CN115062086A - Application program function pushing method and device, computer equipment and storage medium - Google Patents

Application program function pushing method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN115062086A
CN115062086A CN202210756522.9A CN202210756522A CN115062086A CN 115062086 A CN115062086 A CN 115062086A CN 202210756522 A CN202210756522 A CN 202210756522A CN 115062086 A CN115062086 A CN 115062086A
Authority
CN
China
Prior art keywords
data
user behavior
function
target function
application program
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210756522.9A
Other languages
Chinese (zh)
Inventor
李志韬
林洁
梁敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industrial and Commercial Bank of China Ltd ICBC
Original Assignee
Industrial and Commercial Bank of China Ltd ICBC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Industrial and Commercial Bank of China Ltd ICBC filed Critical Industrial and Commercial Bank of China Ltd ICBC
Priority to CN202210756522.9A priority Critical patent/CN115062086A/en
Publication of CN115062086A publication Critical patent/CN115062086A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/26—Visual data mining; Browsing structured data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/28—Databases characterised by their database models, e.g. relational or object models
    • G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The application relates to an application program function pushing method, an application program function pushing device, computer equipment and a storage medium. The method comprises the following steps: acquiring user behavior data uploaded by an application program; preprocessing the user behavior data to obtain a user behavior sequence; performing data mining on the user behavior sequence to obtain a data mining result; screening a target function data set from the data mining result; and pushing the application program function corresponding to the target function data set to an application program. By adopting the method, the function pushing efficiency of the application program can be improved.

Description

Application program function pushing method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of big data technologies, and in particular, to a method and an apparatus for pushing application program functions, a computer device, a storage medium, and a computer program product.
Background
With the rapid development of mobile internet technology and big data technology, more and more scenes and functions are migrated to terminal applications, and many terminal application programs with various subdivision functions appear. In order to facilitate the use of the user, a method for pushing the function is needed. In the traditional mode, an operator configures functions to be pushed to a terminal in a background configuration mode to show the functions to a user.
However, when the differentiated processing needs to be performed for different guest groups, the conventional method needs a lot of manual configuration work, which results in low efficiency of pushing the application program functions.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an application function pushing method, an application function pushing apparatus, a computer device, a computer readable storage medium, and a computer program product, which can improve the pushing efficiency of application functions.
In a first aspect, the present application provides an application function pushing method. The method comprises the following steps:
acquiring user behavior data uploaded by an application program;
preprocessing user behavior data to obtain a user behavior sequence;
data mining is carried out on the user behavior sequence to obtain a data mining result;
screening a target function data set from the data mining result;
and pushing the application program function corresponding to the target function data set to the application program.
In one embodiment, the data mining of the user behavior sequence, and the obtaining of the data mining result includes:
mining a frequent sequence mode of the user behavior sequence to obtain a frequent behavior sequence which is greater than a first preset support threshold;
and obtaining a data mining result according to the frequent behavior sequence.
In one embodiment, the preprocessing the user behavior data to obtain the user behavior sequence includes:
cleaning the user behavior data to obtain cleaned user behavior data;
and grouping the cleaned user behavior data to obtain a user behavior sequence.
In one embodiment, the grouping processing of the cleaned user behavior data to obtain the user behavior sequence includes:
grouping the cleaned user behavior data to obtain a plurality of grouped data;
and (4) all the grouped data are connected in series to obtain a user behavior sequence.
In one embodiment, the screening the target functional data set in the data mining result comprises:
determining a data mining result which is greater than a second preset support degree threshold value in the data mining results;
arranging the determined data mining results according to a preset sequence;
and selecting a preset number of data mining results from the arranged data mining results, and determining the data mining results as a target function data set.
In one embodiment, pushing the application function corresponding to the target function data set to the application program includes:
sending the target function data set to an operation platform; the target function data set comprises a target function identification; a functional entry material table is prestored in the operation platform; the operation platform is used for associating the target function data set with the function entry material table through the target function identifier;
acquiring picture materials corresponding to the target function data set in a function entry material table according to the target function identifier;
and pushing the target function identification and the obtained picture material to an application program.
In a second aspect, the application also provides an application function pushing device. The device comprises:
the data acquisition module is used for acquiring user behavior data uploaded by the application program;
the preprocessing module is used for preprocessing the user behavior data to obtain a user behavior sequence;
the data mining module is used for carrying out data mining on the user behavior sequence to obtain a data mining result;
the function screening module is used for screening a target function data set from the data mining result;
and the function pushing module is used for pushing the application program function corresponding to the target function data set to the application program.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
acquiring user behavior data uploaded by an application program;
preprocessing user behavior data to obtain a user behavior sequence;
data mining is carried out on the user behavior sequence to obtain a data mining result;
screening a target function data set from the data mining result;
and pushing the application program function corresponding to the target function data set to the application program.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring user behavior data uploaded by an application program;
preprocessing the user behavior data to obtain a user behavior sequence;
performing data mining on the user behavior sequence to obtain a data mining result;
screening a target function data set from the data mining result;
and pushing the application program function corresponding to the target function data set to an application program.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
acquiring user behavior data uploaded by an application program;
preprocessing user behavior data to obtain a user behavior sequence;
data mining is carried out on the user behavior sequence to obtain a data mining result;
screening a target function data set from the data mining result;
and pushing the application program function corresponding to the target function data set to the application program.
According to the application program function pushing method, the application program function pushing device, the computer equipment, the storage medium and the computer program product, after the user behavior data uploaded by the application program are obtained, the user behavior data are automatically preprocessed to obtain the user behavior sequence, so that the user behavior sequence is subjected to data mining to obtain a data mining result, a target function data set is screened from the data mining result, and the application program function corresponding to the target function data set is pushed to the application program. The data mining and pushing of the application program functions can be automatically carried out, full-process automatic processing is realized by using a matched big data processing flow, the workload of manpower configuration is greatly reduced, the pushing efficiency of the application program functions is improved, and the labor cost is reduced.
Drawings
FIG. 1 is a diagram of an application environment in which a method for pushing application functionality is implemented, according to an embodiment;
FIG. 2 is a flowchart illustrating a method for pushing application functionality according to an embodiment;
FIG. 3 is a diagram illustrating an application page after feature push in one embodiment;
FIG. 4 is a flowchart illustrating the steps of performing data mining on a user behavior sequence to obtain data mining results according to an embodiment;
FIG. 5 is a flowchart illustrating a method for pushing application program functions in another embodiment;
FIG. 6 is a block diagram of an application push device in one embodiment;
FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The application function refers to different function service modules in a single application, and is used for embodying the function of a certain module in the application, for example, the application function in the a-bank application may include: the financial services comprise 'electronic payroll', 'pension', 'no-card cash-out' and the like under the financial service classification; the investment financing classification comprises 'financing', 'fund', 'insurance' and the like. The application program function pushing provides functions which show that a user has a higher possibility to use in the near future for the user using the terminal application program, and the functions comprise message pushing, recommendation for you, guess you like and the like. In the traditional mode, an operator configures functions needing to be pushed to a terminal in a background configuration mode to show the functions to a user. However, when the differentiated processing needs to be performed for different customer groups, the conventional method needs a lot of manual configuration work, which results in low efficiency of recommending the application function.
In order to solve the problem of low recommendation efficiency of the application program function, an application program function pushing method is provided.
The application program function pushing method provided by the embodiment of the application program can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. An application program runs in the terminal 102, the application program uploads behavior data of a user to the server 104, and the server 104 preprocesses the behavior data of the user after acquiring the behavior data of the user to obtain a behavior sequence of the user. And then data mining is carried out on the user behavior sequence to obtain a data mining result. And further screening a target function data set from the data mining result, and pushing the application program function corresponding to the target function data set to the application program. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, an application function pushing method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
step 202, obtaining user behavior data uploaded by the application program.
The Application refers to an Application (APP) running on the terminal. The user behavior data refers to behavior data of the user in the application program and is the embodiment of the life habits of the user. The user behavior data may be historical behavior data of one user or historical behavior data of a group of users.
The server acquires user behavior data uploaded by an application program running in the terminal. Specifically, the user behavior data may be click behavior data of the user on an application program interface, which is acquired in an SDK (Software Development Kit) manner, or may be statistical codes implanted in the application program in a manner of manually embedding points in the application program, and when the user uses the application program, the statistical codes of the application program may record each behavior of the user when the user uses the application program, so as to realize acquisition of the user behavior data. Other existing user behavior data acquisition modes can also be adopted, and the embodiment is not limited.
The server is integrated with a data acquisition system, and is used for storing the user behavior data reported by the application program and synchronizing the user behavior data to a data warehouse in a batch mode every day. For example, the data warehouse may be Hive. And further, data mining processing can be performed on the user behavior data in the data warehouse through the big data platform. For example, data mining processing may be performed on user behavior data in a data warehouse through a big data platform using a PySpark framework. The data mining process may include the steps of preprocessing, data mining, targeted functional data set screening, and the like.
Optionally, the server may build a data processing script through the data science platform, and set the running frequency of the data processing script. For example, the operating frequency may be daily. And executing the data processing script according to the running frequency, and performing data mining processing on the user behavior data in the data warehouse according to the data processing script.
And step 204, preprocessing the user behavior data to obtain a user behavior sequence.
The user behavior sequence refers to detail data of the user behavior sequence. The user behavior sequence comprises a plurality of subsequences, and specifically can comprise a function use sequence of the user.
The server preprocesses the user behavior data, wherein the preprocessing refers to performing ETL (Extract-Transform-Load) processing and format conversion on the user behavior data. The ETL processing refers to a process of carrying out data cleaning on user behavior data, and aims to integrate scattered, disordered and standard non-uniform data together and provide a basis for subsequent data mining. The format conversion means that the cleaned user behavior data is converted into a specified format required by data mining so as to carry out data mining subsequently.
And step 206, performing data mining on the user behavior sequence to obtain a data mining result.
The server carries out frequent sequence pattern mining on the user behavior data, a frequent behavior sequence (consequent) is mined, and meanwhile, the support degree (support), the confidence degree (confidence) and the lift degree (lift) corresponding to the frequent behavior sequence can be obtained. Wherein, the frequent behavior sequence refers to a subsequence with a support degree not lower than a minimum support degree threshold in the sequence set. The support degree refers to the frequency of occurrence of a certain subsequence in a sequence set. The preset support threshold may be a user-specified minimum support threshold. The confidence coefficient refers to the probability of the occurrence of a frequent behavior sequence after a certain subsequence in the user behavior sequence occurs. The promotion degree is the ratio of the probability of the occurrence of the frequent behavior sequence after a certain subsequence in the user behavior sequence occurs to the probability of the occurrence of the frequent behavior sequence when the subsequence does not occur. The boost degree can also represent the correlation between a certain subsequence in the user behavior sequence and the frequent behavior subsequence. And determining the frequent behavior sequence and the support degree, the confidence degree and the promotion degree corresponding to the frequent behavior sequence as data mining results. For example, the data mining results may be as shown in table 1 below:
TABLE 1 data mining results
Figure BDA0003722705690000061
Figure BDA0003722705690000071
And step 208, screening a target function data set from the data mining results.
The target function data set refers to a function combination to be pushed, and comprises a target function identifier. Functionality refers to the role an application plays for a service or application provided by a user.
And after data mining is carried out on the data, the server obtains a data mining result, and then screening is carried out on the data mining result to obtain a target function data set. Specifically, the server screens a target function data set meeting preset screening conditions in the data mining results. The preset screening condition may be greater than a screening threshold, and the screening threshold may be a preset support threshold, which is not a minimum support threshold, for example, the screening threshold may be 2.00%.
Step 210, pushing the application program function corresponding to the target function data set to the application program.
A function entry material table is stored in the server in advance, and the function entry material table comprises a plurality of function identifiers in the application program and picture materials corresponding to the function identifiers. After the target function data set is obtained, the target function data set and the function entry material table can be associated through the function identifier. Therefore, when the server pushes the application program function, the function identifier and the picture material of the application program function corresponding to the target function data set are obtained in the function entrance material table according to the incidence relation between the target function data set and the function entrance material table, the function identifier and the picture material of the application program function corresponding to the target function data set are pushed to the application program, and the application program displays the application program page after receiving the pushed function identifier and the corresponding picture material. And realizing personalized application program function pushing for the user. The application page with the pushed functions may be as shown in fig. 3, where four display boxes below recommended for you are the pushed application functions.
According to the application program function pushing method, after user behavior data uploaded by an application program are obtained, the user behavior data are automatically preprocessed to obtain a user behavior sequence, so that data mining is carried out on the user behavior sequence to obtain a data mining result, a target function data set is screened from the data mining result, and the application program function corresponding to the target function data set is pushed to the application program. The data mining and application program function pushing can be automatically carried out, full-process automatic processing is realized by using a matched big data processing flow, the workload of configuration manpower is greatly reduced, the application program function pushing efficiency is improved, and meanwhile, the labor cost is reduced.
In one embodiment, as shown in fig. 4, performing data mining on the user behavior sequence, and obtaining a data mining result includes:
and step 402, performing frequent sequence pattern mining on the user behavior sequence to obtain a frequent behavior sequence which is greater than a first preset support threshold.
And step 404, obtaining a data mining result according to the frequent behavior sequence.
Where a sequence pattern is given a set of different subsequences. Wherein each subsequence is ordered by different elements in sequence, each element is composed of different items, and a support threshold is given. Sequence pattern mining is to find all frequent subsequences. The first preset support threshold refers to a minimum support threshold.
Specifically, the server may perform frequent sequence pattern mining on the user behavior sequence by using a sequence pattern data mining algorithm PrefixSpan to obtain a frequent behavior sequence satisfying a preset support degree threshold, and calculate the support degree of the frequent behavior sequence. Confidence and promotion, thereby generating a data mining result.
Further, the process of performing frequent sequence pattern mining on the user behavior sequence by using the sequence pattern data mining algorithm PrefixSpan includes: and taking the user behavior sequence S and the first preset support threshold alpha as the input of a sequence mode data mining algorithm Prefix span, and outputting all frequent behavior sequences larger than the first preset support threshold.
Specifically, 1) scanning each subsequence in the user behavior sequence S by using a prefix span algorithm, and finding out all subsequence prefixes with the length of 1 and corresponding projection subsequence sets.
2) Calculating the support degree of the subsequence prefix with the length of 1, deleting the subsequences with the support degree lower than a first preset support degree threshold value alpha from the user behavior sequence S, and simultaneously obtaining all frequent behavior sequences.
3) Performing recursive mining operation on each subsequence prefix with the length of i and larger than a first preset support degree threshold value:
a. and finding out a corresponding projection database. If the projection database is empty, the recursive operation is ended and 0 is returned, otherwise 0 is returned directly.
b. And calculating the support degree of each subsequence in the corresponding projection database. If the support of all the subsequences is lower than the first preset support threshold alpha, the recursive operation is ended and 0 is returned, otherwise, 0 is directly returned.
c. And combining the current prefix with each subsequence larger than the first preset support threshold to obtain a plurality of new prefixes.
d. And i is equal to i +1, the prefixes are the prefixes obtained by combining the subsequences larger than the first preset support threshold, and 3) is performed in a recursive manner.
After the above PrefixSpan algorithm is executed, all the frequent behavior sequences can be mined from the user behavior sequence.
Alternatively, the length of the frequent behavior sequence may be determined by setting the length of the preset sequence to support different numbers of function pushing scenarios, for example, the length of the preset sequence may be 10. When the length of the preset sequence is 10, each frequent behavior sequence may include 10 application functions.
In this embodiment, frequent sequence pattern mining is performed on the user behavior sequence through the Prefix span algorithm, and since a candidate sequence does not need to be generated and the projection database is reduced quickly, memory consumption is relatively stable, and efficiency is higher during frequent sequence pattern mining.
In one embodiment, the preprocessing the user behavior data to obtain the user behavior sequence includes: cleaning the user behavior data to obtain cleaned user behavior data; and grouping the cleaned user behavior data to obtain a user behavior sequence.
The server cleans the user behavior data, and the specific process of data cleaning can include screening data in a preset time period, removing user behavior data which are not used functionally, removing abnormal data and the like. For example, the data within the preset time period may be data of approximately 14 days. The user behavior data for non-functional use may include behavior data for login, payment, message push. The exception data may include that the buried point event ID (identification number) is empty, the function usage time is too short, the number of applications used per start exceeds 30, and the like. And after the data cleaning is finished, generating an intermediate table for the next step according to the cleaned user behavior data. Therefore, the cleaned user behavior data are subjected to grouping processing based on the intermediate table, behavior data generated by multiple starting of the same user are divided into a group, and a user behavior sequence is obtained.
In the embodiment, the user behavior data is cleaned, redundant data in the user behavior data is removed, the accuracy of a user behavior sequence is improved, and meanwhile, the interference of abnormal data is avoided. And grouping the cleaned user behavior data to obtain a user behavior sequence. The data format meeting the data mining requirement can be obtained, and the data mining efficiency is improved.
In an optional manner of this embodiment, the grouping the cleaned user behavior data to obtain the user behavior sequence includes: grouping the cleaned user behavior data to obtain a plurality of grouped data; and (4) all the grouped data are connected in series to obtain a user behavior sequence.
Because the behavior data generated by a single start of the same user has the same SessionID (session identifier), and the behavior data generated by multiple starts of the same user has the same SID (Security Identifiers, user serial numbers), which is a unique number for identifying the user, the group and the computer account. The server can group the user behavior data according to the SID, and divide the behavior data belonging to the same user into one group to obtain a plurality of grouped data. Therefore, each group of data is connected in series according to the starting sequence, the function use sequence generated in the same starting is surrounded by small brackets, and the group data after being connected in series is surrounded by middle brackets, so that the user behavior sequence is obtained. User behavior sequences may be represented in sequences. For example, the user behavior sequence may be as shown in table 2 below:
TABLE 2 user behavior sequences
User serial number User behavior sequence
10 <a(abc)(ac)d(cf)>
20 <(ad)c(bc)(ae)>
30 <(ef)(ab)(df)cb>
40 <eg(af)cbc>
Each row represents a function use sequence generated by the same user in the batch period, and the sequence on the right side is a behavior sequence generated by the user and is surrounded by middle brackets for algorithm identification. The data in the parenthesis indicates the sequence of function usage that occurred during the same boot. The user behavior sequence detail data is the detail data of the user behavior sequence and is stored as an intermediate table for the sequence mode data mining algorithm Prefix span to use.
In this embodiment, the cleaned user behavior data are grouped, so that the grouped data are concatenated to obtain a user behavior sequence. The data format meeting the data mining requirement can be obtained, and the efficiency and the accuracy of data mining are greatly improved.
In one embodiment, screening the target functional data set in the data mining results comprises: determining a data mining result which is greater than a second preset support degree threshold value in the data mining results; arranging the determined data mining results according to a preset sequence; and selecting a preset number of data mining results from the arranged data mining results, and determining the data mining results as a target function data set.
The second preset support threshold is a corresponding support threshold when the target function data set is screened.
The data mining result comprises a frequent behavior sequence which is larger than a first preset threshold value and a support degree, a confidence degree and a promotion degree which correspond to the frequent behavior sequence. The server may determine, in the data mining results, data mining results larger than a second preset support threshold, for example, the second preset support threshold may be 2.00%, so as to arrange the determined data mining results according to a preset order, for example, the preset order may be an order from high to low according to the confidence and the promotion. And then selecting a preset number of data mining results from the arranged data mining results, and determining the selected data mining results as a target function data set. For example, the preset number may be the top 1000 items. The target function data set thus obtained includes 1000 target function combinations.
In this embodiment, by determining the data mining results greater than the second preset support threshold, a preset number of data mining results are selected from the arranged data mining results, and a target function data set with higher pushing accuracy can be selected from a large number of data mining results, so as to improve the pushing accuracy of the application program function.
In one embodiment, pushing the application function corresponding to the target function data set to the application program comprises: sending the target function data set to an operation platform; the target function data set comprises a target function identification; a functional entry material table is prestored in the operation platform; the operation platform is used for associating the target function data set with the function entrance material table through the target function identifier; acquiring picture materials corresponding to the target function data set in a function entry material table according to the target function identifier; and pushing the target function identification and the obtained picture material to an application program.
And after screening the target function data set in the data mining result, the server stores the target function data set so as to unify the data service interface, and sends the target function data set to the operation platform by calling the data service interface. The operation platform is pre-stored with a function entrance material table.
The operation platform is used for connecting the target function data set with a pre-stored function entrance material table in an internal mode by taking the target function identification as a main key, and association is achieved. The target function identifier refers to a unique identifier for distinguishing different functions, and for example, the target function identifier may be a target function ID. Therefore, the server can acquire the picture material corresponding to the target function data set in the function entry material table according to the target function identifier, further push the target function identifier and the acquired picture material to the application program, and display the picture material through the application program interface.
Optionally, the target function data set and a pre-stored function entry material table may be internally connected by using the target function identifier as a main key through the operation platform, so as to generate a push result table for real-time calling, and the push result table is cached in a redis database of the operation platform. When the server obtains a function pushing request sent by the application program, the function pushing request is analyzed, and an application program identifier is obtained. And calling a preset interface according to the function pushing request, acquiring a target function identifier and picture materials corresponding to the target function data set from a pushing result table of the redis database, and pushing the target function identifier and the picture materials to an application program corresponding to the application program identifier.
In this embodiment, the target function data set and the pre-stored function entry material table are associated through the target function identifier by the operation platform, so that the picture material corresponding to the target function data set is obtained in the function entry material table according to the association relationship, and then the target function identifier and the obtained picture material are pushed to the application program, so that the picture material corresponding to the target function data set can be quickly obtained, and the function pushing efficiency of the application program is improved.
In another embodiment, as shown in fig. 5, there is provided an application function pushing method, including the steps of:
step 502, obtaining user behavior data uploaded by an application program.
And step 504, cleaning the user behavior data to obtain the cleaned user behavior data.
And step 506, grouping the cleaned user behavior data to obtain a plurality of grouped data.
And step 508, the grouped data are connected in series to obtain a user behavior sequence.
And 510, performing frequent sequence pattern mining on the user behavior sequence to obtain a frequent behavior sequence meeting a preset support threshold.
And step 512, obtaining a data mining result according to the frequent behavior sequence.
And 514, screening a target function data set from the data mining result.
Step 516, sending the target function data set to an operation platform; the target function data set comprises a target function identification; a functional entry material table is prestored in the operation platform; and the operation platform is used for associating the target function data set with the function entrance material table through the target function identifier.
And step 518, acquiring the picture material corresponding to the target function data set in the function entry material table according to the target function identifier.
And step 520, pushing the target function identifier and the acquired picture material to an application program.
In the embodiment, the user behavior data are cleaned, redundant data in the user behavior data are removed, the accuracy of a user behavior sequence is improved, and meanwhile, the interference of abnormal data is avoided. And grouping the cleaned user behavior data to obtain a user behavior sequence. The data format meeting the data mining requirement can be obtained, and the data mining efficiency is improved. Frequent sequence pattern mining is carried out on the user behavior sequence through the Prefix span algorithm, and due to the fact that candidate sequences do not need to be generated, the projection database is reduced quickly, memory consumption is stable, and efficiency is high when the frequent sequence pattern mining is carried out. By associating the target function data set with the pre-stored function entry material table through the target function identifier, the picture material corresponding to the target function data set can be quickly acquired, and therefore the function pushing efficiency of the application program is improved. According to the embodiment, the full-process automatic processing is realized by using the matched big data processing flow, the workload of configuration manpower is greatly reduced, the application program function pushing efficiency is improved, and the labor cost is reduced.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides an application function pushing device for implementing the application function pushing method mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the application function pushing device provided below may refer to the limitations in the above application function pushing method, and details are not described herein again.
In one embodiment, as shown in fig. 6, there is provided an application function pushing apparatus, including: the system comprises a data acquisition module 602, a preprocessing module 604, a data mining module 606, a function screening module 608 and a function pushing module 610, wherein:
a data obtaining module 602, configured to obtain user behavior data uploaded by an application.
The preprocessing module 604 is configured to preprocess the user behavior data to obtain a user behavior sequence.
And the data mining module 606 is used for performing data mining on the user behavior sequence to obtain a data mining result.
And the function screening module 608 is configured to screen a target function data set from the data mining result.
The function pushing module 610 is configured to push an application function corresponding to the target function data set to an application.
In one embodiment, the data mining module 606 is further configured to perform frequent sequence pattern mining on the user behavior sequence to obtain a frequent behavior sequence greater than a first preset support degree threshold; and obtaining a data mining result according to the frequent behavior sequence.
In one embodiment, the preprocessing module 604 is further configured to clean the user behavior data to obtain cleaned user behavior data; and grouping the cleaned user behavior data to obtain a user behavior sequence.
In one embodiment, the preprocessing module 604 is further configured to group the cleaned user behavior data to obtain a plurality of grouped data; and (4) all the grouped data are connected in series to obtain a user behavior sequence.
In one embodiment, the functional screening module 608 is further configured to determine, in the data mining results, data mining results that are greater than a second preset support threshold; arranging the determined data mining results according to a preset sequence; and selecting a preset number of data mining results from the arranged data mining results, and determining the data mining results as a target function data set.
In one embodiment, the function pushing module 610 is further configured to send the target function data set to the operation platform; the target function data set comprises a target function identification; a functional entry material table is prestored in the operation platform; the operation platform is used for associating the target function data set with the function entry material table through the target function identifier; acquiring picture materials corresponding to the target function data set in a function entry material table according to the target function identifier; and pushing the target function identification and the obtained picture material to an application program.
All or part of the modules in the application function pushing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O for short), and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing user behavior data, target function data sets and other data. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement an application function pushing method.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above-described method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant country and region.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (10)

1. An application function pushing method, the method comprising:
acquiring user behavior data uploaded by an application program;
preprocessing the user behavior data to obtain a user behavior sequence;
performing data mining on the user behavior sequence to obtain a data mining result;
screening a target function data set from the data mining result;
and pushing the application program function corresponding to the target function data set to the application program.
2. The method of claim 1, wherein the data mining the sequence of user behaviors to obtain a data mining result comprises:
mining the frequent sequence mode of the user behavior sequence to obtain a frequent behavior sequence which is larger than a first preset support threshold;
and obtaining a data mining result according to the frequent behavior sequence.
3. The method of claim 1, wherein the preprocessing the user behavior data to obtain a user behavior sequence comprises:
cleaning the user behavior data to obtain cleaned user behavior data;
and grouping the cleaned user behavior data to obtain a user behavior sequence.
4. The method according to claim 3, wherein the grouping the cleaned user behavior data to obtain a user behavior sequence comprises:
grouping the cleaned user behavior data to obtain a plurality of grouped data;
and (4) connecting the grouped data in series to obtain a user behavior sequence.
5. The method of claim 1, wherein the screening target functional data sets in the data mining results comprises:
determining a data mining result which is greater than a second preset support degree threshold value in the data mining results;
arranging the determined data mining results according to a preset sequence;
and selecting a preset number of data mining results from the arranged data mining results, and determining the data mining results as a target function data set.
6. The method according to any one of claims 1 to 5, wherein the pushing the application function corresponding to the target function data set to the application program comprises:
sending the target function data set to an operation platform; the target function data set comprises a target function identification; a functional entry material table is prestored in the operation platform; the operation platform is used for associating the target function data set with the function entry material table through the target function identifier;
acquiring picture materials corresponding to the target function data set in the function entrance material table according to the target function identification;
and pushing the target function identification and the acquired picture material to the application program.
7. An application function pushing apparatus, the apparatus comprising:
the data acquisition module is used for acquiring user behavior data uploaded by the application program;
the preprocessing module is used for preprocessing the user behavior data to obtain a user behavior sequence;
the data mining module is used for carrying out data mining on the user behavior sequence to obtain a data mining result;
the function screening module is used for screening a target function data set from the data mining result;
and the function pushing module is used for pushing the application program function corresponding to the target function data set to the application program.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
CN202210756522.9A 2022-06-30 2022-06-30 Application program function pushing method and device, computer equipment and storage medium Pending CN115062086A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210756522.9A CN115062086A (en) 2022-06-30 2022-06-30 Application program function pushing method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210756522.9A CN115062086A (en) 2022-06-30 2022-06-30 Application program function pushing method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115062086A true CN115062086A (en) 2022-09-16

Family

ID=83203560

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210756522.9A Pending CN115062086A (en) 2022-06-30 2022-06-30 Application program function pushing method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115062086A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115562967A (en) * 2022-11-10 2023-01-03 荣耀终端有限公司 Application program prediction method, electronic device and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115562967A (en) * 2022-11-10 2023-01-03 荣耀终端有限公司 Application program prediction method, electronic device and storage medium
CN115562967B (en) * 2022-11-10 2023-10-13 荣耀终端有限公司 Application program prediction method, electronic device and storage medium

Similar Documents

Publication Publication Date Title
CA2895893C (en) Searchable data archive
US9256686B2 (en) Using a bloom filter in a web analytics application
CN111222922B (en) Advertisement putting method and device, advertisement putting server and storage medium
CN115062086A (en) Application program function pushing method and device, computer equipment and storage medium
CN108874876B (en) Message pushing method, computer readable storage medium and terminal equipment
CN112307297B (en) User identification unification method and system based on priority rule
CN112016027A (en) Method and device for monitoring access data operation platform
WO2020253067A1 (en) Project scheme management method based on data analysis, related device and storage medium
US20140089525A1 (en) Compressed analytics data for multiple recurring time periods
CN111553749A (en) Activity push strategy configuration method and device
CN111666298A (en) Method and device for detecting user service class based on flink, and computer equipment
CN111753203A (en) Card number recommendation method, device, equipment and medium
CN115408396B (en) Method, device, computer equipment and storage medium for storing business data
CN114662007B (en) Data recommendation method and device, computer equipment and storage medium
CN109919470B (en) Method and device for distributing customer information
CN116541454B (en) Event configuration method, device, computer equipment and storage medium
EP2767911A1 (en) Data storage and retrieval
CN117033591A (en) Problem solving method, device, computer equipment and storage medium
CN110019352B (en) Method and apparatus for storing data
CN115641017A (en) Service data processing method and device, computer equipment and storage medium
CN115329034A (en) User information identification method and device, computer equipment and storage medium
CN116595054A (en) Interaction state determining method and device and computer equipment
CN115865857A (en) Response data pushing method and device, computer equipment and storage medium
CN117194768A (en) Method, device, computer equipment and storage medium for determining activity label
CN116561456A (en) Information screening method, device and computer equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination