Identity recognition method, device and equipment

Abstract

The embodiments of this specification provide an identity recognition method, device, and equipment. The method includes: generating target timing data containing point cloud data based on the transmitted signal and received signal of a signal transmitting device within an identity recognition cycle, where the point cloud data is determined by the transmitted signal and received signal; determining, from the point cloud data included in the target timing data, the target point cloud data corresponding to a target user to be recognized based on the target timing data, and generating spatial feature data corresponding to the target user according to the target point cloud data; performing identity recognition on the target user based on the spatial feature data to obtain an identity recognition result.

Description

Technical Field

[0001] This document relates to the field of identity recognition technology, and in particular, to an identity recognition method, device, and equipment. Background Art

[0002] With the rapid development of computer technology, the digitalization of personal identity information has become more and more common, and the methods of identifying users through fingerprints, irises, face images, etc. have become more and more common. For example, an identity recognition device can obtain a user's face image through a camera, perform image matching based on the pre-stored face image and the obtained image, and determine the user identity corresponding to the successfully matched face image as the user identity of this user.

[0003] However, since data such as face images, fingerprints, and irises contain a large amount of user privacy data, there may be a risk of privacy leakage during the data acquisition process. Therefore, the security of the method of authenticating users through face images, fingerprints, etc. is low. Therefore, a solution to improve the privacy protection security of identity recognition is needed. Summary of the Invention

[0004] The purpose of the embodiments of this specification is to provide an identity recognition method, device, and equipment to provide a solution that can improve the privacy protection security of identity recognition.

[0005] To achieve the above technical solution, the embodiments of this specification are implemented as follows:

[0006] In a first aspect, the embodiments of this specification provide an identity recognition method, including: generating target time-series data including point cloud data based on the transmitted signal and received signal of a signal transmission device within an identity recognition period, where the point cloud data is determined by the transmitted signal and received signal; based on the target time-series data, determining target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target time-series data, and generating spatial feature data corresponding to the target user according to the target point cloud data; and performing identity recognition on the target user based on the spatial feature data to obtain an identity recognition result.

[0007] Second aspect, an embodiment of this specification provides an identity recognition device, and the device includes: a data generation module, configured to generate target timing data including point cloud data based on a transmitted signal and a received signal of a signal transmission device within an identity recognition period, where the point cloud data is determined by the transmitted signal and the received signal; a data selection module, configured to determine, based on the target timing data, target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target timing data, and generate spatial feature data corresponding to the target user according to the target point cloud data; an identity recognition module, configured to perform identity recognition on the target user based on the spatial feature data to obtain an identity recognition result.

[0008] Third aspect, an embodiment of this specification provides an identity recognition device, where the identity recognition device is a device in a blockchain system, and the identity recognition device includes: a processor; and a memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to: generate target timing data including point cloud data based on a transmitted signal and a received signal of a signal transmission device within an identity recognition period, where the point cloud data is determined by the transmitted signal and the received signal; determine, based on the target timing data, target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target timing data, and generate spatial feature data corresponding to the target user according to the target point cloud data; perform identity recognition on the target user based on the spatial feature data to obtain an identity recognition result.

[0009] Fourth aspect, an embodiment of this specification provides a storage medium, where the storage medium is used to store computer-executable instructions, and the executable instructions, when executed, implement the following process: generate target timing data including point cloud data based on a transmitted signal and a received signal of a signal transmission device within an identity recognition period, where the point cloud data is determined by the transmitted signal and the received signal; determine, based on the target timing data, target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target timing data, and generate spatial feature data corresponding to the target user according to the target point cloud data; perform identity recognition on the target user based on the spatial feature data to obtain an identity recognition result. Description of the Drawings

[0010] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0011] Figure 1A It is a flowchart of an embodiment of an identity recognition method in this specification;

[0012] Figure 1B It is a schematic diagram of the processing process of an embodiment of an identity recognition method in this specification;

[0013] Figure 2 It is a schematic diagram of a signal sending device in this specification;

[0014] Figure 3 It is a flowchart of an embodiment of an identity recognition method in this specification;

[0015] Figure 4 It is a schematic diagram of a target point cloud data in this specification;

[0016] Figure 5 It is a schematic diagram of a model training in this specification;

[0017] Figure 6 It is a schematic structural diagram of another embodiment of an identity recognition device in this specification;

[0018] Figure 7 It is a schematic structural diagram of an identity recognition device in this specification. Specific embodiments

[0019] The embodiments of this specification provide an identity recognition method, device and equipment.

[0020] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0021] Embodiment 1

[0022] As Figure 1A and Figure 1B shown, the embodiments of this specification provide an identity recognition method. The execution subject of this method can be a server, and the server can be an independent server or a server cluster composed of multiple servers.

[0023] Specifically, this method can include the following steps:

[0024] In S102, based on the transmitted signal and received signal of the signal sending device within the identity recognition cycle, generate target timing data including point cloud data.

[0025] Among them, the signal sending device can be any device capable of sending a transmitted signal and receiving a received signal reflected back by an object after the transmitted signal. For example, the signal sending device can be a 3D camera, a time-of-flight camera, or a radar that uses radio frequency signals in a preset frequency band and frequency modulation continuous wave technology (i.e., it can transmit a continuous wave with a changing frequency within a sweep period). Specifically, for example, the signal sending device can be a millimeter wave radar that uses the 77 - 81 GHz frequency band. The millimeter wave radar can transmit a continuous radio frequency signal with a changing frequency within a sweep period. That is, the transmitted signal and the received signal of the signal sending device can be millimeter wave signals. The identity recognition period can be a period of any duration. For example, the identity recognition period can be 1 minute, 3 minutes, etc. The point cloud data can be information of a large number of points measured by the signal sending device in an automated manner in areas such as the surface of an object. In addition to geometric position information, the point cloud data can also include RGB color information, grayscale information, depth information, etc. of a point. The point cloud data can be determined by the transmitted signal and the received signal. For example, the distance information, speed information, and angle information between the object and the signal sending device can be determined through the frequency difference between the transmitted signal and the received signal, and the point cloud data is determined based on the above information obtained.

[0026] In practice, with the rapid development of computer technology, the digitization of personal identity information is becoming more and more common. The methods of identifying users through fingerprints, irises, face images, etc. are becoming more and more common. For example, the identity recognition device can obtain the face image of the user through a camera, perform image matching based on the pre-stored face image and the obtained image, and determine the user identity corresponding to the successfully matched face image as the user identity of this user. However, since data such as face images, fingerprints, and irises contain a large amount of user privacy data, there may be a risk of privacy leakage during the data acquisition process. Therefore, the security of the method of authenticating users through face images, fingerprints, etc. is low. Therefore, a solution to improve the privacy protection security of identity recognition is needed. For this reason, the embodiments of this specification provide a technical solution that can solve the above problems. For specific details, please refer to the following content.

[0027] As Figure 2 shown, taking the signal sending device as a millimeter wave radar as an example, the millimeter wave radar can send a transmitted signal within a preset sweep period and receive the received signal reflected by the object. The millimeter wave radar can send the transmitted signal and the received signal to the server within the identity recognition period. Since the millimeter wave radar has high spatial resolution, strong anti-interference ability, and precise recognition ability, the accuracy of subsequent data processing can be improved through the transmitted signal and the received signal of the millimeter wave radar.

[0028] Alternatively, the signal sending device may be a device configured within the terminal device. The terminal device may be a device that needs to identify the user's identity, such as a resource transfer device or an access control device. The terminal device may obtain the transmitted signal and the received signal of the signal sending device, and send the transmitted signal and the received signal obtained during the identity recognition period to the server.

[0029] After receiving the transmitted signal and the received signal, the server may generate point cloud data based on the transmitted signal and the received signal. For example, it may determine the distance information, speed information, and angle information between the object and the signal sending device according to the frequency difference between the transmitted signal and the received signal, and then determine the point cloud data based on the above obtained information. Then, according to the point cloud data and the corresponding time, the target time series data is constructed.

[0030] In addition, to improve the identity recognition efficiency and save the processing resources of the server, the terminal device may determine whether the received signal of the signal sending device fluctuates. If the received signal fluctuates, it can be considered that there is a user to be identified within the signal sending area of the signal sending device. At this time, the terminal device may send the transmitted signal and the received signal during the identity recognition period to the server, so that the server performs user identity recognition processing based on the transmitted signal and the fluctuating received signal.

[0031] Alternatively, the terminal device may also trigger the signal sending device to send a transmitted signal and receive the corresponding received signal when receiving an identity recognition instruction. The terminal device may send the obtained transmitted signal and received signal to the server for processing. For example, the terminal device may be a resource transfer device. When the terminal device detects that the user triggers an identity verification instruction for the resource transfer service, it may trigger the signal sending device to send a transmitted signal based on a preset frequency sweep period and obtain the corresponding received signal. The terminal device may send the obtained transmitted signal and received signal to the server for processing.

[0032] In S104, based on the target time series data, determine the target point cloud data corresponding to the target user to be identified from the point cloud data included in the target time series data, and generate spatial feature data corresponding to the target user according to the target point cloud data.

[0033] Among them, the target user may be any user to be identified, and the spatial feature data may be feature data that can characterize the target user in multiple dimensions.

[0034] In implementation, the server can determine whether there is a target user to be recognized according to the target timing data. For example, it can judge whether there is a target user to be recognized based on whether there is dynamically changing point cloud data in the target timing data. Specifically, for example, it can compare the point cloud data corresponding to every two adjacent moments to determine whether there is dynamically changing point cloud data (i.e., dynamic point cloud data). If there is dynamic point cloud data, it can be determined that there is a target user to be recognized. Or, it can also determine whether there is a target user to be recognized according to the quantity of the dynamic point cloud data, or the shape of the point cloud data cluster formed by the dynamic point cloud data, etc.

[0035] The above method for determining whether there is a target user to be recognized is an optional and implementable determination method. In actual application scenarios, there can also be various different determination methods, which can vary according to different actual application scenarios. The embodiments of this specification do not make specific limitations in this regard.

[0036] In addition, it can also determine the quantity of the target users to be recognized according to the dynamic point cloud data. For example, it can determine the quantity of the target users to be recognized according to the quantity of the point cloud data clusters formed by the dynamic point cloud data, or the change information of the dynamic point cloud data (such as the change quantity, change amplitude, etc.) of the dynamic point cloud data.

[0037] In the case of determining that there is a target user to be recognized, the above dynamic point cloud data can be determined as the target point cloud data corresponding to the target user. Or, it can also determine the center point cloud data of the point cloud data cluster formed by the dynamic point cloud data as the target point cloud data. In addition, there can be various methods for determining the target point cloud data, which can vary according to different actual application scenarios. The embodiments of this specification do not make specific limitations in this regard.

[0038] Based on the determined target point cloud data, spatial feature data corresponding to the target user can be generated. For example, the target point cloud data can be determined as the spatial feature data corresponding to the target user. Among them, the target point cloud data can include distance information, speed information, and angle information in the horizontal direction, as well as distance information, speed information, and angle information in the vertical direction, etc. Therefore, the generated spatial feature data can contain feature data in multiple dimensions such as the horizontal direction and the vertical direction.

[0039] The above method for determining the spatial feature data corresponding to the target user is an optional and implementable determination method. In actual application scenarios, there can also be various different determination methods, which can vary according to different actual application scenarios. The embodiments of this specification do not make specific limitations in this regard.

[0040] In S106, based on the spatial feature data, perform identity recognition on the target user to obtain an identity recognition result.

[0041] In implementation, it is possible to obtain the spatial feature data that matches the spatial feature data corresponding to the target user from the pre-stored spatial feature data, and obtain the user identity corresponding to the matching spatial feature data, and determine this user identity as the identity recognition result for identifying the target user.

[0042] In addition, when the number of target users to be identified is multiple, the identity of each target user can be identified separately to obtain the identity recognition result.

[0043] Such as Figure 1B As shown, after the server determines the identity recognition result of the target user, it can return the identity recognition result to the sending device (such as a terminal device including a signal receiving device, etc.). Among them, if there are multiple target users, the server can also determine the location information of each target user according to the target timing data, and then return the identity recognition result and location information of the target user to the terminal device.

[0044] The above method for determining the identity recognition result of the target user is an optional and implementable determination method. In actual application scenarios, there can also be multiple different determination methods, which can vary according to different actual application scenarios. The embodiments of this specification do not make specific limitations on this.

[0045] Since the signal sending device can send out transmission signals based on a preset sweep period, the server can obtain the transmission signals and reception signals of the signal sending device based on the identity recognition period, and identify the target user according to the transmission signals and reception information, that is, it is possible to achieve the identity recognition of the target user without the user's awareness. And when the signal sending device is a millimeter-wave radar, since the millimeter-wave radar can obtain accurate signals (such as accurate signals like heartbeats), therefore, according to the transmission signals and reception signals of the millimeter-wave radar, the spatial feature data of the target user can be accurately determined to improve the accuracy of user identity recognition.

[0046] An embodiment of this specification provides an identity recognition method. Based on the transmitted signal and received signal of a signal transmitting device within an identity recognition period, target timing data including point cloud data is generated. The point cloud data is determined by the transmitted signal and received signal. Based on the target timing data, target point cloud data corresponding to a target user to be recognized is determined from the point cloud data included in the target timing data, and based on the target point cloud data, spatial feature data corresponding to the target user is generated. Based on the spatial feature data, identity recognition of the target user is performed to obtain an identity recognition result. In this way, since only the transmitted signal and received signal of the signal transmitting device are required to generate the target timing data, and data processing is performed based on the target timing data to perform identity recognition of the target user, without the need to obtain the privacy data of the target user (such as face images, fingerprints, etc.), it has a good privacy data protection effect and improves the security of privacy protection for identity recognition.

[0047] Embodiment 2

[0048] As Figure 3 shown, an embodiment of this specification provides an identity recognition method. The execution subject of this method can be a server, and this server can be an independent server or a server cluster composed of multiple servers. This method can specifically include the following steps:

[0049] In S302, based on the transmitted signal and received signal of the signal transmitting device within the identity recognition period, first distance information and first angle information between the signal transmitting device and the object to be recognized are determined.

[0050] In implementation, in practical applications, the processing method of the above S302 can be various. The following provides an optional implementation method, which can specifically refer to the processing of the following steps 1 to 3:

[0051] Step 1, perform difference frequency processing on the transmitted signal and received signal of the signal transmitting device within the identity recognition period to obtain a first signal.

[0052] Step 2, determine the first distance information based on the frequency and bandwidth of the first signal.

[0053] In implementation, the first signal can be processed to obtain the frequency of the first signal. For example, the frequency of the first signal can be obtained by performing fast Fourier transform processing on the first signal. Then, substituting the frequency of the first signal and the bandwidth of the first signal into the formula

[0054]

[0055] to obtain the first distance information, where d is the first distance information, c is the speed of light, f b is the frequency of the first signal, and S is the bandwidth of the first signal.

[0056] Step 3: Determine first angle information based on the wavelength of the received signal, the phase difference between two adjacent receiving antennas, and the distance between the two adjacent receiving antennas in the signal transmitting device within the identity recognition cycle.

[0057] In implementation, the signal transmitting device may have multiple transmitting antennas and multiple receiving antennas, and the wavelength of the received signal of each receiving antenna, the phase difference between two adjacent receiving antennas, and the distance therebetween can be obtained.

[0058] Substitute the phase difference and distance between the first receiving antenna and the second receiving antenna, and the wavelength of the received signal into the formula.

[0059]

[0060] The first angle information is obtained, where θ is the first angle information, λ is the signal wavelength of the received signal, ΔΦ is the phase difference between the first receiving antenna and the second receiving antenna, l is the distance between the first receiving antenna and the second receiving antenna, and the first receiving antenna and the second receiving antenna are any two adjacent receiving antennas in the signal transmitting device.

[0061] In S304, generate point cloud data based on the first distance information, the first angle information, and the corresponding time.

[0062] In S306, generate target timing data based on the point cloud data and the corresponding time.

[0063] For the specific processing procedures of the above S304 to S306, reference can be made to the relevant content of S102 in the first embodiment above, which will not be elaborated here.

[0064] In S308, determine the location information of the target user based on the target timing data.

[0065] In implementation, the location information of the target user can be determined according to the point cloud data cluster formed by the dynamic point cloud data (i.e., the point cloud data that undergoes dynamic changes) in the target timing data. For example, the location information of the point cloud data cluster can be determined as the location information of the target user, or alternatively, the location information of the central point cloud data of the point cloud data cluster can be determined as the location information of the target user. In addition, there can be multiple methods for determining the location information of the target user, which can vary according to different actual application scenarios, and this embodiment of the specification does not make specific limitations thereon.

[0066] In S310, determine the target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target timing data based on the location information.

[0067] In implementation, in practical applications, the processing method of the above S310 can be various. The following provides an optional implementation method, which can be specifically referred to the processing of Step 1 to Step 2 below:

[0068] Step 1: Obtain the second point cloud data corresponding to the position information in the target time-series data.

[0069] In implementation, since the target time-series data contains multiple frames of data composed of point cloud data at different times, and each frame of data corresponds to a moment. After determining the position information of the target user, the second point cloud data corresponding to the position information of the target user in each frame of data can be obtained.

[0070] Step 2: Determine the second point cloud data as the target point cloud data corresponding to the target user.

[0071] In S312, obtain the third point cloud data with the same horizontal position information as the target point cloud data in the target time-series data, and the fourth point cloud data with the same vertical position information as the target point cloud data.

[0072] In S314, based on the target point cloud data and the third point cloud data, determine the horizontal feature data corresponding to the target user.

[0073] In implementation, as Figure 4 shown, taking the point cloud data corresponding to any moment within the identity acquisition period as an example, according to the position information of the target point cloud data, the third point cloud data in the same horizontal direction as the target point cloud data can be obtained. Based on the target point cloud data and the third point cloud data, the horizontal feature data corresponding to the target user can be constructed. Among them, the target point cloud data is determined by the first angle information and the first distance information. Therefore, the first angle information and the first distance information of the target point cloud data and the third point cloud data can be extracted to obtain the horizontal feature data corresponding to the target user. Specifically, in the distance-angle spectrogram constructed by the first angle information and the first distance information, the feature representation corresponding to the position information of the target point cloud data and the third point cloud data can be extracted as the horizontal feature data corresponding to the target user.

[0074] In S316, based on the target point cloud data and the fourth point cloud data, determine the vertical feature data corresponding to the target user.

[0075] In implementation, as Figure 4As shown in the figure, taking the point cloud data corresponding to any moment within the identity acquisition period as an example, according to the position information of the target point cloud data, the fourth point cloud data in the same vertical direction as the target point cloud data can be obtained. Based on the target point cloud data and the fourth point cloud data, vertical feature data corresponding to the target user can be constructed, where the first angle information and the first distance information of the target point cloud data and the fourth point cloud data can be extracted for feature extraction to obtain the vertical feature data corresponding to the target user. Specifically, for example, in the distance-angle spectrogram constructed by the first angle information and the first distance information, the feature representation corresponding to the position information of the target point cloud data and the fourth point cloud data in the spectrogram can be extracted as the horizontal feature data corresponding to the target user.

[0076] In S318, based on the horizontal feature data and the vertical feature data, the spatial feature data corresponding to the target user is determined.

[0077] In S320, based on the pre-trained feature extraction model, the behavior feature vector corresponding to the spatial feature data is obtained.

[0078] Among them, the feature extraction model can be trained based on historical spatial feature data for a model constructed by a preset data feature extraction algorithm, and the preset data feature extraction algorithm can be any deep learning algorithm.

[0079] In implementation, taking the preset data feature extraction algorithm as the Long Short-Term Memory (LSTM) algorithm as an example, a feature extraction model as shown in the figure can be constructed based on the LSTM network. Among them, the LSTM network can include an LSTM layer of 64 dimensions, an LSTM layer of 128 dimensions, and an LSTM layer of 256 dimensions. The feature extraction model can also include a fully connected network constructed by 3 fully connected layers, and the fully connected network can be used for model training. Figure 5 As shown in the figure, the feature extraction model can be constructed based on the LSTM network. Among them, the LSTM network can include an LSTM layer of 64 dimensions, an LSTM layer of 128 dimensions, and an LSTM layer of 256 dimensions. The feature extraction model can also include a fully connected network constructed by 3 fully connected layers, and the fully connected network can be used for model training.

[0080] Historical spatial feature data and the corresponding user identity can be obtained. The historical spatial feature data can include historical horizontal feature data and historical vertical feature data. After inputting the historical spatial feature data into the LSTM network, the corresponding behavior feature vector can be obtained. Using the user identity as a label, the constructed feature extraction model is trained through the fully connected network, the behavior feature vector output by the LSTM network, the label, and the preset gradient descent method to obtain the pre-trained feature extraction model.

[0081] After inputting the spatial feature data into the pre-trained feature extraction model, the behavior feature vector corresponding to the spatial feature data can be obtained.

[0082] In S322, based on the behavior feature vector, the identity recognition result for identifying the target user is determined.

[0083] In implementation, in practical applications, the processing method of the above S322 can be various. The following provides an optional implementation method, which can be specifically referred to the processing in the following Step 1 to Step 2:

[0084] Step 1: Obtain the target feature vector that matches the behavior feature vector among multiple pre-stored feature vectors.

[0085] In implementation, the target feature vector that matches the behavior feature vector can be obtained based on a preset vector matching algorithm. For example, based on the preset matching algorithm, the matching degree between each pre-stored feature vector and the behavior feature vector can be obtained, and the feature vector with the maximum matching degree is determined as the target feature vector.

[0086] Step 2: Obtain the user identity corresponding to the target feature vector, and determine the user identity as the identity recognition result for identifying the target user.

[0087] Since the feature vectors are pre-stored in the database and the feature vectors cannot be used to steal the user's privacy data, that is, the risk of data leakage caused by storing privacy data such as user images and fingerprints can be avoided, and the data security of the identity recognition process is improved.

[0088] An embodiment of this specification provides an identity recognition method. Based on the transmitted signal and received signal of the signal sending device within the identity recognition period, target timing data including point cloud data is generated. The point cloud data is determined by the transmitted signal and received signal. Based on the target timing data, the target point cloud data corresponding to the target user to be recognized is determined from the point cloud data included in the target timing data, and based on the target point cloud data, spatial feature data corresponding to the target user is generated. Based on the spatial feature data, the identity of the target user is recognized to obtain an identity recognition result. In this way, since only the transmitted signal and received signal of the signal sending device are required to generate the target timing data, and data processing is performed based on the target timing data to recognize the identity of the target user, without the need to obtain the privacy data (such as face images, fingerprints, etc.) of the target user, it has a good privacy data protection effect and improves the security of privacy protection for identity recognition.

[0089] Embodiment 3

[0090] The above is the identity recognition method provided by the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide an identity recognition device, as Figure 6 shown.

[0091] The identity recognition device includes: a data generation module 601, a data selection module 602, and an identity recognition module 603, where:

[0092] A data generation module 601, configured to generate target timing data including point cloud data based on the transmitted signal and received signal of a signal sending device during an identity recognition period, where the point cloud data is determined by the transmitted signal and received signal;

[0093] A data selection module 602, configured to determine target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target timing data based on the target timing data, and generate spatial feature data corresponding to the target user according to the target point cloud data;

[0094] An identity recognition module 603, configured to perform identity recognition on the target user based on the spatial feature data to obtain an identity recognition result.

[0095] In an embodiment of this specification, the identity recognition module 603 includes:

[0096] A feature acquisition unit, configured to obtain a behavior feature vector corresponding to the spatial feature data based on a pre-trained feature extraction model, where the feature extraction model is obtained by training a model constructed by a preset data feature extraction algorithm based on historical spatial feature data;

[0097] An identity recognition unit, configured to determine an identity recognition result for performing identity recognition on the target user based on the behavior feature vector.

[0098] In an embodiment of this specification, the data generation module 601 includes:

[0099] An information determination unit, configured to determine first distance information and first angle information between the signal sending device and an object to be recognized based on the transmitted signal and received signal of the signal sending device during an identity recognition period;

[0100] A first generation unit, configured to generate the point cloud data based on the first distance information, the first angle information, and the corresponding time;

[0101] A second generation unit, configured to generate the target timing data based on the point cloud data and the corresponding time.

[0102] In an embodiment of this specification, the data selection module 602 includes:

[0103] A position determination unit, configured to determine the position information of the target user based on the target timing data;

[0104] A data determination unit, configured to determine target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target timing data based on the position information.

[0105] In the embodiments of the present specification, the data determination unit is configured to:

[0106] Obtain second point cloud data corresponding to the position information in the target time series data;

[0107] Determine the second point cloud data as the target point cloud data corresponding to the target user.

[0108] In the embodiments of the present specification, the data selection module 602 includes:

[0109] A data acquisition unit, configured to acquire third point cloud data with the same horizontal position information as the target point cloud data and fourth point cloud data with the same vertical position information as the target point cloud data in the target time series data;

[0110] A first determination unit, configured to determine horizontal feature data corresponding to the target user based on the target point cloud data and the third point cloud data;

[0111] A second determination unit, configured to determine vertical feature data corresponding to the target user based on the target point cloud data and the fourth point cloud data;

[0112] A third determination unit, configured to determine spatial feature data corresponding to the target user based on the horizontal feature data and the vertical feature data.

[0113] In the embodiments of the present specification, the identity recognition unit is configured to:

[0114] Obtain a target feature vector that matches the behavior feature vector among a plurality of pre-stored feature vectors;

[0115] Obtain the user identity corresponding to the target feature vector, and determine the user identity as the identity recognition result of the identity recognition of the target user.

[0116] In the embodiments of the present specification, the information determination unit is configured to:

[0117] Perform difference frequency processing on the transmitted signal and the received signal of the signal transmitting device within the identity recognition period to obtain a first signal;

[0118] Determine the first distance information based on the frequency and the bandwidth of the first signal.

[0119] In the embodiments of the present specification, the information determination unit is configured to:

[0120] Based on the wavelength of the received signal, the phase difference and the distance between two adjacent receiving antennas in the signal transmitting device within the identity recognition period, determine the first angle information.

[0121] An embodiment of this specification provides an identity recognition device. Based on the transmitted signal and the received signal of the signal sending device within the identity recognition period, generate target timing data including point cloud data. The point cloud data is determined by the transmitted signal and the received signal. Based on the target timing data, determine the target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target timing data, and generate spatial feature data corresponding to the target user according to the target point cloud data. Based on the spatial feature data, perform identity recognition on the target user to obtain an identity recognition result. In this way, since only the transmitted signal and the received signal of the signal sending device are required to generate the target timing data, and data processing is performed based on the target timing data to perform identity recognition on the target user, without the need to obtain the privacy data of the target user (such as face images, fingerprints, etc.), it has a good privacy data protection effect and improves the security of privacy protection for identity recognition.

[0122] Embodiment 4

[0123] Based on the same idea, an embodiment of this specification also provides an identity recognition device, as Figure 7 shown.

[0124] The identity recognition device may vary greatly due to configuration or performance, and may include one or more processors 701 and a memory 702. One or more application programs or data may be stored in the memory 702. Among them, the memory 702 may be short-term storage or persistent storage. The application programs stored in the memory 702 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the identity recognition device. Further, the processor 701 may be set to communicate with the memory 702 and execute a series of computer-executable instructions in the memory 702 on the identity recognition device. The identity recognition device may also include one or more power supplies 703, one or more wired or wireless network interfaces 704, one or more input / output interfaces 705, and one or more keyboards 706.

[0125] Specifically, in this embodiment, the identity recognition device includes a memory and one or more programs, where one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions in the identity recognition device, and is configured to execute the one or more programs by one or more processors, and the one or more programs include computer-executable instructions for performing the following:

[0126] Based on the transmitted signal and received signal of the signal sending device during the identity recognition period, generate target timing data including point cloud data, where the point cloud data is determined by the transmitted signal and received signal;

[0127] Based on the target timing data, determine the target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target timing data, and generate spatial feature data corresponding to the target user according to the target point cloud data;

[0128] Based on the spatial feature data, perform identity recognition on the target user to obtain an identity recognition result.

[0129] Optionally, the performing identity recognition on the target user based on the spatial feature data to obtain an identity recognition result includes:

[0130] Based on a pre-trained feature extraction model, obtain a behavior feature vector corresponding to the spatial feature data, where the feature extraction model is trained based on historical spatial feature data on a model constructed by a preset data feature extraction algorithm;

[0131] Based on the behavior feature vector, determine the identity recognition result for performing identity recognition on the target user.

[0132] Optionally, the generating target timing data including point cloud data based on the transmitted signal and received signal of the signal sending device during the identity recognition period includes:

[0133] Based on the transmitted signal and received signal of the signal sending device during the identity recognition period, determine the first distance information and the first angle information between the signal sending device and the object to be recognized;

[0134] Based on the first distance information, the first angle information and the corresponding time, generate the point cloud data;

[0135] Based on the point cloud data and the corresponding time, generate the target timing data.

[0136] Optionally, determining the target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target time series data includes:

[0137] Based on the target time series data, determine the location information of the target user;

[0138] Based on the location information, determine the target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target time series data.

[0139] Optionally, determining the target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target time series data based on the location information includes:

[0140] Obtain the second point cloud data corresponding to the location information in the target time series data;

[0141] Determine the second point cloud data as the target point cloud data corresponding to the target user.

[0142] Optionally, generating the spatial feature data corresponding to the target user according to the target point cloud data includes:

[0143] Obtain the third point cloud data with the same horizontal position information as the target point cloud data and the fourth point cloud data with the same vertical position information as the target point cloud data in the target time series data;

[0144] Based on the target point cloud data and the third point cloud data, determine the horizontal feature data corresponding to the target user;

[0145] Based on the target point cloud data and the fourth point cloud data, determine the vertical feature data corresponding to the target user;

[0146] Based on the horizontal feature data and the vertical feature data, determine the spatial feature data corresponding to the target user.

[0147] Optionally, determining the identity recognition result for performing identity recognition on the target user based on the behavior feature vector includes:

[0148] Obtain the target feature vector that matches the behavior feature vector among the multiple pre-stored feature vectors;

[0149] Obtain the user identity corresponding to the target feature vector and determine the user identity as the identity recognition result for performing identity recognition on the target user.

[0150] Optionally, determining the first distance information between the signal sending device and the object to be identified based on the transmitted signal and the received signal of the signal sending device within the identity recognition period includes:

[0151] Performing difference frequency processing on the transmitted signal and the received signal of the signal sending device within the identity recognition period to obtain a first signal;

[0152] Determining the first distance information based on the frequency and the bandwidth of the first signal.

[0153] Optionally, determining the first angle information between the signal sending device and the object to be identified based on the transmitted signal and the received signal of the signal sending device within the identity recognition period includes:

[0154] Determining the first angle information based on the wavelength of the received signal, the phase difference and the distance between two adjacent receiving antennas in the signal transmitting device within the identity recognition period.

[0155] An embodiment of this specification provides an identity recognition device. Based on the transmitted signal and the received signal of a signal sending device within an identity recognition period, target timing data including point cloud data is generated. The point cloud data is determined by the transmitted signal and the received signal. Based on the target timing data, target point cloud data corresponding to the target user to be identified is determined from the point cloud data included in the target timing data, and based on the target point cloud data, spatial feature data corresponding to the target user is generated. Based on the spatial feature data, identity recognition of the target user is performed to obtain an identity recognition result. In this way, since only the transmitted signal and the received signal of the signal sending device are required to generate the target timing data, and data processing is performed based on the target timing data to perform identity recognition of the target user, without the need to obtain the privacy data of the target user (such as face images, fingerprints, etc.), it has a good privacy data protection effect and improves the security of privacy protection for identity recognition.

[0156] Embodiment Five

[0157] An embodiment of this specification also provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, each process of the above identity recognition method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0158] An embodiment of this specification provides a computer-readable storage medium, which generates target timing data including point cloud data based on the transmitted signal and received signal of a signal sending device during an identity recognition period. The point cloud data is determined by the transmitted signal and received signal. Based on the target timing data, target point cloud data corresponding to a target user to be recognized is determined from the point cloud data included in the target timing data, and spatial feature data corresponding to the target user is generated according to the target point cloud data. Based on the spatial feature data, identity recognition of the target user is performed to obtain an identity recognition result. In this way, since only the transmitted signal and received signal of the signal sending device are required to generate the target timing data, and data processing is performed based on the target timing data to perform identity recognition of the target user, without the need to obtain the privacy data of the target user (such as face images, fingerprints, etc.), it has a good privacy data protection effect and improves the security of privacy protection for identity recognition.

[0159] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0160] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software improvements (improvements to method flows). However, with the development of technology, many method flow improvements today can be regarded as direct improvements to hardware circuit structures. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement to a method flow cannot be implemented using a hardware entity module. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logical function is determined by a user's programming of the device. Designers can program on their own to "integrate" a digital system onto a single PLD, without having to ask a chip manufacturer to design and fabricate a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compilers used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a Hardware Description Language (HDL). There is not just one type of HDL, but many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be aware that by simply performing some logical programming on the method flow using the above-mentioned several hardware description languages and programming it into an integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0161] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to logically program the method steps to enable the controller to be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. to achieve the same function. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or structures within the hardware component.

[0162] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0163] For the convenience of description, the above devices are described by dividing them into various units according to their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0164] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0165] Embodiments of this specification are described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable identity devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable identity devices produce a means for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0166] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable identity device to operate in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0167] These computer program instructions can also be loaded onto a computer or other programmable identity device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0168] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0169] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0170] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0171] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0172] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Thus, one or more embodiments of this specification may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0174] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiment.

[0175] The above is only the embodiment of this specification and is not used to limit this specification. For those skilled in the art, various changes and modifications can be made to this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included within the scope of the claims of this specification.

Claims

1. An identity recognition method, comprising: Generating target timing data including point cloud data based on the transmitted signal and received signal of a signal transmitting device within an identity recognition period, wherein the point cloud data is determined by the transmitted signal and received signal; Based on the target timing data, determining target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target timing data, and generating spatial feature data corresponding to the target user according to the target point cloud data, wherein the spatial feature data is determined based on horizontal feature data and vertical feature data, the horizontal feature data is determined based on the target point cloud data and third point cloud data, the vertical feature data is determined based on the target point cloud data and fourth point cloud data, the third point cloud data is the point cloud data in the target timing data having the same horizontal position information as the target point cloud data, and the fourth point cloud data is the point cloud data in the target timing data having the same vertical position information as the target point cloud data; Based on the spatial feature data, performing identity recognition on the target user to obtain an identity recognition result.

2. The method according to claim 1, wherein the performing identity recognition on the target user based on the spatial feature data to obtain an identity recognition result comprises: Obtaining a behavior feature vector corresponding to the spatial feature data based on a pre-trained feature extraction model, wherein the feature extraction model is trained based on historical spatial feature data on a model constructed by a preset data feature extraction algorithm; Based on the behavior feature vector, determining an identity recognition result for performing identity recognition on the target user.

3. The method according to claim 1, wherein the generating target timing data including point cloud data based on the transmitted signal and received signal of a signal transmitting device within an identity recognition period comprises: Determining first distance information and first angle information between the signal transmitting device and a target user to be recognized based on the transmitted signal and received signal of the signal transmitting device within the identity recognition period; Generating the point cloud data based on the first distance information, the first angle information and the corresponding time; Generating the target timing data based on the point cloud data and the corresponding time.

4. The method according to claim 3, wherein the determining target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target timing data based on the target timing data comprises: Determining the position information of the target user based on the target timing data; Based on the position information, determining target point cloud data corresponding to the target user to be recognized from the point cloud data included in the target timing data.

5. The method according to claim 4, wherein the determining target point cloud data corresponding to a target user to be recognized from the point cloud data included in the target timing data based on the position information comprises: Obtaining second point cloud data corresponding to the position information in the target timing data; Determining the second point cloud data as the target point cloud data corresponding to the target user.

6. The method according to claim 2, wherein determining an identity recognition result for identifying the target user based on the behavior feature vector includes: obtaining a target feature vector that matches the behavior feature vector from a plurality of pre-stored feature vectors; obtaining the user identity corresponding to the target feature vector, and determining the user identity as the identity recognition result for identifying the target user.

7. The method according to claim 3, wherein determining first distance information between the signal sending device and a target user to be identified based on the transmitted signal and the received signal of the signal sending device during an identity recognition period includes: performing difference frequency processing on the transmitted signal and the received signal of the signal sending device during the identity recognition period to obtain a first signal; determining the first distance information based on the frequency of the first signal and the bandwidth of the first signal.

8. The method according to claim 3, wherein determining first angle information between the signal sending device and a target user to be identified based on the transmitted signal and the received signal of the signal sending device during an identity recognition period includes: determining the first angle information based on the wavelength of the received signal, the phase difference between two adjacent receiving antennas in the signal sending device, and the distance between the two adjacent receiving antennas during the identity recognition period.

9. An identity recognition device, comprising: a data generation module, configured to generate target timing data including point cloud data based on a transmitted signal and a received signal of a signal sending device during an identity recognition period, where the point cloud data is determined by the transmitted signal and the received signal; a data selection module, configured to determine, based on the target timing data, target point cloud data corresponding to a target user to be identified from the point cloud data included in the target timing data, and generate spatial feature data corresponding to the target user according to the target point cloud data, where the spatial feature data is determined based on horizontal feature data and vertical feature data, the horizontal feature data is determined based on the target point cloud data and third point cloud data, the vertical feature data is determined based on the target point cloud data and fourth point cloud data, the third point cloud data is point cloud data in the target timing data having the same horizontal position information as the target point cloud data, and the fourth point cloud data is point cloud data in the target timing data having the same vertical position information as the target point cloud data; an identity recognition module, configured to perform identity recognition on the target user based on the spatial feature data to obtain an identity recognition result.

10. An identity recognition device, the identity recognition device comprising: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to: generate target timing data including point cloud data based on a transmitted signal and a received signal of a signal sending device during an identity recognition period, where the point cloud data is determined by the transmitted signal and the received signal; Based on the target time-series data, determine the target point cloud data corresponding to the target user to be identified from the point cloud data included in the target time-series data, and generate spatial feature data corresponding to the target user according to the target point cloud data, where the spatial feature data is determined based on horizontal feature data and vertical feature data, the horizontal feature data is determined based on the target point cloud data and the third point cloud data, the vertical feature data is determined based on the target point cloud data and the fourth point cloud data, the third point cloud data is the point cloud data in the target time-series data with the same horizontal position information as the target point cloud data, and the fourth point cloud data is the point cloud data in the target time-series data with the same vertical position information as the target point cloud data; Based on the spatial feature data, perform identity recognition on the target user to obtain an identity recognition result.

11. A storage medium for storing computer-executable instructions, which, when executed by a processor, implement the following process: Generate target time-series data including point cloud data based on the transmitted signal and received signal of a signal transmitting device during an identity recognition period, where the point cloud data is determined by the transmitted signal and received signal; Based on the target time-series data, determine the target point cloud data corresponding to the target user to be identified from the point cloud data included in the target time-series data, and generate spatial feature data corresponding to the target user according to the target point cloud data, where the spatial feature data is determined based on horizontal feature data and vertical feature data, the horizontal feature data is determined based on the target point cloud data and the third point cloud data, the vertical feature data is determined based on the target point cloud data and the fourth point cloud data, the third point cloud data is the point cloud data in the target time-series data with the same horizontal position information as the target point cloud data, and the fourth point cloud data is the point cloud data in the target time-series data with the same vertical position information as the target point cloud data; Based on the spatial feature data, perform identity recognition on the target user to obtain an identity recognition result.

Images