User backflow processing method and device for application program, equipment and medium

Abstract

The invention discloses a user backflow processing method and device for an application program, equipment and a medium, and belongs to the technical field of Internet. The method comprises the following steps: acquiring historical use data of an offline user of an application program; screening the historical use data, and determining a backflow target user; determining target discount information matched with the backflow target user from discount information published by a discount server according to historical use data of the backflow target user; building reaching information based on the target discount information, and determining a reaching mode and sending time of the reaching information according to historical use data of the backflow target user; and after the sending time is up, sending touch information to the backflow target user according to the determined touch mode. According to the technical scheme, the discount information of the actual demand can be determined based on the historical use data of the offline user so as to determine the reaching information, the reaching mode and the sending time, and therefore the backflow proportion of the offline user can be increased, and the purpose of efficient backflow is achieved.

Description

Technical Field

[0001] The present application belongs to the field of Internet technology, and specifically relates to a method, device, equipment and medium for processing user return flow of an application. Background Art

[0002] With the rapid popularization of smart terminals, various types of applications are emerging. For some applications, there will be a certain number of online users for a period of time after the release, but as the user's demand for use gradually upgrades, or because of the existence of other competing applications, some users will no longer go online and become offline users of the application.

[0003] The number of online users will directly affect the application maintenance and management of the application developer and the benefits obtained after development. Therefore, how to return offline data has become a technical issue that some application developers are gradually paying attention to. Summary of the invention

[0004] The embodiments of the present application provide a method, apparatus, device and medium for processing user reflow of an application, the purpose of which is to screen offline users and determine the discount information actually required by offline users based on their historical usage data to determine the contact information, contact method and sending time, thereby improving the reflow rate of offline users and achieving the purpose of efficient reflow.

[0005] In a first aspect, an embodiment of the present application provides a method for processing user reflow of an application program, the method comprising:

[0006] Get historical usage data of offline users of the application;

[0007] Screening the historical usage data to determine target return users;

[0008] Determining target discount information matching the return target user from discount information published by a discount server according to historical usage data of the return target user;

[0009] Constructing the reaching information based on the target discount information, and determining the reaching method and sending time of the reaching information according to the historical usage data of the returning target user;

[0010] After the sending time is reached, the reaching information is sent to the return target user according to the determined reaching method.

[0011] Further, according to the historical usage data of the return target user, the target discount information matching the return target user is determined from the discount information published by the discount server, including:

[0012] Read whether there is any historical purchase data in the historical usage data of the return target user, and the purchase object if there is any historical purchase data;

[0013] If there is no historical purchase data in the historical usage data, determining default recommended information from the discount information published by the discount server as the target discount information;

[0014] If there is historical purchase data in the historical usage data, information with the highest correlation with the purchase object is determined from the discount information published by the discount server as target discount information.

[0015] Furthermore, constructing the reaching information based on the target discount information, and determining the reaching method and sending time of the reaching information according to the historical usage data of the returning target user, including:

[0016] Constructing text content of the reaching information based on the target discount information;

[0017] Determine the contact method of the contact information according to the accumulated recharge amount in the historical usage data of the return target user; wherein the contact method includes: at least one of telephone contact, SMS contact, WeChat contact and friend transmission;

[0018] The sending time of the contact information is determined according to the historical usage time period in the historical usage data of the return target user.

[0019] Further, the contact method of the contact information is determined according to the accumulated recharge amount in the historical usage data of the return target user, including:

[0020] If the cumulative recharge amount of the target return user exceeds the first amount, determining that the contact method of the target return user is telephone contact;

[0021] If the cumulative recharge amount of the target return user is less than the first amount and exceeds the second amount, determining that the contact method of the target return user is WeChat contact;

[0022] If the accumulated recharge amount of the target returning user is less than the second amount and exceeds the third amount, it is determined that the contact method for the target returning user is SMS contact or game friend communication.

[0023] Further, determining the sending time of the contact information according to the historical usage time period in the historical usage data of the return target user includes:

[0024] The historical usage time period of the target returning user falls into the time period with the most in each time period of each day, and is determined as the game time period of the target returning user.

[0025] The starting time of the game period of the returning target user is determined as the sending time of the reaching information.

[0026] Further, according to the historical usage data of the return target user, the target discount information matching the return target user is determined from the discount information published by the discount server, including:

[0027] According to the game level data of the historical usage data of the target returning user, target discount information matching the game level data of the target returning user is determined from the discount information published by the discount server; wherein the game level data includes the team data and / or the game duration data of the master camp.

[0028] Furthermore, after sending the reaching information to the return target user according to the determined reaching method, the method further includes:

[0029] Collect statistics on actual return data of target users through various contact methods;

[0030] The actual return data is input into the reward model together with the offline user's historical usage data, reach information and reach method, and the reward score for the offline user's historical usage data in each reach information and each reach method is determined to obtain the optimal reach information and optimal reach method for each offline user's historical usage data.

[0031] In a second aspect, an embodiment of the present application provides a user reflow processing device for an application, the device comprising:

[0032] A historical usage data acquisition module is used to acquire the historical usage data of offline users of the application;

[0033] A return target user determination module, used to screen the historical usage data and determine the return target users;

[0034] A target discount information determination module, configured to determine target discount information matching the return target user from the discount information published by the discount server according to the historical usage data of the return target user;

[0035] A reach parameter determination module, used to construct the reach information based on the target discount information, and determine the reach method and sending time of the reach information according to the historical usage data of the return target user;

[0036] A reaching information sending module is used to send reaching information to the return target user according to the determined reaching method after the sending time is reached.

[0037] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the method described in the first aspect.

[0038] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the method described in the first aspect is implemented.

[0039] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0040] In an embodiment of the present application, historical usage data of offline users of an application are obtained; the historical usage data are screened to determine the target users for return flow; based on the historical usage data of the target users for return flow, target discount information matching the target users for return flow is determined from the discount information published by the discount server; reach information is constructed based on the target discount information, and the reach method and sending time of the reach information are determined based on the historical usage data of the target users for return flow; after the sending time is reached, the reach information is sent to the target users for return flow in accordance with the determined reach method. The above technical solution can be used in conjunction with a discount server based on the historical usage data of offline users, so as to provide offline users with the possibility of recall with reach information that matches their usage needs, thereby achieving efficient return of offline users and increasing the number of return of offline users of the application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of a method for processing user return flow of an application program provided in Embodiment 1 of the present application;

[0042] Figure 2 It is a flowchart of a method for processing user return flow of an application program provided in Embodiment 2 of the present application;

[0043] Figure 3 This is a flow chart of user return flow of an application program provided in Embodiment 2 of the present application;

[0044] Figure 4 This is a schematic diagram of the structure of a user return flow processing device for an application provided in Embodiment 3 of the present application;

[0045] Figure 5 It is a schematic diagram of the structure of the electronic device provided in Example 4 of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0048] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0049] In conjunction with the accompanying drawings, the user reflow processing method, device, equipment and medium of the application provided by the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0050] Embodiment 1

[0051] Figure 1 1 is a flow chart of a method for processing user return flow of an application program provided in the first embodiment of the present application. Figure 1 As shown, the specific steps include:

[0052] S101, obtaining historical usage data of offline users of the application;

[0053] First, this application is applicable to the scenario of performing reflow analysis and reflow operation on offline users of an application. Based on the above scenario, it can be understood that the execution subject of this application can be the server of the application or other devices with the function of sending reach information.

[0054] The application may be a communication application, a navigation application, or other applications. This solution takes a game application as an example for explanation.

[0055] Offline users are users who have registered in the game but are not currently online. The offline user's historical usage data may include offline user's historical login related information, such as the number of logins, login time, and online duration after each login, etc. It may also include recharge behavior data, such as recharge amount, purchase history, etc. It may also include game behavior data, such as the character level in the game, the team to which the character belongs, and the proficiency in the game.

[0056] In this solution, historical usage data can be directly obtained based on the offline user's historical operation records and the recorded offline user's historical behavior information, or obtained through processing. In an instantiated scenario, big data or database technology can be used to apply offline computing methods to export the game's history of all imported users, including user account information, in-game login behavior, and payment behavior.

[0057] S102, screening the historical usage data to determine the target return users;

[0058] For the screening of historical usage data, screening rules can be pre-set, and the target users for return flow can be screened out from the historical usage data of all offline users based on the screening rules. The screening rules can be based on the number of historical logins of the user. For example, the possibility of return flow is low for users who have registered and logged in for the first time and have not logged in again, so such offline users can be deleted, that is, not used as target users for return flow. The screening rules can also be based on the historical recharge of the user. For example, the possibility of return flow is high for users who have logged in multiple times and recharged, so such offline users can be determined as target users for return flow.

[0059] S103, determining target discount information matching the return target user from discount information published by a discount server according to the historical usage data of the return target user;

[0060] Taking the game's discount server as an example, it can refer to a specific server that provides players with certain recharge discounts or discounts during the game operation process. The following is some common game discount server related information: Channel server discount: Some games downloaded from unofficial channels (channel servers) may have more discounts and discounts. For example, in the DNF mobile game, players can get more discounts in some channel servers than in the official servers. Specific platform discounts: Some game platforms will launch discount activities for specific games. For example, Meizu Game Center provides lv2 and above users with a 25% or 30% discount coupon per month for in-game recharge, and there is no threshold for use. Users can collect it at the monthly exclusive benefits of the member club members in the account center in the upper right corner of the Meizu Game Center. Discount servers provided by game manufacturers: Wanjian Supreme Welfare Discount Edition: It is a role-playing game with a size of 248.21MB, providing recharge discounts and other benefits. Dark Night Legion Discount Edition: A new strategy card mobile game with a size of 15MB, providing players with recharge discounts. True Spirit Legend Discount Server: The discount server version of the fantasy turn-based mobile game allows players to play more refreshingly and upgrade more easily. Cao Cao Mobile Game Discount Version: The discount version of the placement card mobile game brings recharge discounts to players. Dragon King Legend Discount Server: In the discount server of this mobile game, players can enjoy a more favorable recharge discount than the official server. Discounts for different server groups: Some games have different server groups, some of which may have discounts. For example, the minimum discount for the first charge of a game account is 40% off, and the recharge is 38% off, or the first charge is 58% off, and the recharge is 33% off.

[0061] It should be noted that the discount servers of different games are different, and the discount strength, activity rules and scope of application may also vary.

[0062] The discount information may be issued by a discount server, which may include recharge discounts, equipment discounts, skin discounts, and the like.

[0063] In this solution, target discount information matching the target user can be determined from the discount information published by the discount server according to the historical usage data of the target user. For example, if the target user indicates that the offline user has played the game in the master camp for a long time, the equipment-related information in the discount information can be determined as the target discount information.

[0064] S104, constructing reaching information based on the target discount information, and determining a reaching method and a sending time of the reaching information according to the historical usage data of the returning target user;

[0065] The reaching information may be text information, picture information, video information, etc. provided to the returning target users. The construction method may be to extract text content, representative pictures, and representative short videos as the reaching information based on the target discount information.

[0066] Based on the historical usage data of the returning target users, the method of reaching out to the information can be determined, such as telephone reaching out, SMS reaching out, etc. In addition, the sending time of the reaching out information can also be determined. For example, the sending time can be determined based on the historical game time in the historical usage data of the returning target users. For example, if the returning target users always play games from 21:00 to 23:00 every day, then the sending time of the reaching out information can be determined to be 21:00.

[0067] S105: After the sending time is reached, the reaching information is sent to the return target user according to the determined reaching method.

[0068] After the sending time is reached, a contact message can be sent to the target returning user according to the determined contact method. In this way, after the target returning user receives the contact message, he or she may re-login to the current application, such as reopening a game played a long time ago, to achieve the purpose of returning offline users.

[0069] In this embodiment, optionally, according to the historical usage data of the return target user, determining the target discount information matching the return target user from the discount information published by the discount server includes:

[0070] Read whether there is any historical purchase data in the historical usage data of the return target user, and the purchase object if there is any historical purchase data;

[0071] If there is no historical purchase data in the historical usage data, determining default recommended information from the discount information published by the discount server as the target discount information;

[0072] If there is historical purchase data in the historical usage data, information with the highest correlation with the purchase object is determined from the discount information published by the discount server as target discount information.

[0073] Among them, when there is historical purchase data in the historical usage data read, the purchase object can be further determined, such as purchasing a recharge card, purchasing equipment, purchasing a character skin, etc.

[0074] When there is no historical purchase data in the historical usage data, default recommendation information may be determined from the discount information published by the discount server as the target discount information, for example, a first recharge discount and a renewal discount may be determined as the target discount information.

[0075] When there is historical purchase data in the historical usage data, the information with the highest correlation with the purchase object can be determined from the discount information published by the discount server as the target discount information. For example, in a shooting game, if the user has purchased bulletproof vests many times, the discount information published by the discount server related to bulletproof vests can be determined as the target discount information, or if there is no information related to bulletproof vests, equipment with increased defense attributes can be selected as the target discount information.

[0076] Through such a setting, this solution can improve the matching degree between the contact information sent and the interest points that the target users of the return flow paid attention to in the historical games, thereby improving the success rate of the return flow.

[0077] The technical solution provided in this embodiment obtains the historical usage data of offline users of the application; screens the historical usage data to determine the target users for return; determines the target discount information that matches the target users for return from the discount information published by the discount server based on the historical usage data of the target users for return; constructs the reach information based on the target discount information, and determines the reach method and sending time of the reach information based on the historical usage data of the target users for return; after the sending time is reached, sends the reach information to the target users for return in accordance with the determined reach method. The above technical solution can be used in conjunction with a discount server based on the historical usage data of offline users, and can provide offline users with the possibility of recall with reach information that matches their usage needs, thereby achieving efficient return of offline users and increasing the number of return of offline users of the application.

[0078] On the basis of the above embodiments, optionally, according to the historical usage data of the return target user, determining the target discount information matching the return target user from the discount information published by the discount server includes:

[0079] According to the game level data of the historical usage data of the target returning user, target discount information matching the game level data of the target returning user is determined from the discount information published by the discount server; wherein the game level data includes the team data and / or the game duration data of the master camp.

[0080] Among them, the game level data can be data that can reflect the level of the target user who returns during historical use, such as the historical level of a document editing user is "Super VIP", or the historical level in a game application is "Admiral", "Diamond", etc. Similar data can directly reflect historical usage data. In addition, other historical usage data can also be used. For example, the target user who returns has entered the master camp, or 50% of the game time is spent participating in competitions in the master camp, or the game results that the target user who returns has achieved in specific events, etc. These historical usage data indirectly reflect the game level of the target user who returns, and can also be used as game level data.

[0081] In another case, it can be determined that the game level data includes the team data. For example, if it is obtained that the target user has joined multiple teams, then it can be determined that the game level of the target user is upper-middle or upper. Alternatively, after obtaining the number of people in the team joined by the target user, the game level of the target user can be determined based on the correspondence between the number of people and the game level. Alternatively, after obtaining the level data of other team members in the team joined by the target user, the game level of the target user can be determined based on the average of the level data of other team members.

[0082] In this solution, statistics can be used to find that the level is "Admiral", and then the favorite equipment that other "Admiral" levels often buy, such as smoke bomb equipment, can be determined. If the smoke bomb equipment is discounted in the discount server, the discount information of the smoke bomb equipment can be determined as the target discount information to match it with the game level data of the return target user. Or, statistics can be used to find that the level is "Diamond", and then the favorite equipment that other "Diamond" levels often buy, such as a specific hero character, can be determined. If the specific hero character is discounted in the discount server, the discount information of the specific hero character can be determined as the target discount information to match it with the game level data of the return target user.

[0083] The technical solution provided in this embodiment can not only obtain the historical usage data of the returning target users, but also determine the level of the returning target users and the target discount information corresponding to the level based on some information in the historical usage data. By determining the target discount information in this way, the target discount information can be more in line with the usage needs of the returning target users, and the purpose of recalling the returning target users can be better achieved.

[0084] On the basis of the above embodiments, optionally, after sending the reaching information to the reflow target user according to the determined reaching method, the method further includes:

[0085] Collect statistics on actual return data of target users through various contact methods;

[0086] The actual return data is input into the reward model together with the offline user's historical usage data, reach information and reach method, and the reward score for the offline user's historical usage data in each reach information and each reach method is determined to obtain the optimal reach information and optimal reach method for each offline user's historical usage data.

[0087] In this embodiment, after sending the reaching information to the target return users, the actual return data of the target return users can be counted, wherein the actual return data can be the proportion of the actual return users to the target return users, or the number of the actual return users.

[0088] Among them, in the actual return data, the relevant data of each actual return user can be marked, such as the contact information content data, contact method data and contact time data, etc.

[0089] After obtaining the above information, specifically, the actual return data can be input into the reward model together with the historical usage data, reach information and reach method of offline users. For the same or similar historical usage data of offline users, the reward score of each reach information and each reach method can be determined to obtain the optimal reach information and reach method for various offline users' historical usage data, so as to increase the number of actual return users, or the ratio of actual return users to return target users.

[0090] Through such an arrangement, this embodiment can score the content, contact method, etc. of the contact information after the contact information is sent, based on whether the return target user reuses the application. In this way, the optimal contact information and contact method can be determined for offline users with different types of historical usage data, so as to improve the return effect of offline users.

[0091] Embodiment 2

[0092] Figure 2It is a flowchart of the user return processing method of the application provided in Example 2 of the present application. This solution makes a better improvement on the above-mentioned embodiment, and the specific improvement is: constructing the contact information based on the target discount information, and determining the contact method and sending time of the contact information according to the historical usage data of the return target user, including: constructing the text content of the contact information based on the target discount information; determining the contact method of the contact information according to the accumulated recharge amount in the historical usage data of the return target user; wherein, the contact method includes: at least one of telephone contact, SMS contact, WeChat contact and friend transmission; determining the sending time of the contact information according to the historical usage time period in the historical usage data of the return target user.

[0093] like Figure 2 As shown, the specific steps include:

[0094] S201, obtaining historical usage data of offline users of the application;

[0095] S202, screening the historical usage data to determine the return target users;

[0096] S203, determining target discount information matching the return target user from the discount information published by the discount server according to the historical usage data of the return target user;

[0097] S204, constructing text content of the reaching information based on the target discount information;

[0098] Among them, after determining the target discount information that matches the return target user, it is necessary to prioritize the text content of the reach information. Because whether it is through text messages, telephone voice or other means, the text content can be intuitively presented to the audience. For example, through text message reach, the text content can be all or part of the text message content, and through telephone voice reach, the text content can be all or part of the telephone voice content. In a special case, such as reaching through a drawn return package, it is also necessary to reflect the target discount information in the drawn poster image. For example, the image content of the drawn poster image is a bulletproof vest, and the corresponding text content needs to be configured on its image. For example, the original price is 39.9 yuan, and the current discount information is 30% off, that is, 11.97 yuan after the discount.

[0099] S205, determining a contact method of the contact information according to the accumulated recharge amount in the historical usage data of the return target user;

[0100] The contact method includes at least one of: telephone contact, SMS contact, WeChat contact, and friend contact;

[0101] Among them, several ways of reaching out, such as telephone reaching out, SMS reaching out, WeChat reaching out, and friend conveying, have been mentioned before and will not be repeated here.

[0102] The accumulated recharge amount in the historical usage data of the target return user can reflect the historical usage time, preference for the application, and satisfaction with the usage experience of the target return user, etc. Therefore, after obtaining the historical usage data, it is necessary to read the accumulated recharge amount of the current target return user and use it to determine the contact method of the contact information.

[0103] For example, if the cumulative recharge amount is 0 yuan, the contact method can be SMS contact, the cumulative recharge amount is 1-100 yuan, the contact method can be WeChat contact, the cumulative recharge amount is 101-999 yuan, the contact method can be phone contact, and the cumulative recharge amount is more than 1,000 yuan, the contact method can be friend transmission. Among them, friend transmission can be sending text messages, WeChat, and making phone calls to friends, informing the user that your friend has a high cumulative recharge amount in historical use, whether you can call friends to use this application together. Friends can be WeChat friends, friends in games, etc.

[0104] S206, determining the sending time of the reaching information according to the historical usage time period in the historical usage data of the return target user;

[0105] After the historical usage data, you can get the historical usage time periods, such as 1pm to 4pm, 5pm to 8pm, 9pm to 11pm, and 11am to 2am, etc.

[0106] In this solution, the time for sending the reaching information can be determined based on the historical usage time period of the returning target user. For example, if the returning target user always opens the game program and plays the game between 7 and 9 p.m., the reaching information can be sent at 7, 7:30 or 8 p.m.

[0107] S207: After the sending time is reached, the reaching information is sent to the return target user according to the determined reaching method.

[0108] Based on the above, this embodiment proposes a specific method for determining the reach information, the reach method and the time when the reach information is sent. Through such a setting, the reach information can be more in line with the historical usage habits of offline users and the reflux effect can be improved.

[0109] On the basis of the above embodiments, optionally, determining the contact method of the contact information according to the accumulated recharge amount in the historical usage data of the return target user includes:

[0110] If the cumulative recharge amount of the target return user exceeds the first amount, determining that the contact method of the target return user is telephone contact;

[0111] If the cumulative recharge amount of the target return user is less than the first amount and exceeds the second amount, determining that the contact method of the target return user is WeChat contact;

[0112] If the accumulated recharge amount of the target returning user is less than the second amount and exceeds the third amount, it is determined that the contact method for the target returning user is SMS contact or game friend communication.

[0113] Among them, the first limit is a relatively high limit. When the cumulative recharge amount of the target return user exceeds the first limit, the target return user can be set to be contacted by phone. On the one hand, contacting by phone can make users truly understand the target discount information, avoiding the situation where users do not read the information carefully through SMS and other methods, resulting in ineffective return of users. On the other hand, contacting by phone can be more convincing and can be accompanied by more auxiliary content to enhance users' interest in use.

[0114] For the target return users whose cumulative recharge amount is less than the first amount and exceeds the second amount, WeChat can be used to reach them. For these target return users, they have a certain degree of satisfaction with the application in the past, but the historical recharge amount of these users is small. Therefore, using WeChat to reach them will make it easier for them to download and use the application, which can improve the return efficiency to a certain extent.

[0115] For target users whose cumulative recharge amount is less than the second amount and exceeds the third amount, SMS or game friends can be used. The third amount can be a lower amount or 0 yuan, that is, no recharge has been made. For these historical users, their satisfaction and preference for the application may be average. Therefore, SMS can be used to show the difference between the recharge amount before and after the discount in text, which is more intuitive and attractive. Alternatively, friends can be used to convey the information. This method is conveyed through game friends, which is more appealing and can better play the role of discount information and improve the return effect of offline users.

[0116] The advantage of this setting of the scheme is that by dividing the accumulated recharge amounts into different amounts and adopting different contact methods, the discount information can be better displayed to offline users, which helps to improve the return efficiency.

[0117] On the basis of the above embodiments, optionally, determining the sending time of the reaching information according to the historical usage time period in the historical usage data of the return target user includes:

[0118] The historical usage time period of the target returning user falls into the time period with the most in each time period of each day, and is determined as the game time period of the target returning user.

[0119] The starting time of the game period of the returning target user is determined as the sending time of the reaching information.

[0120] For example, the historical usage time segments of the return target user include 1:00 to 4:00 p.m. and 7:00 to 9:00 p.m., but the usage frequency from 7:00 to 9:00 p.m. is higher. For example, within one month, the return target user uses it 20 times from 1:00 to 4:00 p.m. and 60 times from 7:00 to 9:00 p.m., then it can be determined that the gaming period of the return target user is from 7:00 to 9:00 p.m.

[0121] Then, in the subsequent process of sending the contact information, it can be determined that 7 to 9 p.m. is the time for sending the contact information.

[0122] Through such a setting, this solution can make the sending time of the contact information consistent with the historical usage habits of offline users, so as to play the greatest role and improve the return effect.

[0123] In order to allow those skilled in the art to have a clearer understanding of the present solution, a specific implementation method is given below using a game project as an example to illustrate the technical solution.

[0124] Figure 3 Schematic diagram of the user return flow of the application provided in the second embodiment of the present application. Figure 3 As shown, this scheme includes the following steps:

[0125] Use big data or database technology and apply offline computing methods to export usage data of all historical users of the game; the usage data includes user account information, in-game login behavior, payment behavior, etc.

[0126] Through big data or database technology, SQL (Structured Query Language) is applied to filter out users who are active in the current week and users who enter the game for the first time in history but have never entered the game again (non-secondary users).

[0127] Reach out to filtered users, and use different contact processes for different users. First, all contacts need to be made within the scope of their previous activity. Secondly, different contact strategies are implemented for different user game payment levels. For example, high-recharge players will be contacted through multiple rounds or even manual phone calls, while low-recharge players only need SMS or in-game notifications.

[0128] By adjusting the attribution method, all users who actually return through the above return strategies will be attributed to the return strategies for calculating the return effects.

[0129] For example, Project A is a game that has attracted more than 10 million users in history, but as time goes by, it is now the sixth year and has fewer active users. At this time, you can set up a discount server for this game and use the discount server to attract users who have played the game before to re-enter the game to experience it. You can select the users who are suitable for reflow from the 10 million users and send accurate contact information to improve the reflow effect.

[0130] In addition, the user filtering algorithm in this solution can be defined by strategies such as no third-rate users and zero-recharge users in addition to active and non-secondary users, and even an algorithm model can be built to predict the probability of return flow. As for the contact method, in addition to in-game contact, SMS contact and phone contact, other contact methods can also be used, such as third-party push, video calls, super SMS and information flow advertising.

[0131] This solution can help games that are at the end of their life cycle to attract historical users when they cannot be promoted well. Because historical users have already experienced the game, the conversion rate of returning users will be much higher than that of conventional promotions, and the cost will be lower. In addition, user return strategies and content can be tailored to each user, which will improve the return effect.

[0132] Embodiment 3

[0133] Figure 4 Schematic diagram of the structure of the user return flow processing device of the application provided in the third embodiment of the present application. Figure 4 As shown, the device comprises:

[0134] The historical usage data acquisition module 401 is used to acquire the historical usage data of offline users of the application program;

[0135] A return target user determination module 402 is used to screen the historical usage data to determine the return target users;

[0136] A target discount information determination module 403 is used to determine target discount information matching the return target user from the discount information published by the discount server according to the historical usage data of the return target user;

[0137] A reach parameter determination module 404 is used to construct the reach information based on the target discount information, and determine the reach method and sending time of the reach information according to the historical usage data of the return target user;

[0138] The reaching information sending module 405 is used to send the reaching information to the return target user according to the determined reaching method after the sending time is reached.

[0139] The technical solution provided in this embodiment obtains the historical usage data of offline users of the application; screens the historical usage data to determine the target users for return; determines the target discount information that matches the target users for return from the discount information published by the discount server based on the historical usage data of the target users for return; constructs the reach information based on the target discount information, and determines the reach method and sending time of the reach information based on the historical usage data of the target users for return; after the sending time is reached, sends the reach information to the target users for return in accordance with the determined reach method. The above technical solution can be used in conjunction with a discount server based on the historical usage data of offline users, and can provide offline users with the possibility of recall with reach information that matches their usage needs, thereby achieving efficient return of offline users and increasing the number of return of offline users of the application.

[0140] The user return flow processing device of the application in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a palm computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0141] The user return flow processing device of the application in the embodiment of the present application can be a device with an operating system. The operating system can be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0142] The user reflow processing device for an application provided in the embodiment of the present application can implement each process of the above method embodiment, and will not be described again here to avoid repetition.

[0143] Embodiment 4

[0144] Figure 5 Schematic diagram of the structure of the electronic device provided in the fourth embodiment of the present application. Figure 5 As shown, an embodiment of the present application also provides an electronic device 500, including a processor 501, a memory 502, and a program or instruction stored in the memory 502 and executable on the processor 501. When the program or instruction is executed by the processor 501, each process of the user reflow processing method embodiment of the above-mentioned application is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0145] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0146] Embodiment 5

[0147] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the user reflow processing method embodiment of the above-mentioned application is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0148] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0149] Embodiment 6

[0150] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the user reflow processing method embodiment of the above-mentioned application, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0151] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0152] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0153] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0154] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0155] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for processing user return flow of an application, characterized in that: The method comprises: Get historical usage data of offline users of the application; Screening the historical usage data to determine target return users; Determining target discount information matching the return target user from discount information published by a discount server according to historical usage data of the return target user; Constructing the reaching information based on the target discount information, and determining the reaching method and sending time of the reaching information according to the historical usage data of the returning target user; After the sending time is reached, the reaching information is sent to the return target user according to the determined reaching method.

2. The method for processing user reflow of an application according to claim 1, characterized in that: According to the historical usage data of the return target user, determining target discount information matching the return target user from the discount information published by the discount server includes: Read whether there is any historical purchase data in the historical usage data of the return target user, and the purchase object if there is any historical purchase data; If there is no historical purchase data in the historical usage data, determining default recommended information from the discount information published by the discount server as the target discount information; If there is historical purchase data in the historical usage data, information with the highest correlation with the purchase object is determined from the discount information published by the discount server as target discount information.

3. The method for processing user reflow of an application according to claim 1, characterized in that: Constructing the reaching information based on the target discount information, and determining the reaching method and sending time of the reaching information according to the historical usage data of the returning target user, including: Constructing text content of the reaching information based on the target discount information; Determine the contact method of the contact information according to the accumulated recharge amount in the historical usage data of the return target user; wherein the contact method includes: at least one of telephone contact, SMS contact, WeChat contact and friend transmission; The sending time of the contact information is determined according to the historical usage time period in the historical usage data of the return target user.

4. The method for processing user reflow of an application according to claim 3, characterized in that: Determining the contact method of the contact information according to the accumulated recharge amount in the historical usage data of the return target user includes: If the cumulative recharge amount of the target return user exceeds the first amount, determining that the contact method of the target return user is telephone contact; If the cumulative recharge amount of the target return user is less than the first amount and exceeds the second amount, determining that the contact method of the target return user is WeChat contact; If the accumulated recharge amount of the target returning user is less than the second amount and exceeds the third amount, it is determined that the contact method for the target returning user is SMS contact or game friend communication.

5. The method for processing user reflow of an application according to claim 3, characterized in that: Determining the sending time of the contact information according to the historical usage time period in the historical usage data of the return target user includes: The historical usage time period of the target returning user falls into the time period with the most in each time period of each day, and is determined as the game time period of the target returning user. The starting time of the game period of the returning target user is determined as the sending time of the reaching information.

6. The method for processing user reflow of an application according to claim 1, characterized in that: According to the historical usage data of the return target user, determining target discount information matching the return target user from the discount information published by the discount server includes: According to the game level data of the historical usage data of the target returning user, target discount information matching the game level data of the target returning user is determined from the discount information published by the discount server; wherein the game level data includes the team data and / or the game duration data of the master camp.

7. The method for processing user reflow of an application according to claim 1, characterized in that: After sending the reaching information to the reflow target user according to the determined reaching method, the method further includes: Collect statistics on actual return data of target users through various contact methods; The actual return data is input into the reward model together with the offline user's historical usage data, reach information and reach method, and the reward score for the offline user's historical usage data in each reach information and each reach method is determined to obtain the optimal reach information and optimal reach method for each offline user's historical usage data.

8. A user return flow processing device for an application, characterized in that: The device comprises: A historical usage data acquisition module is used to acquire the historical usage data of offline users of the application; A return target user determination module, used to screen the historical usage data and determine the return target users; a target discount information determination module, configured to determine target discount information matching the return target user from the discount information published by the discount server according to the historical usage data of the return target user; A reach parameter determination module, used to construct the reach information based on the target discount information, and determine the reach method and sending time of the reach information according to the historical usage data of the return target user; A reaching information sending module is used to send reaching information to the return target user according to the determined reaching method after the sending time is reached.

9. An electronic device, characterized in that: The invention comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements a user reflow processing method for an application program according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by the processor, the user reflow processing method of the application program according to any one of claims 1 to 7 is implemented.

Images