CN111178339A

CN111178339A - User identity identification method, device, equipment and medium

Info

Publication number: CN111178339A
Application number: CN202010276558.8A
Authority: CN
Inventors: 郑丹丹; 李亮; 王立彬
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-04-10
Filing date: 2020-04-10
Publication date: 2020-05-19

Abstract

One or more embodiments of the present specification provide a user identification method, apparatus, device, and medium. In one embodiment, a user identification method includes: firstly, acquiring first biological characteristic data, wherein the first biological characteristic data comprises first face characteristic data; then, identifying target face feature data matched with the first face feature data in the plurality of preset face feature data, wherein the target face feature data are preset face feature data of which the similarity with the first face feature data meets a first preset condition; and finally, under the condition that the similarity between the target face characteristic data and the first face characteristic data is greater than or equal to a preset similarity threshold value and the target biological characteristic data meets a second preset condition, determining first user identity information corresponding to the first biological characteristic data according to target user identity information associated with the target biological characteristic data, wherein the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs.

Description

User identity identification method, device, equipment and medium

Technical Field

One or more embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for user identity recognition.

Background

With the rapid development of computer technology, user identification technology is widely used. At present, a user identification device generally collects biometric data of a user, and then reports the biometric data to a user identification server, and the user identification server performs user identification based on the biometric data.

However, the reporting process of the biometric data needs to depend on the network, so that the dependence of the user identification process on the network is strong, and when the network has a bottleneck, the time consumption of the reporting process of the biometric data is increased, and further, the time consumption of the user identification is long.

Disclosure of Invention

One or more embodiments of the present disclosure provide a method, an apparatus, a device, and a medium for user identity recognition, which can reduce the dependence of a user identity recognition process on a network and improve the efficiency of user identity recognition.

The technical scheme provided by one or more embodiments of the specification is as follows:

in a first aspect, a user identity recognition method is provided, including:

acquiring first biological characteristic data; the first biological characteristic data comprises first face characteristic data;

identifying target face feature data matched with the first face feature data in a plurality of preset face feature data; the target face feature data is preset face feature data, and the similarity between the target face feature data and the first face feature data meets a first preset condition;

under the condition that the similarity between the target face characteristic data and the first face characteristic data is greater than or equal to a preset similarity threshold value and the target biological characteristic data meets a second preset condition, determining first user identity information corresponding to the first biological characteristic data according to target user identity information associated with the target biological characteristic data; the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs.

In a second aspect, there is provided a user identification apparatus, including:

the first acquisition module is used for acquiring first biological characteristic data; the first biological characteristic data comprises first face characteristic data;

the first identification module is used for identifying target face characteristic data matched with the first face characteristic data in a plurality of preset face characteristic data; the target face feature data is preset face feature data, and the similarity between the target face feature data and the first face feature data meets a first preset condition;

the first determining module is used for determining first user identity information corresponding to the first biological characteristic data according to target user identity information associated with the target biological characteristic data under the condition that the similarity between the target human face characteristic data and the first human face characteristic data is greater than or equal to a preset similarity threshold value and the target biological characteristic data meets a second preset condition; the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs.

In a third aspect, there is provided a user identification device, comprising: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements a user identification method as described in the first aspect.

In a fourth aspect, a computer-readable storage medium is provided, on which computer program instructions are stored, which when executed by a processor implement the user identification method according to the first aspect.

According to one or more embodiments of the present disclosure, after the first facial feature data is obtained, the local end directly performs matching recognition processing on the first facial feature data, and if, in a plurality of preset facial feature data, target facial feature data whose similarity to the first facial feature data satisfies a first preset condition is recognized, and it is further confirmed that the similarity between the target facial feature data and the first facial feature data is greater than or equal to a preset similarity threshold and target biometric data to which the target facial feature data belongs satisfies a second preset condition, the local end can determine first user identity information corresponding to the first biometric data directly according to target user identity information associated with the target biometric data, so that the method can reduce dependence of user identity recognition on a network, and avoid long time consumption of user identity recognition when the network has a bottleneck, the time consumption of user identity recognition can be shortened, and the efficiency of user identity recognition is improved.

Drawings

In order to more clearly illustrate the technical solutions of one or more embodiments of the present disclosure, the drawings needed to be used in one or more embodiments of the present disclosure will be briefly described below, and those skilled in the art may also obtain other drawings according to the drawings without any creative effort.

FIG. 1 is a system architecture diagram of a user identification system provided in one embodiment of the present description;

fig. 2 is a schematic flow chart of a user identification method provided in an embodiment of the present specification;

fig. 3 is a schematic flow chart of a user identification method according to another embodiment of the present disclosure;

FIG. 4 is a flow chart illustrating a user identification method according to another embodiment of the present disclosure;

FIG. 5 is a schematic flow chart of a detection process for detecting the opening of a gate according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a user identification device according to an embodiment of the present disclosure;

fig. 7 is a schematic hardware structure diagram of a user identification device according to an embodiment of the present disclosure.

Detailed Description

Features and exemplary embodiments of various aspects of the present specification will be described in detail below, and in order to make objects, technical solutions and advantages of the specification more apparent, the specification will be further described in detail below with reference to the accompanying drawings and specific embodiments. It is to be understood that the embodiments described herein are only a few embodiments of the present disclosure, and not all embodiments. It will be apparent to one skilled in the art that the present description may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present specification by illustrating examples thereof.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

However, the reporting process of the biometric data needs to depend on the network, so that the dependence of the user identification process on the network is strong, when the network has a bottleneck, the time consumption of the reporting process of the biometric data is increased, the time consumption of the user identification reaches 5-10s, and the time consumption of the user identification is long.

Taking the application of the user identity recognition technology to an access gate as an example, in a subway scene, the passenger flow volume is large, and if the waiting time for each passenger to perform user identity recognition is long, people flow congestion can be caused, so that in the subway scene, the requirement on timeliness of user identity recognition is high, and generally, the time consumption of user identity recognition needs to be within 500 ms. Therefore, based on the existing user identity identification method, the requirement of high timeliness of the subway scene on user identity identification cannot be met.

Therefore, in order to solve the problems in the prior art, embodiments of the present specification provide a user identification system.

Fig. 1 is a system architecture diagram illustrating a user identification system provided in one embodiment of the present specification. As shown in fig. 1, the user identification system includes a user identification terminal. The user identification terminal may include, but is not limited to, a mobile phone, a desktop computer, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted terminal, a point of sale (POS) device, an access gate, a wearable device, and the like.

The user identification terminal may perform user identification processing based on a plurality of preset biometric data. Specifically, after the user identification terminal acquires the first biological characteristic data, the local terminal can directly perform matching identification processing on the first facial characteristic data in the first biological characteristic data, if target face feature data with the similarity degree meeting a first preset condition with first face feature data is identified in preset face feature data in a plurality of preset biological feature data, and data judgment is carried out on the target face feature data, if the similarity between the target face feature data and the first face feature data is greater than or equal to a preset similarity threshold, meanwhile, the target biological characteristic data to which the target face characteristic data belongs meets a second preset condition, the first user identity information corresponding to the first biometric data may be determined directly from the target user identity information associated with the target biometric data.

Therefore, the user identification system can reduce the dependence of user identification on the network, avoid the long time consumption of user identification when the network has a bottleneck, shorten the time consumption of user identification and improve the efficiency of user identification.

Based on the user identity recognition system provided by the embodiments of the present specification, one or more embodiments of the present specification further provide a user identity recognition method, apparatus, device, and medium. First, a user identification method provided in this specification will be described below.

Fig. 2 is a flowchart illustrating a user identification method according to an embodiment of the present disclosure.

In some embodiments of the present description, the method shown in fig. 2 may be performed by an electronic device, which may be, for example, a user identification terminal shown in fig. 1.

As shown in fig. 2, the user identification method may include:

s110, acquiring first biological characteristic data; the first biological characteristic data comprises first face characteristic data;

s120, identifying target face feature data matched with the first face feature data in the plurality of preset face feature data; the target face feature data is preset face feature data, and the similarity between the target face feature data and the first face feature data meets a first preset condition;

s130, under the condition that the similarity between the target face characteristic data and the first face characteristic data is greater than or equal to a preset similarity threshold value and the target biological characteristic data meets a second preset condition, determining first user identity information corresponding to the first biological characteristic data according to target user identity information associated with the target biological characteristic data; the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs.

Specific implementations of the above steps will be described in detail below.

In the embodiment of the present specification, after the first facial feature data is acquired, the local end directly performs matching recognition processing on the first facial feature data, if target facial feature data with a similarity to the first facial feature data satisfying a first preset condition is recognized in a plurality of preset facial feature data, and it is further confirmed that the similarity between the target facial feature data and the first facial feature data is greater than or equal to a preset similarity threshold value and target biological feature data to which the target facial feature data belongs satisfies a second preset condition, the first user identity information corresponding to the first biological feature data can be directly determined according to target user identity information associated with the target biological feature data, so that the method can reduce dependence of user identity recognition on a network, and avoid long time consumption of user identity recognition when the network has a bottleneck, the time consumption of user identity recognition can be shortened, and the efficiency of user identity recognition is improved.

Specific implementations of the above steps are described below.

In an embodiment of the present specification, the first facial feature data may include at least one of a two-dimensional facial feature, a two-dimensional facial image, a three-dimensional facial feature, and a three-dimensional facial image.

In some embodiments of the present description, the first facial feature data may include a first facial image, and the first facial image may include at least one of a two-dimensional facial image and a three-dimensional facial image.

Optionally, in S110 of these embodiments, the electronic device may first acquire, by using the camera, a first face video containing face features of the user to be recognized, and then select, as the first face feature data, one frame of first face image with the highest image quality from the first face video.

In other embodiments of the present description, the first facial feature data may include first facial features, and the first facial features may include at least one of two-dimensional facial features and three-dimensional facial features.

Optionally, in S110 of these embodiments, the electronic device may first acquire, by using the camera, a first face video including face features of a user to be recognized, then select, as first face feature data, a first face image with a highest image quality from the first face video, and finally perform feature recognition on the first face image to obtain first face features corresponding to the first face image, as the first face feature data.

Taking the first face feature as a two-dimensional face feature as an example, the electronic device may first acquire a two-dimensional face video including a face feature of a user to be identified through the camera, then select a frame of two-dimensional face image with the highest image quality from the two-dimensional face video, and finally perform face feature point identification on the two-dimensional face image to obtain a two-dimensional face feature corresponding to the two-dimensional face image, which is used as first face feature data.

The above is a specific implementation of S110, and a specific implementation of S120 is described below.

In some embodiments of the present specification, the first preset condition may include that the similarity is a maximum similarity between the plurality of preset facial feature data and the first facial feature data.

Optionally, in these embodiments, the specific method of S120 may include: the method comprises the steps of firstly calculating the similarity between each preset human face feature data and first human face feature data, and then selecting the preset human face feature data with the maximum similarity with the first human face feature data as target human face feature data.

Thus, the target face feature data matching the first face feature data can be preliminarily determined.

In some embodiments of the present description, if the first facial feature data includes a first facial image, the preset facial feature data may include a preset feature image of the same type as the first facial image. For example, if the first face image is a two-dimensional face image, the preset feature image may be a two-dimensional face image.

At this time, the image similarity between the preset feature image and the first face image may be used as the similarity between the preset face feature data and the first face feature data.

In other embodiments of the present disclosure, if the first facial feature data includes a first facial feature, the preset facial feature data may include a preset facial feature of the same type as the first facial feature. For example, if the first face feature is a two-dimensional face feature, the preset face feature may also be a two-dimensional face feature.

At this time, the feature similarity between the preset face feature and the first face feature may be used as the similarity between the preset face feature data and the first face feature data.

It should be noted that the methods for calculating the image similarity and the feature similarity are all existing methods, and are not described herein again.

The above is a specific implementation of S120, and a specific implementation of S130 is described below.

In this embodiment of the present specification, the preset similarity threshold may be preset according to a risk threshold of a false recognition rate, and if the similarity between the target face feature data and the first face feature data is greater than or equal to the preset similarity threshold, it is determined that the false recognition rate of the target face feature data is lower than the risk threshold, and it may be further determined that the target biometric data matches the first biometric data, and the two biometric data may belong to the same user.

In some embodiments of the present description, the second preset condition may include that the target biometric data is associated with a target user, and the target user is a user who satisfies the third preset condition.

At least part of users can be selected as target users from the total number of users, so that the face feature data of the target users can be compared only at the local end, the user identity recognition can be completed quickly and simply, and the user identity recognition efficiency is improved.

In some embodiments of the present description, the third preset condition may include at least one of:

the user identification frequency of the user is greater than or equal to the preset frequency threshold, the user does not have similar biological characteristics, and the user identification information safety level of the user is higher than the preset safety level.

If the user identification frequency of the user is greater than or equal to the preset frequency threshold, it indicates that the frequency of obtaining the user identification information by the user through user identification is higher, and the user belongs to a common user for user identification.

The preset frequency threshold value can be preset according to actual needs.

Therefore, the target user can be selected from the total number of users through the user identity recognition frequency of the user, and the high-frequency user is used as the user with low error recognition rate, so that the user identity recognition efficiency of the user is improved.

If the user does not have the user with similar biological characteristics, the fact that other users do not have the similar biological characteristics with the user is indicated. Taking the facial features as an example, if there is no user with facial features similar to the user, it indicates that the user is not a twin or a similar-face user.

Therefore, users with similar biological characteristics can be excluded, and the identification efficiency of users without similar biological characteristics can be improved.

If the user identity information security level of the user is higher than the preset security level, the user identity information of the user is in an attack-free state or a security state, and the risk of identifying the user identity through the local end of the electronic equipment is low.

Wherein, the preset safety level can be preset according to the requirement.

Therefore, users with high attack risk of user identity information can be eliminated, and the user identity identification efficiency with low risk can be improved.

Therefore, the target user can be determined as the user with low identification risk, and the user identity identification process for the target user can be shortened.

In this embodiment of the present specification, at least some users may be selected as target users from among the total number of users based on a preset target user identification model or a target user selection policy.

Further, if the similarity between the target face feature data and the first face feature data is greater than or equal to the preset similarity threshold and the target biological feature data to which the target face feature data belongs meets the second preset condition, it can be determined that the target biological feature data and the first biological feature data belong to the same user and the user belongs to a user with low recognition risk.

In some embodiments of the present specification, a specific method for determining the first user identity information corresponding to the first biometric data according to the target user identity information associated with the target biometric data may be:

and taking the target user identity information associated with the target biological characteristic data as first user identity information corresponding to the first biological characteristic data.

In some embodiments of the present description, the first user identity information may include at least one of basic user information, payment account information, and social account information of the user to be identified.

The basic user information may include at least one of a user name, a user age, a user communication account, and a user address. The payment account information may include a bank card account number, a payment history, and the like. The social account information may include account numbers and account names of social applications or social websites.

In other embodiments of the present disclosure, the target user identity information may further include other information related to the user to be identified, and may be determined according to the actual processing content.

In some embodiments of the present disclosure, the preset biometric data may be biometric data stored in a registration database in the shared memory. The registration database is used for storing the biological characteristic data of the whole registered users. The plurality of electronic devices can perform data reading and writing operations on the registered database in the shared memory through the database management application program.

Specifically, the user may use the electronic device to perform registration of the user identification function in the user identification server, and the biometric data is collected by the electronic device during registration as the preset biometric data in the registration database.

In these embodiments, the user identification system shown in fig. 1 may further include a user identification server and a database server.

Taking an electronic device such as a mobile phone and a tablet personal computer which is only provided with a common camera as an example, a user can register a user identity recognition function by using an application program in the electronic device, and a two-dimensional face image is acquired by the common camera of the electronic device, so that the two-dimensional face image or two-dimensional face features corresponding to the two-dimensional face image are uploaded to a user identity recognition server as face feature data, and are stored to a database server by the user identity recognition server and are issued to a shared memory by the database server, and biological feature data stored in a registration database are obtained.

In other embodiments of the present description, the first biometric data may further include first texture feature data, and the first texture feature data may include first iris feature data and/or first palm vein feature data.

Wherein the first iris feature data may include at least one of an iris feature and an iris image, and the first palm vein feature data may include at least one of a palm vein feature and a palm vein image.

In still other embodiments of the present description, the first texture feature data may further include first fingerprint feature data. Wherein the first fingerprint feature data may comprise at least one of a fingerprint feature and a fingerprint image.

Accordingly, the preset biometric data may include preset texture feature data of the same type as the first texture feature data.

Taking electronic equipment with a specific camera, such as access gate registration equipment and the like as an example, a user can use an application program in the electronic equipment to register the user identity recognition function, a two-dimensional face image is acquired through a common camera of the electronic equipment, a three-dimensional face image is acquired through a three-dimensional camera of the electronic equipment, and an iris image, a palm vein image or a fingerprint image is acquired through other special cameras of the electronic equipment, so that biological characteristic data stored in a registration database is obtained.

In some embodiments of the present disclosure, the preset biometric data may also be biometric data stored in a target database in the shared memory, that is, a plurality of preset facial feature data are stored in the target database. The plurality of electronic devices can perform data reading and writing operations on the target database in the shared memory through the database management application program.

Optionally, in these embodiments, the specific method of S120 may include:

and identifying target face feature data from a plurality of preset face feature data in a target database.

In some embodiments, the preset biometric data may be encrypted and stored through a preset encryption algorithm, and accordingly, after the first biometric data is encrypted, the similarity calculation may be performed by using the encrypted first biometric data and the preset biometric data, so as to protect privacy of the user.

In other embodiments, the target database may be a database for storing biometric data of both newly registered users and high frequency users. Specifically, the database management application may select, at predetermined time intervals, biometric data of new registered users and high-frequency users within a preset time period or in a preset number from biometric data in a registered database in the database server, and update the biometric data in the target database in the shared memory using the selected data, thereby ensuring user experience of the new registered users and the high-frequency users under the condition that the limitation of the storage space of the local shared content is satisfied.

Specifically, the preset time period and the preset number may be set as needed. The high-frequency user refers to a user whose user identification frequency exceeds a certain frequency set according to needs.

Therefore, the user identification of the users can be ensured to be carried out at the local end, the efficiency of the user identification is improved, and the user experience of the newly registered user and the high-frequency user is improved.

Optionally, in these embodiments, in a case that the similarity between the target face feature data and the first face feature data is smaller than a preset similarity threshold, the electronic device may upload the first face feature data to the user identification server, and complete user identification based on the biometric data in the database server through the user identification server.

In still other embodiments, in a subway scenario, the target database may also be an inbound database, and specifically, when a user enters from an inbound access gate, the preset biometric data of the user and the preset user identity information associated with the preset biometric data are temporarily stored in the inbound database. When the user is out of the station at the outbound entrance guard gate, the outbound entrance guard gate can directly identify the user identity based on the preset biological characteristic data in the inbound database, so that the data processing amount can be reduced, the data processing efficiency is improved, and even if the efficiency of identifying the user identity when the user enters the station is slightly low, the efficiency of identifying the user identity when the user leaves the station can be greatly improved.

In other embodiments of the present description, after S130, the method for identifying a user may further include:

and sending a brake opening instruction to the brake.

At this moment, the electronic device is specifically an access control gate, and after the access control gate confirms the first user identity information of the user to be identified, an opening instruction can be sent to the gate based on the first user identity information, so that the function of an intelligent door lock or an intelligent gate is realized.

In still other embodiments of the present specification, after S130, before sending the gate opening instruction to the gate, the user identification method may further include:

acquiring second biological characteristic data;

comparing the second biometric data with the first biometric data;

accordingly, a specific method for sending the switching-off instruction to the gate machine may include:

and under the condition that the second biological characteristic data is the same as the first biological characteristic data, a brake opening instruction is sent to the brake.

Therefore, after the first user identity information corresponding to the first biological characteristic data is determined, the second biological characteristic data can be obtained again, the second biological characteristic data is compared with the first biological characteristic data, if the second biological characteristic data is the same as the first biological characteristic data, a person who is in front of the entrance guard gate and performs user identity identification at present is indicated, an opening instruction can be sent to the gate, and otherwise, if the second biological characteristic data is different from the first biological characteristic data, the user identity identification is performed again, so that the safety of the user identity identification is improved.

In some embodiments of the present specification, after S130, the user identification method may further include:

determining a data quality of the first biometric data;

and updating the first biological characteristic data into new target biological characteristic data under the condition that the data quality of the first biological characteristic data is greater than that of the target biological characteristic data.

In some embodiments, each type of data in the first biometric data may be compared to a data quality of corresponding data in the target biometric data, respectively, and if at least one type of data in the first biometric data is of a higher data quality than the target biometric data, the data quality of the first biometric data may be determined to be greater than the data quality of the target biometric data, and the first biometric data may be updated to new target biometric data.

In other embodiments, the data quality of the first facial feature data and the target facial feature data may also be compared. For example, the first facial feature data is a first facial image, the image quality of the first facial image in the first biometric data may be compared with the image quality of the target facial image in the target biometric data, and if the image quality of the first facial image is higher than the image quality of the target facial image, the first facial image may be regarded as a new target facial image. For another example, the first face feature data is a first face feature, the image quality of a first face image corresponding to the first face feature may be compared with the image quality of a target face image corresponding to the target face feature, if the image quality of the first face image is higher than the image quality of the target face image, the feature quality of the first face feature is higher than the feature quality of the target face feature, and the first face image may be used as a new target face image.

In still other embodiments, the data quality of the first texture feature data and the target texture feature data may also be compared, and the comparison method is similar to the comparison method of the face feature data, which is not described herein again.

In still other embodiments, each type of data in the first biometric data may be compared to a corresponding data quality in the target biometric data, respectively, and if at least one type of data in the first biometric data has a data quality higher than the target biometric data and there is no data of a data quality lower than the type of target biometric data, then it may be determined that the data quality of the first biometric data is greater than the data quality of the target biometric data, and the first biometric data is updated to be the new target biometric data.

In other embodiments of the present description, the updating of the first biometric data to the new target biometric data is prohibited in case the data quality of the first biometric data is less than or equal to the data quality of the target biometric data.

Fig. 3 is a flowchart illustrating a user identification method according to another embodiment of the present disclosure.

In some embodiments of the present description, the method shown in fig. 3 may be performed by an electronic device, which may be, for example, a user identification terminal shown in fig. 1.

As shown in fig. 3, the user identification method may include:

s210, acquiring first biological characteristic data; the first biological characteristic data comprises first face characteristic data;

s220, identifying target face feature data matched with the first face feature data in the plurality of preset face feature data; the target face feature data is preset face feature data, and the similarity between the target face feature data and the first face feature data meets a first preset condition;

s230, under the condition that the similarity between the target face characteristic data and the first face characteristic data is greater than or equal to a preset similarity threshold value and the target biological characteristic data meets a second preset condition, determining first user identity information corresponding to the first biological characteristic data according to target user identity information associated with the target biological characteristic data; the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs;

the principles of S210-S230 are similar to those of S110-S130 in the embodiment shown in fig. 2, and are not described herein again.

S240, comparing the first texture feature data with the target texture feature data under the condition that the similarity between the target face feature data and the first face feature data is greater than or equal to a preset similarity threshold value and the target biological feature data does not meet a second preset condition; wherein the target texture feature data belongs to target biological feature data;

and S250, under the condition that the first texture feature data is the same as the target texture feature data, determining first user identity information corresponding to the first biological feature data according to target user identity information associated with the target biological feature data.

The following describes specific implementations of the above-mentioned S240 and S250.

In S240 in some embodiments of the present specification, if the similarity between the target human face feature data and the first human face feature data is greater than or equal to the preset similarity threshold and the target biological feature data to which the target human face feature data belongs does not satisfy the second preset condition, it may be determined that the target biological feature data and the first biological feature data may belong to the same user and the user belongs to a user with a high recognition risk, and therefore, the user to be recognized needs to perform further user identity recognition. Specifically, first texture feature data of the first biometric data and target texture feature data of the target biometric data need to be compared.

The method for comparing the first texture feature data with the target texture feature data may be to calculate a similarity between the first texture feature data and the target texture feature data.

It should be noted that the method for calculating the similarity between the first texture feature data and the target texture feature data is similar to the method for calculating the similarity between the first face feature data and the preset face feature data in the embodiment shown in fig. 2, and details are not repeated here.

In S250 of some embodiments of the present specification, if the similarity between the first texture feature data and the target texture feature data is greater than or equal to the texture similarity threshold, it is determined that the first texture feature data is the same as the target texture feature data, that is, the target biometric data and the first biometric data belong to the same user, and the first user identity information corresponding to the first biometric data may be determined according to the target user identity information associated with the target biometric data, so that the false recognition rate of user identity identification may be reduced, and the security of the user identity information may be improved.

In this embodiment, the texture similarity threshold may also be preset according to a risk threshold of the false recognition rate.

It should be noted that the specific method for determining the first user identity information corresponding to the first biometric data according to the target user identity information associated with the target biometric data is similar to the method in the embodiment shown in fig. 2, and details are not repeated here.

In some embodiments of the present specification, after determining the first user identification information corresponding to the first biometric data in S230 or S250, the user identification method may further include:

determining a data quality of the first biometric data;

The above method has been described in detail in the embodiment shown in fig. 2, and is not described herein again.

In some embodiments of the present specification, after S240, the user identification method may further include:

acquiring an image identification code under the condition that the first texture feature data is different from the target texture feature data or the target biological feature data does not have the target texture feature data;

performing information identification processing on the image identification code to obtain second user identity information corresponding to the image identification code;

and determining first user identity information corresponding to the first biological characteristic data according to second user identity information corresponding to the image identification code.

Specifically, when the user registers, the user identification server may generate an image identification code for identifying the user identification information based on the user identification information of the user. The image identification code may be a two-dimensional code or a barcode, and the like, which is not limited herein.

If the first texture characteristic data is different from the target texture characteristic data, the first biological characteristic data and the target biological characteristic data do not belong to the same user, and the preset biological characteristic data does not have biological characteristic data matched with the first biological characteristic data, so that the user can display an image identification code which is owned by the user and comprises second user identity information, the electronic equipment can acquire the image identification code through a camera, and then perform information identification processing on the image identification code to obtain the second user identity information corresponding to the image identification code, and accordingly the first user identity information corresponding to the first biological characteristic data is determined according to the second user identity information corresponding to the image identification code.

If the target biological characteristic data does not have the target texture characteristic data, the texture characteristic data is not collected when the user is registered, so that the user can display the owned image identification code comprising the second user identity information, the electronic equipment can collect the image identification code through the camera, then the image identification code is subjected to information identification processing, the second user identity information corresponding to the image identification code is obtained, and therefore the first user identity information corresponding to the first biological characteristic data is determined according to the second user identity information corresponding to the image identification code.

Therefore, the safety of user identification can be further improved based on the texture feature data.

It should be noted that the method for generating the image identification code based on the user identity information of the user by using the existing method, and identifying the second user identity information by using the image identification code, and determining the first user identity information corresponding to the first biometric data according to the second user identity information corresponding to the image identification code is similar to the embodiment shown in fig. 2, and is not repeated here.

In some embodiments of the present specification, after determining the first user identification information corresponding to the first biometric data according to the second user identification information corresponding to the image identification code, the user identification method may further include:

storing the first biometric data in association with the first user identity information.

Therefore, the first biological characteristic data can be stored as the preset biological characteristic data of the first user identity information for the next user identity identification of the user.

In some embodiments of the present specification, after determining the first user identification information corresponding to the first biometric data, the user identification method may further include:

and sending a brake opening instruction to the brake.

In other embodiments of the present description, after determining the first user identity information corresponding to the first biometric data, before sending the gate opening instruction to the gate machine, the user identity identification method may further include:

acquiring second biological characteristic data;

comparing the second biometric data with the first biometric data;

It should be noted that the above-mentioned method has been described in detail in the embodiment shown in fig. 2, and is not described herein again.

Fig. 4 is a flowchart illustrating a user identification method according to another embodiment of the present disclosure.

In some embodiments of the present description, the method shown in fig. 4 may be performed by an electronic device, which may be, for example, a user identification terminal shown in fig. 1.

As shown in fig. 4, the user identification method may include:

s310, acquiring first biological characteristic data; the first biological characteristic data comprises first face characteristic data;

s320, identifying target face feature data matched with the first face feature data in the plurality of preset face feature data; the target face feature data is preset face feature data, and the similarity between the target face feature data and the first face feature data meets a first preset condition;

s330, under the condition that the similarity between the target face characteristic data and the first face characteristic data is greater than or equal to a preset similarity threshold value and the target biological characteristic data meets a second preset condition, determining first user identity information corresponding to the first biological characteristic data according to target user identity information associated with the target biological characteristic data; the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs;

the principles of S310-S330 are similar to those of S110-S130 in the embodiment shown in fig. 2, and are not described herein again.

S340, under the condition that the similarity between the target face characteristic data and the first face characteristic data is smaller than a preset similarity threshold, acquiring an image identification code;

s350, performing information identification processing on the image identification code to obtain second user identity information corresponding to the image identification code;

s360, determining first user identity information corresponding to the first biological characteristic data according to second user identity information corresponding to the image identification code.

S350-S360 are similar to the method in the embodiment shown in fig. 3, and are not described herein again.

In S340 in some embodiments of the present description, the preset similarity threshold may be preset according to a risk threshold of a false recognition rate, and if the similarity between the target face feature data and the first face feature data is smaller than the preset similarity threshold, it is described that the false recognition rate of the target face feature data is higher than the risk threshold, it may be further determined that the target biometric data is not matched with the first biometric data, the two biometric data do not belong to the same user, and the biometric data matched with the first face feature data may not exist in the electronic device, which requires the user to re-acquire the biometric data.

For example, when the user registers, only the user identity information is filled in, and no biometric data is collected, a situation may occur in which the similarity between the target face feature data and the first face feature data is smaller than a preset similarity threshold.

In some embodiments of the present specification, after S360, the user identification method may further include:

and sending a brake opening instruction to the brake.

acquiring second biological characteristic data;

comparing the second biometric data with the first biometric data;

Fig. 5 is a schematic flow chart illustrating a process of detecting the opening of the gate according to an embodiment of the present disclosure. As shown in fig. 5, the process of detecting the opening of the gate may specifically include:

s401, collecting first biological characteristic data;

s402, identifying target face feature data matched with the first face feature data in a plurality of preset face feature data;

s403, judging whether the similarity between the target face characteristic data and the first face characteristic data is greater than or equal to a preset similarity threshold, if so, executing S404, and if not, executing S408;

s404, judging whether target biological characteristic data to which the target face characteristic data belongs to a target user, namely whether the target face characteristic data belongs to the target user, if so, executing S405, and if not, executing S410;

s405, determining the data quality of at least one of three-dimensional face features, iris features and palm vein features in the first biological feature data, and updating target biological feature data by using the data;

s406, collecting second biological characteristic data;

s407, comparing the second biological characteristic data with the first biological characteristic data, judging whether the user is still in the biological characteristic acquisition area, and if the second biological characteristic data is the same as the first biological characteristic data, sending a brake opening instruction to the brake;

s408, collecting an image identification code, performing information identification processing on the image identification code to obtain second user identity information corresponding to the image identification code, determining first user identity information corresponding to the first biological characteristic data according to the second user identity information corresponding to the image identification code, and then sending a brake opening instruction to a brake machine to realize code scanning brake opening;

s409, storing the first biological characteristic data and the first user identity information in an associated manner;

s410, comparing the first texture feature data with the target texture feature data, judging whether the texture feature data are the same, if so, executing S405, and if not, executing S411;

s411, collecting an image identification code, performing information identification processing on the image identification code to obtain second user identity information corresponding to the image identification code, determining first user identity information corresponding to the first biological characteristic data according to the second user identity information corresponding to the image identification code, then sending a brake opening instruction to a brake machine to realize code scanning brake opening, and then executing S405.

In summary, the embodiment of the present specification can enable a user to obtain real-time experience of user identification at a local end, and can realize user identification through flexible switching of biometric identification and image identification code, thereby ensuring real-time non-coordinated experience of the user.

Fig. 6 is a schematic structural diagram illustrating a user identification apparatus according to an embodiment of the present disclosure.

In some embodiments of the present description, the apparatus shown in fig. 6 may be disposed in an electronic device, and the electronic device may be, for example, a user identification terminal shown in fig. 1.

As shown in fig. 6, the user identification apparatus 500 may include:

a first obtaining module 510, configured to obtain first biometric data; the first biological characteristic data comprises first face characteristic data;

a first identification module 520, configured to identify target face feature data that matches the first face feature data from among a plurality of preset face feature data; the target face feature data is preset face feature data, and the similarity between the target face feature data and the first face feature data meets a first preset condition;

a first determining module 530, configured to determine, according to target user identity information associated with target biometric data, first user identity information corresponding to first biometric data when a similarity between the target facial feature data and the first facial feature data is greater than or equal to a preset similarity threshold and the target biometric data meets a second preset condition; the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs.

In some embodiments of the present specification, the first preset condition includes that the similarity is a maximum similarity between the plurality of preset facial feature data and the first facial feature data.

In some embodiments of the present description, the second preset condition includes that the target biometric data is associated with a target user, and the target user is a user who satisfies the third preset condition.

In some embodiments of the present description, the third preset condition comprises at least one of:

In some embodiments of the present description, the first biometric data further comprises first texture feature data, the first texture feature data comprising first iris feature data and/or first palm vein feature data.

In some embodiments of the present disclosure, the user identification apparatus 500 further includes:

the first comparison module is used for comparing the first texture feature data with the target texture feature data under the condition that the similarity between the target face feature data and the first face feature data is greater than or equal to a preset similarity threshold value and the target biological feature data does not meet a second preset condition; wherein the target texture feature data belongs to target biological feature data;

and the second determining module is used for determining the first user identity information corresponding to the first biological characteristic data according to the target user identity information associated with the target biological characteristic data under the condition that the first texture characteristic data is the same as the target texture characteristic data.

the third determining module is used for determining the data quality of the first biological characteristic data;

and the data updating module is used for updating the first biological characteristic data into new target biological characteristic data under the condition that the data quality of the first biological characteristic data is greater than that of the target biological characteristic data.

the first acquisition module is used for acquiring the image identification code under the condition that the first texture feature data is different from the target texture feature data;

the second identification module is used for carrying out information identification processing on the image identification code to obtain second user identity information corresponding to the image identification code;

and the fourth determining module is used for determining the first user identity information corresponding to the first biological characteristic data according to the second user identity information corresponding to the image identification code.

the second acquisition module is used for acquiring the image identification code under the condition that the similarity between the target face characteristic data and the first face characteristic data is smaller than a preset similarity threshold;

the second acquisition module is used for carrying out information identification processing on the image identification code to obtain second user identity information corresponding to the image identification code;

and the fifth determining module is used for determining the first user identity information corresponding to the first biological characteristic data according to the second user identity information corresponding to the image identification code.

and the data storage module is used for storing the first biological characteristic data and the first user identity information in a correlation mode.

and the instruction sending module is used for sending a brake opening instruction to the brake machine.

the second acquisition module is used for acquiring second biological characteristic data;

the second comparison module is used for comparing the second biological characteristic data with the first biological characteristic data;

the instruction sending module is specifically configured to:

In some embodiments of the present description, a plurality of predetermined facial feature data is stored in a target database;

the first identifying module 520 is specifically configured to:

It should be noted that the user identification apparatus provided in this embodiment can implement the processes and effects in the method embodiments shown in fig. 2 to 5, and details are not described herein to avoid repetition.

Fig. 7 is a schematic diagram illustrating a hardware structure of a user identification device according to an embodiment of the present disclosure. As shown in fig. 7, the user identification apparatus 600 includes an input apparatus 601, an input interface 602, a central processor 603, a memory 604, an output interface 605, and an output apparatus 606. The input interface 602, the central processing unit 603, the memory 604, and the output interface 605 are connected to each other via a bus 610, and the input device 601 and the output device 606 are connected to the bus 610 via the input interface 602 and the output interface 605, respectively, and further connected to other components of the user identification device 600.

Specifically, the input device 601 receives input information from the outside, and transmits the input information to the central processor 603 through the input interface 602; the central processor 603 processes input information based on computer-executable instructions stored in the memory 604 to generate output information, stores the output information temporarily or permanently in the memory 604, and then transmits the output information to the output device 606 through the output interface 605; the output device 606 outputs the output information to the outside of the user identification apparatus 600 for use by the user.

That is, the user identification apparatus shown in fig. 7 may also be implemented to include: a memory storing computer-executable instructions; and a processor, which when executing computer-executable instructions may implement the user identification method and apparatus described in the embodiments of this specification.

Embodiments of the present specification also provide a computer-readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement the user identification method provided by the embodiments of the present specification.

The functional blocks shown in the above structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of this specification are programs or code segments that are used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

It should also be noted that the above describes certain embodiments of the specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in the order of execution in different embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

As described above, only the specific implementation manner of the present specification is provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present disclosure is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present disclosure, and these modifications or substitutions should be covered within the scope of the present disclosure.

Claims

1. A user identity recognition method comprises the following steps:

acquiring first biological characteristic data; wherein the first biometric data comprises first facial feature data;

under the condition that the similarity between the target face feature data and the first face feature data is greater than or equal to a preset similarity threshold and target biological feature data meet a second preset condition, determining first user identity information corresponding to the first biological feature data according to target user identity information associated with the target biological feature data; and the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs.

2. The method according to claim 1, wherein the first preset condition includes that the similarity is a maximum similarity between a plurality of preset face feature data and the first face feature data.

3. The method of claim 1, wherein the second preset condition comprises that the target biometric data is associated with a target user, the target user being a user satisfying a third preset condition.

4. The method according to claim 3, wherein the third preset condition comprises at least one of:

the user identification frequency of the user is greater than or equal to a preset frequency threshold, the user does not have a user with similar biological characteristics, and the user identity information security level of the user is higher than a preset security level.

5. The method of claim 1, wherein the first biometric data further comprises first texture feature data, the first texture feature data comprising first iris feature data and/or first palm vein feature data.

6. The method of claim 5, wherein after identifying the target facial feature data matching the first facial feature data among the plurality of preset facial feature data, the method further comprises:

comparing the first texture feature data with target texture feature data under the condition that the similarity between the target face feature data and the first face feature data is greater than or equal to the preset similarity threshold and the target biological feature data does not meet the second preset condition; wherein the target texture feature data belongs to the target biometric data;

and under the condition that the first texture feature data is the same as the target texture feature data, determining first user identity information corresponding to the first biological feature data according to target user identity information associated with the target biological feature data.

7. The method of claim 5 or 6, wherein after determining the first user identity information corresponding to the first biometric data, the method further comprises:

determining a data quality of the first biometric data;

and updating the first biological characteristic data into new target biological characteristic data when the data quality of the first biological characteristic data is greater than that of the target biological characteristic data.

8. The method of claim 6, wherein after the comparing the first texture feature data and the target texture feature data, the method further comprises:

acquiring an image identification code under the condition that the first texture feature data is different from the target texture feature data;

9. The method of claim 1, wherein after identifying target facial feature data matching the first facial feature data among the plurality of preset facial feature data, the method further comprises:

acquiring an image identification code under the condition that the similarity between the target face feature data and the first face feature data is smaller than the preset similarity threshold;

10. The method of claim 8 or 9, wherein after determining the first user identity information corresponding to the first biometric data, the method further comprises:

11. The method of claim 1, 6, 8 or 9, wherein after determining the first user identity information corresponding to the first biometric data, the method further comprises:

and sending a brake opening instruction to the brake.

12. The method of claim 11, wherein prior to sending an open command to a gate, the method further comprises:

acquiring second biological characteristic data;

comparing the second biometric data with the first biometric data;

wherein, send the switching-off instruction to the floodgate machine, include:

and sending the brake opening instruction to the brake machine under the condition that the second biological characteristic data is the same as the first biological characteristic data.

13. The method of claim 1, wherein a plurality of said predetermined facial feature data are stored in a target database;

wherein, among a plurality of preset human face feature data, identifying target human face feature data matched with the first human face feature data comprises:

and identifying the target face feature data from a plurality of preset face feature data in the target database.

14. A user identification apparatus comprising:

the first acquisition module is used for acquiring first biological characteristic data; wherein the first biometric data comprises first facial feature data;

the first identification module is used for identifying target face feature data matched with the first face feature data in a plurality of preset face feature data; the target face feature data is preset face feature data, and the similarity between the target face feature data and the first face feature data meets a first preset condition;

the first determining module is used for determining first user identity information corresponding to the first biological characteristic data according to target user identity information associated with the target biological characteristic data under the condition that the similarity between the target human face characteristic data and the first human face characteristic data is greater than or equal to a preset similarity threshold and the target biological characteristic data meets a second preset condition; and the target biological characteristic data is preset biological characteristic data to which the target face characteristic data belongs.

15. The apparatus according to claim 14, wherein the first preset condition includes that the similarity is a maximum similarity between a plurality of preset face feature data and the first face feature data.

16. The apparatus of claim 14, wherein the second preset condition comprises the target biometric data being associated with a target user, the target user being a user meeting a third preset condition.

17. The apparatus of claim 16, wherein the third preset condition comprises at least one of:

18. The apparatus of claim 14, wherein the first biometric data further comprises first texture feature data, the first texture feature data comprising first iris feature data and/or first palm vein feature data.

19. The apparatus of claim 18, wherein the user identification means further comprises:

the first comparison module is used for comparing the first texture feature data with the target texture feature data under the condition that the similarity between the target human face feature data and the first human face feature data is greater than or equal to the preset similarity threshold and the target biological feature data does not meet the second preset condition; wherein the target texture feature data belongs to the target biometric data;

and a second determining module, configured to determine, according to target user identity information associated with the target biometric data, first user identity information corresponding to the first biometric data when the first texture feature data is the same as the target texture feature data.

20. The apparatus of claim 18 or 19, wherein the user identification means further comprises:

a third determining module, configured to determine data quality of the first biometric data;

21. The apparatus of claim 19, wherein the user identification means further comprises:

the first acquisition module is used for acquiring an image identification code under the condition that the first texture feature data is different from the target texture feature data;

22. The apparatus of claim 14, wherein the user identification means further comprises:

the second acquisition module is used for acquiring an image identification code under the condition that the similarity between the target face characteristic data and the first face characteristic data is smaller than the preset similarity threshold;

23. The apparatus of claim 21 or 22, wherein the user identification means further comprises:

and the data storage module is used for storing the first biological characteristic data and the first user identity information in a correlation manner.

24. The apparatus of claim 14, 19, 21 or 22, wherein the user identification means further comprises:

25. The apparatus of claim 24, wherein the user identification means further comprises:

a second comparison module for comparing the second biometric data with the first biometric data;

the instruction sending module is specifically configured to:

26. The apparatus of claim 14, wherein a plurality of said predetermined facial feature data are stored in a target database;

wherein the first identification module is specifically configured to:

27. A user identification device, wherein the device comprises: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements the user identification method of any of claims 1-13.

28. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the user identification method of any one of claims 1-13.