Example 1
There are also provided method embodiments of a method of ranking sub-applications in an App, according to embodiments of the invention, it being noted that the steps illustrated in the flowchart of the figure may be performed in a computer system such as sets of computer-executable instructions and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
For example, as running on a computer terminal, fig. 1 is a hardware structure block diagram of a computer terminal applying a sorting method of sub applications in App of the embodiments of the present invention, as shown in fig. 1, a computer terminal 10 may include or more (only is shown in the figure) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication function, as those skilled in the art will understand, the structure shown in fig. 1 is only schematic, and does not limit the structure of the electronic device described above.
The memory 104 may be configured to store software programs and modules of application software, such as program instructions/modules corresponding to a sorting method of sub-applications in the application App in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 104, so as to implement the vulnerability detection method of the application programs described above.
The transmission device 106 is used for receiving or transmitting data via networks, the specific examples of the networks may include a wireless Network provided by a communication provider of the computer terminal 10, in examples, the transmission device 106 includes Network Interface Controllers (NICs) which may be connected to other Network devices through a base station so as to communicate with the internet, and in examples, the transmission device 106 may be a Radio Frequency (RF) module for communicating with the internet in a wireless manner.
Under the operating environment, the application provides a sorting method of sub-applications in application App as shown in fig. 2 is a flowchart of a sorting method of sub-applications in application App according to an embodiment of the present invention.
As shown in fig. 2, the method for sorting sub-applications in the App may include the following implementation steps:
step S202, user attribute information of an th application App is obtained, wherein the user attribute information is used for indicating the information of the characteristics of the user, and the th application App comprises a plurality of th sub-applications.
The th application App in the step S202 is not limited to application software such as Payment treasures, Taobao travel and the like, and the th sub-application is not limited to application software such as air ticket purchasing, water, electricity and coal payment and the like.
In the embodiment of the invention, the user attribute information can be used for indicating the characteristics of the user, and the user attribute information comprises or a combination of of occupation, age, sex, consumption type and consumption degree, wherein the occupation, age, sex, consumption type and consumption degree can be obtained according to information input when the user registers and logs in an account on the App, or can be obtained by presumption of operation information of the user, for example, if the user A purchases airline tickets frequently and the position changes frequently, the occupation of the user A can be presumed to be a commercial person, and for example, if the user B purchases ladies frequently, the sex of the user B can be presumed to be women.
And step S204, matching the user attribute information with an application feature library pre-established by each th sub-application, and sequencing each th sub-application according to the matching result of the user attribute information and the application feature library.
And matching the user attribute information with the application feature library pre-established by each th sub-application, specifically comprising the steps of respectively calculating the information similarity of the user attribute information and the application feature library pre-established by each th sub-application, wherein the information similarity is the matching result of the user attribute information and each application feature library.
For every th sub-application, respectively, by using the historical user attribute information of each th sub-application, an application feature library of each th sub-application is pre-established, that is, the characteristics of a crowd currently using the th sub-application are extracted, and quantifiable and locatable attribute tags are listed as the application feature library of the th sub-application, the more the user satisfies the characteristics of a certain th sub-application, the greater the probability that the user uses the sub-application.
Further, the respective -th sub-applications are sorted according to the information similarity between the user attribute information and the application feature library of the respective -th sub-applications.
Optionally, when the user attribute information of the App using the is acquired in S202, the method may further include acquiring operation information of each th sub-application of the th App in a th preset time period, where the operation information includes operation behavior information of the user of the th App in each th sub-application.
In the embodiment of the invention, the operation information can comprise operation behavior information of a user of the th application App in each th sub-application, and the operation behavior information comprises or a combination of the following 3936 times of use time, the number of clicks and the number of payments.
For example, taking application a as an example, when any login accounts successfully registered with the pay bank are successful in logging in the pay bank, the function of each th sub-application in the bank can be paid, specifically, the ranking device applying App sub-applications can count the operation information (including operation behavior information) of each application generated by paying the bank within a preset time period (for example, within 3 months) of , for example, within three months of 2015 year 1 month to 3 months, the last use time of user a for the "airplane ticket" application is 2015 year 3 month 28 days, the number of clicks is 67 times, the number of payments is 9 times, the last use time of the "hydroelectric coal" application is 2015 year 1 month 31 days, the number of clicks is 5 times, the number of payments is 1 time, the last use time of the "panning point" application is 2015 year 1 month 12 days, the number of clicks is 16 times, the number of payments is 5 times, and the ranking device applying App sub-book application can obtain the ranking information, the ranking information includes ranking the application information of the applications according to the age of the user, the user a, the water and the ranking information of the water and the ranking of the aforementioned applications.
Then, in step S204, matching the user attribute information with the application feature library pre-established by each th sub-application includes calculating a recommendation score of each th sub-application according to the operation behavior information, the weight of the operation behavior information, and the user attribute information.
In the above steps of the present application, the weight of the operation behavior information may be pre-stored in the sorting apparatus for sub-application in App by a designer, and a specific weight value may be determined by an operator, a Business Intelligence (BI), and a product designer.
Still taking application a as an example, within three months of acquisition, namely 1 month to 3 months in 2015, the last times of use time of user a for the "air ticket" application is 2015 year 3 month 28 days, the number of clicks is 67 times, the number of payments is 9 times, the last times of use time of the "water and electricity coal" application is 2015 year 1 month 31 days, the number of clicks is 5 times, the number of payments is 1 time, the last times of use time of the "panning point" application is 2015 year 1 month 12 days, the number of clicks is 16 times, the number of payments is 5 times, and the attribute information of user a includes sex male, age 37 years, professional manager and the like, and the ranking device applying App neutron application can calculate the recommended degree scores of the "air ticket" application, the "water and electricity coal" application and the "panning point" application respectively according to the above data and the weight of the operation behavior information.
The sequencing method of the sub-applications in the App, provided by the embodiment of the invention, can restore the behavior habit that a user uses each th sub-application in the th preset period, so that the clicking times and the payment times can be focused on, the time factor is weakened, sequencing is performed only under the condition that the clicking times and the payment times are close to each other, and the weight of the payment times > the weight of the clicking times > the weight of the final use times can be preset.
It should be noted that the sorting method for sub-applications in App according to the embodiment of the present invention can set corresponding weights for the operation behavior information according to different attention degrees, and all of the methods are within the protection scope of the embodiment of the present invention.
Optionally, after the step S204, the step S206 is further included, and the th sub-application is recommended to the th application App according to the sorting result of the respective th sub-applications.
In the above step S206, the sorting apparatus of App sub-applications may recommend the th sub-application to the th application according to the recommendation score of each th sub-application after calculating the recommendation score of each th sub-application respectively, and the sorting apparatus of App sub-applications may, but is not limited to, recommend the th sub-application to the th application by generating an application recommendation list including each th sub-application and recommending the application recommendation list to the th application App according to the recommendation score of each th sub-application.
Still taking application a as an example, the sorting device applying sub application in App generates an application recommendation list containing "air ticket" application, "power and coal" application and "water and power and coal" application according to the recommendation degree scores of "air ticket" application, "water and power and coal" application and "pan point" application, and after the updated version of the paid treasures is paid, the application recommendation list is pushed to user a. For user a, the "airline ticket" applications that are frequently used by him are arranged in the front position, and the "hydroelectric coal" applications that are not frequently used are arranged in the rear position.
As can be seen from the above, in the scheme provided in the foregoing embodiment of the present application, by sequencing the th sub-applications according to the attribute information and the operation information of the th sub-applications, the purpose of restoring the essential requirements of the user through the real behavior data of the user and recommending an application suitable for the use habit of each user to the user is achieved, so that the technical effect of increasing the adaptability of the application software is achieved, and the technical problem that in the process of using the application software in the prior art, the th sub-application that is frequently used or wanted is difficult to find by the user after the version update, which results in poor adaptability of the application software is solved.
Optionally, the matching of the user attribute information and the application feature library pre-established by each th sub-application includes respectively calculating a recommendation score of each th sub-application according to the operation behavior information, the weight of the operation behavior information, and the user attribute information.
In alternatives provided by the foregoing embodiment of the present application, as shown in fig. 3, the sorting the th sub-applications according to the matching result of the user attribute information and the application feature library may include:
s302, according to the recommendation degree scores of the th sub-applications, the th sub-applications are sorted.
In the above step S302 of the present application, the sorting device of the sub-applications in the App may implement sorting of the th sub-applications in a scoring manner, and the sorting device of the sub-applications in the App may score the th sub-applications based on the operation behavior information, the weight of the operation behavior information, and the user attribute information, and sort the th sub-applications according to the recommendation degree score of the th sub-applications.
Optionally, in the step S302, based on the operation behavior information, the weight of the operation behavior information, and the user attribute information, the following embodiments may be adopted to score each th sub-application:
step S3022, calculating th scores of the respective th sub-applications according to the operation behavior information and the weight of the operation behavior information.
In the above step S3022 of the present application, the sorting apparatus of the App sub-application may calculate the th score of each th sub-application according to the operation behavior information and the weight of the operation behavior information, and in addition, may calculate the second score of each th sub-application according to the user attribute information, first, the embodiment of the present invention describes how the sorting apparatus of the App sub-application calculates the th score of each th sub-application according to the operation behavior information and the weight of the operation behavior information in detail:
alternatively, in the step S3022, the following embodiment may be adopted to calculate the th score of each th sub-application according to the operation behavior information and the weight of the operation behavior information:
and S10, performing processing on the operation behavior information.
In the above step S10, since the operation behavior information (for example, the last times of usage time, the number of clicks and the number of payments) is not in dimensions, the sorting apparatus applying the App neutron application can perform the processing of classifying on the operation behavior information, wherein classifying is dimensionless processing means, that is, the dimensionless expression is transformed into the dimensionless expression and becomes a scalar.
The operation behavior information comprises or the combination of the following , the last times of use time, clicks and payment times.
Optionally, in the case that the operation behavior information includes the last times of usage time, the step S10 of classifying the operation behavior information into may include obtaining the maximum value and the minimum value corresponding to the last times of usage time in the pre-collected user behavior sample set, and obtaining the maximum value and the minimum value according to the formula Y1=(R-Rmax)/(Rmax-Rmin) Calculating the last times of use time after the classification of , wherein Y1Indicating the last hours of use after being classified into , R indicating the last hours of use, RmaxRepresents the maximum value, R, corresponding to the last times of useminIndicating the minimum value corresponding to the last times of use.
In the case that the operation behavior information includes the number of clicks, the step S10 of classifying the operation behavior information into classes may include obtaining a maximum value and a minimum value corresponding to the number of clicks in a pre-collected user behavior sample set, and obtaining the maximum value and the minimum value according to a formula Y2=(F-Fmin)/(Fmax-Fmin) Calculating the number of clicks classified into , wherein Y2Indicating the number of clicks classified into , F indicating the number of clicks, FmaxIndicates the maximum value, F, corresponding to the number of clicksminIndicating the minimum value corresponding to the number of clicks.
In the case that the operation behavior information includes the payment times, the step S10 of classifying the operation behavior information may include obtaining a maximum value and a minimum value corresponding to the payment times in a user behavior sample set collected in advance, and obtaining the maximum value and the minimum value according to a formula Y3=(M-Mmin)/(Mmax-Mmin) Calculating classified payment timesWherein Y is3Indicating the number of payments classified into , F indicating the number of payments, MmaxIndicating a maximum value, M, corresponding to the number of paymentsminThe representation corresponds to a minimum value of the number of payments.
In the process of performing the grouping processing on the operation behavior information, the embodiment of the invention can perform special processing on extreme values in the number of clicks and the number of payments, for example, removing obviously abnormal values in the sample set to avoid influencing the effect of the grouping processing.
S12, by formula
Calculating th score of each th sub-application, wherein S1 represents th score, Y
iIndicating the operation behavior information classified into , n indicating the number of operation behavior information, X
iA weight representing the operational behavior information.
In the above step S12, after the sorting device for sub-application in App performs the grouping process on the operation behavior information, the sorting device can use a formula
The th score of each th sub-application was calculated.
For example, in the case where the operation behavior information includes the last usage times, the number of clicks, and the number of payments, S1 ═ X1×Y1+X2×Y2+X3×Y3Wherein Y is1Indicates the last hours of use, Y, after classification into 2Indicates the number of clicks, Y, classified into 3Indicating the number of payments, X, attributed to 1Weight X representing the preset time corresponding to the last uses2Weight, X, representing the preset number of clicks3Weight, X, corresponding to a predetermined number of payments3>X2>>X1。
Step S3024, matching the user attribute information with a pre-established application feature library, and calculating a second score of each of the th sub-applications.
In the above step S3024 of the present application, the pre-established application feature library may be set forth in advance from each application, a product manager and/or a service operator may extract the crowd features currently using each application together, list quantifiable and locatable attribute tags, determine corresponding attribute tags for each application, and further obtain the pre-established application feature library, in the following, the embodiment of the present invention describes in detail how the ranking device applying App sub-applications matches user attribute information with the pre-established application feature library, and calculates the second score of each th sub-application:
optionally, in the step S3024, the following implementation may be adopted to calculate the second score of each th sub-application by matching the user attribute information with a pre-established application feature library:
and S20, searching the application matched with the user attribute information in the pre-established application feature library.
In step S20, the sorting device applying App sub-applications may search for applications matching with the user attribute information in a pre-established application feature library, for example, the sorting device applying App sub-applications may determine corresponding attribute tags to match with the applications according to occupation, age, gender, consumption type, consumption degree, and the like in the user attribute information, and then search for applications matching with the user attribute information.
For example, the attribute tags of the "stock market" application and the "outbound" application in the pre-established application feature library include business people, and the attribute information of the user a includes: gender male, age 37 years old, professional sales manager, wherein the professional can judge that the user A belongs to a business person, the sequencing device applying the App neutron application can search the 'stock market' application and the 'overseas' application matched with the attribute information of the user A from the pre-established application feature library.
S22, a preset score is given to the application matched with the user attribute information.
In step S22, after the sorting apparatus of the sub-application in the application App searches the application feature library established in advance for the application matching with the user attribute information, a preset score may be given to the application matching with the user attribute information, where the preset score may also be determined by the operator, the BI, and the product designer. For example, the ranking means of the sub-application in the application App may assign the preset score to the application of "stock market" and the application of "overseas" that are found to match the attribute information of the user a from the pre-established application feature library, and not to the unmatched applications.
S24, calculating a second score of each sub-application according to the preset score.
In step S24, the sorting device of the sub-application in the App may calculate the second score of each th sub-application after assigning a preset score to the application matching the user attribute information.
Step S3026, summing up the th score and the second score of each th sub-application to obtain a score of the recommendation score corresponding to each th sub-application.
In the above step S3026 of the present application, based on the score of each th sub-application obtained in the above steps S10 to S12 and the second score of each th sub-application obtained in the above steps S20 to S24, the ranking device of App sub-applications sums the score and the second score to obtain the score of the recommendation score corresponding to each th sub-application.
S304, recommending the first N th sub-applications to the th application App, wherein N is a preset positive integer, or recommending the th sub-applications with the recommendation degree scores larger than a preset threshold to the th application App.
In step S304, after calculating the score of each th sub-application, the sorting device applying the App sub-applications may sort each th sub-application in the order of descending scores, and recommend the top N th sub-applications to the th application App, or recommend the th sub-application having a recommendation score larger than a preset threshold value to the th application App, for example, the sorting device applying the App sub-applications calculates that for the user a, the score of the "ticket" application larger than the "panning point" application is larger than the score of the "water-electricity-coal" application of the "outdoor travel" application, and the sorting device applying the App sub-applications generates the above-mentioned sub-application score in the order of descending scores from ascending to descending scores, and generates the above-mentioned sub-application recommendation score or the top N th sub-application recommendation score larger than the preset threshold value.
It should be noted that the embodiment of the present invention is only an exemplary illustration, and the individual th sub-applications may be sorted in order of scores from large to small, and other manners may also be adopted, for example, scores from small to large, and the like, which is not limited by the present invention.
In alternatives provided in the foregoing embodiment of the present application, as shown in fig. 4, in step S206, before recommending the th sub-application to the App applied to the according to the recommendation degree score of each th sub-application, the method for sorting the sub-applications applied to the App may further include:
s402, determining a second sub-application of the th application App which does not generate the operation information in the th preset time period and the th application App which generates the operation information in the second preset time period.
In the above steps S202 to S206, the sorting device applying App sub-applications sorts each sub-application that generates operation information within the th preset time period, and optionally, in the above step S402 of the present application, the sorting device applying App sub-applications may also recommend to a silence loss user of an application, that is, a second sub-application that does not generate operation information within the th preset time period and generates operation information within the th preset time period (for example, is not used within the last 3 months, but used within the last 1 year).
Still taking application a as an example, if user a is not used in the last three months but used in the last 1 year is a "ledger" application, the sorting means of the sub-applications in application App can find out the "ledger" application according to the above conditions.
S404, endowing a preset score to the second sub-application.
In step S404, after determining that the th App does not generate operation information within the th preset time period and the th App generates operation information within the second preset time period, the ranking device of the sub-applications in the App may assign a preset score to the second sub-application.
Still taking application a as an example, after finding out the "ledger" application according to the above conditions, the sorting device applying the sub-application in App can assign a score to the "ledger" application, and then when sorting the applications according to the score from large to small, the "air ticket" application, the "pan point" application, the "stock quotation" application, the "overseas" application, the "water and coal" application, and the "ledger" application should be sorted together, so as to generate an application recommendation list including the "air ticket" application, the "pan point" application, the "stock quotation" application, the "overseas" application, the "water and coal" application, and the "ledger" application.
Optionally, recommending the th sub-application to the App according to the recommendation degree scores of the th sub-applications comprises recommending the th sub-application and the second sub-application to the th application App according to the scores in the descending order.
In optional solutions provided in the foregoing embodiment of the present application, in the step S206, before recommending the th sub-application to the App applied to the th sub-application according to the recommendation degree score of each th sub-application, the method for sorting the sub-applications applied to the App may further include:
s30, a third sub-application to be arranged before each sub-application is obtained.
The recommending method comprises the steps of recommending th sub-applications to App according to recommendation degree scores of th sub-applications, sorting the third sub-applications and th sub-applications, deleting applications, identical to the third sub-applications, in the th sub-applications, and recommending the third sub-applications and th sub-applications to th application App, wherein the th sub-applications do not contain the applications identical to the third sub-applications.
In the step S30, based on the requirement of the operator for the application or based on some applications with higher importance, the method for sorting sub-applications in the application App according to the embodiment of the present invention may further obtain a third sub-application that needs to be arranged before each sub-application before generating the application recommendation list.
Still taking application a as an example, if the "treasures" application, "money transfer" application, "mobile phone recharge" application, "credit card repayment" application, and the like belong to applications that the operator needs to push or applications with higher importance, and the applications need to be arranged at the front position ( is generally fixed in position), and the positions of the applications are the same for each application, the ranking device of the sub-application App can obtain the "treasures" application, "money transfer" application, "mobile phone recharge" application, "credit card repayment" application, and the like before generating the application recommendation list, and then rank the "treasures" application, "transfer" application, "mobile phone recharge" application, "credit card repayment" application, "ticket" application, "pan point" application, "stock quotation" application, "outrun" application, "hydropower coal" application, and "book" application, it should be noted that the same applications may appear in the third sub-application in each of the sub-applications, and then, the same applications as the third sub-application in each of the third sub-application should be deleted in the ranking, and each of the third sub-application contains no-application, and each of the third sub-application is identical to the third sub-recommendation 3925.
In optional solutions provided in the foregoing embodiment of the present application, in the step S206, before recommending the th sub-application to the App applied to the th sub-application according to the recommendation degree score of each th sub-application, the method for sorting the sub-applications applied to the App may further include:
s40, a fourth sub-application to be arranged after each sub-application is obtained.
The recommending method comprises the steps of recommending th sub-applications to the App according to the recommendation degree scores of the th sub-applications, sorting the fourth sub-applications and the th sub-applications, deleting the applications, identical to the th sub-applications, in the fourth sub-applications, and recommending the fourth sub-applications and the th sub-applications to the App, wherein the fourth sub-applications do not contain the applications identical to the th sub-applications.
In the step S40, based on the usage habit of the public, the method for sorting sub-applications in the App according to the embodiment of the present invention may further obtain a fourth sub-application that needs to be arranged before each sub-application.
Still taking application a as an example, the "loving donation" application, the "AA collection" application, the "financial instrument" application, the "go a" application, and the like belong to applications conforming to the use habits of the public, and these applications may be arranged at a later position, so that the sorting device applying the App sub-applications may obtain the "loving donation" application, the "AA collection" application, the "financial instrument" application, the "go a" application, and the like before generating the application recommendation list, and further sort the "loving donation" application, the "AA collection" application, the "financial instrument" application, the "go a" application, the "ticket" application, the "pan point" application, the "market quotation" application, the "abroad stock trip" application, the "coal" application, and the "book" application, it should be noted that each of the sub-applications may appear in the same applications as the fourth sub-application, and then each of the fourth sub-applications may be recommended to the same applications as the fourth sub-applications and no application, and each of the fourth sub-application may include the same applications .
It should be added that, with the sorting method for sub-applications in application App according to the embodiment of the present invention, if the sorting device for sub-applications in application App cannot obtain the attribute information of the th application App and the operation information of each th sub-application in the th preset time period of the th application App, for example, the user is downloading the th application App times and never used, the sorting device for sub-applications in application App may obtain a default initial application list and push the default initial application list to the th application App.
The overall scheme of the present application is exemplarily described below with reference to fig. 5:
step A, part (highest priority) is the fixed location of the third sub-application.
In the step a of the present application, based on a push requirement of an operator for an application or based on some applications with higher importance, the ranking method of sub-applications in the application App according to the embodiment of the present invention may further obtain a third sub-application that needs to be ranked before each sub-application before generating the application recommendation list.
Taking application a as an example, applications such as "treasures of balance" application, "transfer" application, "mobile phone recharging" application, "credit card repayment" application and the like belong to applications which an operator needs to push or applications with higher importance, the applications need to be arranged at front positions (fixed positions in the case of ), and the positions of the applications are the same for each application, so that the sorting device of the sub-application in the application App can acquire applications such as "treasures of balance" application, "transfer" application, "mobile phone recharging" application, "credit card repayment" application and the like before generating the application recommendation list
Step B, second part (priority order): personalized preferences of each user for the application.
In the step B, the purpose of restoring the essential requirements of the user through the real behavior data of the user and generating the application recommendation list suitable for the use habit of each user can be achieved according to the user attribute information and the real user behavior (i.e., the operation information).
Step B1, calculating a score for each th sub-application based on the operation information.
The operation information can comprise operation behavior information comprising or a combination of use times, clicks and payment times, for example, the sorting device of the sub application App in the application App can record the times of ticket purchase of the user a, the times of ticket purchase of the clicks and the time of ticket purchase of the last use.
Step B2, based on the user attribute information, calculates a score for each th sub-application.
The occupation, age, sex, consumption type and consumption degree can be obtained according to information input when the user registers and logs in an account on a App, and can also be obtained through operation information conjecture of the user, for example, if the user A frequently purchases airline tickets and the position is frequently changed, the occupation of the user A can be conjectured to be a commercial person, and for example, if the user B frequently purchases ladies, the gender of the user B can be conjectured to be women.
Step B3, ranking the th sub-applications based on the scores of the applications.
The method comprises the steps of constructing an application personalized preference model of a user by superposing user attribute information and an application matching degree on the basis of RFM, wherein R represents the last times of the user clicking an application, F represents the times (namely clicking times) of the user clicking the application in a -th preset time period, M represents the payment times of the user in a -th preset time period, and -th preset time period can be preset according to needs.
Step C, third part (lowest priority): a fourth sub-application.
In the step C, based on the use habit of the public, the sorting method for sub-applications in the application App according to the embodiment of the present invention may further obtain a fourth sub-application that needs to be arranged before each th sub-application after generating the application recommendation list.
And D, generating an application recommendation list.
It should be noted that, finally, the priority of the App home page application of the application may be that the user actively sets > strategic fixed bit (i.e. the aforementioned part ) > intelligent sorting based on user behaviors and characteristics (i.e. the aforementioned second part) > default list sorting (i.e. the aforementioned third part), and then generates a personalized application recommendation list suitable for the user according to the priority.
According to the ranking method of the sub-applications in the App, the ranking of the applications is that the real user behaviors of 3 dimensions of the last times of use time, the number of clicks and the number of payments of a user are collected, an RFM model is built to restore the real use habits of the user on each application and give a use score of each application, the corresponding use scores are matched with a pre-established application feature library based on user attribute information of the user, such as occupation, age, sex, travel and online consumption features, and are given, for each user, the two scores are added to obtain a final score, the final score is ranked according to the score, the personalized partial application ranking suitable for the use habits of the user is obtained, the application recommendation list can be generated while recommending the user is adopted in a mode of combining multiple rule priorities of designated application fixed position, personalized partial application ranking and default ranking, the application recommendation list is stored in a cloud, the application ranking of the user cannot be changed along with the updating of the version of the user, the application recommendation list can be generated while the application recommendation list is used, and the user experience of the application recommendation list can be fully found, so that the user can be obtained.
In the embodiment of the invention, the method comprises the steps of obtaining user attribute information of a th application App and operation information of each 1 th sub-application of a th application App user in a 0 preset time period, wherein the user attribute information is used for indicating the characteristic information of the user, the operation information comprises the operation behavior information of the 2 th application App user in each th sub-application, respectively calculating the recommendation degree score of each th sub-application according to the operation behavior information, the weight of the operation behavior information and the user attribute information, recommending the th sub-application to a th application App according to the recommendation degree score of each th sub-application, reducing the essential requirement of the user through the real behavior data of the user by calculating the recommendation degree score of each th sub-application according to the attribute information and the operation information of each th sub-application, recommending the application suitable for each user use habit to the user, achieving the technical effect of increasing the application software adaptability, further solving the technical problem that the application of the prior art is difficult to find the application with the version after the application is used, and the application is difficult to be adapted to the .
It should be noted that for simplicity of description, the aforementioned method embodiments are described as series combinations of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the invention.
Based on the understanding that the technical solution of the present invention per se or parts contributing to the prior art can be embodied in the form of software products stored in storage media (such as ROM/RAM, magnetic disk, optical disk) and including instructions for causing terminal devices (which may be mobile phones, computers, servers, or network devices) to execute the methods according to the embodiments of the present invention.
Example 2
According to the embodiment of the present invention, there are also provided apparatus embodiments for implementing the above method embodiments, and the apparatus provided by the above embodiments of the present application can be run on a computer terminal.
Fig. 6 is a schematic structural diagram of a sorting apparatus applying App sub-applications according to a second embodiment of the present application.
As shown in fig. 6, the ranking device for sub-applications in the App may include an -th acquisition unit 602, a processing unit 604, and a ranking unit 606.
The device comprises an obtaining unit 602, a processing unit 604 and a sorting unit 606, wherein the obtaining unit is used for obtaining user attribute information of a th application App, the user attribute information is used for indicating information of characteristics of a user, the th application App comprises a plurality of th sub-applications, the processing unit 604 is used for matching the user attribute information with an application characteristic library pre-established by each th sub-application, and the sorting unit 606 is used for sorting each th sub-application according to a matching result of the user attribute information and the application characteristic library.
As can be seen from the above, in the scheme provided in the second embodiment of the present application, the th sub-applications are sorted according to the matching result of the user attribute information and the application feature library, so as to achieve the purpose of restoring the essential requirements of the user through the real behavior data of the user, and further recommend an application suitable for the use habit of each user to the user, thereby achieving the technical effect of increasing the adaptability of the application software, and further solving the technical problem that in the process of using the application software in the prior art, the th sub-application that is frequently used or wanted is difficult to find by the user after the version update, which results in poor adaptability of the application software.
It should be noted here that the aforementioned acquiring unit 602, processing unit 604 and sorting unit 606 correspond to steps S202 to S204 in embodiment , and three modules are the same as examples and application scenarios realized by the corresponding steps, but are not limited to what is disclosed in embodiment .
Optionally, the processing unit 604 is configured to perform the step of matching the user attribute information with the application feature library pre-established by each th sub-application by respectively calculating information similarity between the user attribute information and the application feature library pre-established by each th sub-application, where the information similarity is a matching result between the user attribute information and each application feature library.
Optionally, the apparatus further includes a second obtaining unit, configured to obtain operation information of each th sub-application of the preset time period by the user of the th application App, where the operation information includes operation behavior information of the th application App within each th sub-application.
Optionally, the processing unit 604 is configured to perform a step of matching the user attribute information with an application feature library pre-established by each th sub-application, wherein a recommendation score of each th sub-application is obtained through calculation according to the operation behavior information, the weight of the operation behavior information, and the user attribute information.
Optionally, the sorting unit 606 is configured to perform the steps of sorting the th sub-applications according to the matching result of the user attribute information and the application feature library, sorting the th sub-applications according to the recommendation degree score of the th sub-applications;
wherein, as shown in fig. 7, the apparatus further comprises:
the recommending unit 702 is configured to recommend the first N th sub-applications to the th application App, where N is a preset positive integer, or recommend the th sub-applications with the recommendation degree score larger than a preset threshold to the th application App.
Optionally, as shown in fig. 8, the processing unit 604 may include an th calculation module 802, a second calculation module 804, and a third calculation module 806.
The system comprises an calculation module 802 for calculating th scores of the th sub-applications according to the operation behavior information and the weight of the operation behavior information, a second calculation module 804 for matching the user attribute information with a pre-established application feature library and calculating second scores of the th sub-applications, and a third calculation module 806 for summing the th scores of the th sub-applications and the second scores to obtain the scores corresponding to the th sub-applications.
It should be noted here that the aforementioned computing module 802, the second computing module 804 and the third computing module 806 correspond to steps S3022 to S3026 in embodiment , and the three modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure in embodiment .
Optionally, the calculation module 802 is configured to calculate the score of each sub-application according to the operation behavior information and the weight of the operation behavior information, wherein the operation behavior information is classified , and the score is calculated according to a formula
Calculating the score of the respective th sub-application, wherein S1 represents the th score, Y
iIndicating the operation behavior information classified into , n indicating the number of operation behavior information, X
iA weight representing the operational behavior information.
Optionally, the operation behavior information comprises one or more of the following combination of time of last uses, clicks and payments.
Optionally, when the operational behavior information includes the last usesIn the meantime, the th calculation module 802 includes a th sub-obtaining module for obtaining the maximum and minimum values corresponding to the last times of usage time in the pre-collected user behavior sample set, and a th sub-calculation module for calculating the maximum and minimum values according to formula Y1=(R-Rmax)/(Rmax-Rmin) Calculating the last usage times after the classification of , wherein Y1Representing the last times of use after the classification of , R representing the last times of use, RmaxRepresents the maximum value, R, corresponding to said last times of useminRepresents the minimum value corresponding to the last usage times.
Optionally, in a case that the operation behavior information includes the number of clicks, the calculating module 802 includes a second sub-obtaining module configured to obtain a maximum value and a minimum value corresponding to the number of clicks in the pre-collected user behavior sample set, and a second sub-calculating module configured to calculate the maximum value and the minimum value according to a formula Y2=(F-Fmin)/(Fmax-Fmin) Calculating the number of clicks classified into , wherein Y2Represents the number of clicks classified into , F represents the number of clicksmaxRepresents the maximum value, F, corresponding to said number of clicksminRepresenting a minimum value corresponding to the number of clicks;
optionally, in a case that the operation behavior information includes the payment times, the th calculation module 802 includes a third sub-acquisition module configured to acquire a maximum value and a minimum value corresponding to the payment times in the pre-collected user behavior sample set, and a third sub-calculation module configured to calculate the payment times according to a formula Y3=(M-Mmin)/(Mmax-Mmin) Calculating the number of payments classified , wherein Y3Representing the number of payments attributed , F representing the number of payments, MmaxRepresenting a maximum value, M, corresponding to said number of paymentsminRepresenting a minimum value corresponding to said number of payments.
Optionally, as shown in fig. 9, the second calculation module 804 may include a matching sub-module 902, an assignment sub-module 904, and a calculation sub-module 906.
The system comprises a matching submodule 902 used for searching the application matched with the user attribute information in the pre-established application feature library, an assignment submodule 904 used for giving a preset score to the application matched with the user attribute information, and a calculation submodule 906 used for calculating the second score of each th sub-application according to the preset score.
It should be noted here that the matching sub-module 902, the assignment sub-module 904, and the calculation sub-module 906 correspond to steps S20 to S24 in the embodiment , and the modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure of the embodiment .
Optionally, as shown in fig. 10, the apparatus may further include: a determination unit 1002 and an assignment unit 1004.
The device comprises a determining unit 1002, a assigning unit 1004, a sorting unit 606 and a recommending unit, wherein the determining unit is used for determining that the th application App does not generate the operation information in a th preset time period and the th application App generates a second sub-application of the operation information in a second preset time period, the assigning unit is used for giving a preset score to the second sub-application, the sorting unit 606 is used for recommending the th sub-application to the th application according to the recommendation degree scores of the sub-applications, and the th sub-application and the second sub-application are recommended to the th application App according to the sequence of scores from high to low.
It should be noted here that the determining unit 1002 and the assigning unit 1004 correspond to steps S402 to S404 in the embodiment , and the modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of the embodiment .
Optionally, as shown in fig. 11, the apparatus may further include: a third acquisition unit 1102.
The third obtaining unit 1102 is configured to obtain third sub-applications to be arranged before the respective th sub-applications, wherein the recommending unit 606 is configured to perform the following steps of recommending the th sub-applications to the App according to the recommendation degree scores of the respective th sub-applications, sorting the third sub-applications and the respective th sub-applications, deleting applications, which are the same as the third sub-applications, in the respective th sub-applications, and recommending the third sub-applications and the respective th sub-applications to the App, where the respective th sub-applications do not include the same applications as the third sub-applications.
It should be noted that the third obtaining unit 1102 corresponds to step S30 in the embodiment , and the module is the same as the example and application scenario realized by the corresponding step, but is not limited to the disclosure of the embodiment . it should be noted that the module can be operated in the computer terminal 10 provided in the embodiment as part of the apparatus, and can be realized by software or hardware.
Optionally, as shown in fig. 12, the apparatus may further include: a fourth acquisition unit 1202.
The sequencing unit 606 is configured to perform the following steps of recommending the th sub-application to the th application App according to the recommendation degree score of each th sub-application, sequencing the fourth sub-application and each th sub-application, deleting the same application as each th sub-application in the fourth sub-application, and recommending the fourth sub-application and each th sub-application to the th application App, where the fourth sub-application does not include the same application as each th sub-application.
It should be noted that the fourth obtaining unit 1202 corresponds to step S40 in the embodiment , and the module is the same as the example and application scenario realized by the corresponding step, but is not limited to the disclosure of the embodiment . it should be noted that the module can be operated in the computer terminal 10 provided in the embodiment as part of the apparatus, and can be realized by software or hardware.
Optionally, the user attribute information includes or a combination of job, age, gender, consumption type and consumption degree.
Example 3
Optionally, in this embodiment, the storage medium may be configured to store program codes executed by the sorting method of the sub-application in the application App provided in embodiment .
Optionally, in this embodiment, the storage medium may be located in any computer terminals in a computer terminal group in a computer network, or in any mobile terminals in a mobile terminal group.
Optionally, in this embodiment, the storage medium is configured to store program codes for performing the steps of obtaining user attribute information using an -th application App, wherein the user attribute information is used for indicating information of a feature of a user, the -th application App includes a plurality of -th sub-applications, matching the user attribute information with an application feature library pre-established for each -th sub-application, and sorting the -th sub-applications according to a matching result of the user attribute information and the application feature library.
Optionally, the storage medium is further configured to store program code for performing the step of calculating information similarity of the user attribute information and an application feature library pre-established by each th sub-application, respectively, the information similarity being a matching result of the user attribute information and each application feature library.
Optionally, the storage medium is further configured to store program codes for obtaining operation information of each th sub-application of the preset time period of the user of the th application App, wherein the operation information includes operation behavior information of the th application App within each th sub-application.
Optionally, the storage medium is further configured to store program code for performing the step of calculating recommendation degree scores of the th sub-applications respectively according to the operation behavior information, the weight of the operation behavior information, and the user attribute information.
Optionally, the storage medium is further configured to store program code for sorting the th sub-applications according to the recommendation score of the th sub-applications, recommending the first N th sub-applications to the th application App after sorting the th sub-applications according to the recommendation score of the th sub-applications, wherein N is a preset positive integer, or recommending the th sub-applications with the recommendation score larger than a preset threshold to the th application App.
Optionally, the storage medium is further configured to store program code for calculating scores of the th sub-applications according to the operation behavior information and the weight of the operation behavior information, matching the user attribute information with a pre-established application feature library, calculating second scores of the th sub-applications, and summing the scores of the th sub-applications and the second scores to obtain the score of the recommendation score corresponding to the th sub-application.
Optionally, the storage medium is further configured to store program code for performing the steps of grouping the operational behavior information, formulating
Calculating the score of the respective th sub-application, wherein S1 represents the th score, Y
iRepresenting the operation behavior information after being classified into , n representsThe number of the operation behavior information, X
iA weight representing the operational behavior information.
Optionally, the storage medium is further configured to store program code for performing the step of, in the event that the operational behavior information includes the last times usage time, performing the process of classifying the operational behavior information, including obtaining a maximum value and a minimum value corresponding to the last times usage time in a pre-collected set of user behavior samples, and performing the step of classifying the operational behavior information by using a formula Y1=(R-Rmax)/(Rmax-Rmin) Calculating the last usage times after the classification of , wherein Y1Representing the last times of use after the classification of , R representing the last times of use, RmaxRepresents the maximum value, R, corresponding to said last times of useminRepresenting the minimum value corresponding to the last times of use time, and under the condition that the operation behavior information comprises the click times, performing processing on the operation behavior information, wherein the processing comprises acquiring the maximum value and the minimum value corresponding to the click times in the pre-collected user behavior sample set, and obtaining the maximum value and the minimum value through a formula Y2=(F-Fmin)/(Fmax-Fmin) Calculating the number of clicks classified into , wherein Y2Represents the number of clicks classified into , F represents the number of clicksmaxRepresents the maximum value, F, corresponding to said number of clicksminRepresenting the minimum value corresponding to the click times, performing the normalization processing on the operation behavior information under the condition that the operation behavior information comprises the payment times, including the steps of obtaining the maximum value and the minimum value corresponding to the payment times in the pre-collected user behavior sample set, and obtaining the maximum value and the minimum value through a formula Y3=(M-Mmin)/(Mmax-Mmin) Calculating the number of payments classified , wherein Y3Representing the number of payments attributed , F representing the number of payments, MmaxRepresenting a maximum value, M, corresponding to said number of paymentsminRepresenting a minimum value corresponding to said number of payments.
Optionally, the storage medium is further configured to store program code for searching for an application matching the user attribute information in the pre-established application feature library, assigning a preset score to the application matching the user attribute information, and calculating the second score of each th sub-application according to the preset score.
Optionally, the storage medium is further configured to store program code for determining that the th application App does not generate the operation information within a th preset time period and a th application App generates a second sub-application of the operation information within a second preset time period, and assigning a preset score to the second sub-application, wherein the recommending the th sub-application to the th application App according to the recommendation degree scores of the th sub-applications comprises recommending the th sub-application and the second sub-application to the application apps in an order of scores from large to small.
Optionally, the storage medium is further configured to store program code for obtaining a third sub-application to be arranged before each th sub-application, wherein the recommending the th sub-application to the th application App according to the recommendation degree score of each th sub-application includes sorting the third sub-application and each th sub-application and deleting an application, which is the same as the third sub-application, in each th sub-application, and recommending the third sub-application and each th sub-application to the App, wherein each th sub-application does not include the application which is the same as the third sub-application.
Optionally, the storage medium is further configured to store program code for obtaining a fourth sub-application to be arranged after each th sub-application, wherein recommending the th sub-application to the th application according to the recommendation degree score of each th sub-application includes sorting the fourth sub-application and each th sub-application and deleting an application in the fourth sub-application that is the same as each th sub-application, and recommending the fourth sub-application and each th sub-application to the App, wherein the fourth sub-application does not include an application that is the same as each th sub-application.
Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Optionally, the specific example in this embodiment may refer to the example described in embodiment 1 above, and this embodiment is not described again here.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in this application, it should be understood that the disclosed technology can be implemented in other ways, such as the above-described device embodiments are only illustrative, for example, the division of the units is only logical function divisions, and in actual implementation, there may be other division ways, for example, multiple units or components may be combined or integrated with another systems, or features may be omitted, or not executed.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in places, or may also be distributed on multiple network units.
In addition, the functional units in the embodiments of the present invention may be integrated into processing units, or each unit may exist alone physically, or two or more units are integrated into units.
Based on the understanding, the technical solution of the present invention, which is essentially or partially contributed to by the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in storage media, which includes several instructions for making computer devices (which may be personal computers, servers, or network devices) execute all or part of the steps of the methods described in the embodiments of the present invention.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.