CN107886079A - Object identifying method, apparatus and system - Google Patents
Object identifying method, apparatus and system Download PDFInfo
- Publication number
- CN107886079A CN107886079A CN201711177901.8A CN201711177901A CN107886079A CN 107886079 A CN107886079 A CN 107886079A CN 201711177901 A CN201711177901 A CN 201711177901A CN 107886079 A CN107886079 A CN 107886079A
- Authority
- CN
- China
- Prior art keywords
- identified
- information
- image
- alternative objects
- storehouse
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/30—Scenes; Scene-specific elements in albums, collections or shared content, e.g. social network photos or video
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Abstract
The invention provides a kind of object identifying method, apparatus and system, is related to image identification technical field, and this method includes obtaining the image of object to be identified；The image of object to be identified is identified by temporary library, to determine the identity of object to be identified；Wherein, temporary library includes the bottom storehouse image information for meeting default constraints extracted from Zong Ku.The present invention is by increasing temporary library newly, the bottom storehouse image information of the qualified object filtered out in total storehouse is stored in temporary library, object to be identified is identified using output image memory less temporary library, can effectively lift recognition accuracy, is easy to directly determine the identity of object to be identified.
Description
Technical field
The present invention relates to image identification technical field, more particularly, to a kind of object identifying method, apparatus and system.
Background technology
In the image recognition technologys such as recognition of face again, it usually needs (may be used in the total storehouse of image for being stored with great amount of images
Referred to as bottom storehouse) it is compared, so that it is determined that the identity of object to be identified.However, when the image stored in the total storehouse of image is more
When, easily occur misidentifying or leaking identification.The total storehouse of image is bigger, and recognition accuracy is lower, is more difficult to directly determine identity.
The content of the invention
In view of this, it is an object of the invention to provide a kind of object identifying method, apparatus and system, to improve existing skill
The total storehouse of image present in art is bigger, and recognition accuracy is lower, the problem of being more difficult to directly determine identity.
To achieve these goals, the technical scheme that the embodiment of the present invention uses is as follows：
In a first aspect, the embodiments of the invention provide a kind of object identifying method, including：Obtain the figure of object to be identified
Picture；The image of the object to be identified is identified by temporary library, to determine the identity of the object to be identified；Wherein,
The temporary library includes the bottom storehouse image information for meeting default constraints extracted from Zong Ku.
Further, total stock contains the bottom storehouse image information of multiple alternative objects, and methods described also includes：Monitoring institute
State whether alternative objects meet the default constraints；If it is, the bottom by the alternative objects stored in total storehouse
Storehouse image information is synchronized to the temporary library.
Further, the default constraints includes a variety of constraintss；Whether the monitoring alternative objects meet
The step of default constraints, including：Monitor whether the alternative objects meet in the default constraints at least
A kind of constraints, if it is, determining that the alternative objects meet the default constraints；Or monitoring is described alternative right
As if the no whole constraintss met in the default constraints, if it is, it is described pre- to determine that the alternative objects meet
If constraints.
Further, the default constraints includes geographic location constraint condition, and whether the monitoring alternative objects
The step of meeting the default constraints, including：The alternative objects are gathered by the mobile terminal of the alternative objects
Geographical location information；The geographical location information is judged whether in default geographical position range, if it is, determining described standby
Object is selected to meet the geographic location constraint condition.
Further, the default constraints includes time constraint condition；Whether the monitoring alternative objects meet
The step of default constraints, including：Judge whether temporal information corresponding to the alternative objects is located at the default time
In section；If it is, determine that the alternative objects meet the time constraint condition.
Further, the default constraints includes object information constraints；Whether the monitoring alternative objects
The step of meeting the default constraints, including：Judge whether the related information of the alternative objects matches with presupposed information；
The related information includes the one or more in identity information, attribute information or information to be serviced；If it is, determine described standby
Object is selected to meet the object information constraints.
Further, the described the step of image of the object to be identified is identified by temporary library, including：By described in
The image of object to be identified is compared with each bottom storehouse image in the temporary library, obtain the object to be identified with it is described
The similarity of each bottom storehouse image in temporary library；Judge whether the peak of the similarity is higher than predetermined threshold value；If it is,
It is the object to be identified to determine object corresponding to the peak of the similarity.
Further, methods described also includes；If the peak of the similarity is less than the predetermined threshold value, institute is switched to
Total storehouse is stated the image of the object to be identified is identified.
Further, methods described also includes：Regularly update the temporary library.
Further, described the step of regularly updating the temporary library, including：Periodically updated what is stored in total storehouse
The bottom storehouse image information that moment meets the alternative objects of the default constraints is synchronized to the temporary library；And/or periodically will
The bottom storehouse image information that the object of the default constraints is not met in the renewable time of the interim library storage is deleted.
Second aspect, the embodiment of the present invention also provide a kind of object recognition equipment, including：Acquisition module, treated for obtaining
The image of identification object；Identification module, for the image of the object to be identified to be identified by temporary library, to determine
State the identity of object to be identified；Wherein, the temporary library includes the bottom storehouse figure for meeting default constraints extracted from Zong Ku
As information.
The third aspect, the embodiments of the invention provide a kind of object recognition system, the system includes：Image collector
Put, processor and storage device；Described image harvester, for gathering the image of object to be identified；On the storage device
Computer program is stored with, the computer program performs the side described in any one of first aspect when being run by the processor
Method.
Fourth aspect, the embodiments of the invention provide a kind of computer-readable recording medium, the computer-readable storage
Computer program is stored with medium, the side described in any one of first aspect is performed when the computer program is run by processor
The step of method.
, can be by temporary library to acquisition the embodiments of the invention provide a kind of object identifying method, apparatus and system
The image of object to be identified is identified, and determines the identity of object to be identified.With direct application image amount of storage in the prior art
Larger total storehouse, which is identified, to be compared, and the present embodiment has increased temporary library newly, by the qualified object filtered out in total storehouse
Bottom storehouse image information is stored in temporary library, object to be identified is identified using output image memory less temporary library, energy
Enough effectively lifting recognition accuracies, it is easy to directly determine the identity of object to be identified.
Other feature and advantage of the disclosure will illustrate in the following description, or, Partial Feature and advantage can be with
Deduce from specification or unambiguously determine, or the above-mentioned technology by implementing the disclosure can be learnt.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art
The required accompanying drawing used is briefly described in embodiment or description of the prior art, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid
Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 shows the structural representation for a kind of electronic equipment that the embodiment of the present invention is provided；
Fig. 2 shows a kind of object identifying method flow chart that the embodiment of the present invention is provided；
Fig. 3 shows a kind of structured flowchart for object recognition equipment that the embodiment of the present invention is provided；
Fig. 4 shows the structured flowchart for another object recognition equipment that the embodiment of the present invention is provided.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Technical scheme be clearly and completely described, it is clear that described embodiment is part of the embodiment of the present invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
Face recognition technology has started to progressively be applied to each rows such as safety-security area, consumer field, field of traffic at present
Each industry, 1 is carried out to face by the bottom storehouse for being previously stored with N number of image information：N matching identifications, to determine face identity.All
Such as possess the huge airport occasion of consumption platform, the flow of the people of numerous users, bottom storehouse used is often wrapped in recognition of face
Containing even more than million grades of user images information of tens of thousands of, hundreds of thousands, that is, N value quantity is often huge.It is appreciated that
It is, when N value quantity is larger, to be not easy to determine user identity, the problems such as leakage identification, misrecognition, recognition accuracy easily occur
It is not high, it is more difficult to reach when N values are only hundred, thousand etc. compared with fractional value when can realize " identification i.e. ejection " it is accurate
Recognition effect.For problems, current safety-security area takes the mode that manual intervention intervenes mostly, is manually determined.But
It is that customer count is numerous for consumer field, it is difficult to realized in a manner of by manpower intervention, the still more side of manpower intervention
Formula takes time and effort, and reliability also is difficult to ensure.Therefore need rational resolution policy badly and be difficult to directly determine to use to tackle big bottom storehouse
Family identity, the problem of recognition accuracy is not high, therefore, a kind of object identifying method provided in an embodiment of the present invention, device and being
System, the technology can be applied to need the occasion of recognition of face, be realized using corresponding software and hardware, below to the embodiment of the present invention
Describe in detail.
Embodiment one：
First, reference picture 1 come describe for realize the embodiment of the present invention object identifying method, the example of apparatus and system
Electronic equipment 100.
The structural representation of a kind of electronic equipment as shown in Figure 1, electronic equipment 100 include one or more processors
102nd, one or more storage devices 104, input unit 106, output device 108 and image collecting device 110, these components
Interconnected by bindiny mechanism's (not shown) of bus system 112 and/or other forms.It should be noted that the electronic equipment shown in Fig. 1
100 component and structure is illustrative, and not restrictive, and as needed, the electronic equipment can also have other
Component and structure.
The processor 102 can be CPU (CPU) or be performed with data-handling capacity and/or instruction
The processing unit of the other forms of ability, and other components in the electronic equipment 100 can be controlled desired to perform
Function.
The storage device 104 can include one or more computer program products, and the computer program product can
With including various forms of computer-readable recording mediums, such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memory is such as can include random access memory (RAM) and/or cache memory (cache).It is described non-
Volatile memory is such as can include read-only storage (ROM), hard disk, flash memory.In the computer-readable recording medium
On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute
The client functionality (realized in the embodiment of the present invention stated by processor) and/or other desired functions.In the meter
Can also store various application programs and various data in calculation machine readable storage medium storing program for executing, for example, the application program use and/or
Caused various data etc..
The input unit 106 can be the device that user is used for input instruction, and can include keyboard, mouse, wheat
One or more of gram wind and touch-screen etc..
The output device 108 can export various information (for example, image or sound) to outside (for example, user), and
And one or more of display, loudspeaker etc. can be included.
Described image harvester 110 can shoot the desired image of user (such as photo, video etc.), and will be clapped
The image taken the photograph is stored in the storage device 104 so that other components use.
Exemplarily, for realizing the exemplary electron of object identifying method according to embodiments of the present invention, apparatus and system
Equipment may be implemented as on the mobile terminals such as smart mobile phone, tablet personal computer.
Embodiment two：
A kind of object identifying method flow chart shown in reference picture 2, this method comprise the following steps：
Step S202, obtain the image of object to be identified.In one embodiment, camera, camera etc. can be passed through
The facial image of object to be identified is gathered by shooting style.
Step S204, the image of object to be identified is identified by temporary library, to determine the identity of object to be identified.
Wherein, the temporary library includes the bottom storehouse image information for meeting default constraints extracted from Zong Ku.
Specifically, above-mentioned temporary library is to contain the bottom storehouse image of multiple alternative objects from the word bank of total storehouse extraction, total stock
Information, temporary library are stored with the bottom storehouse image information of at least one preferred pair elephant；Preferred pair likes sieves from multiple alternative objects
That selects meets the object of default constraints；Bottom storehouse image information includes the bottom storehouse image of object, and bottom storehouse image with it is right
As the corresponding relation of identity.Wherein, the image in identification process, which compares, can take characteristic value alignments, and image feature value can be straight
Connect and extracted from image.In addition, bottom storehouse image information can also include the related information of object, such as identity information (such as hand
Machine number, passport NO., title, person identifier etc.), attribute information (such as member's grade, sex, age categories, shopping frequency
Deng), information to be serviced (treating landing gate number, running number to be multiplied, subscription services etc.), certainly, these are only and schematically enumerate,
Related information can also include other information, will not be repeated here.
It is to be understood that total storehouse is the great Di Ku for including all objects, such as include million quantity in the big bottom storehouse
The bottom storehouse image information of level and the above, and temporary library is interim handle storehouse for identification, such as only included thousand orders of magnitude and
Following bottom storehouse image information.By presetting the screening of constraints, it can differentiate whether the object being stored in total storehouse may need
It is to be identified, that is, whether the alternative objects whether met to determine in total storehouse of default constraints are synchronized with temporary library.On
State method and the information for the object that may need to identify in total storehouse is all synchronized to temporary library, by the temporary library for including less object
It is identified, can preferably lifts the accuracy of identification, is easy to directly determine the identity of object to be identified.
Above-mentioned object identifying method provided in an embodiment of the present invention, can be by temporary library to the object to be identified of acquisition
Image is identified, and determines the identity of object to be identified.Larger total storehouse is entered with direct application image amount of storage in the prior art
Row identification is compared, and the present embodiment has increased temporary library newly, by the bottom storehouse image information of the qualified object filtered out in total storehouse
It is stored in temporary library, object to be identified is identified using output image memory less temporary library, can effectively lifts knowledge
Other accuracy rate, it is easy to directly determine the identity of object to be identified.
This gives a kind of advance building process of temporary library, specifically, the above method also includes：Monitoring is alternative
Whether object meets default constraints；If it is, the image information of the alternative objects stored in total storehouse is synchronized to temporary library.
Wherein, total stock contains the bottom storehouse image information of multiple alternative objects.That is, each alternative objects in total storehouse are supervised
Survey, the alternative objects for meeting default constraints are synchronized to temporary library.If the alternative objects meet default constraints,
Determine the alternative objects for preferred pair as by its bottom storehouse image information synchronized push to temporary library.By way of this screening,
The object information that may be identified in total storehouse is all first positioned in temporary library, treated first by the less temporary library of amount of storage
Identification object is identified, and can preferably ensure recognition accuracy.
Above-mentioned default constraints can be set according to the actual requirements and flexibly, and default constraints can set one kind,
It can also set a variety of, in one embodiment, above-mentioned default constraints includes such as geographic location constraint condition, time
A variety of constraintss such as constraints and object information constraints.
The step of whether monitoring alternative objects meet default constraints, following two embodiments can be used：
Mode one：Whether monitoring alternative objects meet at least one of default constraints constraints, if it is, really
Determine alternative objects and meet default constraints.In this approach, when default constraints has a variety of, as long as alternative right in total storehouse
As meeting one of which condition, you can think the alternative objects be may synchronize to the preferred pair of temporary library as.
Mode two：Whether monitoring alternative objects meet whole constraintss in default constraints, if it is, determining standby
Object is selected to meet default constraints.In this approach, it is necessary to which the alternative objects in total storehouse expire when default constraints has a variety of
The whole constraintss of foot, just can consider the alternative objects is that may synchronize to the preferred pair of temporary library as namely passing through multidimensional
Degree differentiates to alternative objects.
In actual applications, can to judge whether alternative objects meet from one of aforesaid way as needed and flexibly pre-
If constraints.
Geographic location constraint condition, time constraint condition and object information can be included about based on above-mentioned default constraints
Beam condition etc., in order to make it easy to understand, the present embodiment sets forth the following example for judging whether to meet each constraints：
Example one：Judge whether to meet geographic location constraint condition：
Default constraints includes geographic location constraint condition, and whether monitoring alternative objects meet the step of default constraints
Suddenly, including：The geographical location information of alternative objects is gathered by the mobile terminal of alternative objects；Whether judge geographical location information
In default geographical position range, if it is, determining that alternative objects meet geographic location constraint condition.Usual alternative objects
Mobile terminal can determine the geographical location information of alternative objects using GPS positioning technology, and mobile terminal can be with performing this reality
The terminal or server for applying the object identifying method of example offer are connected, and the geographical position of alternative objects is uploaded in real time, and
It is updated in total storehouse.Such as, the member storehouse in solid shop (that is, total storehouse) internal memory contains whole members (that is, alternative
Object) information, server corresponding to solid shop also real-time reception and can record the geographical location information that each member's mobile phone uploads,
When monitoring member A near the solid shop in the range of 500 meters, determine that member A meets default constraints, it will member A
As may member's (that is, preferred pair as) for identifying of needs, it will member A synchronizing information pushes to identification storehouse (that is, interim
Storehouse), when entering shop identification in order to member A, it can directly utilize the identity for identifying storehouse identification member A.
Example two：Judge whether to meet time constraint condition：
The step of default constraints includes time constraint condition, and whether monitoring alternative objects meet default constraints,
Including：Judge temporal information corresponding to alternative objects whether within the default period；If it is, determine that alternative objects meet
Time constraint condition.Such as, record has nearest consumption time corresponding to each member in the member storehouse in shop, when setting default
Between section be cycle of activity September 1 day to December 1, the activity is that member can carry out making a call to 9 during consumption for the second time in preset time
Folding；If monitor that nearest consumption time was located in cycle of activity corresponding to member B, thus it is speculated that the member B may come shop again
Consumption, then using member B as the member that may need to identify, the information of the member B pushes to identification storehouse, in order to the member B
When entering shop consumption again, the identity for identifying storehouse identification member B can be directly utilized.
Example three：Judge whether to meet object information constraints：
Default constraints includes object information constraints；Object refers to the individual with unique identities, in this implementation
In example, object can be people.Object information can specifically include the related information of object, such as, everyone related information tool
Body can include identity information (title, identity card piece number, cell-phone number, membership number etc.), attribute information (such as sex, year
Age, member's grade etc.), information to be serviced (Flight Information, reservation information) etc..Whether monitoring alternative objects, which meet, is preset about
The step of beam condition, including：Judge whether the related information of alternative objects matches with presupposed information；Related information is believed including identity
One or more in breath, attribute information or information to be serviced；If it is, determine that alternative objects meet object information constraint bar
Part.Wherein, object information constraints includes presupposed information, and presupposed information corresponding can be set with the related information of alternative objects
Put, such as when the related information of alternative objects includes identity information and attribute information, presupposed information can also include identity letter
Breath and attribute information, by accordingly comparing the related information and presupposed information of alternative objects, can judge whether alternative objects accord with
Close object information constraints.Such as, the application recognition methods in airport, related information include the identity letter for seizing the opportunity personnel
The various dimensions information such as breath, Flight Information, Boarding door.When the personnel A of seizing the opportunity crosses safety check, obtained by safety check platform and seize the opportunity personnel A
Related information be：It number is XXX to seize the opportunity personnel identity card, flight 14:00 flight XXX for flying to Shanghai by Beijing, boarding
Door is C2.Judge that this seizes the opportunity personnel A related information and presupposed information (flight 14:The 00 flight XXX for flying to Shanghai by Beijing
Number, landing gate C2) it is same to personnel A image information (including A recognizable face head portrait, related information etc.) will be seized the opportunity during correspondence
Step pushes to C2 corresponding to C2 landing gates and identifies storehouse (that is, temporary library), in order to seize the opportunity personnel A in boarding, directly passes through
C2 identifications storehouse determines to seize the opportunity personnel identity.
Based on above-mentioned example, whether alternative objects can be met with default constraints and carry out objective judgement.Actually should
In, constraints can flexibly be set according to application scenario, to carry out rationally dividing storehouse to total storehouse, be entered by the word bank separated
Row efficient identification, recognition accuracy is improved, directly determines the identity of object to be identified,
In the specific implementation, the present embodiment gives the figure by temporary library to object to be identified in a kind of step S204
As the embodiment being identified, comprise the following steps：
(1) image of the object to be identified is compared with each bottom storehouse image in the temporary library, treated
Identification object and the similarity of each bottom storehouse image in temporary library.The essence that image compares is the comparison of image feature value,
The characteristics extraction of image is out compared, the image of the object stored in total storehouse can be image feature value, pass through
Characteristic value comparison result determines similarity.
(2) judge whether the peak of similarity is higher than predetermined threshold value.If it is, determine corresponding to the peak of similarity
Object is object to be identified.
Predetermined threshold value can such as set predetermined threshold value as 85% with sets itself, if the peak of similarity reaches
85%, it is determined that preferred pair corresponding with the peak of the similarity is as object to be identified.
In view of may not include image information corresponding to object to be identified in temporary library, temporary library None- identified is caused to go out
The identity of object to be identified, the above method also include：If the peak of similarity is less than predetermined threshold value, total storehouse pair is switched to
The image of object to be identified is identified.That is, if the peak of similarity is less than predetermined threshold value, show for various originals
Cause, temporary library, which fails, determines the identity of object to be identified, then switches to and carried out comprising object images total storehouse the most comprehensive
Identification, the identification method in total storehouse can use correlation technique to realize, will not be repeated here.
In view of needing to identify that the crowd of identity is to change over time, in one embodiment, the above method
Also include：Regularly update temporary library.Meet default constraints in renewable time specifically, will periodically can be stored in total storehouse
The bottom storehouse image informations of alternative objects be synchronized to temporary library；Not and/or regular not met interim library storage in renewable time
The bottom storehouse image information of the object of default constraints is deleted.
It should be appreciated that temporary library can be dynamically adjusted, it is necessary to be carried out in special time to total storehouse and temporary library
Check, the change such as increased, deleted to temporary library according to actual conditions and operating, it is out of date right by what is included in temporary library
Image information is deleted, and will newly meet that the object information of condition increases to temporary library again in total storehouse, ensures temporary library memory storage as far as possible
Identified object information is likely to require, is easy to directly and accurately determine the identity of object to be identified in identification process；And
The operation periodically deleted is also prevented from the unrestricted growth of temporary library, by controlling the amount of storage of temporary library compared with small category
It is interior, it can be ensured that temporary library has higher recognition accuracy, directly to determine the identity of object to be identified.
Embodiment three：
Based on previous embodiment, this gives a kind of specific application scenarios.The above method is applied to consumption
Platform, using identifying scene under navigation, line on the line of the entity trade companies such as U.S. group, popular comment.
Specifically, many users can be registered as by network on line into the consumption platform such as group to the United States or popular comment
The member of entity businessman, now the entity businessman under line can by the log-on message of user and get the head portrait of user believe
The personal information such as breath, identity information, and establish member storehouse.The member storehouse includes respectively (equivalent to total storehouse in previous embodiment)
All members of the businessman oneself among its CRM (client management system) system are (equivalent to alternative right in previous embodiment
As), the recognizable facial image and identity information of all members are stored with, the related information of member can also be included, such as noted
Volume time, consumption time, member's grade etc..
The recognizable facial image of each member stored in member storehouse can obtain in several ways：(1) inside CRM storehouses
The photographic intelligence of existing subscriber；(2) facial image that the identity document uploaded by user obtains；(3) user is in registration phase
The facial image directly obtained in a manner of self-timer.
Practical application is referred to as follows：
Step 1：The real-time geographical locations that member is obtained by the handheld terminal (mobile phone, tablet personal computer etc.) of member are believed
Breath, is specifically as follows LBS information.
For example, in solid shops such as restaurant, retail shops, can be released certainly in the mobile terminal such as mobile phone or tablet personal computer
Oneself APP applications, such as application software of IOS or Andriod versions, or H5 public numbers etc., can also be by such as popular
The third-party platform displayings such as comment, U.S. group.After member installs APP corresponding to solid shop and registers, the mobile terminal of member
GPS information certainly, can be reported by the GPS information of the APP background program real-time report members resided, namely LBS information
When, the information that member account, cell-phone number etc. can determine that membership can be also carried simultaneously.
Step 2：Judge whether to push away the membership information of the member from member storehouse according to the real-time geographical locations information of member
Deliver to temporary library.
When having monitored that member A enters in default geographical position range according to GPS information, such as, apart from the entity
When in the zone of action in 500 meters of the radius of retail shop, determine that member A meets geographic location constraint condition, compared in member storehouse
Other members, member A have larger possibility to need to shop to identify, therefore complete member storehouse to identification by database synchronization technology
The membership information in storehouse (equivalent to the temporary library in previous embodiment) is synchronous, it will and member A membership information is synchronized to identification storehouse, this
When, member A equivalent to the preferred pair in previous embodiment as.In this way, it is easy to, when member is to shop, directly pass through knowledge
Other storehouse identifies the identity of the member.
Step 3：When member to shop needs to identify identity, identification is carried out to the member by temporary library first.
Due to qualified membership information synchronized push to temporary library, it is possible to directly member is entered by temporary library
Row identification.In view of it is this based on geographical position judge member whether close to shop mode, it is necessary to the mobile end for passing through member
End positions to member, but is likely to occur member and does not have the special circumstances such as band mobile phone, can not now get member reality
Geographical location information.Because the membership information of the member is not synchronized to identification storehouse in advance, therefore when the member to shop identifies,
Identification storehouse None- identified goes out the identity of the member, now switches to member storehouse and the member is identified, further determine that the meeting
Member's identity.
In order to prevent identifying the unrestricted growth in storehouse, recognition success rate is reduced beyond the identification range that system is born,
Identification storehouse can be updated according to default mode, the membership information that will no longer conform to condition is deleted.Can be according to the time
Part membership information is deleted, such as, deletes and knows after timing 24h, 24h membership information is synchronized to the push time in identification storehouse
The membership information stored in other storehouse.Membership information can also be deleted according to geographical position, such as, member A enters default LBS
When setting in radius, its membership information is from member storehouse synchronized push to identification storehouse, when monitoring that it is default that member A leaves
When LBS sets radius, then the membership information of the member A in identification storehouse is deleted.
By the above-mentioned means, identification storehouse can be made according to actual conditions and dynamically updated, the meeting for no longer needing to identify is deleted
Member's information, the membership information that identifies may currently be needed by adding, and ensure the amount of storage in identification storehouse in default zone of reasonableness, with compared with
Membership more can be accurately identified in identification process well, reaches the effect of " identification is ejected ", that is, works as member
When being identified, the identity information of the member is quickly ejected.
Example IV：
Based on previous embodiment, this gives another specific application scenarios.By the method in embodiment two
The communications and transportation occasions such as the airport larger applied to flow of the people, railway station, bus station, are verified as with the recognition of face on airport below
Example illustrates.
Practical application is referred to as follows：
Step 1：When seizing the opportunity personnel's safety check, personal information, including head image information, the identity letter for seizing the opportunity personnel are seized the opportunity in acquisition
The various dimensions information such as breath, Flight Information, Boarding door.
It is required for, by safety check sales counter, the body of oneself now being provided to security staff on airport specifically, seizing the opportunity personnel
Part certificate, air ticket boarding card etc. prove.Security staff can will seize the opportunity personal information typing to airport people by modes such as barcode scannings
Member storehouse (equivalent to total storehouse in previous embodiment), seize the opportunity personal information include seizing the opportunity the head image information of personnel (can be with during safety check
It is required that this is seized the opportunity personnel and come back and captures front and shine), the identity information of seizing the opportunity personnel, Flight Information, the various dimensions information such as landing gate.
Associate each various dimensions information.
Step 2：According to personal information is seized the opportunity, identification storehouse corresponding to landing gate is pushed to (equivalent in previous embodiment
Temporary library).
Such as, the flight for seizing the opportunity personnel A is 14:00 flight for flying to Shanghai by Beijing, landing gate C2, is seizing the opportunity personnel
A seizes the opportunity personnel A information i.e. synchronized push to C2 and identifies storehouse after safety check.
Step 3：When the personnel that seize the opportunity carry out recognition of face in the boarding period at landing gate C2, pass through C2 first and identify storehouse pair
This is seized the opportunity personnel and carries out identification.
In addition, after landing gate is closed, then that removes above-mentioned boarding period for being stored in C2 identifications storehouse seizes the opportunity personal information.
If also fly to the flight in Guangzhou in Beijing after detecting the personnel of seizing the opportunity, landing gate D1 can also be in setting time (such as
2h before flight takeoff) will seize the opportunity personal information push to D1 identification storehouse.
In actual applications, due to multiple landing gates, each landing gate is required for carrying out authentication, institute to seizing the opportunity personnel
Can be respectively that each landing gate is correspondingly arranged identification storehouse, believe according to the Flight Information for seizing the opportunity personnel and landing gate got
Breath, personal information will be seized the opportunity and push to corresponding landing gate identification storehouse.When it is determined that landing gate is closed, what removing stored before should
Flight seizes the opportunity personal information, then receive the Next Flight pushed by airport personnel storehouse seize the opportunity personal information.
By the above-mentioned means, each landing gate can be made to identify that storehouse dynamically updates according to actual conditions, deletion no longer needs
Personal information is seized the opportunity in identification, adds the personal information of seizing the opportunity that may currently need to identify, the amount of storage in control identification storehouse is pre-
If in zone of reasonableness, accurately determine to seize the opportunity personnel identity with more, reach the effect of " identification is ejected ", be easy to seize the opportunity personnel
When boarding carries out recognition of face, the identity for seizing the opportunity personnel can be quickly determined.
Embodiment five：
For the object identifying method provided in embodiment two, the embodiments of the invention provide a kind of Object identifying dress
Put, a kind of structured flowchart of object recognition equipment shown in Figure 3, including：
Image collection module 302, for obtaining the image of object to be identified.
Temporary library identification module 304, for the image of object to be identified to be identified by temporary library, to determine to wait to know
The identity of other object.
Wherein, temporary library includes the bottom storehouse image information for meeting default constraints extracted from Zong Ku.
Above-mentioned object recognition equipment provided in an embodiment of the present invention, can be by temporary library to the object to be identified of acquisition
Image is identified, and determines the identity of object to be identified.Larger total storehouse is entered with direct application image amount of storage in the prior art
Row identification is compared, and said apparatus has increased temporary library newly, and the image information of the qualified object filtered out in total storehouse is stored
In temporary library, object to be identified is identified using output image memory less temporary library, it is accurate can effectively to lift identification
True rate, it is easy to directly determine the identity of object to be identified.
Total stock contains the bottom storehouse image information of multiple alternative objects, another object recognition equipment shown in Figure 4
Structured flowchart, on the basis of Fig. 3, said apparatus also includes：
Monitoring modular 402, for monitoring whether alternative objects meet default constraints；
Temporary library synchronization module 404, for condition monitor module monitoring result for be when, it is standby by what is stored in total storehouse
The bottom storehouse image information of object is selected to be synchronized to temporary library.
In one embodiment, presetting constraints includes a variety of constraintss；
Above-mentioned monitoring modular 402 includes the first monitoring unit or the second monitoring unit, and the first monitoring unit is standby for monitoring
Select whether object meets at least one of default constraints constraints, preset about if it is, determining that alternative objects meet
Beam condition；Second monitoring unit is used to monitor whether alternative objects meet whole constraintss in default constraints, if
It is to determine that alternative objects meet default constraints.
Based on above-mentioned embodiment, the present embodiment sets forth the following example for judging whether to meet constraints.
Example one：Judge whether to meet geographic location constraint condition：
Default constraints includes geographic location constraint condition, and above-mentioned monitoring modular 402 includes geographical monitoring unit, is used for
The geographical location information of alternative objects is gathered by the mobile terminal of alternative objects；Judge geographical location information whether default
In geographical position range, if it is, determining that alternative objects meet geographic location constraint condition.
Example two：Judge whether to meet time constraint condition：
Default constraints includes time constraint condition；Above-mentioned monitoring modular 402 includes time supervision unit, for judging
Whether temporal information corresponding to alternative objects is within the default period；If it is, determine that alternative objects meet time-constrain
Condition.
Example three：Judge whether to meet object information constraints：
Default constraints includes object information constraints；Above-mentioned monitoring modular 402 includes information monitoring unit, is used for
Judge whether the related information of alternative objects matches with presupposed information；Related information includes identity information, attribute information or waits to take
One or more in information of being engaged in；If it is, determine that alternative objects meet object information constraints.
Further, this gives a kind of embodiment of identification module 404, wherein, identification module 404 is used
In：The image of object to be identified is compared with each bottom storehouse image in temporary library, obtains object to be identified and temporary library
In each bottom storehouse image similarity；Judge whether the peak of similarity is higher than predetermined threshold value；If it is, determine similarity
Peak corresponding to object be object to be identified.
Also illustrate that said apparatus also includes in Fig. 4：Total storehouse identification module 406, if the peak for similarity
Less than predetermined threshold value, switch to total storehouse and the image of object to be identified is identified.
Further, illustrate that said apparatus also includes in Fig. 4：Temporary library update module 408, it is interim for regularly updating
Storehouse.Specifically, the present embodiment provides the embodiment of following temporary library update module：
Temporary library update module 408 is used to periodically meet the standby of default constraints in renewable time by what is stored in total storehouse
The bottom storehouse image information of object is selected to be synchronized to temporary library；And/or periodically interim library storage do not met in renewable time default
The bottom storehouse image information of the object of constraints is deleted.
The device that the present embodiment is provided, its realization principle and caused technique effect are identical with previous embodiment, for letter
Describe, device embodiment part does not refer to part, refers to corresponding contents in preceding method embodiment.
Embodiment six：
The embodiments of the invention provide a kind of object recognition system, the system includes：Image collecting device, processor and deposit
Storage device；
Image collecting device, for gathering the image of object to be identified；
Computer program is stored with storage device, the computer program performs such as preceding method when being run by processor
The object identifying method that embodiment is provided.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
Specific work process, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
Further, the present embodiment additionally provides a kind of computer-readable recording medium, the computer-readable recording medium
On be stored with computer program, the computer program performs what above-mentioned preceding method embodiment was provided when being run by processor
The step of object identifying method.
Object identifying method that the embodiment of the present invention is provided, the computer program product of apparatus and system, including storage
The computer-readable recording medium of program code, the instruction that described program code includes can be used for performing previous methods embodiments
Described in method, specific implementation can be found in embodiment of the method, will not be repeated here.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
Finally it should be noted that：Embodiment described above, it is only the embodiment of the present invention, to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that：Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent substitution is carried out to which part technical characteristic；And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of technical scheme of the embodiment of the present invention, should all cover the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (13)
- A kind of 1. object identifying method, it is characterised in that including：Obtain the image of object to be identified；The image of the object to be identified is identified by temporary library, to determine the identity of the object to be identified；Wherein, the temporary library includes the bottom storehouse image information for meeting default constraints extracted from Zong Ku.
- 2. according to the method for claim 1, total stock contains the bottom storehouse image information of multiple alternative objects, its feature It is, methods described also includes：Monitor whether the alternative objects meet the default constraints；If it is, the bottom storehouse image information of the alternative objects stored in total storehouse is synchronized to the temporary library.
- 3. according to the method for claim 2, it is characterised in that the default constraints includes a variety of constraintss；The step of whether the monitoring alternative objects meet the default constraints, including：Monitor whether the alternative objects meet at least one of default constraints constraints, if it is, determining The alternative objects meet the default constraints；OrMonitor whether the alternative objects meet whole constraintss in the default constraints, if it is, described in determining Alternative objects meet the default constraints.
- 4. according to the method for claim 2, it is characterised in that the default constraints includes geographic location constraint bar Part, the step of whether monitoring alternative objects meet the default constraints, including：The geographical location information of the alternative objects is gathered by the mobile terminal of the alternative objects；The geographical location information is judged whether in default geographical position range, if it is, determining the alternative objects symbol Close the geographic location constraint condition.
- 5. according to the method for claim 2, it is characterised in that the default constraints includes time constraint condition；Institute The step of whether the monitoring alternative objects meet the default constraints is stated, including：Judge temporal information corresponding to the alternative objects whether within the default period；If it is, determine that the alternative objects meet the time constraint condition.
- 6. according to the method for claim 2, it is characterised in that the default constraints includes object information constraint bar Part；The step of whether the monitoring alternative objects meet the default constraints, including：Judge whether the related information of the alternative objects matches with presupposed information；The related information includes identity information, category One or more in property information or information to be serviced；If it is, determine that the alternative objects meet the object information constraints.
- 7. according to the method for claim 1, it is characterised in that the image by temporary library to the object to be identified The step of being identified, including：The image of the object to be identified is compared with each bottom storehouse image in the temporary library, obtained described to be identified The similarity of object and each bottom storehouse image in the temporary library；Judge whether the peak of the similarity is higher than predetermined threshold value；If it is, determine that object corresponding to the peak of the similarity is the object to be identified.
- 8. according to the method for claim 7, it is characterised in that methods described also includes：If the peak of the similarity is less than the predetermined threshold value, figure of the total storehouse to the object to be identified is switched to As being identified.
- 9. according to the method described in any one of claim 1 to 8, it is characterised in that methods described also includes：Regularly update described Temporary library.
- 10. according to the method for claim 9, it is characterised in that described the step of regularly updating the temporary library, including：The bottom storehouse image for meeting the alternative objects of the default constraints in renewable time that will periodically be stored in total storehouse Synchronizing information is to the temporary library；And/orPeriodically by the bottom storehouse figure that the object of the default constraints is not met in the renewable time of the interim library storage As information deletion.
- A kind of 11. object recognition equipment, it is characterised in that including：Acquisition module, for obtaining the image of object to be identified；Identification module, it is described to be identified right to determine for the image of the object to be identified to be identified by temporary library The identity of elephant；Wherein, the temporary library includes the bottom storehouse image information for meeting default constraints extracted from Zong Ku.
- 12. a kind of object recognition system, it is characterised in that the system includes：Image collecting device, processor and storage dress Put；Described image harvester, for gathering the image of object to be identified；Computer program is stored with the storage device, the computer program is performed when being run by the processor as weighed Profit requires the method described in 1 to 10 any one.
- 13. a kind of computer-readable recording medium, computer program is stored with the computer-readable recording medium, its feature Be, when the computer program is run by processor perform any one of the claims 1 to 10 described in method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711177901.8A CN107886079A (en) | 2017-11-22 | 2017-11-22 | Object identifying method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711177901.8A CN107886079A (en) | 2017-11-22 | 2017-11-22 | Object identifying method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107886079A true CN107886079A (en) | 2018-04-06 |
Family
ID=61774650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711177901.8A Pending CN107886079A (en) | 2017-11-22 | 2017-11-22 | Object identifying method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107886079A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921055A (en) * | 2018-06-15 | 2018-11-30 | 北京蜂盒科技有限公司 | Personal identification method, device, storage medium and electronic equipment |
| CN109117808A (en) * | 2018-08-24 | 2019-01-01 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device, electronic equipment and computer readable medium |
| CN109145707A (en) * | 2018-06-20 | 2019-01-04 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109190466A (en) * | 2018-07-26 | 2019-01-11 | 高新兴科技集团股份有限公司 | A kind of method and apparatus that personnel position in real time |
| CN109376743A (en) * | 2018-09-28 | 2019-02-22 | 北京旷视科技有限公司 | Image processing method, device, image recognition apparatus and storage medium |
| CN110321834A (en) * | 2019-06-28 | 2019-10-11 | 深圳市商汤科技有限公司 | A kind of identity determines method and device, storage medium |
| CN110443198A (en) * | 2019-08-06 | 2019-11-12 | 中国工商银行股份有限公司 | Personal identification method and device based on recognition of face |
| CN111368622A (en) * | 2019-10-18 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Personnel identification method and device, and storage medium |
| CN111400520A (en) * | 2020-02-26 | 2020-07-10 | 北京沃东天骏信息技术有限公司 | Construction method of face recognition library, face payment method, device and system |
| CN111950364A (en) * | 2020-07-07 | 2020-11-17 | 北京思特奇信息技术股份有限公司 | System and method for identifying face of tens of millions of base libraries in different libraries |
| CN112101254A (en) * | 2020-09-21 | 2020-12-18 | 深圳喜为智慧科技有限公司 | Method and system for improving image recognition precision and speed |
| CN112329570A (en) * | 2020-10-27 | 2021-02-05 | 湖北邮电规划设计有限公司 | Airport customs intelligent card port system integrating 5G and block chain technology |
| CN112395904A (en) * | 2019-08-12 | 2021-02-23 | 北京蜂盒科技有限公司 | Biological feature recognition method and system |
| WO2022227562A1 (en) * | 2021-04-27 | 2022-11-03 | 北京市商汤科技开发有限公司 | Identity recognition method and apparatus, and electronic device, storage medium and computer program product |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537351A (en) * | 2014-12-31 | 2015-04-22 | 深圳泰山在线科技有限公司 | Quick large-number face recognition method and system |
| CN105473058A (en) * | 2013-06-18 | 2016-04-06 | 达美生物识别科技有限公司 | Iris imaging apparatus and methods for configuring an iris imaging apparatus |
| CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
-
2017
- 2017-11-22 CN CN201711177901.8A patent/CN107886079A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105473058A (en) * | 2013-06-18 | 2016-04-06 | 达美生物识别科技有限公司 | Iris imaging apparatus and methods for configuring an iris imaging apparatus |
| CN104537351A (en) * | 2014-12-31 | 2015-04-22 | 深圳泰山在线科技有限公司 | Quick large-number face recognition method and system |
| CN106446816A (en) * | 2016-09-14 | 2017-02-22 | 北京旷视科技有限公司 | Face recognition method and device |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921055A (en) * | 2018-06-15 | 2018-11-30 | 北京蜂盒科技有限公司 | Personal identification method, device, storage medium and electronic equipment |
| CN109145707A (en) * | 2018-06-20 | 2019-01-04 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109145707B (en) * | 2018-06-20 | 2021-09-14 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109190466A (en) * | 2018-07-26 | 2019-01-11 | 高新兴科技集团股份有限公司 | A kind of method and apparatus that personnel position in real time |
| CN109117808B (en) * | 2018-08-24 | 2020-11-03 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device, electronic equipment and computer readable medium |
| CN109117808A (en) * | 2018-08-24 | 2019-01-01 | 深圳前海达闼云端智能科技有限公司 | Face recognition method and device, electronic equipment and computer readable medium |
| CN109376743A (en) * | 2018-09-28 | 2019-02-22 | 北京旷视科技有限公司 | Image processing method, device, image recognition apparatus and storage medium |
| CN110321834A (en) * | 2019-06-28 | 2019-10-11 | 深圳市商汤科技有限公司 | A kind of identity determines method and device, storage medium |
| CN110443198B (en) * | 2019-08-06 | 2022-02-25 | 中国工商银行股份有限公司 | Identity recognition method and device based on face recognition |
| CN110443198A (en) * | 2019-08-06 | 2019-11-12 | 中国工商银行股份有限公司 | Personal identification method and device based on recognition of face |
| CN112395904A (en) * | 2019-08-12 | 2021-02-23 | 北京蜂盒科技有限公司 | Biological feature recognition method and system |
| CN111368622A (en) * | 2019-10-18 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Personnel identification method and device, and storage medium |
| CN111368622B (en) * | 2019-10-18 | 2024-01-12 | 杭州海康威视系统技术有限公司 | Personnel identification method and device and storage medium |
| CN111400520A (en) * | 2020-02-26 | 2020-07-10 | 北京沃东天骏信息技术有限公司 | Construction method of face recognition library, face payment method, device and system |
| CN111400520B (en) * | 2020-02-26 | 2023-08-04 | 北京沃东天骏信息技术有限公司 | Face recognition library construction method, face payment method, device and system |
| CN111950364A (en) * | 2020-07-07 | 2020-11-17 | 北京思特奇信息技术股份有限公司 | System and method for identifying face of tens of millions of base libraries in different libraries |
| CN111950364B (en) * | 2020-07-07 | 2024-03-22 | 北京思特奇信息技术股份有限公司 | System and method for identifying library-separating face of tens of millions of libraries |
| CN112101254A (en) * | 2020-09-21 | 2020-12-18 | 深圳喜为智慧科技有限公司 | Method and system for improving image recognition precision and speed |
| CN112329570A (en) * | 2020-10-27 | 2021-02-05 | 湖北邮电规划设计有限公司 | Airport customs intelligent card port system integrating 5G and block chain technology |
| WO2022227562A1 (en) * | 2021-04-27 | 2022-11-03 | 北京市商汤科技开发有限公司 | Identity recognition method and apparatus, and electronic device, storage medium and computer program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107886079A (en) | Object identifying method, apparatus and system | |
| CN107403173B (en) | Face recognition system and method | |
| US20220012512A1 (en) | Intelligent gallery management for biometrics | |
| IL258817A (en) | Methods and apparatus for false positive minimization in facial recognition applications | |
| CN108170732A (en) | Face picture search method and computer readable storage medium | |
| CN106709776A (en) | Commodity pushing method and apparatus thereof | |
| CN109783685A (en) | A kind of querying method and device | |
| CN109710780A (en) | A kind of archiving method and device | |
| CN105279496B (en) | A kind of method and apparatus of recognition of face | |
| CN102945366A (en) | Method and device for face recognition | |
| CN108664914A (en) | Face retrieval method, apparatus and server | |
| CN109872419A (en) | Method, apparatus, server and storage medium are moved in guest room based on recognition of face | |
| US20170091584A1 (en) | Classifying and Grouping Electronic Images | |
| CN109857891A (en) | A kind of querying method and device | |
| CN107357815A (en) | A kind of recognition methods of image content and system | |
| CN112199530B (en) | Multi-dimensional face library picture automatic updating method, system, equipment and medium | |
| CN108108711A (en) | Face supervision method, electronic equipment and storage medium | |
| CN108615286B (en) | Intelligent management method and system for cell | |
| CN109800318A (en) | A kind of archiving method and device | |
| CN204791137U (en) | Hotel moves in management system by oneself | |
| CN109359689B (en) | Data identification method and device | |
| CN112925899A (en) | Ranking model establishing method, case clue recommending device and medium | |
| CN110390747A (en) | A kind of Intelligent Office space building guard method and computer readable storage medium | |
| CN109859011A (en) | Based on the information push method in store, system and its storage medium in jewellery wire | |
| WO2021135933A1 (en) | Target recognition method and device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180406 |
|
| RJ01 | Rejection of invention patent application after publication |