CN109816005A - Application program trade classification method, storage medium and terminal based on CNN - Google Patents
Application program trade classification method, storage medium and terminal based on CNN Download PDFInfo
- Publication number
- CN109816005A CN109816005A CN201910048882.1A CN201910048882A CN109816005A CN 109816005 A CN109816005 A CN 109816005A CN 201910048882 A CN201910048882 A CN 201910048882A CN 109816005 A CN109816005 A CN 109816005A
- Authority
- CN
- China
- Prior art keywords
- homepage
- application program
- pictures
- picture
- trade classification
- 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.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of application program trade classification method, storage medium and terminal based on CNN, it is characterized in that, comprising: obtain the homepage picture of each application program, and the homepage picture that will acquire is divided into the first homepage pictures and the second homepage pictures, wherein, the first homepage pictures include the homepage picture of the first preset quantity；The third homepage pictures of the second preset quantity are extended to by the first homepage pictures that preset enhancing algorithm will acquire；Relationship model is constructed according to deep learning algorithm and the third homepage pictures；Classified according to the Relationship model to the second homepage pictures, to carry out trade classification to the corresponding application program of homepage picture each in the second homepage pictures.In this way, can effectively be classified to picture, by the convolutional neural networks in deep learning, especially deep learning to realize the trade classification to application program.
Description
Technical field
The present invention relates to intelligent terminal technical fields, in particular to application program trade classification method, storage based on CNN
Medium and terminal.
Background technique
APP(application program at present) there is many APP in the market, according to incompletely statistics, the data of APP have close to 500
Ten thousand sections, in these APP, some APP are crucial industry APP, include core data inside the APP of these crucial industries, have
Stringent industry and requirements of the national standard has the requirement that branch trade supervision is carried out to it from State-level.APP is supervised
Pipe, a most basic element task is to carry out trade classification to the APP in APP application market, although major APP applies city
All there is a classification to APP on field, but there is a problem of that classification and the trade classification of country are inconsistent, and the classification of application shop
It is more biased towards in function classification, rather than trade classification.Artificial installation and operation APP one by one is currently also needed, then determines institute again
Belong to industry, efficiency is extremely low.
Thus the prior art could be improved and improve.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the deficiencies of the prior art, providing the application program row based on CNN
Industry classification method, storage medium and terminal, to solve then to determine again there is still a need for manually installed each APP of operation in the prior art
The problem of affiliated industry, low efficiency.
In order to solve the above-mentioned technical problem, the technical solution adopted in the present invention is as follows:
A kind of application program trade classification method based on CNN comprising:
The homepage picture that obtains the homepage picture of each application program, and will acquire be divided into the first homepage pictures and
Second homepage pictures, wherein the first homepage pictures include the homepage picture of the first preset quantity；
The third homepage of the second preset quantity is extended to by the first homepage pictures that preset enhancing algorithm will acquire
Face pictures；
Relationship model is constructed according to deep learning algorithm and the third homepage pictures；
Classified according to the Relationship model to the second homepage pictures, to each master in the second homepage pictures
The corresponding application program of page pictures carries out trade classification.
The application program trade classification method based on CNN, wherein the first homepage pictures include first pre-
If the homepage picture of quantity specifically includes:
The industry type of third preset quantity is chosen, and chooses the application program of the 4th preset quantity under every profession and trade type；
The homepage picture of the application program of the 4th preset quantity under the industry type of the third preset quantity constitutes
One homepage pictures.
The application program trade classification method based on CNN, wherein the preset enhancing algorithm specifically includes:
Picture is rotated by 90 °, 180 degree is rotated, rotates 270 degree, mirror image, translation changes brightness, changes contrast, color
One or more of noise is added in adjustment.
The application program trade classification method based on CNN, wherein described according to deep learning algorithm and the third
Homepage pictures building Relationship model specifically includes:
By third homepage pictures according to preset ratio cut partition be training set, test set and verifying collect；
Training set, test set and verifying collection according to deep learning algorithm and after dividing generate Relationship model.
The application program trade classification method based on CNN, wherein it is described according to deep learning algorithm and divide after
Training set, test set and verifying collection generate Relationship model and specifically include:
Increase deep learning algorithm to after division training set, test set and verifying collection number of run, with reduce test set and
Verify the loss of collection；
When loss minimizes, the Relationship model of generation is saved.
The application program trade classification method based on CNN, wherein it is described according to the Relationship model to second
Homepage pictures are classified, to carry out industry to the corresponding application program of homepage picture each in the second homepage pictures
Classification specifically includes:
Obtain the Relationship model of homepage picture and industry type；
Classified according to the Relationship model to each homepage picture in the second homepage pictures；
Trade classification is carried out according to the classification of each homepage picture, and then to the corresponding application program of each homepage picture.
The application program trade classification method based on CNN, wherein the homepage picture for obtaining each application program
Further include:
The packet name of each application program is obtained, and establishes the homepage picture of each application program and the corresponding relationship of packet name.
The application program trade classification method based on CNN, wherein the deep learning algorithm is LeNet-5 depth
Learning algorithm.
A kind of computer readable storage medium, wherein the computer-readable recording medium storage has one or more
Program, one or more of programs can be executed by one or more processor, to realize described in any one as above
Step in application program trade classification method based on CNN.
A kind of terminal device, wherein include: processor and memory;Being stored on the memory can be by the processing
The computer-readable program that device executes；The processor is realized described in any one as above when executing the computer-readable program
The application program trade classification method based on CNN in step.
The utility model has the advantages that compared with prior art, the present invention provides a kind of application program trade classification side based on CNN
Method, storage medium and terminal, which comprises obtain the homepage picture of each application program, and the homepage that will acquire
Picture is divided into the first homepage pictures and the second homepage pictures, wherein the first homepage pictures include the
The homepage picture of one preset quantity；Second is extended to by the first homepage pictures that preset enhancing algorithm will acquire
The third homepage pictures of preset quantity；Relationship is constructed according to deep learning algorithm and the third homepage pictures
Model；Classified according to the Relationship model to the second homepage pictures, to each in the second homepage pictures
The corresponding application program of homepage picture carries out trade classification.In this way, passing through the convolution in deep learning, especially deep learning
Neural network can effectively classify to picture, to realize the trade classification to application program.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the application program trade classification method preferred embodiment based on CNN provided by the invention.
Fig. 2 is the specific stream of step S300 in a kind of application program trade classification method based on CNN provided by the invention
Cheng Tu.
Fig. 3 is the specific stream of step S400 in a kind of application program trade classification method based on CNN provided by the invention
Cheng Tu.
Fig. 4 is the structure principle chart of terminal device preferred embodiment provided by the invention.
Specific embodiment
The present invention provides trade classification method, storage medium and the terminal of a kind of application program page text, to make this hair
Bright purpose, technical solution and effect are clearer, clear, as follows in conjunction with drawings and embodiments to of the invention further detailed
Explanation.It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
The main information of application program is contained in the application program page, manual sort is also that typically in operation application program
During viewer applications the page, the function and affiliated industry of application program are judged by the information of the page, it is special
It is not homepage, contains the most functions and information of application program, therefore by the picture of application program homepage with regard to base
Instinct judges the affiliated industry of application program.Therefore, the present invention is by obtaining application program for application program automatic running
Homepage is classified in conjunction with machine learning so as to the industry to application program, and application program industry is greatly improved
The efficiency of classification.With reference to the accompanying drawing, by the description of the embodiment, further explanation of the contents of the invention are made.
Fig. 1 is please referred to, Fig. 1 is that a kind of trade classification method of application program page text provided by the invention is preferably implemented
The flow chart of example.The described method includes:
S100, the homepage picture for obtaining each application program, and the homepage picture that will acquire is divided into the first homepage figure
Piece collection and the second homepage pictures, wherein the first homepage pictures include the homepage picture of the first preset quantity.
Specifically, successively each application program can be parsed, to get the packet name and homepage of each application program
The corresponding Activity in face in the present embodiment, mobile phone can be inserted into computer, by sending adb push order, will be applied
Program is installed to mobile phone, and starts application program and corresponding homepage Activity by adb shell-command, has been started
At the rear screencap for calling android system included by adb shell-command, to obtain homepage picture, finally by
The homepage picture that adb pull order will acquire downloads on computer, then terminate application program operation and unloading described in answer
Use program.The mode that application program page picture is obtained in the present invention is different from traditional manual mode of operation, and the present invention passes through
Script can automated execution, such that large-scale application program page picture obtains.
Further, the homepage picture that will acquire is divided into the first homepage pictures and the second homepage pictures,
Wherein, the first homepage pictures include the homepage picture of the first preset quantity.
Specifically, in order to obtain the homepage picture of application program and the corresponding relationship of trade classification, the present invention selects in advance
Take the application program of preparatory quantity to get the image collection of application program trade classification, correspondingly, first homepage
Face pictures include that the homepage picture of the first preset quantity specifically includes:
The industry type of third preset quantity is chosen, and chooses the application program of the 4th preset quantity under every profession and trade type；
The homepage picture of the application program of the 4th preset quantity under the industry type of the third preset quantity constitutes
One homepage pictures.
In this example, 25 industries for comparing concern can be chosen, can be bank, security, fund, insurance, trust,
It is the consumer finance, P2P finance, movement, connection, telecommunications, institutional settings, health care, the energy, education, traffic, journalism media, new
Media, electric business, audio-visual, news reading, service for life, tourism trip, social, camera shooting, other this 25 industries.Further, exist
Each industry selects 200 application programs, and each homepage picture for the application program that will acquire is stored to corresponding row
In industry classified catalogue.That is, the first homepage pictures contain this 25 industries and respectively select under this 25 industries
The homepage picture of 200 application programs.It should be noted that the third preset quantity and the 4th preset quantity can bases
Actual demand limits, here with no restriction.
Further, the homepage picture for obtaining each application program further include:
The packet name of each application program is obtained, and establishes the homepage picture of each application program and the corresponding relationship of packet name.In this way, side
Face is according to the corresponding relationship of picture and packet name after an action of the bowels, the trade information of application program in Lai Gengxin application database.
S200, the second preset quantity is extended to by the first homepage pictures that preset enhancing algorithm will acquire
Third homepage pictures.
Specifically, the first homepage pictures are subjected to data enhancing by preset enhancing algorithm, by each industry point
200 pictures are extended to 100,000 originally in class, so that the third homepage pictures of the second preset quantity are obtained, in this way, this
Invention enhances technology by data, in the lesser situation of sample size, to sample can expand and then be used for deep learning, lead to
The study for crossing small sample solves the problems, such as the mechanized classification of large sample.It should be noted that second preset quantity is here not
It is restricted, in this implementation, preferably 100,000.
Further, the preset enhancing algorithm specifically includes:
Picture is rotated by 90 °, 180 degree is rotated, rotates 270 degree, mirror image, translation changes brightness, changes contrast, color
One or more of noise is added in adjustment.By above-mentioned operation, picture can be extended to desired number, it is convenient
Obtain Relationship model.The present invention enhances technology by manual data collection and classification, by data, lesser in sample size
In the case of, to sample can expand and then be used for deep learning, the study for passing through small sample solves the automation point of large sample
Class problem.
S300, Relationship model is constructed according to deep learning algorithm and the third homepage pictures.
Specifically, convolutional neural networks (Convolutional Neural Networks, CNN) are a kind of comprising convolution
The feedforward neural network (Feedforward Neural Networks) for calculating and having depth structure, is deep learning (deep
Learning one of representative algorithm) can effectively classify to picture, and in the present embodiment, the deep learning is calculated
Method is LeNet-5 deep learning algorithm, it should be noted that above-mentioned deep learning algorithm simultaneously unrestricted, the depth
Practising algorithm can be arranged according to user demand, it is possible to understand that, other CNN algorithms also may be implemented.
Further, due to the not disclosed image set about application program classification, the training set of machine learning is surveyed
Examination collection, verifying collection need manual construction.Correspondingly, referring to figure 2., Fig. 2 is a kind of application journey based on CNN provided by the invention
The specific flow chart of step S300 in sequence trade classification method.It is described according to deep learning algorithm and the third homepage picture
Collection building Relationship model specifically includes:
S301, by third homepage pictures according to preset ratio cut partition be training set, test set and verifying collect；
S302, the training set according to deep learning algorithm and after dividing, test set and verifying collection generate Relationship model.
In the present embodiment, third homepage pictures are divided into training set, test set and verifying according to the ratio of 8:1:1
Collection, in general, data can be divided into training set, test set and verifying collection when training has the machine learning model of supervision,
Division proportion is generally 8:1:1, and by carrying out the divisions of three set to initial data, being to be able to select effect (can be with
It is interpreted as accuracy rate) best, the optimal model of generalization ability.
Further, the training set according to deep learning algorithm and after dividing, test set and verifying collection generate industry and close
It is that model specifically includes:
Increase deep learning algorithm to after division training set, test set and verifying collection number of run, with reduce test set and
Verify the loss of collection；
When loss minimizes, the Relationship model of generation is saved.
In the present embodiment, LeNet-5 deep learning algorithm will be run on the training set of generation, test set, verifying collection, not
Disconnected increase number of run, loss when running 100 times on test set and verifying collection is minimum, the row obtained in this way
Industry relational model is more acurrate.That is, when loss minimizes, then save the Relationship model of generation.
S400, classified according to the Relationship model to the second homepage pictures, to the second homepage figure
Piece concentrates the corresponding application program of each homepage picture to carry out trade classification.
Specifically, the second homepage picture is homepage pictures unselected in S100 step, according to acquisition
The second homepage pictures can classify for picture, that is, remaining application program classification in application shop.Accordingly
, referring to figure 3., Fig. 3 is the tool of step S400 in a kind of application program trade classification method based on CNN provided by the invention
Body flow chart.It is described to be classified according to the Relationship model to the second homepage pictures, to the second homepage figure
Piece is concentrated the corresponding application program of each homepage picture to carry out trade classification and is specifically included:
S401, the Relationship model for obtaining homepage picture and industry type；
S402, classified according to the Relationship model to each homepage picture in the second homepage pictures；
S403, trade classification is carried out according to the classification of each homepage picture, and then to the corresponding application program of each homepage picture.
Specifically, by obtaining the Relationship model of homepage picture and industry type, and according to the Relationship
Model classifies to each homepage picture in the second homepage pictures, further, according to the classification of each homepage picture, from
And trade classification is carried out to the corresponding application program of each homepage picture to realize.Meanwhile picture according to the pre-stored data with
The corresponding relationship of packet name can update the trade information of application program in application database, in this way, can realize to institute
There is the automation trade classification of application program, needs to spend a large amount of APP trade classifications that could manually complete to ask to solve
Topic.It should be noted that the application database is to preset, the independence of data ensure that.
The present invention recycles more mature depth learning technology, divides page pictures by obtaining APP page pictures
Class, and then mechanized classification is carried out to APP, it solves the problems, such as to need to spend a large amount of APP trade classifications that could manually complete, is
Country carries out supervision to APP and provides technical foundation.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage has one
Or multiple programs, one or more of programs can be executed by one or more processor, to realize above-described embodiment
Step in the trade classification method of the application program page text.
The present invention also provides a kind of terminal devices, as shown in Figure 4 comprising at least one processor (processor)
20；Display screen 21；And memory (memory) 22, can also include communication interface (Communications Interface)
23 and bus 24.Wherein, processor 20, display screen 21, memory 22 and communication interface 23 can be completed mutually by bus 24
Between communication.Display screen 21 is set as preset user in display initial setting mode and guides interface.Communication interface 23 can pass
Defeated information.Processor 20 can call the logical order in memory 22, to execute the method in above-described embodiment.
In addition, the logical order in above-mentioned memory 22 can be realized and as only by way of SFU software functional unit
Vertical product when selling or using, can store in a computer readable storage medium.
Memory 22 is used as a kind of computer readable storage medium, and it is executable to may be configured as storage software program, computer
Program, such as the corresponding program instruction of method or module in the embodiment of the present disclosure.Processor 30 is stored in memory by operation
Software program, instruction or module in 22, thereby executing functional application and data processing, i.e. side in realization above-described embodiment
Method.
Memory 22 may include storing program area and storage data area, wherein storing program area can storage program area, extremely
Application program needed for a few function；Storage data area, which can be stored, uses created data etc. according to terminal device.This
Outside, memory 22 may include high-speed random access memory, can also include nonvolatile memory.For example, USB flash disk, movement
Hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory,
RAM), a variety of media that can store program code such as magnetic or disk, are also possible to transitory memory medium.
In addition, a plurality of instruction processing unit in above-mentioned storage medium and mobile terminal loads and the detailed process executed exists
It has been described in detail in the above method, has just no longer stated one by one herein.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of application program trade classification method based on CNN, characterized in that it comprises:
The homepage picture that obtains the homepage picture of each application program, and will acquire be divided into the first homepage pictures and
Second homepage pictures, wherein the first homepage pictures include the homepage picture of the first preset quantity；
The third homepage of the second preset quantity is extended to by the first homepage pictures that preset enhancing algorithm will acquire
Face pictures；
Relationship model is constructed according to deep learning algorithm and the third homepage pictures；
Classified according to the Relationship model to the second homepage pictures, to each master in the second homepage pictures
The corresponding application program of page pictures carries out trade classification.
2. the application program trade classification method based on CNN according to claim 1, which is characterized in that first homepage
Face pictures include that the homepage picture of the first preset quantity specifically includes:
The industry type of third preset quantity is chosen, and chooses the application program of the 4th preset quantity under every profession and trade type；
The homepage picture of the application program of the 4th preset quantity under the industry type of the third preset quantity constitutes
One homepage pictures.
3. the application program trade classification method based on CNN according to claim 1, which is characterized in that the preset increasing
Strong algorithms specifically include:
Picture is rotated by 90 °, 180 degree is rotated, rotates 270 degree, mirror image, translation changes brightness, changes contrast, color
One or more of noise is added in adjustment.
4. the application program trade classification method based on CNN according to claim 1, which is characterized in that described according to depth
Learning algorithm and third homepage pictures building Relationship model specifically include:
By third homepage pictures according to preset ratio cut partition be training set, test set and verifying collect；
Training set, test set and verifying collection according to deep learning algorithm and after dividing generate Relationship model.
5. the application program trade classification method based on CNN according to claim 4, which is characterized in that described according to depth
Training set, test set and verifying collection after learning algorithm and division generate Relationship model and specifically include:
Increase deep learning algorithm to after division training set, test set and verifying collection number of run, with reduce test set and
Verify the loss of collection；
When loss minimizes, the Relationship model of generation is saved.
6. the application program trade classification method based on CNN according to claim 4, which is characterized in that described according to
Relationship model classifies to the second homepage pictures, with corresponding to homepage picture each in the second homepage pictures
Application program carry out trade classification specifically include:
Obtain the Relationship model of homepage picture and industry type；
Classified according to the Relationship model to each homepage picture in the second homepage pictures；
Trade classification is carried out according to the classification of each homepage picture, and then to the corresponding application program of each homepage picture.
7. the application program trade classification method based on CNN according to claim 1, which is characterized in that the acquisition is respectively answered
With the homepage picture of program further include:
The packet name of each application program is obtained, and establishes the homepage picture of each application program and the corresponding relationship of packet name.
8. the application program trade classification method based on CNN according to claim 4, which is characterized in that the deep learning
Algorithm is LeNet-5 deep learning algorithm.
9. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be executed by one or more processor, to realize such as claim 1~8
The step in application program trade classification method described in any one based on CNN.
10. a kind of terminal device characterized by comprising processor and memory;Being stored on the memory can be described
The computer-readable program that processor executes；The processor realizes such as claim 1 when executing the computer-readable program
The step in application program trade classification method described in~8 any one based on CNN.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910048882.1A CN109816005B (en) | 2019-01-18 | 2019-01-18 | Application program industry classification method based on CNN, storage medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910048882.1A CN109816005B (en) | 2019-01-18 | 2019-01-18 | Application program industry classification method based on CNN, storage medium and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109816005A true CN109816005A (en) | 2019-05-28 |
| CN109816005B CN109816005B (en) | 2021-08-03 |
Family
ID=66604617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910048882.1A Active CN109816005B (en) | 2019-01-18 | 2019-01-18 | Application program industry classification method based on CNN, storage medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816005B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222022A (en) * | 2021-05-13 | 2021-08-06 | 支付宝(杭州)信息技术有限公司 | Webpage classification identification method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989112A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Application program classification method and server |
| CN106294902A (en) * | 2015-05-28 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Method, device and the electronic equipment of prediction mobile applications page performance |
| CN106548074A (en) * | 2016-12-09 | 2017-03-29 | 江苏通付盾科技有限公司 | Application program analyzing monitoring method and system |
| CN107391383A (en) * | 2017-08-11 | 2017-11-24 | 上海巍擎信息技术有限责任公司 | The method of testing and test system of a kind of Application Program Interface |
| CN107608877A (en) * | 2017-08-11 | 2018-01-19 | 上海巍擎信息技术有限责任公司 | A kind of automation application program interface method of testing and test system based on machine learning |
| CN107809526A (en) * | 2017-09-28 | 2018-03-16 | 努比亚技术有限公司 | End application sorting technique, mobile terminal and computer-readable recording medium |
| CN109214178A (en) * | 2017-06-30 | 2019-01-15 | 中国电信股份有限公司 | APP application malicious act detection method and device |
-
2019
- 2019-01-18 CN CN201910048882.1A patent/CN109816005B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105989112A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Application program classification method and server |
| CN106294902A (en) * | 2015-05-28 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Method, device and the electronic equipment of prediction mobile applications page performance |
| CN106548074A (en) * | 2016-12-09 | 2017-03-29 | 江苏通付盾科技有限公司 | Application program analyzing monitoring method and system |
| CN109214178A (en) * | 2017-06-30 | 2019-01-15 | 中国电信股份有限公司 | APP application malicious act detection method and device |
| CN107391383A (en) * | 2017-08-11 | 2017-11-24 | 上海巍擎信息技术有限责任公司 | The method of testing and test system of a kind of Application Program Interface |
| CN107608877A (en) * | 2017-08-11 | 2018-01-19 | 上海巍擎信息技术有限责任公司 | A kind of automation application program interface method of testing and test system based on machine learning |
| CN107809526A (en) * | 2017-09-28 | 2018-03-16 | 努比亚技术有限公司 | End application sorting technique, mobile terminal and computer-readable recording medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113222022A (en) * | 2021-05-13 | 2021-08-06 | 支付宝(杭州)信息技术有限公司 | Webpage classification identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109816005B (en) | 2021-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109344262A (en) | Architectonic method for building up, device and storage medium | |
| CN108491866A (en) | Porny identification method, electronic device and readable storage medium storing program for executing | |
| CN102426567A (en) | Graphical editing and debugging system of automatic answer system | |
| CN107592399A (en) | The display methods and mobile terminal of a kind of contact person | |
| CN109739700A (en) | A kind of interface test method and device | |
| CN109816005A (en) | Application program trade classification method, storage medium and terminal based on CNN | |
| CN110489242A (en) | Distributed data calculation method, device, terminal device and storage medium | |
| CN111652327A (en) | Model iteration method, system and computer equipment | |
| CN112801266B (en) | Neural network construction method, device, equipment and medium | |
| CN110362698A (en) | A kind of pictorial information generation method, device, mobile terminal and storage medium | |
| CN111708880A (en) | System and method for identifying class cluster | |
| CN110532448A (en) | Document Classification Method, device, equipment and storage medium neural network based | |
| CN110222286A (en) | Information acquisition method, device, terminal and computer readable storage medium | |
| CN109800808A (en) | A kind of trade classification method, storage medium and the terminal device of application program description | |
| CN109816007A (en) | Trade classification method, storage medium and the terminal device of application program text information | |
| CN110427399A (en) | Real-time data acquisition method, system, device and storage medium | |
| CN105721697A (en) | Mobile phone short message shielding method and system | |
| CN115205677A (en) | Method, device, electronic equipment and computer readable medium for identifying image information | |
| CN107688535A (en) | A kind of mobile device APP performance data display methods and device | |
| CN109726768A (en) | Trade classification method, storage medium and the terminal device of application program page text | |
| CN114492584A (en) | Automatic content grading method for android Chinese application market | |
| CN112948251A (en) | Automatic software testing method and device | |
| CN112926952A (en) | Cloud computing-combined big data office business processing method and big data server | |
| CN110134775A (en) | Question and answer data creation method and device, storage medium | |
| CN112783775A (en) | Special character input testing method and device |
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 |