Application popularization method and device based on scene, equipment and readable medium
By obtaining and analyzing the semantic information of the user group, personalized promotion is carried out for different user groups, which solves the problem of low conversion rate caused by consistent promotion methods in the existing technology, and achieves more efficient application promotion results.
Patent Information
- Application Number
- CN202411186833.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-25
- Publication Date
- 2024-11-05
AI Technical Summary
When applying and promoting the existing technology, it usually uses a consistent method to promote it to different users, resulting in the conversion rate not meeting expectations, and it is believed that the user's acceptance is low, but it may actually be a problem with the promotion method and it has failed to effectively promote it to different user groups. .
By obtaining the scene identifier with semantic information of the target application, statistics are carried out on the first user group, user characteristics are extracted, the second user group matching the feature is determined, and customized information based on semantic information is used for promotion to improve the conversion rate .
Effectively discover potential users who use target applications, improve the conversion rate of promotion, and improve user acceptance through customized promotion page design of semantic information.
Smart Images

Figure CN118897916A_ABST
Abstract
Description
[0001] This application is a divisional application of the Chinese patent application. The application date of the original application is: January 25, 2022; the application number is: 202210090761.5; the name of the invention is: A scenario-based application promotion method, device, equipment and readable medium. Technical Field
[0002] The present application relates to the field of computer technology, and in particular to a scenario-based application promotion method, device, equipment and readable medium. Background Art
[0003] In the prior art, the method for promoting an application is usually to promote the application to a large number of different users in the same way. After the promotion, when the conversion rate of the application does not meet expectations, it is usually considered that the user's acceptance of the application is low.
[0004] However, after analysis, it was found that the actual situation was not necessarily a problem with the application itself, but it might also be due to problems with the promotion method. Summary of the invention
[0005] In view of this, the embodiments of the present application provide a scenario-based application promotion method, apparatus, device and readable medium for performing targeted promotion of target applications, thereby increasing the usage rate of the target applications among users.
[0006] To solve the above technical problems, the embodiments of this specification are implemented as follows:
[0007] The embodiment of this specification provides a scenario-based application promotion method, including:
[0008] Obtaining a scene identifier with semantic information for a target application;
[0009] Performing statistics on the first user group corresponding to the scenario identifier to obtain statistical data;
[0010] If the data value of the statistical data reaches the target value, extracting user features of the first user group;
[0011] determining a second user group matching the user characteristics;
[0012] The target application is promoted to the second user group using information customized based on the semantic information.
[0013] The embodiment of this specification provides a scenario-based application promotion device, including:
[0014] A scene identification acquisition module, used to acquire a scene identification with semantic information for a target application;
[0015] A user group statistics module, used to collect statistics on the first user group corresponding to the scenario identifier to obtain statistical data;
[0016] A user feature extraction module, configured to extract user features of the first user group if the data value of the statistical data reaches a target value;
[0017] A matching module, used to determine a second user group matching the user characteristics;
[0018] A target application promotion module is used to promote the target application to the second user group by using information customized based on the semantic information.
[0019] The embodiment of this specification provides a scenario-based application promotion device, including:
[0020] at least one processor; and,
[0021] a memory communicatively connected to the at least one processor; wherein,
[0022] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:
[0023] Obtaining a scene identifier with semantic information for a target application;
[0024] Performing statistics on the first user group corresponding to the scenario identifier to obtain statistical data;
[0025] If the data value of the statistical data reaches the target value, extracting user features of the first user group;
[0026] determining a second user group matching the user characteristics;
[0027] The target application is promoted to the second user group using information customized based on the semantic information.
[0028] An embodiment of the present specification provides a computer-readable medium on which computer-readable instructions are stored. The computer-readable instructions can be executed by a processor to implement a scenario-based application promotion method.
[0029] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:
[0030] By obtaining a scene identifier with semantic information for the target application, statistics are collected for the first user group corresponding to the scene identifier to obtain statistical data. If the data value of the statistical data reaches the target value, the user characteristics of the first user group are extracted, thereby obtaining the characteristic data of active users who actually use the target application. On the one hand, the second user group that matches the user characteristics can be determined based on the characteristic data, thereby effectively mining potential users who use the target application and promoting the target application to the second user group. On the other hand, since the scene identifier has semantic information, designers can design the promotion page in a targeted manner based on the semantic information of the scene identifier, obtain information customized based on the semantic information, and use the information customized based on the semantic information to promote the target application to the second user group, thereby improving the conversion rate of the promoted users. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0032] Figure 1 A flowchart of a scenario-based application promotion method provided in an embodiment of this specification;
[0033] Figure 2 A schematic diagram of information customized based on semantic information;
[0034] Figure 3 Another schematic diagram of information customized based on semantic information;
[0035] Figure 4 A first schematic diagram of a customized page in a scenario-based application promotion method provided in an embodiment of this specification;
[0036] Figure 5 A second schematic diagram of a customized page in a scenario-based application promotion method provided in an embodiment of this specification;
[0037] Figure 6 A schematic diagram of a prompt message sent to a first user for inviting a second user provided in an embodiment of this specification;
[0038] Figure 7 A swimlane diagram for promoting a target application to a new user group based on the scenario-based application promotion method provided by the present invention;
[0039] Figure 8 The embodiments of this specification provide corresponding to Figure 1 A schematic diagram of a structural diagram of a scene-based application promotion device;
[0040] Fig. 9 The embodiments of this specification provide corresponding to Figure 1 A structural schematic diagram of a scenario-based application promotion device. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0042] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards in the relevant regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0043] The inventor has found through research that for different user groups, the effect of promotion by using a recommendation method for the user group will be significantly improved. However, how to classify user groups is a difficult problem. Because if the clustering algorithm in the prior art is used, users with the same characteristics can only be aggregated into one category from a mathematical level, but no meaningful information can be obtained about what method should be used to recommend to such aggregated users.
[0044] In the technical solution of this application, data with semantic information is used as a scene identifier, and users are classified according to this scene identifier. For user groups classified into the same category, relevant technical personnel in the field can know that the user group has characteristics corresponding to the semantic information. Because the characteristics correspond to the semantic information, relevant technical personnel in the field can understand it, so that a promotion method corresponding to the characteristics can be set for promotion. In this way, when the conversion rate does not meet expectations, applications that are considered to have low user acceptance can be promoted well.
[0045] In order to make the purpose, technical solutions and advantages of one or more embodiments in this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of one or more embodiments of this specification. It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, this information should not be limited to these terms, which are only used to distinguish the same type of information from each other.
[0046] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.
[0047] Figure 1 A schematic diagram of a flow chart of a scenario-based application promotion method provided in an embodiment of this specification. From the perspective of a device, the execution subject of the flow can be a server. From the perspective of a program, the execution subject of the flow can be a program installed on an application server.
[0048] like Figure 1 As shown, the process may include the following steps:
[0049] Step S102: Obtain a scene identifier with semantic information for the target application.
[0050] In this step, the target application may refer to an application to be promoted, such as a newly developed application by a company, which needs to be promoted in order to occupy market share. The application may be a complete software application installed on a PC or client in the form of an installation package, or an application that can be attached to other applications for use as a plug-in or applet.
[0051] In this step, the target application may have multiple specific usage scenarios, so that different groups of people can use the target application involving specific usage scenarios according to their own preferences. For example, the target application involves specific scenarios for different groups of people, such as paying for a meal order together, saving money to buy a car together, and saving money to buy a house together. Different groups of people can use the target application for specific scenarios according to their own needs.
[0052] In this step, semantic information can refer to information with certain meaning that can eliminate the uncertainty of things, such as obtaining certain useful information through textual propositions or descriptive sentences, or obtaining useful information contained in pictures or videos through analysis. In some cases, semantic information can be obtained through simple analysis. For example, for a user group named "class dining group", a simple analysis of this group name can show that this is a message group used to communicate or negotiate dining issues among classmates in a class.
[0053] Scenario identification may refer to identification information that can obtain the user's purpose or intention of using the target application, or the way the target application is used. Taking the aforementioned user group as an example, the group name of this user group is "class dining group", then the scene identification can be directly determined as "class dining group" or determined as "dining group" or "dining" from a larger semantic level.
[0054] The scene identifier can be obtained from relevant text, pictures or videos. For example, semantic analysis can be performed on the text, pictures or videos to analyze the scene identifier related to the usage of the target application.
[0055] It should be noted that in this step, several keywords related to the meaning of the scene identifier can be pre-set, that is, several scene identifiers are preset, and in the subsequent stage, the scene identifiers of the actual usage scenarios of the users using the target application are matched with the preset scene identifiers, so as to mine out the scene identifiers with semantic information for the target application; since the users use the target application in various ways and to some extent are unknown, in the subsequent stage, new scene identifiers of the users using the target application can be mined from the information related to the scenarios in which the users actually use the target application, such as text, pictures or videos, that is, new usage scenarios of the users for the target application can be mined.
[0056] Step S104: performing statistics on the first user group corresponding to the scenario identifier to obtain statistical data.
[0057] The first user group may refer to customers who have used the target application, including users who have used the target application for a period of time or who have just used the target application.
[0058] In this step, the number of user groups involving scenario identification in the first user group is counted, so as to analyze the proportion of user groups involving scenario identification in the first user group. For example, the first user group includes 10,000 message groups, each of which includes a number of users, where, in order to maintain generality, in special cases, a message group can also be understood as including only one user. There are 1,000 message groups involving a specific scenario identification, so it can be known that the proportion of message groups involving this specific application scenario is 10%.
[0059] Step S106: If the data value of the statistical data reaches the target value, the user characteristics of the first user group are extracted.
[0060] In this step, the target value can be a pre-set threshold used to measure whether the statistical data obtained in step S104 meets the standard. Specifically, the target value can be a specific numerical value or a numerical range, where the numerical value can be a number representing an absolute size, such as 500, or a number representing a relative size in proportion, such as thirty percent.
[0061] User characteristics may refer to attribute information used to indicate the behavioral characteristics of the first user. For example, if the identity of the first user group is prospective parents, the user characteristics may be understood as the identity characteristics of the user, i.e., prospective parents. By analyzing the specific user characteristic of "prospective parents", the behavioral characteristics of the user may be discovered, such as the user's shopping tendency, such as buying consumer goods such as baby products. By analyzing the specific user characteristic of college students who have just graduated and are working, it may be discovered that they have behavioral characteristics such as saving money to buy gifts for their parents or buying new mobile phones for themselves.
[0062] Specifically, user characteristics can be extracted from multiple dimensions, such as analyzing the basic attributes, social relations, consumption capacity, behavioral characteristics, psychological characteristics and other specific dimensions of the first user group, so as to mine the user characteristics of the first user group, wherein the basic attributes can refer to specific attributes such as occupation, social relations can refer to social attributes such as whether married, whether having children, whether having brothers, etc., consumption capacity can refer to user attributes indicating consumption capacity such as monthly consumption, whether credit cards are opened, whether there is a mortgage, etc., behavioral characteristics can refer to behavioral attributes such as whether group purchases are often made, whether discounted goods are purchased, etc., and psychological characteristics can refer to psychological attributes such as whether there is a preference for a certain brand, whether goods are often put into the shopping cart without being purchased, etc. In this step, by extracting the user characteristics of the first user group, the subsequent steps can mine the second user group with the same user characteristics as the first user group.
[0063] The user characteristics of the first user group may be extracted by analyzing the specific usage behavior of the first user group for the target application, such as analyzing the consumption behavior and money-saving behavior of the first user group when using the target application.
[0064] Step S108: Determine a second user group that matches the user characteristics.
[0065] In this step, the second user group may refer to the user group targeted at the stage of large-scale promotion of the target application. The second user group may be users who have not used the target application before, or users who have used the target application but have not used the target application in a specific scenario. The purpose of this step is to mine the second user group with the same user characteristics as the first user group. Since the second user group and the first user group have the same user characteristics, it can be reasonably inferred that the second user group and the first user group have the same behavioral characteristics, so the second user group is more inclined to use the target application than general users.
[0066] The technical solution of this embodiment does not limit the method of determining the second user group. For example, the second user group matching the user characteristics can be determined based on information such as the user's online shopping behavior and the consumption behavior based on payment software.
[0067] Step S110: promoting the target application to the second user group using information customized based on the semantic information.
[0068] In the technical solution of this embodiment, customized information may refer to information used to attract the second user group to use the target application, such as a paragraph of text carrying a hypertext link of a textual nature, where the user can install the target application by clicking the hypertext link in the paragraph of text, or use the target application in the form of a mini-program; or a picture that can be used as a hypertext link, where the user can install or directly use the target application after clicking the picture. In this step, the method for promoting the target application to the second user group may be to send relevant text, pictures or videos containing a hypertext link pointing to the target application to the second user group, such as by direct push via text message or based on the application to which the target application is attached.
[0069] Figure 2 A schematic diagram of information customized based on semantic information. Figure 2 The schematic diagram may be a web page displayed on a mobile phone terminal. The web page may be a page promoting a target application for a home scene. Figure 2As shown, the picture 201 is a picture for a family scene, for example, it can show a family of three. The text 202 represents textual promotional information for the family scene, such as "save a sum of money for the family every day".
[0070] Figure 3 Another schematic diagram of information customized based on semantic information. Figure 3 The schematic diagram may be a web page displayed on a mobile phone terminal. The web page may be a page promoting a target application for a couple scene. Figure 3 As shown, the picture 301 is a picture for a couple scene, for example, it can show a couple. The text 302 can represent textual promotional information for the couple scene, such as "save a sum every day to save money for future marriage and house purchase".
[0071] It should be noted that the first user group may correspond to several scene identifiers, and the aforementioned steps only start from the perspective of a scene identifier among the several scene identifiers, dig out the second user group corresponding to this scene identifier, and recommend the target application to the second user group based on the scene corresponding to the scene identifier. For all or part of the remaining scene identifiers among the several scene identifiers, the corresponding user groups can also be dug out respectively, and the target application can be recommended to the dug out user groups based on the scenes corresponding to each scene identifier.
[0072] Figure 1 The method in the embodiment obtains a scene identifier with semantic information for the target application, performs statistics on the first user group corresponding to the scene identifier, obtains statistical data, and if the data value of the statistical data reaches the target value, extracts the user characteristics of the first user group, thereby obtaining the characteristic data of active users who actually use the target application. On the one hand, the second user group matching the user characteristics can be determined based on the characteristic data, thereby effectively mining potential users who use the target application and promoting the target application to the second user group. On the other hand, since the scene identifier has semantic information, the designer can design the promotion page in a targeted manner based on the semantic information of the scene identifier, obtain information customized based on the semantic information, and use the information customized based on the semantic information to promote the target application to the second user group, thereby improving the conversion rate of the promoted users.
[0073] It should be understood that in the methods described in one or more embodiments of this specification, the order of some steps can be adjusted according to actual needs, or some steps can be omitted.
[0074] based on Figure 1 The method, the examples of this specification also provide some specific implementation plans of the method, which are described below.
[0075] In an optional technical solution, the target application is an application that has the function of transferring resources using a shared account among multiple people. The resources here may refer to resources with a certain use value, such as financial resources with payment functions such as money, electronic currency, and tradable virtual items, or virtual resources related to computers such as storage resources (such as cloud storage space) and computing resources (such as computing threads and computing devices). It should be noted that this is only for illustrative purposes only, and the examples given do not constitute a limitation on the specific coverage of the meaning of the term "resources".
[0076] In an optional technical solution, obtaining a scenario identifier with semantic information for a target application may specifically include: obtaining the scenario identifier from consumption category information of a user for the target application; or, obtaining the scenario identifier from a group name of a user group formed by a user for the target application; or, obtaining the scenario identifier from the user's note information for the target application.
[0077] Specifically, it has been described above that the first user group is a user group that has used the target application, so the scenario identifier with semantic information is obtained by using the usage information of the first user group when using the target application.
[0078] For example, under the premise that the target application is an application that has the function of using a shared account of multiple people to transfer resources, when the first user group consumes through the target application and thus spends payment resources, it can be analyzed based on the consumption category to find out which specific categories of consumption scenarios account for a larger proportion of expenditure or a higher frequency, thereby obtaining a scene identifier with semantic information, that is, obtaining the scene identifier from the user's consumption category information for the target application. For example, among the various categories of consumption items of the first user group, the proportion of consumption expenditure for the consumption scenario of "dining" is higher, so the scene identifier of "catering consumption" can be obtained.
[0079] For another example, in the real world, several users will form a user group based on a certain purpose, such as forming a user group for common consumption. At this time, the purpose of forming the user group can generally be analyzed from the group name of the user group formed by the user. For example, if the group name of a user group is "Happy Outdoor Family Group", it can be analyzed from the group name that the purpose of the user forming this group is to facilitate communication when traveling together, and the scene identifier "travel" can be obtained based on the group name. That is, the scene identifier can be obtained from the group name of the user group formed by the user for the target application.
[0080] For another example, users may transfer financial resources based on the user groups they have established, such as transferring money. When transferring money, in order to let the other party know the purpose of the transfer or remittance, they may add a note about the transfer or remittance, such as "Please check the annual property fee of xxxx yuan". The note information can be used to obtain the scene identifier with semantic information of the user's use of the target application.
[0081] In an optional embodiment technical solution, the statistics on the first user group corresponding to the scene identifier to obtain statistical data may specifically include: counting the number of users in the first user group; or, the statistics on the first user group corresponding to the scene identifier to obtain statistical data may specifically include: counting the number of users in the first user group; calculating the proportion of the number of users in the third user group; the number of users in the third user group is greater than the number of users in the first user group.
[0082] In the technical solution of this embodiment, the third user group may refer to a parent user group, and a first user group may be selected from the parent user group, wherein the first user group has a certain user feature. For example, at the current stage, there are 100 million user groups using this target application. If the 100 million user groups are used as a sample space, and the first user group corresponding to the scene identifier with semantic information of the target application is determined therefrom, then since the number of users included in the 100 million user groups is too large, it is not convenient to implement. A number of user groups, such as 100,000 user groups, may be determined therefrom as the third user group, and then the third user group may be used as a sample space, and then the first user group corresponding to the scene identifier with semantic information may be determined from the sample space, and then the proportion of the number of users included in the first user group to the number of users included in the third user group may be counted.
[0083] In an optional embodiment technical solution, the use of information customized based on the semantic information to promote the target application to the second user group may specifically include: using a page customized based on the semantic information to promote the target application to the second user group; the page contains pictures and / or text customized based on the semantic information.
[0084] In the technical solution of this embodiment, based on the second user group having the same user characteristics as the first user group as previously determined, this step can promote the target application to the second user group. Specifically, a user-friendly promotion information presentation form can be designed during the promotion stage, so that the second user group can more easily accept the promotion information and then install or use the target application. Figure 4 As shown in the figure, when the semantic information of the scene identifier is "buy gifts for parents", the following can be designed: Figure 4 The page containing this semantic information contains the information "Start early, save a little every day, and buy a necklace for mom on her birthday this year", and also contains a picture of a gift, which the user can click Figure 4 , indicating that you agree to the service agreement of the target application, and then click the button labeled "Click to start the target application" to use the target application. Figure 5 As shown in the figure, when recommending target applications for large-item purchase scenarios for users in a husband-wife or couple relationship, you can design the following Figure 5 The promotion page shown in the figure has the message "Work hard every day, buy a car together, and don't embezzle!" Figure 4 In the same way, users can click Figure 5 , indicating that you agree to the service agreement of this target application, and then click the button labeled "Click to start target application" to use the target application.
[0085] In an optional embodiment technical solution, before promoting the target application to the second user group, the following steps may also be included:
[0086] Determining a fourth user group matching the user characteristics; the number of users in the fourth user group is less than the number of users in the second user group;
[0087] recommending the target application to the fourth user group using information customized based on the semantic information;
[0088] Obtaining a first conversion rate of the fourth user group for the information customized based on the semantic information;
[0089] Determine whether the first conversion rate meets a preset condition, and obtain a first determination result;
[0090] The promoting the target application to the second user group may specifically include:
[0091] If the first judgment result indicates that the first conversion rate meets a preset condition, the target application is promoted to the second user group.
[0092] In the technical solution of this embodiment, the fourth user group may refer to a user group that is first tested in a small range to detect the promotion effect before the target application is promoted to the second user group, which is a large-scale target group. The purpose of the test is to obtain the ratio of the number of people who use this target application in the mined fourth user group to the number of people in the fourth user group, that is, the first conversion rate, based on the premise that the user characteristics match those of the first user group, so as to verify the effect of the technical solution of the embodiment of the present invention in a small range based on this ratio. In the subsequent stage, the test plan can be iteratively changed based on whether the test effect reaches the expected goal, so as to optimize the technical solution of the present invention.
[0093] In an optional embodiment technical solution, before determining whether the first conversion rate meets a preset condition, the following steps may also be included:
[0094] A fifth user group is randomly selected, and an absolute value of a difference between the number of users in the fifth user group and the number of users in the fourth user group is less than a set threshold;
[0095] recommending the target application to the fifth user group using information customized based on the semantic information;
[0096] Obtaining a second conversion rate of the fifth user group for the information customized based on the semantic information;
[0097] The determining whether the first conversion rate meets a preset condition may specifically include:
[0098] Determine whether the first conversion rate is statistically significantly higher than the second conversion rate.
[0099] The foregoing describes that based on the premise of having user characteristics matching the first user group, the ratio of the number of people using this target application in the mined fourth user group to the number of people in the fourth user group is obtained, thereby verifying the effect of the technical solution of the embodiment of the present invention in a small range. In order to verify the effect of the technical solution of the embodiment of the present invention from another perspective, on the basis of the steps in the foregoing, a fifth user group can be randomly selected, and this target application can be recommended to the fifth user group, and the ratio of users in the fifth user group who use this target application based on this recommendation information to the total number of users in the fifth user group is obtained, that is, the second conversion rate is obtained, and then the first conversion rate obtained in the foregoing is numerically compared with the second conversion rate here, and it is determined whether the first conversion rate is statistically significantly higher than the second conversion rate, thereby verifying the effect of the technical solution of the present invention. Among them, significant means that the difference is significant, that is, the difference between the two is very large, so large that it can be considered that the difference between the two is due to substantial differences in statistics, rather than just measurement errors.
[0100] In an optional embodiment technical solution, the method may also include: determining a first user who matches the user characteristics from users who have used the target application; determining at least one second user from users who have a relationship with the first user; and sending a prompt message to the first user to invite the second user to use the target application together with the first user. The technical effect of the aforementioned steps is that for a first user who has used the target application, a second user who has a relationship with the first user that matches the specific scenario can be determined for a specific scenario corresponding to the aforementioned scenario identifier, and a prompt message is sent to the first user, prompting the first user to send a share or invitation to the second user. If the second user accepts the share or invitation after receiving the share or invitation message, the second user can join the user group corresponding to the specific scenario through operations such as confirmation, so that the first user and the second user can join the user group together to promote the target application.
[0101] Figure 6 Schematic diagram of a prompt message sent to a first user for inviting a second user provided in an embodiment of this specification. Figure 6 As shown, the prompt information can exist in the form of a page. The page may include the text message "Click on the link to invite friends to participate in the xxx plan". At the same time, the page may also include a list of users to be shared recommended to the first user. The list may include the identifiers of multiple users. The first user can select the user in the list to determine the user selected by the first user as the second user. More specifically, the users in the user list can be users who have a user relationship with the first user that meets a specific scenario and are determined based on the relationship identification of users who have financial transactions with the first user, friends of the first user, and members of the address book.
[0102] In the technical solution of this embodiment, after extracting the user features of the first user group in step S106, specifically, a first user with a specific number of one with this user feature can be determined, and based on the social relationship of the first user, a second user with a certain relationship with the first user can be determined. Depending on the specific type of this social relationship, the number of second users can be one or more. For example, when this social relationship is a family relationship, multiple second users with a family relationship with the first user can be determined, or, when this social relationship is a couple relationship or a husband-and-wife relationship, a second user with a couple relationship or a husband-and-wife relationship with the first user can be determined, so that in the technical solution of this embodiment, a prompt message can be sent to the first user, and this prompt message is used to prompt the first user to invite the second user to use this target application together with the first user in order to achieve a common goal. For example, taking the scene identifier "traveling" with semantic information as an example, the first user is a family member in a family, and a user group based on this target application for saving money to travel or consume together can be sent to the rest of the family members of the first user.
[0103] In an optional technical solution, determining at least one second user from users who have a relationship with the first user may specifically include: obtaining first user information in the first user's address book; obtaining second user information of users who have resource transfers with the first user within a preset time range; and determining at least one second user based on the first user information and the second user information.
[0104] In the technical implementation stage, at least one second user who has a certain social relationship with the first user can be determined based on the address book of the first user's communication tool, where the communication tool can refer to a hardware communication tool such as a mobile phone or a landline, or the address book of the first user recorded on the communication software running on the hardware communication tool. For example, the first user may record the note of his father's mobile phone number as "Dad", then at least one second user who has a certain social relationship with the first user can be found by reading this address book. At the same time, at least one second user who has a certain social relationship with the first user can also be determined by mining the first user's resource transfer records within a certain period of time, such as the payee information of the transfer record and the remittance record. For example, in a certain scenario, the first user may transfer money to a second user, and the transfer note information is "Brother, living expenses for June", then based on this information, the second user who is a brother or sister to the first user can be determined.
[0105] In an optional embodiment technical solution, determining at least one second user based on the first user information and the second user information may specifically include: determining the relationship type corresponding to the scene identifier; calculating the relationship association degree for users who have a relationship with the first user according to the relationship type based on the first user information and the second user information; and determining a preset number of second users in order of the relationship association degrees from high to low.
[0106] In the technical solution of this embodiment, in a certain scenario, multiple second users may be determined, such as the first user distributing virtual red envelopes to multiple relatives during the holidays, such as sending virtual red envelopes to 68 relatives, and the first user may only want to invite several relatives with the closest relationship when forming a relative travel group based on the target application. In this embodiment, after analyzing the relationship type corresponding to the scene identifier, according to the specific type of this relationship type, such as lovers, families, relatives, etc., only a preset number of second users can be determined based on the relationship correlation of the social relationship corresponding to the relationship type with the first user. The technical solution of the embodiment of the present application does not limit the method of obtaining this relationship correlation, such as it can be obtained from the notes of the first user's address book. For example, the first user can annotate some relatives as "Dad", "Mom", "Eldest Sister", "Aunt", etc., then the semantics of these notes can be analyzed to determine a preset number of second users, which will be submitted to the first user for confirmation, or the first user can determine several second users by actively selecting.
[0107] In an optional technical solution, after sending the prompt information to the first user to invite the second user to use the target application together with the first user, it may also include: obtaining a sharing operation performed by the first user based on the prompt information; based on the sharing operation, sending invitation information to the second user to invite the second user to use the target application together with the first user.
[0108] Based on the foregoing description, a specific embodiment is given below to illustrate the technical solution of the present invention based on a specific scenario.
[0109] Figure 7 This is a swimlane diagram for promoting target applications to new user groups in the scenario-based application promotion method proposed by the present invention. Figure 7 As shown, the following steps are included:
[0110] Step S702: Get the group name.
[0111] The first user group that has used the target application has formed several user groups based on the target application. This step obtains the group names of these user groups. According to the previous records, it can be known that this step can also obtain the consumption records of the user group, and based on the consumption category information in the consumption records, subsequent steps such as mining scene identification can also be performed.
[0112] Step S704: mining scene identifiers.
[0113] This step analyzes the group names of these user groups and mines out several scene identifiers with semantic information.
[0114] Step S706: Determine multiple scenes.
[0115] This step determines multiple specific scenarios in which the first user group uses the target application, such as family scenarios, couple scenarios, food and drink scenarios, travel scenarios, etc., based on the scenario identifiers determined in step S704.
[0116] Step S708: Determine a significant scene identifier.
[0117] Since several scene identifiers with semantic information can be mined, it is possible to determine from these scene identifiers which scene identifiers correspond to user groups with a larger proportion of group names, thereby determining significant scene identifiers.
[0118] Step S710: extracting user features.
[0119] In this step, for each of the newly determined scene identifiers, user features of the corresponding user group are extracted respectively.
[0120] Step S712: Determine the user group to be promoted based on user characteristics.
[0121] In this step, based on user characteristics, a user group to be promoted is determined for each scenario identifier within a small user group that has not used the target application.
[0122] Step S714: Determine whether the user conversion rate within a small range exceeds a predetermined threshold. If yes, proceed to step S716; if no, proceed to step S704.
[0123] In this step, the corresponding target applications with scene identifiers are pushed to the user groups to be promoted determined in step S712 respectively, and then it is determined whether the user conversion rate of this small range of user groups exceeds the predetermined threshold. If it does not exceed the predetermined threshold, the reason can be analyzed, such as re-analyzing whether several scene identifiers with semantic information mined from the first user group are indeed scene identifiers that account for a relatively large proportion of all scene identifiers.
[0124] Step S716: Model iteration.
[0125] If the user conversion rate within the small user population in step S714 exceeds a predetermined threshold, the target application can be promoted to a new user group that is slightly larger than the small user population in step S712, and the model can be iteratively optimized based on the user characteristics of users who are successfully converted after the promotion.
[0126] Step S718: Score the entire user group by scenario.
[0127] Step S720: For each scenario, determine a user group with a high score.
[0128] Step S722: Promote the target application to high-scoring user groups in the form of a customized page.
[0129] The purpose of step S718 and step S720 is to determine which scene identifiers correspond to the target applications in the scenarios that should be pushed to each individual user during the large-scale promotion stage of the target application within the entire user group. Specifically, for a certain scene identifier, it can be screened according to the feature matching principle. For example, there are scene identifiers A and B. For the user User, the user characteristics of this user User can be matched with the user characteristics corresponding to the scene identifiers A and B respectively, so that the target application can be pushed to the user User based on the scene identifier with the highest matching degree. Therefore, for each scene identifier, since the corresponding user group is accurately screened, this user group has a stronger tendency to use the target application in the scenario corresponding to this scene identifier, thereby improving the user conversion rate of the target application. In this process, the target application can be promoted to each user group to be promoted in the form of a customized page.
[0130] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method. Figure 8 The embodiments of this specification provide corresponding to Figure 1 A schematic diagram of the structure of a scene-based application promotion device. Figure 8 As shown, the device may include:
[0131] A scene identification acquisition module 802 is used to acquire a scene identification with semantic information for a target application;
[0132] A user group statistics module 804, configured to collect statistics on the first user group corresponding to the scenario identifier to obtain statistical data;
[0133] A user feature extraction module 806, configured to extract user features of the first user group if the data value of the statistical data reaches a target value;
[0134] A matching module 808, configured to determine a second user group matching the user characteristics;
[0135] The target application promotion module 810 is configured to promote the target application to the second user group by using information customized based on the semantic information.
[0136] based on Figure 8 The present specification also provides some specific implementation schemes of the method, which are described below.
[0137] In an optional embodiment technical solution, the device may further include a target application promotion module, which is used to: determine a fourth user group matching the user characteristics; the number of users in the fourth user group is less than the number of users in the second user group;
[0138] recommending the target application to the fourth user group using information customized based on the semantic information;
[0139] Obtaining a first conversion rate of the fourth user group for the information customized based on the semantic information;
[0140] Determine whether the first conversion rate meets a preset condition, and obtain a first determination result;
[0141] The promoting the target application to the second user group may specifically include:
[0142] If the first judgment result indicates that the first conversion rate meets a preset condition, the target application is promoted to the second user group.
[0143] In an optional embodiment technical solution, the device may further include a prompt information sending module, which is used to: determine a first user matching the user characteristics from users who have used the target application;
[0144] determining at least one second user from users having a relationship with the first user;
[0145] Sending a prompt message to the first user for inviting the second user to use the target application together with the first user.
[0146] It is understood that the above modules refer to computer programs or program segments for executing one or more specific functions. In addition, the distinction between the above modules does not mean that the actual program codes must also be separated.
[0147] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method.
[0148] Fig. 9The embodiments of this specification provide corresponding to Figure 1 A schematic diagram of the structure of a scenario-based application promotion device. Fig. 9 As shown, the device 900 may include:
[0149] at least one processor 910; and,
[0150] A memory 930 in communication with the at least one processor; wherein,
[0151] The memory 930 stores instructions 920 that can be executed by the at least one processor 910. The instructions are executed by the at least one processor 910 to enable the at least one processor 910 to:
[0152] Obtaining a scene identifier with semantic information for a target application;
[0153] Performing statistics on the first user group corresponding to the scenario identifier to obtain statistical data;
[0154] If the data value of the statistical data reaches the target value, extracting user features of the first user group;
[0155] determining a second user group matching the user characteristics;
[0156] The target application is promoted to the second user group using information customized based on the semantic information.
[0157] Based on the same idea, the embodiment of this specification also provides a computer-readable medium corresponding to the above method. The computer-readable medium stores computer-readable instructions, which can be executed by a processor to implement the following method:
[0158] Obtaining a scene identifier with semantic information for a target application;
[0159] Performing statistics on the first user group corresponding to the scenario identifier to obtain statistical data;
[0160] If the data value of the statistical data reaches the target value, extracting user features of the first user group;
[0161] determining a second user group matching the user characteristics;
[0162] The target application is promoted to the second user group using information customized based on the semantic information.
[0163] The above is a description of a specific embodiment of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0164] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.
[0165] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.
[0166] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0167] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0168] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0169] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0170] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0172] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0173] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0174] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0175] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0176] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0177] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0178] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A scenario-based application promotion method, comprising: Obtaining a scene identifier with semantic information for a target application; Extracting user characteristics of a first user group corresponding to the scenario identifier; determining a second user group matching the user characteristics; The target application is promoted to the second user group using information customized based on the semantic information. 2 . The method according to claim 1 , wherein the target application is an application having a function of transferring resources using a multi-person shared account.
3. According to the method of claim 2, the first user group is a user group that has used the target application; and the step of obtaining a scene identifier with semantic information for the target application comprises: The scenario identifier is acquired based on usage information of the target application by the first user group.
4. The method according to claim 3, wherein obtaining the scenario identifier based on the usage information of the target application by the first user group specifically comprises: Acquiring the scenario identifier from the user's consumption category information for the target application; Alternatively, the scenario identifier is obtained from a group name of a user group formed by a user for the target application; Alternatively, the scenario identifier is obtained from the user's remark information for the target application.
5. According to the method of claim 1, extracting the user characteristics of the first user group corresponding to the scene identifier specifically comprises: Performing statistics on the first user group to obtain statistical data; If the data value of the statistical data reaches the target value, the user features of the first user group are extracted.
6. The method according to claim 5, wherein the performing statistics on the first user group to obtain statistical data specifically comprises: Counting and obtaining the number of users in the first user group; Alternatively, the performing statistics on the first user group to obtain statistical data specifically includes: Counting the number of users in the first user group; The proportion of the number of users in the third user group is calculated; the number of users in the third user group is greater than the number of users in the first user group; and the first user group is a user group determined from the third user group.
7. The method according to claim 1, wherein the using information customized based on the semantic information to promote the target application to the second user group specifically comprises: Using a page customized based on the semantic information to promote the target application to the second user group; The page includes pictures and / or texts customized based on the semantic information.
8. The method according to claim 1, before promoting the target application to the second user group, further comprising: Determining a fourth user group matching the user characteristics; the number of users in the fourth user group is less than the number of users in the second user group; recommending the target application to the fourth user group using information customized based on the semantic information; Obtaining a first conversion rate of the fourth user group for the information customized based on the semantic information; Determine whether the first conversion rate meets a preset condition, and obtain a first determination result; The promoting the target application to the second user group specifically includes: If the first judgment result indicates that the first conversion rate meets a preset condition, the target application is promoted to the second user group.
9. The method according to claim 8, further comprising: If the first judgment result indicates that the first conversion rate does not meet the preset condition, the step of obtaining the scene identification with semantic information for the target application is executed again.
10. The method according to claim 8, before determining whether the first conversion rate meets a preset condition, further comprising: A fifth user group is randomly selected, and an absolute value of a difference between the number of users in the fifth user group and the number of users in the fourth user group is less than a set threshold; recommending the target application to the fifth user group using information customized based on the semantic information; Obtaining a second conversion rate of the fifth user group for the information customized based on the semantic information; The determining whether the first conversion rate meets a preset condition specifically includes: Determine whether the first conversion rate is statistically significantly higher than the second conversion rate.
11. The method according to claim 1, further comprising: Determining a first user matching the user characteristics from among users who have used the target application; determining at least one second user from users having a relationship with the first user; Sending a prompt message to the first user for inviting the second user to use the target application together with the first user.
12. The method according to claim 11, wherein the prompt information includes a list of users to be shared that includes multiple user identifiers and is recommended to the first user; the users in the list of users to be shared include users who have a user relationship with the first user that meets the specific scenario and are determined after relationship identification is performed on users who have a resource transfer relationship with the first user, friends of the first user, and address book members; The determining at least one second user from users having a relationship with the first user specifically includes: A user selected by the first user from the to-be-shared user list is determined as the second user.
13. The method according to claim 11, wherein determining at least one second user from users having a relationship with the first user comprises: Obtaining first user information from the first user's address book; Acquire information of a second user who has transferred resources with the first user within a preset time range; At least one second user is determined based on the first user information and the second user information.
14. The method according to claim 13, wherein determining at least one second user based on the first user information and the second user information comprises: Determining a relationship type corresponding to the scene identifier; Based on the first user information and the second user information, and according to the relationship type, calculating a relationship association degree for users having a relationship with the first user; A preset number of second users are determined according to the order of the relationship association from high to low.
15. The method according to claim 11, after sending the prompt information for inviting the second user to use the target application together with the first user to the first user, further comprising: Acquire a sharing operation performed by the first user based on the prompt information; Based on the sharing operation, invitation information is sent to the second user to invite the second user to use the target application together with the first user.
16. A scenario-based application promotion device, comprising: A scene identification acquisition module, used to acquire a scene identification with semantic information for a target application; A user feature extraction module, used to extract user features of the first user group corresponding to the scene identifier; A matching module, used to determine a second user group matching the user characteristics; A target application promotion module is used to promote the target application to the second user group by using information customized based on the semantic information.
17. A scenario-based application promotion device, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Obtaining a scene identifier with semantic information for a target application; Extracting user characteristics of a first user group corresponding to the scenario identifier; determining a second user group matching the user characteristics; The target application is promoted to the second user group using information customized based on the semantic information.
18. A computer-readable medium having computer-readable instructions stored thereon, wherein the computer-readable instructions can be executed by a processor to implement the scenario-based application promotion method according to any one of claims 1 to 15.
