CN107491991A - Based on the man-machine recognition methods rocked and apply its advertisement placement method and system - Google Patents
Based on the man-machine recognition methods rocked and apply its advertisement placement method and system Download PDFInfo
- Publication number
- CN107491991A CN107491991A CN201710698102.9A CN201710698102A CN107491991A CN 107491991 A CN107491991 A CN 107491991A CN 201710698102 A CN201710698102 A CN 201710698102A CN 107491991 A CN107491991 A CN 107491991A
- Authority
- CN
- China
- Prior art keywords
- client
- man
- machine
- content
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of based on the man-machine recognition methods rocked, it includes:The request that client is sent is received, gathers the body dynamics information of client, according to the motion feature model pre-set, man-machine identification is carried out to the client;Wherein, the motion feature model is:If obtained according to dry run sample training, human manipulation and the grader of machine operation.The invention also discloses a kind of advertisement putting control method based on man-machine identification and the advertisement delivery system based on man-machine identification.
Description
Technical field
It is more particularly to a kind of based on the man-machine recognition methods rocked the present invention relates to technical field of network multimedia, and should
With its advertisement placement method and system.
Background technology
The charging that moving advertising transaction is mainly consumed using equipment as unit, such as CPC is (according to pointing device number meter
Take), CPM (according to the charging of exposure sources number), CPA (according to the charging of activation equipment number).As advertisement is paid increasingly to movement
End tilts, the true degree more and more higher of plan of in the market virtual unit.Existing anti-cheating method be mostly based on device identification and its
Derivative means are judged, but profit is only capable of accomplishing ex-post analysis in this way, it is impossible to accomplish Prior Control.
The content of the invention
The APP on many smart mobile phones has the function of shaking at present, and social or participation activity is carried out by shaking.
Inventor expects suddenly:The action shaken is that the mankind could realize, can be carried out using (i.e. equipment rock) is shaken
Man-machine identification, identifies virtual unit.
According to present invention one side, present invention offer is a kind of based on the man-machine recognition methods rocked, and it includes:
The request that client is sent is received,
The body dynamics information of client is gathered,
According to the motion feature model pre-set, man-machine identification is carried out to the client;Wherein, the motion is special
Levying model is:If obtained according to dry run sample training, human manipulation and the grader of machine operation.
Preferably, the body dynamics information is included in motion track information, direction of motion information and motion velocity information
One or more.
Preferably, the body dynamics information is obtained by the sensor built in client.
Preferably, the sensor built in the client includes one kind in acceleration transducer, gyroscope and magnetometer
It is or a variety of.
The present inventor and then a kind of interesting, easy received advertisement putting control method of offer, it carries people
Machine identification function, Prior Control can be accomplished, not only save tranaction costs, moreover it is possible to avoid invalid dispensing occupied bandwidth.
According to second aspect of the present invention, the present invention provides a kind of advertisement putting control method based on man-machine identification, its
Including:
Advertisement playing request is received, plays man-machine identification suggestion content;
Receive the body dynamics information of the first operation from client collection, being triggered according to the suggestion content;
According to the motion feature model pre-set, man-machine identification is carried out to the client;Wherein, the motion is special
Levying model is:If obtained according to dry run sample training, human manipulation and the grader of machine operation;
When the recognition result of the first operation is less than threshold value, ad content is launched to the client.
Preferably, the body dynamics information is included in motion track information, direction of motion information and motion velocity information
One or more.
Preferably, the body dynamics information is obtained by the sensor built in client.
Preferably, the sensor built in the client includes one kind in acceleration transducer, gyroscope and magnetometer
It is or a variety of.
Preferably, the prompting includes semantic prompting and/or voice message.
Preferably, first operation is to rock client according to the semanteme of the ad content.
Alternatively, when receiving the advertisement playing request, the portion material of the ad content can be preloaded.
Alternatively, when the recognition result of the first operation is less than threshold value, the ad content of preloading is played.
According to third aspect of the present invention, the present invention provides a kind of advertisement delivery system based on man-machine identification, and it includes:
Authentication unit, verification tip is sent to client, the motion for gathering the first operation triggered according to suggestion content is special
Reference is ceased, and man-machine identification is carried out to the triggering main body of the described first operation;
Advertising content unit, the material of ad content is stored, ad content is launched according to the recognition result of authentication unit.
Preferably, the prompting includes semantic prompting and/or voice message.
Preferably, first operation is to rock client according to the semanteme of the suggestion content.
Preferably, the authentication unit includes:
Acquisition module, for the body dynamics information of the first operation triggered from client collection according to suggestion content;With
Identification module, according to the motion feature model pre-set, man-machine identification is carried out to the client;Wherein,
The motion feature model is:If obtained according to dry run sample training, human manipulation and the grader of machine operation.
Preferably, when the recognition result that authentication unit obtains is less than threshold value, triggering advertising content unit is launched in advertisement
Hold.
Preferably, the body dynamics information is included in motion track information, direction of motion information and motion velocity information
One or more.
Preferably, the body dynamics information is obtained by the sensor built in client.
Preferably, the sensor built in the client includes one kind in acceleration transducer, gyroscope and magnetometer
It is or a variety of.
Alternatively, when receiving the advertisement playing request, the portion material of the ad content can be preloaded.
Alternatively, when the recognition result of the first operation is less than threshold value, the ad content of preloading is played.
Brief description of the drawings
The preferred embodiments of the present invention will be described in detail by referring to accompanying drawing below, and make one of ordinary skill in the art more
The above and other feature and advantage of the clear present invention, in accompanying drawing:
Fig. 1 is the flow chart of method according to the second aspect of the invention;
Fig. 2 is the schematic diagram of system according to the third aspect of the invention we;
Fig. 3 is the flow chart of method according to the first aspect of the invention.
Embodiment
In the following description, a large amount of concrete details are given to provide more thorough understanding of the invention.So
And it will be apparent to one skilled in the art that the present invention can be able to without one or more of these details
Implement.In other examples, in order to avoid obscuring with the present invention, do not enter for some technical characteristics well known in the art
Row description.
Turing test (Turingtest) be that figure spirit proposes in nineteen fifty one is on judging whether machine can be thought deeply
Famous experiment, test the intelligence that whether certain machine can show and people is of equal value or cannot be distinguished by.Carrying out turing test is typically
Computer as server automatically generates a problem and answered by user, and this problem can be generated and commented by computer
Sentence, but must only have the mankind to answer, because computer can not answer.
Internet arena is taken an overall view of, inventor has found that the identification technology of biological characteristic is due to being difficult to by mould in research process
It is imitative and crack, when be commonly used in the field of authentication of height confidentiality.Such as fingerprint recognition, iris recognition, recognition of face etc..It is limited
In the hardware resource of smart mobile phone, those recognition methods influence the normal work of other functions of mobile phone due to consuming a large amount of mobile phone resources
Make, thus reduce the effect of Consumer's Experience.
In field of advertisement spotting, advertiser and the specific identity for paying no attention to watching the object of advertisement, advertisement exposure is only focused on
Object whether be the real mankind that can be converted into purchase.More specifically, advertiser pays close attention to whether this mankind is energy
Understand the individual of ad content, such as it is also invalid that advertisement, which plays to the baby of false touch screen,.
Therefore, in an embodiment of the present invention, the behavioural characteristic model of various dimensions by machine learning, can be clustered out,
Subsequently whether can possess biological characteristic by the biological characteristic model come the interactive operation that determining server is currently received, from
And more accurately carry out man-machine identification.The technology applies first purpose in field of advertisement spotting to be to determine that this exposure is
No counting, if it is determined that initiate request for the mankind, then count;Conversely, then disregarding, advertiser need not be this time exposure payment.
From existing by unlike ex-post analysis amendment counting:The method of the present invention can realize Prior Control, i.e., in advertisement putting
Whether the main body for judging to initiate request before is the mankind, so as to avoid wasting the bandwidth of media (advertising service business).
Under normal circumstances, advertisement page is accessed from client, Advertisement Server receives advertisement playing request, jumps to wide
Content page is accused, asked ad content is returned to client.
As shown in Fig. 1~Fig. 2, in the present invention, Advertisement Server is when receiving advertisement playing request, first to client
The suggestion content for man-machine identification is returned, the client of request is initiated according to by the acquisition module collection of authentication unit
Suggestion content and trigger first operation.
The identification module of authentication unit is according to the behavioural characteristic model pre-set, to the triggering master of the described first operation
Body carries out man-machine identification;Wherein, the behavioural characteristic model is:If according to dry run sample training obtain, human manipulation and
The grader of machine operation.
The suggestion content includes voice or semantic prompting, and suggestion content is that one or more mobile phones rock operation.With mesh
Preceding equipment virtual technology, go back None- identified voice or semantic prompting.Such as " please mobile phone is shaken under three ", even if can recognize that
The words, equipment virtual technology can not also realize the action of " please mobile phone is shaken under three ", and the mankind then can easily complete
This action.
Pass through such mode, it is easy to which ground carries out man-machine identification, and great entertaining, acceptance are higher.
When the result of identification is less than default threshold value, it is believed that initiate request for the mankind.Then to the client
Launch ad content.
Certainly, it is artificial defined that fraction belongs to the mankind to belong to the mankind again below threshold value higher than threshold value.For example, artificially set
Determine machine 10 to divide, the mankind be 0 point, then higher than threshold value when be machine.Opposite setting can then obtain opposite result.In order to facilitate table
State, in the present invention, it is machine (virtual unit) that we, which are provided higher than threshold decision,.It will be understood by those skilled in the art that base
In the thought of the present invention, term " be higher than threshold value " refers to be judged as closer machine, and is not limited to being higher than mathematically.Accordingly
Ground, term " being less than threshold value " refer to be judged as closer to the mankind.
In the present invention, can be as needed, train behavioural characteristic model using known various methods.
In feature extraction phases, by carrying out a series of data analysis and process to primitive behavior information, from raw line
To extract satisfactory characteristic in information, reaching the multiple behavior of rocking of different user can be identified as conforming to
The characteristic not required, and available for the tagsort of next stage.
The operation data of equipment can be extracted in database:Including facility information and behavioural information.
In facility information, browsing by which version number when browser information can be corresponding operation sample triggering
Device, operating system can represent corresponding to operation sample triggering when be by which kind of operating system, such as android is still
Windows etc., hardware information can represent corresponding to No. MEI of mobile terminal of operation sample when being triggered, or computer
The information such as IP address.
In behavioural information, the information of acceleration transducer, gyroscope and magnetometer record can be used as primitive behavior
Information.Certainly, it is stored with above- mentioned information type incessantly in the database of server.For the primitive behavior obtained in slave unit
Information also needs to carry out feature extraction, and this step is feature extraction phases.
Extraction rock feature method have it is a variety of.For example, can be by building three-dimensional acceleration coordinate system (acceleration sky
Between), and connect the original of user in acceleration space in temporal sequence and rock data, exist so as to obtain the behavior of rocking of user
" shape " in acceleration space.
This step is specially:S21, Sloshing equation S is built, inputs the primitive behavior when user rocks the client
Information, the intuitionistic feature that the user is rocked to the client is converted into and can carry out the characteristic function f of sort operation, described
Characteristic function f expression formulas are:F=s (u (xt, yt, zt));
Wherein, xtWhen rocking the client for the user, in time point t, in the x side of three-dimensional acceleration coordinate system
To acceleration;
ytWhen rocking the client for the user, in time point t, in the y directions of three-dimensional acceleration coordinate system
Acceleration;
ztWhen rocking the client for the user, in time point t, in the z directions of three-dimensional acceleration coordinate system
Acceleration;
S22, solution calculating is carried out to the characteristic function f, obtained result of calculation is the S2 behavioural characteristic number
According to.
Sloshing equation is required to export unique and stable user and rocks feature, and needs that there is relatively low calculating to answer
Miscellaneous degree and higher transformation efficiency.Using the Sloshing equation for meeting condition in this area in the present invention, after conversion, shaken
Dynamic data representation figure.
Characteristic function f can be obtained by a variety of methods, only lift two herein, those skilled in the art can use known
Any method obtains characteristic function f.
A. three-dimensional acceleration space is built, and connects the user's in the three-dimensional acceleration space in temporal sequence
It is original to rock data, obtain user and rock " shape " of the behavior in the three-dimensional acceleration space;
Calculate the geometric center c that the user rocks " shape " of the behavior in the three-dimensional acceleration space, while with
Machine chooses the N number of acceleration information { a of the user1, a2..., aN, calculate each acceleration information aiWith c in the three-dimensional acceleration
The Euclidean distance d spent in spacei=| aiC |, obtain N number of Euclidean distance { d1, d2..., dN};By N number of Europe it is several in
Obtain distance { d1, d2..., dNM are divided into apart from section { (d1, d2), (d2, d3) ..., (dM, dM+1)};Count each distance
Section (di, di+1) frequency wi, obtain the M frequency { w apart from section1, w2..., wM};By each frequency apart from section obtained
Rate { w1, w2..., wM, generating probability distribution function pn(d)=wi, di< d < di+1, turn into the characteristic function f.
B. acceleration space is built, when the acceleration space is that the user rocks the client, in different time
Acceleration information caused by point;
The user N is randomly selected to acceleration information { (b1, e1), (b2, e2) ..., (bN, eN), calculate each pair acceleration
Euclidean distance d of the data in the acceleration spacei=| biei|, obtain N number of Euclidean distance { d1, d2...,
dN};By N number of Euclidean distance { d1, d2..., dNM are divided into apart from section { (d1, d2), (d2, d3) ..., (dM,
dM+1)};Statistics is each apart from section (di, di+1) frequency wi, obtain the M frequency { w apart from section1, w2..., wM};By obtaining
Each frequency { the w apart from section obtained1, w2..., wM, generating probability distribution function pn(d)=wi, di< d < di+1, turn into institute
State characteristic function f.
It is special in the behavior for extracting operation sample by gathering the primitive behavior information of compulsory exercise (prompt action) extensively
After levying data, speed and operation degree of randomness can be rocked according to the operation of these operation samples, if to the dry run sample
Carry out pre-filtering.Wherein, operate translational speed represent operation sample track translational speed, if operation translational speed it is too fast or
It may be exactly machine behavior that it is short, which to operate traveling time, by person, such as within 100ms, then it is assumed that corresponding operation sample is obvious machine
Device behavior, this operation sample is filtered out.And operate degree of randomness and then represent the situation that the track for operating sample is shaken up and down, example
Such as, an operation sample there is no shake up and down, is also considered as it and belongs to obvious machine behavior, can also be by this operation
Sample filters out.
Realize that the method for training behavioural characteristic model is not limited to this sets of plan of above-mentioned offer in the present invention.This area skill
Art personnel can be needed to find other available schemes according to this thinking based on design, it is only necessary to which satisfaction can recognize that people
Class behavior feature.In the present invention, motion track information, direction of motion information and motion velocity information can be used as row
For the foundation of model.
In certain embodiments of the present invention, avoid period of reservation of number long, can be pre- in play cuing content
The portion material of carrying advertisement content, such as carrying advertisement piece are first-class., can be with once the man-machine identification of suggestion content is verified
Broadcasting advertisement content immediately, with broadcasting, remaining material of continuation carrying advertisement content.Such scheme can be in occupied bandwidth
Balanced between period of reservation of number, obtain a user and experience more preferable solution.
As shown in figure 3, in other embodiments of the present invention, with provided by the present invention based on the man-machine knowledge rocked
Not as main checking means, can be used cooperatively as plug-in unit with other application.
The advantage of the invention is that make use of the difference of the mankind with machine substantially to carry out man-machine identification, equipment is used than pure
Information Authentication is much more accurate.And the characteristics of taking full advantage of advertisement, in the case where not increasing burden for users, realize people
Machine identifies.And the data of more various dimensions are acquired, provide data for follow-up data analysis, it is most important that those dimensions
Data be not related to individual privacy.
The invention is not restricted to above-mentioned embodiment, and various changes can be carried out in the scope of the inventive concept.The present invention
It is illustrated by above-described embodiment, but it is to be understood that, the purpose that above-described embodiment is only intended to illustrate and illustrated,
And it is not intended to limit the invention in described scope of embodiments.In addition it will be appreciated by persons skilled in the art that originally
Invention is not limited to above-described embodiment, according to present invention teach that more kinds of variants and modifications can also be made, these modifications
All fallen within modification within scope of the present invention.Protection scope of the present invention by the appended claims and its
Equivalent scope is defined.
Claims (10)
1. a kind of based on the man-machine recognition methods rocked, it includes:
The request that client is sent is received,
The body dynamics information of client is gathered,
According to the motion feature model pre-set, man-machine identification is carried out to the client;Wherein, the motion feature mould
Type is:If obtained according to dry run sample training, human manipulation and the grader of machine operation.
2. according to the method for claim 1, wherein the body dynamics information includes motion track information, the direction of motion is believed
One or more in breath and motion velocity information.
3. according to the method for claim 2, wherein the body dynamics information is obtained by the sensor built in client.
4. according to the method for claim 3, wherein the sensor built in the client includes acceleration transducer, gyro
One or more in instrument and magnetometer.
5. a kind of advertisement putting control method based on man-machine identification, it includes:
Advertisement playing request is received, plays man-machine identification suggestion content;
Receive the body dynamics information of the first operation from client collection, being triggered according to the suggestion content;
According to the motion feature model pre-set, man-machine identification is carried out to the client;Wherein, the motion feature mould
Type is:If obtained according to dry run sample training, human manipulation and the grader of machine operation;
When the recognition result of the first operation is less than threshold value, ad content is launched to the client.
6. according to the method for claim 5, wherein the prompting includes semantic prompting and/or voice message.
7. a kind of advertisement delivery system based on man-machine identification, it includes:
Authentication unit, verification tip is sent to client, the motion feature for gathering the first operation triggered according to suggestion content is believed
Breath, man-machine identification is carried out to the triggering main body of the described first operation;
Advertising content unit, the material of ad content is stored, ad content is launched according to the recognition result of authentication unit.
8. system according to claim 7, wherein the authentication unit includes:
Acquisition module, for the body dynamics information of the first operation triggered from client collection according to suggestion content;With
Identification module, according to the motion feature model pre-set, man-machine identification is carried out to the client;Wherein, it is described
Motion feature model is:If obtained according to dry run sample training, human manipulation and the grader of machine operation.
9. system according to claim 7, wherein when the recognition result that authentication unit obtains is less than threshold value, trigger advertisement
Content element launches ad content.
10. system according to claim 7, wherein the body dynamics information is obtained by the sensor built in client
.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710698102.9A CN107491991A (en) | 2017-08-15 | 2017-08-15 | Based on the man-machine recognition methods rocked and apply its advertisement placement method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710698102.9A CN107491991A (en) | 2017-08-15 | 2017-08-15 | Based on the man-machine recognition methods rocked and apply its advertisement placement method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107491991A true CN107491991A (en) | 2017-12-19 |
Family
ID=60646238
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710698102.9A Pending CN107491991A (en) | 2017-08-15 | 2017-08-15 | Based on the man-machine recognition methods rocked and apply its advertisement placement method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107491991A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019001558A1 (en) * | 2017-06-29 | 2019-01-03 | 苏州锦佰安信息技术有限公司 | Human and machine recognition method and device |
CN110059794A (en) * | 2018-01-18 | 2019-07-26 | 北京京东金融科技控股有限公司 | Man-machine recognition methods and device, electronic equipment, storage medium |
CN110427737A (en) * | 2019-06-20 | 2019-11-08 | 平安科技(深圳)有限公司 | Man-machine recognition methods, device and the computer equipment of operation behavior |
CN113362070A (en) * | 2021-06-03 | 2021-09-07 | 中国工商银行股份有限公司 | Method, apparatus, electronic device, and medium for identifying operating user |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102654913A (en) * | 2011-03-04 | 2012-09-05 | 谢韬 | Method for selectively delivering advertisement |
CN103152324A (en) * | 2013-01-29 | 2013-06-12 | 北京凯华信业科贸有限责任公司 | User authentication method based on behavior features |
CN106022836A (en) * | 2016-05-27 | 2016-10-12 | 深圳追科技有限公司 | Advertisement promotion method combined with advertiser effect feedbacks |
CN106155298A (en) * | 2015-04-21 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Man-machine recognition methods and device, the acquisition method of behavior characteristics data and device |
CN106776674A (en) * | 2016-10-13 | 2017-05-31 | 上海拓畅信息技术有限公司 | A kind of advertisement delivery system and method |
WO2017101690A1 (en) * | 2015-12-18 | 2017-06-22 | 北京国双科技有限公司 | Advertisement detection method and device |
-
2017
- 2017-08-15 CN CN201710698102.9A patent/CN107491991A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102654913A (en) * | 2011-03-04 | 2012-09-05 | 谢韬 | Method for selectively delivering advertisement |
CN103152324A (en) * | 2013-01-29 | 2013-06-12 | 北京凯华信业科贸有限责任公司 | User authentication method based on behavior features |
CN106155298A (en) * | 2015-04-21 | 2016-11-23 | 阿里巴巴集团控股有限公司 | Man-machine recognition methods and device, the acquisition method of behavior characteristics data and device |
WO2017101690A1 (en) * | 2015-12-18 | 2017-06-22 | 北京国双科技有限公司 | Advertisement detection method and device |
CN106022836A (en) * | 2016-05-27 | 2016-10-12 | 深圳追科技有限公司 | Advertisement promotion method combined with advertiser effect feedbacks |
CN106776674A (en) * | 2016-10-13 | 2017-05-31 | 上海拓畅信息技术有限公司 | A kind of advertisement delivery system and method |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019001558A1 (en) * | 2017-06-29 | 2019-01-03 | 苏州锦佰安信息技术有限公司 | Human and machine recognition method and device |
CN110059794A (en) * | 2018-01-18 | 2019-07-26 | 北京京东金融科技控股有限公司 | Man-machine recognition methods and device, electronic equipment, storage medium |
CN110427737A (en) * | 2019-06-20 | 2019-11-08 | 平安科技(深圳)有限公司 | Man-machine recognition methods, device and the computer equipment of operation behavior |
CN113362070A (en) * | 2021-06-03 | 2021-09-07 | 中国工商银行股份有限公司 | Method, apparatus, electronic device, and medium for identifying operating user |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107491991A (en) | Based on the man-machine recognition methods rocked and apply its advertisement placement method and system | |
CN108537017B (en) | Method and equipment for managing game users | |
CN104519124B (en) | A kind of distribution method and device of virtual resource | |
CN105917404A (en) | Digital personal assistant interaction with impersonations and rich multimedia in responses | |
CN101853259A (en) | Methods and device for adding and processing label with emotional data | |
CN105824799B (en) | A kind of information processing method, equipment and terminal device | |
CN108108996A (en) | Advertisement placement method, device, computer equipment and readable medium in video | |
CN110347872A (en) | Video cover image extracting method and device, storage medium and electronic equipment | |
US20230094558A1 (en) | Information processing method, apparatus, and device | |
CN107483445A (en) | A kind of silent Application on Voiceprint Recognition register method, device, server and storage medium | |
CN110033153A (en) | A kind of pair of information recommendation carries out resource bonusing method, device and equipment | |
CN106611447A (en) | Work attendance method and apparatus | |
CN110084651A (en) | A kind of lottery drawing method based on block chain, device and terminal | |
CN110287399A (en) | Live information processing method, device, electronic equipment and storage medium | |
CN110474944A (en) | Processing method, device and the storage medium of the network information | |
CN106407287A (en) | Multimedia resource pushing method and system | |
CN110366023A (en) | A kind of living broadcast interactive method, apparatus, medium and electronic equipment | |
CN107451185B (en) | Recording method, reading system, computer readable storage medium and computer device | |
CN110276633A (en) | Advertisement placement method, system, equipment and storage medium based on online education | |
CN112860213B (en) | Audio processing method and device, storage medium and electronic equipment | |
CN110384929A (en) | A kind of game interaction method, apparatus, medium and electronic equipment | |
CN110336957A (en) | A kind of video creating method, device, medium and electronic equipment | |
CN110354505A (en) | A kind of online business interaction method, apparatus, medium and electronic equipment | |
CN107704448B (en) | Method and system for acquiring children education resource content | |
CN107545464A (en) | Man-machine recognition methods based on WiFi and apply its advertisement placement method and system |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171219 |