

[0145] The content push device provided in the embodiment of the present invention belongs to the same inventive concept as the content push method provided in the aforementioned embodiments. For details not fully described in the embodiment of the content push device, reference can be made to the relevant contents of the aforementioned method embodiments, and the corresponding beneficial effects can also be referred to the beneficial effect analysis of the aforementioned method embodiments.

[0146] Figure 7 A structural diagram of a content push device provided by an embodiment of the present invention. Figure 7 A block diagram of an exemplary content push device 12 suitable for implementing embodiments of the present invention is shown. Figure 7 The content push device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0147] like Figure 7As shown, the content push device 12 is in the form of a general-purpose computing device. The components of the content push device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0148] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0149] The content push device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the content push device 12, including volatile and non-volatile media, removable and non-removable media.

[0150] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory (i.e., Figure 7 The content push device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 7 not shown, usually called a "hard drive"). Although Figure 7 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0151] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0152] The content push device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may also communicate with one or more devices that enable a user to interact with the content push device 12, and / or may communicate with any device that enables the content push device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the content push device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. Figure 7 As shown, the network adapter 20 communicates with other modules of the content push device 12 via the bus 18. It should be understood that although Figure 7 Not shown, other hardware and / or software modules may be used in conjunction with the content push device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0153] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, such as implementing the content push method steps provided in an embodiment of the present invention, the method comprising: obtaining a target operation information table of the target account for historical push content; wherein the target operation information table includes each target operation information within a preset historical time period; based on the operation attribute field of each target operation information, the content type field of each target operation information, and the attribute weights corresponding to each candidate operation attribute, determining at least one preferred content type corresponding to the target account from each candidate content type; and pushing content to the target account based on each preferred content type.

[0154] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the content push method provided by any embodiment of the present invention.

[0155] The present embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a content push method as provided in the aforementioned embodiment of the present invention, the method comprising: obtaining a target operation information table of a target account for historical pushed content; wherein the target operation information table includes each piece of target operation information within a preset historical time period; based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute, determining at least one preferred content type corresponding to the target account from each candidate content type; and pushing content to the target account based on each preferred content type.

[0156] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0157] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0158] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0159] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or content push device. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0160] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0161] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A content push method, It is characterized in that The method comprises: Obtaining a target operation information table for a target account with respect to historical push content; wherein the target operation information table includes each piece of target operation information within a preset historical time period; Based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute, determining at least one preferred content type corresponding to the target account from each candidate content type; Content is pushed to the target account based on each of the preferred content types.

2. The content push method according to claim 1, It is characterized in that The determining, based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute, from each candidate content type, at least one preferred content type corresponding to the target account includes: Based on the operation attribute field of each piece of target operation information and the content type field of each piece of target operation information, respectively determine the initial evaluation parameters of the target account for each candidate operation attribute under each candidate content type; Based on the initial evaluation parameters of the candidate operation attributes under the candidate content types and the attribute weights respectively corresponding to the candidate operation attributes, respectively determine the weighted evaluation parameters of the target account for the candidate content types; Based on the weighted evaluation parameters, the preferred content types corresponding to the target account are determined from the candidate content types.

3. The content push method according to claim 2, It is characterized in that The determining, based on the weighted evaluation parameters, the preferred content types corresponding to the target account from the candidate content types includes: Sorting the candidate content types based on the weighted evaluation parameters to obtain a sorting result; Based on the ranking result and the preset number, the preferred content types corresponding to the target account are determined from the candidate content types.

4. The content push method according to claim 1, It is characterized in that The method further comprises: Create periodic tasks with preset execution intervals; Among them, the task content of the periodic task includes: obtaining the target operation information table of the target account, and based on the operation attribute field of each target operation information, the content type field of each target operation information, and the attribute weights corresponding to each candidate operation attribute, determining the preferred content types corresponding to the target account from the candidate content types.

5. The content push method according to claim 4, It is characterized in that The step of obtaining the target operation information table of the target account includes: Obtaining a source operation information table of each candidate account for the historical pushed content; wherein the source operation information table includes various pieces of source operation information; For each candidate account, the current candidate account is used as the target account, and based on the account identification field of each source operation information and the operation time field of each source operation information, the target operation information table of the target account is determined from the source operation information table.

6. The content push method according to claim 1, It is characterized in that The pushing of content to the target account based on each of the preferred content types includes: When receiving a content acquisition request initiated by a client, determining the target account based on the login credentials carried in the content acquisition request; Based on the display parameter field carried in the content acquisition request and the preferred content types corresponding to the target account, determining at least one piece of content to be pushed from a preset content library; Return each of the contents to be pushed to the client.

7. The content push method according to claim 6, It is characterized in that The determining at least one piece of content to be pushed from a preset content library based on the display parameter field carried by the content acquisition request and each of the preferred content types corresponding to the target account includes: Determine at least one candidate push content from the preset content library based on the first access permission field carried in the content acquisition request and the stored second access permission field; Based on the display parameter field and the preferred content types, the to-be-pushed content is selected from the candidate pushed content.

8. The content push method according to any one of claims 1 to 7, It is characterized in that The pushing of content to the target account based on each of the preferred content types includes: Based on the content format field of each piece of target operation information, respectively determine the format weight of the target account for each candidate content format; Based on the preferred content types and the format weights, content is pushed to the target account.

9. A content push device, It is characterized in that The device comprises: An acquisition module, used to acquire a target operation information table of a target account for historical push content; wherein the target operation information table includes each target operation information within a preset historical time period; a determination module, configured to determine at least one preferred content type corresponding to the target account from each candidate content type based on the operation attribute field of each piece of target operation information, the content type field of each piece of target operation information, and the attribute weights corresponding to each candidate operation attribute; The content push module is used to push content to the target account based on each of the preferred content types.

10. A content push device, It is characterized in that The content push device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the content pushing method as described in any one of claims 1-8.

11. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the content pushing method as described in any one of claims 1 to 8 is implemented.

Images