CN111311297B - Method and device for generating member face library and computing equipment - Google Patents
Method and device for generating member face library and computing equipment Download PDFInfo
- Publication number
- CN111311297B CN111311297B CN201811520919.8A CN201811520919A CN111311297B CN 111311297 B CN111311297 B CN 111311297B CN 201811520919 A CN201811520919 A CN 201811520919A CN 111311297 B CN111311297 B CN 111311297B
- Authority
- CN
- China
- Prior art keywords
- face
- album
- payment
- identified
- time
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a method, a device and computing equipment for generating a member face library. The method comprises the following steps: acquiring a face information sequence, wherein the face information sequence comprises a plurality of face data records sequenced according to acquisition time, and each face data record comprises a face picture and acquisition time; acquiring a bill information sequence, wherein the bill information sequence comprises a plurality of payment data records ordered according to payment time, and each payment data record comprises a user identification and payment time; and associating the face picture with the user identifier according to the acquisition time and the payment time to generate a member face library. The invention improves the efficiency of the face registration process of the member.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for generating a member face library and computing equipment.
Background
Under the super business environment, the member identity information and the face information are required to be correlated to generate a member face library, so that basic data are provided for subsequent store identification, accurate marketing, portrait depiction and the like.
The face and member identity association can be achieved by operating activities such as face registration equipment of online store-down and online Application (APP) face submitting entrance, and users are attracted to actively submit face pictures with discounts and interests, so that association of face and member accounts is achieved.
Therefore, the existing member face registration scheme is complicated, and requires additional multi-step operation of a user, so that the operation cost is high, and the user experience is poor.
Disclosure of Invention
The present invention has been made in view of the above-mentioned problems, and it is therefore an object of the present invention to provide a method, apparatus and computing device for generating a membership face library that overcomes or at least partially solves the above-mentioned problems.
According to one aspect of the present invention, there is provided a method of generating a member face library, comprising:
acquiring a face information sequence, wherein the face information sequence comprises a plurality of face data records sequenced according to acquisition time, and each face data record comprises a face picture and acquisition time;
acquiring a bill information sequence, wherein the bill information sequence comprises a plurality of payment data records ordered according to payment time, and each payment data record comprises a user identification and payment time;
and associating the face picture with the user identifier according to the acquisition time and the payment time to generate a member face library.
Optionally, according to the method for generating a member face library of the present invention, the associating the face picture with the user identifier according to the collection time and the payment time to generate the member face library includes: traversing the payment data records in the bill information sequence, and generating a time window containing the payment time of each traversed payment data record; acquiring a face picture set in the time window range from a face information sequence; updating the photo album to be identified, which is associated with the user identification of the payment data record, according to the acquired face picture set; when the confidence coefficient of the album to be identified is larger than the confidence coefficient threshold value, identifying the album to be identified as a member album of the member with the user identification, and adding the user identification and the member album into a member face library.
Optionally, according to the method for generating a member face library of the present invention, the updating, according to the obtained face picture set, the album to be identified associated with the user identifier of the payment data record includes: if the photo album to be identified corresponding to the user identification does not exist, the face picture set is created as the photo album to be identified corresponding to the user identification, and an initial score is set for the face pictures in the photo album to be identified; if the photo album to be identified corresponding to the user identification exists, the face picture set is added into the photo album to be identified, and the score of the face picture in the photo album to be identified is updated.
Optionally, according to the method for generating a member face library of the present invention, the updating the score of the face picture in the album to be identified includes: comparing face pictures in the face picture set with face pictures in the album to be identified one by one;
when the comparison result shows that the two face pictures belong to the same person, the scores of the two face pictures are respectively increased by a preset value.
Optionally, according to the method for generating a face library of a member of the present invention, after updating the score of the face picture in the album to be identified, the method further includes: and reserving a preset number of face pictures with the maximum scores in the album to be identified, and deleting the rest face pictures.
Optionally, the method for generating a member face library according to the present invention, after identifying the album to be identified as a member album, further includes: and reserving the maximum number of face pictures belonging to the same person in the member album, and deleting the rest face pictures.
Optionally, according to the method for generating a member face library of the present invention, when the traversed user identifier of the payment data record has an associated member album in the member face library, the payment data record is skipped, and the processing of the next payment data record is performed.
Optionally, the method for generating the member face library according to the present invention further includes: clustering face pictures in the face information sequence, so that the same picture identification is distributed for the face pictures belonging to the same person; correspondingly, after the face picture set is obtained, the face pictures in the face picture set are subjected to de-duplication processing according to the picture identification.
Optionally, the method for generating the member face library according to the present invention further includes filtering the face picture set according to the white list library, and deleting the face picture matched with the face picture in the white list library from the face picture set.
Optionally, according to the method for generating the member face library of the present invention, the face picture is acquired by the image capturing device under the authorization of the user.
According to another aspect of the present invention, there is provided an apparatus for generating a member face library, comprising:
the first acquisition module is suitable for acquiring a face information sequence, wherein the face information sequence comprises a plurality of face data records sequenced according to acquisition time, and each face data record comprises a face picture and acquisition time;
a second acquisition module adapted to acquire a billing information sequence comprising a plurality of payment data records ordered by payment time, each payment data record comprising a user identification and payment time;
and the association module is suitable for associating the face picture with the user identifier according to the acquisition time and the payment time so as to generate a member face library. The member face library includes a plurality of member records, each member record including a user identification of a member and an associated member album, the member album including one or more face pictures of the member.
Optionally, according to the device for generating the member face library of the present invention, the face picture is acquired by the image capturing device under the authorization of the user.
According to yet another aspect of the present invention, there is provided a computing device comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods described above.
According to yet another aspect of the present invention, there is provided a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods described above.
According to the scheme for generating the member face library, after the user authorization is obtained, the face information sequence and the bill information sequence are obtained, and the face information sequence comprises the acquisition time of the face picture, the bill information sequence comprises the payment time of the user, and the face picture is associated with the user identifier through the internal relationship between the acquisition time and the payment time, so that the member face library can be automatically generated without actively submitting the face picture by the user for registration. Therefore, the operation and time cost of the user are reduced, the efficiency of the face registration process of the member is improved, and the user experience is further improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 illustrates a schematic diagram of a system 100 for generating a membership face library according to one embodiment of the present invention;
FIG. 2 shows a schematic diagram of a computing device 200 according to one embodiment of the invention;
FIG. 3 illustrates a flow chart of a method 300 of generating a membership face library according to one embodiment of the present invention;
FIG. 4 illustrates a flow chart of a method 400 of generating a membership face library according to another embodiment of the present invention;
fig. 5 shows a schematic diagram of an apparatus 500 for generating a membership face library according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Fig. 1 shows a schematic diagram of a system 100 for generating a membership face library according to one embodiment of the invention. As shown in fig. 1, the system 100 includes a checkout device 110, an image capturing device 120, a data storage 130, and a computing device 200.
The checkout devices 110 are disposed within online off-premise superstores, each of which may be disposed one or more checkout devices 110. The checkout device 110, for example, a checkout POS, may be a manual checkout device or a self-checkout device. When a user uses an APP with a unique user Identification (ID) to carry out electronic payment (such as a payment treasure, a payment code and the like), the checkout equipment records the payment account number, the payment time and other commodity related information of the user to form a payment data record comprising the user identification and the payment time. The plurality of payment data are ordered by payment time, generating a billing information sequence (orderset). The billing information sequence may be expressed, for example, as:
wherein (1)>
Is indicated at +.>
By user ID j A purchase payment was successfully made.
The image pickup apparatuses 120 are arranged in online off-premise superstores, and each store may be provided with one or more image pickup apparatuses 120. In the case of obtaining the authorization of the user, the image capturing apparatus 120, for example, a face snapshot machine, adopts a form of an integrated network camera with an intelligent face snapshot algorithm or a form of a general camera plus an intelligent analysis box, and implements face detection and image interception of a face part in a visual field. Generally, the system has a tracking function, continuously tracks the actions of the same person, and selects one or more face pictures which are best in the tracking period. The image capturing apparatus 120 records the face picture and the acquisition time to form a face data record. It can be seen that, in the embodiment of the present invention, the face data collected and recorded by the image capturing apparatus 120 is performed with the user's knowledge and consent.
The user may perform the authorization in various ways, for example, clicking an authorization button on the payment APP, smiling a lens, performing a specified step operation according to a text/voice/operator's prompt, or the like. The embodiment of the invention does not limit the specific authorization mode.
The face data records are ordered according to the acquisition time to generate a face information sequence (face). The face information sequence may be expressed, for example, as:
wherein (1)>
Is indicated at +.>
A face picture f is obtained i 。
The image capturing apparatus 120 is typically disposed at the same physical location as the checkout apparatus 110 or on the same physical machine. Therefore, if the acquisition time of the face picture is the same as the payment time of the user for payment, or the time difference of the acquisition time and the payment time is within a preset range, the face picture is the face picture of the user for payment in a high probability, and therefore the face picture and the user identification are associated, and a member face library can be formed.
In one implementation, the image capture device 120 may send a plurality of face data records to a data server in the cloud or to the computing device 200, with the face information sequence being formed by the data server or the computing device 200. It should be noted that, the data server or the computing device generally receives face data records sent by multiple image capturing devices (which may be image capturing devices of one store or multiple stores), so that the face data records in the face information sequence correspond to face pictures collected by the multiple image capturing devices. The face data records are typically sent to the cloud data server or computing device 200 via a general file transfer protocol such as FTP or a proprietary data protocol based on HTTP/TCP/UDP.
Similarly, the checkout device 110 may send the plurality of payment data records to a data server at the cloud or to the computing device 200, with the billing information sequence being formed by the data server or the computing device 200. The data server or computing device typically receives payment data records transmitted by multiple checkout devices (which may be one or more store-superbars checkout devices) such that the payment data records in the billing information sequence correspond to the payment data records generated by the multiple checkout devices.
The computing device 200 may perform offline association of face pictures with user identifications to generate a member face library based on the locally stored face information sequence and billing information sequence, or by retrieving the face information sequence and billing information sequence from a data server. The member face library includes a plurality of member records, each member record including a user identification of a member and an associated member album, the member album including a face picture of one or more members.
The member face database may be stored in the data storage device 130, and the data storage device 130 may be a relational database such as MySQL, ACCESS, etc., or a non-relational database such as NoSQL, etc.; the data storage device 130 may be a local database residing in the computing device 200, or may be a distributed database, such as HBase, disposed at a plurality of geographic locations, and in any case, the data storage device 130 is used to store data, and the specific deployment and configuration of the data storage device 130 is not limited by the present invention. The computing device 200 may connect with the data store 130 and retrieve data stored in the data store 130. For example, the computing device 200 may directly read the data in the data storage 130 (when the data storage 130 is a local database of the computing device 200), or may access the internet through a wired or wireless manner, and obtain the data in the data storage 130 through a data interface.
The method of generating a member face library of the present invention may be performed in a computing device. FIG. 2 illustrates a block diagram of a computing device 200 according to one embodiment of the invention. As shown in FIG. 2, in a basic configuration 202, computing device 200 typically includes a system memory 206 and one or more processors 204. A memory bus 208 may be used for communication between the processor 204 and the system memory 206.
Depending on the desired configuration, the processor 204 may be any type of processing including, but not limited to: a microprocessor (μp), a microcontroller (μc), a digital information processor (DSP), or any combination thereof. Processor 204 may include one or more levels of cache, such as a first level cache 210 and a second level cache 212, a processor core 214, and registers 216. The example processor core 214 may include an Arithmetic Logic Unit (ALU), a Floating Point Unit (FPU), a digital signal processing core (DSP core), or any combination thereof. The example memory controller 218 may be used with the processor 204, or in some implementations, the memory controller 218 may be an internal part of the processor 204.
Depending on the desired configuration, system memory 206 may be any type of memory including, but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. The system memory 106 may include an operating system 220, one or more applications 222, and program data 224. The application 222 is in effect a plurality of program instructions for instructing the processor 204 to perform a corresponding operation. In some implementations, the application 222 can be arranged to cause the processor 204 to operate with the program data 224 on an operating system.
The network communication link may be one example of a communication medium. Communication media may typically be embodied by computer readable instructions, data structures, program modules, and may include any information delivery media in a modulated data signal, such as a carrier wave or other transport mechanism. A "modulated data signal" may be a signal that has one or more of its data set or changed in such a manner as to encode information in the signal. By way of non-limiting example, communication media may include wired media such as a wired network or special purpose network, and wireless media such as acoustic, radio Frequency (RF), microwave, infrared (IR) or other wireless media. The term computer readable media as used herein may include both storage media and communication media.
In the computing device 200 according to the invention, the application 222 comprises means 500 for generating a membership face library, the means 500 comprising a plurality of program instructions which may instruct the processor 104 to perform the method 300 or the method 400 for generating a membership face library.
Fig. 3 illustrates a flow chart of a method 300 of generating a membership face library according to one embodiment of the invention. The method 300 is suitable for execution in a computing device, such as the computing device 200 described previously. As shown in fig. 3, the method 300 sequentially includes steps S310 to S330.
In step S310, a face information sequence is acquired, where the face information sequence includes a plurality of face data records ordered according to a collection time, and each face data record includes a face picture and a collection time. The computing device may receive face data records transmitted by the plurality of image capturing devices and sort the face data records according to the acquisition time to generate a face information sequence. The face information sequence may also be generated by the data server from a face data record sent by the image capturing apparatus, and then the computing apparatus acquires the face information sequence from the data server. In the embodiment of the present invention, the image capturing apparatus performs the acquisition of the face data under the condition that the user authorization is obtained, that is, the face data acquired and recorded by the image capturing apparatus is performed under the condition that the user knows and agrees.
The user may perform the authorization in various ways, for example, clicking an authorization button on the payment APP, smiling a lens, performing a specified step operation according to a text/voice/operator's prompt, or the like. The embodiment of the invention does not limit the specific authorization mode.
In step S320, a billing information sequence is obtained, the billing information sequence comprising a plurality of payment data records ordered by payment time, each payment data record comprising a user identification and a payment time. The computing device may receive payment data records sent by the plurality of checkout devices and sort the payment data records by payment time to generate a billing information sequence. The billing information sequence may also be generated by the data server from the payment data record sent by the checkout device, and the computing device then obtains the billing information sequence from the data server.
In addition, the execution sequence of step S310 and step S320 is not limited in the embodiment of the present invention.
In step S330, the face picture is associated with the user identifier according to the collection time and the payment time, so as to generate a member face library. The member face library includes a plurality of member records, each member record including a user identification of a member and an associated member album, the member album including a face picture of one or more members. If the collection time of the face picture is the same as the payment time of the user for payment, or the time difference of the collection time and the payment time is within a preset range, the face picture is the face picture of the user for payment in a high probability, and therefore a member face library can be formed by associating the corresponding face picture with the user identification.
The application scene of the embodiment of the invention can be that a plurality of camera shooting devices and checkout devices of a plurality of shops are used for data acquisition, so that the correlation is directly carried out according to the acquisition time and the payment time, the generated member face library is not accurate enough, and the condition that the association between the face picture and the user identifier is wrong exists, and the association error needs to be eliminated manually. Thus, in another embodiment, a more accurate correlation algorithm is also provided.
Fig. 4 illustrates a flow chart of a method 400 of generating a membership face library according to another embodiment of the present invention. The method 400 is suitable for execution in a computing device, such as the computing device 200 described previously. As shown in fig. 4, the method 400 begins at step S410. In step S410, a face information sequence and a billing information sequence are acquired, and billing data in the billing information sequence may be cleaned as needed. Cleaning the bill data can comprise data retrieval according to information such as store names, equipment numbers and the like, cleaning out incomplete entries of key fields and the like, and forming a bill information sequence with complete data. Here, the face data is acquired by the image pickup apparatus, and the face data acquired and recorded by the image pickup apparatus is performed with the user's knowledge and consent. The user may perform the authorization in various ways, for example, clicking an authorization button on the payment APP, smiling a lens, performing a specified step operation according to a text/voice/operator's prompt, or the like. The embodiment of the invention does not limit the specific authorization mode.
The face information sequence may be expressed, for example, as:
wherein (1)>
Is indicated at +.>
A face picture f is obtained i . The billing information sequence may be expressed as:
wherein (1)>
Is indicated at +.>
By user ID j A purchase payment was successfully made. />
In step S420, the payment data records in the bill information sequence are traversed in order of the payment time from the smaller to the larger, and the user identification ID in each traversed payment data record is acquired j According to user identification ID j And querying a member face library, and judging whether a member album associated with the user identification exists in the member face library. If yes, skipping the payment data record, and executing the processing of the next payment data record; otherwise, the next processing is carried out.
In step S430, a payment time containing the payment data record is generated
And acquiring a face picture set in the range of the time window from the face information sequence. For example, record +.>
To pay for time->
Setting a time window for reference>
The face sequence facet in the facet corresponding to the time window is taken j ，faceset j And the face picture set to be processed is the current face picture set to be processed. Set T left And T right The purpose of (a) is that the user collects when making paymentThe acquisition time and the payment time of the face pictures often have deviation, so that the face pictures cannot be matched strictly according to the same time. T (T) left And T right The values of (2) may be determined based on empirical values, for example, 90s and 10s, respectively.
In step S440, face pictures are assembled j And performing face de-duplication. According to an embodiment of the present invention, for performing face deduplication, after obtaining the face of the face information sequence, clustering may be performed on the face images in the face data sequence in advance, so as to assign the same picture identifier (personID) to the face images belonging to the same person. Thus, to reduce the amount of subsequent processing computation, the faces can be identified based on unique personID identification assigned to each individual during the clustering process j Performing de-duplication, i.e. the same person (same personID), only keeping one face picture to obtain a face picture set facet after de-duplication j，unique 。
In step S450, the face picture set after the duplication removal is filtered according to the white list library, and the face picture matched with the face picture in the white list library is deleted from the face picture set. To reduce the influence of high-frequency salesmen on the association algorithm, according to one embodiment of the invention, face pictures of the salesmen are acquired in advance, and a white list database is established whitelist ＝[f 1 ,f 2 ，…，f k ，…，]Wherein f k And a face picture representing the employee. For fasceset j，unique Each face picture in the database, whether the face picture exists in the white list library or not is retrieved, if yes, the white list is displayed in the face whitelist In the middle match, then from the facet j,unique Obtaining a filtered face picture set facet by deleting j,ctmr 。
In step S460, it is determined whether the library to be identified has a user identification ID j If so, entering step S470; if not, the filtered face picture set is created as a user identification ID j Corresponding photo album to be identified, and setting initial score for face picture in photo album to be identified, e.g. toAnd setting the initial score of each face picture in the album to be 0, storing the user identification and the album to be identified in a library to be identified in an associated mode, returning to step S420, and executing the processing of one payment data record. Here, the face picture stored in the library to be recognized is a face picture which has been traversed from the face information sequence, and whether it is a member is not recognized.
In step S470, the user identification ID is compared with the user identification ID j Updating the associated album to be identified, which comprises the following steps: face picture collection face j,ctmr The face pictures in the album to be identified are added into the album to be identified, and the score of the face pictures in the album to be identified is updated. Specifically, face images in the face image set and face images in the album to be identified can be compared one by one, and when the comparison result shows that the two face images belong to the same person, the scores of the two face images are respectively increased by a preset value, for example, each value is increased by 1.
Further, only the predetermined number of face pictures with the largest score value, for example, 2 to 7, may be reserved in the album to be identified, and the remaining face pictures may be deleted.
In step S480, the confidence level of the album to be identified is compared with a confidence level threshold, and if the confidence level of the album to be identified is not greater than the confidence level threshold, it is not yet possible to confirm whether the face picture in the album to be identified is the user ID j Returning to step S420, and executing a process for a payment data record; if the confidence coefficient of the album to be identified is larger than the confidence coefficient threshold value, the next step is carried out.
According to one embodiment of the invention, the confidence of the album to be identified is N/M, M is the number of face pictures included in the album to be identified, and N is the maximum number of face pictures belonging to the same person in the album to be identified. For example, the album to be identified includes 7 face pictures, 4 of the photos belong to the user a, 2 of the photos belong to the user b, and 1 of the photos belong to the user c, and then m=7, n=4, and the confidence is 4/7. In addition, the confidence threshold may be empirically set, for example, to 0.8-0.99.
In step S490, the object is identifiedIdentifying another album as having a user identification ID j And storing the user identification and the member album in a member face library, and further deleting the album to be identified from the library to be identified.
Fig. 5 shows a schematic diagram of an apparatus 500 for generating a membership face library according to one embodiment of the present invention, the apparatus 500 residing in a computing device (e.g., the aforementioned computing device 200) to cause the computing device to perform the method of generating a membership face library of the present invention (e.g., the aforementioned methods 300 and 400). As shown in fig. 5, the apparatus 500 includes a first acquisition module 510, a second acquisition module 520, and an association module 530.
The first obtaining module 510 is adapted to obtain a face information sequence, where the face information sequence includes a plurality of face data records ordered according to a collection time, and each face data record includes a face picture and a collection time; here, the face data is acquired by the image pickup apparatus, and the face data acquired and recorded by the image pickup apparatus is performed with the user's knowledge and consent. The user may perform the authorization in various ways, for example, clicking an authorization button on the payment APP, smiling a lens, performing a specified step operation according to a text/voice/operator's prompt, or the like. The embodiment of the invention does not limit the specific authorization mode.
The second obtaining module 520 is adapted to obtain a billing information sequence comprising a plurality of payment data records ordered by payment time, each payment data record comprising a user identification and a payment time;
the association module 530 is adapted to associate the face picture with the user identification according to the acquisition time and the payment time, so as to generate a member face library. The member face library includes a plurality of member records, each member record including a user identification of a member and an associated member album, the member album including one or more face pictures of the member.
According to the scheme for generating the member face library, in the offline store area where the user authorization is obtained, the face photo can be actively submitted by the user for registration without depending on the user, the association library establishment of the face picture and the user identification is continuously and incrementally realized through limited hardware investment, and the association speed of the subsequent old customers can be continuously accelerated along with the continuous operation of the system. Furthermore, the duplication elimination and white list filtering are realized based on the face recognition technology, so that the convergence rate of the association algorithm can be increased.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Claims (14)
1. A method of generating a membership face library, comprising:
acquiring a face information sequence, wherein the face information sequence comprises a plurality of face data records sequenced according to acquisition time, and each face data record comprises a face picture and acquisition time;
acquiring a bill information sequence, wherein the bill information sequence comprises a plurality of payment data records ordered according to payment time, and each payment data record comprises a user identification and payment time;
and correlating the face picture with the user identifier, wherein the time difference between the acquisition time and the payment time is within a preset range, so as to generate a member face library.
2. The method of claim 1, wherein the associating the face picture with the user identification, the time difference between the collection time and the payment time being within a preset range, to generate the member face library, further comprises:
traversing the payment data records in the bill information sequence, and generating a time window containing the payment time of each traversed payment data record;
acquiring a face picture set in the time window range from a face information sequence;
updating the photo album to be identified, which is associated with the user identification of the payment data record, according to the acquired face picture set;
when the confidence coefficient of the album to be identified is larger than the confidence coefficient threshold value, identifying the album to be identified as a member album of the member with the user identification, and adding the user identification and the member album into a member face library.
3. The method of claim 2, wherein updating the album to be identified associated with the user identification of the payment data record according to the acquired face picture set comprises:
if the photo album to be identified corresponding to the user identification does not exist, the face picture set is created as the photo album to be identified corresponding to the user identification, and an initial score is set for the face pictures in the photo album to be identified;
if the photo album to be identified corresponding to the user identification exists, the face picture set is added into the photo album to be identified, and the score of the face picture in the photo album to be identified is updated.
4. The method of claim 3, wherein the updating of the score of the face picture in the album to be identified comprises:
comparing face pictures in the face picture set with face pictures in the album to be identified one by one;
when the comparison result shows that the two face pictures belong to the same person, the scores of the two face pictures are respectively increased by a preset value.
5. The method of claim 4, wherein after updating the score of the face picture in the album to be identified, further comprising:
and reserving a preset number of face pictures with the maximum scores in the album to be identified, and deleting the rest face pictures.
6. The method of claim 5, wherein after identifying the album to be identified as a member album, further comprising:
and reserving the maximum number of face pictures belonging to the same person in the member album, and deleting the rest face pictures.
7. The method of claim 2, wherein when the user identification of the traversed payment data record has an associated member album in the member face library, the payment data record is skipped and processing of the next payment data record is performed.
8. The method of claim 2, further comprising: clustering face pictures in the face information sequence, so that the same picture identification is distributed for the face pictures belonging to the same person;
correspondingly, after the face picture set is obtained, the face pictures in the face picture set are subjected to de-duplication processing according to the picture identification.
9. The method of claim 8, further comprising filtering the set of face pictures according to the whitelist library, and deleting face pictures from the set of face pictures that match face pictures in the whitelist library.
10. The method of claim 1, wherein the face picture is acquired by an image capture device under user authorization.
11. An apparatus for generating a member face library, comprising:
the first acquisition module is suitable for acquiring a face information sequence, wherein the face information sequence comprises a plurality of face data records sequenced according to acquisition time, and each face data record comprises a face picture and acquisition time;
a second acquisition module adapted to acquire a billing information sequence comprising a plurality of payment data records ordered by payment time, each payment data record comprising a user identification and payment time;
the association module is suitable for associating the face pictures with the user identifications, the time difference of the acquisition time and the payment time of which is within a preset range, so as to generate a member face library, wherein the member face library comprises a plurality of member records, each member record comprises the user identifications of the members and an associated member album, and the member album comprises one or more face pictures of the members.
12. The apparatus of claim 11, wherein the face picture is acquired by an image capture device under user authorization.
13. A computing device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods of claims 1-10.
14. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811520919.8A CN111311297B (en) | 2018-12-12 | 2018-12-12 | Method and device for generating member face library and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811520919.8A CN111311297B (en) | 2018-12-12 | 2018-12-12 | Method and device for generating member face library and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111311297A CN111311297A (en) | 2020-06-19 |
| CN111311297B true CN111311297B (en) | 2023-05-05 |
Family
ID=71152748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811520919.8A Active CN111311297B (en) | 2018-12-12 | 2018-12-12 | Method and device for generating member face library and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111311297B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010061266A (en) * | 2008-09-02 | 2010-03-18 | Fujifilm Corp | Use management system and use management method |
| CN102622580A (en) * | 2012-02-20 | 2012-08-01 | 华焦宝 | Face detection and recognition method and system |
| CN107767168A (en) * | 2017-09-19 | 2018-03-06 | 神策网络科技（北京）有限公司 | User behavior data processing method and processing device, electronic equipment and storage medium |
| CN108280368A (en) * | 2018-01-22 | 2018-07-13 | 北京腾云天下科技有限公司 | On a kind of line under data and line data correlating method and computing device |
| CN108346050A (en) * | 2018-03-29 | 2018-07-31 | 深圳正品创想科技有限公司 | A kind of method, apparatus creating user account and unmanned shop |
-
2018
- 2018-12-12 CN CN201811520919.8A patent/CN111311297B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010061266A (en) * | 2008-09-02 | 2010-03-18 | Fujifilm Corp | Use management system and use management method |
| CN102622580A (en) * | 2012-02-20 | 2012-08-01 | 华焦宝 | Face detection and recognition method and system |
| CN107767168A (en) * | 2017-09-19 | 2018-03-06 | 神策网络科技（北京）有限公司 | User behavior data processing method and processing device, electronic equipment and storage medium |
| CN108280368A (en) * | 2018-01-22 | 2018-07-13 | 北京腾云天下科技有限公司 | On a kind of line under data and line data correlating method and computing device |
| CN108346050A (en) * | 2018-03-29 | 2018-07-31 | 深圳正品创想科技有限公司 | A kind of method, apparatus creating user account and unmanned shop |
Non-Patent Citations (1)
| Title |
|---|
| 潘国庆 ; 徐文博 ; .基于Asp．Net的B2C电子商务的安全认证.微型电脑应用.2007,(第02期),35-37. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111311297A (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112055225B (en) | Live broadcast video interception, commodity information generation and object information generation methods and devices | |
| CN110799972A (en) | Dynamic human face image storage method and device, electronic equipment, medium and program | |
| US8774462B2 (en) | System and method for associating an order with an object in a multiple lane environment | |
| US9477685B1 (en) | Finding untagged images of a social network member | |
| JP5934653B2 (en) | Image classification device, image classification method, program, recording medium, integrated circuit, model creation device | |
| US11176597B2 (en) | Associating shoppers together | |
| JP5477017B2 (en) | Electronic device, content transmission method and program | |
| US10984250B2 (en) | Method and system for management of article storage and computer-readable medium | |
| CN107909443A (en) | Information-pushing method, apparatus and system | |
| JP5808371B2 (en) | Image recognition apparatus, image recognition method, and image recognition program | |
| WO2007004520A1 (en) | Searching system and searching method | |
| US9633272B2 (en) | Real time object scanning using a mobile phone and cloud-based visual search engine | |
| JP2010033143A (en) | Pos terminal device for acquiring personal attribute information, pos system, method for acquiring attribute information, and program for acquiring attribute information | |
| JP2019091487A (en) | Method of benchmarking media content based on viewer behavior | |
| US20160260106A1 (en) | Information processing apparatus, information processing method, and non-transitory computer readable medium | |
| KR101743169B1 (en) | System and Method for Searching Missing Family Using Facial Information and Storage Medium of Executing The Program | |
| JP2010231744A (en) | Information processing apparatus, program and image data management method | |
| CN111311297B (en) | Method and device for generating member face library and computing equipment | |
| JP6635208B1 (en) | Search device, search method, and program | |
| JP2019083532A (en) | Image processing system, image processing method, and image processing program | |
| JP5946315B2 (en) | Image search system | |
| JP2022058833A (en) | Information processing system, information processing apparatus, information processing method, and program | |
| JP6210554B2 (en) | Recognition device, recognition program, and recognition method | |
| JP2018194956A (en) | Image recognition dive, method and program | |
| WO2019157944A1 (en) | Item information processing method, system and device, and computer-readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |