CN115659305A - Identity information identification method and system and electronic equipment - Google Patents
Identity information identification method and system and electronic equipment Download PDFInfo
- Publication number
- CN115659305A CN115659305A CN202211681566.6A CN202211681566A CN115659305A CN 115659305 A CN115659305 A CN 115659305A CN 202211681566 A CN202211681566 A CN 202211681566A CN 115659305 A CN115659305 A CN 115659305A
- Authority
- CN
- China
- Prior art keywords
- identity
- data
- cloud server
- identity information
- white list
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000000605 extraction Methods 0.000 claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 16
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000003862 health status Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011496 digital image analysis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The application discloses an identity information identification method, an identity information identification system and electronic equipment, relates to the technical field of information identification, and aims to solve the technical problem that an existing information identification management system is low in identification efficiency. The identity information identification method is used for terminal equipment and comprises the following steps: performing feature extraction on the acquired first identity data to acquire first identity mark data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment; retrieving from the terminal device whether the first identity token data is present; if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data; and obtaining a recognition result based on the target identity mark data received from the cloud server.
Description
Technical Field
The present application relates to the field of information identification technologies, and in particular, to a method, a system, and an electronic device for identifying identity information.
Background
With the development of modern social technology, the safety awareness of people is gradually improved, an information identification system appears, and only data for storing the identity information of a detector is detected and can be opened, so that the method is very convenient and efficient. For example, the human face biological pattern detection and recognition technology, that is, the non-contact recognition technology using computer image analysis, model theory, artificial intelligence and pattern recognition technology, can detect characteristic human face information from a complex image scene and perform matching recognition.
At present, the technology of human face biological pattern detection and recognition tends to be mature, but most of terminal equipment on the market only supports single-machine human face recognition at present, but the human face picture information which can be stored by single terminal equipment is limited, the average number is about 50000, the requirements of urban human face recognition are difficult to meet, and the use limitation is large. Although the cloud face recognition can expand the storage capacity as required, the system is easy to crash due to excessive concurrent pressure during the recognition peak use period, so that the recognition efficiency is low.
Disclosure of Invention
The present application mainly aims to provide an identity information identification method, an identity information identification system, and an electronic device, and aims to solve the technical problem that an existing information identification management system is prone to system breakdown due to too high concurrent pressure during a peak period, so that identification efficiency is low.
In order to solve the above technical problem, an embodiment of the present application provides: an identity information identification method is used for terminal equipment and comprises the following steps:
performing feature extraction on the acquired first identity data to acquire first identity mark data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment;
retrieving from the terminal device whether the first identity token data is present;
if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data;
and obtaining a recognition result based on the target identity mark data received from the cloud server.
As some optional embodiments of the present application, the retrieving, from the terminal device, whether the first identity token data exists includes:
retrieving from a first white list identity information base stored in the terminal device to obtain similar identity label data;
judging whether the matching confidence value of the similar identity marking data meets a first matching confidence threshold value;
and if so, the first identity marking data exists in the terminal equipment.
As some optional embodiments of the present application, after obtaining the recognition result based on the target identity token data received from the cloud server, the method further includes:
judging whether the target identity mark data is resident identity information or not;
and if the target identity marking data is resident identity information, recording the target identity marking data into the first white list identity information base.
As some optional embodiments of the present application, the determining whether the target identity token data is resident identity information includes:
acquiring a matching confidence value of the target identity marking data;
and if the matching confidence value of the target identity marking data meets a preset second matching confidence threshold, the target identity marking data is resident identity information.
As some optional embodiments of the present application, the entering the target identity label data into the first white list identity information base includes:
judging whether a first white list identity information base of the terminal equipment is full or not;
if the balance is not full, the first identity mark data is recorded into the first white list identity information base;
and if the balance is full, deleting the white list identity information which does not meet a preset sorting threshold value in the first white list identity information base, and inputting the first identity mark data into the first white list identity information base.
As some optional embodiments of the present application, the deleting the white list identity information that does not satisfy the preset sorting threshold in the first white list identity information base includes:
sorting the use frequency of the white list identity information in the first white list identity information base by adopting an LFU algorithm; wherein the usage frequency ordering comprises usage time ordering and usage time ordering;
and deleting the white list identity information which does not meet the preset sorting threshold according to the sorted white list information.
In order to solve the above technical problem, an embodiment of the present application further provides: an identity information identification method is used for a cloud server and comprises the following steps:
receiving first identity data sent by terminal equipment under the condition that the first identity marking data does not exist in the terminal equipment; the first identity marking data is obtained by carrying out feature extraction on the basis of the first identity data, and the first identity data comprises electronic data record information generated when a user uses an identification terminal device;
performing feature extraction on the first identity data to obtain second identity mark data;
retrieving whether target identity tag data corresponding to the second identity tag data exists in the cloud server or not based on the second identity tag data;
and if the target identity mark data exists in the cloud server, feeding the target identity mark data back to the terminal equipment so that the terminal equipment can obtain an identification result according to the target identity mark data.
As some optional embodiments of the present application, the retrieving, based on the second identity token data, whether target identity token data corresponding to the second identity token data exists in the cloud server includes:
retrieving from a second white list identity information base stored in the cloud server based on the second identity label data to obtain similar identity label data;
judging whether the matching confidence of the similar identity marking data meets a first matching confidence threshold value;
and if so, the target identity marking data exists in a second white list identity information base of the cloud server.
In order to solve the above technical problem, an embodiment of the present application further provides: an identity information recognition system comprising:
the terminal equipment is used for carrying out feature extraction on the acquired first identity data to acquire first identity mark data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment; retrieving from the terminal device whether the first identity token data is present; if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data; obtaining a recognition result based on the target identity mark data received from the cloud server;
the cloud server is used for receiving first identity data sent by the terminal equipment under the condition that the first identity marking data do not exist in the terminal equipment; the first identity marking data is obtained by carrying out feature extraction on the basis of the first identity data, and the first identity data comprises electronic data record information generated when a user uses an identification terminal device; extracting the characteristics of the first identity data to obtain second identity mark data; retrieving whether target identity tag data corresponding to the second identity tag data exists in the cloud server or not based on the second identity tag data; and if the target identity marking data exists in the cloud server, feeding the target identity marking data back to the terminal equipment so that the terminal equipment can obtain a recognition result according to the target identity marking data.
In order to solve the above technical problem, an embodiment of the present application further provides: an electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the identity information identification method.
Compared with the prior art, the identity information identification method is used for the terminal equipment, namely the first identity mark data is obtained by carrying out feature extraction on the obtained first identity data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment; the feature extraction can be set according to actual requirements, and if the method is applied to face recognition, the features refer to face features, and the corresponding first identity mark data is face information. The terminal equipment is provided with a storage system which can be used for storing identity mark information with certain capacity, so that after the first identity mark data is obtained, the method preferentially searches whether the first identity mark data exists in the terminal equipment; if the first identity marking data exists in the terminal equipment, the terminal equipment identifies the first identity marking data obtained by retrieval, through the steps, in a peak identification use period, a network congestion phenomenon of cloud retrieval can be effectively avoided, but due to the fact that the storage capacity of the terminal equipment is limited, the situation that the first identity marking data does not exist in the terminal equipment possibly occurs, and under the situation, the first identity marking data is sent to a cloud server, so that the cloud server retrieves according to the first identity marking data and obtains target identity marking data; by the cloud retrieval mode, the technical defect that the storage capacity of the terminal equipment is limited can be effectively overcome, and therefore the identification result is obtained based on the target identity mark data received from the cloud server. Therefore, the identity identification method is based on the acquired user identity information, the retrieval is performed in the local storage system of the terminal equipment, the service pressure of cloud retrieval in the peak identification service period is reduced to a great extent, and the network transmission time is shortened; however, because the storage capacity of the local storage system is limited, if the user identity information is not retrieved in the local storage system, the user identity information is sent to the cloud server for supplementary retrieval, so that the steady operation of the identity recognition system is ensured, and the identity information recognition efficiency is improved.
Drawings
Fig. 1 is a schematic flow chart of an identity information identification method according to an embodiment of the present application;
FIG. 2 is a logic diagram of an identity information recognition method according to an embodiment of the present application;
fig. 3 is a schematic diagram of a possible architecture of an identity information recognition system according to an embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The main solution of the embodiment of the application is as follows: an identity information identification method is used for terminal equipment and comprises the following steps: performing feature extraction on the acquired first identity data to acquire first identity mark data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment; retrieving from the terminal device whether the first identity token data is present; if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data; and obtaining a recognition result based on the target identity mark data received from the cloud server.
Taking the face recognition which is widely applied at present as an example, most of the terminal devices which are used as epidemic prevention sentinels in the market at present only support single-machine face recognition, but the face picture information which can be stored by a single terminal device is limited, the average number is about 50000, and the requirements of the face recognition at the city level are difficult to meet. Although the storage capacity can be expanded by cloud face recognition as required, the system is easily crashed due to too much concurrent pressure during the recognition peak use period, and the recognition efficiency is low.
Based on the identification method, the identification method is high in identification efficiency and capable of reducing concurrent pressure of identifying peak use periods. The identification peak use period refers to a time period in which face identification is performed intensively, for example, an on-duty time period and an off-duty time period.
Compared with the prior art, the identity information identification method is used for the terminal equipment, namely the first identity mark data is obtained by carrying out feature extraction on the obtained first identity data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment; the feature extraction can be set according to actual requirements, and if the method is applied to face recognition, the features refer to face features, and the corresponding first identity mark data is face information. The terminal equipment is provided with a storage system which can be used for storing identity mark information with certain capacity, so that after the first identity mark data is obtained, the method preferentially searches whether the first identity mark data exists in the terminal equipment; if the first identity marking data exists in the terminal equipment, the terminal equipment identifies the first identity marking data obtained by retrieval, through the steps, in a peak identification use period, a network congestion phenomenon of cloud retrieval can be effectively avoided, but due to the fact that the storage capacity of the terminal equipment is limited, the situation that the first identity marking data does not exist in the terminal equipment possibly occurs, and under the situation, the first identity marking data is sent to a cloud server, so that the cloud server retrieves according to the first identity marking data and obtains target identity marking data; by the cloud retrieval mode, the technical defect that the storage capacity of the terminal equipment is limited can be effectively overcome, and therefore the identification result is obtained based on the target identity mark data received from the cloud server. Therefore, the identity identification method is based on the acquired user identity information, the retrieval is carried out on the local storage system of the terminal equipment, the service pressure of cloud retrieval in the peak identification service period is reduced to a great extent, and the network transmission time is reduced; however, because the storage capacity of the local storage system is limited, if the user identity information is not retrieved in the local storage system, the user identity information is sent to the cloud server for supplementary retrieval, so that the steady operation of the identity recognition system is ensured, and the identity information recognition efficiency is improved.
The method of this embodiment may be executed in a program manner based on an existing computer device running a program, where the computer device may be a terminal device such as a mobile phone, a tablet, a desktop computer, or a server, and the computer device may include a processor, a storage medium, and the like, where the storage medium is used to store the program for executing the method of this embodiment, and the processor is used to run the program to execute the method of identifying identity information according to this embodiment.
Referring to fig. 1, an embodiment of the present application provides an identity information identification method, which is used for a terminal device, and includes the following steps:
and S10, performing feature extraction on the acquired first identity data to acquire first identity marking data.
In a specific application, the first identity data refers to originally acquired data that can be used for identifying a user identity, for example, face image data, fingerprint data, and the like, and may be generated when a user uses a terminal device. Correspondingly, the first identity marking data refers to data which is obtained by processing the first identity information and can be used for identifying the identity of the user. The first identity data has different expression forms according to different application scenes, and the corresponding first identity marking data also has different forms, for example, when the application scene is human face recognition, the expression form of the first identity data can be an originally acquired human face image including a background, and the first identity marking data obtained after feature extraction can be a marked human face feature image or an image only including a human face; if the application scene is fingerprint identification, the expression form of the first identity data can be original fingerprint data, and the first identity mark data obtained after feature extraction can be an image consistent with the original fingerprint data or an image for marking fingerprint features.
And step S20, retrieving whether the first identity marking data exists from the terminal equipment.
Specifically, the terminal device is provided with a local storage system, configured to store the first identity token data and other identity token data, and configured to retrieve whether the first identity token data exists from the local storage system of the terminal device after the first identity token data is acquired. In addition, optionally, in the local storage system, identity information corresponding to each identity tag data, such as name, identification number, gender, native place, etc., may also be stored. After the first identity token data is identified, the identity information can be used to confirm whether the personnel matching is accurate again. The local storage system is used as the first-level cache of the cloud server, so that the face recognition efficiency is effectively improved, and meanwhile, the high concurrency pressure of the cloud server in the recognition peak use period is reduced.
Specifically, the step S20 of retrieving whether the first identity token data exists from the terminal device includes:
and S21, retrieving from a first white list identity information base stored in the terminal equipment to obtain similar identity mark data.
In a specific application, the first white list identity information base comprises a plurality of white list identity information. Each whitelist identity information may include identity token data and its corresponding identity information. Taking a face recognition scene of a certain park as an example, the white list identity information refers to face images and identity information of people in the park. In order to improve the identification efficiency of the identity information and avoid the high concurrent pressure of the cloud server in the peak period, the identity marking data of the personnel and the corresponding identity information are stored in the first white list identity information base of the terminal equipment in the method, so that local retrieval is facilitated.
Similar identity mark data are retrieved, but because the white list identity information in the first white list identity information base is numerous and a plurality of similar situations may occur in image or fingerprint comparison, when the first identity mark data are input into the first white list identity information base for retrieval, a plurality of similar identity mark data are likely to occur, and therefore, in order to accurately screen and obtain the first identity mark data from the plurality of similar identity mark data, after the step, the following step S22 is further included.
Step S22, judging whether the matching confidence value of the similar identity mark data meets a first matching confidence threshold value; and if so, the first identity marking data exists in the terminal equipment.
In a specific application, the method determines whether the first identity token data exists in the first white list identity information base by determining whether the matching confidence value of the similar identity token data satisfies a first matching confidence threshold. The matching confidence value can be obtained by calculating by using an identity recognition algorithm such as Huacheng cloud, and the first matching confidence threshold value can be set according to actual requirements or according to an industry recognition standard value, such as the highest matching confidence value is greater than 0.93. For example, in a face recognition scenario, based on the first identity label data, a plurality of face images similar to the first identity label data may be retrieved from the first white list identity information base, and at this time, it needs to be determined whether the face images are the first identity label data through a confidence calculation.
Step S30, if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data.
In a specific application, since the local storage system of the terminal device has a limited storage capacity, it is highly likely that the first identity token data is not present in the terminal device; in this case, the first identity tag data is sent to a cloud server, so that the cloud server retrieves the first identity tag data and obtains target identity tag data, thereby avoiding a failure in identification due to insufficient storage capacity of a local storage system. It should be noted that the retrieval process at the cloud server is similar to the local retrieval process at the terminal device, and is not described herein again.
And S40, obtaining a recognition result based on the target identity mark data received from the cloud server.
In a specific application, the target identity tag data is similar to the first identity tag data, and after the cloud server retrieves the target identity tag data, the target identity tag data is fed back to the terminal device, and the terminal device obtains a recognition result based on the target identity tag data received from the cloud server, that is, if the target identity tag data can be retrieved from the cloud server, the target identity tag data is in a second white list identity information base of the cloud server, so that the recognition result is successful. Certainly, the step S40 may be expanded according to an actual application scenario, if the current epidemic situation is severe, and some parks have epidemic prevention requirements, the park may correlate the health status of the target identity tag data again based on the target identity tag data received from the cloud server, such as health indicators such as body temperature, and if the health status is abnormal, even if the target identity tag data belongs to the second white list identity information base, the identification result is unsuccessful; in this application scenario, the health status of the target identity label data is normal while the target identity label data is retrieved and obtained from the first white list identity information base or the second white list identity information base, and the identification result is successful.
In a specific application, in order to avoid that the first identity data still needs to be sent to a cloud server for retrieval after being acquired next time, in step S40 of the present application, after obtaining an identification result based on the target identity tag data received from the cloud server, the method further includes:
step S41, judging whether the target identity mark data is resident identity information or not;
in a specific application, whether a user corresponding to the target identity tag data is a resident person or not can be queried through offline, or whether the target identity tag data is resident identity information or not can be judged according to the matching confidence degree calculation, and if the matching confidence degree value of the target identity tag data is greater than 0.93, the target identity tag data is determined to be resident identity information. Specifically, the step S41 of determining whether the target identity tag data is resident identity information includes: acquiring a matching confidence value of the target identity marking data; and if the matching confidence value of the target identity marking data meets a preset second matching confidence threshold, the target identity marking data is resident identity information.
After determining whether the target identification mark data is resident identification information by the above method, step S42 is executed as follows.
And step S42, if the target identity mark data is resident identity information, recording the target identity mark data into the first white list identity information base.
Specifically, the step S42 of entering the target identity label data into the first white list identity information base includes:
step S421, judging whether a first white list identity information base of the terminal equipment is full; and if the balance is not full, the first identity mark data is recorded into the first white list identity information base.
In a specific application, since the storage capacity of the local storage system of the terminal device is limited, the first white list identity information base may be full, and therefore, before the target identity tag data is entered into the first white list identity information base, it is necessary to determine whether the first white list identity information base of the terminal device is full. If the first white list identity information base of the terminal equipment is full, corresponding error information can be prompted during inputting, and judgment can be carried out through the prompting information of the terminal equipment. If not, the first identity mark data can be directly recorded into the first white list identity information base.
Step S422, if the balance is full, deleting the white list identity information that does not satisfy the preset sorting threshold in the first white list identity information base, and inputting the first identity marking data into the first white list identity information base.
In specific application, the white list identity information in the first white list identity information base is subjected to use frequency sequencing by adopting an LFU algorithm; wherein the usage frequency ordering comprises usage time ordering and usage time ordering; and deleting the white list identity information which does not meet the preset sorting threshold according to the sorted white list information. If the usage frequency or the latest usage time of the white list identity information in the first white list identity information base is sequenced by using an LFU algorithm, if the identity information of a certain user is rarely acquired by the terminal equipment within the latest month and is ranked at the last position after the usage frequency sequencing, the user can be deleted under the condition that the first white list identity information base is full; or the identity information of a certain user is not acquired by the terminal equipment for a long time and is ranked at the end after the use time sequencing, and then the identity information can be deleted under the condition that the first white list identity information base is full. The preset sorting threshold value can be set, the white list identity information which does not meet the preset sorting threshold value is determined as the terminal resident personnel, and the terminal resident personnel are deleted.
In a specific application, in order to speed up the efficiency of entering the first identity mark data into the first white list identity information base, the first white list identity information base in the terminal device may be set to have an automatic deletion function, and in an automatic mode, the first white list identity information base may delete the white list identity information that does not meet a preset sorting threshold periodically or quantitatively according to the preset sorting threshold, so as to avoid the occurrence of the full amount of the first white list identity information base.
In order to solve the above technical problem, an embodiment of the present application further provides: an identity information identification method is used for a cloud server and comprises the following steps:
step SS10, receiving first identity data sent by the terminal equipment under the condition that the first identity marking data does not exist in the terminal equipment; the first identity marking data is obtained by performing feature extraction based on the first identity data, and the first identity data comprises electronic data record information generated when a user uses an identification terminal device.
In a specific application, a second white list identity information base is arranged in the cloud server, and due to the fact that the storage capacity of a first white list identity information base in the terminal device is limited, when the balance is full and new white list identity information needs to be input, the white list identity information in the first white list identity information base needs to be deleted; the second white list information base is synchronized when the first white list identity information base inputs white list identity information, but is not synchronized when the first white list identity information base deletes the white list identity information, so that the white list identity information in the second white list identity information base comprises and is more than the white list identity information in the first white list identity information base. And under the condition that the first identity marking data do not exist in the terminal equipment, the cloud server receives the first identity marking data sent by the terminal equipment and searches in the second white list information base.
And SS20, performing feature extraction on the first identity data to obtain second identity mark data.
In a specific application, after receiving first identity data sent by the terminal device, the cloud server also needs to perform feature extraction on the first identity data to obtain second identity tag data. Similarly to the foregoing embodiment, the first identity data has different expression forms according to different application scenarios, and the corresponding second identity label data also has different expression forms; if the application scene is human face recognition, the expression form of the first identity data can be an originally acquired human face image including a background, and the second identity marking data obtained after feature extraction can be a marked human face feature image or an image only including a human face; if the application scene is fingerprint identification, the expression form of the first identity data can be original fingerprint data, and the second identity mark data obtained after feature extraction can be an image consistent with the original fingerprint data or an image marked with fingerprint features.
And step SS30, retrieving whether target identity tag data corresponding to the second identity tag data exists in the cloud server or not based on the second identity tag data.
Specifically, the step SS30 of retrieving, based on the second identity tag data, whether target identity tag data corresponding to the second identity tag data exists in the cloud server includes:
and step SS31, based on the second identity label data, retrieving from a second white list identity information base stored in the cloud server to obtain similar identity label data.
In a specific application, the second white list identity information base of the cloud server includes the first white list identity information base in the terminal device and the white list identity information bases in other associated terminal devices except the terminal device. Therefore, when retrieving from the second white list identity information base stored in the cloud server based on the second identity label data, a plurality of similar identity label data may be retrieved, so that the method described in step SS32 needs to be performed to obtain the target identity label data by screening, that is:
step SS32, judging whether the matching confidence of the similar identity mark data meets a first matching confidence threshold; and if so, the target identity marking data exists in a second white list identity information base of the cloud server.
In specific application, whether the target identity marking data exists in a second white list identity information base of the cloud server is judged in a mode that whether the matching confidence value of the similar identity marking data meets a first matching confidence threshold value. The matching confidence value can be obtained by calculating by using an identity recognition algorithm such as Huacheng cloud, and the first matching confidence threshold value can be set according to actual requirements or according to an industry recognition standard value, such as the highest matching confidence value is greater than 0.93.
And SS40, if the target identity marking data exists in the cloud server, feeding the target identity marking data back to the terminal equipment so that the terminal equipment can obtain a recognition result according to the target identity marking data.
It should be noted that the method of this embodiment uses the cloud server as an execution main body, the actual contents of which are the same as those of the method in the foregoing embodiment, and for the explanation and description of the implementation, reference may be made to the foregoing embodiment, which is not described again here.
In specific application, the technical defect that the storage capacity of the terminal equipment is limited can be effectively overcome through the identity recognition method for the cloud server, and the first identity data received by the cloud server are retrieved through the terminal equipment and do not exist, namely after the terminal equipment acquires the first identity data, each first identity data is not sent to the cloud server for retrieval, but is retrieved based on a local storage system of the terminal equipment and sent to the cloud server after the retrieval is unsuccessful, so that the cloud retrieval service pressure in the peak identification use period is greatly reduced, the network transmission time is shortened, the steady operation of the identity recognition system is ensured, and the identity information recognition efficiency is improved.
For ease of understanding, the present application explains the logical relationship of the method described in the present application in conjunction with fig. 2:
taking an epidemic prevention system for face recognition as an example, when a certain user visits, a stand-alone face is shot to obtain first identity data, the first identity data is searched in a stand-alone white list (namely a first white list database in the embodiment) based on the first identity data, if the search result is yes, the identity information and the health code of the user are correlated, and therefore the health state of the user is obtained; and then judging whether to allow the passage or not based on the health state of the bus. And if the retrieval result obtained after retrieval in the stand-alone white list based on the first identity data is negative, sending the first identity data to a cloud for cloud cross-database retrieval, comparing face information, obtaining a plurality of similar identity information, judging whether target identity marking data exist or not according to confidence, and feeding back the retrieval result to the stand-alone to judge whether passage is allowed or not.
In order to implement the foregoing face recognition, a single white list needs to be entered before a user visits. Specifically, the method includes the steps that firstly, personnel information (including first identity data and identity information) is collected, then, if the first identity data of the user is not in the single-computer white list, whether the single-computer white list is full is judged, and if the first identity data of the user is not in the single-computer white list, the personnel information is recorded into the single-computer white list and is synchronized to a cloud database; and if the single white list is full, sequencing the use frequency of the terminal list of the single white list, and acquiring and deleting terminal resident personnel and non-resident personnel, so that the personnel information of the user is recorded into the single white list and is synchronized to a database of the cloud server.
In addition, based on the same inventive concept as the previous embodiment, referring to fig. 3, the embodiment of the present application further provides: an identity information recognition system comprising:
the terminal equipment is used for extracting the characteristics of the acquired first identity data to acquire first identity marking data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment; retrieving from the terminal device whether the first identity token data is present; if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data; obtaining a recognition result based on the target identity mark data received from the cloud server;
the cloud server is used for receiving first identity data sent by the terminal equipment under the condition that the first identity marking data do not exist in the terminal equipment; the first identity marking data is obtained by performing feature extraction on the basis of the first identity marking data; extracting the characteristics of the first identity data to obtain second identity mark data; retrieving whether target identity tag data corresponding to the second identity tag data exists in the cloud server or not based on the second identity tag data; and if the target identity marking data exists in the cloud server, feeding the target identity marking data back to the terminal equipment so that the terminal equipment can obtain a recognition result according to the target identity marking data.
In a specific application, taking face recognition as an example, as shown in fig. 3, the system of the present application includes a cloud server and a terminal device. Based on the method of the foregoing embodiment, the process of specifically implementing face recognition is as follows: a certain user carries out face recognition through terminal equipment, and locally judges whether the user is a person in a first white list identity information base or not by utilizing the terminal equipment, and if so, the user directly feeds back the face recognition; if not, the identity data of the user is sent to a cloud server to judge whether the user belongs to a second white list identity information base of the cloud. Meanwhile, in order to improve the identification efficiency of the subsequent terminal equipment on the user, if the user is a resident person, the user enters a first white list identity information base of the local equipment through the resident person and synchronizes to the cloud server.
In addition, based on the same inventive concept as the foregoing embodiments, the embodiments of the present application further provide a terminal device, which at least includes a processor and a memory, wherein,
the memory is used for storing a computer program;
the processor is used for loading and executing the computer program so as to enable the terminal device to execute the identity information identification method provided by the embodiment of the application.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The sequence of the embodiments of the present application is merely for description, and does not represent the advantages and disadvantages of the embodiments.
In summary, the identity information identification method is used for the terminal device, and performs feature extraction on the acquired first identity data to acquire first identity mark data; the feature extraction can be set according to actual requirements, and if the method is applied to face recognition, the features refer to face features, and the corresponding first identity mark data is face information. The terminal equipment is provided with a storage system which can be used for storing identity mark information with certain capacity, so that after the first identity mark data is obtained, the method preferentially searches whether the first identity mark data exists in the terminal equipment; if the first identity marking data exists in the terminal equipment, the terminal equipment identifies the first identity marking data obtained through retrieval, through the steps, in a peak identification use period, a network congestion phenomenon of cloud retrieval can be effectively avoided, but due to the fact that the storage capacity of the terminal equipment is limited, the situation that the first identity marking data does not exist in the terminal equipment may occur, and under the situation, the first identity marking data is sent to a cloud server, so that the cloud server retrieves according to the first identity marking data and obtains target identity marking data; by the cloud retrieval mode, the technical defect that the storage capacity of the terminal equipment is limited can be effectively overcome, and therefore the identification result is obtained based on the target identity mark data received from the cloud server. Therefore, the identity identification method is based on the acquired user identity information, the retrieval is carried out on the local storage system of the terminal equipment, the service pressure of cloud retrieval in the peak identification service period is reduced to a great extent, and the network transmission time is reduced; however, because the storage capacity of the local storage system is limited, if the user identity information is not retrieved in the local storage system, the user identity information is sent to the cloud server for supplementary retrieval, so that the steady operation of the identity recognition system is ensured, and the identity information recognition efficiency is improved.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. An identity information identification method is used for terminal equipment and comprises the following steps:
performing feature extraction on the acquired first identity data to acquire first identity mark data;
retrieving from the terminal device whether the first identity token data is present;
if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data;
and obtaining a recognition result based on the target identity mark data received from the cloud server.
2. The identity information recognition method of claim 1, wherein the retrieving from the terminal device whether the first identity token data is present comprises:
retrieving from a first white list identity information base stored in the terminal device to obtain similar identity label data;
judging whether the matching confidence value of the similar identity marking data meets a first matching confidence threshold value;
and if so, the first identity marking data exists in the terminal equipment.
3. The identity information recognition method of claim 1, wherein after obtaining the recognition result based on the target identity tag data received from the cloud server, the method further comprises:
judging whether the target identity mark data is resident identity information or not;
and if the target identity mark data is resident identity information, recording the target identity mark data into the first white list identity information base.
4. The identity information recognition method of claim 3, wherein the determining whether the target identity tag data is resident identity information comprises:
acquiring a matching confidence value of the target identity marking data;
and if the matching confidence value of the target identity marking data meets a preset second matching confidence threshold, the target identity marking data is resident identity information.
5. The identity information recognition method of claim 3, wherein the entering the target identity label data into the first white list identity information base comprises:
judging whether a first white list identity information base of the terminal equipment is full or not;
if the balance is not full, the first identity marking data is recorded into the first white list identity information base;
and if the balance is full, deleting the white list identity information which does not meet a preset sorting threshold value in the first white list identity information base, and inputting the first identity mark data into the first white list identity information base.
6. The identity information recognition method of claim 5, wherein the deleting the white list identity information in the first white list identity information base that does not meet a preset sorting threshold comprises:
sorting the use frequency of the white list identity information in the first white list identity information base by adopting an LFU algorithm; wherein the usage frequency ordering comprises usage time ordering and usage time ordering;
and deleting the white list identity information which does not meet the preset sorting threshold according to the sorted white list information.
7. An identity information identification method is used for a cloud server, and comprises the following steps:
receiving first identity data sent by terminal equipment under the condition that the first identity mark data does not exist in the terminal equipment; the first identity marking data is obtained by carrying out feature extraction on the basis of the first identity data, and the first identity data comprises electronic data record information generated when a user uses an identification terminal device;
extracting the characteristics of the first identity data to obtain second identity mark data;
retrieving whether target identity tag data corresponding to the second identity tag data exists in the cloud server or not based on the second identity tag data;
and if the target identity marking data exists in the cloud server, feeding the target identity marking data back to the terminal equipment so that the terminal equipment can obtain a recognition result according to the target identity marking data.
8. The identity information recognition method of claim 7, wherein the retrieving, based on the second identity token data, whether target identity token data corresponding to the second identity token data exists in the cloud server comprises:
retrieving from a second white list identity information base stored in the cloud server based on the second identity label data to obtain similar identity label data;
judging whether the matching confidence of the similar identity marking data meets a first matching confidence threshold value;
and if so, the target identity marking data exists in a second white list identity information base of the cloud server.
9. An identity information recognition system, comprising:
the terminal equipment is used for carrying out feature extraction on the acquired first identity data to acquire first identity mark data; the first identity data comprises electronic data record information generated when a user uses the terminal equipment; retrieving from the terminal device whether the first identity token data is present; if the first identity marking data does not exist in the terminal equipment, the first identity marking data is sent to a cloud server, so that the cloud server can retrieve according to the first identity marking data and obtain target identity marking data; obtaining a recognition result based on the target identity mark data received from the cloud server;
the cloud server is used for receiving first identity data sent by the terminal equipment under the condition that the first identity marking data do not exist in the terminal equipment; the first identity marking data is obtained by carrying out feature extraction on the basis of the first identity data, and the first identity data comprises electronic data record information generated when a user uses an identification terminal device; performing feature extraction on the first identity data to obtain second identity mark data; retrieving whether target identity tag data corresponding to the second identity tag data exists in the cloud server or not based on the second identity tag data; and if the target identity mark data exists in the cloud server, feeding the target identity mark data back to the terminal equipment so that the terminal equipment can obtain an identification result according to the target identity mark data.
10. An electronic device, characterized in that the electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the identity information identification method according to any one of claims 1-6 or claims 7-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211681566.6A CN115659305A (en) | 2022-12-27 | 2022-12-27 | Identity information identification method and system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211681566.6A CN115659305A (en) | 2022-12-27 | 2022-12-27 | Identity information identification method and system and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115659305A true CN115659305A (en) | 2023-01-31 |
Family
ID=85022284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211681566.6A Pending CN115659305A (en) | 2022-12-27 | 2022-12-27 | Identity information identification method and system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115659305A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991431A (en) * | 2020-03-03 | 2020-04-10 | 支付宝(杭州)信息技术有限公司 | Face recognition method, device, equipment and storage medium |
| CN111179017A (en) * | 2019-11-21 | 2020-05-19 | 海尔卡奥斯物联生态科技有限公司 | Customized delivery method, equipment and system based on face recognition |
| CN111340972A (en) * | 2020-03-23 | 2020-06-26 | 郑州智利信信息技术有限公司 | Attendance checking method based on voice recognition |
| CN111368622A (en) * | 2019-10-18 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Personnel identification method and device, and storage medium |
| CN111401171A (en) * | 2020-03-06 | 2020-07-10 | 咪咕文化科技有限公司 | Face image recognition method and device, electronic equipment and storage medium |
| CN111614697A (en) * | 2020-06-02 | 2020-09-01 | 支付宝(杭州)信息技术有限公司 | Method and system for identity recognition |
| CN112562843A (en) * | 2020-12-03 | 2021-03-26 | 北京软通智慧城市科技有限公司 | Epidemic situation management system, epidemic situation management method, equipment and storage medium |
| CN113014543A (en) * | 2020-12-28 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Identity recognition system, method, apparatus, computer device and storage medium |
| CN113965345A (en) * | 2021-09-08 | 2022-01-21 | 福建库克智能科技有限公司 | Identity recognition method and device, electronic equipment and storage medium |
| CN114723454A (en) * | 2021-01-06 | 2022-07-08 | 腾讯科技（深圳）有限公司 | Identity recognition method and device, electronic equipment and readable storage medium |
-
2022
- 2022-12-27 CN CN202211681566.6A patent/CN115659305A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368622A (en) * | 2019-10-18 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Personnel identification method and device, and storage medium |
| CN111179017A (en) * | 2019-11-21 | 2020-05-19 | 海尔卡奥斯物联生态科技有限公司 | Customized delivery method, equipment and system based on face recognition |
| CN110991431A (en) * | 2020-03-03 | 2020-04-10 | 支付宝(杭州)信息技术有限公司 | Face recognition method, device, equipment and storage medium |
| CN111401171A (en) * | 2020-03-06 | 2020-07-10 | 咪咕文化科技有限公司 | Face image recognition method and device, electronic equipment and storage medium |
| CN111340972A (en) * | 2020-03-23 | 2020-06-26 | 郑州智利信信息技术有限公司 | Attendance checking method based on voice recognition |
| CN111614697A (en) * | 2020-06-02 | 2020-09-01 | 支付宝(杭州)信息技术有限公司 | Method and system for identity recognition |
| CN112562843A (en) * | 2020-12-03 | 2021-03-26 | 北京软通智慧城市科技有限公司 | Epidemic situation management system, epidemic situation management method, equipment and storage medium |
| CN113014543A (en) * | 2020-12-28 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Identity recognition system, method, apparatus, computer device and storage medium |
| CN114723454A (en) * | 2021-01-06 | 2022-07-08 | 腾讯科技（深圳）有限公司 | Identity recognition method and device, electronic equipment and readable storage medium |
| CN113965345A (en) * | 2021-09-08 | 2022-01-21 | 福建库克智能科技有限公司 | Identity recognition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446816B (en) | Face recognition method and device | |
| US20160098636A1 (en) | Data processing apparatus, data processing method, and recording medium that stores computer program | |
| US7860319B2 (en) | Image management | |
| US10275355B2 (en) | Method and apparatus for cleaning files in a mobile terminal and associated mobile terminal | |
| JP5037627B2 (en) | Image identification using face recognition | |
| CN106534344B (en) | Cloud platform video processing system and application method thereof | |
| CN110472082B (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN110033018B (en) | Graph similarity judging method and device and computer readable storage medium | |
| CN103220352B (en) | Terminal, server, file storage system and file storage method | |
| CN110019891B (en) | Image storage method, image retrieval method and device | |
| US7945543B2 (en) | Method and system for deferred maintenance of database indexes | |
| US9947105B2 (en) | Information processing apparatus, recording medium, and information processing method | |
| TW201415264A (en) | Forensic system, forensic method, and forensic program | |
| CN108470071B (en) | Data processing method and device | |
| WO2007129474A1 (en) | Object recognition device, object recognition program, and image search service providing method | |
| CN110597630B (en) | Method and system for processing content resources in distributed system | |
| JP2022043631A (en) | Information processing apparatus, information processing method, and program | |
| CN111368867A (en) | Archive classification method and system and computer readable storage medium | |
| CN111125417A (en) | Data searching method and device, electronic equipment and storage medium | |
| US9036946B2 (en) | Image processing apparatus that retrieves similar images, method of controlling the same, and storage medium | |
| US8533196B2 (en) | Information processing device, processing method, computer program, and integrated circuit | |
| CN107590233A (en) | A kind of file management method and device | |
| US11544276B2 (en) | Search device, method and program recording medium | |
| KR101138873B1 (en) | Method and apparatus for reducing the number of photo in photo album | |
| CN116226681B (en) | Text similarity judging method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230131 |