CN113051981B - Face recognition method and device - Google Patents

Face recognition method and device Download PDF

Info

Publication number
CN113051981B
CN113051981B CN201911382570.0A CN201911382570A CN113051981B CN 113051981 B CN113051981 B CN 113051981B CN 201911382570 A CN201911382570 A CN 201911382570A CN 113051981 B CN113051981 B CN 113051981B
Authority
CN
China
Prior art keywords
user
local
face recognition
face
active
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
Application number
CN201911382570.0A
Other languages
Chinese (zh)
Other versions
CN113051981A (en
Inventor
曾文彬
严寒
袁钰斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Uniview Technologies Co Ltd
Original Assignee
Zhejiang Uniview Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Uniview Technologies Co Ltd filed Critical Zhejiang Uniview Technologies Co Ltd
Priority to CN201911382570.0A priority Critical patent/CN113051981B/en
Publication of CN113051981A publication Critical patent/CN113051981A/en
Application granted granted Critical
Publication of CN113051981B publication Critical patent/CN113051981B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06V40/161—Detection; Localisation; Normalisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The embodiment of the invention discloses a face recognition method and device. The method comprises the following steps: collecting a face image to be identified, and extracting feature information to be identified of the face image to be identified; identifying the characteristic information to be identified according to the characteristic information of the active users in the local active user set; if the identification fails, the characteristic information to be identified is identified according to the characteristic information of the common users in the local common user set. According to the face recognition method and device, the users corresponding to the face images stored in the face recognition terminal are divided into the active users and the common users, so that when the face images to be recognized are recognized, the face images of the active users are preferentially utilized for recognition, the face recognition efficiency is improved, and the recognition time is saved.

Description

Face recognition method and device
Technical Field
The embodiment of the invention relates to the technical field of face recognition, in particular to a face recognition method and device.
Background
Face recognition is widely applied to different fields, such as a face attendance machine, an identity login system, a face lock, a security monitoring system and the like. In the face recognition technology, whether the persons in the images are identical or not is judged by comparing the similarity of the two images.
In the actual use process, when recognizing the face in the image, the face recognition terminal usually compares the collected face image with the face stored by itself to obtain a recognition result. However, when the number of faces is large in the face recognition terminal, the face images are compared with all faces one by one, so that the time consumed by face image recognition is long and the efficiency is low.
Disclosure of Invention
The embodiment of the invention provides a face recognition method and device, which improves the face recognition efficiency and saves the recognition time.
In a first aspect, an embodiment of the present invention provides a face recognition method, including:
collecting a face image to be identified, and extracting feature information to be identified of the face image to be identified;
identifying the characteristic information to be identified according to the characteristic information of the active users in the local active user set;
if the identification fails, the characteristic information to be identified is identified according to the characteristic information of the common users in the local common user set.
In a second aspect, an embodiment of the present invention further provides a face recognition device, including:
the information extraction module is used for collecting the face image to be identified and extracting the characteristic information to be identified of the face image to be identified;
The first identification module is used for identifying the characteristic information to be identified according to the characteristic information of the active users in the local active user set;
and the second recognition module is used for recognizing the feature information to be recognized according to the feature information of the common users in the local common user set if the recognition fails.
The technical scheme disclosed by the embodiment of the invention has the following beneficial effects:
the method comprises the steps of collecting face images to be recognized, extracting feature information to be recognized of the face images to be recognized, recognizing the feature information to be recognized according to the feature information of active users in a local active user set, and recognizing the feature information to be recognized according to the feature information of common users in the local common user set when recognition fails. Therefore, the users corresponding to the face images stored in the face recognition terminal are divided into the active users and the common users, so that the face images of the active users are preferentially utilized for recognition when the face images to be recognized are recognized, the face recognition efficiency is improved, and the recognition time is saved.
Drawings
Fig. 1 is a schematic flow chart of a face recognition method according to an embodiment of the present invention;
Fig. 2 is a schematic flow chart of another face recognition method according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of another face recognition method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a face recognition device according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in further detail below with reference to the drawings and examples. It should be understood that the particular embodiments described herein are illustrative only and are not limiting of embodiments of the invention. It should be further noted that, for convenience of description, only some, but not all of the structures related to the embodiments of the present invention are shown in the drawings.
The following describes a face recognition method and device according to an embodiment of the present invention with reference to the accompanying drawings. Fig. 1 is a schematic flow chart of a face recognition method according to an embodiment of the present invention, where the embodiment is applicable to the case of recognizing the acquired face image, the method may be performed by a face recognition device, and the face recognition device may be composed of hardware and/or software. The face recognition method specifically comprises the following steps:
s101, acquiring a face image to be identified, and extracting feature information to be identified of the face image to be identified.
The feature information to be identified may include: the feature information of the five sense organs, the face curve information, the positional relationship related to the five sense organs, and the like can be determined specifically according to actual needs, and are not particularly limited here.
Before executing S101, the embodiment of the present invention may introduce a plurality of face images into a face recognition terminal by using an external device, so that the face recognition terminal extracts feature information of each of the introduced face images, and obtains feature information corresponding to each of the face images. The imported face images may be obtained from a standard image library through the internet, or may be collected by a face recognition terminal in a history manner, which is not limited herein. In the embodiment of the invention, the face recognition terminal is defined as a local face recognition terminal.
After a plurality of face images are imported into the local face recognition terminal, user-defined operation can be performed on users corresponding to the face images, so that basis is provided for subsequent face recognition. For example, defining the user corresponding to the imported plurality of face images as a common user; or defining the users corresponding to the imported face images as active users; or, the users corresponding to the imported face images are divided into two types, namely active users and common users.
Furthermore, when a plurality of face images are imported into the local face recognition terminal, user identity information corresponding to each face image can be imported together, so that a foundation is laid for displaying the user identity information corresponding to the face image and a base map (the face image when imported) after any face image is successfully recognized later. The user identity information can be adaptively set according to the application scene. For example, if the application scenario is a campus, the user identity information may include: name, gender, company name, etc.; as another example, if the application scenario is a station, the user identity information may include: name, gender, identification card number, birth address, etc.; for another example, if the application scenario is a company, the user identity information may include: name, gender, department, post, etc.
In order to facilitate the description of the embodiments of the present invention, the above-mentioned classification of the plurality of face images imported in the local face recognition terminal into two types is used to describe the local active users and the local normal users, respectively.
Optionally, when the local face recognition terminal captures a face, automatically acquiring a face image, and taking the acquired face image as the face image to be recognized. And then extracting the feature information to be recognized of the face image to be recognized.
In the embodiment of the invention, the extraction of the feature information to be identified of the face image to be identified can be realized in various modes. For example, one or more of a face feature point based recognition algorithm, an entire face image based recognition algorithm, and a neural network model based recognition.
S102, identifying the feature information to be identified according to the feature information of the active users in the local active user set.
For example, after extracting the feature information to be identified of the face image to be identified, the local face identification terminal may calculate a similarity (first similarity) between the feature information to be identified and the feature information of each active user in the local active user set. And then, comparing the calculated at least two first similarities with a similarity threshold value respectively to determine whether first similarities larger than the similarity threshold value exist or not. If the first similarity is larger than the similarity threshold, the identification is successful; if all the first similarities are smaller than the similarity threshold, the recognition fails.
The similarity threshold in the embodiment of the present invention may be set with different precision according to practical applications, which is not specifically limited herein. It should be noted that, in the embodiment of the present invention, all similarity thresholds are the same value. Of course, it may also be provided differently. The invention is not limited in this regard.
That is, according to the feature information of the active users in the local active user set, the embodiment of the present invention identifies the feature information to be identified, including:
determining a first similarity between the feature information to be identified and the feature information of each active user in the local active user set;
if any first similarity is larger than a similarity threshold, the identification is successful;
if all the first similarities are smaller than or equal to the similarity threshold, the identification fails.
Further, the local active user set further includes: user identity information and base map corresponding to the characteristic information of each active user. When the local face recognition terminal determines that the calculated at least two first similarities have the first similarity larger than the similarity threshold, the first similarity quantity larger than the similarity threshold can be determined, and user identity information and a base map corresponding to the characteristic information of the active user associated with the first similarity are acquired from the local active user set in different modes according to the first similarity quantity so as to display the acquired user identity information and the base map.
When the first similarity number larger than the similarity threshold is determined to be one, user identity information and a base map corresponding to the characteristic information of the active user associated with the first similarity are obtained from the local active user set; and if the number of the first similarities larger than the similarity threshold is at least two, selecting the largest first similarity from the at least two first similarities, and acquiring user identity information and a base map corresponding to the characteristic information of the active user associated with the largest first similarity from the local active user set.
And displaying the obtained user identity information and the base map corresponding to the characteristic information of the active user associated with the first similarity or the first similarity with the maximum similarity.
And S103, if the identification fails, identifying the characteristic information to be identified according to the characteristic information of the common users in the local common user set.
Optionally, when the feature to be identified fails to be identified according to the feature information of the active users in the local active user set, the feature information of the common users in the local common user set may be utilized to identify the feature information to be identified.
In specific implementation, the similarity (second similarity) between the feature to be identified and the feature information of each general user in the local general user set is calculated. And then, comparing the obtained at least two second similarities with a similarity threshold value respectively, and determining whether the second similarities larger than the similarity threshold value exist or not. If the second similarity is larger than the similarity threshold, the identification is successful; if all the second similarities are smaller than the similarity threshold, the recognition fails.
It should be noted that, in the embodiment of the present invention, the active user set and the common user set in the local face recognition terminal may also be updated according to the recognition situation of the historical face image. In the specific implementation, the historical face image is identified to obtain a historical user to which the historical face image belongs, and the occurrence frequency of the historical user is updated; and placing face images of the historical users into a local active user set or a local common user set according to the occurrence frequency of the historical users.
That is, the more frequently any historical user occurs, the more frequently the historical user is identified, at which time the historical user may be placed into a local active user set; the less frequently any historical user occurs, the less rarely the historical user is identified, at which point the historical user may be placed into a local set of common users.
According to the face recognition method provided by the embodiment of the invention, the face image to be recognized is acquired, and the feature information to be recognized of the face image to be recognized is extracted, so that the feature information to be recognized is recognized according to the feature information of the active user in the local active user set, and when the recognition fails, the feature information to be recognized is recognized according to the feature information of the common user in the local common user set. Therefore, the users corresponding to the face images stored in the face recognition terminal are divided into the active users and the common users, so that the face images of the active users are preferentially utilized for recognition when the face images to be recognized are recognized, the face recognition efficiency is improved, and the recognition time is saved.
Based on the above embodiment, after embodiment S103 of the present invention, it further includes:
detecting whether each active user in a local active user set performs face recognition operation in a preset time;
If any active user does not perform face recognition operation within the preset time, the active user is placed into a local common user set, and the active user is deleted from the local active user set.
The preset time may be set according to actual requirements, which is not limited herein. For example, one week, two weeks, etc.
It should be noted that, in the embodiment of the present invention, whether each active user in the local active user set performs the face recognition operation in the preset time is detected, specifically, the detection operation is performed when the local face recognition terminal is not in the face recognition operation, that is, the detection operation is performed in the idle time, so that the normal face recognition operation performed by the local face recognition terminal is not affected.
According to the embodiment of the invention, whether the active users in the local active user set are regulated or not is determined by detecting whether the active users in the local active user set are subjected to identification operation or not within the preset time, so that the active users in the active user set of the local face recognition terminal are always users with high identification frequency, and the face recognition speed is improved.
In a specific implementation process, although a plurality of face images are stored in the local face recognition terminal, the local face recognition terminal cannot meet the requirement for face recognition under the scene of a large number of users (for example, more than 10 tens of thousands of parks or stations, etc.). Therefore, the embodiment of the invention constructs the face recognition terminal cluster, so that when the characteristic information of the active users in the active user set in the local face recognition terminal cannot recognize the face image to be recognized, the characteristic information to be recognized is recognized according to the characteristic information of the common users in the local common user set, and the concurrent recognition can be performed based on the user sets in other face recognition terminals in the cluster, thereby not only improving the recognition speed, but also increasing the number of the face images to meet the face recognition requirement under the scene of a large number of users. The above-mentioned case of the face recognition method according to the embodiment of the present invention will be described with reference to fig. 2.
Fig. 2 is a schematic flow chart of another face recognition method according to an embodiment of the present invention. As shown in fig. 2, the method specifically includes the following steps:
s201, acquiring a face image to be identified, and extracting feature information to be identified of the face image to be identified.
S202, identifying the feature information to be identified according to the feature information of the active users in the local active user set.
S203, if the identification fails, the obtained characteristic information to be identified is sent to other face identification terminals so as to instruct the other face identification terminals to identify the characteristic information to be identified; wherein the other face recognition terminals and the local face recognition terminal belong to the same cluster.
Wherein the number of other face recognition terminals is at least one.
For clarity of explanation of the embodiment of the present invention, first, explanation will be given for constructing a face recognition terminal cluster in the embodiment of the present invention.
In the embodiment of the invention, the face recognition terminal cluster can be constructed according to actual needs. For example, a plurality of face recognition terminals including any area of the local face recognition terminals are built into a face recognition terminal cluster; or, a plurality of face recognition terminals deployed in a plurality of areas are organized into a face recognition terminal cluster, wherein any one of the plurality of areas includes a local face recognition terminal, and so on. Wherein, the region may refer to: a community, a station, a park, a security check channel and the like.
It should be noted that, in other face recognition terminals in the cluster, a plurality of face images and identity information of users corresponding to each face image are also stored, and the face images stored in each other face recognition terminal are different. The number of the face images can be the same as or different from that of the local face recognition terminal. In the embodiment of the invention, the number of the face images stored in each other face recognition terminal is preferably the same as the number in the local face recognition terminal.
In order to monitor the operation condition of each face recognition terminal in the face recognition terminal cluster, the embodiment of the invention can also randomly select one face recognition terminal from the face recognition terminal cluster as a management terminal. The management terminal monitors face recognition terminals except the management terminal in the cluster, and when any face recognition terminal is abnormal (can not work normally), the abnormal notification message of the face recognition terminal is sent to other face recognition terminals which are normal in operation, and the abnormal face recognition terminal identification is carried in the notification message, so that the other face recognition terminals which are normal in operation do not send characteristic information to be identified to the abnormal face recognition terminal, and meanwhile early warning messages are sent to staff, so that the staff can maintain in time.
In addition, the face recognition terminals in the cluster can monitor the operation condition of the management terminals. Specifically, the face recognition terminals in the cluster determine whether the management terminal is abnormal according to whether query information sent by the management terminal is received in a preset time. If the query instruction sent by the management terminal is not received within the preset time, the management equipment is determined to be abnormal, at the moment, an abnormal message of the management terminal can be sent to other face recognition terminals, and an early warning message can be sent to staff. The query information is query local state information.
The management terminal may perform the monitoring according to the first preset time period when monitoring the face recognition terminals except the management terminal itself in the cluster, or may perform the monitoring in real time, which is not limited herein.
The monitoring of the management terminal by the face recognition terminal may be performed according to a second preset time period, or may be performed in real time, which is not limited herein.
The first preset time period and the second preset time period may be set as required, which is not specifically limited herein.
It should be noted that the first preset time period and the second preset time period may be the same or different. Preferably, in the embodiment of the present invention, the first preset time period is different from the second preset time period, and the second preset time period is greater than the first preset time period.
After the face recognition terminal cluster is constructed, when the identification of the feature information to be identified fails according to the feature information of the active users in the active user set, the local face recognition terminal can send the obtained feature information to be identified to other face recognition terminals in the cluster so as to instruct the other face recognition terminals to identify the feature information to be identified, so that the concurrent identification operation of the feature to be identified is realized, and the defect that one face recognition terminal stores a small number of face images can be overcome by utilizing the other face recognition terminals in the cluster to identify the feature to be identified, so that the number of the stored face images is increased through the constructed cluster, and the face recognition scene with a large number of users is met.
Each other face recognition terminal comprises other active user sets and other common user sets, and when the other face recognition terminals recognize the feature information to be recognized, the feature information of the active users in the other active user sets is preferentially utilized to recognize, and then the feature information of the common users in the other common user sets is utilized to recognize.
In specific implementation, each other face recognition terminal obtains at least two third similarities by calculating the similarity (third similarity) between the feature to be recognized and the feature information of each active user in the other active user set of the other face recognition terminal and calculating the third similarity between the feature to be recognized and the feature information of each common user in the other common user set of the other face recognition terminal.
For example, if the cluster has 4 face recognition terminals, X1, X2, X3 and X4 respectively, wherein X1 is a local face recognition terminal, X2, X3 and X4 are other face recognition terminals, wherein the other active user set of X2 includes 300 active users, respectively X2-h1, X2-h2, … and X2-h300, and the other common user set includes 300 common users, respectively X2-p1, X2-p2, … and X2-p300; the other active user sets of X3 comprise 300 active users, namely X3-h1, X3-h2, … and X3-h300, and the other common user sets comprise 300 common users, namely X3-p1, X3-p2, … and X3-p300; the other active user sets of X4 comprise 300 active users, namely X4-h1, X4-h2, … and X4-h300, and the other common user sets comprise 300 common users, namely X4-p1, X4-p2, … and X4-p300; the feature to be identified is W.
When X1 sends W to X2, X3 and X4, and X2, X3 and X4 identify W, X2 first utilizes 300 active users in the other active user set: and X2-h1, X2-h2, … and X2-h300, calculating the third similarity between the characteristic information of each active user and W, and obtaining 300 third similarities. Then, X2 utilizes 300 common users in the other common user set: and X2-p1, X2-p2, … and X2-p300, calculating the third similarity between the characteristic information of each common user and W, and obtaining 300 third similarities. Similarly, X3 and X4 are each 600 third similarities obtained as X2.
S204, identifying the characteristic information to be identified according to the characteristic information of the common users in the local common user set to obtain a local common identification result.
The order of executing S202 and S203 may be that S202 is executed first and S203 is executed second; or, S203 is executed first, and S203 is executed next; alternatively, S202 and S203 may be performed simultaneously, which is not particularly limited herein.
S205, receiving other recognition results fed back by other face recognition terminals.
For example, after the other face recognition terminals in the same cluster recognize the feature information to be recognized, each other face recognition terminal may feed back at least two third similarities obtained by recognition to the local face recognition terminal, so as to lay a foundation for the local face recognition terminal to determine a final recognition result based on the recognition results fed back by the other face recognition terminals.
It should be noted that, after identifying the feature information to be identified by each other face recognition terminal in the same cluster to obtain at least two third similarities, the at least two third similarities calculated by each may be fed back to the local face recognition terminal, or the largest third similarity may be selected from the at least two third similarities calculated by each, and then the largest third similarity is fed back to the local face recognition terminal.
Furthermore, when the features to be identified are identified, high precision and accuracy are required, and high speed is also required, so that when the local face identification terminal receives other identification results fed back by other face identification terminals, a waiting time T can be set. And when the waiting time T is exceeded, if the local face recognition terminal does not receive other recognition results fed back by any other face recognition terminal, the local face recognition terminal does not wait any more, and continues to execute subsequent operations so as to improve the face recognition speed.
S206, determining a final recognition result according to the local common recognition result and other recognition results.
In the embodiment of the invention, the final recognition result comprises recognition success or recognition failure.
Wherein the local common recognition result comprises at least two second similarities; the other recognition results include at least two third similarities.
Exemplary, the embodiment of the invention determines a final recognition result according to the local common recognition result and other recognition results, including: selecting the maximum similarity from the at least two second similarities and the at least two third similarities; comparing the maximum similarity with a similarity threshold; if the maximum similarity is greater than the similarity threshold, the identification is successful; if the maximum similarity is smaller than or equal to the similarity threshold, the identification fails.
The maximum similarity may be the second similarity or the third similarity.
Further, when the final recognition result is that the recognition is successful, the local face recognition terminal can acquire the user identity information and the base map corresponding to the feature information of the user associated with the maximum similarity from the local common user set or other face recognition terminals. And then, displaying the acquired user identity information and the base map corresponding to the characteristic information of the user associated with the maximum similarity.
When the final recognition result is recognition failure, the local face recognition terminal can display the recognition failure information of the face image to be recognized. Wherein the identification failure information includes at least one of: failure words and failure symbols are identified. Optionally, the embodiment of the invention can also carry out voice prompt or indicator lamp prompt and the like when displaying the identification failure information. That is, when the face image to be identified fails to be identified, the identification failure information is displayed so that the staff can timely conduct identity verification on the user with failed identification, and the reliability and accuracy of identification are improved.
The face recognition method provided by the embodiment of the invention realizes the following effects: firstly, a face recognition terminal cluster is established to form distributed storage, so that the number of face images is effectively increased, and the face recognition requirement under a scene with a large number of users is met; secondly, users corresponding to the face images stored in the face recognition terminal are divided into active users and common users, so that when the face images to be recognized are recognized, the face images of the active users are preferentially utilized for recognition, the face recognition efficiency is improved, and the recognition time is saved; thirdly, when any face recognition terminal cannot recognize the face image, other face recognition terminals in the cluster can concurrently recognize the face image again, so that the face recognition speed is improved; fourth, when any face recognition terminal is abnormal, other face recognition terminals can continue to work normally, so that the disaster tolerance is high.
On the basis of the above embodiment, the face images stored in each face recognition terminal and the corresponding user may change due to the fact that the face images and the identity information of the corresponding user can be shared and stored between the face recognition terminals in the same cluster. In order to facilitate effective and rapid identification of the collected face images to be identified, the local face identification terminal can detect whether the active users in the local active user set need to be updated or not. The above-mentioned case of the face recognition method according to the embodiment of the present invention will be described with reference to fig. 3.
It should be noted that in the embodiment of the present invention, other face recognition terminals in the cluster may perform operations similar to those of the local face recognition terminal, and the specific implementation process is similar to that of the detection of the local face recognition terminal, which is not described in detail herein.
Fig. 3 is a schematic flow chart of another face recognition method according to an embodiment of the present invention. As shown in fig. 3, the method specifically includes the following steps:
s301, reading face recognition records of active time periods in idle time, wherein the active time periods are time periods in which face recognition operation is frequent.
Wherein the idle time refers to any time other than the active time period.
In the embodiment of the invention, the active time period can be determined according to the intensity of the face recognition records, or can be set by a worker according to the needs, and the active time period is not limited herein. Wherein, the priority of the active time period set by the staff is higher than the time period determined according to the intensity of the face recognition records of the user.
In the actual use process, when the local face recognition terminal executes face recognition operation, a face recognition record is generated and used for storing recognized face information. Therefore, the local face recognition terminal can read the face recognition record in the active time period of the local face recognition terminal in idle time so as to lay a foundation for subsequently checking active users in the active user set.
S302, determining whether the number of times of success of each face recognition is larger than a preset number of times in the face recognition record, if so, executing S303, otherwise, executing S311.
The preset times are set according to actual requirements, and are not limited herein. For example, setting is made according to the active time.
For example, if the preset number of times is 10 times, when it is determined that the number of times of recognition success of the user Q11 is 15 times based on the face recognition record, it is determined that the number of times of recognition success of the user Q11 is greater than 10 times.
S303, if the success times of any face recognition are larger than the preset times, determining whether the user corresponding to the any face belongs to a local user set, if so, executing S304, otherwise, executing S307.
The local user set comprises a local active user set and a local common user set.
In the embodiment of the invention, whether the user corresponding to any face belongs to a local user set is determined based on the face recognition terminal identification in the latest face recognition record.
The face recognition terminal identifier may be any information capable of uniquely determining the identity of the face recognition terminal, such as a number or a serial number, which is not particularly limited herein.
It should be noted that, since the local face recognition terminal may also perform face recognition operation when detecting whether the active users in the active user set need to be updated, the user face recognition record read in S301 is changed, that is, the latest user face recognition record. At this time, it is required to determine whether the user corresponding to any face belongs to the local user set according to the latest user face recognition record.
For example, if the number of successful recognition times of the user Q11 is greater than the preset number, and it is determined according to the latest face recognition record that the user Q11 is successfully recognized by the other face recognition terminals X2 in the cluster, that is, the user Q11 belongs to the user of X2 and not to the user of the local face recognition terminal.
For another example, if the number of successful recognition times of the user Q11 is greater than the preset number, and it is determined according to the latest face recognition record that the user Q11 is successfully recognized by the local face recognition terminal X1, that is, the user Q11 belongs to the user of X1.
S304, if the user belongs to the local user set, determining whether the user belongs to the local active user set, if so, executing S305, otherwise, executing S306.
In the embodiment of the invention, the user identity information of each user in any user can be respectively compared with the user identity information corresponding to the active users in the local active user set to determine whether the user is the active user in the local active user set.
If the user identity information of any user is consistent with the user identity information corresponding to the active user in the local active user set, determining the active user belonging to the local active user set; if not, determining that the active users do not belong to the local active user set.
S305, if the user belongs to an active user in the local active user set, no processing is performed.
And S306, if the user does not belong to the local active user set, placing the user into the local active user set, and deleting the user in the local common user set.
When any user is determined not to belong to the local active user set, the user is indicated to belong to the local common user set, and at the moment, the user can be placed into the local active user set, and the user in the local common user set is deleted.
S307, if the user does not belong to the local user set, the feature information of the user, the user identity information corresponding to the feature information of the user and other face recognition terminal identifications of the base map are recorded in a dynamic pre-record table.
The dynamic pre-transmission record table is used for recording user information that the local face recognition terminal performs face recognition in an active time period and the number of successful recognition times is larger than the preset number. Wherein the user is an active user, and the corresponding user information is active user information.
In the embodiment of the invention, the dynamic pre-record table is generated by the local face recognition terminal and stored in the storage space, and is used for acquiring recorded users and related information thereof from other face recognition terminals in the cluster when the face recognition operation is performed in the active time later.
S308, reading the dynamic pre-record table before the active time is reached.
S309, based on the other face recognition terminal identifications recorded in the dynamic pre-biography table, the characteristic information of the user, the user identity information corresponding to the characteristic information of the user and the base map are obtained from the other face recognition terminals.
S310, the obtained characteristic information of the user, the user identity information corresponding to the characteristic information of the user and the base map are placed in a local active user set.
The method comprises the steps of obtaining user information recorded in a dynamic pre-biography table from other face recognition terminals, placing the obtained user characteristic information, user identity information corresponding to the user characteristic information and a base map into a local active user set, and updating active users in the local active user set, so that conditions are provided for follow-up face recognition.
Further, after obtaining the feature information of the user and the user identity information and the base map corresponding to the feature information of the user from the other face recognition terminals, the embodiment of the present invention further includes:
sending a deleting instruction to the other face recognition terminals so that the other face recognition terminals delete the characteristic information of the user, and the user identity information and the base map corresponding to the characteristic information of the user; the deleting instruction comprises identification information of the user.
S311, if the number of times of success of at least one face recognition is less than or equal to the preset number of times, no processing is performed.
According to the face recognition method, the face recognition record of the active time period is analyzed, and the active users in the active user set are updated according to the analysis result, so that the following face recognition execution is facilitated.
In the actual use process, the embodiment of the invention can be further improved based on the foregoing embodiment to adapt to more application scenes, and the improvement scheme is described below.
Scheme one:
face recognition terminals respectively deployed on a plurality of channels of the same gate form a face recognition terminal cluster, the same quantity of data with different characteristic information is imported into each face recognition terminal, and the characteristic information is used as the characteristic information of active users to form a characteristic information set. Then, the face images corresponding to all the characteristic information in the cluster and the user identity information corresponding to the face images are randomly stored in one face recognition terminal, and the face recognition terminal identification is sent to other face recognition terminals except the face recognition terminal identification.
When any face recognition terminal in the cluster acquires the face image R to be recognized, and after the feature information to be recognized of the face image R to be recognized is extracted, the feature information to be recognized is sent to other face recognition terminals in the cluster, so that the other face recognition terminals in the cluster use the feature information sets stored respectively and recognize the feature information to be recognized concurrently, and a recognition result is obtained.
During specific recognition, each face recognition terminal compares each similarity with a similarity threshold value by calculating the similarity between the feature information to be recognized and each feature information in the feature information set stored in the face recognition terminal so as to obtain a recognition result. And if any similarity is larger than the similarity threshold, the identification is successful, otherwise, the identification fails. The specific identification process is similar or identical to that of the previous embodiment, and will not be repeated here.
When any face recognition terminal successfully recognizes, the face recognition terminal can send an acquisition request to the face recognition terminal storing face images corresponding to all feature information of the clusters and user identity information corresponding to the face images, and display the face images and the user identity information fed back by the face recognition terminal storing the face images corresponding to all feature information of the clusters and the user identity information corresponding to the face images. When all face recognition terminals fail to recognize, the face recognition terminal collecting the face image R to be recognized can send the extracted feature to be recognized to other clusters so as to recognize the feature information to be recognized through the face recognition terminals in the other clusters.
It should be noted that, the face recognition terminal clusters formed by other clusters and the face recognition terminals deployed by multiple channels of the same gate belong to the same area, for example, the same park, the same station, or the like.
Scheme II:
face recognition terminals respectively deployed on a plurality of channels of the same door form a face recognition terminal cluster, the same quantity of data of the same characteristic information is imported into each face recognition terminal, the characteristic information is used as the characteristic information of active users to form a characteristic information set, then face images corresponding to all the characteristic information in the cluster and user identity information corresponding to the face images are randomly stored in one face recognition terminal, and the face recognition terminal identification is sent to other face recognition terminals except the face recognition terminal identification.
When any face recognition terminal in the cluster collects the face image G to be recognized, and extracts the feature information to be recognized of the face image G to be recognized, the similarity between the feature information to be recognized and each feature information in the feature information set stored by the terminal can be calculated, and each similarity is compared with a similarity threshold value to obtain a recognition result. And if the similarity is larger than the similarity threshold, the identification is successful, otherwise, the identification fails.
When the identification is successful, the face identification terminal can send an acquisition request to the face identification terminal storing the face images corresponding to all the characteristic information of the clusters and the user identity information corresponding to the face images, and when the face images and the user identity information fed back by the face identification terminal storing the face images corresponding to all the characteristic information of the clusters and the user identity information corresponding to the face images are received, the face identification terminal displays the face images and the user identity information. And when the face recognition terminal fails to recognize, the extracted feature to be recognized is sent to other clusters so as to recognize the feature information to be recognized through the other clusters.
Fig. 4 is a schematic structural diagram of a face recognition device according to an embodiment of the present invention. As shown in fig. 4, the face recognition device according to the embodiment of the present invention includes: an information extraction module 410, a first identification module 420, and a second identification module 430.
The information extraction module 410 is configured to collect a face image to be identified, and extract feature information to be identified of the face image to be identified;
the first identifying module 420 is configured to identify the feature information to be identified according to feature information of active users in the local active user set;
And the second identifying module 430 is configured to identify the feature information to be identified according to the feature information of the common user in the local common user set if the identification fails.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: an updating module and a first processing module.
The updating module is used for identifying the historical face image to obtain a historical user to which the historical face image belongs, and updating the occurrence frequency of the historical user;
the first processing module is used for placing the face image of the historical user into the local active user set or the local common user set according to the occurrence frequency of the historical user.
As an alternative implementation of an embodiment of the present invention, the first identification module 420 includes: a first determination subunit, a first identification subunit, and a second identification subunit;
the first determining subunit is used for determining a first similarity between the feature information to be identified and the feature information of each active user in the local active user set;
the first recognition subunit is used for recognizing successfully if any first similarity is larger than a similarity threshold value;
And the second recognition subunit is used for recognizing failure if all the first similarity is smaller than or equal to the similarity threshold value.
As an alternative implementation of an embodiment of the present invention, the first identification module 420 further includes: a second determination subunit and a processing subunit;
wherein the second determining subunit is configured to determine a first similarity number that is greater than the similarity threshold;
the processing subunit is configured to acquire, from the local active user set, user identity information and a base map corresponding to feature information of an active user associated with the first similarity if the first number of similarities greater than the similarity threshold is one;
and the processing subunit is further configured to select a maximum first similarity from at least two first similarities if the number of first similarities greater than the similarity threshold is at least two, and acquire user identity information and a base map corresponding to feature information of an active user associated with the maximum first similarity from the local active user set.
As an optional implementation manner of the embodiment of the present invention, the second identifying module 430 is specifically configured to:
the obtained characteristic information to be identified is sent to other face recognition terminals so as to instruct the other face recognition terminals to identify the characteristic information to be identified; the other face recognition terminals and the local face recognition terminal belong to the same cluster;
Identifying the characteristic information to be identified according to the characteristic information of the common users in the local common user set to obtain a local common identification result;
receiving other recognition results fed back by other face recognition terminals;
and determining a final recognition result according to the local common recognition result and other recognition results.
As an optional implementation manner of the embodiment of the present invention, the local common recognition result includes at least two second similarities; the other recognition results comprise at least one third similarity;
accordingly, the second identifying module 430 is further configured to:
selecting the maximum similarity from the at least two second similarities and the at least one third similarity;
comparing the maximum similarity with a similarity threshold;
if the maximum similarity is greater than the similarity threshold, the identification is successful;
if the maximum similarity is smaller than or equal to the similarity threshold, the identification fails.
As an optional implementation manner of the embodiment of the present invention, the second identifying module 430 is further configured to:
acquiring user identity information and a base map corresponding to the characteristic information of the user associated with the maximum similarity from the local common user set or other face recognition terminals;
Wherein, other face identification terminals include: other active user sets and other normal user sets.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: a display module;
the display module is used for displaying the acquired user identity information and the base map corresponding to the characteristic information of the active user associated with the first similarity or the maximum first similarity; or,
and displaying the acquired user identity information and the base map corresponding to the characteristic information of the user associated with the maximum similarity.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: the device comprises a reading module, a first determining module, a second determining module, a third determining module and a second processing module;
the system comprises a reading module, a recognition module and a storage module, wherein the reading module is used for reading face recognition records of an active time period in a first idle time, and the active time period is a time period with frequent face recognition operation;
the first determining module is used for determining whether the success times of each face recognition in the face recognition record are larger than preset times or not;
the second determining module is used for determining whether the user corresponding to the at least one face belongs to a local user set or not if the successful recognition times of the at least one face are larger than the preset times; wherein the local user set comprises a local active user set and a local common user set;
A third determining module, configured to determine whether the user belongs to a local active user set if the user belongs to a local user set;
and the second processing module is used for placing the user into the local active user set and deleting the user in the local common user set if the user does not belong to the local active user set.
As an optional implementation manner of the embodiment of the present invention, the second determining module is specifically configured to:
and determining whether the user corresponding to the at least one face belongs to a local user set or not based on the face recognition terminal identification in the latest face recognition record.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: a third processing module;
wherein, the third processing module is used for:
if the user does not belong to the local user set, recording the characteristic information of the user, user identity information corresponding to the characteristic information of the user and other face recognition terminal identifications of the base map in a dynamic pre-biography table;
reading the dynamic pre-biographic table before the active period is reached;
acquiring the characteristic information of the user, and user identity information and a base map corresponding to the characteristic information of the user from other face recognition terminals based on other face recognition terminal identifiers recorded in the dynamic pre-biography table;
And placing the acquired characteristic information of the user, and user identity information and a base map corresponding to the characteristic information of the user into a local active user set.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: a control module;
the control module is used for sending a deleting instruction to the other face recognition terminals so that the other face recognition terminals delete the characteristic information of the user, the user identity information and the base map corresponding to the characteristic information of the user; the deleting instruction comprises identification information of the user.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: a detection module and a deletion module;
the detection module is used for detecting whether each active user in the local active user set performs face recognition operation in a preset time or not in a second idle time;
the deletion module is used for placing the active user into a local common user set if any active user does not perform face recognition operation within a preset time, and deleting the active user from the local active user set.
It should be noted that the foregoing explanation of the embodiment of the face recognition method is also applicable to the face recognition device of this embodiment, and the implementation principle is similar, and will not be repeated here.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.

Claims (13)

1. A face recognition method, comprising:
collecting a face image to be identified, and extracting feature information to be identified of the face image to be identified;
identifying the characteristic information to be identified according to the characteristic information of the active users in the local active user set;
if the identification fails, identifying the characteristic information to be identified according to the characteristic information of the common users in the local common user set;
reading face recognition records of an active time period in idle time, wherein the active time period is a time period with frequent face recognition operation;
Determining whether the successful times of each face recognition are larger than preset times in the face recognition record;
if the successful times of the identification of any face is greater than the preset times, determining whether the user corresponding to the any face belongs to a local user set; wherein the local user set comprises a local active user set and a local common user set;
if the user belongs to the local user set, determining whether the user belongs to the local active user set;
and if the user does not belong to the local active user set, placing the user into the local active user set, and deleting the user in the local common user set.
2. The method according to claim 1, wherein the method further comprises:
recognizing a historical face image to obtain a historical user to which the historical face image belongs, and updating the occurrence frequency of the historical user;
and placing the face image of the historical user into the local active user set or the local common user set according to the occurrence frequency of the historical user.
3. The method according to claim 1 or 2, wherein the identifying the feature information to be identified according to the feature information of active users in the local active user set comprises:
Determining a first similarity between the feature information to be identified and the feature information of each active user in the local active user set;
if any first similarity is larger than a similarity threshold, the identification is successful;
if all the first similarities are smaller than or equal to the similarity threshold, the identification fails.
4. A method according to claim 3, further comprising, after said identifying is successful:
determining a first number of similarities greater than the similarity threshold;
if the number of the first similarity greater than the similarity threshold is one, acquiring user identity information and a base map corresponding to the characteristic information of the active user associated with the first similarity from the local active user set;
and if the number of the first similarities larger than the similarity threshold is at least two, selecting the largest first similarity from at least two first similarities, and acquiring user identity information and a base map corresponding to the characteristic information of the active user associated with the largest first similarity from the local active user set.
5. The method according to claim 1 or 2, wherein the identifying the feature information to be identified according to the feature information of the general users in the local general user set includes:
The obtained characteristic information to be identified is sent to other face recognition terminals so as to instruct the other face recognition terminals to identify the characteristic information to be identified; the other face recognition terminals and the local face recognition terminal belong to the same cluster;
identifying the characteristic information to be identified according to the characteristic information of the common users in the local common user set to obtain a local common identification result;
receiving other recognition results fed back by other face recognition terminals;
and determining a final recognition result according to the local common recognition result and other recognition results.
6. The method of claim 5, wherein the local normal recognition result includes at least two second similarities; the other recognition results comprise at least two third similarities;
correspondingly, the determining the final recognition result according to the local common recognition result and other recognition results comprises the following steps:
selecting the maximum similarity from the at least two second similarities and the at least two third similarities;
comparing the maximum similarity with a similarity threshold;
if the maximum similarity is greater than the similarity threshold, the identification is successful;
If the maximum similarity is smaller than or equal to the similarity threshold, the identification fails.
7. The method of claim 6, further comprising, after the identifying is successful:
acquiring user identity information and a base map corresponding to the characteristic information of the user associated with the maximum similarity from the local common user set or other face recognition terminals;
wherein, other face identification terminals include: other active user sets and other normal user sets.
8. The method according to claim 4 or 7, characterized in that the method further comprises:
displaying user identity information and a base map corresponding to the acquired characteristic information of the active user associated with the first similarity or the largest first similarity; or,
and displaying the acquired user identity information and the base map corresponding to the characteristic information of the user associated with the maximum similarity.
9. The method of claim 1, wherein determining whether the user corresponding to the arbitrary face belongs to a local user set comprises:
and determining whether the user corresponding to any face belongs to a local user set or not based on the face recognition terminal identification in the latest face recognition record.
10. The method according to claim 1, wherein after determining whether the user corresponding to the arbitrary face belongs to the local user set, further comprises:
if the user does not belong to the local user set, recording the characteristic information of the user, user identity information corresponding to the characteristic information of the user and other face recognition terminal identifications of the base map in a dynamic pre-biography table;
reading the dynamic pre-biographic table before the active period is reached;
acquiring the characteristic information of the user, and user identity information and a base map corresponding to the characteristic information of the user from other face recognition terminals based on other face recognition terminal identifiers recorded in the dynamic pre-biography table;
and placing the acquired characteristic information of the user, and user identity information and a base map corresponding to the characteristic information of the user into a local active user set.
11. The method according to claim 10, further comprising, after the obtaining the feature information of the user from the other face recognition terminal, and the user identity information and the base map corresponding to the feature information of the user:
Sending a deleting instruction to the other face recognition terminals so that the other face recognition terminals delete the characteristic information of the user, and the user identity information and the base map corresponding to the characteristic information of the user; the deleting instruction comprises identification information of the user.
12. The method according to claim 1, wherein the method further comprises:
detecting whether each active user in a local active user set performs face recognition operation in a preset time;
if any active user does not perform face recognition operation within the preset time, the active user is placed into a local common user set, and the active user is deleted from the local active user set.
13. A face recognition device, comprising:
the information extraction module is used for collecting the face image to be identified and extracting the characteristic information to be identified of the face image to be identified;
the first identification module is used for identifying the characteristic information to be identified according to the characteristic information of the active users in the local active user set;
the second recognition module is used for recognizing the feature information to be recognized according to the feature information of the common users in the local common user set if the recognition fails;
The reading module is used for reading the face recognition record of the active time period in the first idle time, wherein the active time period is a time period with frequent face recognition operation;
the first determining module is used for determining whether the success times of each face recognition in the face recognition record are larger than preset times or not;
the second determining module is used for determining whether the user corresponding to the at least one face belongs to a local user set or not if the successful recognition times of the at least one face are larger than the preset times; wherein the local user set comprises a local active user set and a local common user set;
a third determining module, configured to determine whether the user belongs to a local active user set if the user belongs to a local user set;
and the second processing module is used for placing the user into the local active user set and deleting the user in the local common user set if the user does not belong to the local active user set.
CN201911382570.0A 2019-12-28 2019-12-28 Face recognition method and device Active CN113051981B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911382570.0A CN113051981B (en) 2019-12-28 2019-12-28 Face recognition method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911382570.0A CN113051981B (en) 2019-12-28 2019-12-28 Face recognition method and device

Publications (2)

Publication Number Publication Date
CN113051981A CN113051981A (en) 2021-06-29
CN113051981B true CN113051981B (en) 2024-03-26

Family

ID=76507381

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911382570.0A Active CN113051981B (en) 2019-12-28 2019-12-28 Face recognition method and device

Country Status (1)

Country Link
CN (1) CN113051981B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112989937B (en) * 2021-02-07 2022-05-06 支付宝(杭州)信息技术有限公司 Method and device for user identity authentication

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102184391A (en) * 2011-05-19 2011-09-14 汉王科技股份有限公司 Distributed type face recognition method and system as well as face recognition terminal
CN106469296A (en) * 2016-08-30 2017-03-01 北京旷视科技有限公司 Face identification method, device and gate control system
CN108170750A (en) * 2017-12-21 2018-06-15 深圳英飞拓科技股份有限公司 A kind of face database update method, system and terminal device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI427541B (en) * 2009-03-18 2014-02-21 Ind Tech Res Inst System and method for performing rapid facial recognition

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102184391A (en) * 2011-05-19 2011-09-14 汉王科技股份有限公司 Distributed type face recognition method and system as well as face recognition terminal
CN106469296A (en) * 2016-08-30 2017-03-01 北京旷视科技有限公司 Face identification method, device and gate control system
CN108170750A (en) * 2017-12-21 2018-06-15 深圳英飞拓科技股份有限公司 A kind of face database update method, system and terminal device

Also Published As

Publication number Publication date
CN113051981A (en) 2021-06-29

Similar Documents

Publication Publication Date Title
WO2021027527A1 (en) Information processing method, apparatus and device
CN107273833B (en) Method for monitoring floating population and system thereof
CN109656973B (en) Target object association analysis method and device
US20160098636A1 (en) Data processing apparatus, data processing method, and recording medium that stores computer program
CN109858354B (en) Face identity library, track table establishment method and face track query method and system
CN112819989A (en) Park patrol method, device and equipment
CN111063144A (en) Abnormal behavior monitoring method, device, equipment and computer readable storage medium
CN111708794B (en) Data comparison method and device based on big data platform and computer equipment
CN111368619A (en) Method, device and equipment for detecting suspicious people
CN109636090B (en) Station allocation method, device, equipment and storage medium
WO2019019767A1 (en) Client identity information processing method and apparatus, storage medium and computer device
CN110543584B (en) Method, device, processing server and storage medium for establishing face index
CN111625342B (en) Data tracing method, device and server
CN113051981B (en) Face recognition method and device
CN115187435A (en) Smart campus management method, device, equipment and storage medium
CN114139016A (en) Data processing method and system for intelligent cell
CN112183161B (en) Face database processing method, device and equipment
CN113254335B (en) Test data processing method and device, server and storage medium
CN111291595A (en) Information relevance processing method, device and system
CN115391596A (en) Video archive generation method and device and storage medium
CN111385511B (en) Video data processing method and device and video recording equipment
CN113568811A (en) Distributed safety monitoring data processing method
CN112487997A (en) Portrait feature extraction method and device
CN112883879B (en) False position identification method, system, electronic equipment and medium
CN112835954B (en) Method, device and equipment for determining target service object

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