Content push method, device, server and storage medium
By selecting user characteristics layer by layer in the existing content push system, querying users with the first characteristic from the target database and further selecting users with the second characteristic, and pushing corresponding content to them, the problem of inaccurate push in the existing technology is solved, and more efficient resource utilization is achieved.
Patent Information
- Application Number
- CN202080094717.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-02-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2040-02-28
AI Technical Summary
Existing content delivery methods lack precision, leading to wasted resources.
By querying the target database for the first target user corresponding to the first feature, and selecting users with the second feature as the second target user, content corresponding to the second feature is pushed to them.
It improves the accuracy of users and content in content delivery, enhancing the targeting and value of the push notifications.
Smart Images

Figure CN115023933B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of content push, and more specifically, to a content push method, device, server and storage medium. Background Art
[0002] When users interact with servers through electronic devices, a large amount of data is generated. These data can represent the characteristics of users, so that content can be pushed to users based on these data. In existing push methods, the pushed users and content are usually not accurate enough, resulting in a waste of push resources. Summary of the invention
[0003] In view of the above problems, the present application proposes a content push method, device, server and storage medium to improve the above problems.
[0004] In a first aspect, an embodiment of the present application provides a content push method, the method comprising: querying a first target user corresponding to a first feature from a target database, the target database including user data updated in real time, the user data including features corresponding to each user, and users corresponding to each feature; selecting a user with a second feature from the first target users as a second target user, the second feature being different from the first feature; and pushing content to be pushed corresponding to the second feature to the second target user.
[0005] In the second aspect, an embodiment of the present application provides a content push device, which includes: a first query module, used to query a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, and the user data includes features corresponding to each user, and users corresponding to each feature; a second query module, used to select a user with a second feature from the first target users as a second target user, wherein the second feature is different from the first feature; and a push module, used to push the content to be pushed corresponding to the second feature to the second target user.
[0006] In a third aspect, an embodiment of the present application provides a server, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are executed by the processors to perform the above-mentioned method.
[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a program code is stored. The program code can be called by a processor to execute the above method.
[0008] The content push method, device, server and storage medium provided in the embodiments of the present application first select a user with a first feature as the first target user based on a target database updated in real time, and then further select a user with a second feature as the second target user based on the first target user. When pushing content, the content corresponding to the second feature is pushed to the second target user, so that the pushed user is a user accurately selected based on the first feature through the second feature, and the pushed content corresponds to the second feature, which improves the accuracy of the pushed user and the accuracy of the pushed content. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0010] Figure 1 A flow chart of a content push method provided by an embodiment of the present application is shown.
[0011] Figure 2 A flow chart of a content push method provided by another embodiment of the present application is shown.
[0012] Figure 3 A flowchart of a content push method provided by yet another embodiment of the present application is shown.
[0013] Figure 4 A flow chart of a content push method provided in yet another embodiment of the present application is shown.
[0014] Figure 5 A functional module diagram of a content push device provided in an embodiment of the present application is shown.
[0015] Figure 6 A structural block diagram of a server provided in an embodiment of the present application is shown.
[0016] Figure 7 It is a storage unit of an embodiment of the present application for storing or carrying program codes for implementing the content push method according to an embodiment of the present application. DETAILED DESCRIPTION
[0017] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.
[0018] In the process of interaction between the user and the server through the electronic device, a large amount of data will be generated, from which the characteristics of the user can be analyzed. The characteristics of the user can indicate one or more user information such as the user's preferences, personality, financial status, family status, travel mode, circle of friends, etc. For example, the characteristics can be the user's attribute information such as the user's age, gender, occupation, constellation, birthday, etc. determined from the user's registered information or other methods; the characteristics can also be the user behavior characteristics generated by the user's operation of the electronic device, such as the number of times the user opens a certain software, the number of times a certain product is browsed, the number of a certain type of product is browsed, the time of downloading a certain program, etc. Among them, the attribute information of each user can be information with small changes, such as usually at least a preset time interval may change, for example, for the same user, the gender, constellation, birthday, etc. are basically unchanged, and the age, occupation, etc. change slowly, usually It takes a long time to change. User behavior characteristics are generated by the user's operation of the electronic device. If the user continues to operate the electronic device, the user behavior characteristics will change quickly, such as usually within a time period, such as a day, will change.
[0019] When pushing content, users are selected for push based on their characteristics, so that target users who need to be maintained can be selected more accurately for push. Therefore, the embodiments of the present application provide a content push method, device, server, and storage medium, which select users for push layer by layer according to their characteristics, so as to accurately select users to push content. The content push method, device, server, and storage medium provided by the embodiments of the present application will be described in detail through specific embodiments.
[0020] See also Figure 1 , shows a content push method provided by an embodiment of the present application. Specifically, the method includes:
[0021] Step S110: querying a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, and the user data includes features corresponding to each user and users corresponding to each feature.
[0022] Step S120: Selecting a user with a second feature from the first target users as a second target user, where the second feature is different from the first feature.
[0023] Step S130: Pushing the content to be pushed corresponding to the second feature to the second target user.
[0024] In this implementation, the method of selecting users may be to first select users with the first characteristic as target users, and then select users with the second characteristic from the first target users as second target users, thereby selecting users with the second characteristic from users with the first characteristic, and accurately selecting users to whom content is to be pushed. The content to be pushed corresponding to the second characteristic is pushed to the second target user, and since the pushed content has a corresponding relationship with the second characteristic, more accurate content can be pushed to the selected user.
[0025] The present application also provides an embodiment, in which the second feature may be determined. Figure 2 , the method provided in this embodiment includes:
[0026] Step S210: querying a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, and the user data includes features corresponding to each user and users corresponding to each feature.
[0027] The correspondence between users and features can be stored in the target database as user data. The correspondence can include features corresponding to each user and users corresponding to each feature. Features corresponding to a user represent features possessed by the user; users corresponding to features represent users possessing the features.
[0028] Specifically, users and features can be stored through two corresponding relationships. In one corresponding relationship, the features corresponding to each user can be constructed based on a forward index, that is, the user's identity information can be used as an index keyword to index all features corresponding to the user. For example, user A corresponds to features a1, a2, and a3, which means that the user has features a1, a2, and a3. The user's features a1, a2, and a3 can be indexed through the identity information of user A. In another corresponding relationship, the user corresponding to each feature is constructed based on an inverted index, that is, the feature can be used as an index keyword to index all users with the feature. For example, if the users with feature a1 are A, B, and C, then feature a1 corresponds to features A, B, and C. Through feature a1, it can be indexed that the users with feature a1 are A, B, and C.
[0029] The user data in the target database can be updated in real time. The real-time update means that if new user data is generated, the new user data is stored in the target database. For example, for a user, if a certain software is opened once, the number of times the software is started, which is a user behavior feature, increases by one. In the user behavior feature, the number of times the user corresponding to the software is opened increases by one.
[0030] In addition, the target database may also store user data that has been generated before, that is, user data that was generated before the current moment, such as user data that was generated within the most recent preset time period.
[0031] In the embodiment of the present application, the target database is not limited to a specific database, for example, it can be a storage engine. The storage engine can have analysis capabilities. In addition, optionally, the content push method of the embodiment of the present application can be implemented by the storage engine based on real-time updated user data. The storage engine can be a server that executes the method of the embodiment of the present application.
[0032] When content push is required, the first feature can be determined based on the type of user to whom the content needs to be pushed, and the user corresponding to the first feature can be queried from the target database as the first target user. For example, for an important business, it is necessary to analyze the active users in the past month to determine what kind of marketing plan is more helpful in improving the retention of this group of users in a targeted manner. The active time in the past month can be used as the first feature. Among them, whether the user is active can be defined according to the needs of each software or platform. For example, for this important business, if the user logs in on a certain day, the user is considered active on that day, and the user's recent active time is the number of consecutive active days.
[0033] As an implementation mode, if the server executes the method, the server can perform user search and push in response to the push request of the push terminal. The first feature can be sent by the push terminal.
[0034] As another implementation, the first feature may also be determined by the server according to a predetermined push logic. For example, when the number of users corresponding to a certain feature reaches a certain preset amount, it indicates that there are many users with this feature, and there may be more receiving users when pushing content, and the pushed content can play a greater value, so this feature is used as the first feature. For another example, if the number of users of a certain feature has grown rapidly recently, such as the daily growth rate is higher than the preset growth rate, it means that users with this feature have potential for development, and this feature can be used as the first feature for user selection push to attract more users.
[0035] When querying the target database for users corresponding to the first feature, you can query which users correspond to the first feature based on the users corresponding to each feature, and define the found users as the first target users. For example, if the first feature is the gender feature of male, then search for users corresponding to the gender feature of male, that is, search for male users in the target database as the first target users. For another example, if the first feature is the active time in the last month, then search for users corresponding to the feature of active time in one month as the first target users, and the first target users are active users in the last month. It can be understood that in the embodiment of the present application, the first target user may be one user or multiple users, and the specific number is not limited in the embodiment of the present application, and can be determined by the actual query results.
[0036] Optionally, in the embodiment of the present application, the first feature may be a user behavior feature. Since the user behavior feature changes rapidly, and the user data in the target database is updated in real time, it can be ensured that the first target user queried is a more timely user, and the search result is more accurate.
[0037] Step S220: Determine the second feature.
[0038] Optionally, in the embodiment of the present application, it may also include determining a second feature that is different from the first feature, so as to further select users based on the first target users, so as to make the selected users more accurate.
[0039] In the embodiment of the present application, in order to select a user who is more suitable for content push from the first target users, the second feature can be determined based on the found first target users.
[0040] Specifically, the second feature may be determined according to a feature corresponding to the first target user that is different from the first feature. That is, among the features corresponding to the first target user, there is a feature that is different from the first feature, and the second feature is determined according to the feature that is different from the first feature.
[0041] As an implementation mode, the first target user may include multiple users, each of which corresponds to multiple features. The method of determining the second feature according to the feature different from the first feature corresponding to the first target user may be to determine the number of users in the first target user corresponding to each feature from the features different from the first feature corresponding to the first target user; and obtain one or more features corresponding to the largest number of users as the second feature.
[0042] That is to say, each user in the first target users has corresponding features, and the features between different users overlap. For each feature that is different from the first feature and corresponds to the first target users, there may be multiple users in the first target users corresponding to it. Then, one or more features corresponding to the largest number of users can be selected as the second feature.
[0043] Among them, when determining the number of users corresponding to each feature, the number of users in the first target users corresponding to each feature can be determined based on the inverted index, that is, based on the users with the feature corresponding to each feature. The number of users can be represented by a quantitative value or by a proportion. The higher the proportion of the total number of first target users, the greater the number. Therefore, when selecting users through the second feature determined by this implementation, the various second features selected are features corresponding to a large number of users, and the push of the content to be pushed corresponding to each second feature can maximize its push value.
[0044] For example, the first target users include users A, B, and C. Among the features different from the first feature, the features corresponding to user A include features a1, a2, and a3, the features corresponding to user B include a1, b1, and b2, and the features corresponding to user C include a1, a2, and b2. Then it can be determined that the features corresponding to the first target users include a1, a2, a3, b1, and b2. The number of users corresponding to a1 is 3, the number of users corresponding to a2 is 2, the number of users corresponding to b2 is 2, the number of users corresponding to a3 is 1, and the number of users corresponding to b1 is 1. Then the feature that corresponds to the largest number of users is a1, and a1 is selected as the second feature.
[0045] Optionally, in the embodiment of the present application, the features that characterize the characteristics of the user can be divided into multiple categories, and the different contents in each category are different features, and the features of different categories are different features. For example, when the categories are gender, occupation, constellation, active time, etc., the corresponding contents of each category are different features in the category, such as the different features in the gender category are male and female, the different features in the occupation category include white-collar workers, primary and secondary school students, teachers, shopping services, college students and other occupations; the different features in the constellation category include 12 constellations such as Aries and Gemini; the different features in the active time can be different numbers of time units such as 1 day, 2 days, 3 days, etc.
[0046] When selecting users with the second feature from the first target users, a feature different from the category where the first feature is located can be used as the second feature, that is, the second feature can be determined from a category different from the category where the first feature is located. The specific category is not limited, and can be all categories different from the category where the first feature is located, or a specific category that is different from the category where the first feature is located. For example, if the first feature is the active 30 days feature in the active time category, the second feature can be a feature in the occupation category.
[0047] When determining the number of users in the first target users corresponding to each feature from the features corresponding to the first target users, the number of users corresponding to each feature can be determined from the features in the specified category corresponding to the first target users. For example, from the various occupations in the occupational category corresponding to the first target users, the number of users in the first target users corresponding to each occupation can be determined, that is, the number of users corresponding to various occupations in the first target users can be determined, such as the number of white-collar users, the number of primary and secondary school students, the number of teachers, etc.
[0048] In addition, whether one feature or multiple features are selected as the second feature is not limited in the embodiments of the present application. If one feature is selected as the second feature, the feature with the largest number of users can be selected; if multiple features are selected, such as a preset number of features, multiple features ranked high in descending order of the number of users can be selected; in addition, a feature with a number of users greater than a specified number can also be selected as the second feature.
[0049] As another implementation manner, the second feature may be determined according to the feature corresponding to the first target user by selecting a feature that is the same as the target feature from the features corresponding to the first target user as the second feature.
[0050] Specifically, it may be determined that a target feature is a feature possessed by a user to whom content can be pushed, and the target feature is different from the first feature. The target feature may include multiple features, and the feature corresponding to the first target user may include multiple features. From the features corresponding to the first target user, a feature having an intersection with the target feature is determined as the second feature.
[0051] For example, the features different from the first feature corresponding to the first target user include a1, b1, and c1, and the target features include a1 and c1, then a1 can be determined as the second feature.
[0052] In this embodiment, the target feature may be a feature in a category different from the category in which the first feature belongs. The target feature may be used to select a specified user. For example, if the target feature is after-sales service, users with the target feature represent users who need after-sales service; or if the target feature is customer service marketing, users with the target feature represent users who need customer service marketing.
[0053] As another implementation, there may be a corresponding relationship between different contents to be pushed and features. If a feature corresponds to content to be pushed, the content to be pushed corresponding to the feature may be pushed. Therefore, the method of determining the second feature according to the feature different from the first feature corresponding to the first target user may be to select the feature corresponding to the content to be pushed from the features different from the first feature corresponding to the first target user as the second feature. For example, the first target user corresponds to features a1, b1, and c1 different from the first feature. If a1 and b1 correspond to content to be pushed, and c1 does not correspond to content to be pushed, a1 and b1 are selected as the second features.
[0054] In this embodiment, when selecting the second feature, it can also be selected from other categories different from the category in which the first feature belongs, such as determining the features corresponding to the first target user in the specified category, and obtaining the features corresponding to the content to be pushed from the determined features as the second feature.
[0055] In addition, optionally, in the embodiment of the present application, the second feature may also be sent by a push terminal.
[0056] Optionally, in the embodiment of the present application, the second feature may be a user behavior feature. Since the user behavior feature changes rapidly, and the user data in the target database is updated in real time, it can be ensured that the second target user queried is a more timely user, and the search result is more accurate.
[0057] Optionally, the second feature may be a feature that can characterize user preferences and measure whether the user retains the current service, so that the content corresponding to the second feature meets the user's preferences and is more attractive to the user. When the corresponding current service is pushed, it can be more helpful to retain the user.
[0058] Optionally, the second feature may be a feature with a higher importance level. For example, different features are marked with different importance levels, and one or more features with the highest importance level are selected as the second feature.
[0059] Step S230: Selecting a user with a second characteristic from the first target users as a second target user.
[0060] Some of the first target users have the second feature, while some may not have the second feature. After determining the second feature, users with the second feature can be selected from the first target users to achieve accurate selection of users. Users with the second feature selected from the first target users are defined as second users.
[0061] In the embodiment of the present application, when selecting the second target user from the first target users, the selection may be based on different correspondences between users and features, for example, the selection may be based on a forward index or a reverse index.
[0062] In one implementation, when selecting based on the forward index, a user having a second characteristic may be selected from the first target users according to the characteristic corresponding to each user as the second target user.
[0063] Optionally, the user is used as an index keyword to index the features corresponding to each user, and it is determined whether the features corresponding to each user include the second feature. The user including the second feature is selected as the second target user. For example, the target database includes users A, B, C, D, etc., and the second feature is feature a1. If the features corresponding to user A include feature a1, user A is selected, otherwise user A is not selected; other users are determined to be selected in the same way.
[0064] In another implementation, selection may be performed based on an inverted index. Specifically, based on the users corresponding to each feature, the user corresponding to the second feature may be selected as the third target user; and the intersection of the third target user and the first target user may be obtained from the third target user as the second target user.
[0065] Optionally, each feature in the second feature can be used as an index keyword, each feature constructed based on the inverted index corresponds to all users, and all users corresponding to the second feature are indexed as third target users. Users who are the same as the first target users are selected from the third target users as second target users.
[0066] Optionally, in an embodiment of the present application, if the second feature includes more than one feature, when obtaining second target users having the second feature among the first target users, users among the first target users corresponding to different second features can be obtained as second target users corresponding to different second features.
[0067] Optionally, if there are duplicate users among the second target users corresponding to different second features, a deduplication operation may be performed, and only one duplicate user is retained among the second target users corresponding to all the second features, so as to avoid repeated push of the same user.
[0068] Optionally, in the embodiment of the present application, after determining the second target user, the users who are prohibited from pushing content can also be removed from the second target users. For example, if the user turns off content push, or the user has complained about the content push operation, these users can no longer be pushed. In the embodiment of the present application, a feature can be used to represent the feature of prohibiting content push, and the feature is defined as the third feature.
[0069] After determining the second target users, users with the third feature among the second target users may be searched, and users with the third feature may be deleted from the second target users to serve as updated second users for content push.
[0070] Step S240: Pushing the content to be pushed corresponding to the second feature to the second target user.
[0071] When the second target user is determined, the content may be pushed to the second target user. In order to make the pushed content more accurate and to better influence the user, the content to be pushed corresponding to the second feature may be pushed to the second target user.
[0072] Optionally, in an embodiment of the present application, the stored content to be pushed may correspond to a content tag, which characterizes the characteristics of the content to be pushed. In addition, a preset correspondence between content tags and characteristics may also be stored. When pushing the content to be pushed corresponding to the second characteristic to the second target user, the content to be pushed may correspond to the content tag, and the content tag corresponding to the second characteristic may be determined. When pushing the content corresponding to the second characteristic to the second target user, the content corresponding to the content tag corresponding to the second characteristic corresponding to the second target user is pushed to the second target user. For example, if the second characteristic corresponding to the second target user is characteristic a1, the content corresponding to the content tag corresponding to characteristic a1 is pushed to the second target user.
[0073] In addition, in the embodiment of the present application, the target database includes multiple contents to be pushed, and the second feature may include multiple features, and different second features correspond to different contents to be pushed. When pushing the contents to be pushed corresponding to the second feature to the second target user, different contents to be pushed are pushed to the second target users corresponding to different features, and the pushed contents are the contents corresponding to the corresponding second features.
[0074] Specifically, different contents to be pushed corresponding to different second features can be selected from the contents to be pushed; the selected contents to be pushed are pushed to the second target user with the corresponding second feature. For example, the second features include a1 and b1, the second target user corresponding to a1 is U1, the second target user corresponding to b1 is U2, U1 may include multiple users, and U2 may include multiple users. When pushing, the contents to be pushed corresponding to a1 are pushed to U1, and the contents to be pushed corresponding to b1 are pushed to U2.
[0075] In addition, when the second feature includes multiple features, the method of selecting the content to be pushed corresponding to different second features from the content to be pushed can be to determine the content tags corresponding to each second feature according to the preset correspondence between the content tag and the feature; select the content to be pushed corresponding to each determined content tag as the content to be pushed corresponding to the corresponding second feature, so as to achieve automatic matching of users and content. It can be understood that the corresponding second feature is the second feature corresponding to the selected content tag.
[0076] In an embodiment of the present application, a first target user is selected based on a first feature, and then a second target user with a second feature is selected based on the first target user, and content corresponding to the second feature is pushed to the second target user, thereby making the pushed content more targeted to the user and better maximizing the value of the pushed content.
[0077] For example, in a specific usage scenario, in order to more specifically improve the retention of this group of users for the active users in the last month, the activeness in the last month can be used as the first feature, and the active users in the last month can be selected as the first target users to push content to this part of users. However, in order to increase the attractiveness of content to users, it is necessary to match the characteristics of the content and the users. Different users have different characteristics, and their preferences are different. If push is performed based on the different characteristics of all users, the push volume will be too large and the value will be too low. Therefore, users with a second feature can be selected from the first target users. The users with the second feature can be users with a relatively high proportion or users with high importance. Content corresponding to the second feature can be pushed to this part of users to improve the accuracy of content push and the value of push.
[0078] This application also provides an embodiment, in which closed-loop adjustments can be made to features, pushed content, or users. Figure 3 , the method comprising:
[0079] Step S310: querying a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, and the user data includes features corresponding to each user and a user corresponding to each feature.
[0080] Step S320: Selecting a user with a second feature from the first target users as a second target user, where the second feature is different from the first feature.
[0081] Step S330: Pushing the content to be pushed corresponding to the second feature to the second target user.
[0082] Steps S310 to S330 may refer to the same or corresponding steps in the above-mentioned embodiments, and will not be described in detail here.
[0083] Optionally, in the embodiment of the present application, ordinary content or content that is of interest to most users verified by big data can be pushed to users who are different from the second target users among the first target users. Therefore, a user who is different from the second target user can be determined from the first target users as a fourth user; preset content can be pushed to the fourth user, which is content that most users may be interested in. Therefore, content can also be pushed to users who do not have the second characteristic, and when the pushed content is used for marketing, marketing can be achieved for all users who meet the first characteristic.
[0084] Step S340: Acquire the operation data of the second target user on the content to be pushed.
[0085] After pushing content to the second target user, the user may perform operations based on the pushed content, thereby generating operation data. The operation data includes clicks, views, and viewing time; purchases of goods, adding to shopping carts, etc. The server can obtain the operation data generated by each target user's operations on the pushed content.
[0086] Step S350: Optimize the data in the target database according to the acquired operation data.
[0087] After the operation data is obtained, it can be determined whether the data stored in the target database is accurate, for example, whether the correspondence between the features and the content to be pushed is accurate, whether the correspondence between the features and the user is accurate, etc.
[0088] If it is inaccurate, the data in the target database may be optimized. For example, at least one of the following adjustments may be made: adjusting the content to be pushed corresponding to the second feature according to the acquired operation data; adjusting the user corresponding to the second feature according to the acquired operation data.
[0089] In a specific implementation, if the operation data of the second target user on the content to be pushed meets the preset conditions, it can be considered that the data stored in the target database may be accurate. If the operation data of the second target user on the content to be pushed does not meet the preset conditions, it can be considered that the data stored in the target database may not be accurate, and the data in the target database can be optimized. The preset conditions can be set according to different contents to be pushed. For example, for article-type content to be pushed, the proportion of second target users who have viewed the content to be pushed for a preset time is lower than the preset proportion of the total second target users; for commodity-type content to be pushed, the proportion of second target users who have added the content to the shopping cart is lower than the preset proportion, etc. The preset proportions set for different contents to be pushed may be different.
[0090] In addition, according to the acquired operation data, the adjustment of the content to be pushed corresponding to the second feature may be to replace the content to be pushed corresponding to the second feature. According to the acquired operation data, the adjustment of the user corresponding to the second feature may be to reanalyze the user's data and determine the user corresponding to the second feature based on the result of the reanalysis; or to no longer regard the user who has not viewed the content to be pushed as the user corresponding to the second feature. It can be understood that if the user corresponding to the second feature changes, the corresponding relationship between the second feature and the user in the forward index and the inverted index will be changed accordingly.
[0091] When optimizing the data in the target database according to the acquired operation data, the above-mentioned different optimization methods may be selected at different times, or user methods may be selected at the same time for optimization. After the optimization, the second target user is selected again according to the optimized data with the same first feature and second feature to push the content corresponding to the second feature, and the accuracy of the data stored in the target database is determined again according to the operation data of the second target user until the data stored in the target database is accurate.
[0092] In this implementation, after pushing the content, the data in the target database can be optimized based on the user's operation data on the pushed content, so that the correspondence between features and users and between features and content is more accurate. Through continuous optimization, the users to whom the content is pushed can be more precise, and the content to be pushed can be more targeted to the users.
[0093] The present application also provides an embodiment. In this embodiment, information can be obtained from the selected second target user for other services. Figure 4 As shown, the method of this embodiment includes:
[0094] Step S410: querying a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, and the user data includes features corresponding to each user and a user corresponding to each feature.
[0095] Step S420: Selecting a user with a second feature from the first target users as a second target user, where the second feature is different from the first feature.
[0096] Step S430: Obtain basic information of the second target user.
[0097] In this embodiment, the second target user who needs to be used in certain specified business scenarios can be selected through the first feature and the second feature, and the basic information of the second target user can be obtained for use in the specified business scenario. For example, the basic information of the second target user corresponding to the features such as after-sales service and customer service marketing can be obtained for targeted communication in scenarios such as after-sales service and overcoming influence.
[0098] There is no limitation on what information the basic information specifically includes, such as address, age, etc. In addition, optionally, the basic information of the user may also be some characteristics of the user.
[0099] The present application embodiment also provides a content push device 500. Figure 5 The device 500 includes: a first query module 510, used to query a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, wherein the user data includes features corresponding to each user and a user corresponding to each feature; a second query module 520, used to select a user having a second feature from the first target users as a second target user, wherein the second feature is different from the first feature; and a push module 530, used to push content to be pushed corresponding to the second feature to the second target user.
[0100] Optionally, the device further includes a feature determination module, configured to determine the second feature according to a feature corresponding to the first target user that is different from the first feature.
[0101] Optionally, the first target user includes multiple users, each of which corresponds to multiple features. The feature determination module can be used to determine the number of users in the first target user corresponding to each feature from the features that are different from the first feature and correspond to the first target user; and obtain one or more features that correspond to the largest number of users as the second feature.
[0102] Optionally, the feature determination module may be configured to select a feature that is the same as the target feature from features that are different from the first feature and correspond to the first target user, as the second feature.
[0103] Optionally, the feature determination module may be configured to select, from features corresponding to the first target user and different from the first features, a feature corresponding to the content to be pushed as the second feature.
[0104] Optionally, the second feature includes multiple features, and the target database includes multiple content to be pushed. The push module 530 may include a content selection unit, which is used to select content to be pushed corresponding to different second features from the content to be pushed; and a push unit, which is used to push the selected content to be pushed to a second target user with the corresponding second feature.
[0105] Optionally, the content selection unit may be configured to determine the content tags corresponding to each second feature according to a preset correspondence between the content tags and the features; and select the content to be pushed corresponding to each determined content tag as the content to be pushed corresponding to the corresponding second feature.
[0106] Optionally, the second query module 520 may be configured to select a user having a second characteristic from the first target users as the second target user according to the characteristic corresponding to each user.
[0107] Optionally, the second query module 520 may be configured to select a user corresponding to the second feature as a third target user based on the users corresponding to each feature; and obtain an intersection with the first target user from the third target user as the second target user.
[0108] Optionally, the device may further include a data elimination module, configured to search for users with a third feature among the second target users, wherein the third feature is a feature for prohibiting content push; and to delete users with the third feature from the second target users as updated second users.
[0109] Optionally, the device may further include a third query module, configured to determine a user different from the second target user from the first target users as a fourth user; and the push module may further be configured to push preset content to the fourth user.
[0110] Optionally, the device may further include an operation data acquisition module, used to acquire the operation data of the second target user on the content to be pushed; and an optimization module, used to optimize the data in the target database according to the acquired operation data.
[0111] Optionally, the optimization module can be used to perform at least one of the following optimizations: adjusting the content to be pushed corresponding to the second feature according to the acquired operation data; adjusting the user corresponding to the second feature according to the acquired operation data.
[0112] Optionally, the feature corresponding to each user in the target database is constructed based on a forward index; and the user corresponding to each feature is constructed based on an inverted index.
[0113] Optionally, the target database is a storage engine.
[0114] Optionally, the first feature is a user behavior feature, or the second feature is a user behavior feature, wherein the user behavior feature is generated by a user's operation on the electronic device.
[0115] In the embodiments of the present application, different implementations of different embodiments can be combined with each other if it is logical.
[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the above-mentioned method embodiments can refer to each other; the specific working processes of the above-mentioned devices and modules can refer to the corresponding processes in the aforementioned method embodiments, which will not be repeated here.
[0117] In several embodiments provided in the present application, the coupling between modules may be electrical, mechanical or other forms of coupling.
[0118] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. Each module can be configured in different electronic devices or in the same electronic device, which is not limited by the embodiments of the present application.
[0119] Please refer to Figure 6 , which shows a structural block diagram of a server 600 provided in an embodiment of the present application. The electronic device may include one or more processors 610 (only one is shown in the figure), a memory 620 and one or more programs. Among them, the one or more programs are stored in the memory 620 and are configured to be executed by the one or more processors 610. The one or more programs are executed by the processor to perform the method described in the above embodiment.
[0120] The processor 610 may include one or more processing cores. The processor 610 uses various interfaces and lines to connect various parts of the entire server 600, and executes various functions and processes data of the server 600 by running or executing instructions, programs, code sets or instruction sets stored in the memory 620, and calling data stored in the memory 620. Optionally, the processor 610 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 610 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 610, but may be implemented separately through a communication chip.
[0121] The memory 620 may include a random access memory (RAM) or a read-only memory (ROM). The memory 620 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the electronic device during use, etc.
[0122] Please refer to Figure 7 , which shows a structural block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable storage medium 700 stores program codes, which can be called by a processor to execute the method described in the above method embodiment.
[0123] The computer readable storage medium 700 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk, or a ROM. Optionally, the computer readable storage medium 700 includes a non-transitory computer-readable storage medium. The computer readable storage medium 700 has storage space for program code 710 that performs any method step in the above method. These program codes can be read from or written to one or more computer program products. The program code 710 can be compressed, for example, in an appropriate form.
[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A content push method, It is characterized in that The method comprises: Querying a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, the user data includes features corresponding to each user, and a user corresponding to each feature, wherein the first feature includes at least one of a feature that the number of corresponding users in the target database reaches a preset number and a feature that a daily growth rate of the number of corresponding users in the target database is higher than a preset growth rate; According to the users corresponding to each feature, users corresponding to the second feature are selected as the third target users, wherein the second feature includes at least one of after-sales service and customer service marketing, users with the after-sales service represent users who need after-sales service, users with the customer service marketing represent users who need customer service marketing, and the third target users represent users who need to have targeted communication later; Acquire an intersection between the third target user and the first target user as a second target user; Searching for a user with a third feature among the second target users, where the third feature is a feature that prohibits content from being pushed; Deleting users having the third feature from the second target users as updated second users; Push the to-be-pushed content corresponding to the second feature to the updated second user.
2. The method according to claim 1, It is characterized in that Before selecting the user corresponding to the second feature as the third target user according to the user corresponding to each feature, the method further includes: The second feature is determined according to a feature corresponding to the first target user that is different from the first feature.
3. The method according to claim 2, It is characterized in that The first target user includes a plurality of users, each user corresponds to a plurality of features, and determining the second feature according to a feature different from the first feature and corresponding to the first target user includes: Determine, from the features corresponding to the first target users and different from the first features, the number of users among the first target users corresponding to each feature; One or more features corresponding to the largest number of users are obtained as the second features.
4. The method according to claim 2, It is characterized in that The determining the second feature according to a feature different from the first feature corresponding to the first target user includes: From the features corresponding to the first target user that are different from the first features, a feature that is the same as the target feature is selected as the second feature.
5. The method according to claim 2, It is characterized in that The determining the second feature according to a feature different from the first feature corresponding to the first target user includes: From the features corresponding to the first target user that are different from the first features, a feature corresponding to the content to be pushed is selected as the second feature.
6. The method according to any one of claims 1 to 5, It is characterized in that The second feature includes a plurality of features, the target database includes a plurality of contents to be pushed, and the pushing the contents to be pushed corresponding to the second feature to the updated second user includes: Selecting, from the content to be pushed, the content to be pushed corresponding to different second features; The selected content to be pushed is pushed to the updated second user having the corresponding second characteristic.
7. The method according to claim 6, It is characterized in that The content to be pushed has content tags corresponding to it, and the content corresponding to different second features is selected from the content to be pushed, including: Determining content labels corresponding to respective second features according to a preset correspondence between content labels and features; The content to be pushed corresponding to each determined content tag is selected as the content to be pushed corresponding to the corresponding second feature.
8. The method according to any one of claims 1 to 5, It is characterized in that The method further comprises: determining a user different from the second target user from the first target users as a fourth user; The preset content is pushed to the fourth user.
9. The method according to any one of claims 1 to 5, It is characterized in that After pushing the content corresponding to the second feature to the updated second user, the method further includes: Acquire updated operation data of the second user on the content to be pushed; The data in the target database is optimized according to the acquired operation data.
10. The method according to claim 9, It is characterized in that The optimizing the data in the target database according to the acquired operation data includes at least one of the following: Adjust the content to be pushed corresponding to the second feature according to the acquired operation data; According to the acquired operation data, the user corresponding to the second feature is adjusted.
11. The method according to any one of claims 1 to 5, It is characterized in that The feature corresponding to each user in the target database is constructed based on the forward index; the user corresponding to each feature is constructed based on the inverted index.
12. The method according to any one of claims 1 to 5, It is characterized in that The target database is a storage engine.
13. The method according to any one of claims 1 to 5, It is characterized in that The first feature is a user behavior feature, or the second feature is a user behavior feature, wherein the user behavior feature is generated by a user's operation on the electronic device.
14. A content push device, It is characterized in that The device comprises: A first query module is used to query a first target user corresponding to a first feature from a target database, wherein the target database includes user data updated in real time, and the user data includes features corresponding to each user and a user corresponding to each feature, wherein the first feature includes at least one of a feature that the number of corresponding users in the target database reaches a preset number and a feature that a daily growth rate of the number of corresponding users in the target database is higher than a preset growth rate; The second query module is used to select users corresponding to the second feature as third target users according to users corresponding to each feature, wherein the second feature includes at least one of after-sales service and customer service marketing, users with the after-sales service represent users who need after-sales service, users with the customer service marketing represent users who need customer service marketing, and the third target users represent users who need to have targeted communication in the future; obtain the intersection with the first target user from the third target users as the second target users; search for users with the third feature among the second target users, wherein the third feature is a feature that prohibits content from being pushed; delete users with the third feature from the second target users as the updated second users; A push module is used to push the content to be pushed corresponding to the second feature to the updated second user.
15. The device according to claim 14, It is characterized in that The device also includes: A feature determination module is used to determine the second feature according to a feature corresponding to the first target user that is different from the first feature.
16. A server, It is characterized in that include: one or more processors; Memory; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are executed by the processors to perform the method according to any one of claims 1 to 13.
17. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores program code, and the program code can be called by a processor to execute the method according to any one of claims 1 to 13.
