CN107729924A - Picture review probability interval generation method and picture review decision method - Google Patents
Picture review probability interval generation method and picture review decision method Download PDFInfo
- Publication number
- CN107729924A CN107729924A CN201710876917.1A CN201710876917A CN107729924A CN 107729924 A CN107729924 A CN 107729924A CN 201710876917 A CN201710876917 A CN 201710876917A CN 107729924 A CN107729924 A CN 107729924A
- Authority
- CN
- China
- Prior art keywords
- probability
- picture
- review
- original
- interval
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Abstract
The present invention relates to a kind of picture review probability interval generation method, device, storage medium and computer equipment.Methods described includes：Obtain the bad probability that each picture in the pictures corresponding with original review probability interval is imperfect picture；For every group of picture with identical bad probability, the first quantity for being determined as normal picture by review is counted, and is determined as the second quantity of imperfect picture by review；Picture review probability interval is regenerated according to the first quantity and the second quantity corresponding to every group of bad probability.Above-mentioned picture review probability interval generation method, device, storage medium and computer equipment passes through the result after combining artificial review, review probability interval is adjusted, so that newly-generated picture review probability interval scope is more accurate, the workload of picture review is reduced, so as to improve the efficiency of imperfect picture review.
Description
Technical field
The present invention relates to communication technical field, more particularly to a kind of picture review probability interval generation method, device, deposits
Storage media and computer equipment and a kind of picture review decision method, device, storage medium and computer equipment.
Background technology
With the development of the communication technology, for the ease of the communication of user, the increasing network platform is such as social flat
Platform, financial platform etc., all provide the user picture and upload the function of downloading.This also causes the propagation of imperfect picture increasingly to hold
Easily.In order to prevent the propagation of imperfect picture, many network platforms are entered by the way that the picture of transmission is accessed into imperfect picture identification system
Row differentiates that imperfect picture identification system feedback can be that picture is accredited as to single class a kind of in normal, sexy, pornographic three classes
Other probability, or when picture is accredited as into normal, sexy, pornographic three class respectively corresponding to three probability.
However, because current imperfect picture identification system has loss or false drop rate, differentiate system by imperfect picture
Still some picture needs to carry out artificial review to confirm in picture after system identification.In imperfect picture identification system discrimination
In the case of limited, the picture review probability interval of imperfect picture identification system generation is bigger, therefore the work of artificial review
Amount is also corresponding larger, it is necessary to a large amount of unnecessary times be expended, so as to cause the review of imperfect picture less efficient.
The content of the invention
The embodiment of the present invention provides a kind of picture review probability interval generation method, device, storage medium and computer and set
It is standby, can effectively solve the less efficient technical problem of imperfect picture review.
The embodiment of the present invention provides a kind of picture review decision method, device, storage medium and computer equipment, Ke Yiyou
Effect solves the less efficient technical problem of imperfect picture review.
A kind of picture review probability interval generation method, methods described include：Obtain relative with original review probability interval
Each picture is the bad probability of imperfect picture in the pictures answered；For every group of picture with identical bad probability, statistics
It is determined as the first quantity of normal picture by review, and is determined as the second quantity of imperfect picture by review；It is bad according to every group
First quantity corresponding to probability and the second quantity regenerate picture review probability interval.
In one of the embodiments, each scheme in the acquisition pictures corresponding with original review probability interval
Before piece is the bad probability of imperfect picture, including：Obtain in default pictures, each picture for imperfect picture it is initially general
Rate；Probability corresponding to each picture is calculated, it is imperfect picture to generate each picture in the default pictures
Bad probability；Original review probability interval is set, and extracts picture corresponding to the bad probability positioned at original review probability interval,
Form the pictures corresponding with the original review probability interval.
In one of the embodiments, the first quantity and second quantity according to corresponding to every group of bad probability are given birth to again
Into picture review probability interval, including：Obtain original Upper Probability and the original lower limit probability of the original review probability interval；
Two class probabilities are gone out according to the original Upper Probability and original lower limit probability calculation, can be obtained by two class probability
The second quantity sum corresponding to original lower limit probability to two class probabilities, corresponding to two class probabilities to original Upper Probability
The first quantity sum, the minimum value of the two summation；It is general to original Upper Probability and original lower limit according to two class probability
Rate is calculated, and regenerates picture review probability interval.
In one of the embodiments, it is described according to two class probability to original Upper Probability and original lower limit probability
Calculated, regenerate picture review probability interval, including：When two class probabilities are less than or equal to predetermined probabilities, according to public affairs
FormulaCalculated, regenerate Upper Probability s2', wherein, s1For original lower limit probability, s2
For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；When two class probabilities are more than predetermined probabilities, according to formulaCalculated, regenerate lower limit probability s1', wherein, s1For original lower limit probability, s2To be original
Upper Probability, t are two class probabilities, x0For predetermined probabilities；According to the new Upper Probability s2' or the new lower limit probability
s1', regenerate picture review probability interval.
In one of the embodiments, it is described to obtain each picture in the pictures corresponding with original review probability interval
After the bad probability of imperfect picture, in addition to：Obtain the picture system power of image transmission system corresponding to the pictures
Value；It is described that original Upper Probability and original lower limit probability are calculated according to two class probability, regenerate picture and answer
Probability interval is examined, including：According to two class probability and the picture system weights, to original Upper Probability and original lower limit
Probability is calculated, and regenerates picture review probability interval.
A kind of picture review decision method, methods described include：Obtain the bad probability that picture to be identified is imperfect picture；
The bad probability is judged whether within default picture review probability interval, and the picture review probability interval is according to above-mentioned
Picture review probability interval generation method described in each embodiment and generate；If so, then judge that the picture to be identified needs
Carry out picture review.
A kind of picture review probability interval generating means, described device include：Bad probability acquisition module, for obtain with
Each picture is the bad probability of imperfect picture in the corresponding pictures of original review probability interval；Picture judges quantity statistics
Module, for having the picture of identical bad probability for every group, the first quantity for being determined as normal picture by review is counted, and
It is determined as the second quantity of imperfect picture by review；Picture review probability interval generation module, for according to every group of bad probability
Corresponding first quantity and the second quantity regenerate picture review probability interval.
A kind of picture review decision maker, described device include：The bad probability acquisition module of picture to be identified, for obtaining
Picture to be identified is the bad probability of imperfect picture；Picture review judge module, for judging the bad probability whether pre-
If picture review probability interval within, picture review probability interval picture according to any one of claim 1-5
Review probability interval generation method generates；If so, then judge that the picture to be identified needs to carry out picture review.
A kind of computer-readable recording medium, is stored thereon with computer program, and the program is realized when being executed by processor
The step of picture review probability interval generation method described in above-mentioned each embodiment.
A kind of computer-readable recording medium, is stored thereon with computer program, and the program is realized when being executed by processor
The step of picture review decision method described in above-mentioned each embodiment.
A kind of computer equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, the picture review probability interval described in above-mentioned each embodiment is realized during the computing device described program
The step of generation method.
A kind of computer equipment, including memory, processor and storage can be run on a memory and on a processor
Computer program, the picture review decision method described in above-mentioned each embodiment is realized during the computing device described program
The step of.
Above-mentioned picture review probability interval generation method, device, storage medium and computer equipment and picture review are sentenced
Method, apparatus, storage medium and computer equipment are determined, by the artificial review that pictures are corresponded to reference to original review probability interval
As a result, for every group of picture with identical bad probability, the first quantity for being determined as normal picture by review is counted, and answered
Trial is set to the second quantity of imperfect picture, and original review probability interval is calculated according to the first quantity and the second quantity,
Regenerate picture review probability interval.Review probability interval is adjusted according to the review result of statistics so that newly-generated
Picture review probability interval scope it is more accurate, reduce picture review workload, so as to improve the effect of imperfect picture review
Rate.
Brief description of the drawings
Fig. 1 is the applied environment figure of picture review probability interval generation method in one embodiment；
Fig. 2 is the flow chart of picture review probability interval generation method in one embodiment；
Fig. 3 is the flow chart of picture review probability interval generation method in another embodiment；
Fig. 4 is the flow chart of picture review probability interval generation method in another embodiment；
Fig. 5 is the flow chart of picture review decision method in one embodiment；
Fig. 6 is the structured flowchart of picture review probability interval generating means in one embodiment；
Fig. 7 is the structured flowchart of picture review probability interval generating means in another embodiment；
Fig. 8 is the structured flowchart of picture review decision maker in one embodiment；
Fig. 9 is the cut-away view of the first computer equipment in one embodiment.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.
It is appreciated that term " first " used in the present invention, " second " etc. can be used to describe various elements herein,
But these elements should not be limited by these terms.These terms are only used for distinguishing first element and another element.Citing
For, without departing from the scope of the invention, the first quantity can be referred to as the second quantity, and similarly, can be by
Two quantity are referred to as the first quantity.First quantity and the second quantity both quantity, but it is not same quantity.
The picture review probability interval generation method that the embodiment of the present invention is provided, can be applied to the application environment such as Fig. 1
In.Reference picture 1, the application environment include the first computer equipment 102 and second computer equipment 104.First computer equipment
102 and second computer equipment 104 can be terminal be alternatively server.Wherein, terminal includes but is not limited to mobile phone, tablet personal computer
Or personal digital assistant or Wearable etc., server can be independent physical server or multiple physics
The server cluster that server is formed.First computer equipment 102 and second computer equipment can be the computer of same type
Equipment, or different types of computer equipment.First computer equipment 102 can be used for the execution embodiment of the present invention to be provided
Picture review probability interval generation method.Second computer equipment 104 can be stored with the end of imperfect picture identification system
End or server, available for discriminating imperfect picture and export the probability of picture.First computer equipment 102 can be with the second meter
The network connection of machine equipment 104 is calculated, such as, the first computer equipment 102 can obtain second computer equipment 104 and picture is carried out
Differentiate that data, the network connections such as obtained probability include but is not limited to wireless network, cable network etc..
In one embodiment, the first computer equipment 102 and second computer equipment 104 can be that same computer is set
It is standby.
In one embodiment, as shown in Figure 2, there is provided a kind of picture review probability interval generation method, this method can
Applied to the first computer equipment 102 in application environment as shown in Figure 1, this method includes：
Step S202, obtain in pictures corresponding with original review probability interval each picture as imperfect picture not
Good probability.
In the present embodiment, original review probability interval can refer to the review probability interval of default fixation or preceding
The review probability interval once adjusted.Wherein, review probability interval refers in imperfect picture qualification process, it is necessary to carry out artificial
Probability interval corresponding to the picture of review.Bad probability refers to the possibility degree that picture is imperfect picture, and bad probability is in
In original review probability interval.The probability that can be exported according to imperfect picture identification systems, is calculated according to default algorithm
To bad probability.Further, can be not plan deliberately according to each picture in the pictures corresponding with original review probability interval
The bad probability of piece, the bad distribution of picture formed on original review probability interval is counted, wherein, it is horizontal in the bad distribution of picture
Coordinate can be bad probability, and ordinate can be the picture number corresponding to identical bad probability.
Step S204, for every group of picture with identical bad probability, count and be determined as the of normal picture by review
One quantity, and it is determined as by review the second quantity of imperfect picture.
In the present embodiment, the picture counted in original review probability interval is determined as normal picture or imperfect picture by review
Quantity.Wherein, in the picture of identical bad probability, it is determined as that the picture number of normal picture is the first quantity by review, quilt
Review is determined as that the picture number of imperfect picture is the second quantity.
Step S206, picture review probability is regenerated according to the first quantity and the second quantity corresponding to every group of bad probability
Section.
In the present embodiment, new picture review probability interval refers to for judging whether picture will carry out the general of artificial review
Rate section, among the bad probability of the picture newly received is in the new picture review probability interval that the above method is calculated
When, the picture can be judged to needing to carry out artificial review.Further, can also be according to corresponding to the picture of each bad probability
The first quantity and the second quantity, formed respectively after the first distributed number and the second distributed number, according to every group of bad probability
Corresponding first distributed number and the second distributed number regenerate picture review probability interval.
In above-described embodiment, by corresponding to the artificial review result of pictures with reference to original review probability interval, quilt is counted
Review is determined as the first quantity of normal picture, and is determined as the second quantity of imperfect picture by review, according to the first quantity and
Second quantity is calculated original review probability interval, regenerates picture review probability interval.By combining artificial review
Result afterwards, review probability interval is adjusted so that newly-generated picture review probability interval scope is more accurate, reduces
The workload of picture review, so as to improve the efficiency of imperfect picture review.
In one embodiment, as shown in figure 3, before step S202, in addition to：
Step S302, obtain in default pictures, each picture is the probability of imperfect picture.
In the present embodiment, default pictures refer to that picture system inputs imperfect picture identification system in preset time period
The pictures that picture is formed.Each picture of probability imperfect picture identification system output differentiate after probability, not plan deliberately
The output of piece identification system can be that picture is accredited as to single class probability a kind of in normal, sexy, pornographic three classes, either
Three multi-class probability corresponding to difference when picture is accredited as into normal, sexy, pornographic three class.Wherein, single class probability and
Multi-class probability can be that picture is the corresponding other confidence level of picture category.The value of single class probability and multi-class probability can be 0
To 1.
Step S304, probability corresponding to each picture is calculated, generating each picture in default pictures is
The bad probability of imperfect picture.
In the present embodiment, bad probability is that have system according to obtained from calculating probability according to default algorithm
The probability of one standard.Specifically, single class probability or multi-class probability are uniformly mapped as to the probability on same term of reference.
Further, obtain in default pictures, each picture is the picture category corresponding to the probability of imperfect picture
Other weights；Picture classification weights according to corresponding to the probability of identical picture, enter to probability corresponding to each picture
Row calculates, and generates the bad probability that each picture in default pictures is imperfect picture.Wherein, picture classification weights refer to bad
Weights corresponding to the picture classification of picture identification system output.When probability is single class probability, each picture institute
Corresponding picture classification weights are to preset one kind in normal weights, default sexy weights, the default pornographic class of weights three；When initial
When probability is multi-class probability, the picture classification weights corresponding to each picture can be three, be default normal weights respectively, pre-
If sexy weights and default pornographic weights.
Step S306, original review probability interval is set, and extract the bad probability pair positioned at original review probability interval
The picture answered, form the pictures corresponding with original review probability interval.
, can be according to original review probability after calculating the bad probability that each picture is imperfect picture in the present embodiment
Section extracts corresponding picture, forms the pictures corresponding with original review probability interval, and the pictures are to need to carry out
The pictures of artificial review.Further, the pictures corresponding with original review probability interval can be extracted store to
Database under preset path so that picture review personnel directly can carry out review to the picture extracted.
In above-described embodiment, uniformly it is mapped to by the probability for the picture for exporting imperfect picture identification systems bad
Probability is compared, enabling it is determined that the original review probability interval with unified normative reference, and it is general according to original review
The artificial review result of the corresponding pictures in rate section, calculates original review probability interval, regenerates picture and answer
Probability interval is examined, the specification determination mode of picture review probability interval, improves the degree of accuracy of picture review probability interval.
In one embodiment, step S206, in addition to：Obtain the original Upper Probability and original of original review probability interval
Beginning lower limit probability；Two class probabilities are gone out according to original Upper Probability and original lower limit probability calculation, can by two class probabilities
The second quantity sum corresponding to original lower limit probability to two class probabilities is obtained, with two class probabilities to original Upper Probability institute
Corresponding first quantity sum, the minimum value of the two summation；It is general to original Upper Probability and original lower limit according to two class probabilities
Rate is calculated, and regenerates picture review probability interval.
In the present embodiment, original Upper Probability and original lower limit probability refers to the end points of original review probability interval, and former
The value of beginning Upper Probability is more than the value of original lower limit probability.Two class probabilities refer to original review probability interval being divided into two
The value in section, two class probabilities are more than original lower limit threshold value and are less than original upper limit threshold.Specifically, by original lower limit probability
To the second quantity sum corresponding to two class probabilities, with the first quantity corresponding to two class probabilities to original Upper Probability it
With, when both summations take minimum value, available two class probabilities.It is represented by formulaWherein,
s1For original lower limit probability, s2For original Upper Probability, MiRepresent the second quantity that probability is i, NiRepresent first that probability is i
Quantity, by takingWithThe minimum value of sum of the two can try to achieve two class probability t.
Specifically, original Upper Probability and the original lower limit probability of original review probability interval, can be according to bad with calculating
The default algorithm of probability identical is calculated.Because each imperfect picture identification system has loss or false drop rate, often
Individual imperfect picture identification system has itself default probability section for needing to carry out review, can extract the probability section
Initial upper limit probability and initial lower limit probability calculated, obtain original Upper Probability and original lower limit probability.Original review
It is straight that original Upper Probability and the original lower limit probability of probability interval is alternatively the picture review probability interval once adjusted before
Connect determination.
Further, can also be after the first distributed number and the second distributed number be formed, by the second distributed number in original
Beginning lower limit probability is to the integration of two class probabilities, the integration with the first distributed number in two class probabilities to original Upper Probability,
Both integration sums take minimum value to calculate to obtain two class probabilities.According to two class probabilities to original Upper Probability and original lower limit
Probability is calculated separately or together according to default, regenerates picture review probability interval.
In one embodiment, each picture is bad in the pictures corresponding with original review probability interval are obtained
After the bad probability of picture, in addition to：Obtain the picture system weights of image transmission system corresponding to pictures.Step S206
Including：According to two class probabilities and picture system weights, original Upper Probability and original lower limit probability are calculated, given birth to again
Into picture review probability interval.
In the present embodiment, picture system weights are and one or more weights corresponding to picture system.Wherein, picture system
System includes but is not limited to recreational system, such as blind date forum, social platform etc., or be alternatively financial field is
System, such as banking system, securities system etc..Specifically, picture system weights can be carried out according to the attribute or parameter of picture system
Assignment.For example assignment can be carried out according to picture/mb-type, wherein, picture/mb-type includes but is not limited to invoice document class, client's document
Class etc. is linked up in class, credentials file class, work circulation class, customer communication, according to inside to external traffic flow degree by it is low to
High assignment；Assignment can also be carried out according to picture access frequency, wherein, access frequency can be divided into outside access frequency and lower carrier frequency
Rate etc., according to the value assignment from low to high of frequency；Assignment can also be carried out according to picture significance level, such as can be according to picture
Carry out assignment with the correlation degree of transaction, can according to picture and transaction voucher, promotional and the degree of correlation of customer account management by
Low to high assignment.Further, can be according to one or more the system weights and two class probabilities of picture system, to the original upper limit
Probability and original lower limit probability are calculated, and regenerate picture review probability interval.Specifically, can also be by multiple system weights
And the integrated system weights as the picture system.When integrated system weights are in default weights section, take corresponding
Separately or concurrently original Upper Probability and original lower limit probability are calculated.
In one embodiment, weights q can be determined according to picture/mb-type1, weights q can be determined according to picture access frequency2,
Weights q can be determined according to picture significance level3.Specifically, can be according to q1、q2、q3Weights sum determines integrated system weights Q=q1
+q2+q3, and q can be limited1、q2、q3Span.Such as q1Can value 1 to 10, q2Value 1 to 20, q3Value 1 to 10.Enter
One step, according to integrated system weights Q and the size of predetermined threshold value corresponding calculation formula can be taken to regenerate the original upper limit
Probability and original lower limit probability.Such as when integrated system weights Q be less than or equal to 20, adjustmentWork as synthesis
System weights Q is more than 20, adjustmentWherein, wherein, s1For original lower limit probability, s2To be original
Upper Probability, t are two class probabilities, s1' it is new lower limit probability, s2' it is new Upper Probability.
In one embodiment, the class of picture can be determined according to the keyword in the URL (resource unifies finger URL) of picture
Type.Such as if the keyword related URL of a pictures is goods, payment for goods, payment etc., document can be stamped to picture
Label.Specifically, the mapping relations of keyword and type can with the database of predetermined keyword, be generated.When extracting in URL
Comprising keyword when, the keyword is matched with the predetermined keyword in database, obtained and the key that the match is successful
Word has the picture/mb-type of mapping relations, as picture/mb-type corresponding with the picture.
In the present embodiment, corresponding picture review probability interval is generated for the situation of different picture systems so that raw
Into picture review probability interval more conform to actual demand, improve the degree of accuracy in picture review section.
In one embodiment, can also there are corresponding picture system weights for different users.The picture system weights
Diagram data can be sent out according to the history of user and carry out assignment.Such as the picture sent out in being recorded according to user's history is bad
Degree carries out assignment；The picture access frequency that figure can be also sent out according to user's history carries out assignment；It can also be recorded according to user's history
The undesirable level of the other forms content such as text of middle hair carries out assignment.For example, it is above to be transmitted through for a historical custom
Porny, and picture access frequency is more than the user of predetermined threshold value, can assign of a relatively high weights.
In one embodiment, the undesirable level for the picture sent out in being recorded according to user's history determines weights c1, can root
Weights c is determined according to the picture access frequency of user's history hair figure2, the other forms such as the text sent out in being recorded according to user's history
The undesirable level of content determines weights c3.Specifically, can be according to c1、c2、c3Weights sum determines integrated system weights C=c1+c2+
c3, and c can be limited1、c2、c3Span.Such as c1Can value 1 to 10, c2Value 1 to 20, c3Value 1 to 10.Further
Ground, according to integrated system weights C and the size of predetermined threshold value corresponding calculation formula can be taken to regenerate original Upper Probability
With original lower limit probability.Such as when integrated system weights C be less than or equal to 20, adjustmentWork as integrated system
Weights C is more than 20, adjustmentWherein, wherein, s1For original lower limit probability, s2For the original upper limit
Probability, t are two class probabilities, s1' it is new lower limit probability, s2' it is new Upper Probability.
In the present embodiment, corresponding picture review probability interval is generated for the historical record of different user so that generation
Picture review probability interval more conform to actual demand, improve the degree of accuracy in picture review section.
In one embodiment, as shown in Figure 4, there is provided another picture review probability interval generation method, this method
Including：
Step S402, obtain in default pictures, each picture is the probability of imperfect picture, corresponding to each picture
Probability calculated, generate the bad probability that each picture in default pictures is imperfect picture.
In the present embodiment, each picture of probability imperfect picture identification system output differentiate after probability, not plan deliberately
The output of piece identification system can be that picture is accredited as to single class probability a kind of in normal, sexy, pornographic three classes, either
Three multi-class probability corresponding to difference when picture is accredited as into normal, sexy, pornographic three class.
In one embodiment, when probability is single class probability, can preset respectively normal, sexy and pornographic three kinds
The mapping equation of single class probability, calculate and generate bad probability.Such as differentiating single class probability A for normal picture,
Mapping equation can be bad probabilityFor differentiating single class probability B for sexy picture, mapping equation can be bad general
RateFor differentiating single class probability C for porny, mapping equation can be bad probabilityIts
In, if A, B, C value all be 0 to 1, bad probability y values corresponding with probability A be 0 toIt is corresponding with probability B bad
Probability y values areExtremelyBad probability y values corresponding with probability C areTo 1, therefore bad probability y span is 0
To 1.In the present embodiment, by the way that three kinds of single class probabilities are mapped as into the substandard bad probability of same value, reduce and compare
The difficulty of imperfect picture identification system output probability, the specification standard of bad probability, improve and determine review probability interval
The degree of accuracy.
In one embodiment, when probability is multi-class probability, can integrate normal general corresponding to every pictures
Rate, sexy probability and pornographic probability, according to unified mapping equation, calculate and generate bad probability.Such as identical picture
Corresponding normal probability D, sexy probability E and pornographic probability F, and three probability sums can be 1, predeterminable mapping equation is not
Good probabilityIn the present embodiment, bad probability is obtained by comprehensive three multi-class probability calculations,
Reduce the difficulty for comparing imperfect picture identification system output probability, the specification standard of bad probability, improve determination review
The degree of accuracy of probability interval.
Step S404, original review probability interval is set, and extract the bad probability pair positioned at original review probability interval
The picture answered, form the pictures corresponding with original review probability interval.
Specifically, original review probability interval can be determined according to the mapping equation for determining bad probability.Wherein, it is original multiple
Probability interval is examined in the interval of the bad probability corresponding to default pictures.
Step S406, obtain in pictures corresponding with original review probability interval each picture as imperfect picture not
Good probability.
Step S408, for every group of picture with identical bad probability, count and be determined as the of normal picture by review
One quantity, and it is determined as by review the second quantity of imperfect picture.
In the present embodiment, using the corresponding pictures of original review probability interval as the picture for needing to carry out artificial review
Collection so that the picture in the pictures is determined as normal picture or imperfect picture by picture review personnel.
In one embodiment, for picture review, it is possible to provide corresponding picture review interface, displaying is former on the surface
Picture in the corresponding pictures of beginning review probability interval, picture review personnel can select normogram therein according to judgement
Piece or imperfect picture.Further, can be according to picture corresponding to each bad probability displaying, when detecting picture review personnel's
Clicking operation, then corresponding label can be stamped to the picture, count the number of labels of uniform type as the first quantity or
Two quantity.
For example, picture review personnel can be clicked on to the picture of selection as imperfect picture and be labeled as " 1 ", will not had
The picture of selection is clicked as normal picture and is labeled as " 0 ", when all having carried out review to picture corresponding to the bad probability
Afterwards, mark under the bad probability can be counted and be labeled as the picture of " 0 " as the first quantity, statistics for 0 " picture number
Quantity is as the second quantity.
Step S410, original Upper Probability and the original lower limit probability of original review probability interval is obtained, on original
Limit probability and original lower limit probability calculation go out two class probabilities.
In the present embodiment, second corresponding to original lower limit probability to two class probabilities can be obtained by two class probabilities
Quantity sum, with the first quantity sum corresponding to two class probabilities to original Upper Probability, the minimum value of the two summation.Specifically
Ground, obtain original Upper Probability s corresponding to original review probability interval2With original lower limit probability s1, wherein, original Upper Probability
s2With original lower limit probability s1It can be determined according to the loss and false drop rate of imperfect picture identification system.
In one embodiment, the first distributed number P can be generated according to the first quantity corresponding to each bad probability1
(x), accordingly, the second distributed number P can be generated according to the second quantity corresponding to each bad probability2(x).Further,
Can be according to formulaTwo class probability t of generation are calculated, wherein two class probability t cause, by the
Two distributed number P2(x) in original lower limit probability s1To two class probability t integration, with the first distributed number P1(x) in two classification
Probability t to original Upper Probability s2Integration, both integration sums take minimum value.
Step S412, judges whether two class probabilities are more than predetermined probabilities.
In the present embodiment, when two class probabilities are less than or equal to predetermined probabilities, step S314 is performed；When two class probabilities are big
When predetermined probabilities, step S316 is performed.
Step S414, calculated according to default first formula, regenerate Upper Probability.
Specifically, the first formula is predeterminable isWherein, s1For original lower limit probability,
s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities, s2' it is new Upper Probability.
Step S416, calculated according to default second formula, regenerate lower limit probability.
Specifically, the second formula is predeterminable isWherein, s1For original lower limit probability, s2For original
Beginning Upper Probability, t are two class probabilities, x0For predetermined probabilities, s1' it is new lower limit probability.
Step S418, according to the Upper Probability regenerated or the lower limit probability regenerated, regenerate picture review
Probability interval.
Specifically, according to new Upper Probability s2' or new lower limit probability s1', picture review probability interval is regenerated,
The picture review probability interval is s1' to s2’。
In above-described embodiment, uniformly it is mapped to by the probability for the picture for exporting imperfect picture identification systems bad
Probability is compared, and result of the picture according to corresponding to original review probability interval after artificial review, is counted by review
It is determined as the first quantity of normal picture, and is determined as the second quantity of imperfect picture by review, according to the first quantity and second
Quantity is calculated original review probability interval, regenerates picture review probability interval.After combining artificial review
As a result, two class probabilities of generation are calculated.According to the size of two class probabilities and predetermined probabilities by the adjustment to review probability interval
It is divided into two kinds of situations so that newly-generated picture review probability interval scope is more accurate, reduces the workload of picture review, from
And improve the efficiency of imperfect picture review.
In one embodiment, as shown in Figure 5, there is provided a kind of picture review decision method, this method include：
Step S502, obtain the bad probability that picture to be identified is imperfect picture.
In the present embodiment, picture to be identified is made to determine whether the picture of image review to be carried out for needs.Specifically, obtain
The bad probability that picture to be identified is imperfect picture is taken to preset the calculation of the bad probability of each picture in pictures with calculating
Unanimously.
Step S504, judge bad probability whether within default picture review probability interval.
In the present embodiment, the generation method of picture review probability interval includes：Obtain relative with original review probability interval
Each picture is the bad probability of imperfect picture in the pictures answered；For every group of picture with identical bad probability, statistics
It is determined as the first quantity of normal picture by review, and is determined as the second quantity of imperfect picture by review；It is bad according to every group
First quantity corresponding to probability and the second quantity regenerate picture review probability interval.If so, then perform step S506；If
It is no, then perform step S508.
Step S506, judge that picture to be identified needs to carry out picture review.
Step S508, judge that picture to be identified need not carry out picture review.
In one embodiment, the generation method of picture review probability interval also includes：Obtaining and original review probability
In the corresponding pictures in section, before each picture is the bad probability of imperfect picture, obtain in default pictures, Mei Getu
Piece is the probability of imperfect picture；Probability corresponding to each picture is calculated, generated each in default pictures
Picture is the bad probability of imperfect picture；Original review probability interval is set, and is extracted positioned at original review probability interval not
Picture corresponding to good probability, form the pictures corresponding with original review probability interval.
In one embodiment, the first quantity and the second quantity according to corresponding to every group of bad probability regenerate picture and answered
Probability interval is examined, including：Obtain original Upper Probability and the original lower limit probability of original review probability interval；According to the original upper limit
Probability and original lower limit probability calculation go out two class probabilities, and original lower limit probability can be obtained to two classification by two class probabilities
The second quantity sum corresponding to probability, and the first quantity sum corresponding to two class probabilities to original Upper Probability, the two
The minimum value of summation；Original Upper Probability and original lower limit probability are calculated according to two class probabilities, regenerate picture
Review probability interval.
In one embodiment, original Upper Probability and original lower limit probability are calculated according to two class probabilities, weight
Newly-generated picture review probability interval, including：When two class probabilities are less than or equal to predetermined probabilities, according to formulaCalculated, regenerate Upper Probability s2', wherein, s1For original lower limit probability, s2For
Original Upper Probability, t are two class probabilities, x0For predetermined probabilities；When two class probabilities are more than predetermined probabilities, according to formulaCalculated, regenerate lower limit probability s1', wherein, s1For original lower limit probability, s2To be original
Upper Probability, t are two class probabilities, x0For predetermined probabilities；According to new Upper Probability s2' or new lower limit probability s1', again
Generate picture review probability interval.
In one embodiment, it is not plan deliberately to obtain each picture in the pictures corresponding with original review probability interval
After the bad probability of piece, in addition to：Obtain the picture system weights of image transmission system corresponding to pictures；According to two classification
Probability is calculated original Upper Probability and original lower limit probability, regenerates picture review probability interval, including：According to two
Class probability and picture system weights, are calculated original Upper Probability and original lower limit probability, regenerate picture review
Probability interval.
In above-described embodiment, uniformly it is mapped to by the probability for the picture for exporting imperfect picture identification systems bad
Probability is compared, and result of the picture according to corresponding to original review probability interval after artificial review, is counted by review
It is determined as the first quantity of normal picture, and is determined as the second quantity of imperfect picture by review, according to the first quantity and second
Quantity is calculated original review probability interval, regenerates picture review probability interval.After combining artificial review
As a result, review probability interval is adjusted so that newly-generated picture review probability interval scope is more accurate, reduces picture
The workload of review, so as to improve the efficiency of imperfect picture review.
In one embodiment, as shown in Figure 6, there is provided a kind of picture review probability interval generating means 600, the device
Including：Bad probability acquisition module 602, it is for obtaining each picture in the pictures corresponding with original review probability interval
The bad probability of imperfect picture；Picture judges quantity statistical module 604, for having the figure of identical bad probability for every group
Piece, the first quantity for being determined as normal picture by review is counted, and be determined as the second quantity of imperfect picture by review；Picture is answered
Probability interval generation module 606 is examined, figure is regenerated for the first quantity and the second quantity according to corresponding to every group of bad probability
Piece review probability interval.
In one embodiment, as shown in Figure 7, there is provided another picture review probability interval generating means 700, the dress
Putting, which also includes original review pictures, forms module 601, and for obtaining in default pictures, each picture is the first of imperfect picture
Beginning probability；Probability corresponding to each picture is calculated, it is imperfect picture to generate each picture in default pictures
Bad probability；Original review probability interval is set, and extracts picture corresponding to the bad probability positioned at original review probability interval,
Form the pictures corresponding with original review probability interval.
In one embodiment, picture review probability interval generation module 606 is additionally operable to obtain original review probability interval
Original Upper Probability and original lower limit probability；Two class probabilities are gone out according to original Upper Probability and original lower limit probability calculation,
The second quantity sum corresponding to original lower limit probability to two class probabilities can be obtained by two class probabilities, it is general with two classification
The first quantity sum corresponding to rate to original Upper Probability, the minimum value of the two summation；According to two class probabilities on original
Limit probability and original lower limit probability are calculated, and regenerate picture review probability interval.
In one embodiment, picture review probability interval generation module 606 is additionally operable to when two class probabilities are less than or equal to
During predetermined probabilities, according to formulaCalculated, regenerate Upper Probability s2', wherein, s1
For original lower limit probability, s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；When two class probabilities are more than in advance
If during probability, according to formulaCalculated, regenerate lower limit probability s1', wherein, s1To be original
Lower limit probability, s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；According to new Upper Probability s2' or new
Lower limit probability s1', regenerate picture review probability interval.
In one embodiment, picture review probability interval generation module 606 is additionally operable to obtain picture corresponding to pictures
The picture system weights of Transmission system；According to two class probabilities and picture system weights, to original Upper Probability and original lower limit
Probability is calculated, and regenerates picture review probability interval.
In one embodiment, as shown in Figure 8, there is provided a kind of picture review decision maker 800, the device includes：Treat
The bad probability acquisition module 802 of picture is identified, for obtaining the bad probability that picture to be identified is imperfect picture；Picture review is sentenced
Disconnected module 804, for judging bad probability whether within default picture review probability interval, picture review probability interval
Generation method includes：It is the bad general of imperfect picture to obtain each picture in the pictures corresponding with original review probability interval
Rate；In the picture for every group with identical bad probability, the first quantity for being determined as normal picture by review is counted, and answered
Trial is set to the second quantity of imperfect picture；Figure is regenerated according to the first quantity and the second quantity corresponding to every group of bad probability
Piece review probability interval；If so, then judge that picture to be identified needs to carry out picture review.
In one embodiment, each picture is bad in the pictures corresponding with original review probability interval are obtained
Before the bad probability of picture, including：Obtain in default pictures, each picture is the probability of imperfect picture；To each
Probability is calculated corresponding to picture, generates the bad probability that each picture in default pictures is imperfect picture；Setting
Original review probability interval, and extract positioned at original review probability interval bad probability corresponding to picture, formed with it is original multiple
Examine the corresponding pictures of probability interval.
In one embodiment, the first quantity and the second quantity according to corresponding to every group of bad probability regenerate picture and answered
Probability interval is examined, including：Obtain original Upper Probability and the original lower limit probability of original review probability interval；According to the original upper limit
Probability and original lower limit probability calculation go out two class probabilities, and original lower limit probability can be obtained to two classification by two class probabilities
The second quantity sum corresponding to probability, and the first quantity sum corresponding to two class probabilities to original Upper Probability, the two
The minimum value of summation；Original Upper Probability and original lower limit probability are calculated according to two class probabilities, regenerate picture
Review probability interval.
In one embodiment, original Upper Probability and original lower limit probability are calculated according to two class probabilities, weight
Newly-generated picture review probability interval, including：When two class probabilities are less than or equal to predetermined probabilities, according to formulaCalculated, regenerate Upper Probability s2', wherein, s1For original lower limit probability, s2For
Original Upper Probability, t are two class probabilities, x0For predetermined probabilities；When two class probabilities are more than predetermined probabilities, according to formulaCalculated, regenerate lower limit probability s1', wherein, s1For original lower limit probability, s2To be original
Upper Probability, t are two class probabilities, x0For predetermined probabilities；According to new Upper Probability s2' or new lower limit probability s1', again
Generate picture review probability interval.
In one embodiment, it is not plan deliberately to obtain each picture in the pictures corresponding with original review probability interval
After the bad probability of piece, in addition to：Obtain the picture system weights of image transmission system corresponding to pictures；According to two classification
Probability is calculated original Upper Probability and original lower limit probability, regenerates picture review probability interval, including：According to two
Class probability and picture system weights, are calculated original Upper Probability and original lower limit probability, regenerate picture review
Probability interval.
Above-mentioned picture review probability interval generating means and picture review decision maker can be implemented as a kind of computer
The form of program, computer program can be run on such as Fig. 9 the first computer equipment.It is non-volatile on first computer equipment
Property storage medium can store each program mould for forming the picture review probability interval generating means and picture review decision maker
Bad probability acquisition module 602, picture in block, such as Fig. 6 judge quantity statistical module 604, the life of picture review probability interval
Into the bad probability acquisition module 802 of picture to be identified in module 606 and Fig. 8 and picture review judge module 804 etc..It is each
Program module includes computer program, and the application that computer program is used to make server perform described in this specification is each
Step in the picture review probability interval generation method and picture review decision method of embodiment, in the first computer equipment
Processor can call the picture review probability interval stored in the non-volatile memory medium of the first computer equipment to generate dress
Each program module with picture review decision maker is put, computer program corresponding to operation, realizes that picture is answered in this specification
Examine function corresponding to the modules of probability interval generating means and picture review decision maker.
In one embodiment, there is provided a kind of computer-readable recording medium, be stored thereon with computer program, the journey
Following steps are realized when sequence is executed by processor：Obtaining each picture in the pictures corresponding with original review probability interval is
The bad probability of imperfect picture；For every group of picture with identical bad probability, count and normal picture is determined as by review
First quantity, and it is determined as by review the second quantity of imperfect picture；According to the first quantity corresponding to every group of bad probability and
Two quantity regenerate picture review probability interval.
In one embodiment, when the program is executed by processor, acquisition and the original review probability interval phase realized
It is further comprising the steps of before each picture is the bad probability step of imperfect picture in corresponding pictures：Obtain default figure
Piece is concentrated, and each picture is the probability of imperfect picture；Probability corresponding to each picture is calculated, generation is default
Each picture is the bad probability of imperfect picture in pictures；Original review probability interval is set, and extracts and is located at original review
Picture corresponding to the bad probability of probability interval, form the pictures corresponding with original review probability interval.
In one embodiment, when the program is executed by processor, realized according to corresponding to every group of bad probability
One quantity and the second quantity regenerate the step of picture review probability interval, specifically include following steps：Obtain original review
Original Upper Probability and the original lower limit probability of probability interval；Go out two points according to original Upper Probability and original lower limit probability calculation
Class probability, the second quantity sum corresponding to original lower limit probability to two class probabilities can be obtained by two class probabilities, with
The first quantity sum corresponding to two class probabilities to original Upper Probability, the minimum value of the two summation；According to two class probabilities
Original Upper Probability and original lower limit probability are calculated, regenerate picture review probability interval.
In one embodiment, when the program is executed by processor, realized according to two class probabilities to the original upper limit
Probability and original lower limit probability are calculated, the step of regenerating picture review probability interval, specifically include following steps：When
When two class probabilities are less than or equal to predetermined probabilities, according to formulaCalculated, regenerated
Upper Probability s2', wherein, s1For original lower limit probability, s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；
When two class probabilities are more than predetermined probabilities, according to formulaCalculated, it is general to regenerate lower limit
Rate s1', wherein, s1For original lower limit probability, s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；According to new
Upper Probability s2' or new lower limit probability s1', regenerate picture review probability interval.
In one embodiment, when the program is executed by processor, acquisition and the original review probability interval phase realized
After the step of each picture is the bad probability of imperfect picture in corresponding pictures, in addition to：Obtain corresponding to pictures
The picture system weights of image transmission system；Realized according to two class probabilities to original Upper Probability and original lower limit probability
Calculated, the step of regenerating picture review probability interval, specifically included：Weighed according to two class probabilities and picture system
Value, calculates original Upper Probability and original lower limit probability, regenerates picture review probability interval.
In one embodiment, there is provided a kind of computer-readable recording medium, be stored thereon with computer program, the journey
Following steps are realized when sequence is executed by processor：Obtain the bad probability that picture to be identified is imperfect picture；Judge bad probability
Whether within default picture review probability interval, picture of the picture review probability interval in above-mentioned each embodiment is answered
Examine probability interval generation method and generate.
In one embodiment, there is provided a kind of computer equipment, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize following steps in configuration processor：：Obtain and original review
Each picture is the bad probability of imperfect picture in the corresponding pictures of probability interval；There is identical bad probability for every group
Picture, count the first quantity for being determined as normal picture by review, and be determined as the second quantity of imperfect picture by review；Root
Picture review probability interval is regenerated according to the first quantity and the second quantity corresponding to every group of bad probability.
In one embodiment, during above-mentioned computing device program, acquisition and the original review probability interval phase realized
It is further comprising the steps of before the step of each picture is the bad probability of imperfect picture in corresponding pictures：Obtain default
In pictures, each picture is the probability of imperfect picture；Probability corresponding to each picture is calculated, generation is pre-
If each picture is the bad probability of imperfect picture in pictures；Original review probability interval is set, and is extracted positioned at original multiple
Picture corresponding to the bad probability of probability interval is examined, forms the pictures corresponding with original review probability interval.
In one embodiment, during above-mentioned computing device program, realized according to corresponding to every group of bad probability
One quantity and the second quantity regenerate the step of picture review probability interval, specifically include following steps：Obtain original review
Original Upper Probability and the original lower limit probability of probability interval；Go out two points according to original Upper Probability and original lower limit probability calculation
Class probability, the second quantity sum corresponding to original lower limit probability to two class probabilities can be obtained by two class probabilities, with
The first quantity sum corresponding to two class probabilities to original Upper Probability, the minimum value of the two summation；According to two class probabilities
Original Upper Probability and original lower limit probability are calculated, regenerate picture review probability interval.
In one embodiment, during above-mentioned computing device program, realized according to two class probabilities to the original upper limit
Probability and original lower limit probability are calculated, the step of regenerating picture review probability interval, specifically include following steps：When
When two class probabilities are less than or equal to predetermined probabilities, according to formulaCalculated, regenerated
Upper Probability s2', wherein, s1For original lower limit probability, s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；
When two class probabilities are more than predetermined probabilities, according to formulaCalculated, it is general to regenerate lower limit
Rate s1', wherein, s1For original lower limit probability, s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；According to new
Upper Probability s2' or new lower limit probability s1', regenerate picture review probability interval.
In one embodiment, during above-mentioned computing device program, acquisition and the original review probability interval phase realized
After the step of each picture is the bad probability of imperfect picture in corresponding pictures, in addition to：Obtain corresponding to pictures
The picture system weights of image transmission system；Realized according to two class probabilities to original Upper Probability and original lower limit probability
Calculated, the step of regenerating picture review probability interval, specifically included：Weighed according to two class probabilities and picture system
Value, calculates original Upper Probability and original lower limit probability, regenerates picture review probability interval.
In one embodiment, there is provided a kind of computer equipment, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor realize following steps in configuration processor：Obtain picture to be identified
For the bad probability of imperfect picture；Bad probability is judged whether within default picture review probability interval, and picture review is general
Picture review probability interval generation method of the rate section in above-mentioned each embodiment and generate.
In one embodiment, above-mentioned computer equipment may include but be not limited to independent physical server, either
The server cluster that multiple physical servers are formed.It is that the internal structure of the first computer equipment in one embodiment is shown such as Fig. 9
It is intended to.The first computer equipment 102 that first computer equipment can be applied in Fig. 1 application environment.First computer
Equipment includes processor, non-volatile memory medium, built-in storage and the network interface connected by system bus.Wherein, should
The processor of first computer equipment is used to provide calculating and control ability, supports the operation of whole first computer equipment.The
The non-volatile memory medium of one computer equipment is stored with operating system, database and computer program.Deposited in the database
A kind of picture review probability interval generation method provided for each embodiment more than realizing is provided and picture review judges
The related data of method, for example the probability in default pictures corresponding to each pictures can be stored with.The computer
Program can be performed by processor, for realizing that a kind of picture review probability interval that each embodiment is provided above generates
Method and a kind of picture review decision method.Built-in storage in first computer equipment is the behaviour in non-volatile memory medium
Make the running environment that system, database and computer program provide cache.Network interface can be Ethernet card or wireless
Network interface card etc., for outside terminal or server communicated, such as with the second computer equipment in Fig. 1 application environment
104 are communicated, and obtain the probability that each picture in default pictures is imperfect picture.
It will be understood by those skilled in the art that the structure of the first computer equipment shown in Fig. 9, it is only and the application
The block diagram of the related part-structure of scheme, the limit for the first computer equipment being applied thereon to application scheme is not formed
Fixed, specific first computer equipment can include, than more or less parts in figure, either combining some parts or tool
There is different part arrangements.For example the first computer equipment in the figure may also include display screen etc..
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, described program can be stored in a non-volatile computer and can be read
In storage medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage is situated between
Matter can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more specific and detailed, but simultaneously
Can not therefore it be construed as limiting the scope of the patent.It should be pointed out that come for one of ordinary skill in the art
Say, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of picture review probability interval generation method, methods described include：
Obtain the bad probability that each picture in the pictures corresponding with original review probability interval is imperfect picture；
For every group of picture with identical bad probability, the first quantity for being determined as normal picture by review is counted, and answered
Trial is set to the second quantity of imperfect picture；
Picture review probability interval is regenerated according to the first quantity and the second quantity corresponding to every group of bad probability.
2. according to the method for claim 1, it is characterised in that corresponding with original review probability interval in the acquisition
Before each picture is the bad probability of imperfect picture in pictures, including：
Obtain in default pictures, each picture is the probability of imperfect picture；
Probability corresponding to each picture is calculated, it is imperfect picture to generate each picture in the default pictures
Bad probability；
Original review probability interval is set, and extracts picture corresponding to the bad probability positioned at original review probability interval, is formed
The pictures corresponding with the original review probability interval.
3. according to the method for claim 1, it is characterised in that first quantity according to corresponding to every group of bad probability and
Second quantity regenerates picture review probability interval, including：
Obtain original Upper Probability and the original lower limit probability of the original review probability interval；
Two class probabilities are gone out according to the original Upper Probability and original lower limit probability calculation, can by two class probability
The second quantity sum corresponding to original lower limit probability to two class probabilities is obtained, with two class probabilities to original Upper Probability institute
Corresponding first quantity sum, the minimum value of the two summation；
Original Upper Probability and original lower limit probability are calculated according to two class probability, it is general to regenerate picture review
Rate section.
4. the method stated according to claim 3, it is characterised in that it is described according to two class probability to original Upper Probability and
Original lower limit probability is calculated, and regenerates picture review probability interval, including：
When two class probabilities are less than or equal to predetermined probabilities, according to formulaCalculated, weight
Newly-generated Upper Probability s2', wherein, s1For original lower limit probability, s2For original Upper Probability, t is two class probabilities, x0To be pre-
If probability；
When two class probabilities are more than predetermined probabilities, according to formulaCalculated, regenerate lower limit
Probability s1', wherein, s1For original lower limit probability, s2For original Upper Probability, t is two class probabilities, x0For predetermined probabilities；
According to the new Upper Probability s2' or the new lower limit probability s1', regenerate picture review probability interval.
5. according to the method for claim 3, it is characterised in that described to obtain the figure corresponding with original review probability interval
After piece concentrates each picture as the bad probability of imperfect picture, in addition to：
Obtain the picture system weights of image transmission system corresponding to the pictures；
It is described that original Upper Probability and original lower limit probability are calculated according to two class probability, regenerate picture and answer
Probability interval is examined, including：
According to two class probability and the picture system weights, original Upper Probability and original lower limit probability are counted
Calculate, regenerate picture review probability interval.
6. a kind of picture review decision method, methods described include：
Obtain the bad probability that picture to be identified is imperfect picture；
Judge the bad probability whether within default picture review probability interval, the picture review probability interval according to
Picture review probability interval generation method any one of claim 1 to 5 generates；
If so, then judge that the picture to be identified needs to carry out picture review.
7. a kind of picture review probability interval generating means, it is characterised in that described device includes：
Bad probability acquisition module, it is bad for obtaining each picture in the pictures corresponding with original review probability interval
The bad probability of picture；
Picture judges quantity statistical module, for having the picture of identical bad probability for every group, counts and is determined as by review
First quantity of normal picture, and it is determined as by review the second quantity of imperfect picture；
Picture review probability interval generation module, for the first quantity and the second quantity to be again according to corresponding to every group of bad probability
Generate picture review probability interval.
8. a kind of picture review decision maker, it is characterised in that described device includes：
The bad probability acquisition module of picture to be identified, for obtaining the bad probability that picture to be identified is imperfect picture；
Picture review judge module, for judging the bad probability whether within default picture review probability interval, institute
Picture review probability interval picture review probability interval generation method according to any one of claim 1 to 5 is stated to generate；If
It is then to judge that the picture to be identified needs to carry out picture review.
9. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is held by processor
The step of any one methods described in claim 1 to 6 is realized during row.
10. a kind of computer equipment, including memory, processor and storage are on a memory and the meter that can run on a processor
Calculation machine program, it is characterised in that side described in any one in claim 1 to 6 is realized during the computing device described program
The step of method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710876917.1A CN107729924B (en) | 2017-09-25 | 2017-09-25 | Picture review probability interval generation method and picture review determination method |
| PCT/CN2017/108480 WO2019056496A1 (en) | 2017-09-25 | 2017-10-31 | Method for generating picture review probability interval and method for picture review determination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710876917.1A CN107729924B (en) | 2017-09-25 | 2017-09-25 | Picture review probability interval generation method and picture review determination method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107729924A true CN107729924A (en) | 2018-02-23 |
| CN107729924B CN107729924B (en) | 2019-02-19 |
Family
ID=61206890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710876917.1A Active CN107729924B (en) | 2017-09-25 | 2017-09-25 | Picture review probability interval generation method and picture review determination method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107729924B (en) |
| WO (1) | WO2019056496A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491866A (en) * | 2018-03-06 | 2018-09-04 | 平安科技（深圳）有限公司 | Porny identification method, electronic device and readable storage medium storing program for executing |
| CN109491970A (en) * | 2018-10-11 | 2019-03-19 | 平安科技（深圳）有限公司 | Imperfect picture detection method, device and storage medium towards cloud storage |
| CN109886865A (en) * | 2019-01-07 | 2019-06-14 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of automatic shield flame |
| CN112445410A (en) * | 2020-12-07 | 2021-03-05 | 北京小米移动软件有限公司 | Touch event identification method and device and computer readable storage medium |
| CN113095563A (en) * | 2021-04-07 | 2021-07-09 | 全球能源互联网研究院有限公司 | Method and device for reviewing prediction result of artificial intelligence model |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101692639A (en) * | 2009-09-15 | 2010-04-07 | 西安交通大学 | Bad webpage recognition method based on URL |
| CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
| CN102340424A (en) * | 2010-07-21 | 2012-02-01 | 中国移动通信集团山东有限公司 | Bad message detection method and bad message detection device |
| CN102663093A (en) * | 2012-04-10 | 2012-09-12 | 中国科学院计算机网络信息中心 | Method and device for detecting bad website |
| CN103064858A (en) * | 2011-10-19 | 2013-04-24 | 北京千橡网景科技发展有限公司 | Method and apparatus for objectionable image detection in social networking websites |
| US20140185918A1 (en) * | 2011-09-29 | 2014-07-03 | Hitachi High-Technologies Corporation | Charged particle beam apparatus that performs image classification assistance |
| CN105654057A (en) * | 2015-12-31 | 2016-06-08 | 中国建设银行股份有限公司 | Picture auditing system and picture auditing method based on picture contents |
| CN107145904A (en) * | 2017-04-28 | 2017-09-08 | 北京小米移动软件有限公司 | Determination method, device and the storage medium of image category |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359372B (en) * | 2008-09-26 | 2011-05-11 | 腾讯科技（深圳）有限公司 | Training method and device of classifier, method and apparatus for recognising sensitization picture |
| CN106485528A (en) * | 2015-09-01 | 2017-03-08 | 阿里巴巴集团控股有限公司 | The method and apparatus of detection data |
| CN106776842B (en) * | 2016-11-28 | 2021-03-19 | 腾讯科技（上海）有限公司 | Multimedia data detection method and device |
-
2017
- 2017-09-25 CN CN201710876917.1A patent/CN107729924B/en active Active
- 2017-10-31 WO PCT/CN2017/108480 patent/WO2019056496A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101996180A (en) * | 2009-08-12 | 2011-03-30 | 升东网络科技发展(上海)有限公司 | Picture examination and filter system and method |
| CN101692639A (en) * | 2009-09-15 | 2010-04-07 | 西安交通大学 | Bad webpage recognition method based on URL |
| CN102340424A (en) * | 2010-07-21 | 2012-02-01 | 中国移动通信集团山东有限公司 | Bad message detection method and bad message detection device |
| US20140185918A1 (en) * | 2011-09-29 | 2014-07-03 | Hitachi High-Technologies Corporation | Charged particle beam apparatus that performs image classification assistance |
| CN103064858A (en) * | 2011-10-19 | 2013-04-24 | 北京千橡网景科技发展有限公司 | Method and apparatus for objectionable image detection in social networking websites |
| CN102663093A (en) * | 2012-04-10 | 2012-09-12 | 中国科学院计算机网络信息中心 | Method and device for detecting bad website |
| CN105654057A (en) * | 2015-12-31 | 2016-06-08 | 中国建设银行股份有限公司 | Picture auditing system and picture auditing method based on picture contents |
| CN107145904A (en) * | 2017-04-28 | 2017-09-08 | 北京小米移动软件有限公司 | Determination method, device and the storage medium of image category |
Non-Patent Citations (2)
| Title |
|---|
| AZHAM MD. ALI等: ""Internal Audit in the Federal Government Organizations of Malaysia: The Good, The Bad and The Very Ugly?"", 《ASIAN JOURNAL OF BUSINESS AND GOVERNANCE》 * |
| YU FEI等: ""Information audit based on image content filtering"", 《WUHAN UNIVERSITY JOURNAL OF NATURAL SCIENCES》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491866A (en) * | 2018-03-06 | 2018-09-04 | 平安科技（深圳）有限公司 | Porny identification method, electronic device and readable storage medium storing program for executing |
| CN109491970A (en) * | 2018-10-11 | 2019-03-19 | 平安科技（深圳）有限公司 | Imperfect picture detection method, device and storage medium towards cloud storage |
| CN109886865A (en) * | 2019-01-07 | 2019-06-14 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of automatic shield flame |
| CN109886865B (en) * | 2019-01-07 | 2024-01-23 | 平安科技（深圳）有限公司 | Method, device, computer equipment and storage medium for automatically shielding bad information |
| CN112445410A (en) * | 2020-12-07 | 2021-03-05 | 北京小米移动软件有限公司 | Touch event identification method and device and computer readable storage medium |
| CN112445410B (en) * | 2020-12-07 | 2023-04-18 | 北京小米移动软件有限公司 | Touch event identification method and device and computer readable storage medium |
| CN113095563A (en) * | 2021-04-07 | 2021-07-09 | 全球能源互联网研究院有限公司 | Method and device for reviewing prediction result of artificial intelligence model |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019056496A1 (en) | 2019-03-28 |
| CN107729924B (en) | 2019-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107729924B (en) | Picture review probability interval generation method and picture review determination method | |
| CN107767021A (en) | A kind of risk control method and equipment | |
| US20220245472A1 (en) | Data processing method and apparatus, and non-transitory computer readable storage medium | |
| WO2020082733A1 (en) | Method for message push request flow control based on service rules, device and medium | |
| CN107046468A (en) | A kind of physical layer certification thresholding determines method and system | |
| CN104615760A (en) | Phishing website recognizing method and phishing website recognizing system | |
| CN112380570A (en) | Data analysis method applied to block chain and edge computing server | |
| CN108108743A (en) | Abnormal user recognition methods and the device for identifying abnormal user | |
| CN107517394A (en) | Identify the method, apparatus and computer-readable recording medium of disabled user | |
| CN110046297B (en) | Operation and maintenance violation identification method and device and storage medium | |
| CN108243191A (en) | Risk behavior recognition methods, storage medium, equipment and system | |
| WO2021208695A1 (en) | Method and apparatus for target item recommendation, electronic device, and computer readable storage medium | |
| CN107491674A (en) | Feature based information carries out the method and device of user's checking | |
| CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
| CN104484600B (en) | Intrusion detection method and device based on improved density clustering | |
| CN110348238A (en) | A kind of application oriented secret protection stage division and device | |
| CN109905328A (en) | The recognition methods of data flow and device | |
| CN109918678A (en) | A kind of field meanings recognition methods and device | |
| CN109583228A (en) | A kind of privacy information management method, device and system | |
| CN109492031A (en) | Display methods, server and the computer storage medium of list data | |
| CN110335143A (en) | Financial Risk Analysis method, apparatus and electronic equipment based on multiple temporal verifying | |
| CN110222187B (en) | Common activity detection and data sharing method for protecting user privacy | |
| CN109218211A (en) | The method of adjustment of threshold value, device and equipment in the control strategy of data flow | |
| CN114598556B (en) | IT infrastructure configuration integrity protection method and protection system | |
| CN114296775B (en) | Intelligent operation and maintenance method and system based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |