CN111522747A

CN111522747A - Application processing method, device, equipment and medium

Info

Publication number: CN111522747A
Application number: CN202010336341.1A
Authority: CN
Inventors: 梁华盛
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-04-24
Filing date: 2020-04-24
Publication date: 2020-08-11
Anticipated expiration: 2040-04-24
Also published as: CN111522747B

Abstract

The embodiment of the application discloses a processing method of an application program. The method comprises the following steps: acquiring a sequence set of the target application program, wherein the sequence set comprises N behavior sequences, each behavior sequence is used for describing a primary historical use record of the target application program, N is a positive integer, performing feature extraction processing on the behavior sequences in the sequence set to obtain quality features of the target application program, and fitting the quality features of the target application program to obtain a quality identification result of the target application program. Therefore, the quality characteristics of the target application program are obtained through the sequence set of the target application program, the quality characteristics of the target application program obtained through prediction of the sequence set of the target application program can accurately reflect the overall quality of the target application program, and the accurate quality identification result of the target application program is obtained based on the quality characteristics of the target application program.

Description

Application processing method, device, equipment and medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to the field of application-related technologies, and in particular, to an application processing method, an application processing apparatus, an application processing device, and a computer-readable storage medium.

Background

With the development of computer technology, an installation-free application (i.e., an application that can be used without downloading and installing) is developed rapidly and rapidly with the advantages of convenience and small memory occupation. The application programs have the characteristics of multiple categories, complex functions, various carriers, multiple content, multiple structures and the like, so that the quality of the application programs is difficult to be well identified by using a single technology. At present, two quality identification technologies for the application program are mainly used, one is manual review, and special operation and maintenance personnel review the content, functions and the like of the application program to remove some low-quality application programs; this approach is inefficient, costly and not practical. The other method is to adopt the abnormal matching of the model, specifically to adopt some low-quality data to carry out modeling, match the content, the function and the like related to the application program with the model, and if the matching is successful, the content and the function of the application program are regarded as the low-quality data, so as to identify the quality abnormality of the application program; the method has the problems of low precision, difficulty in integrating complex information such as functions, pages, interaction and the like in the application program, low efficiency and high cost.

Disclosure of Invention

The embodiment of the application discloses a processing method, a processing device, processing equipment and a processing medium of an application program, which can accurately identify the quality of the application program through a simple and efficient quality identification technology.

In one aspect, an embodiment of the present application provides a method for processing an application program, where the method includes:

acquiring a sequence set of a target application program, wherein the sequence set comprises N behavior sequences, each behavior sequence is used for describing a primary historical use record of the target application program, and N is a positive integer;

performing characteristic extraction processing on the behavior sequences in the sequence set to obtain quality characteristics of the target application program;

and fitting the quality characteristics of the target application program to obtain a quality identification result of the target application program.

In one aspect, the present application provides an application processing apparatus, including:

the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a sequence set of a target application program, the sequence set comprises N behavior sequences, each behavior sequence is used for describing one-time historical use record of the target application program, and N is a positive integer;

and the processing unit is used for carrying out feature extraction processing on the behavior sequences in the sequence set to obtain the quality features of the target application program, and fitting the quality features of the target application program to obtain the quality identification result of the target application program.

In one embodiment, the one-time historical usage record includes a plurality of operational steps involved in one-time historical usage of the target application, each operational step including at least one of the following operational features: an operation scene, an operation time and an operation type;

a behavior sequence comprising a plurality of behavior elements, a behavior element for recording an operation step; and arranging each behavior element in the behavior sequence according to the sequence of the operation time.

In an embodiment, the processing unit is further configured to perform feature extraction processing on the behavior sequences in the sequence set to obtain quality features of the target application, and specifically configured to:

and respectively carrying out feature extraction processing on the N behavior sequences in the sequence set by adopting a network model to obtain N quality feature components, and expressing the quality features of the target application program by adopting the N quality feature components.

respectively performing first noise reduction processing on the N behavior sequences according to the incidence relation among the operation steps in each behavior sequence, wherein the first noise reduction processing is used for eliminating noise behavior elements in each behavior sequence and reserving effective behavior elements;

and respectively performing feature extraction processing on the N behavior sequences subjected to the noise reduction processing by adopting a network model to obtain N quality feature components, and expressing the quality features of the target application program by adopting the N quality feature components.

In an embodiment, the processing unit is further configured to, fit the quality characteristics of the target application to obtain a quality identification result of the target application, and specifically configured to:

respectively carrying out regression processing on the N quality characteristic components by adopting a regression model to obtain N quality identification result components of the target application program;

and carrying out average operation processing on the N quality identification result components of the target application program to obtain a quality identification result of the target application program.

according to the incidence relation among all behavior sequences in the sequence set, performing second noise reduction processing on the sequence set, wherein the second noise reduction processing is used for eliminating N-M noise behavior sequences in the sequence set and reserving M key behavior sequences; m is a positive integer and M < N;

respectively performing feature extraction processing on the M key behavior sequences by adopting a network model to obtain M key quality feature components;

performing aggregation processing on the M key quality characteristic components to obtain the quality characteristics of the target application program;

the aggregation processing mode comprises a weighted aggregation mode or a concatenation mode.

respectively performing feature extraction processing on the N behavior sequences by adopting a network model to obtain N quality feature components;

performing third noise reduction processing on the N quality characteristic components according to the incidence relation among the behavior sequences in the sequence set, wherein the third noise reduction processing is used for eliminating N-M noise quality characteristic components in the N quality characteristic components and reserving M key quality characteristic components; m is a positive integer and M < N;

and performing regression processing on the quality characteristics of the target application program by adopting a regression model to obtain a quality identification result of the target application program.

In one embodiment, the target application is an install-free application, which refers to any sub-application hosted within the client.

In one embodiment, the processing unit is further configured to:

displaying a search page of a client, wherein the client comprises a target application program, and the target application program refers to any sub-application program parasitized in the client;

if the quality identification result of the target application program meets the recommendation condition, acquiring the information of the target application program;

and displaying the information of the target application program in a search page of the client.

In one embodiment, the quality identification result includes a quality score; the quality identification result of the target application program meeting the recommendation condition means that the quality score of the application program is greater than a quality threshold; the information of the target application includes at least one of: identification, subject attributes, categories, function profiles of the target application;

the processing unit is further configured to display information of the target application program in a search page of the client, and specifically configured to:

adding information of a target application program into a recommendation list of a client, wherein the recommendation list comprises a plurality of pieces of information to be recommended, and the information is sorted according to the sequence of the quality scores of the corresponding application programs from high to low;

and displaying the information in the recommendation list of the client in the search page of the client.

In one embodiment, the quality identification result includes a quality score; the quality identification result of the target application program meeting the recommendation condition means that the quality score of the target application program is greater than the quality threshold;

the processing unit is further configured to:

if the quality score of the target application program is smaller than a penalty threshold, performing penalty processing on the target application program, wherein the penalty threshold is smaller than the quality threshold, and the penalty processing comprises at least one of the following steps: and shielding, deleting and sending the correction prompt information to the operator of the target application program.

In one aspect, the present application provides an application processing device, including:

a memory storing computer readable instructions;

a processor coupled to the memory for executing the computer readable instructions to implement the processing method of the application program described above.

In one aspect, the present application provides a computer-readable storage medium storing one or more instructions adapted to be loaded by a processor and to execute the processing method of the application program.

In the embodiment of the application, a sequence set of a target application is obtained, where the sequence set is a sequence package formed by packaging N behavior sequences, each behavior sequence is used to describe a one-time history usage record of the target application, and the one-time history usage record represents one usage example of the target application, so that the sequence set reflects multiple usage examples of the target application; and finally, obtaining a quality identification result of the target application program by fitting the quality characteristics of the target application program, wherein the quality identification result is used for expressing the quality of the target application program. Because the quality characteristics of the application program are derived from the relatively comprehensive information of the multiple use examples of the application program, and each use example covers the operation scene, the operation step and the operation type of the target application program and the information of the response of the application program to the operation and the like, the multiple use examples can relatively comprehensively reflect the information of the function, the content, the service and the like of the target application program, the quality of the target application program is identified based on the multiple use examples of the target application program, the relatively accurate quality assessment of the target application program can be obtained, and the scheme has the advantages of simple operation, high efficiency, low cost and relatively high practicability.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 illustrates an architecture diagram of a processing system for an application provided by an exemplary embodiment of the present application;

FIG. 2 is a flow chart illustrating a method for processing an application according to an exemplary embodiment of the present application;

FIG. 3 illustrates a sequence diagram of behavior provided by an exemplary embodiment of the present application;

FIG. 4 is a flow chart illustrating a method for processing a further application provided by an exemplary embodiment of the present application;

FIG. 5a is a flow chart of feature extraction for a single sequence using Bi-RNN according to an exemplary embodiment of the present application;

FIG. 5b is a flow chart illustrating a feature extraction for a single sequence using a transform model according to an exemplary embodiment of the present application;

FIG. 5c is a flowchart illustrating a method for processing another application program according to an exemplary embodiment of the present application;

FIG. 5d is a flowchart illustrating a method for processing another application program according to an exemplary embodiment of the present application;

FIG. 5e is a flowchart illustrating a method for processing another application program according to an exemplary embodiment of the present application;

FIG. 5f is a flowchart illustrating a method for processing another application program according to an exemplary embodiment of the present application;

FIG. 6 is a flow chart illustrating a method for processing a further application provided by an exemplary embodiment of the present application;

FIG. 7a illustrates a search page diagram of a client provided by an exemplary embodiment of the present application;

FIG. 7b illustrates a search results page diagram of a client provided by an exemplary embodiment of the present application;

fig. 8 is a schematic structural diagram illustrating a processing apparatus of an application according to an exemplary embodiment of the present application;

fig. 9 is a schematic structural diagram illustrating a processing device of an application according to an exemplary embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

The embodiment of the application relates to Artificial Intelligence (AI), Natural Language Processing (NLP) and Machine Learning (ML), and hidden information with potential value in data can be mined by combining the AI, the NLP and the ML, so that equipment can predict and identify an application more accurately. The AI is a theory, method, technique and application system that simulates, extends and expands human intelligence, senses the environment, acquires knowledge and uses the knowledge to obtain the best results using a digital computer or a machine controlled by a digital computer. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The AI technology is a comprehensive subject, and relates to the field of extensive technology, both hardware level technology and software level technology. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, processing technologies for large applications, operating/interactive systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

NLP is an important direction in the fields of computer science and AI. It studies various theories and methods that enable efficient communication between humans and computers using natural language. NLP is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. NLP techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like.

ML is a multi-field interdisciplinary, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. ML is the core of artificial intelligence, is the fundamental way to make computers intelligent, and its application is spread over various fields of artificial intelligence. ML and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, migratory learning, inductive learning, and formal learning.

The embodiment of the application relates to processing of an application program. An application herein may refer to an installation-free application, i.e., an application that can be used without downloading installation, which is also known as an applet, and is typically hosted in a client as a sub-application. The client (which may also be referred to as an application client, APP client) refers to a program that is downloaded and installed in the terminal and runs in the terminal. Various types of clients may be included in the terminal, including but not limited to: an IM (instant messaging) client (e.g., a wechat client, a QQ client, etc.), an SNS (social networking Services) client (e.g., a microblog client, a map client with social networking functions, etc.), a content service client (e.g., a news client), an image processing client, a search client, etc. Unless otherwise noted, the application programs mentioned in the following embodiments of the present application are all described by taking sub-application programs (i.e., applets) hosted by various clients of the terminal as examples.

Due to the wide variety and quantity of the application programs, the quality of the application programs is also uneven, and the application programs can be generally divided into high-quality application programs and low-quality application programs. Wherein the quality of the application can be evaluated from multiple dimensions of traffic, services, content, etc. From the traffic dimension, a good application may refer to an application whose traffic (e.g., accumulated praise or attention) exceeds a threshold, for example: if the accumulated number of praise of a user to an application exceeds 100 ten thousand, the application can be regarded as a good application. Conversely, a bad application is an application that does not reach a threshold value for flow, or an application that is reported to increase flow by an improper means, such as: applications that increase traffic by falsifying information such as names and trademarks of others or by inducing sharing and purchasing false attention are considered to be inferior applications. From the service dimension, the high-quality application may refer to an application that can smoothly provide a service for a user, and the low-quality application may refer to an application that cannot normally provide a service for a user, for example: applications that provide unavailable services due to expired and abnormal certificates or malicious services such as induced downloads and plug-ins are considered as inferior applications. From the content dimension, the priority application program refers to an application program which does not contain advertisement information, has positive energy and does not contain illegal or false information, and the content of the application program is positive and upward; the inferior application program refers to an application program with a large amount of advertisement information or illegal website skip links in the content. Therefore, identifying the quality of the application programs and screening out high-quality application programs to provide high-quality services for users are important means for improving client competitiveness. However, there are major challenges to quality identification of applications because: different application programs have different functions; for example: the news applet provides news searching and browsing functions, and the shopping applet provides an e-commerce function; the content of the application program is rich and various, for example, the news applet comprises various news; the shopping applet contains various commodity information; thirdly, the carriers of the application programs are various; for example, a shopping applet is hosted by an IM client, while a game applet is hosted by a news client; the structures of the application programs are different, and the application programs are developed by using different program frameworks; for the above reasons, there are major technical challenges to the quality identification of applications.

The embodiment of the application provides a scheme for identifying and processing the quality of an application program, the scheme acquires a sequence set of the application program, the sequence set is a sequence packet formed by packaging a plurality of behavior sequences, each behavior sequence is used for describing a historical use record of the application program, and the historical use record represents a use example of the application program, so the sequence set reflects a plurality of use examples of the application program; and finally, obtaining a quality identification result of the target application program by fitting the quality characteristics of the target application program, wherein the quality identification result is used for expressing the quality of the application program. Because the quality characteristics of the application program are derived from the relatively comprehensive information of the multiple use examples of the application program, each use example covers the operation scene, the operation step and the operation type of the application program, and covers the information of the response of the application program to the operation and the like, the multiple use examples can relatively comprehensively reflect the information of the function, the content, the service and the like of the application program, the quality of the application program is identified based on the multiple use examples of the application program, the relatively accurate quality evaluation of the application program can be obtained, and the scheme has the advantages of simple operation, high efficiency, low cost and high practicability.

Fig. 1 illustrates an architecture diagram of a processing system for an application provided in an exemplary embodiment of the present application. As shown in fig. 1, the processing system of the application may include a terminal device 101 and a server 102. The number of the terminal devices and the servers in the processing system of the application program shown in fig. 1 is only an example, for example, the number of the terminal devices and the servers may be multiple, and the application does not limit the number of the terminal devices and the servers.

The terminal device 101 is a device used by a user, and comprises at least one client, wherein the client comprises at least one sub-application (applet); for example, the client is a WeChat client that includes a News applet, a shopping applet, a gaming applet, and the like. An AI model and a sequence set may be included in terminal device 101, with the sequence set in terminal device 101 including a historical usage record of applications used by the user on terminal device 101. Terminal device 101 may include, but is not limited to: examples of the device include a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a portable personal computer, and a mobile internet device (MID for short), which are not limited in the embodiments of the present invention. The server 102 refers to a background device for managing applications and providing services to the terminal device 101. The server 102 can include an AI model and a sequence set that includes a historical usage record of applications used by at least one terminal device 101. The server 102 may include, but is not limited to, a cluster server.

In one embodiment, the process flow of the application may be performed by the server 102. Specifically, the method comprises the following steps: the server 102 performs quality identification on the application program deployed on the server through the processing method of the application program provided in the embodiment of the present application, so as to obtain a quality identification result of the application program. When the terminal device 101 requests the server 102 to acquire the application program, the server 102 provides the corresponding application program to the terminal device 101 according to the quality identification result of the application program; for example, the terminal device 101 requests to acquire an applet related to shopping, and the server 102 includes 10 applets related to shopping, but as can be seen from the quality recognition results of the applets, if only the quality of 3 applets related to shopping meets the push condition, the server 102 transmits the 3 applets related to shopping meeting the push condition to the terminal device 101.

In another embodiment, the processing flow of the application program may be executed by the terminal 101. The terminal device 101 identifies the quality of the application program in the terminal device according to the user behavior sequence stored in the terminal device or the sequence set provided by the server 102 by the application program processing method provided by the embodiment of the application, so as to obtain the quality identification result of the application program, and then recommends the corresponding application program for the user according to the quality identification result of the application program; for example: the terminal 101 includes 10 shopping-related applets, but according to the quality identification results of the applets, only the quality of 3 shopping-related applets meets the recommendation condition, and when a search instruction for a shopping-related applet sent by a user is received, the terminal 101 displays the 3 shopping-related applets meeting the recommendation condition to the user.

In the processing system of the application program shown in fig. 1, the processing flow of the application program mainly includes: obtaining a sequence set of a target application, for example, the sequence set can be obtained from the server 102 or a storage space of the terminal device 101; the sequence set includes N (N is a positive integer) behavior sequences, each behavior sequence is used to describe a history usage record of the target application, for example: the sequence of behaviors as described for a one-time shopping record can be expressed as: open by search- > browse- > pay- > leave. Secondly, performing characteristic extraction processing on the behavior sequences in the sequence set; in one embodiment, a network model may be invoked to perform the feature extraction process, which may include, but is not limited to: bi-directional Recurrent Neural Network (Bi-RNN), transform model, and the like. The information obtained by the feature extraction process may be, for example, extraction of the time when the user uses the target application, presence or absence of a payment operation, or the like. Fitting the quality characteristics of the target application program to obtain a quality identification result of the target application program; in one embodiment, a regression model may be used to operate on the quality features of the target application to achieve the fit, and may include, but is not limited to: logistic Regression (Logistic Regression) model, Linear Regression (Linear Regression) model, Stepwise Regression (Stepwise Regression) model, and the like. Wherein, the identification result can be represented by a quality score.

In the embodiment of the application, a sequence set of an application program is obtained, where the sequence set is a sequence package formed by packaging a plurality of behavior sequences, each behavior sequence is used to describe a history usage record of the application program, and the history usage record represents a usage example of the application program, so that the sequence set reflects a plurality of usage examples of the application program; and finally, obtaining a quality identification result of the target application program by fitting the quality characteristics of the target application program, wherein the quality identification result is used for expressing the quality of the application program. Because the quality characteristics of the application program are derived from the relatively comprehensive information of the multiple use examples of the application program, each use example covers the operation scene, the operation step and the operation type of the application program, and covers the information of the response of the application program to the operation and the like, the multiple use examples can relatively comprehensively reflect the information of the function, the content, the service and the like of the application program, the quality of the application program is identified based on the multiple use examples of the application program, the relatively accurate quality evaluation of the application program can be obtained, and the scheme has the advantages of simple operation, high efficiency, low cost and high practicability.

Fig. 2 is a flowchart illustrating a processing method of an application according to an exemplary embodiment of the present application. The processing method of the application program may be executed by the terminal apparatus 101 or the server 102 shown in fig. 1; as shown in fig. 2, the processing method of the application program includes, but is not limited to, the following steps 201 to 203. The following describes in detail a processing method of an application provided in an embodiment of the present application, taking a terminal device as an example:

201. the terminal equipment acquires a sequence set of the target application program.

The target application refers to any installation-free application in the terminal device, and specifically may refer to a sub-application (applet) in a client of the terminal device; for example, the target application is an applet in the IM client. The sequence set of the target application program comprises N behavior sequences, each behavior sequence is used for describing one-time historical use record of the target application program, and N is a positive integer. The one-time historical use record comprises a plurality of operation steps involved in one-time historical use of the target application program, and each operation step comprises at least one of the following operation characteristics: operation scenario, operation time, and operation type. A behavior sequence comprising a plurality of behavior elements, a behavior element for recording an operation step; and arranging each behavior element in the behavior sequence according to the sequence of the operation time.

Fig. 3 illustrates a behavior sequence diagram provided by an exemplary embodiment of the present application. As shown in fig. 3, 301 is a behavior sequence in a sequence set, where the behavior sequence includes 5 behavior elements, "search entry", "page browsing", "sharing", "browsing continuously", and "exit", and each behavior element records an operation characteristic of a corresponding operation step. For example: let the one-time usage record of the user 1 for the target application include: it takes 3 minutes to browse news 1, then clicks on the video that was playing news 1 for a period of 2 minutes, then takes another 4 minutes to continue browsing news 1, and finally closes the target application. The operation steps involved in the usage record include: opening a target application program, browsing in a sliding manner, clicking to play a video, continuing browsing in a sliding manner and closing the target application program; thus, the usage record corresponds to a sequence of rows as: open- > browse- > play- > continue browsing- > leave, the sequence of behaviors includes behavior elements including "open", "browse", "play", "continue browsing", and "leave". The contents of each behavior element in this behavior sequence are shown in table 1 below:

table 1: behavioral sequence Listing

The behavior element "open" is used for recording the operation steps of "opening the target application", and recording the opening mode and the opening time. The behavior element 'browse' is used for recording the operation steps 'browse the content in the target application program', and the 'browse' records whether a user slides a screen when browsing; the "playing" is used for recording the operation step of "clicking to play the video", and the playing records the video opening mode and the information (such as video name, type and the like) of the played video; the 'continuous browsing' is used for recording the operation steps 'browsing the content in the target application program', and the 'continuous browsing' records whether a screen is slid or not when a browsing user browses; the "leaving" is used to record the operation step "close the target application program", and the "leaving" records the leaving manner and the leaving time. It can be understood that, by comparing the operation time, the execution time of the operation step corresponding to each behavior element can be obtained; for example, the operation time of "play" is "17: 39", and the operation time of "browse" is "17: 36", the operation step "browse contents in target application" time is 3 minutes. It should be noted that the contents in table 1 are only for example and do not constitute a practical limitation of the present application.

In one embodiment, the sequence set is stored in a local storage space of the terminal device (e.g., a storage space built in or extended by the terminal device, or a memory of a client running in the terminal device), and the terminal device obtains the sequence set in the local storage space, where the sequence set includes a history of usage records of a target application used by a user on the terminal device. Specifically, the terminal device may be acquired from a locally stored usage log of the target application. In another embodiment, the terminal device obtains a sequence set by sending an obtaining request to the server, and the sequence set provided by the server includes a historical usage record of at least one terminal device usage target application.

202. And the terminal equipment performs characteristic extraction processing on the behavior sequences in the sequence set to obtain the quality characteristics of the target application program.

The quality characteristics refer to parameters which are referred to when the quality of the application program is measured; for example, the quality characteristics include whether or not to include advertisement push, number of people interested, average number of times used per day, and the like. Specifically, the terminal device extracts the quality features of the target application program included in each behavior sequence in the sequence set through data mining, deep learning, natural language processing and the like, and obtains the quality features of the target application program by combining the quality features of the target application program included in each behavior sequence. For example, assuming that the sequence set of the application 1 includes a behavior sequence 1 and a behavior sequence 2, the terminal device performs feature extraction on the behavior sequence 1 to obtain that the application 1 has a quality feature of "including advertisement information", and performs feature extraction on the behavior sequence 2 to obtain that the application 1 has a quality feature of "having false content", then the terminal device determines that the application 1 has quality features of "including advertisement information" and "having false content".

203. And the terminal equipment fits the quality characteristics of the target application program to obtain a quality identification result of the target application program.

Wherein the quality identification result is used for indicating the quality of the target application program; for example, indicating that the target application is a premium application or a rogue application. In one implementation mode, the terminal equipment judges the quality of the target application program according to the quality characteristics of the target application program to obtain a quality identification result of the target application program; for example, the quality feature of the application 1 is "including false information", and the terminal device determines that the application 1 is a poor application (quality identification result) based on the "including false information".

Fig. 4 is a flowchart illustrating a processing method of another application according to an exemplary embodiment of the present application. The processing method of the application program may be executed by the terminal apparatus 101 or the server 102 shown in fig. 1; as shown in fig. 4, the processing method of the application program includes, but is not limited to, the following steps 401 to 412. The following describes in detail a processing method of an application provided in an embodiment of the present application, taking a terminal device as an example:

401. the terminal equipment acquires a sequence set of the target application program.

The specific implementation of step 401 can refer to the implementation of step 201 in fig. 2, and is not described herein again.

402. And the terminal equipment respectively performs feature extraction processing on the N behavior sequences in the sequence set by adopting a network model to obtain N quality feature components.

In one embodiment, the terminal device uses a network model (such as a Bi-RNN, a transform model, etc.) to perform feature extraction processing on N behavior sequences in the sequence set respectively to obtain N quality feature components, and the quality features of the target application program are represented by the N quality feature components together. Fig. 5a shows a flowchart of feature extraction on a single sequence by using Bi-RNN according to an exemplary embodiment of the present application. As shown in fig. 5a, the terminal device obtains each operation step in the behavior sequence, extracts the feature of each operation step, then inputs the feature of each operation step into the operation unit for operation processing, and then inputs the result after operation processing into the average pool for average processing, so as to obtain the quality feature of the behavior sequence (i.e. the quality feature component of the target application). The operation Unit is specifically a gated loop Unit (GRU). Fig. 5b shows a flowchart of feature extraction on a single sequence by using a transform model according to an exemplary embodiment of the present application. As shown in fig. 5b, the terminal device obtains each operation step in the behavior sequence, extracts the feature of each operation step, then inputs the feature of each operation step into the operation unit for operation, then performs feature mining on the operation result through the association relationship between the operation steps, inputs the mined result into the average pool for average processing, and finally fuses the average processing result to obtain the quality feature of the behavior sequence (i.e. the quality feature component of the target application program). Wherein, the arithmetic unit is a GRU. Compared with Bi-RNN, the transformer model can realize better information coding and extract more subtle features.

Fig. 5c is a flowchart illustrating a processing method of another application according to an exemplary embodiment of the present application. Fig. 5c illustrates the manner in which the target application identification results are obtained through

steps

401, 402, 405 and 406.

For example, assuming that the sequence set corresponding to the application program 1 includes 3 behavior sequences, the terminal device performs feature extraction processing on the behavior sequence 1 by using a network model, and the obtained quality feature component 1 is: the browsing time is 1 minute; and (3) performing feature extraction processing on the behavior sequence 2 by adopting a network model, wherein the obtained quality feature component 2 is as follows: including ad push; and (3) performing feature extraction processing on the behavior sequence 3 by adopting a network model, wherein the obtained quality feature component 3 is as follows: contains small videos, praised. The quality characteristic of application 1 is then: the browsing time is 1 minute, including ad push, including small video, being complied with.

403. And the terminal equipment respectively carries out first noise reduction processing on the N behavior sequences according to the incidence relation among the operation steps in each behavior sequence.

In an implementation manner, the terminal device performs first noise reduction processing on the N behavior sequences respectively according to an association relationship between operation steps in each behavior sequence (for example, in a shopping applet, the time of a user browsing a commodity affects whether the user purchases the commodity, so that the browsing and payment have an association relationship), where the first noise reduction processing is used to remove noise behavior elements in each behavior sequence and retain valid behavior elements. The denoising processing method includes, but is not limited to, ascending dimension denoising including an Attention (Attention) mechanism and descending dimension denoising including Principal Component Analysis (PCA).

Taking the attention mechanism as an example, the terminal device may adopt the attention mechanism to increase the weight of the effective behavior element in the behavior sequence, and assign the weight of the noise behavior element to 0 (i.e., propose the noise behavior element), thereby increasing the influence of the effective behavior element on the quality feature of the behavior sequence. For example, for a game applet, the process of a user playing a game is an effective behavior element, and a browsing interface is a noise behavior element; for a news applet, the process of browsing news by a user is an effective behavior element; for a shopping applet, a user purchases a good as an active behavioral element.

It can be understood that, compared with the manner shown in fig. 5c, by removing the noise behavior elements in each behavior sequence through the first denoising processing (i.e., the manner shown in fig. 5 d), the valid behavior elements are retained, so that the quality features (i.e., quality feature components) of each behavior sequence can be clearer, which is beneficial to improving the precision of the quality identification result of the target application program.

404. And the terminal equipment respectively performs feature extraction processing on the N behavior sequences subjected to the noise reduction processing by adopting a network model to obtain N quality feature components.

And the terminal equipment respectively performs feature extraction processing on the N behavior sequences subjected to the noise reduction processing by adopting a network model to obtain N quality feature components, and the N quality feature components jointly represent the quality features of the target application program. For a specific implementation, reference may be made to the implementation of step 402, which is not described herein again. Fig. 5d is a flowchart illustrating a processing method of another application according to an exemplary embodiment of the present application. Fig. 5d illustrates a manner in which the target application identification result is obtained in steps 403 to 406 through step 401.

405. And the terminal equipment adopts a regression model to carry out regression processing on the N quality characteristic components respectively to obtain N quality identification result components of the target application program.

In one embodiment, the terminal device performs Regression processing on the N quality feature components respectively by using a Regression model (such as a Logistic Regression model, a Linear Regression model, a Stepwise Regression model, or the like) to obtain N quality identification result components of the target application program. For example, the terminal device performs regression processing on the quality characteristic component 1 (with unreal content) of the target application program by using a regression model to obtain a quality identification result component 1 of the target application program, wherein the quality identification result component 1 of the target application program indicates that the target application program is a poor application program; and performing regression processing on the quality characteristic component 2 (without advertisement information) of the target application program by adopting a regression model to obtain a quality identification result component 2 of the target application program, wherein the quality identification result component 2 of the target application program indicates that the target application program is a high-quality application program.

406. And the terminal equipment carries out average operation processing on the N quality identification result components of the target application program to obtain the quality identification result of the target application program.

In one embodiment, the terminal device measures the quality identification result of the target application by means of scoring (e.g., the quality score interval is [0,1], an application with a quality score greater than 0.5 is determined as a premium applet, and an application with a quality score less than 0.5 is determined as a poor applet).

For example, assuming that the quality features of the target application are collectively represented by 3 quality feature components, the terminal device performs regression processing on the 3 quality feature components by using a regression model to obtain scores of a quality identification result component 1 to a quality identification result component 3, which are respectively: 0.7, 0.8 and 0.9, the terminal device performs average operation processing on the scores of the 3 quality identification result components to obtain the quality score of 0.8 in the quality identification result of the target application program.

407. And the terminal equipment performs second noise reduction processing on the sequence set according to the incidence relation among the behavior sequences in the sequence set.

In one embodiment, the terminal device performs second noise reduction processing on the sequence set according to an association relationship between behavior sequences in the sequence set (for example, 10 behavior sequences of a shopping applet are generated according to ten-time usage records of the same user), where the second noise reduction processing is used to remove N-M noise behavior sequences in the sequence set and keep M key behavior sequences; m is a positive integer and M < N. For a specific implementation, refer to step 403, which is not described herein again. For example, assuming that 10 behavior sequences in the shopping applet 1 are generated according to ten usage records of the same user, in the behavior sequences 1 to 9, the time for the user to browse the product is more than 10 minutes and includes the payment operation, and in the behavior sequence 10, the time for the user to browse the product is less than 10 seconds and does not include other behavior elements except for the 3 behavior elements of "browse", "enter" and "exit", as shown in 302 in fig. 3. The terminal device rejects the behavior sequence 10 by a noise reduction processing method, and reserves the behavior sequences 1 to 9.

Fig. 5e is a flowchart illustrating a processing method of another application program according to an exemplary embodiment of the present application. Fig. 5e illustrates the manner in which the target application identification result is obtained through step 401, step 407, step 408, step 411 and step 412.

408. And the terminal equipment respectively performs feature extraction processing on the M key behavior sequences by adopting a network model to obtain M key quality feature components.

409. And the terminal equipment respectively performs feature extraction processing on the N behavior sequences by adopting a network model to obtain N quality feature components.

The specific implementation of step 408 and step 409 can refer to the implementation of step 402, and will not be described herein.

410. And the terminal equipment performs third noise reduction processing on the N quality characteristic components according to the incidence relation among the behavior sequences in the sequence set.

In one implementation, the terminal device performs third denoising processing on the N quality feature components according to an association relationship between each behavior sequence in the sequence set, where the third denoising processing is used to eliminate N-M noise quality feature components in the N quality feature components and keep M key quality feature components; m is a positive integer and M < N. In the specific embodiment, reference may be made to step 407, which is not described herein again.

Fig. 5f is a flowchart illustrating a processing method of another application program according to an exemplary embodiment of the present application. Fig. 5f illustrates a manner in which the target application identification result is obtained in step 401, step 409, and step 412.

It can be understood that the information contained in the plurality of behavior sequences is more than that of a single behavior sequence (i.e. the contained quality characteristics of the target application are more comprehensive), and compared with performing noise reduction processing on a single behavior sequence (i.e. the manner shown in fig. 5 d), performing noise reduction processing on the sequence set according to the association relationship between the behavior sequences in the sequence set (i.e. the manner shown in fig. 5e and 5 f) can mine hidden quality characteristics hidden between the sequences, thereby further improving the accuracy of the quality identification result of the target application. For example, if denoising 1 behavior sequence of the applet 1 to obtain the applet 1 including the key behavior element of "share", but it cannot be predicted that the applet 1 has the feature of inducing the user to share, and if denoising 100 behavior sequences of the applet 1 to obtain 99 behavior sequences including "share", it can be predicted that the applet 1 has the feature of inducing the user to share.

Optionally, the number of behavior sequences in the sequence set is greater than the number threshold, which may increase the complexity of the algorithm and may adversely affect the quality feature prediction of the target application (e.g., excessive noise behavior sequences in the sequences may result in incomplete culling). If the number of the behavior sequences in the sequence set is greater than the number threshold, the terminal device divides the sequence set into a plurality of sequence packets according to the number threshold (for example, 100), and performs feature extraction processing on each sequence packet according to the manner in the above embodiment, so as to obtain quality features of a plurality of target application programs. And selecting the optimal quality characteristic of the target application program (for example, selecting the quality characteristic closest to the quality characteristic of the manually marked target application program) from the quality characteristics of the plurality of target application programs as the key quality characteristic of the target application program by adopting a voting mode.

Optionally, the terminal device performs first noise reduction processing on each behavior sequence according to the association relationship among the operation steps in the behavior sequence, and performs second noise reduction processing or third noise reduction processing on each behavior sequence according to the association relationship among the behavior sequences. I.e. the processing method of the application shown in fig. 5d is combined with the processing method of the application shown in fig. 5e or fig. 5 f. For specific implementation, reference may be made to the implementation in fig. 5d, fig. 5e and fig. 5f, which are not described herein again.

411. And the terminal equipment carries out aggregation processing on the M key quality characteristic components to obtain the quality characteristics of the target application program.

In one embodiment, the terminal device aggregates the M key quality feature components according to a weighted aggregation manner or a concatenation manner to obtain the quality features of the target application program. For example, assuming that the terminal device performs feature extraction on 3 key behavior sequences by using a network model, and obtains that the weight of the feature component 1(f1) is 0.3, the weight of the feature component 2(f2) is 0.7, and the weight of the feature component 3(f3) is 0.4, the quality features of the target application obtained by weight aggregation are as follows: f1 × 0.3+ f2 × 0.7+ f3 × 0.4; the quality characteristics of the target application program obtained by polymerization in a serial connection mode are as follows: f1+ f2+ f 3.

412. And the terminal equipment performs regression processing on the quality characteristics of the target application program by adopting a regression model to obtain a quality identification result of the target application program.

For example, if the quality features of the application 1 include "induced user sharing", the terminal device performs regression processing on the quality features of the application 1 by using a regression model to obtain a quality identification result of the application 1, where the quality identification result indicates that the application 1 is a poor application.

Optionally, the terminal device obtains the quality characteristic of the target application program by means of manual labeling and the like, compares the quality characteristic with the quality of the target application program obtained in the step 202, and trains the network model by using a gradient return method (for example, adjusts parameters in the graph network model), thereby obtaining the optimized network model.

In this embodiment of the present application, the terminal device may process the sequence set of the target application through 4 specific implementations in fig. 5c to fig. 5f, so as to obtain a quality identification result of the target application. Because the quality characteristics of the application program are derived from the relatively comprehensive information of the multiple use examples of the application program, each use example covers the operation scene, the operation step and the operation type of the application program, and covers the information of the response of the application program to the operation and the like, the multiple use examples can relatively comprehensively reflect the information of the function, the content, the service and the like of the application program, the quality of the application program is identified based on the multiple use examples of the application program, the relatively accurate quality evaluation of the application program can be obtained, and the scheme has the advantages of simple operation, high efficiency, low cost and high practicability.

Fig. 6 is a flowchart illustrating a processing method of another application according to an exemplary embodiment of the present application. The processing method of the application program can be executed by the terminal device 101 shown in fig. 1, or by the terminal device 101 shown in fig. 1 and the server 102 in an interactive manner; as shown in fig. 6, the processing method of the application program includes, but is not limited to, the following steps 601 to 606. Wherein:

601. the terminal equipment acquires a sequence set of the target application program.

602. And the terminal equipment performs characteristic extraction processing on the behavior sequences in the sequence set to obtain the quality characteristics of the target application program.

603. And the terminal equipment fits the quality characteristics of the target application program to obtain a quality identification result of the target application program.

The specific implementation of step 601 to step 603 can refer to the implementation of step 201 to step 203 in fig. 2, and is not described herein again. Steps 601 to 603 may be executed by the server.

604. And the terminal equipment displays the search page of the client.

The client is any client on the terminal equipment, the client comprises a target application program, and the target application program refers to any sub-application program parasitic in the client. For example, a mobile phone includes a social APP (i.e., a client), and the social APP includes applets 1 to 10. For another example, the computer includes shopping software 1, and shopping software 1 includes sub-applications 1 to 3.

Alternatively, if steps 601 to 603 are executed by the server, the terminal device obtains the quality identification result of the target application program through the server (for example, by sending a quality identification result obtaining request of the target application program to the server).

605. And if the quality identification result of the target application program meets the recommendation condition, the terminal equipment acquires the information of the target application program.

The condition that the recommendation condition is met means that the quality score of the target application program is larger than a quality threshold; for example, if the quality threshold is 70 points, the quality score of the application 1 is 80 points, and the quality score of the application 2 is 60 points, it is determined that the application 1 satisfies the recommendation condition and the application 2 does not satisfy the recommendation condition. The information of the target application includes at least one of: identification of the target application, subject attributes, categories, function profiles.

In one embodiment, if the terminal device determines that the target application satisfies the recommendation condition, the terminal device obtains information of the target application from the server or the local storage space, and adds the information of the target application to the recommendation list. And the terminal equipment sorts the application programs in the recommendation list according to the sequence of the quality from high to low.

In another embodiment, if the quality score of the target application program is smaller than the penalty threshold, the terminal device performs penalty processing on the target application program. And the penalty threshold is smaller than the quality threshold, namely, the application programs meeting the recommendation condition cannot be penalized, and the penalized application programs cannot be recommended. The penalty processing includes: the method comprises the steps that the terminal device conducts shielding processing on a target application program (namely the terminal device does not display when a user searches the target application program), deleting processing (namely the terminal device deletes the target application program), sending modification prompt information to an operator of the target application program, wherein the modification prompt information comprises possible problems of the target application program (for example, false information exists in an article issued by the operator is prompted), and the modification prompt information is used for prompting the operator to conduct self-checking and modification aiming at the possible problems.

606. And the terminal equipment displays the information of the target application program in a search page of the client.

In one embodiment, a recommendation bar is included in the search page of the client, and the terminal device displays information in the recommendation list in the recommendation bar of the client. Fig. 7a illustrates a search page diagram of a client according to an exemplary embodiment of the present application. As shown in fig. 7a, 701 is a search bar of a client, and when a user needs to search an applet, the user clicks the search bar, inputs a keyword of the applet that needs to be searched, and clicks a "search for" button to perform a search. 702 is a recommendation column of the client, the terminal device displays information in a recommendation list in 702, and the small programs in the recommendation list are small programs of which the quality identification results meet recommendation conditions. The arrangement sequence of the small programs in the recommendation list is obtained by sequencing the quality scores of the small programs from high to low; or after the relevance between the small programs and the historical search records of the user, the quality scores of the small programs and other factors are subjected to comprehensive scores, the small programs are sorted from high to low according to the comprehensive scores.

In another embodiment, after receiving a search instruction of a user, the terminal performs comprehensive scoring according to multiple factors such as the quality scores of the application programs and the like according to the relevance degrees of the keywords, sorts the application programs corresponding to the search instruction according to the sequence of the comprehensive scores from high to low, and displays the sorted result in a search result column. The specific implementation manner may refer to an implementation manner in which information in the recommendation list is displayed in the recommendation bar, and details are not described herein. Fig. 7b illustrates a search result page diagram of a client according to an exemplary embodiment of the present application. As shown in FIG. 7b, the user enters "shopping" at 701 and clicks the "search for" button. 703 is a search result field of the client, and the terminal device determines a corresponding application program according to "shopping", sorts information of the searched application program, and displays the sorted result in the search result field 703.

The following describes in detail the processing method of the application program provided in the embodiment of the present application by using a complete example: assuming that the applet 1 is an applet in the APP1, the terminal device obtains a sequence set of the applet 1, where the sequence set of the applet 1 includes 10 behavior sequences, the terminal device performs feature extraction processing on the 10 behavior sequences by using a transform model to obtain 10 quality feature components (e.g., including advertisement information, having false news, etc.), performs noise reduction processing on the 10 quality feature components according to an association relationship between the 10 behavior sequences (e.g., where 5 behavior sequences belong to the same user) to obtain 3 key quality feature components (e.g., inducing user sharing), and then obtains the quality feature of the APP1 by using a weighted aggregation method. When the user opens the search page of APP1, the terminal device acquires the quality recognition results of other applets in applet 1 and APP 1. And screening out the small programs with the quality scores higher than the quality threshold value and the small programs with the quality scores lower than the penalty threshold value. And sequencing the small programs with the quality scores higher than the quality threshold value from high to low, and sequentially displaying the information of the small programs in a recommendation column of the search page according to the sequencing result. And carrying out punishment processing on the small programs with the quality scores lower than the punishment threshold.

In the embodiment of the application, a sequence set of an application program is obtained, where the sequence set is a sequence package formed by packaging a plurality of behavior sequences, each behavior sequence is used to describe a history usage record of the application program, and the history usage record represents a usage example of the application program, so that the sequence set reflects a plurality of usage examples of the application program; and when a search page of the client is displayed, if the quality identification result of the target application meets the recommendation condition, acquiring information of the target application, and displaying the information of the target application in the search page of the client. Because the quality characteristics of the application program are derived from the relatively comprehensive information of the multiple use examples of the application program, each use example covers the operation scene, the operation step and the operation type of the application program, and covers the information of the response of the application program to the operation and the like, the multiple use examples can relatively comprehensively reflect the information of the function, the content, the service and the like of the application program, the quality identification is carried out on the application program based on the multiple use examples of the application program, the relatively accurate quality evaluation on the application program can be obtained, the application program meeting the recommendation condition is recommended, the probability of selecting and using the high-quality application program by a user is improved, the user experience is further improved, and the scheme is simple to operate, high in efficiency, low in cost and relatively high in practicability.

While the method of the embodiments of the present application has been described in detail above, to facilitate better implementation of the above-described aspects of the embodiments of the present application, the apparatus of the embodiments of the present application is provided below accordingly.

Referring to fig. 8, fig. 8 is a schematic structural diagram of a processing apparatus of an application according to an exemplary embodiment of the present application, where the processing apparatus of the application may be mounted on a terminal device or a server in the foregoing method embodiment. The processing means of the application shown in fig. 8 may be adapted to perform some or all of the functions of the method embodiments described above with reference to fig. 2, 4 and 6. Wherein, the detailed description of each unit is as follows:

an obtaining unit 801, configured to obtain a sequence set of a target application, where the sequence set includes N behavior sequences, each behavior sequence is used to describe a primary history usage record of the target application, and N is a positive integer;

the processing unit 802 is configured to perform feature extraction processing on the behavior sequences in the sequence set to obtain quality features of the target application program, and fit the quality features of the target application program to obtain a quality identification result of the target application program.

In one embodiment, a historical usage record includes a plurality of operational steps involved in historical usage of the target application, each operational step including at least one of the following operational features: an operation scene, an operation time and an operation type;

a said behavior sequence comprising a plurality of behavior elements, a behavior element for recording an operation step; and arranging all the behavior elements in the behavior sequence according to the sequence of the operation time.

In an embodiment, the processing unit 802 is further configured to perform a feature extraction process on the behavior sequences in the sequence set to obtain a quality feature of the target application, and specifically configured to:

and respectively performing feature extraction processing on the N behavior sequences in the sequence set by adopting a network model to obtain N quality feature components, wherein the N quality feature components jointly represent the quality features of the target application program.

and respectively performing feature extraction processing on the N behavior sequences subjected to the noise reduction processing by adopting a network model to obtain N quality feature components, wherein the N quality feature components jointly represent the quality features of the target application program.

In an embodiment, the processing unit 802 is further configured to fit the quality characteristic of the target application to obtain a quality identification result of the target application, and specifically configured to:

performing regression processing on the N quality characteristic components by adopting a regression model to obtain N quality identification result components of the target application program;

In one embodiment, the target application is an installation-free application, and the target application refers to any sub-application hosted in the client.

In one embodiment, the processing unit 802 is further configured to:

In one embodiment, the quality identification result includes a quality score; the quality identification result of the target application program meets the recommendation condition, namely the quality score of the target application program is larger than a quality threshold; the information of the target application includes at least one of: identification, subject attributes, categories, function profiles of the target application;

the processing unit 802 is further configured to display information of the target application program in a search page of the client, and specifically configured to:

adding the information of the target application program into a recommendation list of the client, wherein the recommendation list comprises a plurality of pieces of information to be recommended, and the information is sorted according to the sequence of the quality scores of the corresponding application programs from high to low;

In one embodiment, the quality identification result includes a quality score; the quality identification result of the target application program meets the recommendation condition, namely the quality score of the target application program is larger than a quality threshold;

the processing unit 802 is further configured to:

According to an embodiment of the present application, some steps involved in the processing method of the application shown in fig. 2, fig. 4 and fig. 6 may be executed by each unit in the processing device of the application shown in fig. 8. For example, step 201 shown in fig. 2 may be performed by the acquisition unit 801 shown in fig. 8, and step 202 and step 203 may be performed by the processing unit 802 shown in fig. 8. Step 401 shown in fig. 4 may be performed by the acquisition unit 801 shown in fig. 8, and steps 402 to 412 may be performed by the processing unit 802 shown in fig. 8. Step 601 shown in fig. 6 may be executed by the acquisition unit 801 shown in fig. 8, and steps 602 to 606 may be executed by the processing unit 802 shown in fig. 8. The units in the processing device of the application program shown in fig. 8 may be respectively or entirely combined into one or several other units to form one or several other units, or some unit(s) may be further split into multiple functionally smaller units to form one or several other units, which may achieve the same operation without affecting the achievement of the technical effect of the embodiments of the present application. The units are divided based on logic functions, and in practical application, the functions of one unit can be realized by a plurality of units, or the functions of a plurality of units can be realized by one unit. In other embodiments of the present application, the processing device of the application program may also include other units, and in practical applications, the functions may also be implemented by being assisted by other units, and may be implemented by cooperation of a plurality of units.

According to another embodiment of the present application, a processing apparatus of an application program as shown in fig. 8 may be constructed by running a computer program (including program codes) capable of executing steps involved in the respective methods as shown in fig. 2, fig. 4 and fig. 6 on a general-purpose computing apparatus such as a computer including a processing element such as a Central Processing Unit (CPU), a random access storage medium (RAM), a read-only storage medium (ROM) and a storage element, and a processing method of an application program of an embodiment of the present application may be implemented. The computer program may be recorded on a computer-readable recording medium, for example, and loaded and executed in the above-described computing apparatus via the computer-readable recording medium.

Based on the same inventive concept, the principle and the advantageous effect of the problem solving of the processing apparatus for the application program provided in the embodiment of the present application are similar to the principle and the advantageous effect of the problem solving of the processing method for the application program in the embodiment of the present application, and for brevity, the principle and the advantageous effect of the implementation of the method may be referred to, and are not described herein again.

Referring to fig. 9, fig. 9 is a schematic structural diagram of a processing device for an application according to an exemplary embodiment of the present application, where the processing device for an application includes at least a processor 901, a communication interface 902, and a memory 903. The processor 901, the communication interface 902, and the memory 903 may be connected by a bus or in other manners, and in this embodiment of the application, the connection by the bus is taken as an example. The processor 901 (or Central Processing Unit (CPU)) is a computing core and a control core of a Processing device of an application program, and can analyze various instructions in the terminal device and various data of the terminal device, for example: the CPU can be used for analyzing a power-on and power-off instruction sent to the terminal equipment by a user and controlling the terminal equipment to carry out power-on and power-off operation; the following steps are repeated: the CPU may transmit various types of interactive data between the internal structures of the terminal device, and so on. The communication interface 902 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI, mobile communication interface, etc.), and may be controlled by the processor 901 to transmit and receive data; the communication interface 902 may also be used for transmission and interaction of data within the terminal device. A Memory 903(Memory) is a Memory device in the terminal device and stores programs and data. It is understood that the memory 903 herein may include both the built-in memory of the terminal device and, of course, the expansion memory supported by the terminal device. The memory 903 provides storage space that stores the operating system of the terminal device, which may include, but is not limited to: android system, iOS system, Windows Phone system, etc., which are not limited in this application.

In one embodiment, the processing device of the application may refer to a terminal device or a server, such as the terminal device 101 or the server 102 shown in fig. 1. In this case, the processor 901 performs the following operations by executing the executable program code in the memory 903:

acquiring a sequence set of a target application program through a communication interface 902, wherein the sequence set comprises N behavior sequences, each behavior sequence is used for describing a primary historical use record of the target application program, and N is a positive integer;

performing feature extraction processing on the behavior sequences in the sequence set to obtain quality features of the target application program;

As an alternative embodiment, the one-time history record includes a plurality of operation steps involved in one-time history use of the target application, each operation step including at least one of the following operation features: an operation scene, an operation time and an operation type;

As an optional implementation manner, the specific implementation manner of performing, by the processor 901, feature extraction processing on the behavior sequence in the sequence set to obtain the quality feature of the target application program is as follows:

As an optional implementation manner, the specific implementation manner of the processor 901 fitting the quality characteristics of the target application to obtain the quality identification result of the target application is:

As an alternative embodiment, the target application is an installation-free application, and the target application refers to any sub-application hosted in the client.

As an alternative embodiment, the processor 901 further performs the following operations by executing the executable program code in the memory 903:

As an optional implementation, the quality identification result includes a quality score; the quality identification result of the target application program meets the recommendation condition, namely the quality score of the target application program is larger than a quality threshold; the information of the target application includes at least one of: identification, subject attributes, categories, function profiles of the target application;

the specific implementation of the processor 901 displaying the information of the target application program in the search page of the first client is as follows:

adding the information of the target application program into a recommendation list of the first client, wherein the recommendation list comprises a plurality of pieces of information to be recommended, and the information is sorted according to the sequence of the quality scores of the corresponding application programs from high to low;

and displaying the information in the recommendation list of the first client in the search page of the first client.

As an optional implementation, the quality identification result includes a quality score; the quality identification result of the target application program meets the recommendation condition, namely the quality score of the target application program is larger than a quality threshold;

the processor 901, by executing the executable program code in the memory 903, also performs the following operations:

Based on the same inventive concept, the principle and the advantageous effect of the problem solving of the processing device of the application program provided in the embodiment of the present application are similar to the principle and the advantageous effect of the problem solving of the processing method of the application program in the embodiment of the present application, and for brevity, the principle and the advantageous effect of the implementation of the method may be referred to, and are not described herein again.

The embodiment of the present application further provides a computer-readable storage medium, where one or more instructions are stored in the computer-readable storage medium, and the one or more instructions are adapted to be loaded by a processor and to execute the processing method of the application program according to the above method embodiment.

Embodiments of the present application further provide a computer program product containing instructions, which when run on a computer, cause the computer to execute the processing method of the application program described in the above method embodiments.

It should be noted that, for simplicity of description, the above-mentioned embodiments of the method are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the order of acts described, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

The steps in the method of the embodiment of the application can be sequentially adjusted, combined and deleted according to actual needs.

The modules in the device can be merged, divided and deleted according to actual needs.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, which may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

While the invention has been described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims

1. A processing method of an application program is characterized by comprising the following steps:

2. The method of claim 1, wherein a historical usage record comprises a plurality of operational steps involved in a historical usage of the target application, each operational step comprising at least one of the following operational characteristics: an operation scene, an operation time and an operation type;

3. The method according to claim 2, wherein the performing feature extraction processing on the behavior sequences in the sequence set to obtain the quality features of the target application program comprises:

4. The method according to claim 2, wherein the performing feature extraction processing on the behavior sequences in the sequence set to obtain the quality features of the target application program comprises:

5. The method according to claim 3 or 4, wherein the fitting the quality characteristics of the target application to obtain the quality identification result of the target application comprises:

6. The method according to claim 2, wherein the performing feature extraction processing on the behavior sequences in the sequence set to obtain the quality features of the target application program comprises:

7. The method according to claim 2, wherein the performing feature extraction processing on the behavior sequences in the sequence set to obtain the quality features of the target application program comprises:

8. The method according to claim 6 or 7, wherein the fitting the quality characteristics of the target application to obtain the quality identification result of the target application comprises:

9. The method of claim 1, wherein the target application is an install-free application, and wherein the target application is any sub-application hosted by the client.

10. The method of claim 1, further comprising:

11. The method of claim 10, wherein the quality identification result comprises a quality score; the quality identification result of the target application program meets the recommendation condition, namely the quality score of the target application program is larger than a quality threshold; the information of the target application includes at least one of: identification, subject attributes, categories, function profiles of the target application;

the displaying the information of the target application program in the search page of the client includes:

12. The method of claim 10, wherein the quality identification result comprises a quality score; the quality identification result of the target application program meets the recommendation condition, namely the quality score of the target application program is larger than a quality threshold;

the method further comprises the following steps:

13. An apparatus for processing an application program, comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a sequence set of a target application program, the sequence set comprises N behavior sequences, each behavior sequence is used for describing one-time historical use record of the target application program, and N is a positive integer;

14. An apparatus for processing an application program, comprising:

a memory storing computer readable instructions;

a processor coupled to the memory, the processor configured to execute the computer-readable instructions to implement the method of processing the application program of any of claims 1-12.

15. A computer-readable storage medium, characterized in that it stores one or more instructions adapted to be loaded by said processor and to execute the processing method of an application according to any of claims 1-12.