CN109727058A - User behavior method for detecting abnormality, device, electronic equipment and readable storage medium storing program for executing - Google Patents
User behavior method for detecting abnormality, device, electronic equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109727058A CN109727058A CN201811379243.5A CN201811379243A CN109727058A CN 109727058 A CN109727058 A CN 109727058A CN 201811379243 A CN201811379243 A CN 201811379243A CN 109727058 A CN109727058 A CN 109727058A
- Authority
- CN
- China
- Prior art keywords
- image
- user
- similarity
- preset
- preset template
- 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
Landscapes
- Image Analysis (AREA)
Abstract
Embodiment of the disclosure provides a kind of user behavior method for detecting abnormality, device, electronic equipment and readable storage medium storing program for executing, the described method includes: detecting the pre-set business behavior initiated when user accesses businessman, initiate to request for the shooting of the business conduct to user；User is obtained for the first image of the shooting request shooting；Obtain the preset template image of corresponding the first image；According to the described image feature of preset template image and the first image, the similarity value between the first image and the preset template image is obtained；When the similarity value is lower than default similarity threshold, it is abnormal to determine that the access behavior of the user exists.The similarity between photographed data and preset template image when can access businessman according to user judges the access behavior of user with the presence or absence of efficiency abnormal, that raising is checked extremely.
Description
Technical field
Embodiment of the disclosure be related to detection technique field more particularly to a kind of user behavior method for detecting abnormality, device,
Electronic equipment and readable storage medium storing program for executing.
Background technique
In detection technique field, often through customer manager for access record, Lai Jinhang businessman made by businessman's visit
The authenticity verification of evaluation and test.For example, manager is recorded by the access of customer manager, and the authenticity of examination businessman's evaluation and test, discovery
Its problem of and place to be modified.
However, examining the authenticity of businessman's evaluation and test according to the above method, there are the following problems: when artificial investigation, data base
Number is larger, also, whether the record of customer manager's input system is authentic and valid is difficult to investigate, and visits also more difficult obtain either with or without to shop
It obtains and really feeds back, cause the efficiency of investigation lower.
Summary of the invention
Embodiment of the disclosure provides a kind of user behavior method for detecting abnormality, device, electronic equipment and readable storage medium
Matter, to improve the efficiency checked extremely.
It is according to an embodiment of the present disclosure in a first aspect, providing a kind of user behavior method for detecting abnormality, the method
Include:
It detects the pre-set business behavior initiated when user accesses businessman, the bat for being directed to the business conduct is initiated to user
Take the photograph request；
User is obtained for the first image of the shooting request shooting；
Obtain the preset template image of corresponding the first image；
According to the described image feature of preset template image and the first image, obtain the first image with it is described pre-
Set the similarity value between template image；
When the similarity value is lower than default similarity threshold, it is abnormal to determine that the access behavior of the user exists.
Second aspect according to an embodiment of the present disclosure provides a kind of user behavior abnormal detector, described device
Include:
Shooting request initiation module, the pre-set business behavior initiated when for detecting that user accesses businessman are sent out to user
The shooting risen for the business conduct is requested
First image collection module, for obtaining user for the first image of the shooting request shooting；
Preset template image collection module, for obtaining the preset template image of corresponding the first image；
Similarity value obtains module and obtains for the described image feature according to preset template image and the first image
Take the similarity value between the first image and the preset template image；
First abnormal determining module, for determining the user when the similarity value is lower than default similarity threshold
Access behavior exist it is abnormal.
The third aspect according to an embodiment of the present disclosure, provides a kind of electronic equipment, comprising:
Processor, memory and it is stored in the computer journey that can be run on the memory and on the processor
Sequence, which is characterized in that the processor realizes aforementioned user behavior method for detecting abnormality when executing described program.
Fourth aspect according to an embodiment of the present disclosure provides a kind of readable storage medium storing program for executing, when in the storage medium
Instruction by electronic equipment processor execute when so that electronic equipment is able to carry out aforementioned user behavior method for detecting abnormality.
Embodiment of the disclosure provides a kind of user behavior method for detecting abnormality, device, electronic equipment and readable storage
Medium, which comprises detect the pre-set business behavior initiated when user accesses businessman, initiate to be directed to the industry to user
The shooting of business behavior is requested；User is obtained for the first image of the shooting request shooting；Obtain corresponding the first image
Preset template image；According to the described image feature of preset template image and the first image, the first image is obtained
With the similarity value between the preset template image；When the similarity value is lower than default similarity threshold, described in determination
The access behavior of user exists abnormal.Photographed data when businessman can be accessed according to user, the access behavior for monitoring user is
It is no to there is the efficiency abnormal, raising is checked extremely.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of embodiment of the disclosure, below by the description to embodiment of the disclosure
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only the implementation of the disclosure
Some embodiments of example for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 shows the step flow chart of user behavior method for detecting abnormality in one embodiment of the present disclosure；
Fig. 2 shows the step flow charts of the user behavior method for detecting abnormality in another embodiment of the disclosure；
Fig. 3 shows the structure chart of user behavior abnormal detector in one embodiment of the present disclosure；
Fig. 4 shows the structure chart of the user behavior abnormal detector in another embodiment of the disclosure；
The structure chart for the electronic equipment that one embodiment that Fig. 5 shows the disclosure provides.
Specific embodiment
Below in conjunction with the attached drawing in embodiment of the disclosure, the technical solution in embodiment of the disclosure is carried out clear
Chu is fully described by, it is clear that described embodiment is embodiment of the disclosure a part of the embodiment, rather than whole realities
Apply example.Based on the embodiment in embodiment of the disclosure, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, belong to embodiment of the disclosure protection range.
Embodiment one
Referring to Fig.1, it illustrates the step of user behavior method for detecting abnormality in one embodiment of the present disclosure to flow
Cheng Tu, comprising:
Step 101, it detects the pre-set business behavior initiated when user accesses businessman, initiates to be directed to the business to user
The shooting of behavior is requested.
Embodiment of the disclosure, can when user to shop carries out business operation in the case where user to shop authenticity detects scene
Behavior validation task is accessed to be published to shop to user by application platform, it is specified in businessman shop that validation task requests user to shoot
The image data of scene, for example, sending request shooting to user when user places an order to shop, pays and evaluate operation
The real image data of corresponding points list, payment and evaluation object, user can shoot according to prompt, as corresponding points list is grasped
The photographed scene of work is vegetable image data, and the photographed scene of counterpart expenditure operation is bill, the image data of receipt, and correspondence is commented
The photographed scene of valence operation is the image data of evaluation object, such as environment, vegetable quality, businessman's door head picture number in businessman shop
Image data, the table patch being laid with according to star's poster in, shop check image data etc..
Certainly, in practical applications, pre-set business behavior and corresponding photographed scene be not limited to foregoing description, this public affairs
It is without restriction to this to open embodiment.
Step 102, user is obtained for the first image of the shooting request shooting；
Embodiment of the disclosure, according to foregoing description, after user receives shooting request, according to shooting request shooting pair
The image data of scene is answered as the first image and is uploaded.Certainly, the first image is the specified title as indicator image data,
It is unrelated with sequence.
Wherein, user can select above-mentioned default scene tag to be labeled the first image when shooting image, so as to
It is subsequent to be screened.
Wherein, it is desirable that the first image that user uploads can be static first image, or the first image of dynamic, this
Open embodiment is without restriction to this.
In the embodiment of the present disclosure, after obtaining the first image that user uploads, from the available image primitive letter of first image
Breath is used as detection information, to determine the access behavior of user with the presence or absence of abnormal.
Specifically, image capturing time, location information, capture apparatus information, fingerprint letter are generally comprised in image metamessage
Breath etc..
Certainly, image metamessage is not limited to foregoing description, and the embodiment of the present disclosure is without restriction to this.
Step 103, the preset template image of corresponding the first image is obtained.
In the embodiment of the present disclosure, system is preset at according to label lookup according in corresponding the first image of scene capture in user
In the first image of template, for example, such as star's poster paving in environment in businessman shop, vegetable quality, the first image of businessman's door head, shop
If the first image, table paste first image etc., the first image is as Prototype drawing in the true shop that can be uploaded in advance using businessman
Picture.
Certainly, template image is not limited to foregoing description, and the embodiment of the present disclosure is without restriction to this.
Step 104, according to the described image feature of preset template image and the first image, the first image is obtained
With the similarity value between the preset template image.
In the embodiment of the present disclosure, the first image that user is uploaded in real time is compared with the template image of corresponding scene,
Similarity data are obtained, and judge whether the first image of user's shooting is directed to the true of Same Scene according to similarity data
First image.
Certainly, it can be provided by businessman as template data, be also possible to system setting, for example, star's poster is represented, and
And the template data that businessman provides is also that system is screened by uniform rules, cannot arbitrarily be repaired by businessman after setting
Change, set-up mode and source to template data, the embodiment of the present disclosure is without restriction.
Preferably, step 104 specifically includes:
The preset template image is split as the first picture portion of multiple default sizes by sub-step A1；
Sub-step A2, according to the first image subregion each in preset template image described in described image signature
Weighted value；
Specifically, by taking preset template image is star's poster as an example, template photo will be split as to the block of 3*3, artificially
The weight W [1 ... 9] in each region is set, and ith zone size is denoted as R [w/3, h/3], wherein higher for resolution
The weight of region setting is higher, star's face area and the product area represented or brand region such as on poster, phase
The lower region of resolution is arranged the weighted value of low level-one, and so on for each region be arranged weighted value.
It is to be appreciated that being directed to the division area size of template picture, it can be adjusted according to accuracy of identification, such as want to obtain
High-precision recognition result is obtained, then template image is just divided into small and more region, conversely, big and few region is then divided,
So the mode for dividing region is not limited to the block of the 3*3 of foregoing description, it is without restriction to this embodiment of the present disclosure.
Sub-step A3 is matched the first image with the preset template image by affine transformation, acquisition
With the first image；
Specifically, since the photo angle of shooting there may be inclination, stretching, farther out with preset template photo gap,
In order to preferably be handled, need to carry out carry out affine transformation.Wherein, if material photo (preset template image) has ratio
Obvious yellow, it is necessary first to carry out Edge check, maximum yellow rectangle region be judged, then according to the upper left corner, the right side
Upper angle, three, lower left corner point are positioned, it is corresponding with yellow in template, find out its transformation matrix using affine transformation.
It is successively that three upper left corner, the upper right corner, left comer points are corresponding with template, matrix A and B are found out, and then to picture in its entirety
Carry out affine transformation, it is close and photo is stretched to template photo close to size.
Sub-step A4 will be described according to mapping relations of the first image subregion on the first image of the matching
The second picture portion of multiple default sizes is split as with the first image.
Specifically, the image-region that user after matching shoots is carried out mobile comparison by the division region of corresponding templates image,
I.e. by the method for sliding window, preset template image and user are shot into photo and carry out mobile comparison, so by the first subregion
Corresponding region forms cut zone on matching the first image, corresponding that the first image of matching is divided into multiple default sizes
Second picture portion, if template image is divided into the block of 3*3, then corresponding first image is similarly divided into the area of 3*3
Block, to be compared one by one.
Sub-step A5 is obtained each first similar between each the first image subregion and each second picture portion
Degree；
Specifically, for the first image of ready-portioned template image and user's shooting, the first image that user is shot
Gray processing is carried out according to adaptive Otsu method, it is similar to the maximum of shooting picture using template matching algorithm calculation template picture
It spends S [i].
Template matching algorithm is specific as follows:
Shop photo is arrived for user's shooting, the template photo S [1] ... S [9] of photo generic is found, calculates two
Image is moved to the similarity S [i, j] at position [i, j] in window.
Wherein SD represents the gray value that template gray photo subtracts average value, and OD represents user's gray scale pictures and subtracts average value
Gray value, x ∈ [0,3/w], y ∈ [0, h/3], finally find max (S [i, j]) as template and user shooting photo phase
Like degree.
Wherein, adaptive Otsu method is also referred to as Da-Jin algorithm, is the method for a kind of pair of carrying out image threshold segmentation, it is adaptive
The threshold value of binaryzation is found on ground, 2 part of background and target is divided the image by the gamma characteristic of image, between background and target
Inter-class variance is bigger, illustrates that the difference for constituting 2 parts of image is bigger, when partial target mistake is divided into background or part background mistake point
2 part difference can be all caused to become smaller for target.It by this method obtains template image and to shoot each region of the first image fast
After gray value, using template image as background image, image is shot as foreground image, respectively obtains the inter-class variance in each region
S [i], the maximum similarity as template picture and shooting picture.
Certainly, in practical application, the similarity calculating method between two the first images is not limited to foregoing description, the disclosure
Embodiment does not calculate this.
It is to be appreciated that for template image and shooting the first image request not for different similarity calculating methods
Together, such as characteristics of image, the embodiment of the present disclosure such as resolution ratio, format are without restriction to this.
Sub-step A6 is obtained according to the weighted sum of each first similarity and the weighted value of each the first image subregion
Take the similarity value between the first image and the preset template image.
Specifically, after obtaining template picture and shooting the maximum similarity S [i] of picture, according to S [i] corresponding each mould
The specific weight value in plate region, the final similarity between calculation template picture and shooting picture, i.e., finally by all Prototype drawings
The similarity and weighted value of piece are weighted summation, obtain W=W [i] * S [i], W is as final similarity.
Preferably, the quantity of the first image is multiple；Each first image corresponds to a preset template image；Step
Rapid 104 include:
Sub-step C1, for each the first image, according to the corresponding preset template image of first image and described the
The described image feature of one image obtains the first similarity between the first image and the preset template image；
Specifically, according to the description of above-mentioned steps, user can be requested according to multiple requests when user accesses to shop
First image in multiple shops, each first image, the first image of every kind of requirement corresponds to a preset template image in other words.
Wherein, it by obtaining the characteristics of image of the first image, is compared with preset template image, it is similar to obtain first
Degree.Certainly, characteristics of image is the type according to template image, is determined by image processing method, for example, preset template image
It is portrait figure, then characteristics of image is face characteristic.Therefore, the type embodiment of the present invention of characteristics of image is not limited
System.
Sub-step C2 carries out operation according to preset ratio to corresponding first similarity value of each first image, obtains comprehensive
Close similarity value；
Specifically, the calculation method of comprehensive similarity can be the simple accumulative of multiple similarities, be also possible to according to not
Significance level with the first image is that similarity accounting is arranged in the first image, to the first similarity of multiple first images to it is similar
The product of degree accounting adds up, and obtains comprehensive similarity value, the setting of similarity accounting of the present invention is not subject to concrete restriction.
Step 105, when the similarity value is lower than default similarity threshold, determine that the access behavior of the user exists
It is abnormal.
In the embodiment of the present disclosure, when the similarity value between the first image and preset template image is lower than preset threshold,
Then think to shoot the doubtful falseness of the first image, and then it is abnormal to think that the access behavior of user exists.
Preferably, it according to sub-step C1-C2, step 105, specifically includes:
Sub-step D1 determines the access row of the user when the comprehensive similarity value is lower than default similarity threshold
It is abnormal to exist.
Specifically, according to the description of sub-step C1, when the first image is multiple, by each first image with it is corresponding
The first similarity value that comparison between preset template figure obtains, calculates the comprehensive similarity comprising multiple first similarities
It is abnormal to determine that the access behavior of user exists when comprehensive similarity value is lower than default similarity threshold for value.
In conclusion embodiment of the disclosure provides a kind of user behavior method for detecting abnormality, which comprises inspection
It measures user and accesses the pre-set business behavior initiated when businessman, initiate to request for the shooting of the business conduct to user；It obtains
Family is taken for the first image of the shooting request shooting；Obtain the preset template image of corresponding the first image；According to
The described image feature of preset template image and the first image, obtain the first image and the preset template image it
Between similarity value；When the similarity value is lower than default similarity threshold, determining the access behavior of the user, there are different
Often.The similarity between photographed data and preset template image when can access businessman according to user, judges the access of user
Behavior is with the presence or absence of efficiency abnormal, that raising is checked extremely.
Embodiment two
Referring to Fig. 2, the step of it illustrates user behavior method for detecting abnormality in another embodiment of the disclosure
Flow chart, it is specific as follows.
Step 201, it detects the pre-set business behavior initiated when user accesses businessman, initiates to be directed to the business to user
The shooting of behavior is requested；
This step is identical as step 101, and this will not be detailed here.
Step 202, user is obtained for the first image of the shooting request shooting；
This step is identical as step 102, and this will not be detailed here.
Step 203, the shooting time and location information of the first image are obtained.
In the embodiment of the present disclosure, the geographical position of the shooting of the first image is determined by the location information in image metamessage
It sets, secondly obtains the shooting time information in image metamessage.
It is to be appreciated that enrolling the time point into record, doubtful falseness is thought if including a plurality of record in the short time.
It is to be appreciated that there are chain businessman, using same the first image of door head or poster data, no
It can determine that whether user really accesses wherein specified StoreFront, so needing to be determined by geographical location.
Step 204, according to the shooting time and the location information, the filming frequency of the first image is determined, and/
Or, camera site；
Specifically, the filming frequency of first image can be calculated by shooting time, if comprising a plurality of in the short time
The upload of the first image of the user records, then the access behavior of doubtful user exists abnormal.
Step 205, when the filming frequency or camera site are more than preset threshold, the access behavior of the user is determined
There are exceptions.
Specifically, by the specific location of the first image, the frequency of shooting, this judges whether the first image of shooting is true
It is shot by user to merchant stores, if any of the above-described information in given threshold, thus determines the access behavior of user
There are exceptions, i.e., untrue.
It should be understood that by the distance between the shooting location of user and merchant stores registered address, if the distance
Beyond pre-determined distance, it is that user really shoots to shop that, which can determine the first image not, and the access behavior of user exists abnormal.
Certainly, in practical applications, can be judged jointly in conjunction with much information by the abnormality detection of the first image, it is unlimited
In foregoing description, the embodiment of the present disclosure is without restriction.
Wherein, judge whether the geographical location is less than the distance of setting at a distance from shops is between the labeling position of platform
Threshold value, if being less than the distance threshold of setting, then it is assumed that the access behavior of user exists abnormal.
Preferably, further includes:
Step B1 obtains the image attribute information of the first image.
Specifically, after obtaining the first image of user's shooting, it is true that image is carried out according to the attribute information of the first image
The judgement of property.
It is to be appreciated that attribute information can be for photographing request and distinctive information, such as the fingerprint of the first image is believed
The photographing device information of breath and the first image, for different shooting demands, attribute information can be different, and the disclosure is implemented
Example is without restriction to this.
Step B2 determines the Hamming distance and capture apparatus information of the first image according to the image attribute information；
Specifically, after obtaining the capture apparatus information in the first image, then the first image of history of user upload is obtained
In history capture apparatus information.
Wherein, the first image includes Exif (Exchangeable image file format, exchangeable image file
Format), it is to be set exclusively for the photo of digital camera, can recorde the capture apparatus information of digital photograph.
Preferably, step B2 includes:
Step B21, the detection information include finger print data, using the data fingerprint, obtain the first image
Current finger print vector；
Specifically, in the first image of shooting, each first image is unique recognizable there are one when equipment produces
Coding, which is utilized into the calculated value of pHash, for the pHash finger print data of first image, as first figure
The current finger print vector of picture.
Wherein, pHash is perceptual hash algorithm, is one kind of hash algorithm, main by calculating the first image coding
PHash value, for doing the search work of similar pictures.
Step B22 obtains the history fingerprint vector of preset the first image of history；
Specifically, the user is obtained for the first image of history being transmitted through on current businessman, equally obtains the history first
Unique identifiable coding of image, and calculate its pHash finger print data, as first image of history history fingerprint to
Amount.
Step B23, according to the current finger print vector and the history fingerprint vector, calculate the first image with it is preset
The first image of history between Hamming distance；
Specifically, the Hamming distance between current finger print vector and history fingerprint vector is calculated, wherein Hamming distance indicates
Two (equal length) words correspond to the different quantity in position, we indicate the Hamming distance between two words x, y with d (x, y).To two
A character string carries out XOR operation, and the number that statistical result is 1, then this number is exactly Hamming distance.
Step B3 is less than pre-determined distance threshold value in the Hamming distance, and/or, the capture apparatus information and history are clapped
Take the photograph facility information it is inconsistent when, it is abnormal to determine that the access behavior of the user exists.
Specifically, when calculated Hamming distance is less than pre-determined distance threshold value, then the access behavior of the user is doubtful deposits
In exception.
Specifically, the EXIF information for obtaining current first image, if having with historical device information, i.e. history EXIF information
Variation, then it is assumed that the businessman of user accesses behavior and there is exception.
For example, passing through the variation of EXIF information, it is possible to determine that user may entrust other people to proceed to shop shooting.
Certainly, in practical applications, if user's more exchange device may also lead to the variation of EXIF information.So for
The detection can be set a time threshold and then recognize after that is, user is greater than certain amount using the number that new establishing is shot
For new equipment it is the Default device of user, and it is true to accept the first image that user is shot using the equipment.
It is to be appreciated that obtaining the metamessage of the first image, attribute information and characteristics of image carries out similarity calculation, all
It is judgment basis used in the embodiment of the present disclosure, above-mentioned factor can be used as layer-by-layer judgment method and carry out using can also be only
Use one of those as judgment basis, and be also not necessarily limited to foregoing description for judgment method in practical applications, to this
The embodiment of the present disclosure is without restriction.
It is to be appreciated that the accuracy rate of detection can be higher when the mode in conjunction with multinomial foregoing description carries out abnormality detection.
In conclusion embodiment of the disclosure provides a kind of user behavior method for detecting abnormality, which comprises inspection
It measures user and accesses the pre-set business behavior initiated when businessman, initiate to request for the shooting of the business conduct to user；It obtains
Family is taken for the first image of the shooting request shooting.Obtain the shooting time and location information of the first image；Root
According to the shooting time and the location information, the filming frequency of the first image is determined, and/or, camera site；Described
When filming frequency or camera site are more than preset threshold, it is abnormal to determine that the access behavior of the user exists.It can be according to user
The information obtained in photographed data when accessing businessman judges the access behavior of user with the presence or absence of abnormal, the abnormal investigation of raising
Efficiency improve detection accuracy further, it is also possible to the mode in conjunction with a variety of first image informations carries out abnormality detection.
Embodiment three
Referring to Fig. 3, it illustrates the structure chart of user behavior abnormal detector in one embodiment of the present disclosure,
It is specific as follows.
Shooting request initiation module 301, the pre-set business behavior initiated when for detecting that user accesses businessman, to user
It initiates to request for the shooting of the business conduct；
First image collection module 302, for obtaining user for the first image of the shooting request shooting；
Preset template image collection module 303, for obtaining the preset template image of corresponding the first image；
Similarity value obtains module 304, for the described image feature according to preset template image and the first image,
Obtain the similarity value between the first image and the preset template image；
Preferably, the similarity value obtains module 304, comprising:
First splits submodule, for the preset template image to be split as to the first image point of multiple default sizes
Area；
Weight marks submodule, in the preset template image according to described image signature each described first
The weighted value of picture portion；
It matches the first image and obtains submodule, for passing through affine transformation for the first image and the preset template figure
As being matched, the first image of matching is obtained；
Second splits submodule, for being closed according to mapping of the first image subregion on the first image of the matching
The first image of the matching is split as the second picture portion of multiple default sizes by system；
First similarity acquisition submodule, for obtain each the first image subregion and each second picture portion it
Between each first similarity；
Similarity value acquisition submodule, for the weight according to each first similarity and each the first image subregion
The weighted sum of value obtains the similarity value between the first image and the preset template image.
Preferably, the quantity of the first image is multiple；Each first image corresponds to a preset template image, institute
It states similarity value and obtains module 304, comprising:
First similarity value acquisition submodule, it is corresponding pre- according to first image for being directed to each the first image
The described image feature of template image and the first image is set, is obtained between the first image and the preset template image
The first similarity value；
First abnormal determining module 305, for determining the use when the similarity value is lower than default similarity threshold
The access behavior at family exists abnormal.
Preferably, the described first abnormal determining module 305, comprising:
First abnormal determining submodule, for determining institute when the comprehensive similarity value is lower than default similarity threshold
There is exception in the access behavior for stating user.
In conclusion embodiment of the disclosure provides a kind of user behavior abnormal detector, described device includes: to clap
Request initiation module is taken the photograph, the pre-set business behavior initiated when for detecting that user accesses businessman is initiated to user for described
The shooting of business conduct is requested；First image collection module, for obtaining user for the first figure of the shooting request shooting
Picture；Preset template image collection module, for obtaining the preset template image of corresponding the first image；Similarity value obtains mould
Block, for the described image feature according to preset template image and the first image, obtain the first image with it is described pre-
Set the similarity value between template image；First abnormal determining module, for being lower than default similarity threshold in the similarity value
When value, it is abnormal to determine that the access behavior of the user exists.The photographed data and preset mould when businessman can be accessed according to user
Similarity between plate image judges the access behavior of user with the presence or absence of efficiency abnormal, that raising is checked extremely.
Three corresponding method embodiment one of Installation practice, detailed description are referred to embodiment one, and details are not described herein.
Example IV
Referring to Fig. 4, it illustrates the structure chart of the user behavior abnormal detector in another embodiment of the disclosure,
It is specific as follows.
Shooting request initiation module 401, the pre-set business behavior initiated when for detecting that user accesses businessman, to user
It initiates to request for the shooting of the business conduct；
First image collection module 402, for obtaining user for the first image of the shooting request shooting；
Shooting time and location information obtain module 403, for obtaining the shooting time and positioning letter of the first image
Breath.
Filming frequency computing module 404, for determining first figure according to the shooting time and the location information
The filming frequency of picture, and/or, camera site；
Second abnormal determining module 405, for determining institute when the filming frequency or camera site are more than preset threshold
There is exception in the access behavior for stating user.
Preferably, further includes:
Image attribute information obtains module, for obtaining the image attribute information of the first image；
Hamming distance determining module, for determining the Hamming distance of the first image according to the image attribute information
With capture apparatus information；
Preferably, the image attribute information includes finger print data, the Hamming distance determining module, comprising:
Fingerprint vector acquisition submodule, for using the data fingerprint, obtain the current finger print of the first image to
Amount；
History fingerprint vector acquisition submodule, for obtaining the history fingerprint vector of preset the first image of history；
Hamming distance computational submodule, for calculating institute according to the current finger print vector and the history fingerprint vector
State the Hamming distance between the first image and preset the first image of history.
Third exception determining module is used to be less than pre-determined distance threshold value in the Hamming distance, and/or, the shooting is set
When standby information and inconsistent history capture apparatus information, it is abnormal to determine that the access behavior of the user exists.
In conclusion embodiment of the disclosure provides a kind of user behavior abnormal detector, described device includes: to clap
Request initiation module is taken the photograph, the pre-set business behavior initiated when for detecting that user accesses businessman is initiated to user for described
The shooting of business conduct is requested；First image collection module, for obtaining user for the first figure of the shooting request shooting
Picture；Shooting time and location information obtain module, for obtaining the shooting time and location information of the first image.Shooting frequency
Rate computing module, for according to the shooting time and the location information, determining the filming frequency of the first image, and/
Or, camera site；Second abnormal determining module, for determining when the filming frequency or camera site are more than preset threshold
The access behavior of the user exists abnormal.The information obtained in photographed data when can access businessman according to user, judgement
The access behavior of user is with the presence or absence of efficiency abnormal, that raising is checked extremely, further, it is also possible in conjunction with a variety of first image informations
Mode carry out abnormality detection, improve detection accuracy.
Four corresponding method embodiment two of Installation practice, detailed description are referred to embodiment two, and details are not described herein.
Embodiment of the disclosure additionally provides a kind of electronic equipment, referring to Fig. 5, comprising: processor 501, memory 502
And it is stored in the computer program 5021 that can be run on the memory and on the processor, the processor executes institute
The user behavior method for detecting abnormality of previous embodiment is realized when stating program.
Embodiment of the disclosure additionally provides a kind of readable storage medium storing program for executing, when the instruction in the storage medium is set by electronics
When standby processor executes, so that electronic equipment is able to carry out the user behavior method for detecting abnormality of previous embodiment.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, embodiment of the disclosure is also not for any particular programming language.It should be understood that can be with
The content of embodiment of the disclosure described herein is realized using various programming languages, and is retouched above to what language-specific was done
Stating is preferred forms in order to disclose embodiment of the disclosure.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the disclosure
The embodiment of example can be practiced without these specific details.In some instances, it is not been shown in detail well known
Methods, structures and technologies, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of the exemplary embodiment of embodiment of the disclosure, each feature of embodiment of the disclosure is sometimes by together
It is grouped into single embodiment, figure or descriptions thereof.However, it is as follows that the method for the disclosure should not be construed to reflection
Be intended to: embodiment of the disclosure i.e. claimed requires more more than feature expressly recited in each claim
Feature.More precisely, as reflected in the following claims, inventive aspect is single less than disclosed above
All features of embodiment.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the specific embodiment party
Formula, wherein separate embodiments of each claim as embodiment of the disclosure itself.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of any method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint
The claims, abstract and drawings) disclosed in each feature can with an alternative feature that provides the same, equivalent, or similar purpose come
Instead of.
The various component embodiments of embodiment of the disclosure can be implemented in hardware, or in one or more processing
The software module run on device is realized, or is implemented in a combination thereof.It will be understood by those of skill in the art that can be in reality
It tramples using microprocessor or digital signal processor (DSP) and realizes in sequencing equipment according to an embodiment of the present disclosure
Some or all components some or all functions.Embodiment of the disclosure is also implemented as executing institute here
Some or all device or device programs of the method for description.Such program for realizing embodiment of the disclosure can
May be stored on the computer-readable medium, or may be in the form of one or more signals.Such signal can be from
Downloading obtains on internet website, is perhaps provided on the carrier signal or is provided in any other form.
It should be noted that above-described embodiment illustrates rather than to embodiment of the disclosure embodiment of the disclosure
It is limited, and those skilled in the art can be designed replacement without departing from the scope of the appended claims and implement
Example.In the claims, any reference symbol between parentheses should not be configured to limitations on claims.Word
"comprising" does not exclude the presence of element or step not listed in the claims.Word "a" or "an" located in front of the element is not
There are multiple such elements for exclusion.Embodiment of the disclosure can be by means of including the hardware of several different elements and borrowing
Help properly programmed computer to realize.In the unit claims listing several devices, several in these devices
A can be is embodied by the same item of hardware.The use of word first, second, and third does not indicate any suitable
Sequence.These words can be construed to title.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The foregoing is merely the preferred embodiments of embodiment of the disclosure, not to limit the implementation of the disclosure
Example, all made any modifications, equivalent replacements, and improvements etc. within the spirit and principle of embodiment of the disclosure should all include
Within the protection scope of embodiment of the disclosure.
The above, the only specific embodiment of embodiment of the disclosure, but the protection scope of embodiment of the disclosure
It is not limited thereto, anyone skilled in the art, can in the technical scope that embodiment of the disclosure discloses
Change or replacement are readily occurred in, should all be covered within the protection scope of embodiment of the disclosure.Therefore, embodiment of the disclosure
Protection scope should be subject to the protection scope in claims.
Claims (14)
1. a kind of user behavior method for detecting abnormality, which is characterized in that the described method includes:
It detects the pre-set business behavior initiated when user accesses businessman, initiates to ask for the shooting of the business conduct to user
It asks；
User is obtained for the first image of the shooting request shooting；
Obtain the preset template image of corresponding the first image；
According to the described image feature of preset template image and the first image, the first image and the preset mould are obtained
Similarity value between plate image；
When the similarity value is lower than default similarity threshold, it is abnormal to determine that the access behavior of the user exists.
2. the method according to claim 1, wherein described according to preset template image and the first image
Described image feature, the step of obtaining the similarity value between the first image and the preset template image, comprising:
The preset template image is split as to the first picture portion of multiple default sizes；
According to the weighted value of the first image subregion each in preset template image described in described image signature；
The first image is matched with the preset template image by affine transformation, obtains the first image of matching；
According to mapping relations of the first image subregion on the first image of the matching, the first image of the matching is split
For the second picture portion of multiple default sizes；
Obtain each first similarity between each the first image subregion and each second picture portion；
According to the weighted sum of each first similarity and the weighted value of each the first image subregion, the first image is obtained
With the similarity value between the preset template image.
3. the method according to claim 1, wherein in the acquisition user for the shooting request shooting
After the step of first image, further includes:
Obtain the shooting time and location information of the first image；
According to the shooting time and the location information, the filming frequency of the first image is determined, and/or, camera site；
When the filming frequency or camera site are more than preset threshold, it is abnormal to determine that the access behavior of the user exists.
4. the method according to claim 1, wherein in the acquisition user for the shooting request shooting
After the step of first image, further includes:
Obtain the image attribute information of the first image；
According to the image attribute information, the Hamming distance and capture apparatus information of the first image are determined；
It is less than pre-determined distance threshold value in the Hamming distance, and/or, the capture apparatus information and history capture apparatus information are not
When consistent, it is abnormal to determine that the access behavior of the user exists.
5. according to the method described in claim 4, it is characterized in that, the image attribute information includes finger print data, described
According to the image attribute information, the step of determining the Hamming distance of the first image, comprising:
Using the data fingerprint, the current finger print vector of the first image is obtained；
Obtain the history fingerprint vector of preset the first image of history；
According to the current finger print vector and the history fingerprint vector, the first image and preset the first figure of history are calculated
Hamming distance as between.
6. the method according to claim 1, wherein the quantity of the first image is multiple；Each first
Image corresponds to a preset template image；
The described image feature according to preset template image and the first image, obtain the first image with it is described pre-
Set the similarity value between template image, comprising:
For each the first image, according to the figure of first image corresponding preset template image and the first image
As feature, the first similarity between the first image and the preset template image is obtained；
Operation is carried out according to preset ratio to corresponding first similarity value of each first image, obtains comprehensive similarity value；
It is described when the similarity value is lower than default similarity threshold, abnormal, the packet that determines that the access behavior of the user exists
It includes:
When the comprehensive similarity value is lower than default similarity threshold, it is abnormal to determine that the access behavior of the user exists.
7. a kind of user behavior abnormal detector, which is characterized in that described device includes:
Shooting request initiation module, the pre-set business behavior initiated when for detecting that user accesses businessman initiate needle to user
Shooting request to the business conduct；
First image collection module, for obtaining user for the first image of the shooting request shooting；
Preset template image collection module, for obtaining the preset template image of corresponding the first image；
Similarity value obtains module, for the described image feature according to preset template image and the first image, obtains institute
State the similarity value between the first image and the preset template image；
First abnormal determining module, for determining the visit of the user when the similarity value is lower than default similarity threshold
It is abnormal to ask that behavior exists.
8. device according to claim 7, which is characterized in that the similarity value obtains module, comprising:
First splits submodule, for the preset template image to be split as to the first picture portion of multiple default sizes；
Weight marks submodule, for each the first image in the preset template image according to described image signature
The weighted value of subregion；
Match the first image and obtain submodule, for by affine transformation by the first image and the preset template image into
Row matching obtains the first image of matching；
Second splits submodule, will for the mapping relations according to the first image subregion on the first image of the matching
The first image of the matching is split as the second picture portion of multiple default sizes；
First similarity acquisition submodule, for obtaining between each the first image subregion and each second picture portion
Each first similarity；
Similarity value acquisition submodule, for according to each first similarity and the weighted value of each the first image subregion
Weighted sum obtains the similarity value between the first image and the preset template image.
9. device according to claim 7, which is characterized in that further include:
Shooting time and location information obtain module, for obtaining the shooting time and location information of the first image.
Filming frequency computing module, for determining the bat of the first image according to the shooting time and the location information
Frequency is taken the photograph, and/or, camera site；
Second abnormal determining module, for determining the user when the filming frequency or camera site are more than preset threshold
Access behavior exist it is abnormal.
10. device according to claim 7, which is characterized in that further include:
Image attribute information obtains module, for obtaining the image attribute information of the first image；
Hamming distance determining module, for determining the Hamming distance and bat of the first image according to the image attribute information
Take the photograph facility information；
Third exception determining module is used to be less than pre-determined distance threshold value in the Hamming distance, and/or, the capture apparatus letter
When breath is inconsistent with history capture apparatus information, it is abnormal to determine that the access behavior of the user exists.
11. device according to claim 8, which is characterized in that the image attribute information includes finger print data, the Chinese
Prescribed distance determining module, comprising:
Fingerprint vector acquisition submodule obtains the current finger print vector of the first image for using the data fingerprint；
History fingerprint vector acquisition submodule, for obtaining the history fingerprint vector of preset the first image of history；
Hamming distance computational submodule, for according to the current finger print vector and the history fingerprint vector, calculating described the
Hamming distance between one image and preset the first image of history.
12. device according to claim 7, which is characterized in that the quantity of the first image is multiple；Each first
Image corresponds to a preset template image；
The similarity value obtains module, comprising:
First similarity value acquisition submodule, for being directed to each the first image, according to the corresponding preset mould of first image
The described image feature of plate image and the first image obtains the between the first image and the preset template image
One similarity value；
Comprehensive similarity value acquisition submodule, for corresponding first similarity value of each first image according to preset ratio into
Row operation obtains comprehensive similarity value；
Described first abnormal determining module, comprising:
First abnormal determining submodule, for determining the use when the comprehensive similarity value is lower than default similarity threshold
The access behavior at family exists abnormal.
13. a kind of electronic equipment characterized by comprising
Processor, memory and it is stored in the computer program that can be run on the memory and on the processor,
It is characterized in that, the processor realizes the user behavior as described in one or more in claim 1-6 when executing described program
Method for detecting abnormality.
14. a kind of readable storage medium storing program for executing, which is characterized in that when the instruction in the storage medium is held by the processor of electronic equipment
When row, so that electronic equipment is able to carry out the user behavior abnormality detection as described in one or more in claim to a method 1-6
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811379243.5A CN109727058A (en) | 2018-11-19 | 2018-11-19 | User behavior method for detecting abnormality, device, electronic equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811379243.5A CN109727058A (en) | 2018-11-19 | 2018-11-19 | User behavior method for detecting abnormality, device, electronic equipment and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109727058A true CN109727058A (en) | 2019-05-07 |
Family
ID=66295480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811379243.5A Pending CN109727058A (en) | 2018-11-19 | 2018-11-19 | User behavior method for detecting abnormality, device, electronic equipment and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109727058A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110704A (en) * | 2019-05-21 | 2019-08-09 | 北京首汽智行科技有限公司 | A kind of vehicle sanitation monitoring method and system |
| CN110716817A (en) * | 2019-09-10 | 2020-01-21 | 中国平安财产保险股份有限公司 | System operation fault processing method and device, storage medium and electronic equipment |
| CN113011449A (en) * | 2019-12-20 | 2021-06-22 | 中移(上海)信息通信科技有限公司 | Behavior determination method, behavior determination device, behavior determination equipment and storage medium |
| CN116503815A (en) * | 2023-06-21 | 2023-07-28 | 宝德计算机系统股份有限公司 | Big data-based computer vision processing system |
-
2018
- 2018-11-19 CN CN201811379243.5A patent/CN109727058A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110704A (en) * | 2019-05-21 | 2019-08-09 | 北京首汽智行科技有限公司 | A kind of vehicle sanitation monitoring method and system |
| CN110716817A (en) * | 2019-09-10 | 2020-01-21 | 中国平安财产保险股份有限公司 | System operation fault processing method and device, storage medium and electronic equipment |
| CN110716817B (en) * | 2019-09-10 | 2024-06-25 | 中国平安财产保险股份有限公司 | System operation fault processing method and device, storage medium and electronic equipment |
| CN113011449A (en) * | 2019-12-20 | 2021-06-22 | 中移(上海)信息通信科技有限公司 | Behavior determination method, behavior determination device, behavior determination equipment and storage medium |
| CN116503815A (en) * | 2023-06-21 | 2023-07-28 | 宝德计算机系统股份有限公司 | Big data-based computer vision processing system |
| CN116503815B (en) * | 2023-06-21 | 2024-01-30 | 宝德计算机系统股份有限公司 | Big data-based computer vision processing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109727058A (en) | User behavior method for detecting abnormality, device, electronic equipment and readable storage medium storing program for executing | |
| Walia et al. | Digital image forgery detection: a systematic scrutiny | |
| AU2017209231B2 (en) | Method, system, device and readable storage medium for realizing insurance claim fraud prevention based on consistency between multiple images | |
| CN105928598A (en) | Method and system for measuring object mass based on photographing | |
| CN110378900A (en) | The detection method of product defects, apparatus and system | |
| CN110276366A (en) | Carry out test object using Weakly supervised model | |
| WO2016177259A1 (en) | Similar image recognition method and device | |
| JP2020507836A (en) | Tracking surgical items that predicted duplicate imaging | |
| CN107679475B (en) | Store monitoring and evaluating method and device and storage medium | |
| EP1347417A2 (en) | Face detection computer program product for redeye correction | |
| CN108734106B (en) | Rapid riot and terrorist video identification method based on comparison | |
| CN109858504A (en) | A kind of image-recognizing method, device, system and calculate equipment | |
| US11657644B2 (en) | Automatic ruler detection | |
| CN108323209B (en) | Information processing method, system, cloud processing device and computer storage medium | |
| CN110781917B (en) | Method and device for detecting repeated image, electronic equipment and readable storage medium | |
| CN108876835A (en) | Depth information detection method, device and system and storage medium | |
| CN111126098B (en) | Certificate image acquisition method, device, equipment and storage medium | |
| CN110969045B (en) | Behavior detection method and device, electronic equipment and storage medium | |
| CN116416190A (en) | Flaw detection method and device, electronic equipment and storage medium | |
| WO2019148923A1 (en) | Method and apparatus for searching for images with image, electronic device, and storage medium | |
| CN116433559A (en) | Product appearance defect detection method, electronic equipment and storage medium | |
| CN109906458B (en) | Method and system for generating surface feature codes | |
| CN109508623A (en) | Item identification method and device based on image procossing | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| JP6857373B1 (en) | Information processing equipment, information processing methods, and programs |
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 |