WO2020258102A1

WO2020258102A1 - Content pushing method and apparatus, mobile terminal and storage medium

Info

Publication number: WO2020258102A1
Application number: PCT/CN2019/093110
Authority: WO
Inventors: 喻婷
Original assignee: 深圳市欢太科技有限公司; Oppo广东移动通信有限公司
Priority date: 2019-06-26
Filing date: 2019-06-26
Publication date: 2020-12-30
Also published as: CN113412607A; CN113412607B

Abstract

Provided is a content pushing method, comprising: grabbing M user identifiers (IDs), and determining N natural person IDs corresponding to the M user IDs; checking whether a target natural person ID is an abnormal natural person ID, wherein the target natural person ID is any one of the N natural person IDs; and if so, refusing to push content to the target natural person ID. According to the method, the accuracy of content pushing can be improved.

Description

Content pushing method, device, mobile terminal and storage medium

Technical field

This application relates to the field of communication technology, and in particular to a content pushing method, device, mobile terminal and storage medium.

Background technique

At present, when a server (for example, a server) pushes content to a user (for example, an application client), it generally pushes content according to the user profile of the user's identity (ID) logged in to the client. However, once the user portrait of the user ID is judged incorrectly, the server will push the wrong content to the client.

Summary of the invention

The embodiments of the present application provide a content pushing method, device, mobile terminal, and storage medium, which can improve the accuracy of content pushing.

In the first aspect, an embodiment of the present application provides a content pushing method, including:

Grab M user identification IDs, and determine N natural person IDs corresponding to the M user IDs, where M and N are both positive integers, and N is less than or equal to M;

Detecting whether the target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of the N natural person IDs;

If yes, refuse to push content to the target natural person ID.

In a second aspect, an embodiment of the present application provides a content pushing device, the content pushing device includes a capturing unit, a determining unit, a detecting unit, and a processing unit, wherein:

The grabbing unit is used to grab M user identification IDs;

The determining unit is configured to determine N natural person IDs corresponding to the M user IDs, where M and N are both positive integers, and N is less than or equal to M;

The detection unit is configured to detect whether a target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of the N natural person IDs;

The processing unit is configured to refuse to push content to the target natural person ID when the detection unit detects that the target natural person ID is an abnormal natural person ID.

In a third aspect, an embodiment of the present application provides a mobile terminal, including a processor and a memory, the memory is used to store one or more programs, and the one or more programs are configured to be executed by the processor. The program includes instructions for executing the steps in the first aspect of the embodiments of the present application.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the foregoing computer-readable storage medium stores a computer program for electronic data exchange, wherein the foregoing computer program enables a computer to execute Some or all of the steps described in one aspect.

In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute Example part or all of the steps described in the first aspect. The computer program product may be a software installation package.

It can be seen that the content push method described in the embodiment of the application specifically includes the following steps: grab M user identification IDs, and determine N natural person IDs corresponding to the M user IDs, where M and N are both positive Integer, N is less than or equal to M; check whether the target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of N natural person IDs; if so, refuse to push content to the target natural person ID. To implement the embodiments of this application, first convert M user IDs into N natural person IDs, reduce the number of IDs pushed, and then identify abnormal natural person IDs in natural person IDs, and do not push content to abnormal natural person IDs, further reducing the number of pushes The number of natural person IDs can avoid pushing content to abnormal natural person IDs and improve the accuracy of content pushing. Since the number of natural person IDs that meet the pushing conditions is less than M user identification IDs, it can reduce the pressure of content pushing on the server, thereby increasing The speed of content delivery.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flowchart of a content pushing method disclosed in an embodiment of the present application;

Figure 2 is a schematic diagram of judging whether a natural person ID is a substitute ID disclosed in an embodiment of the present application;

FIG. 3 is a schematic flowchart of another content pushing method disclosed in an embodiment of the present application;

Figure 4 is a schematic structural diagram of a content pushing device disclosed in an embodiment of the present application;

Fig. 5 is a schematic structural diagram of a mobile terminal disclosed in an embodiment of the present application.

Detailed ways

In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only It is a part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific sequence. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes unlisted steps or units, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.

Reference to "embodiments" herein means that a specific feature, structure or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art clearly and implicitly understand that the embodiments described herein can be combined with other embodiments.

The mobile terminals involved in the embodiments of this application may include various handheld devices with wireless communication functions, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to wireless modems, as well as various forms of user equipment (User Equipment, UE), mobile station (Mobile Station, MS), terminal device (terminal device), etc. For ease of description, the devices mentioned above are collectively referred to as mobile terminals.

The following describes the embodiments of the present application in detail.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a content pushing method disclosed in an embodiment of the present application. As shown in FIG. 1, the content pushing method includes the following steps.

101. The server grabs M user identification IDs, and determines N natural person IDs corresponding to the M user IDs. Both M and N are positive integers, and N is less than or equal to M.

In the embodiments of the present application, the server serves the client, and the content of the service includes providing resources to the client and storing client data. The server is a targeted service program, and the device running the server can be called a server. The server can establish connections with multiple clients at the same time, and can provide services to multiple clients at the same time. The services provided by the server for the client in the embodiments of the present application mainly include content push services. The content push service may include: browser content push service, application download push service, game content push service, etc. The server can include application server, browser server, game server, etc.

The server can grab M user identities (IDs) from the database, and can push specific content to the clients logged in by the M user IDs. User ID can include any one or more of the following types: single sign on identity (SSOID), OpenID, integrated circuit card identity (ICCID), international mobile device identity (International Mobile) Equipment (Identity, IMEI), telephone number (telephone, TEL), etc. SSO is in multiple application systems. Users only need to log in once to access all mutually trusted application systems.

The server can randomly grab M user IDs from the database, and subsequently can push different content to the normal natural person IDs among the N natural person IDs corresponding to the M user IDs. The server can also grab M user IDs with the same characteristics from the database, and subsequently can push the same content to the normal natural person IDs among the N natural person IDs corresponding to the M user IDs.

The server determines the N natural person IDs corresponding to the M user IDs, which may specifically be: the server determines the N natural person IDs corresponding to the M user IDs according to the generated correspondence between the user ID and the natural person ID.

The first situation: if the M user IDs are all in the corresponding relationship between the user IDs and the natural person IDs that have been generated, the N natural person IDs corresponding to the M user IDs are directly determined according to the above method.

The second case: if none of the M user IDs are in the corresponding relationship between the generated user ID and the natural person ID, the server can obtain all the natural person IDs in the corresponding relationship between the generated user ID and the natural person ID, according to The user behavior data of M user IDs analyzes the similarity between the M user IDs and each of the above-mentioned natural person IDs. If the first user ID (the first user ID is any one of the above-mentioned M user IDs) and If the similarity of the natural person ID with the highest similarity among all the above natural person IDs is greater than the preset similarity threshold, then the first user ID is associated with the natural person ID with the highest similarity among all the natural person IDs. If the first user ID is If the similarity of the natural person ID with the highest similarity among all natural person IDs is greater than the preset similarity threshold, the user behavior data of the first user ID is matched with the user behavior data of other user IDs in the database. If the similarity between the user behavior data and the user ID with the highest similarity among other user IDs in the aforementioned database is greater than the preset similarity threshold, the first user ID is established with the user ID with the highest similarity among other user IDs in the aforementioned database The corresponding relationship forms a new natural person ID, which corresponds to the user ID with the highest similarity among the first user ID and other user IDs in the database.

The third case: if part of the M user IDs are in the corresponding relationship between the user IDs and natural person IDs that have been generated above, and another part is not in the corresponding relationship between the user IDs that have been generated and the natural person IDs, then they have been generated above The user ID in the corresponding relationship between the user ID and the natural person ID directly determines the corresponding natural person ID according to the corresponding relationship, and the user ID that is not in the corresponding relationship between the user ID and the natural person ID that has been generated above is determined according to the method in the second case above The corresponding natural person ID.

Among them, the natural person ID in the embodiment of this application corresponds to a natural person. This natural person may correspond to at least one mobile terminal (for example, mobile phone), at least one phone number, at least one application account, at least one OpenID, one SSOID, at least one ICCID, and at least one IMEI. For example, if a natural person has a mobile phone, a phone number, and 5 application accounts, the IMEI, phone number, and 5 application accounts of the mobile phone are labeled with a natural person ID. The user behavior data corresponding to these 5 application accounts all belong to the user behavior data of this natural person ID. In this way, a real natural person can have many user IDs (for example, the IMEI of a mobile phone, a phone number, and 5 application accounts), but only one unique natural person ID is corresponding.

102. The server detects whether the target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of the above N natural person IDs. If yes, go to step 103, if not, go to step 104.

In the embodiment of the present application, the abnormal natural person ID includes: all user IDs corresponding to the abnormal natural person ID are offline for a long time, and all user IDs corresponding to the abnormal natural person ID have user IDs with abnormal logins (for example, a certain application account After the account is stolen, a large number of spam messages are sent to friends in the contact list), and all user IDs corresponding to the abnormal natural person ID have user IDs that have swiping behavior (for example, the user ID frequently downloads and uninstalls applications, the user Recharge accounts with a large number of IDs, etc.), and all user IDs corresponding to the abnormal natural person ID have user IDs with substitute behaviors (for example, the user behavior habits of the user ID are very different from previous user behavior habits).

If the server detects that the target natural person ID is an abnormal natural person ID, it will not push content to the target natural person ID, reducing unnecessary content pushing, reducing the pressure of the server content pushing, thereby increasing the speed of content pushing.

If the server detects that the target natural person ID is not an abnormal natural person ID, it will push content to the target natural person ID. Specifically, the server may push content to any one of the multiple user IDs corresponding to the target natural person ID. For example, if the target natural person ID corresponds to 5 different application accounts (for example, A browser application account, B browser application account, C browser application account, D browser application account, E browser App account), if there is breaking news, the server only needs to send and push the breaking news message to one of the 5 different application accounts, so there is no need to send the breaking news to the other 4 applications. Sending the same push message to an account can improve the efficiency of message push and avoid repeated push of messages.

Among them, the content pushed by the server can be notification messages (for example, news messages), marketing messages (for example, product promotion information), etc.

Optionally, in step 102, the server detects whether the target natural person ID is an abnormal natural person ID, including:

(11) The server obtains the user behavior data of the target natural person ID, and analyzes whether the target natural person ID is a swipe ID based on the user behavior data of the target natural person ID;

(12) If the target natural person ID is a swipe ID, the server determines that the target natural person ID is an abnormal natural person ID;

(13) If the target natural person ID is not a swipe ID, the server uses a machine learning algorithm to detect whether the target natural person ID is a substitute ID;

(14) If the target natural person ID is a substitute ID, the server determines that the target natural person ID is an abnormal natural person ID.

In the embodiment of this application, the server first analyzes whether the target natural person ID is a swipe ID. If it is a swipe ID, the target natural person ID is considered to be an abnormal natural person ID. If it is not a swipe ID, it further detects whether the target natural person ID is The substitute ID, if it is a substitute ID, the target natural person ID is considered to be an abnormal natural person ID, and if it is not a substitute ID, the target natural person ID is considered to be a normal natural person ID and belongs to a natural person ID that meets the content push conditions.

Among them, the core demand of scalping users is to get more attention, thereby bringing in greater traffic and attracting more users. By observing the user behavior data of large-cap users, we found several more obvious characteristics of users who scam users: For software stores, users who scam users are more of downloads, and for games, they want to let the platform show them better. Location, compared with normal users, this kind of user is easier to identify. Observing the behavior distribution of large-cap users, you can formulate corresponding rules and conditions, and preliminarily eliminate very obvious users who are brushing.

The brush ID has certain behavioral characteristics: For example, for the brush ID of the APP rankings, the number of apps installed per day is 100+ times, the number of apps uninstalled per day is 100+ times, and the brush ID is always positioned at In the same place, the amount of ID is used to purchase VIPs for one month, only active for a week or even one or two days, the payment amount of the amount of ID is 3000+, and so on.

Compared with the amount of ID, the substitute ID is difficult to identify. The embodiment of the present application uses a machine learning algorithm to detect whether the target natural person ID is a substitute ID. Specifically, the embodiments of this application can use random forests, decision trees, xgboost, local sensitive hashes in machine learning based on user location characteristics, travel preferences, APP usage habits and interests, device usage characteristics, and the unique identifier corresponding to the device itself. (Locality-Sensitive Hashing, LSH), the graph database method connects various information islands, thereby enriching the normal life cycle of a user's equipment. For example, please refer to FIG. 2, which is a schematic diagram of judging whether a natural person ID is a substitute ID disclosed in an embodiment of the present application. As shown in Figure 2, the server obtains multiple application data logged in by the user through multiple application IDs in advance, determines multiple sets of features based on the multiple application data, and trains the multiple sets of features to obtain a machine learning model. After each login, collect some current data and perform feature extraction to obtain the features, and input the features into the machine learning model to obtain the substitution weight value of the account, so as to better judge whether the account has substitution behavior.

Optionally, the above-mentioned user behavior data includes application installation data, application uninstallation data, and payment amount. In the above step (11), the server analyzes whether the target natural person ID is a credit ID based on the user behavior data of the target natural person ID. for:

(111) The server detects whether there is data in the application installation data of the target natural person ID that the total number of single-day installations is greater than the preset upper threshold of the number of installations; whether there is a single-day uninstallation data that is greater than the total number of uninstallation data of the target natural person ID Data of the preset upper limit threshold of the number of unloading; detecting whether the payment amount of the target natural person ID exceeds the preset amount threshold;

(112) If there is data in the application installation data of the target natural person ID that the total number of single-day installations is greater than the upper threshold of the preset number of installations, and there is data in the application uninstallation data of the target natural person ID that the total number of single-day uninstalls is greater than the preset uninstallation number Data of the upper limit threshold, and the payment amount of the target natural person ID exceeds the preset amount threshold, the server determines the target natural person ID as the amount ID.

In the embodiment of the present application, the user behavior data of the target natural person ID may include user behavior data of multiple user IDs corresponding to the target natural person ID. For example, if there are 5 application program accounts corresponding to the target natural person ID, the user behavior data of the target natural person ID includes user behavior data of the 5 application program accounts. As long as the user behavior data of any one of the five application accounts is abnormal, the target natural person ID is considered to be an abnormal natural person ID. User behavior data may include: application installation data, application uninstallation data, payment quota, application activity data, positioning data, and the like.

Optionally, if there is data in the application installation data of the target natural person ID that the total number of single-day installations is greater than the upper threshold of the preset number of installations, and the positioning data of the target natural person ID does not change within the preset time period, the server determines The target natural person ID is the amount ID;

If there is data in the application uninstallation data of the target natural person ID that the total number of uninstalls in a single day is greater than the upper threshold of the preset number of uninstalls, and the positioning data of the target natural person ID does not change within the preset time period, the server determines that the target natural person ID is Brush ID;

If the payment amount of the target natural person ID exceeds the preset amount threshold, and the positioning data of the target natural person ID does not change within the preset time period, the server determines that the target natural person ID is the amount ID.

The embodiment of the application provides a method for determining whether the target natural person ID is a credit ID, which can quickly identify whether the target natural person ID is a credit ID, avoid subsequent content pushing to the credit ID, and reduce the pressure of content pushing on the server.

Optionally, in the above (13), the server uses a machine learning algorithm to detect whether the target natural person ID is a substitute ID, specifically:

(131) The server determines at least one user ID corresponding to the target natural person ID;

(132) After the first user ID corresponding to the target natural person ID logs in to the target device, the server obtains the location characteristics of the target device, the travel preference characteristics of the first user ID, the application usage habit characteristics of the first user ID, and the first user Interest characteristics of the ID, device usage characteristics of the target device, and target device identification; the first user ID is any one of at least one user ID;

(133) The server combines the location characteristics of the target device, the travel preference characteristics of the first user ID, the application usage habit characteristics of the first user ID, the interest characteristics of the first user ID, the device usage characteristics of the target device, and the target device identification Input the trained machine learning model to get the surrogate weight value of the first user ID;

(134) If the substitute weight value of the first user ID is greater than the preset weight threshold, the server determines the target natural person ID as the substitute ID.

In the embodiment of the present application, the location feature of the target device may be extracted from GPS location information periodically reported by the target device. The travel preference feature can be extracted from the itinerary and GPS location information reported by the first user ID. The application usage habit characteristics of the first user ID can be reported from the application opening time, application closing time, application brightness, application volume, application function usage, and application continuous operation reported by the first user ID It is extracted from the duration and accumulated running time of the application. The interest feature of the first user ID can be extracted from the web browsing records, favorite records, and search records reported by the first user ID. The device usage characteristics of the target device can be extracted from the usage habits of the target device (for example, the boot time of the target device, the shutdown time, the backlight brightness of the target device, the volume of the target device, the holding posture of the target device, etc.).

Wherein, the trained machine learning model can be obtained by training according to historical user behavior data of at least one user ID corresponding to the target natural person ID.

In the embodiment of this application, the trained machine learning model is obtained by training based on the historical user behavior data of all user IDs corresponding to the target natural person ID. The trained machine learning model can better reflect a user's habit of using equipment After the user ID corresponding to the natural person ID logs in, the user behavior data of the user ID corresponding to the natural person ID can be input into the trained machine learning model to obtain a substitute weight value. Generally speaking, the higher the substitution weight value, the higher the possibility of the user ID being substituted. The preset weight threshold can be set in advance for judging the substitution behavior of the user ID. As shown in Figure 2, natural person IDs correspond to three user IDs (openid1, openid2, openid3), APP rules include application usage habits, geographic location rules include target device location characteristics, and account system rules include travel preference characteristics and interest characteristics . The preset weight threshold can be set to 0.5, then for openid1, it is recognized as a substitute ID, and for openid2 and openid3, it is recognized as a self-use ID. Since one of the three user IDs corresponding to the natural person ID is a substitute ID, it can be determined that the natural person ID is an abnormal natural person ID.

Optionally, before step (131) is performed, the following steps can also be performed:

The server obtains in advance multiple application data reported by at least one user ID, determines multiple sets of features based on the multiple application data, and trains the multiple sets of features to obtain a trained machine learning model.

In the embodiment of this application, the trained machine learning model is a set of features (APP feature, location feature, target device) extracted from multiple application data reported by the server according to at least one user ID corresponding to the target natural person ID obtained in advance. Use feature) for training, the trained machine learning model is determined for the user habits of the target natural person ID, and can accurately screen the use of other natural persons who are not the target natural person, and accurately identify whether the user ID is Out of modern use.

103. The server refuses to push content to the target natural person ID.

104. The server pushes content to the target natural person ID.

In the embodiment of this application, first convert M user IDs into N natural person IDs, reduce the number of IDs pushed, and then identify the abnormal natural person IDs in the natural person IDs, and do not push content to the abnormal natural person IDs, further reducing the number of pushes The number of natural person IDs can avoid pushing content to abnormal natural person IDs and improve the accuracy of content pushing. Since the number of natural person IDs that meet the pushing conditions is less than M user identification IDs, it can reduce the pressure of content pushing on the server, thereby increasing The speed of content delivery.

The embodiments of this application can identify normal natural person IDs and abnormal natural person IDs (fake users, interfering users), eliminate abnormal natural person IDs in time, reduce unnecessary economic and analysis losses; push content of normal natural person IDs, thereby improving the accuracy of the push Performance, reduce resource waste, and achieve precise operation.

Please refer to FIG. 3, which is a schematic flowchart of another content pushing method disclosed in an embodiment of the present application. Fig. 3 is obtained by further optimization on the basis of Fig. 1. As shown in Fig. 3, the content pushing method includes the following steps.

301. The server obtains the behavior data of multiple user IDs reported by multiple clients, and uses a graph storage calculation engine to calculate the similarity between the behavior data of the multiple user IDs.

302. The server constructs a relationship pair between user IDs based on the similarity between the behavior data of the multiple user IDs.

303. The server constructs a corresponding relationship between the user ID and the natural person ID according to the relationship between the user IDs.

In the embodiments of the present application, the graph storage calculation engine may also be referred to as a graph calculation engine. The graph storage calculation engine uses the PageRank algorithm, the shortest path algorithm, and the Alternating Least Squares (ALS) algorithm to calculate the The similarity between the behavior data of multiple user IDs. A relationship pair is established for user IDs whose similarity is greater than a preset similarity threshold. For example, SSOID1<->IMEI2, OPENID1<->ICCID3, SSOID2<->TEL2, IMEI2<->TEL3, IMEI2<->ICCID1, SSOID2<->OPENID1, IMEI1<->SSOID2. Then SSOID1, IMEI2, TEL3, and ICCID1 correspond to one natural person ID (for example, natural person ID1), and OPENID1, ICCID3, SSOID2, TEL2, and IMEI1 correspond to another natural person ID (for example, natural person ID2). See Table 1 for details.

Table 1

用户IDUser ID	自然人IDNatural person ID
SSOID1、IMEI2、TEL3、ICCID1SSOID1, IMEI2, TEL3, ICCID1	自然人ID1Natural person ID1
OPENID1、ICCID3、SSOID2、TEL2、IMEI1OPENID1, ICCID3, SSOID2, TEL2, IMEI1	自然人ID2Natural person ID2

Table 1 is a table of correspondence between user IDs and natural person IDs disclosed in the embodiments of the present application. As shown in Table 1, the correspondence between natural person ID1 and SSOID1, IMEI2, TEL3, and ICCID1, and the correspondence between natural person ID2 and OPENID1, ICCID3, SSOID2, TEL2, and IMEI1.

304. The server grabs M user identification IDs, and the server acquires the corresponding relationship between the user ID and the natural person ID.

305. The server determines N natural person IDs corresponding to the M user IDs according to the corresponding relationship between the user ID and the natural person ID.

In the implementation of this application, the correspondence between the user ID and the natural person ID can be obtained in advance. The correspondence between the user ID and the natural person ID can be determined in steps 301 to 303. Step 304 is executed after step 301 to step 303. The correspondence between user IDs and natural person IDs does not need to be generated in real time, and N natural person IDs corresponding to M user IDs can be quickly determined.

306. The server detects whether the target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of the above N natural person IDs. If yes, go to step 307, if not, go to step 308.

307. The server refuses to push content to the target natural person ID.

308. The server pushes content to the target natural person ID.

For the specific implementation of step 306 to step 308 in the embodiment of the present application, reference may be made to the description of step 102 to step 104 shown in FIG. 1, which will not be repeated here.

In the embodiment of this application, first, according to the corresponding relationship between the user ID and the natural person ID, the M user IDs are converted into N natural person IDs, the number of IDs pushed is reduced, and then the abnormal natural person ID in the natural person ID is identified, and the abnormal natural person ID is not reported to the abnormal natural person. ID pushes content, further reduces the number of natural person IDs that are pushed, can avoid pushing content to abnormal natural person IDs, and improve the accuracy of content pushing. Since the number of natural person IDs that meet the pushing conditions is less than M user identification IDs, it can be reduced The pressure of server-side content push, thereby increasing the speed of content push.

The foregoing mainly introduces the solution of the embodiment of the present application from the perspective of the execution process on the method side. It can be understood that, in order to implement the above-mentioned functions, the mobile terminal includes hardware structures and/or software modules corresponding to each function. Those skilled in the art should easily realize that in combination with the units and algorithm steps of the examples described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered as going beyond the scope of the present invention.

The embodiments of the present application may divide the mobile terminal into functional units according to the foregoing method examples. For example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.

Please refer to FIG. 4, which is a schematic structural diagram of a content pushing device disclosed in an embodiment of the present application. As shown in Figure 4, the content pushing device 400 includes a grabbing unit 401, a determining unit 402, a detecting unit 403, and a processing unit 404, wherein:

The grabbing unit 401 is configured to grab M user identification IDs;

The determining unit 402 is configured to determine N natural person IDs corresponding to the M user IDs, where M and N are both positive integers, and N is less than or equal to M;

The detection unit 403 is configured to detect whether the target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of the N natural person IDs;

The processing unit 404 is configured to refuse to push content to the target natural person ID when the detection unit 403 detects that the target natural person ID is an abnormal natural person ID.

Optionally, the processing unit 404 is further configured to push content to the target natural person ID when the detection unit 403 detects that the target natural person ID is not an abnormal natural person ID.

Optionally, the detection unit 403 detects whether the target natural person ID is an abnormal natural person ID, specifically: acquiring user behavior data of the target natural person ID, and analyzing whether the target natural person ID is based on the user behavior data of the target natural person ID Is the amount ID; if the target natural person ID is the amount ID, the target natural person ID is determined to be an abnormal natural person ID; if the target natural person ID is not the amount ID, a machine learning algorithm is used to detect whether the target natural person ID Is a substitute ID; if the target natural person ID is a substitute ID, it is determined that the target natural person ID is an abnormal natural person ID.

Optionally, the user behavior data includes application installation data, application uninstallation data, and payment amount, and the detection unit 403 analyzes whether the target natural person ID is a credit ID based on the user behavior data of the target natural person ID, Specifically: detecting whether there is data in the application installation data of the target natural person ID that the total number of single-day installations is greater than the preset upper limit of the number of installations; detecting whether there is a single-day uninstallation data in the application uninstallation data of the target natural person ID The amount of data is greater than the preset upper limit threshold of the number of uninstalls; it is detected whether the payment amount of the target natural person ID exceeds the preset amount threshold; if there is a total number of single-day installations in the target natural person ID application installation data greater than the preset The data of the upper limit threshold of the number of installations, and there is data in the application uninstallation data of the target natural person ID that the total amount of uninstallation in a single day is greater than the preset upper limit of the uninstallation number threshold, and the payment amount of the target natural person ID exceeds the preset If the quota threshold is set, the target natural person ID is determined as the amount ID.

Optionally, the detection unit 403 uses a machine learning algorithm to detect whether the target natural person ID is a substitute ID, specifically: determining at least one user ID corresponding to the target natural person ID; After the user ID logs in to the target device, obtain the location feature of the target device, the travel preference feature of the first user ID, the application usage habit feature of the first user ID, the interest feature of the first user ID, The device usage feature of the target device and the target device identifier; the first user ID is any one of the at least one user ID; the location feature of the target device and the travel preference feature of the first user ID , The application usage habit characteristics of the first user ID, the interest characteristics of the first user ID, the device usage characteristics of the target device, and the target device identification input a trained machine learning model to obtain the first user The substitution weight value of the ID; if the substitution weight value of the first user ID is greater than the preset weight threshold, it is determined that the target natural person ID is the substitution ID.

Optionally, before the detecting unit 403 determines the at least one user ID corresponding to the target natural person ID, it is further configured to obtain in advance multiple pieces of application data reported by the at least one user ID, and determine the multiple pieces according to the multiple pieces of application data. Group features, training the multiple groups of features to obtain a trained machine learning model.

Optionally, the determining unit 402 determines the N natural person IDs corresponding to the M user IDs, specifically: acquiring the corresponding relationship between the user ID and the natural person ID; and determining the corresponding relationship according to the corresponding relationship between the user ID and the natural person ID. N natural person IDs corresponding to the M user IDs.

Optionally, before the determining unit 402 obtains the corresponding relationship between the user ID and the natural person ID, it is also used to obtain the behavior data of multiple user IDs reported by multiple clients, and calculate the multiple user IDs using a graph storage calculation engine. The similarity between the behavior data of the user ID; the relationship between the user ID is constructed based on the similarity between the behavior data of the multiple user IDs; the relationship between the user ID and the natural person ID is constructed based on the relationship between the user IDs Correspondence.

Implement the content pushing device shown in Figure 4, first convert M user IDs into N natural person IDs, reduce the number of IDs pushed, and then identify abnormal natural person IDs in natural person IDs, and do not push content to abnormal natural person IDs. Further narrowing the number of natural person IDs pushed can avoid pushing content to abnormal natural person IDs, and improve the accuracy of content pushing. Since the number of natural person IDs that meet the push conditions is less than M user identification IDs, it can reduce the amount of server-side content pushing Pressure to increase the speed of content delivery.

Please refer to FIG. 5, which is a schematic structural diagram of a mobile terminal disclosed in an embodiment of the present application. As shown in FIG. 5, the mobile terminal 500 includes a processor 501 and a memory 502. The mobile terminal 500 may also include a bus 503. The processor 501 and the memory 502 may be connected to each other through the bus 503. The bus 503 may be a peripheral component. Connect the standard (Peripheral Component Interconnect, referred to as PCI) bus or extended industry standard architecture (Extended Industry Standard Architecture, referred to as EISA) bus, etc. The bus 503 can be divided into an address bus, a data bus, a control bus, and so on. For ease of presentation, only one thick line is used in FIG. 5 to represent, but it does not mean that there is only one bus or one type of bus. The mobile terminal 500 may also include an input and output device 504, and the input and output device 504 may include a display screen, such as a liquid crystal display screen. The memory 502 is used to store one or more programs containing instructions; the processor 501 is used to call the instructions stored in the memory 502 to execute some or all of the method steps in FIGS. 1 to 3.

Implement the mobile terminal shown in Figure 5, first convert M user IDs into N natural person IDs, reduce the number of IDs pushed, and then identify abnormal natural person IDs in natural person IDs, and do not push content to abnormal natural person IDs, and further Reducing the number of natural person IDs pushed can avoid pushing content to abnormal natural person IDs and improve the accuracy of content pushing. Since the number of natural person IDs that meet the pushing conditions is less than M user identification IDs, it can reduce the pressure of server content pushing , Thereby improving the speed of content push.

The embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes the computer to execute any part of the content push method recorded in the above method embodiment Or all steps.

The embodiments of the present application also provide a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a computer to execute any of the methods described in the foregoing method embodiments. Part or all of the steps of a content push method.

It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described sequence of actions. Because according to the present invention, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the involved actions and modules are not necessarily required by the present invention.

In the above-mentioned embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, A number of instructions are included to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other various media that can store program codes.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable memory, and the memory can include: flash disk , Read-only memory (English: Read-Only Memory, abbreviation: ROM), random access device (English: Random Access Memory, abbreviation: RAM), magnetic disk or optical disc, etc.

The embodiments of the present application are described in detail above, and specific examples are used in this article to illustrate the principles and implementation of the present invention. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present invention; Persons of ordinary skill in the art, based on the idea of the present invention, will have changes in the specific implementation and the scope of application. In summary, the content of this specification should not be construed as limiting the present invention.

Claims

A content pushing method, characterized in that it comprises:

Grab M user identification IDs, and determine N natural person IDs corresponding to the M user IDs, where M and N are both positive integers, and N is less than or equal to M;

Detecting whether the target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of the N natural person IDs;

If yes, refuse to push content to the target natural person ID.
The method according to claim 1, wherein the detecting whether the target natural person ID is an abnormal natural person ID comprises:

Obtain user behavior data of the target natural person ID, and analyze whether the target natural person ID is a credit ID based on the user behavior data of the target natural person ID;

If the target natural person ID is a brush amount ID, it is determined that the target natural person ID is an abnormal natural person ID;

If the target natural person ID is not a swipe ID, use a machine learning algorithm to detect whether the target natural person ID is a substitute ID;

If the target natural person ID is a substitute ID, it is determined that the target natural person ID is an abnormal natural person ID.
The method according to claim 2, wherein the user behavior data includes application installation data, application uninstallation data, and payment amount, and the user behavior data based on the target natural person ID analyzes the target natural person ID Whether it is the brush ID, including:

Detect whether there is data in the application installation data of the target natural person ID that the total number of single-day installations is greater than the preset upper limit threshold of the number of installations; detect whether there is a single-day uninstallation data that is greater than the expected amount in the application uninstallation data of the target natural person ID Set the data of the upper limit threshold of the number of uninstalls; detect whether the payment amount of the target natural person ID exceeds the preset amount threshold;

If there is data in the application installation data of the target natural person ID that the total number of single-day installations is greater than the upper limit threshold of the preset number of installations, and the application uninstallation data of the target natural person ID includes the total number of single-day uninstalls greater than all According to the data of the upper limit threshold of the preset amount of unloading, and the payment amount of the target natural person ID exceeds the preset amount threshold, it is determined that the target natural person ID is the amount ID.
The method according to claim 2, wherein the detecting whether the target natural person ID is a substitute ID by using a machine learning algorithm comprises:

Determine at least one user ID corresponding to the target natural person ID;

After the first user ID corresponding to the target natural person ID logs in to the target device, the location characteristics of the target device, the travel preference characteristics of the first user ID, the application usage habit characteristics of the first user ID, The interest feature of the first user ID, the device usage feature of the target device, and the target device identifier; the first user ID is any one of the at least one user ID;

The location feature of the target device, the travel preference feature of the first user ID, the application usage habit feature of the first user ID, the interest feature of the first user ID, and the device usage of the target device Input the trained machine learning model to the characteristics and the target device identification to obtain the substitute weight value of the first user ID;

If the substitute weight value of the first user ID is greater than a preset weight threshold, it is determined that the target natural person ID is the substitute ID.
The method according to claim 4, wherein before the determining at least one user ID corresponding to the target natural person ID, the method further comprises:

Acquire multiple application data reported by the at least one user ID in advance, determine multiple sets of features based on the multiple application data, and train the multiple sets of features to obtain a trained machine learning model.
The method according to any one of claims 1 to 5, wherein the determining N natural person IDs corresponding to the M user IDs comprises:

Obtain the correspondence between the user ID and the natural person ID;

The N natural person IDs corresponding to the M user IDs are determined according to the correspondence between the user ID and the natural person ID.
The method according to claim 6, characterized in that, before the obtaining the correspondence between the user ID and the natural person ID, the method further comprises:

Obtain the behavior data of multiple user IDs reported by multiple clients, and use a graph storage calculation engine to calculate the similarity between the behavior data of the multiple user IDs;

Constructing a relationship pair between user IDs based on the similarity between the behavior data of the multiple user IDs;

The corresponding relationship between the user ID and the natural person ID is constructed according to the relationship between the user IDs.
A content pushing device, characterized in that the content pushing device includes a grabbing unit, a determining unit, a detecting unit and a processing unit, wherein:

The grabbing unit is used to grab M user identification IDs;

The determining unit is configured to determine N natural person IDs corresponding to the M user IDs, where M and N are both positive integers, and N is less than or equal to M;

The detection unit is configured to detect whether a target natural person ID is an abnormal natural person ID, and the target natural person ID is any one of the N natural person IDs;

The processing unit is configured to refuse to push content to the target natural person ID when the detection unit detects that the target natural person ID is an abnormal natural person ID.
A mobile terminal, characterized by comprising a processor and a memory, the memory is used to store one or more programs, the one or more programs are configured to be executed by the processor, and the programs include Perform the method according to any one of claims 1-7.
A computer-readable storage medium, characterized in that the computer-readable storage medium is used to store a computer program for electronic data exchange, wherein the computer program causes a computer to execute any one of claims 1-7 method.