WO2020087388A1

WO2020087388A1 - Quick application recommendation method and apparatus, storage medium, and electronic device

Info

Publication number: WO2020087388A1
Application number: PCT/CN2018/113168
Authority: WO
Inventors: 林进全
Original assignee: 深圳市欢太科技有限公司; Oppo广东移动通信有限公司
Priority date: 2018-10-31
Filing date: 2018-10-31
Publication date: 2020-05-07
Also published as: CN112673370A

Abstract

A quick application recommendation method and apparatus, a storage medium, and an electronic device. The recommendation method comprises: collecting multiple features available upon activation of quick applications as samples, and establishing a sample library (S101); performing clustering of samples in the sample library to obtain a target clustering result (S102); upon detecting a quick application recommendation command, acquiring current environment feature information (S103); and performing comparison according to the environment feature information and the target clustering result to determine a corresponding quick application, and recommending the same (S104). The recommendation method improves accuracy of recommending a quick application.

Description

Recommended method, device, storage medium and electronic equipment for fast application

Technical field

The present application relates to the technical field of electronic equipment, and in particular, to a recommended method, device, storage medium, and electronic equipment for fast application.

Background technique

With the continuous development of electronic technology, the functions of electronic devices such as mobile phones are becoming more and more powerful. Users can browse the original pages of the application through various fast applications. The fast application is an application that can be experienced without installing the application. Lightweight application with native features.

At present, after the mobile phone opens the list of fast apps, the most recently used fast apps will be listed. The order of the list is the time of the most recently opened fast apps by the user, and the recently used fast apps will be ranked according to the opening time At the forefront, this recommendation method is relatively rigid and cannot be intelligently recommended according to user needs, and the recommendation accuracy rate is low.

Summary of the invention

Embodiments of the present application provide a quick application recommendation method, device, storage medium, and electronic equipment, which can improve the recommendation accuracy of fast applications.

In the first aspect, an embodiment of the present application provides a quick application recommendation method, including:

Collect the multi-dimensional features when the fast application is started as a sample, and establish a sample library;

Performing clustering processing on the samples in the sample library to obtain the target clustering result;

When the recommended instruction for quick application is detected, the current environmental characteristic information is obtained;

Based on the comparison between the environmental characteristic information and the target clustering result, the corresponding target quick application is determined and recommended.

In a second aspect, an embodiment of the present application provides a quick application recommendation device, including:

The collection unit is used to collect multi-dimensional features when the fast application is started as a sample, and establish a sample library;

A processing unit, configured to perform clustering processing on the samples in the sample library to obtain a target clustering result;

An obtaining unit, configured to obtain current environmental characteristic information when a quick application recommendation instruction is detected;

The determining unit is used to compare the environment feature information with the target clustering result, determine the corresponding target quick application and make recommendations.

In a third aspect, a storage medium provided by an embodiment of the present application has a computer program stored thereon, and when the computer program runs on a computer, the computer is allowed to execute the recommended method for fast application as provided by any embodiment of the present application .

According to a fourth aspect, an electronic device provided by an embodiment of the present application includes a processor and a memory, and the memory has a computer program, wherein the processor is used to perform the steps by calling the computer program:

BRIEF DESCRIPTION

The technical solutions and other beneficial effects of the present application will be apparent through the detailed description of the specific implementation of the present application in conjunction with the accompanying drawings.

FIG. 1 is a schematic flowchart of a quick application recommendation method provided by an embodiment of the present application.

FIG. 2 is another schematic flowchart of a quick application recommendation method provided by an embodiment of the present application.

FIG. 3 is a schematic block diagram of a quick application recommendation device provided by an embodiment of the present application.

4 is a schematic diagram of another module of a quick application recommendation device provided by an embodiment of the present application.

5 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

FIG. 6 is another schematic structural diagram of an electronic device provided by an embodiment of the present application.

detailed description

Please refer to the drawings in which the same component symbols represent the same components. The principle of the present application is illustrated by implementation in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application, which should not be considered as limiting other specific embodiments not detailed herein.

The term "module" used in this article can be regarded as a software object executed on the computing system. The different components, modules, engines and services described in this article can be regarded as the implementation objects on the computing system. However, the device and method described herein are preferably implemented in the form of software, and of course can also be implemented in hardware, which are all within the protection scope of the present application.

The embodiment of the present application provides a method for recommending a fast application. The main body of the method for recommending a fast application may be the device for recommending a fast application provided in the embodiment of the present application, or an electronic device integrated with the device for recommending a fast application, wherein The quick application recommendation device can be implemented in hardware or software. Among them, the electronic device may be a smart phone, a tablet computer, a PDA (Personal Digital Assistant) and so on.

The specific analysis is explained below.

An embodiment of the present invention provides a quick application recommendation method, including:

In one embodiment, the step of clustering the samples in the sample library to obtain the target clustering result may include: analyzing each sample in the sample library according to the clustering model, Each sample generates a corresponding clustering point; each clustering point is clustered according to the clustering model to obtain the target clustering result.

In one embodiment, the step of performing clustering processing on each clustering point according to the clustering model to obtain a target clustering result may include: performing convergence processing on the clustering points according to the clustering model to obtain A plurality of convergent cluster clusters, the cluster cluster is composed of a plurality of convergent cluster points; the plurality of convergent cluster clusters is determined as a target clustering result.

In an embodiment, the step of determining the corresponding target application and recommending based on the comparison between the environmental feature information and the target clustering result may include: calculating the environmental feature information and each cluster Euclidean distance of the cluster; the cluster cluster with the smallest Euclidean distance is determined as the target cluster, and the corresponding target application is determined and recommended according to the target cluster.

In one embodiment, the step of collecting multi-dimensional features when the fast application is opened as a sample, and before the step of establishing a sample library, may further include: when the application is detected to be opened, acquiring the corresponding name attribute of the currently opened application; judgment Whether the name attribute is a preset name attribute; when it is determined that the name attribute is a preset name attribute, the currently opened application is determined to be a fast application, and a multi-dimensional feature when the quick application is opened is collected as a sample, and a sample is created Library steps.

In one embodiment, the step of determining whether the name attribute is a preset name attribute may include: extracting keyword information from the name attribute; determining whether the keyword information and the preset keyword information Match; when it is determined that the keyword information matches the preset keyword information, it is determined that the name attribute is the preset name attribute; when it is determined that the keyword information does not match the preset keyword information, it is determined The name attribute is not a preset name attribute.

In one embodiment, the step of collecting multi-dimensional features when the quick application is started as a sample and establishing a sample library may include: starting to calculate a time value and collecting the multi-dimensional features when the quick application is started as a sample; when the time When the accumulated value reaches the preset time, the collected samples will be established into a sample library.

An embodiment of the present application provides a quick application recommendation method. As shown in FIG. 1, FIG. 1 is a schematic flowchart of a quick application recommendation method provided by an embodiment of the present application. The quick application recommendation method may include the following steps:

In step S101, multi-dimensional features when the quick application is started are collected as samples, and a sample library is established.

It should be noted that when users use some fast apps, they often need to start in specific scenarios, such as the quick order app will be opened near the company at 12 noon, and will be near the subway at 8 am and around 6 pm Open the Metro Express app and so on, so the Express app has clustering properties when it starts.

Based on this, when the user starts the fast application, the electronic device will correspondingly collect the multi-dimensional features at the start of the fast application. As a sample, the multi-features may include, but are not limited to, the start time, fast geographic location, and fast start of the fast application. For the application name of the application, etc., a sample within a preset time may be collected to establish a sample library. In an embodiment, the preset time may be 7 days or 14 days, etc.

In some embodiments, the step of acquiring the multi-dimensional feature when the quick start application is used as a sample and establishing a sample library may include:

(1) Start to calculate the time value and collect the multi-dimensional features when the fast application is started as a sample;

(2) When the accumulated time value reaches the preset time, the collected samples will be established into a sample library.

Among them, in order to be more in line with the user's usage habits, the user's habits when opening the fast application in the past week or two weeks can be collected as a sample to establish a sample library, that is, the time value is calculated, and the preset time can be set according to the usage habits, such as The preset time is one week or two weeks, and samples are collected continuously until the calculated time value reaches the preset time cumulatively.

Further, when the accumulated time value reaches the preset time, the continuously collected samples are summarized and a sample library is established. In one embodiment, after the sample library is established, the time value can be continuously calculated, and the sample within the preset time can be collected. When the time value reaches the preset time again, the newly collected sample can replace the sample in the original sample library. Re-update the sample library to ensure the real-time nature of the samples.

In step S102, perform clustering processing on the samples in the sample library to obtain the target clustering result.

Among them, the clustering process can be realized by a cluster analysis algorithm. As the saying goes: "things are clustered by clusters, people are clustered by clusters". In the natural and social sciences, there are a lot of classification problems, and the clustering algorithm Put similar samples into the same set.

Based on this, the samples in the sample library can be clustered according to specific features through the algorithm of cluster analysis, and samples with similar specific features can be put into corresponding sets respectively to obtain multiple different sets, and combine multiple different Is determined as the target clustering result.

In an embodiment, the clustering analysis algorithm may be a K-means algorithm, which is a typical distance-based clustering algorithm, and uses distance as a similarity evaluation index, that is, two objects are considered The closer the distance, the greater the similarity. The algorithm believes that clusters are composed of objects close to each other, so the final goal is to obtain compact and independent clusters, that is, multiple compact and independent clusters can be used as the target clustering result.

In some embodiments, the step of clustering the samples in the sample library to obtain the target clustering result may include:

(1) Analyze each sample in the sample library according to the clustering model, and generate a corresponding cluster point for each sample;

(2) Perform clustering processing on each clustering point according to the clustering model to obtain the target clustering result.

Wherein, the clustering model may be a K-means algorithm model, and each sample in the sample library is analyzed with a specific feature according to the K-means algorithm. In one embodiment, the specific feature may be a start-up time feature and a start-up location feature. In this way, the K-means algorithm model generates a corresponding cluster point for each sample, and the spatial attributes of the cluster point are composed of specific features.

Further, according to the K-means algorithm, clustering points with high similarity are clustered to obtain multiple similar clustering sets, and the multiple similar clustering sets are determined as the target clustering result.

In some embodiments, the step of clustering each clustering point according to the clustering model to obtain the target clustering result may include:

(1.1) Perform convergence processing on the clustering points according to the clustering model to obtain a plurality of converging clustering clusters, the clustering cluster is composed of a plurality of converging clustering points;

(1.2) Determine multiple convergent clusters as the target clustering result.

Among them, because the clustering model uses the K-means algorithm, the K-means algorithm uses distance as an evaluation index of similarity, that is, the closer the distance between two objects, the greater the similarity. The K-means algorithm It is considered that the clusters are composed of objects that are close to each other, so the final goal is to obtain compact and independent clusters.

Further, a preset number of initial cluster centers can be randomly selected in the sample library, the distance between each cluster point and the cluster center can be calculated, and each cluster can be clustered according to the distance between each cluster point and the cluster center The point is assigned to the closest cluster. After all the cluster points are examined, an iterative operation is completed, the new cluster center is calculated, and so on, until the cluster points in the cluster cluster no longer change, that is to say The clustering cluster has converged, and multiple clustering clusters are determined as the target clustering result.

In step S103, when the quick application recommendation instruction is detected, the current environmental characteristic information is acquired.

Wherein, when the user opens the quick application list, the electronic device needs to obtain multiple quick application icons to display in the quick application list. In the prior art, the quick application icons recently used by the user are displayed on the quick application according to the order of use time In the list, this mechanical arrangement will cause inconvenience to users. In this solution, when the user opens the quick application list, a quick application recommendation instruction will be generated, and when the electronic device detects the quick application recommendation instruction, it will obtain the current environmental feature information accordingly. The environmental feature information is the user ’s current location. Scene information, such as the current time and current location, etc. It should be noted that the environmental feature information may correspond to the specific feature used for clustering.

In step S104, according to the environmental characteristic information and the target clustering result, the corresponding target quick application is determined and recommended.

Among them, since the environmental feature information corresponds to the specific feature of the clustering process, different sets of the environmental feature information and the target clustering result after the clustering process may have corresponding similarity information, corresponding, The set with the highest similarity is determined as the target set, and multiple samples distributed in the target set are obtained, the application names of the fast apps in the multiple samples are extracted, and multiple target fast apps are determined and displayed on the fast Apply in the list to make recommendations.

In an embodiment, the number of repeated application names may be counted, and multiple target fast applications may be sorted and displayed and recommended according to the counted order from high to low.

In some embodiments, the step of comparing the environment feature information with the target clustering result to determine the corresponding target application and recommending may include:

(1) Calculate the Euclidean distance between the environmental feature information and each cluster;

(2) The cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster, and the corresponding target fast application is determined and recommended according to the target cluster cluster.

It should be noted that the Euclidean distance generally refers to the Euclidean metric, which is a commonly used distance definition, which refers to the true distance between two points in the m-dimensional space, or the natural length of the vector (That is, the distance from the point to the origin). The Euclidean distance in two-dimensional and three-dimensional space is the actual distance between two points. From this, the distance between two cluster points can be measured by the Euclidean distance, and the distance between two cluster points can be obtained. Similarity.

Among them, the Euclidean distance (also can be understood as the similarity) of the cluster points in each cluster cluster on a specific feature is relatively close, and since the environmental feature information corresponds to the specific feature, the obtained The Euclidean distance between the environmental feature information and the center point of each cluster, the cluster with the smallest Euclidean distance, that is, the highest similarity, is determined as the target cluster. The target cluster has the most environmental feature information corresponding to the current environment. Is close, so the target cluster represents the user's historical usage habits in this environment.

Further, the corresponding application name of each cluster point in the target cluster is obtained, and the number of repeated application names is counted, and the corresponding fast application icons are sorted and displayed according to the order of the statistical number from high to bottom, to Recommend to users.

As can be seen from the above, a method for recommending a fast application provided by this embodiment, by collecting multi-dimensional features when the fast application is started as a sample, and establishing a sample library; clustering the samples in the sample library to obtain the target cluster Results; when the quick application recommendation instruction is detected, the current environmental feature information is obtained; according to the environmental feature information and the target clustering result is compared, the corresponding target quick application is determined and recommended. In this way, a sample library is established according to the multi-dimensional features of the user when the fast application is started, and the samples in the sample library are clustered to obtain the corresponding target clustering result. When the recommended instruction of the fast application is detected, the current environmental feature information is obtained. According to the comparison between the environmental feature information and the target clustering results, the target fast application suitable for the current environment is determined and intelligent recommendation is made, which improves the accuracy rate of fast application recommendation.

According to the method described in the above embodiment, the following examples will be used for further detailed description.

Please refer to FIG. 2, which is another schematic flowchart of a method for recommending a fast application provided by an embodiment of the present application.

Specifically, the method includes:

In step S201, when it is detected that the application is opened, the name attribute corresponding to the currently opened application is acquired.

Among them, electronic devices such as mobile phones include applications installed through software installation packages and lightweight fast applications that are directly opened through script file parsing configuration files. Compared with applications, this fast application does not require downloading installation packages and does not occupy The storage space of the phone, but you can also directly experience the native functions of the application.

Therefore, when the mobile phone detects that the application is opened, it can obtain the corresponding name attribute of the currently opened application, that is, the name attribute of the current application can be grabbed from the background, and the name attribute can be a piece of program code, such as com.opper.mm. plugin.appbrand.ui.appBrandUI.

In step S202, it is determined whether the name attribute is a preset name attribute.

Among them, the name attribute of the fast application will contain a part of the program code, such as opper, you can determine the part of the program code as the preset name attribute, determine whether the obtained name attribute matches the preset name attribute, when it is determined that the name attribute is pre When the name attribute is set, step S203 is executed. When it is determined that the name attribute is not the preset name attribute, it means that the currently running application is not a fast application, and the process returns to step S201.

In some embodiments, the step of determining whether the name attribute is a preset name attribute may include:

(1) Extract keyword information in the name attribute;

(2) Determine whether the keyword information matches the preset keyword information;

(3) When it is determined that the keyword information matches the preset keyword information, it is determined that the name attribute is the preset name attribute;

(4) When it is determined that the keyword information does not match the preset keyword information, it is determined that the name attribute is not the preset name attribute.

Among them, the keyword information in the name attribute can be extracted. The keyword information can be representative information of the fast application, such as the opper, etc., and the keyword information can also be representative information of the application, such as the apk. Extract keyword information opper such as com.opper.mm.plugin.appbrand.ui.appBrandUI, determine whether the keyword information opper matches the preset keyword information, the preset keyword information is fast application keyword information opper , Matches the extracted keyword information opper, then it is determined that the name attribute is a preset name attribute. If the extracted keyword information is apk and does not match the preset keyword information, it is determined that the name attribute is not the preset name attribute.

In step S203, it is determined that the currently opened application is a fast application, and a multi-dimensional feature when the fast application is started is collected as a sample, and a sample library is established.

Among them, when it is judged that the name attribute is a preset name attribute, it means that the currently running application is a fast application, for example, the name attribute com.opper.mm.plugin.appbrand.ui.appBrandUI contains an opper, and the currently opened application is judged to be fast Application, and collect the multi-dimensional characteristics of the currently running fast application when it is started as a sample. The multi-dimensional characteristics can include the startup time, the current geographic location, the application name of the fast application, and so on. You can continuously collect samples within two weeks to establish For the sample library, it should be noted that the current geographic location can be latitude and longitude.

In step S204, each sample in the sample library is parsed according to the clustering model, and each sample is generated into a corresponding clustering point.

Among them, when the user starts the fast application, it is often started according to the actual needs in a specific scenario, for example, the fast order application will be opened near the company's geographical location at about 12 noon, and will be in the subway station at 8 am and about 6 pm Start the Metro Express app nearby, etc. It can be seen that the express app has a clustering trend at a certain point in time and geographical location.

In this way, according to the K-means clustering algorithm model, each sample in the sample library can be used as a specific classification feature according to the startup time and the current geographic location, and a two-dimensional coordinate system corresponding to the startup time and the current geographic location can be established. Corresponding clustering points are generated according to the starting time and geographic location.

In step S205, the clustering points are converged according to the clustering model to obtain a plurality of convergent clustering clusters.

Among them, you can randomly select any K objects as the cluster center point of the initial cluster through the K-means clustering algorithm model, and calculate the Euclidean distance between each cluster point and the cluster center point, which represents the cluster point The similarity to the cluster center point, the smaller the Euclidean distance, the greater the similarity between the two points, the smaller the Euclidean distance, the smaller the similarity between the two points.

Further, according to the distance between each cluster point and each cluster center point, the nearest point is assigned to the corresponding cluster center to form K cluster clusters, and then all clusters in the cluster cluster are calculated The mean value of the points forms a new clustering center and repeats until the clustering points begin to converge to obtain K convergent clustering clusters.

In step S206, a plurality of converged cluster clusters are determined as the target clustering result.

Among them, since the cluster point in each cluster cluster is closest to other cluster points in the same cluster cluster, multiple convergent cluster clusters can be opened on behalf of users at a certain time and corresponding geographic location The habit of fast application, the multiple convergent clusters form the corresponding target clustering result.

In step S207, when the quick application recommendation instruction is detected, the current environmental characteristic information is acquired.

Among them, when the user needs to use the fast application, the fast application list needs to be opened. Correspondingly, the fast application recommendation instruction can be generated. When the mobile phone detects the fast application recommendation instruction, the user needs to intelligently recommend the fast application that the user wants to open according to the current environmental scene application.

Therefore, when the quick application recommendation instruction is detected, the environmental characteristic information in the current scene, such as the current time and the current geographic location, can be obtained.

In step S208, the Euclidean distance between the environmental feature information and each cluster is calculated.

Among them, since the clustering cluster is a two-dimensional coordinate system modeling based on the start time and geographic location, after obtaining the current time and current geographic location in the current scene, the current time and current geographic location can be calculated with each cluster The Euclidean distance of the clustering center point of the cluster. When the Euclidean distance is smaller, the two are more similar. When the Euclidean distance is larger, the difference between the two is larger.

In step S209, the cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster, and the corresponding target quick application is determined and recommended according to the target cluster cluster.

Among them, the cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster, that is, the cluster cluster that is most similar to the current time and the current geographic location is determined as the target cluster cluster, and the distribution of the target cluster cluster indicates that in the scene Under the habit of users to open fast apps, get the corresponding app name of each cluster point in the cluster, and count the number of repeated app names, get the target fast app corresponding to the app name, and follow the statistics from high to Sort the target fast apps in a low order and display them in the quick apps list for recommendation. For example, if the environmental feature information is 12:01 and company coordinates, then according to the usual clustering processing results, you can determine that multiple points are displayed in the list. Fast food application and so on.

As can be seen from the above, a method for recommending a fast application provided by this embodiment determines whether the application is a fast application according to the name attribute of the current application when the application is detected to be opened, and when the fast application is Multi-dimensional features are used as samples, and a sample library is established, and the samples in the sample library are clustered according to the K-means clustering model to obtain multiple convergent cluster clusters, and the multiple convergent cluster clusters are determined as target clusters As a result, when the recommended instruction for fast application is detected, the current environmental feature information is obtained, the Euclidean distance between the environmental feature information and each cluster cluster is calculated, and the cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster. The target cluster determines the corresponding target application and recommends it. In this way, a sample library is established according to the multi-dimensional features of the user when the fast application is started, and the samples in the sample library are clustered to obtain the corresponding target clustering result. When the recommended instruction of the fast application is detected, the current environmental feature information is obtained. According to the comparison between the environmental feature information and the target clustering results, the target fast application suitable for the current environment is determined and intelligent recommendation is made, which improves the accuracy rate of fast application recommendation.

To facilitate better implementation of the quick application recommendation method provided by the embodiments of the present application, the embodiment of the present application further provides an apparatus based on the quick application recommendation method. The meaning of the nouns is the same as in the above-mentioned quick application recommendation method. For specific implementation details, refer to the description in the method embodiment.

An embodiment of the present invention provides a quick application recommendation device, including:

In an embodiment, the processing unit may include: a parsing subunit and a processing subunit, the parsing subunit is used to parse each sample in the sample library according to the clustering model, and generate a corresponding Clustering point; this processing subunit is used to perform clustering processing on each clustering point according to the clustering model to obtain the target clustering result.

In one embodiment, the processing subunit is specifically configured to: perform convergence processing on the clustering points according to the clustering model to obtain multiple converging clustering clusters, where the clustering cluster is composed of multiple converging clustering points Composition; determine multiple clustering clusters as the target clustering result.

In one embodiment, the determining unit is specifically configured to: calculate the Euclidean distance between the environmental feature information and each cluster cluster; determine the cluster cluster with the smallest Euclidean distance as the target cluster cluster, and cluster according to the target cluster The cluster determines the corresponding target application and recommends it.

In one embodiment, the collection unit is specifically configured to: start to calculate the time value, collect multi-dimensional features when the application is started as a sample; when the time value reaches the preset time cumulatively, establish a sample library of the collected samples.

Please refer to FIG. 3, which is a schematic block diagram of a quick application recommendation device provided by an embodiment of the present application. Specifically, the quick application recommendation device 300 includes an acquisition unit 31, a processing unit 32, an acquisition unit 33, and a determination unit 34.

The collection unit 31 is used to collect multi-dimensional features when the fast application is started as a sample, and establish a sample library.

When the user starts the fast application, the collection unit 31 will correspondingly collect the multi-dimensional features when the fast application is started. As a sample, the multi-features may include, but are not limited to, the startup time when the fast application is started, the startup geographic location, and For the application name of the application, etc., the collection unit 31 may collect samples within a preset time to establish a sample library. In an embodiment, the preset time may be 7 days or 14 days, and so on.

In some embodiments, the collection unit 31 is specifically configured to start calculating a time value and collect multi-dimensional features when the application is started as a sample; when the time value reaches the preset time cumulatively, the collected sample is used to establish a sample library.

The processing unit 32 is configured to perform clustering processing on the samples in the sample library to obtain a target clustering result.

Based on this, the processing unit 32 can cluster the samples in the sample library according to specific features through a cluster analysis algorithm, and put samples with similar specific features into corresponding sets to obtain multiple different sets, and Multiple different sets are determined as the target clustering result.

The obtaining unit 33 is configured to obtain current environmental characteristic information when a quick application recommendation instruction is detected.

Wherein, when the user opens the quick application list, the electronic device needs to obtain multiple quick application icons to display in the quick application list. In the prior art, the quick application icons recently used by the user are displayed on the quick application according to the order of use time In the list, this mechanical arrangement will cause inconvenience to users. In this solution, when the user opens the quick application list, a quick application recommendation instruction will be generated, and when the acquisition unit 33 detects the quick application recommendation instruction, it will obtain the current environmental feature information accordingly. The environmental feature information is that the user is currently in The scene information, such as the current time and current location, etc. It should be noted that the environmental feature information may correspond to the specific feature used for clustering.

The determining unit 34 is configured to compare the environmental feature information with the target clustering result, determine the corresponding target quick application, and recommend it.

Among them, since the environmental feature information corresponds to the specific feature of the clustering process, different sets of the environmental feature information and the target clustering result after the clustering process may have corresponding similarity information, corresponding, The determining unit 34 determines the set with the highest similarity as the target set, and acquires multiple samples distributed in the target set, extracts the application names of the fast apps in the multiple samples, and determines multiple target fast apps according to the application name and Appear in the list of quick apps for recommendations.

In an embodiment, the determining unit 34 may count the number of times of repeated application names, sort multiple target fast apps according to the counted number from high to low, and perform display recommendation.

In some embodiments, the determining unit 34 is specifically configured to calculate the Euclidean distance between the environmental feature information and each cluster cluster; determine the cluster cluster with the smallest Euclidean distance as the target cluster cluster, and cluster according to the target cluster The cluster determines the corresponding target application and recommends it.

Reference may also be made to FIG. 4, which is another schematic diagram of another module for a quick application recommendation device provided by an embodiment of the present application. The quick application recommendation device 300 may further include:

The processing unit 32 may include a parsing subunit 321 and a processing subunit 322.

Further, the analysis subunit 321 is configured to analyze each sample in the sample library according to the clustering model, and generate a corresponding cluster point for each sample. The processing subunit 322 is configured to perform clustering processing on each clustering point according to the clustering model to obtain the target clustering result.

In some embodiments, the processing subunit 322 is specifically configured to perform convergence processing on the clustering points according to the clustering model to obtain multiple converging clustering clusters, where the clustering cluster is composed of multiple converging clustering points ; Determine multiple clustering clusters as the target clustering result.

An embodiment of the present application also provides an electronic device. Referring to FIG. 5, the electronic device 500 includes a processor 501 and a memory 502. The processor 501 and the memory 502 are electrically connected.

The processor 500 is the control center of the electronic device 500, which uses various interfaces and lines to connect the various parts of the entire electronic device, executes or loads the computer program stored in the memory 502, and calls the data stored in the memory 502 to execute The electronic device 500 performs various functions and processes data to perform overall monitoring of the electronic device 500.

The memory 502 can be used to store software programs and modules. The processor 501 runs computer programs and modules stored in the memory 502 to execute various functional applications and data processing. The memory 502 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, computer programs required by at least one function (such as a sound playback function, an image playback function, etc.), etc .; the storage data area may store Data created by the use of electronic devices, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 502 may further include a memory controller to provide the processor 501 with access to the memory 502.

In the embodiment of the present application, the processor 501 in the electronic device 500 will load the instructions corresponding to the process of one or more computer programs into the memory 502 according to the following steps, and the processor 501 executes and stores the instructions in the memory 502 The computer program in, which realizes various functions, is as follows:

In some embodiments, when performing clustering processing on the samples in the sample library to obtain a target clustering result, the processor 501 may specifically perform the following steps:

Analyze each sample in the sample library according to the clustering model, and generate a corresponding clustering point for each sample;

Perform clustering processing on each clustering point according to the clustering model to obtain the target clustering result.

In some embodiments, when performing clustering processing on each clustering point according to the clustering model to obtain a target clustering result, the processor 501 may specifically perform the following steps:

Performing convergence processing on the clustering points according to the clustering model to obtain multiple converging clustering clusters, the clustering cluster being composed of multiple converging clustering points;

Multiple convergent clusters are determined as the target clustering result.

In some embodiments, when comparing the environment feature information with the target clustering result to determine the corresponding target application and recommend it, the processor 501 may specifically perform the following steps:

Calculating the Euclidean distance between the environmental feature information and each cluster;

The cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster, and the corresponding target quick application is determined and recommended according to the target cluster cluster.

In some embodiments, before collecting the multi-dimensional features when the fast application is started as a sample and establishing a sample library, the processor 501 may further specifically perform the following steps:

When it is detected that the application is opened, the corresponding name attribute of the currently opened application is obtained;

Determine whether the name attribute is a preset name attribute;

When it is determined that the name attribute is a preset name attribute, it is determined that the currently opened application is a fast application, and a step of collecting multi-dimensional features when the fast application is started is taken as a sample and establishing a sample library.

In some embodiments, when determining whether the name attribute is a preset name attribute, the processor 501 may specifically perform the following steps:

Extract keyword information in the name attribute;

Determine whether the keyword information matches the preset keyword information;

When it is determined that the keyword information matches the preset keyword information, it is determined that the name attribute is a preset name attribute;

When it is determined that the keyword information does not match the preset keyword information, it is determined that the name attribute is not the preset name attribute.

In some embodiments, the processor 501 may specifically perform the following steps when collecting the multi-dimensional features when the fast application is started as a sample and establishing a sample library:

Start to calculate the time value and collect the multi-dimensional features when the fast application is started as a sample;

When the accumulated time value reaches the preset time, the collected samples are established into a sample library.

Please refer to FIG. 6 together. In some embodiments, the electronic device 500 may further include: a display 503, a radio frequency circuit 504, an audio circuit 505, and a power supply 506. Among them, the display 503, the radio frequency circuit 504, the audio circuit 505, and the power supply 506 are electrically connected to the processor 501, respectively.

The display 503 can be used to display information input by the user or provided to the user and various graphical user interfaces, which can be composed of graphics, text, icons, video, and any combination thereof. The display 503 may include a display panel. In some embodiments, the display panel may be configured in the form of a liquid crystal display (Liquid Crystal) (LCD) or an organic light-emitting diode (Organic Light-Emitting Diode, OLED).

The radio frequency circuit 504 may be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other electronic devices through wireless communication, and to transmit and receive signals with network devices or other electronic devices.

The audio circuit 505 can be used to provide an audio interface between a user and an electronic device through speakers and microphones.

The power supply 506 can be used to power various components of the electronic device 500. In some embodiments, the power supply 506 may be logically connected to the processor 501 through a power management system, so as to implement functions such as charging, discharging, and power management through the power management system.

Although not shown in FIG. 6, the electronic device 500 may further include a camera, a Bluetooth module, etc., which will not be repeated here.

An embodiment of the present application further provides a storage medium that stores a computer program, and when the computer program is run on a computer, the computer is allowed to execute the recommended method of fast application in any of the foregoing embodiments, such as: fast collection Use the multi-dimensional feature when the application is turned on as a sample, and establish a sample library; cluster the samples in the sample library to obtain the target clustering result; when the fast application recommendation instruction is detected, obtain the current environmental feature information; according to the environment The feature information is compared with the target clustering result, and the corresponding target quick application is determined and recommended.

In the embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read Only Memory, ROM,), or a random access memory (Random Access Memory, RAM), etc.

In the above embodiments, the description of each embodiment has its own emphasis. For a part that is not detailed in an embodiment, you can refer to related descriptions in other embodiments.

It should be noted that, for the fast application recommendation method of the embodiments of the present application, ordinary testers in the art can understand that all or part of the process of implementing the fast application recommendation method of the embodiments of the present application can be controlled by a computer program. Hardware, the computer program can be stored in a computer-readable storage medium, such as stored in the memory of the electronic device, and executed by at least one processor in the electronic device, the execution process can include such as fast The flow of the embodiment of the recommended method of application. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, or the like.

For the fast application recommendation device of the embodiment of the present application, each functional module may be integrated into one processing chip, or each module may exist alone physically, or two or more modules may be integrated into one module. The above integrated modules may be implemented in the form of hardware or software function modules. If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium, such as a read-only memory, magnetic disk, or optical disk.

The above describes a fast application recommendation method, device, storage medium, and electronic equipment provided by the embodiments of the present application in detail. Specific examples are used in this article to explain the principles and implementation manners of the present application. The description is only used to help understand the method and the core idea of this application; meanwhile, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation mode and application scope, in summary, The content of this specification should not be construed as limiting the application.

Claims

A fast application recommendation method, which includes:

Collect the multi-dimensional features when the fast application is started as a sample, and establish a sample library;

Performing clustering processing on the samples in the sample library to obtain the target clustering result;

When the recommended instruction for quick application is detected, the current environmental characteristic information is obtained;

Based on the comparison between the environmental characteristic information and the target clustering result, the corresponding target quick application is determined and recommended.
The fast application recommendation method according to claim 1, wherein the step of clustering the samples in the sample library to obtain a target clustering result includes:

Analyze each sample in the sample library according to the clustering model, and generate a corresponding clustering point for each sample;

Perform clustering processing on each clustering point according to the clustering model to obtain the target clustering result.
The fast application recommendation method according to claim 2, wherein the step of clustering each clustering point according to a clustering model to obtain a target clustering result includes:

Performing convergence processing on the clustering points according to the clustering model to obtain multiple converging clustering clusters, the clustering cluster being composed of multiple converging clustering points;

Multiple convergent clusters are determined as the target clustering result.
The method for recommending a fast application according to claim 3, wherein the step of determining the corresponding target fast application and recommending by comparing the environmental feature information with the target clustering result includes:

Calculating the Euclidean distance between the environmental feature information and each cluster;

The cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster, and the corresponding target quick application is determined and recommended according to the target cluster cluster.
The method for recommending a quick application according to claim 1, wherein the step of collecting the multi-dimensional features when the quick application is started as a sample and establishing a sample library further comprises:

When it is detected that the application is opened, the corresponding name attribute of the currently opened application is obtained;

Determine whether the name attribute is a preset name attribute;

When it is determined that the name attribute is a preset name attribute, it is determined that the currently opened application is a fast application, and a step of collecting multi-dimensional features when the fast application is started is taken as a sample and establishing a sample library.
The quick application recommendation method according to claim 5, wherein the step of determining whether the name attribute is a preset name attribute includes:

Extract keyword information in the name attribute;

Determine whether the keyword information matches the preset keyword information;

When it is determined that the keyword information matches the preset keyword information, it is determined that the name attribute is a preset name attribute;

When it is determined that the keyword information does not match the preset keyword information, it is determined that the name attribute is not the preset name attribute.
The method for recommending a fast application according to claim 1, wherein the step of collecting multi-dimensional features when the fast application is started as a sample and establishing a sample library includes:

Start to calculate the time value and collect the multi-dimensional features when the fast application is started as a sample;

When the accumulated time value reaches the preset time, the collected samples are established into a sample library.
A fast application recommendation device, which includes:

The collection unit is used to collect multi-dimensional features when the fast application is started as a sample, and establish a sample library;

A processing unit, configured to perform clustering processing on the samples in the sample library to obtain a target clustering result;

An obtaining unit, configured to obtain current environmental characteristic information when a quick application recommendation instruction is detected;

The determining unit is used to compare the environment feature information with the target clustering result, determine the corresponding target quick application and make recommendations.
The quick application recommendation device according to claim 8, wherein the processing unit comprises:

The analysis subunit is used to analyze each sample in the sample library according to the clustering model, and generate a corresponding cluster point for each sample;

The processing subunit is used to perform clustering processing on each clustering point according to the clustering model to obtain the target clustering result.
The quick application recommendation device according to claim 9, wherein the processing subunit is specifically used for:

Performing convergence processing on the clustering points according to the clustering model to obtain multiple converging clustering clusters, the clustering cluster being composed of multiple converging clustering points;

Multiple convergent clusters are determined as the target clustering result.
The quick application recommendation device according to claim 10, wherein the determination unit is specifically used to:

Calculating the Euclidean distance between the environmental feature information and each cluster;

The cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster, and the corresponding target quick application is determined and recommended according to the target cluster cluster.
The quick application recommendation device according to claim 8, wherein the collection unit is specifically used for:

Start to calculate the time value and collect the multi-dimensional features when the fast application is started as a sample;

When the accumulated time value reaches the preset time, the collected samples are established into a sample library.
A storage medium on which a computer program is stored, wherein, when the computer program is run on a computer, the computer is caused to execute the recommended method of fast application according to claim 1.
An electronic device includes a processor and a memory, and the memory has a computer program, wherein the processor is used to perform steps by calling the computer program:

Collect the multi-dimensional features when the fast application is started as a sample, and establish a sample library;

Performing clustering processing on the samples in the sample library to obtain the target clustering result;

When the recommended instruction for quick application is detected, the current environmental characteristic information is obtained;

Based on the comparison between the environmental characteristic information and the target clustering result, the corresponding target quick application is determined and recommended.
The electronic device of claim 14, wherein the processor is used to execute the steps by calling the computer program:

Analyze each sample in the sample library according to the clustering model, and generate a corresponding clustering point for each sample;

Perform clustering processing on each clustering point according to the clustering model to obtain the target clustering result.
The electronic device according to claim 15, wherein the processor is used to execute the steps by calling the computer program:

Performing convergence processing on the clustering points according to the clustering model to obtain multiple converging clustering clusters, the clustering cluster being composed of multiple converging clustering points;

Multiple convergent clusters are determined as the target clustering result.
The electronic device of claim 16, wherein the processor is configured to execute the steps by calling the computer program:

Calculating the Euclidean distance between the environmental feature information and each cluster;

The cluster cluster with the smallest Euclidean distance is determined as the target cluster cluster, and the corresponding target quick application is determined and recommended according to the target cluster cluster.
The electronic device according to claim 14, wherein the processor is further used to execute the step by calling the computer program:

When it is detected that the application is opened, the corresponding name attribute of the currently opened application is obtained;

Determine whether the name attribute is a preset name attribute;

When it is determined that the name attribute is a preset name attribute, it is determined that the currently opened application is a fast application, and a step of collecting multi-dimensional features when the fast application is started is taken as a sample and establishing a sample library.
The electronic device of claim 18, wherein the processor is configured to execute the steps by calling the computer program:

Extract keyword information in the name attribute;

Determine whether the keyword information matches the preset keyword information;

When it is determined that the keyword information matches the preset keyword information, it is determined that the name attribute is a preset name attribute;

When it is determined that the keyword information does not match the preset keyword information, it is determined that the name attribute is not the preset name attribute.
The electronic device of claim 14, wherein the processor is used to execute the steps by calling the computer program:

Start to calculate the time value and collect the multi-dimensional features when the fast application is started as a sample;

When the accumulated time value reaches the preset time, the collected samples are established into a sample library.