CN108596559A - Task automates checking method, device, equipment and storage medium - Google Patents
Task automates checking method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN108596559A CN108596559A CN201810239757.4A CN201810239757A CN108596559A CN 108596559 A CN108596559 A CN 108596559A CN 201810239757 A CN201810239757 A CN 201810239757A CN 108596559 A CN108596559 A CN 108596559A
- Authority
- CN
- China
- Prior art keywords
- image
- audit
- terminal app
- similarity
- sent
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012550 audit Methods 0.000 claims abstract description 147
- 238000000605 extraction Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 17
- 230000005540 biological transmission Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 210000003128 head Anatomy 0.000 description 4
- 210000004709 eyebrow Anatomy 0.000 description 2
- 210000004209 hair Anatomy 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/06—Protocols specially adapted for file transfer, e.g. file transfer protocol [FTP]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Economics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to business audit technical field, more particularly to a kind of task automation checking method, device, equipment and storage medium, task automation checking method include:Mission bit stream is sent to terminal APP;Receive the character image that terminal APP is sent, character image and default character image are subjected to comparison audit, and send auditing result to terminal APP, when audit passes through, obtain the ground point image that terminal APP is sent, ground point image and preset location image are subjected to comparison audit, and send auditing result to terminal APP, when audit passes through, obtain the contract image that terminal APP is sent, whether the contract signing page in audit contract image meets preset rules, and send auditing result to terminal APP, when audit passes through, confirm completion task, technical solution of the present invention can receive the image information that terminal APP is sent, it is audited automatically according to the preset image information of system server, improve audit rate and accuracy.
Description
Technical field
The present invention relates to business audit technical field more particularly to a kind of task automation checking method, device, equipment and
Storage medium.
Background technology
Current operation personnel go, from when handling various businesses, to need business personnel to shoot action by mobile phone, will scheme
As after being uploaded to system server, the image received in system server needs auditor to audit, auditor's root
Determine whether business personnel completes task, whether by specification progress business operation etc. according to shooting image.When upload photo compared with
When more, auditor is difficult to audit in time, and auditor is subjective in review process, also will appear accuracy rate not
High situation.Therefore, exist in the prior art that manual examination and verification image work amount is big, audit speed is slow and accuracy rate is not high asks
Topic.
Invention content
The purpose of the present invention is to provide a kind of task automation checking method, device, equipment and storage medium, Neng Goushi
Existing system server automatically audits the image received.
The invention is realized in this way first aspect present invention provides a kind of task automation checking method, including:
Step S10. sends mission bit stream to terminal APP, and the mission bit stream includes the shooting image of each workflow
Information;
Step S20. receives the character image that the terminal APP is sent, by the character image and default character image into
Row comparison audit, and auditing result is sent to the terminal APP, when audit passes through, step S30 is executed, when audit does not pass through
When, re-execute step S20;
Step S30. obtains the ground point image that the terminal APP is sent, by described ground point image and preset location image into
Row comparison audit, and auditing result is sent to the terminal APP, when audit passes through, step S40 is executed, when audit does not pass through
When, re-execute step S30;
Step S40. obtains the contract image that the terminal APP is sent, and audits the contract signing page in the contract image
Whether meet preset rules, and auditing result is sent to the terminal APP, when audit passes through, confirms completion task, work as audit
It is obstructed out-of-date, re-execute step S40.
Second aspect of the present invention provides a kind of task automation audit device, and the task automation audit device includes:
Mission bit stream sending module, for sending mission bit stream to terminal APP, the mission bit stream includes each workflow
The shooting image information of journey;
Character image auditing module, the character image sent for receiving the terminal APP, by the character image and in advance
If character image carries out comparison audit, and sends auditing result to the terminal APP;
Place image audit module, for obtaining the terminal APP when character image auditing module audit passes through
Described ground point image and preset location image are carried out comparison audit, and send and examine to the terminal APP by the ground point image of transmission
Core result;
Contract image audit module, for obtaining the terminal APP when place image audit module audit passes through
The contract image of transmission audits the contract signing page in the contract image and whether meets preset rules, and to the terminal APP
Auditing result is sent, and when audit passes through, confirms completion task.
Third aspect present invention provides a kind of terminal device, including memory, processor and is stored in the memory
In and the computer program that can run on the processor, the processor realize such as this hair when executing the computer program
The step of bright first aspect the method.
Fourth aspect present invention provides a kind of computer readable storage medium, and the computer-readable recording medium storage has
Computer program, when the computer program is executed by processor realize as described in the first aspect of the invention method the step of.
A kind of task automation checking method of present invention offer, device, equipment and storage medium, system server is according to stream
The instruction of Cheng personnel forms mission bit stream, and mission bit stream is sent to specified terminal APP, obtains the figure that terminal APP is uploaded
Preset image information is audited automatically in picture information, with system server, is generated auditing result and is simultaneously sent to terminal APP,
And execution workflow is automatically selected according to auditing result, the automation audit of task is realized, the accuracy rate of audit is improved
With accelerate audit speed.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment for those of ordinary skill in the art without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of flow chart for task automation checking method that an embodiment of the present invention provides;
Fig. 2 is a kind of particular flow sheet for task automation checking method step S20 that an embodiment of the present invention provides;
Fig. 3 is a kind of particular flow sheet for task automation checking method step S30 that an embodiment of the present invention provides;
Fig. 4 is a kind of particular flow sheet for task automation checking method step S40 that an embodiment of the present invention provides;
Fig. 5 is a kind of structural schematic diagram for task automation audit device that second embodiment of the invention provides;
Fig. 6 is the character image auditing module in a kind of task automation audit device that second embodiment of the invention provides
52 structural schematic diagram;
Fig. 7 is the structural schematic diagram for the terminal device that third embodiment of the invention provides.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
In order to illustrate technical scheme of the present invention, illustrated below by specific embodiment.
Embodiment 1
First embodiment of the invention provides a kind of task automation checking method, which automates the execution of checking method
Side is system server, as shown in Figure 1, task automation checking method includes:
Step S10. sends mission bit stream to terminal APP, and the mission bit stream includes the shooting image of each workflow
Information.
Wherein, system server forms mission bit stream according to the instruction of flow personnel, and mission bit stream is sent to specified
Terminal APP, mission bit stream is made of multiple tactic workflows, and each workflow includes specific executing thing
, such as time, place and the content of shooting of task are executed, as an implementation, the shooting image of workflow is believed
Breath includes this subtask shooting people information, the shooting building image information for executing task and this subtask shooting contract label
Page information is ordered, this step may be implemented to send mission bit stream to terminal APP, allow business personnel according to the work in mission bit stream
The efficiency that flow operates execution, improves completion task step by step.
Specifically, for example, the instruction that flow personnel send out is that " business personnel A was gone 10 points to 12 points of November 11 in 2017
Safety JinRong Building carries out insurance contract negotiation and signing with client ", system server forms corresponding appoint after receiving the instruction
Business information, mission bit stream include:This task execution staff is " business personnel A ", executes the period of task as November 1 in 2017
Days 10 points to 12 points, to execute task place be safety JinRong Building, execution task is to sign a contract and shoot contract signing page figure
Then the mission bit stream is sent to specified terminal APP by picture.
Step S20. receives the character image that the terminal APP is sent, by the character image and default character image into
Row comparison audit, and auditing result is sent to the terminal APP, when audit passes through, step S30 is executed, when audit does not pass through
When, re-execute step S20;
Wherein, system server receives the character image that business personnel is sent by terminal APP, and character image refers to executing to appoint
The self-timer image of the business personnel of business, default character image refer to business personnel's image that system server stores in advance, when receiving
It, can be according to corresponding business in the identifier extraction system server of terminal APP after the character image that terminal APP is sent
Member's image simultaneously carries out comparison audit therewith, when images match, sends audit to terminal APP and passes through as a result, terminal APP is made to enter
Next workflow sends audit not by as a result, terminal APP is made to keep the work when image is mismatched to terminal APP
Flow, until business personnel uploads correct image.By the way that this step is arranged, may be implemented to recognize the related service personnel of handling
Card ensures that specified services person handles inter-related task.
Specifically, for example, system server receives the character image for the business personnel A that terminal APP is sent, to image progress
Pretreatment, according to the character image of the corresponding business personnel A stored in advance in the identifier extraction system server of terminal APP
Information, and comparison audit is carried out with pretreated image information, when images match success, determine business personnel.Audit is logical
Cross, to terminal APP send it is that audit passes through as a result, and execute step S30, when images match fail, such as when shooting image
Light is too dark or too bright influence compares audit, re-executes step S20 until determining corresponding business personnel.
As an embodiment of the present embodiment, as shown in Fig. 2, in step S20 by the character image with it is pre-
If character image carries out comparison audit, and sends auditing result to the terminal APP, including:
Step S201 determines human face region according to character image.
Step S202, extracts characteristic information from the human face region, and by the characteristic information and default character image
Characteristic information carry out similarity comparison.
Step S203 sends audit to the terminal APP and passes through when the similarity is not less than default similarity threshold
As a result, when the similarity is less than default similarity threshold, to the terminal APP send audit not by result.
In above step S201 to step S203, character image refers to the personage that system server receiving terminal APP is sent
Image, human face region refer to the face area of business personnel in character image, and characteristic information refers to people information in human face region, example
Such as, everyone face characteristic information, it refers to that comparison carries that the character image is carried out the comparison of phase knowledge and magnanimity with default character image
The characteristic information taken and the preset characteristic information of system server, the character image generation sent first according to terminal APP is received
Personal feature head portrait determines the region of face in photo, for example, can be carried to the region of face progress integral projection and edge
It takes, determines face's ellipse precise boundary.Characteristic information is extracted according to the human face region of the personal feature head portrait of generation, for example,
The size of personal feature head portrait is uniformly put, so that the human face region in personal feature head portrait is fixed to pre-set dimension and extracts face again
The characteristic information of local feature information in region, extraction includes face local feature information and the feature using the extraction of LBP algorithms
Vector, face local feature information include:The central point information and the boundary point of boundary point information and face of local feature are believed
Breath, local feature include at least:Any one in nose, face, left eye, right eye, left eyebrow and right eyebrow is several and combinations thereof, will
Local feature information is as fisrt feature information;Using LBP algorithms, the LBP characteristic spectrums of human face region local feature are counted, according to
LBP characteristic spectrums make LBP histograms, the feature vector of LBP histograms are extracted, using the set of feature vector as second feature
Information.The characteristic information of the characteristic information of extraction and the character image to prestore is carried out similarity to compare, similarity comparison refers to
The characteristic information of extraction and preset characteristic information are compared, when similarity is not less than default similarity threshold, then compares success,
It sends through auditing result to terminal APP, when the similarity is less than default similarity threshold, is sent to the terminal APP
Audit not by result.
As an embodiment of the present embodiment, in step S203 by the characteristic information and default character image
Characteristic information carry out similarity comparison, including:
The face local feature information and the first model characteristic information comparison of default character image are obtained into the first phase
Like degree, and the second model characteristic information of described eigenvector and default character image is subjected to comparison and obtains the second similarity;
When first similarity and second similarity be not less than the default similarity threshold, then judgement described in
Similarity is more than the default similarity threshold, and audit passes through;
When in first similarity and second similarity any similarity be less than the default similarity threshold, then
Judge that the similarity is not more than the default similarity threshold, audit does not pass through.
In above step, face local feature information includes:The central point information and boundary point information of local feature with
And the boundary point information of face presets the first model feature of character image using local feature information as fisrt feature information
Information refers to business personnel personage's face local feature information that system server prestores, and feature vector refers to be extracted using LBP algorithms
The feature vector of human face region local feature LBP histograms presets personage using the set of feature vector as second feature information
Second model characteristic information of image refers to the LPB features of the business personnel's character facial region local feature to prestore in system server
Vector, the first similarity are compared by the face local feature information of extraction and the first model characteristic information of default character image
It obtains, the second similarity carries out comparison with the second model characteristic information of default character image by the feature vector of extraction and obtains
It takes, for example, the characteristic information of the characteristic information of extraction and default character image is carried out similarity comparison, the characteristic information of extraction
It is during similarity comparison, first in the characteristic information of extraction is special including fisrt feature information and second feature information
Reference is ceased to be compared with the first model characteristic information progress similarity in feature database, and it is special with the first model to calculate fisrt feature information
Cosine value distance between the corresponding information of reference manner of breathing, according to the first similarity of cosine value Distance Judgment, cosine value distance is got over
Greatly, the first similarity is bigger;Second feature information in the characteristic information of extraction is believed with the second model feature in feature database
Breath carry out similarity comparison, calculate second feature information information corresponding with the second model characteristic information between cosine value away from
From according to the second similarity of cosine value Distance Judgment, cosine value distance is bigger, and the second similarity is bigger;When the first similarity and
Second similarity is not less than default similarity threshold, then judges that similarity is not less than predetermined threshold value, compare successfully, to the end
End APP, which is sent, to be audited passing through as a result, being preset when the first similarity is less than less than default similarity threshold or the second similarity
Similarity threshold, comparison it is unsuccessful, to the terminal APP send audit not by result.
Step S30 obtains the ground point image that the terminal APP is sent, by described ground point image and preset location image into
Row comparison audit, and auditing result is sent to the terminal APP, when audit passes through, step S40 is executed, when audit does not pass through
When, re-execute step S30.
Wherein, system server receives the ground point image that business personnel is sent by terminal APP, and ground point image refers to executing to appoint
The building object image in the place of business, preset location image refers to the ground point image that system server stores in advance, by ground point image
Comparison audit is carried out with preset location image, for example, after receiving the character image that terminal APP is sent, it can be according to the end
Hold in the identifier extraction system server of APP and corresponding ground point image and carry out comparison audit therewith, when images match at
When work(, sends audit to terminal APP and pass through as a result, terminal APP is made to enter next workflow, when image mismatches, to
Terminal APP sends audit not by as a result, making terminal APP keep the workflow, until business personnel uploads correct image.It is logical
It crosses and this step is set, the certification for handling place to related service may be implemented, improve business handling and review efficiency.
Specifically, for example, system server receives the ground point image that terminal APP is sent, safety JinRong Building image is right
Ground point image is pre-processed, and image outline is extracted, according to what is stored in advance in the identifier extraction system server of terminal APP
Corresponding ground point image carries out comparison audit, when images match success, determines task place.Audit passes through, to terminal APP
Send audit pass through as a result, and execute step S40, when images match fail, for example, shooting the image time line too secretly or
It is too bright to influence comparison audit, step S30 is re-executed until determining corresponding task place.
As an embodiment of the present embodiment, as shown in figure 3, in step S30 by described ground point image with
Preset location image carries out comparison audit, and sends auditing result to the terminal APP, including:
Step S301 obtains the contour edge of described image, and several characteristic point of the selection on the profile utilizes choosing
The profile is described in the contextual feature of fixed characteristic point.
Step S302 obtains the profile of the preset location image, takes the spy of several numbers at equal intervals on the profile
Point is levied, the profile is described using the contextual feature of characteristic point.
The contour feature of the contour feature description of described image and the preset location image is described to carry out by step S303
Matching, when successful match, to the terminal APP send audit pass through as a result, when match it is unsuccessful when, to the terminal
APP send audit not by result.
In above step, the contour edge for obtaining described image refers to the ground that system server receives that terminal APP is sent
The contour edge of point image, characteristic point refer to the point with characteristic information chosen on profile, for example, contour feature point can be with
Including angle point, point of contact or inflection point, angle point is the Local modulus maxima that curvature is more than certain threshold value on objective contour, and point of contact is round
Arc and straight line seamlessly transit a little, and inflection point is seamlessly transitting a little for concave arc and dome arc, and the contextual feature of characteristic point refers to
Characteristic information near the characteristic point of selection, for example, the contextual feature of characteristic point can be other pictures in neighborhood of pixel points
The distribution situation of vegetarian refreshments obtains the ground point image that terminal APP is sent and refers to the image shot to the building for executing task, gets
Object image is built, according to the contour edge of building personal image extraction place image, several contour features is chosen on profile
Point is described profile using the contextual feature of selected contour feature point, obtains preset location figure in system server
Picture takes the profile of several numbers at equal intervals according to the contour edge of preset location image zooming-out preset location image on profile
Characteristic point is described profile using the contextual feature of contour feature point.Wherein contour feature point can include angle point, cut
One of point and inflection point are several, and angle point is the Local modulus maxima that curvature is more than certain threshold value on objective contour, is cut
Point is seamlessly transitting a little for circular arc and straight line, and inflection point is seamlessly transitting a little for concave arc and dome arc.By the profile of ground point image
The contour feature description of feature description and preset location image is matched, for example, calculate corresponding angle point, point of contact and inflection point it
Between range difference away from, judge to should angle point, other pixels in point of contact and inflection point neighborhood distribution situation, when matching at
When work(, determine task spot for photography information, to the terminal APP send audit pass through as a result, make terminal APP enter it is next
Workflow, when match it is unsuccessful when, to the terminal APP send audit not by as a result, terminal APP is made to keep the work
Flow, until business personnel uploads correct image.By the way that this step is arranged, it may be implemented to handle place to related service and recognize
Card improves business handling and review efficiency.
Step S40 obtains the contract image that the terminal APP is sent, audits the contract signing page in the contract image
Whether meet preset rules, and auditing result is sent to the terminal APP, when audit passes through, executes step S50, confirmed
It is obstructed out-of-date when auditing at task, re-execute step S40.
Wherein, system server receives the contract image that business personnel is sent by terminal APP, and contract image refers to this
The contract signing page image of business, preset rules are the auditing rules that system server is pre-set, for example, signature region is
No there are handwriting, time fences region whether there is the hand-written time, right after receiving the contract image of terminal APP transmissions
Contract image is handled, and identifies corresponding audit region, such as signature region, time fences region etc., to each audit area
Domain carries out comparison audit, when all audit regions all meet preset rules, sends task to terminal APP and completes as a result, determining
Completion task sends audit not by as a result, making terminal APP when not meeting preset rules in the presence of audit region to terminal APP
The workflow is kept, until business personnel uploads correct image.By the way that this step is arranged, may be implemented to handle related service
The certification of contract improves business handling rate and review efficiency.
Specifically, for example, system server receives the contract image that terminal APP is sent, insurance contract image, to insurance
Contract image is handled, and is carried on the back according to the corresponding contract stored in advance in the identifier extraction system server of terminal APP
Scape image is compared, and identifies handwriting region, in audit handwriting region signature region with the presence or absence of signature, when
Between column region whether there is the time, when character area has signature and when the time, meets preset rules, audit passes through, to terminal
APP sends that task is completed as a result, completing this subtask, in the absence of character area is there is no signature or time fences region
Between when, do not meet preset rules, audit does not pass through, and audit is sent not by as a result, and re-executing step S40 to terminal APP
Until determining that contract image meets preset rules.
As an embodiment of the present embodiment, as shown in figure 4, for the audit contract image in step S40
In contract signing page whether meet preset rules, and send auditing result to the terminal APP, including:
Step S401 pre-processes contract signing page image, wherein the pretreatment, which refers to, utilizes median filter method
Denoising is carried out to the contract signing page image, the image after denoising is subjected to binaryzation.
Step S402 carries out the background image of pretreated contract signing page image and preset contract signing page pair
Than identifying signature region and time fences region.
Step S403, judges whether the signature region deposits with the presence or absence of handwritten signature and the time fences region respectively
In the hand-written time, when there are handwritten signatures and the time fences there are the hand-written time for the signature, sent to the terminal APP
Audit it is passing through as a result, when the hand-written time is not present there is no handwritten signature or the time fences in the signature, to described
Terminal APP send audit not by result.
In above step, it refers to contract signing page image to obtain the contract image that terminal APP is sent, and obtains contract signing
After page image, contract signing page image is pre-processed, for example, pretreatment can utilize median filter method to the mesh
Logo image carries out denoising;Target image after denoising is subjected to binaryzation.Obtain preset contract signing page image
Background image, background image refer to contract signing page image removal character area after image, i.e., blank sign page image graph
Picture.Background image is matched with pretreated contract signing page image, is identified using background image and signs page image
In handwriting area image.Handwriting region includes signature region and time fences region, to contract signing after identification
Handwriting region in page image is replicated and is preserved, and the image in handwriting region is obtained.According to the handwriting
Area image judges whether contract image meets the preset rules of system server, when detect signature exist signature and the time
Column existence time sends that audit passes through as a result, confirming completion task to terminal APP, and when detecting signature, there is no signatures
Or in the absence of time fences between, to terminal APP send audit not by result.Step S40 is re-executed, terminal APP is made to protect
The workflow is held, until business personnel uploads correct image.By the way that this step is arranged, may be implemented to task contract rapidly
Audit improves business handling rate and review efficiency.
Embodiment 2
Second embodiment of the invention provides a kind of task automation audit device, as shown in figure 5, task automation audit dress
Setting 5 includes:
Mission bit stream sending module 51, for sending mission bit stream to terminal APP, the mission bit stream includes each work
The shooting image information of flow;
Character image auditing module 52, the character image sent for receiving the terminal APP, by the character image with
Default character image carries out comparison audit, and sends auditing result to the terminal APP;
Place image audit module 53, for obtaining the terminal when character image auditing module audit passes through
Described ground point image and preset location image are carried out comparison audit, and are sent out to the terminal APP by the ground point image that APP is sent
Send auditing result;
Contract image audit module 54, for the terminal APP hairs when place image audit module audit passes through
The contract image sent, audits whether the contract signing page in the contract image meets preset rules, and is sent out to the terminal APP
Core submit to a higher level for approval or revision as a result, and when audit passes through, confirming completion task.
The present invention provides a kind of task automation audit device, and system server forms task according to the instruction of flow personnel
Information, and mission bit stream is sent to specified terminal APP obtains the image information that terminal APP is uploaded, and in system server
Preset image information is audited automatically, is generated and is sent auditing result to terminal APP, and is automatically selected according to auditing result
Workflow is executed, the automation audit of task is realized, improves the accuracy rate of audit and accelerate audit speed.
As a kind of embodiment of second embodiment of the invention, as shown in fig. 6, for character image in above-described embodiment
Auditing module 52 specifically includes:
Human face region determination unit 521, for determining human face region according to character image;
Feature information extraction unit 522, for extracting characteristic information from the human face region;
Similarity comparison unit 523, for the characteristic information is similar to the progress of the characteristic information of default character image
Degree comparison, when the similarity is not less than default similarity threshold, send that audit passes through to the terminal APP as a result, working as
When the similarity is less than default similarity threshold, to the terminal APP send audit not by result.
The feature information extraction unit 522 is specifically used for extracting face local feature information simultaneously from the human face region
By using LBP algorithms feature vector is extracted from the human face region;
The similarity comparison unit 523 is specifically used for the of the face local feature information and default character image
The same plate features information comparison obtains the first similarity, and by the second model feature of described eigenvector and default character image
Information carries out comparison and obtains the second similarity, when first similarity and second similarity are not less than the default phase
Like degree threshold value, then judge that the similarity is more than the default similarity threshold, when first similarity and second phase
It is less than the default similarity threshold like any similarity in degree, then judges that the similarity is less than the default similarity threshold
Value.
Preferably, described ground point image and preset location image are subjected to comparison audit in place image audit module 53,
And auditing result is sent to the terminal APP, including:
The contour edge for obtaining described ground point image, several characteristic point of selection on the profile, using selected
The profile is described in the contextual feature of characteristic point;
The profile for obtaining the preset location image takes the characteristic point of several numbers at equal intervals on the profile, utilizes
The profile is described in the contextual feature of characteristic point;
The description of the contour feature of described image is described to match with the contour feature of the preset location image, when
With success when, to the terminal APP send audit pass through as a result, when match it is unsuccessful when, to the terminal APP send audit
Not by result.
Preferably, audited in contract image audit module 54 the contract signing page in the contract image whether meet it is default
Rule, including:
Contract signing page image is pre-processed;
The background image of pretreated contract signing page image and preset contract signing page is compared, with identification
Go out signature region and time fences region;
When judging that the signature region whether there is hand-written with the presence or absence of handwritten signature and the time fences region respectively
Between, when there are the hand-written times there are handwritten signature and the time fences for the signature, it is logical to send audit to the terminal APP
It is crossing as a result, when the hand-written time is not present there is no handwritten signature or the time fences in the signature, to the terminal
APP send audit not by result.
The specific work process of module, can refer to task in previous embodiment 1 in above-mentioned task automation audit device 5
The corresponding process of checking method is automated, details are not described herein.
Embodiment 3
Third embodiment of the invention provides a computer readable storage medium, is stored on the computer readable storage medium
Computer program, the computer program realize that a kind of task in above-described embodiment 1 automates audit side when being executed by processor
Method, to avoid repeating, which is not described herein again.Alternatively, the computer program is realized when being executed by processor one in above-described embodiment 2
The function of each module/unit in kind task automation audit device, to avoid repeating, which is not described herein again.
It is to be appreciated that the computer readable storage medium may include:The computer program code can be carried
Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disc, CD, computer storage, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal and telecommunications letter
Number etc..
Embodiment 4
Fig. 7 is the schematic diagram of terminal device 6 in the present embodiment.As shown in fig. 7, terminal device 6 includes processor 63, storage
Device 61 and it is stored in the computer program 62 that can be run in memory 61 and on processor 63.Processor 63 executes computer
A kind of each step of task automation checking method in above-described embodiment, such as step shown in FIG. 1 are realized when program 62
S10, S20, S30, S40 and S50.Alternatively, processor 63 realizes a kind of task in above-described embodiment when executing computer program 62
The function of automation audit 5 each module/unit of device, transmission mission bit stream module 51 as shown in Figure 5, personage's auditing module
52, place auditing module 53 and contract audit module 54.
Computer program 62 can be divided into one or more module/units, one or more module/unit is deposited
Storage executes in memory 61, and by processor 63, to complete the present invention.One or more module/units can be can be complete
At 62 instruction segment of series of computation machine program of specific function, the instruction segment is for describing computer program 62 in terminal device 6
In implementation procedure.For example, computer program 62 can be divided into send mission bit stream module 51, personage's auditing module 52,
Place auditing module 53 and contract audit module 54.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work(
Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although with reference to aforementioned reality
Applying example, invention is explained in detail, it will be understood by those of ordinary skill in the art that:It still can be to aforementioned each
Technical solution recorded in embodiment is modified or equivalent replacement of some of the technical features;And these are changed
Or replace, the spirit and scope for various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of task automates checking method, which is characterized in that the task automation checking method includes the following steps:
Step S10. sends mission bit stream to terminal APP, and the mission bit stream includes the shooting image information of each workflow;
Step S20. receives the character image that the terminal APP is sent, and the character image and default character image are carried out pair
Auditing result is sent than audit, and to the terminal APP, when audit passes through, executes step S30, weight obstructed out-of-date when auditing
It is new to execute step S20;
Step S30. obtains the ground point image that the terminal APP is sent, and described ground point image and preset location image are carried out pair
Auditing result is sent than audit, and to the terminal APP, when audit passes through, executes step S40, weight obstructed out-of-date when auditing
It is new to execute step S30;
Step S40. obtains the contract image that the terminal APP is sent, and whether audits contract signing page in the contract image
Meet preset rules, and auditing result is sent to the terminal APP, when audit passes through, confirms completion task, it is obstructed when auditing
It is out-of-date, re-execute step S40.
2. task as described in claim 1 automates checking method, which is characterized in that in the step S20 by the people
Object image carries out comparison audit with default character image, and sends auditing result to the terminal APP, including:
Human face region is determined according to the character image;
Characteristic information is extracted from the human face region, and the characteristic information of the characteristic information and default character image is carried out
Similarity comparison;
When the similarity is not less than default similarity threshold, the result that audit passes through is sent to the terminal APP;
When the similarity is less than default similarity threshold, to the terminal APP send audit not by result.
3. task as claimed in claim 2 automates checking method, which is characterized in that extract feature from the human face region
The characteristic information of the characteristic information and default character image is carried out similarity comparison by information, including:
It from the human face region extracts from extraction face local feature information in the human face region and by using LBP algorithms
Feature vector;
The characteristic information of the characteristic information and default character image is subjected to similarity comparison, including:
The comparison of first model characteristic information of the face local feature information and default character image is obtained into the first similarity,
And the second model characteristic information of described eigenvector and default character image is subjected to comparison and obtains the second similarity;
When first similarity and second similarity be not less than the default similarity threshold, then judge described similar
Degree is more than the default similarity threshold;
When any similarity then judges less than the default similarity threshold in first similarity and second similarity
The similarity is less than the default similarity threshold.
4. task as described in claim 1 automates checking method, which is characterized in that in the step S30 by described
Point image carries out comparison audit with preset location image, and sends auditing result to the terminal APP, including:
The profile for obtaining described ground point image chooses several characteristic points on the profile, utilizes selected characteristic point
The profile is described in contextual feature;
The profile for obtaining preset location image, the characteristic point of several numbers is taken on the profile, utilizes characteristic point at equal intervals
The profile is described in contextual feature;
The description of the contour feature of described image is matched with the description of the contour feature of the preset location image, when match at
It is passing through to terminal APP transmission audits as a result, when matching unsuccessful when work(, it is obstructed to send audit to the terminal APP
The result crossed.
5. task as described in claim 1 automates checking method, which is characterized in that described in the audit in the step S40
Whether the contract signing page in contract image meets preset rules, and sends auditing result to the terminal APP, including:
Contract signing page image is pre-processed;
The background image of pretreated contract signing page image and preset contract signing page is compared, to identify label
Name column region and time fences region;
Judge that the signature region whether there is the hand-written time with the presence or absence of handwritten signature and the time fences region respectively, when
The signature is there are handwritten signature and the time fences are there are the hand-written time, passes through to terminal APP transmission audits
As a result, when the hand-written time is not present there is no handwritten signature or the time fences in the signature, sent out to the terminal APP
Submit to a higher level for approval or revision core not by result.
6. a kind of task automation audit device, which is characterized in that the task automation audits device and includes:
Mission bit stream sending module, for sending mission bit stream to terminal APP, the mission bit stream includes each workflow
Shoot image information;
Character image auditing module, the character image sent for receiving the terminal APP, by the character image and default people
Object image carries out comparison audit, and sends auditing result to the terminal APP;
Place image audit module is sent for obtaining the terminal APP when character image auditing module audit passes through
Ground point image, described ground point image and preset location image are subjected to comparison audit, and audit knot is sent to the terminal APP
Fruit;
Contract image audit module is sent for obtaining the terminal APP when place image audit module audit passes through
Contract image, audit the contract signing page in the contract image and whether meet preset rules, and sent to the terminal APP
Auditing result, and when audit passes through, confirm completion task.
7. task as claimed in claim 6 automation audit device, which is characterized in that personage's auditing module includes:
Human face region determination unit, for determining human face region according to the character image;
Feature information extraction unit, for extracting characteristic information from the human face region;
Similarity comparison unit, for the characteristic information of the characteristic information and default character image to be carried out similarity comparison,
When the similarity is not less than default similarity threshold, sent to the terminal APP that audit passes through as a result, when described similar
When degree is less than default similarity threshold, to the terminal APP send audit not by result.
8. task automation audit device as claimed in claim 7, which is characterized in that the feature information extraction unit is specific
For from the human face region extracting from extraction face local feature information in the human face region and by using LBP algorithms
Feature vector;
The similarity comparison unit is specifically used for the first model of the face local feature information and default character image
Characteristic information comparison obtains the first similarity, and by the second model characteristic information of described eigenvector and default character image into
Row comparison obtains the second similarity, when first similarity and second similarity are not less than the default similarity threshold
Value then judges that the similarity is more than the default similarity threshold, when in first similarity and second similarity
Any similarity is less than the default similarity threshold, then judges that the similarity is less than the default similarity threshold.
9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
The step of any one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810239757.4A CN108596559A (en) | 2018-03-22 | 2018-03-22 | Task automates checking method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810239757.4A CN108596559A (en) | 2018-03-22 | 2018-03-22 | Task automates checking method, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108596559A true CN108596559A (en) | 2018-09-28 |
Family
ID=63627019
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810239757.4A Pending CN108596559A (en) | 2018-03-22 | 2018-03-22 | Task automates checking method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108596559A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109871795A (en) * | 2019-01-31 | 2019-06-11 | 湖北交投智能检测股份有限公司 | A kind of highway condition state method, system and the product of automation |
CN110135265A (en) * | 2019-04-16 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Case automatic auditing method, device, computer equipment and storage medium |
CN110191285A (en) * | 2019-06-12 | 2019-08-30 | 深圳前海微众银行股份有限公司 | A kind of method and device commenced business |
CN110276681A (en) * | 2019-06-17 | 2019-09-24 | 深圳前海微众银行股份有限公司 | A kind of method and device commenced business |
CN111696019A (en) * | 2020-06-08 | 2020-09-22 | 中国联合网络通信集团有限公司 | House signing information recording method based on block chain and house signing management node |
CN111882253A (en) * | 2020-08-21 | 2020-11-03 | 支付宝(杭州)信息技术有限公司 | Task auditing method and device |
CN112597339A (en) * | 2020-12-25 | 2021-04-02 | 合安科技技术有限公司 | Content security auditing method and device and related equipment |
CN116824603A (en) * | 2023-07-28 | 2023-09-29 | 广州淘通科技股份有限公司 | Advertisement page image auditing method and device |
CN117764639A (en) * | 2023-11-15 | 2024-03-26 | 深圳市万人市场调查股份有限公司 | Farmer market evaluation method, farmer market evaluation device, electronic equipment and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004133569A (en) * | 2002-10-09 | 2004-04-30 | Canon Sales Co Inc | Auditing system, auditing server, terminal device, auditing method, program, and recording medium |
US20130282600A1 (en) * | 2012-04-23 | 2013-10-24 | Sap Ag | Pattern Based Audit Issue Reporting |
CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
CN106326922A (en) * | 2016-08-22 | 2017-01-11 | 苏州华兴源创电子科技有限公司 | Certificate information remote real time authentication method and system |
CN106446184A (en) * | 2016-09-29 | 2017-02-22 | 中国银联股份有限公司 | Method and device for data processing of service system |
CN106685950A (en) * | 2016-12-26 | 2017-05-17 | 成都康赛信息技术有限公司 | Flow business data processing method |
CN107067228A (en) * | 2017-03-31 | 2017-08-18 | 南京钧元网络科技有限公司 | A kind of hand-held authentication intelligent checks system and its checking method |
CN107103323A (en) * | 2017-03-09 | 2017-08-29 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of target identification method based on image outline feature |
CN107492154A (en) * | 2017-07-22 | 2017-12-19 | 华中师范大学 | A kind of check class attendance system and its method of work |
CN107784428A (en) * | 2017-08-18 | 2018-03-09 | 平安科技(深圳)有限公司 | Witness method, apparatus, computer equipment and storage medium based on mobile terminal |
CN107818455A (en) * | 2017-11-22 | 2018-03-20 | 中国银行股份有限公司 | The teleprocessing system and method for a kind of image |
-
2018
- 2018-03-22 CN CN201810239757.4A patent/CN108596559A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004133569A (en) * | 2002-10-09 | 2004-04-30 | Canon Sales Co Inc | Auditing system, auditing server, terminal device, auditing method, program, and recording medium |
US20130282600A1 (en) * | 2012-04-23 | 2013-10-24 | Sap Ag | Pattern Based Audit Issue Reporting |
CN105550671A (en) * | 2016-01-28 | 2016-05-04 | 北京麦芯科技有限公司 | Face recognition method and device |
CN106326922A (en) * | 2016-08-22 | 2017-01-11 | 苏州华兴源创电子科技有限公司 | Certificate information remote real time authentication method and system |
CN106446184A (en) * | 2016-09-29 | 2017-02-22 | 中国银联股份有限公司 | Method and device for data processing of service system |
CN106685950A (en) * | 2016-12-26 | 2017-05-17 | 成都康赛信息技术有限公司 | Flow business data processing method |
CN107103323A (en) * | 2017-03-09 | 2017-08-29 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | A kind of target identification method based on image outline feature |
CN107067228A (en) * | 2017-03-31 | 2017-08-18 | 南京钧元网络科技有限公司 | A kind of hand-held authentication intelligent checks system and its checking method |
CN107492154A (en) * | 2017-07-22 | 2017-12-19 | 华中师范大学 | A kind of check class attendance system and its method of work |
CN107784428A (en) * | 2017-08-18 | 2018-03-09 | 平安科技(深圳)有限公司 | Witness method, apparatus, computer equipment and storage medium based on mobile terminal |
CN107818455A (en) * | 2017-11-22 | 2018-03-20 | 中国银行股份有限公司 | The teleprocessing system and method for a kind of image |
Non-Patent Citations (1)
Title |
---|
姚峰林: "《数字图像处理及在工程中的应用》", 30 April 2014 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109871795A (en) * | 2019-01-31 | 2019-06-11 | 湖北交投智能检测股份有限公司 | A kind of highway condition state method, system and the product of automation |
CN110135265A (en) * | 2019-04-16 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Case automatic auditing method, device, computer equipment and storage medium |
CN110191285A (en) * | 2019-06-12 | 2019-08-30 | 深圳前海微众银行股份有限公司 | A kind of method and device commenced business |
CN110276681A (en) * | 2019-06-17 | 2019-09-24 | 深圳前海微众银行股份有限公司 | A kind of method and device commenced business |
CN110276681B (en) * | 2019-06-17 | 2024-05-17 | 深圳前海微众银行股份有限公司 | Method and device for developing business |
CN111696019A (en) * | 2020-06-08 | 2020-09-22 | 中国联合网络通信集团有限公司 | House signing information recording method based on block chain and house signing management node |
CN111882253A (en) * | 2020-08-21 | 2020-11-03 | 支付宝(杭州)信息技术有限公司 | Task auditing method and device |
CN112597339A (en) * | 2020-12-25 | 2021-04-02 | 合安科技技术有限公司 | Content security auditing method and device and related equipment |
CN116824603A (en) * | 2023-07-28 | 2023-09-29 | 广州淘通科技股份有限公司 | Advertisement page image auditing method and device |
CN117764639A (en) * | 2023-11-15 | 2024-03-26 | 深圳市万人市场调查股份有限公司 | Farmer market evaluation method, farmer market evaluation device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108596559A (en) | Task automates checking method, device, equipment and storage medium | |
CN107103218B (en) | Service implementation method and device | |
CN110245573B (en) | Sign-in method and device based on face recognition and terminal equipment | |
CN107895155A (en) | A kind of face identification method and device | |
CN104036254A (en) | Face recognition method | |
Rahman et al. | Automated student attendance system using fingerprint recognition | |
CN109635625B (en) | Intelligent identity verification method, equipment, storage medium and device | |
CN109858222B (en) | Identity verification block chain system based on human face features and verification method thereof | |
CN110634223A (en) | Bill verification method and device | |
CN105868693A (en) | Identity authentication method and system | |
CN107609364A (en) | User identification confirmation method and apparatus | |
CN109145720A (en) | A kind of face identification method and device | |
CN110942066B (en) | Bill checking method and device | |
CN111932270A (en) | Method and device for bank customer identity verification | |
CN111291912A (en) | Number taking method, number taking machine and number taking system using witness verification | |
CN113591603A (en) | Certificate verification method and device, electronic equipment and storage medium | |
CN111192150B (en) | Method, device, equipment and storage medium for processing vehicle danger-giving agent service | |
US20240005691A1 (en) | Validating identification documents | |
CN116186543B (en) | Financial data processing system and method based on image recognition | |
CN109087439A (en) | Bill method of calibration, terminal device, storage medium and electronic equipment | |
CN110414792B (en) | BIM and big data based part collection management system and related products | |
CN111695571A (en) | Notarization file verification method and device, computer equipment and storage medium | |
CN110992155A (en) | Bidding and enclosing processing method and related product | |
KR20170132914A (en) | A system and a method for identifying based on matching of images | |
CN115527241A (en) | Fingerprint template updating method and device, embedded equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |