CN110717108B - Similar mobile application calculation method and device based on feature engineering - Google Patents
Similar mobile application calculation method and device based on feature engineering Download PDFInfo
- Publication number
- CN110717108B CN110717108B CN201910921218.3A CN201910921218A CN110717108B CN 110717108 B CN110717108 B CN 110717108B CN 201910921218 A CN201910921218 A CN 201910921218A CN 110717108 B CN110717108 B CN 110717108B
- Authority
- CN
- China
- Prior art keywords
- similarity
- score
- mobile application
- mobile applications
- mobile
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a similar mobile application calculation method and a similar mobile application calculation device based on feature engineering, wherein the method comprises the following steps: discretizing a data set of the mobile application; extracting effective features from the discretized data set according to preset features, and filtering ineffective features from the discretized data set in an information entropy mode; calculating the similarity of each group of effective characteristics of the two mobile applications, and performing weighted summation to obtain a similar candidate set of the current mobile application; similar mobile applications are obtained from the similar candidate set.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a similar mobile application computing method and device based on feature engineering.
Background
In recent years, with the popularization of smart phone terminals and the rapid development of mobile internet, mobile applications have thoroughly changed the ecological pattern of information dissemination, and have replaced websites/webpages as the main way for netizens to obtain information or services. Meanwhile, mobile applications are also becoming hotbeds for the dissemination of negative information such as pornography and gambling. When a service user finds a certain mobile application that propagates negative information, how to quickly obtain other mobile applications related or similar to the mobile application becomes an important requirement.
Disclosure of Invention
The embodiment of the invention provides a similar mobile application calculation method and device based on feature engineering, which are used for solving the problems in the prior art.
The embodiment of the invention provides a similar mobile application calculation method based on feature engineering, which comprises the following steps:
discretizing a data set of the mobile application;
extracting effective features from the discretized data set according to preset features, and filtering ineffective features from the discretized data set in an information entropy mode;
calculating the similarity of each group of effective characteristics of the two mobile applications, and performing weighted summation to obtain a similar candidate set of the current mobile application;
similar mobile applications are obtained from the similar candidate set.
The embodiment of the invention also provides a similar mobile application computing device based on the characteristic engineering, which comprises:
the data preprocessing module is used for discretizing a data set of the mobile application;
the extraction filtering module is used for extracting effective features from the discretized data set according to preset features and filtering the ineffective features in an information entropy mode;
the weighted summation module is used for calculating the similarity of each group of effective characteristics of the two mobile applications and carrying out weighted summation to obtain a similar candidate set of the current mobile application;
and the result acquisition module is used for acquiring similar mobile applications from the similar candidate set.
The embodiment of the invention also provides a similar mobile application computing device based on feature engineering, which comprises: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the above-described similar mobile application computing method based on feature engineering.
The embodiment of the invention also provides a computer-readable storage medium, wherein an implementation program for information transfer is stored on the computer-readable storage medium, and when the program is executed by a processor, the steps of the similar mobile application computing method based on the feature engineering are implemented.
By adopting the embodiment of the invention, the calculation of similar mobile application is carried out on the current mobile application by screening out the attribute associated with the mobile application, and other mobile applications related to or similar to the mobile application can be quickly obtained.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for computing a similar mobile application based on feature engineering according to an embodiment of the present invention;
FIG. 2 is a diagram of a similar mobile application computing device based on feature engineering according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of a similar mobile application computing device based on feature engineering according to a second embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
According to the embodiment of the invention, a similar mobile application calculation method based on feature engineering is provided, and similar mobile application calculation is carried out on the current mobile application by screening out attributes associated with the mobile application. The benefit of feature engineering is that the computational overhead of similar mobile applications can be reduced on a large scale. We use the K-Nearest Neighbor algorithm (KNN) to find the set of candidate mobile applications that are relevant to the current mobile application. Fig. 1 is a flowchart of a similar mobile application calculation method based on feature engineering according to an embodiment of the present invention, and as shown in fig. 1, the similar mobile application calculation method based on feature engineering according to an embodiment of the present invention specifically includes:
step 101, discretizing a data set of mobile application; specifically, because the source of the integrated mobile application data is different from the standard data processing format, each mobile application attribute is regarded as a corresponding feature, and the attribute value of the feature is discretized, for example: the developer set corresponding to the developer needs to be subdivided.
102, extracting effective features from the discretized data set according to preset features, and filtering ineffective features from the discretized data set in an information entropy mode; the preset characteristics specifically include at least one of the following: ranking of the list in the subcategory of the mobile application, mobile application type, mobile application developer, mobile application operating company, functional points defined by the mobile application.
Due to the fact that a large number of attribute value missing situations exist in real data. Therefore, on the one hand, the effective features are extracted by means of the preset features. On the other hand, some features with invalid attribute values need to be distinguished and filtered in an information entropy mode. For example, when all the features are one value, the information entropy is 0.
103, calculating the similarity of each group of effective characteristics of the two mobile applications, and performing weighted summation to obtain a similar candidate set of the current mobile application;
in step 103, calculating the similarity of each group of valid features of the two mobile applications, and performing weighted summation specifically includes:
step 1, calculating the similarity of each group of effective features of the two mobile applications, wherein if the similarity of the ranking of the list in the subcategory of the two mobile applications is higher than a ranking threshold value, the similarity weight is a first score; if the similarity of the two mobile application types is higher than the type threshold, the similarity weight is a second score; if the similarity between the two mobile application developers is higher than the developer threshold, the similarity weight is a second score, and if the similarity between the two mobile application operating companies is higher than the operating company threshold, the similarity weight is a third score; if the similarity between the function points defined by the two mobile applications is higher than the threshold value of the function points, the similarity weight is a third score; if the similarity between more developers of the two mobile applications is higher than a more developers threshold value, the similarity weight is a fourth score, wherein the first score, the second score, the third score and the fourth score are score ranges, and the first score > the second score > the third score > the fourth score; as shown in table 1.
Table 1 attribute characteristics given by the expert and corresponding priorities
And 2, summing the similarity weights of each group of effective features of the two mobile applications to obtain a final similarity value between the two mobile applications.
Preferably, in step 103, the similarity of each group of valid features of the two mobile applications is calculated through a K-nearest neighbor algorithm, and weighted summation is performed to obtain a similar candidate set of the current mobile application. That is, the K-nearest neighbor algorithm may be utilized to compute a similar candidate set for the current mobile application. Preferably, the Similarity of the attribute values of each dimension of the two mobile applications can be calculated by dot product or Jaccard Similarity and weighted sum is performed.
Step 104, obtaining similar mobile applications from the similar candidate set. The method specifically comprises the following steps: and sorting the mobile applications in the similar candidate set in a descending order according to the weighted summation result, and taking the first K mobile applications as the similar mobile applications obtained by calculation. Wherein, K can be 10 or 20.
Apparatus embodiment one
According to an embodiment of the present invention, a similar mobile application computing device based on feature engineering is provided, and fig. 2 is a schematic diagram of a similar mobile application computing device based on feature engineering according to a first embodiment of the present invention, as shown in fig. 2, specifically including:
a data preprocessing module 20, configured to discretize a data set of a mobile application;
the extraction filtering module 22 is used for extracting effective features from the discretized data set according to preset features and filtering ineffective features in an information entropy mode; the preset characteristics specifically include at least one of the following: ranking of the list in the subcategory of the mobile application, the type of the mobile application, a developer of the mobile application, an operation company of the mobile application and a function point defined by the mobile application;
the weighted summation module 24 is configured to calculate similarity of each group of effective features of the two mobile applications, and perform weighted summation to obtain a similar candidate set of the current mobile application; the weighted summation module 26 is specifically configured to:
calculating the similarity of each group of effective features of the two mobile applications, wherein if the similarity of the ranking of the leaderboard of the two mobile applications is higher than a ranking threshold, the similarity weight is a first score; if the similarity of the two mobile application types is higher than the type threshold, the similarity weight is a second score; if the similarity between the two mobile application developers is higher than the developer threshold, the similarity weight is a second score, and if the similarity between the two mobile application operating companies is higher than the operating company threshold, the similarity weight is a third score; if the similarity between the function points defined by the two mobile applications is higher than the threshold value of the function points, the similarity weight is a third score; if the similarity between more developers of the two mobile applications is higher than a more developers threshold value, the similarity weight is a fourth score, wherein the first score, the second score, the third score and the fourth score are score ranges, and the first score > the second score > the third score > the fourth score; summing the similarity weights of each group of effective features of the two mobile applications to obtain a final similarity value between the two mobile applications;
preferably, the weighted sum module 26 may calculate the similarity of each group of valid features of the two mobile applications through a K-nearest neighbor algorithm, and perform weighted sum to obtain a similar candidate set of the current mobile application.
A result obtaining module 26, configured to obtain similar mobile applications from the similar candidate set.
The result obtaining module 26 is specifically configured to: and sorting the mobile applications in the similar candidate set in a descending order according to the weighted summation result, and taking the first N mobile applications as the similar mobile applications obtained by calculation. Wherein, N may be equal to K, and the first K mobile applications may be taken as similar mobile applications obtained by calculation. Wherein, K can be 10 or 20. .
Example II of the device
An embodiment of the present invention provides a similar mobile application computing apparatus based on feature engineering, as shown in fig. 3, including: a memory 30, a processor 32 and a computer program stored on the memory 30 and executable on the processor 32, the computer program realizing the following method steps when executed by the processor 30:
step 101, discretizing a data set of mobile application; specifically, because the source of the integrated mobile application data is different from the standard data processing format, each mobile application attribute is regarded as a corresponding feature, and the attribute value of the feature is discretized, for example: the developer set corresponding to the developer needs to be subdivided.
102, extracting effective features from the discretized data set according to preset features, and filtering ineffective features from the discretized data set in an information entropy mode; the preset characteristics specifically include at least one of the following: ranking of the list in the subcategory of the mobile application, mobile application type, mobile application developer, mobile application operating company, functional points defined by the mobile application.
Due to the fact that a large number of attribute value missing situations exist in real data. Therefore, on the one hand, the effective features are extracted by means of the preset features. On the other hand, some features with invalid attribute values need to be distinguished and filtered in an information entropy mode. For example, when all the features are one value, the information entropy is 0.
103, calculating the similarity of each group of effective features of the two mobile applications, and performing weighted summation to obtain a similar candidate set of the current mobile application;
in step 103, calculating the similarity of each group of valid features of the two mobile applications, and performing weighted summation specifically includes:
step 1, calculating the similarity of each group of effective features of the two mobile applications, wherein if the similarity of the ranking of the list in the subcategory of the two mobile applications is higher than a ranking threshold value, the similarity weight is a first score; if the similarity of the two mobile application types is higher than the type threshold, the similarity weight is a second score; if the similarity between the two mobile application developers is higher than the developer threshold, the similarity weight is a second score, and if the similarity between the two mobile application operating companies is higher than the operating company threshold, the similarity weight is a third score; if the similarity between the function points defined by the two mobile applications is higher than the threshold value of the function points, the similarity weight is a third score; if the similarity between more developers of the two mobile applications is higher than a more developers threshold value, the similarity weight is a fourth score, wherein the first score, the second score, the third score and the fourth score are score ranges, and the first score > the second score > the third score > the fourth score; as shown in table 1.
Table 2 attribute characteristics given by the expert and corresponding priorities
And 2, summing the similarity weights of each group of effective features of the two mobile applications to obtain a final similarity value between the two mobile applications.
Preferably, in step 103, the similarity of each group of valid features of the two mobile applications is calculated through a K-nearest neighbor algorithm, and weighted summation is performed to obtain a similar candidate set of the current mobile application. That is, the K-nearest neighbor algorithm may be utilized to compute a similar candidate set for the current mobile application. Preferably, the Similarity of the attribute values of each dimension of the two mobile applications can be calculated by dot product or Jaccard Similarity and weighted sum is performed.
Step 104, obtaining similar mobile applications from the similar candidate set. The method specifically comprises the following steps: and sorting the mobile applications in the similar candidate set in a descending order according to the weighted summation result, and taking the first K mobile applications as the similar mobile applications obtained by calculation. Wherein, K can be 10 or 20.
Device embodiment III
The embodiment of the present invention provides a computer-readable storage medium, on which an implementation program for information transmission is stored, and when being executed by a processor 32, the implementation program implements the following method steps:
step 101, discretizing a data set of mobile application; specifically, because the integrated mobile application data source has a certain difference from the standard data processing format, each mobile application attribute is regarded as a corresponding feature, and the attribute value of the feature is discretized, for example: the developer set corresponding to the developer needs to be subdivided.
102, extracting effective features from the discretized data set according to preset features, and filtering ineffective features from the discretized data set in an information entropy mode; the preset characteristics specifically include at least one of the following: ranking of the list in the subcategory of the mobile application, mobile application type, mobile application developer, mobile application operating company, functional points defined by the mobile application.
Due to the fact that a large number of attribute value missing situations exist in real data. Therefore, on the one hand, the effective features are extracted by means of the preset features. On the other hand, some features with invalid attribute values need to be distinguished and filtered in an information entropy mode. For example, when all the features are one value, the information entropy is 0.
103, calculating the similarity of each group of effective features of the two mobile applications, and performing weighted summation to obtain a similar candidate set of the current mobile application;
in step 103, calculating the similarity of each group of valid features of the two mobile applications, and performing weighted summation specifically includes:
step 1, calculating the similarity of each group of effective features of the two mobile applications, wherein if the similarity of the ranking of the list in the subcategory of the two mobile applications is higher than a ranking threshold value, the similarity weight is a first score; if the similarity of the two mobile application types is higher than the type threshold, the similarity weight is a second score; if the similarity between the two mobile application developers is higher than the developer threshold, the similarity weight is a second score, and if the similarity between the two mobile application operating companies is higher than the operating company threshold, the similarity weight is a third score; if the similarity between the function points defined by the two mobile applications is higher than the threshold value of the function points, the similarity weight is a third score; if the similarity between more developers of the two mobile applications is higher than a more developers threshold value, the similarity weight is a fourth score, wherein the first score, the second score, the third score and the fourth score are score ranges, and the first score > the second score > the third score > the fourth score; as shown in table 1.
Table 3 attribute characteristics given by the expert and corresponding priorities
And 2, summing the similarity weights of each group of effective features of the two mobile applications to obtain a final similarity value between the two mobile applications.
Preferably, in step 103, the similarity of each group of valid features of the two mobile applications is calculated through a K-nearest neighbor algorithm, and weighted summation is performed to obtain a similar candidate set of the current mobile application. That is, the K-nearest neighbor algorithm may be utilized to compute a similar candidate set for the current mobile application. Preferably, the Similarity of the attribute values of each dimension of the two mobile applications can be calculated by dot product or Jaccard Similarity and weighted sum is performed.
Step 104, obtaining similar mobile applications from the similar candidate set. The method specifically comprises the following steps: and sorting the mobile applications in the similar candidate set in a descending order according to the weighted summation result, and taking the first K mobile applications as the similar mobile applications obtained by calculation. Wherein, K can be 10 or 20.
The computer-readable storage medium of this embodiment includes, but is not limited to: ROM, RAM, magnetic or optical disks, and the like.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A similar mobile application computing method based on feature engineering is characterized by comprising the following steps:
discretizing a data set of the mobile application;
extracting effective features from the discretized data set according to preset features, and filtering ineffective features from the discretized data set in an information entropy mode;
calculating the similarity of each group of effective features of the two mobile applications, and performing weighted summation to obtain a similar candidate set of the current mobile application, wherein the similarity of the effective features comprises the similarity of the ranking degrees of the list in the subcategory of the mobile applications, and if the similarity of the ranking degrees of the list in the subcategory of the two mobile applications is higher than a ranking threshold, the similarity weight is a first score which is larger than the similarity weights of other effective features;
similar mobile applications are obtained from the similar candidate set.
2. The method of claim 1, wherein obtaining similar mobile applications from the similar candidate set specifically comprises:
and sorting the mobile applications in the similar candidate set in a descending order according to the weighted summation result, and taking the first N mobile applications as the similar mobile applications obtained by calculation.
3. The method according to claim 1, wherein the preset features specifically include at least one of: ranking of the list in the subcategory of the mobile application, mobile application type, mobile application developer, mobile application operating company, functional points defined by the mobile application.
4. The method of claim 1, wherein computing the similarity of each set of valid features for two mobile applications and performing a weighted summation specifically comprises:
calculating the similarity of each group of effective features of the two mobile applications, wherein if the similarity of the two mobile application types is higher than a type threshold value, the similarity weight is a second score; if the similarity between the two mobile application developers is higher than the developer threshold, the similarity weight is a second score, and if the similarity between the two mobile application operating companies is higher than the operating company threshold, the similarity weight is a third score; if the similarity between the function points defined by the two mobile applications is higher than the threshold value of the function points, the similarity weight is a third score; if the similarity between more developers of the two mobile applications is higher than a more developers threshold value, the similarity weight is a fourth score, wherein the first score, the second score, the third score and the fourth score are score ranges, and the second score is larger than the third score and larger than the fourth score;
and summing the similarity weights of each group of effective features of the two mobile applications to obtain a final similarity value between the two mobile applications.
5. The method of claim 1, wherein calculating the similarity of each set of valid features of two mobile applications, and performing weighted summation to obtain a similar candidate set of the current mobile application specifically comprises:
and calculating the similarity of each group of effective characteristics of the two mobile applications through a K nearest neighbor algorithm, and performing weighted summation to obtain a similar candidate set of the current mobile application.
6. A feature engineering based similar mobile application computing apparatus, comprising:
the data preprocessing module is used for discretizing a data set of the mobile application;
the extraction filtering module is used for extracting effective features from the discretized data set according to preset features and filtering the ineffective features in an information entropy mode;
the system comprises a weighted summation module, a comparison module and a comparison module, wherein the weighted summation module is used for calculating the similarity of each group of effective features of two mobile applications, carrying out weighted summation to obtain a similar candidate set of the current mobile application, the similarity of the effective features comprises the similarity of the ranking degrees of the list in the subcategory of the mobile applications, and if the similarity of the ranking degrees of the list in the subcategory of the two mobile applications is higher than a ranking threshold, the similarity weight is a first score which is larger than the similarity weights of other effective features;
and the result acquisition module is used for acquiring similar mobile applications from the similar candidate set.
7. The apparatus of claim 6, wherein the result acquisition module is specifically configured to:
and sorting the mobile applications in the similar candidate set in a descending order according to the weighted sum result, and taking the first N mobile applications as the similar mobile applications obtained by calculation.
8. The apparatus of claim 6, wherein the preset features specifically include at least one of: ranking of the list in the subcategory of the mobile application, the type of the mobile application, a developer of the mobile application, an operation company of the mobile application and a function point defined by the mobile application;
the weighted sum module is specifically configured to:
calculating the similarity of each group of effective characteristics of the two mobile applications, wherein if the similarity of the two mobile application types is higher than a type threshold value, the similarity weight is a second score; if the similarity between the two mobile application developers is higher than the developer threshold, the similarity weight is a second score, and if the similarity between the two mobile application operating companies is higher than the operating company threshold, the similarity weight is a third score; if the similarity between the function points defined by the two mobile applications is higher than the threshold value of the function points, the similarity weight is a third score; if the similarity between more developers of the two mobile applications is higher than a more developers threshold value, the similarity weight is a fourth score, wherein the first score, the second score, the third score and the fourth score are score ranges, and the second score is larger than the third score and larger than the fourth score; summing the similarity weights of each group of effective features of the two mobile applications to obtain a final similarity value between the two mobile applications;
the weighted sum module is specifically configured to: and calculating the similarity of each group of effective characteristics of the two mobile applications through a K nearest neighbor algorithm, and performing weighted summation to obtain a similar candidate set of the current mobile application.
9. A feature engineering based similar mobile application computing apparatus, comprising: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the feature engineering based similar mobile application calculation method of any of claims 1 to 5.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon an information transfer implementing program, which when executed by a processor implements the steps of the feature engineering based similar mobile application computing method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921218.3A CN110717108B (en) | 2019-09-27 | 2019-09-27 | Similar mobile application calculation method and device based on feature engineering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921218.3A CN110717108B (en) | 2019-09-27 | 2019-09-27 | Similar mobile application calculation method and device based on feature engineering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110717108A CN110717108A (en) | 2020-01-21 |
| CN110717108B true CN110717108B (en) | 2022-08-30 |
Family
ID=69211018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910921218.3A Active CN110717108B (en) | 2019-09-27 | 2019-09-27 | Similar mobile application calculation method and device based on feature engineering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110717108B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103810030A (en) * | 2014-02-20 | 2014-05-21 | 北京奇虎科技有限公司 | Application recommendation method, device and system based on mobile terminal application market |
| CN104714959A (en) * | 2013-12-12 | 2015-06-17 | 腾讯科技（深圳）有限公司 | Application query method and application query device |
| CN106599686A (en) * | 2016-10-12 | 2017-04-26 | 四川大学 | Malware clustering method based on TLSH character representation |
| CN107038173A (en) * | 2016-02-04 | 2017-08-11 | 腾讯科技（深圳）有限公司 | Application query method and apparatus, similar application detection method and device |
| CN109446753A (en) * | 2018-09-10 | 2019-03-08 | 平安科技（深圳）有限公司 | Detect method, apparatus, computer equipment and the storage medium of pirate application program |
| CN110209925A (en) * | 2018-10-24 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Using method for pushing, device, computer equipment and storage medium |
-
2019
- 2019-09-27 CN CN201910921218.3A patent/CN110717108B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104714959A (en) * | 2013-12-12 | 2015-06-17 | 腾讯科技（深圳）有限公司 | Application query method and application query device |
| CN103810030A (en) * | 2014-02-20 | 2014-05-21 | 北京奇虎科技有限公司 | Application recommendation method, device and system based on mobile terminal application market |
| CN107038173A (en) * | 2016-02-04 | 2017-08-11 | 腾讯科技（深圳）有限公司 | Application query method and apparatus, similar application detection method and device |
| CN106599686A (en) * | 2016-10-12 | 2017-04-26 | 四川大学 | Malware clustering method based on TLSH character representation |
| CN109446753A (en) * | 2018-09-10 | 2019-03-08 | 平安科技（深圳）有限公司 | Detect method, apparatus, computer equipment and the storage medium of pirate application program |
| CN110209925A (en) * | 2018-10-24 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Using method for pushing, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110717108A (en) | 2020-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271512B (en) | Emotion analysis method, device and storage medium for public opinion comment information | |
| CN111371767B (en) | Malicious account identification method, malicious account identification device, medium and electronic device | |
| US20220230089A1 (en) | Classifier assistance using domain-trained embedding | |
| CN112231555A (en) | Recall method, apparatus, device and storage medium based on user portrait label | |
| CN111078742B (en) | User classification model training method, user classification method and device | |
| CN111612499B (en) | Information pushing method and device, storage medium and terminal | |
| CN113537630B (en) | Training method and device of business prediction model | |
| CN109885834B (en) | Method and device for predicting age and gender of user | |
| CN110852785B (en) | User grading method, device and computer readable storage medium | |
| CN110909222A (en) | User portrait establishing method, device, medium and electronic equipment based on clustering | |
| WO2014176056A2 (en) | Data classification | |
| CN108959236A (en) | Medical literature disaggregated model training method, medical literature classification method and its device | |
| JP2018194919A (en) | Learning program, learning method and learning device | |
| CN113807940A (en) | Information processing and fraud identification method, device, equipment and storage medium | |
| CN110609783A (en) | Method and device for identifying abnormal behavior user | |
| CN114331698A (en) | Risk portrait generation method and device, terminal and storage medium | |
| CN106777285B (en) | Method and device for clustering labels of user communication consumption data | |
| CN110717108B (en) | Similar mobile application calculation method and device based on feature engineering | |
| CN116089616A (en) | Theme text acquisition method, device, equipment and storage medium | |
| CN115393100A (en) | Resource recommendation method and device | |
| CN115423031A (en) | Model training method and related device | |
| CN114373068A (en) | Industry-scene OCR model implementation system, method and equipment | |
| CN113656466A (en) | Policy data query method, device, equipment and storage medium | |
| CN113076450A (en) | Method and device for determining target recommendation list | |
| CN113806636A (en) | Item recommendation method and device, electronic equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |