CN111563127B - Implementation method for synchronizing cloud face photo to face recognition device - Google Patents
Implementation method for synchronizing cloud face photo to face recognition device Download PDFInfo
- Publication number
- CN111563127B CN111563127B CN202010400563.5A CN202010400563A CN111563127B CN 111563127 B CN111563127 B CN 111563127B CN 202010400563 A CN202010400563 A CN 202010400563A CN 111563127 B CN111563127 B CN 111563127B
- Authority
- CN
- China
- Prior art keywords
- face
- cloud
- information
- personnel
- block
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
- G06F16/278—Data partitioning, e.g. horizontal or vertical partitioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
Abstract
The invention belongs to the technical field of face recognition, and provides a method for synchronizing a cloud face photo to face recognition equipment. Meanwhile, when the device is connected to the cloud platform each time, the device needs to request the cloud end to issue the personnel summary information of all face libraries, and the device compares the personnel summary information. And if the comparison is inconsistent, the cloud end is requested to issue inconsistent personnel information, so that data compensation after the network of the equipment end is disconnected is realized, and the running state of the whole face recognition system is ensured to be free from deviation.
Description
Technical Field
The invention relates to the technical field of face recognition, in particular to a method for synchronizing a cloud face picture to face recognition equipment.
Background
The face recognition generally refers to extracting characteristic values of face images, comparing the extracted characteristic values with other face characteristic values, taking the highest comparison score, and if the highest comparison score exceeds a set threshold, considering that two faces are the same person. The human identity can be confirmed based on face recognition, for example, by using face recognition equipment (terminal), which is a piece of equipment integrating a camera, a core board of a CPU/GPU/NPU, and a display/internet access, so that a face photo can be acquired in a coordinated or uncoordinated manner, a face recognition application program is run on the face photo, and a face recognition result is output to the outside. The face recognition device needs to extract a feature value from the face base photo and store the feature value locally, snap the face photo for the person to be recognized and extract the feature value, and compare the feature value of the snap photo with the feature value of the face base photo (a feature value collection of the face base photo is called as a face database) to output a face recognition result.
The face recognition device is widely deployed in various occasions, and people hope to realize the unified management of the face recognition device, namely, the management of a face database, personnel and face photos is uniformly carried out at the cloud. And the cloud can automatically send the face database, the personnel and the face photos in the face database to the specific equipment.
Fig. 1 illustrates a conventional process of synchronizing a cloud picture to a face recognition device, which includes a first step of a system administrator creating a face database in a cloud management system; secondly, a system administrator binds the face database to the equipment in the cloud management system; and thirdly, adding personnel information including personnel numbers, names and face photos into the cloud management system by a system administrator, and associating the personnel with a face database. Fourthly, the cloud automatically issues a face database, personnel information and photo information of the face database to specific equipment; and fifthly, the face recognition equipment stores the face database, the personnel information and the face picture, extracts the characteristic value of the face picture and stores the characteristic value in an associated manner.
When the personnel information is synchronized to the equipment, the personnel information is often inconsistent with the human face database information in the cloud management system due to network failure or failure of equipment to analyze the information or failure of equipment to process the information, so that the operation result of the whole system is deviated, for example, a certain personnel information is not accurately synchronized to the human face recognition equipment, and the identity of the personnel cannot be recognized by the human face recognition equipment.
Disclosure of Invention
The invention aims to provide a method for synchronizing a cloud face photo to face recognition equipment, which can realize accurate synchronization of information of a face database, personnel and the face photo in the cloud to the face recognition equipment and realize tracking of each synchronization result in the cloud.
To achieve the above object, the present invention provides a method for synchronizing a cloud-end face picture to a face recognition device, comprising the following steps:
step 1, responding to the change of a face database of a cloud, and sending the attribute and abstract information of the face database bound by the face recognition device to the face recognition device by the cloud, and taking the attribute and abstract information as a face database information synchronization message;
step 2, the face recognition device receives the face database information synchronization message, the message receipt is sent to the cloud, if the cloud waits for the overtime of the message receipt, the face database information synchronization message is retried until the cloud receives the message receipt, and the step 3 is carried out;
step 3, the face recognition equipment compares the attribute and abstract information of the face database issued by the cloud with the attribute and abstract information stored locally, and if no difference exists or only the attribute has a difference, the face recognition equipment modifies the attribute of the face database and then sends the receipt information which is successfully synchronized and finishes synchronization to the cloud; if the difference of the summary information exists, the face recognition equipment initiates a synchronous request to the cloud end to request the summary information of all blocks of all face databases;
step 4, the cloud end issues corresponding summary information according to the block number requested by the face recognition equipment, wherein the message content of the summary information comprises a face database unique identifier face _ token, a block number and a block summary value;
step 5, the face recognition device compares the local summary information with the summary information issued by the cloud, the face recognition device requests the blocks of the face database with different summary values from the cloud, and the content of the request message comprises: the face database uniquely identifies the face _ token, the block granularity, the block starting position and the block ending position;
step 6, the cloud sends a corresponding block according to the block number requested by the face recognition device, the message content comprises a face database unique identifier face _ token, a block number and block information, and the block information comprises grouped personnel information and a collection thereof;
and 7, the face recognition equipment performs personnel modification operation on the local side according to the received block information to perform face data synchronization, and reports a synchronization result to the cloud.
Further, in the process of synchronizing the face data by the face recognition device, the method includes:
the face recognition device initiates a plurality of synchronous requests in batches according to the actual capacity of a face database at the cloud end, and each synchronous request reports a synchronous result.
Further, the method further comprises:
and the cloud end records the synchronization result every time, and sends an alarm notice to a system administrator if the result is abnormal.
Further, the summary information includes human summary information of 1, 16, 16 × 16 granularities, wherein:
the digest granularity is 1, that is, the MD5 values after all people under one face database are arranged from small to large according to personnd, wherein personnd represents the number of people in the face database;
if the granularity is 16, dividing the personnel into 16 groups, arranging the personnel in each group from small to large according to personId, then taking MD5 values, wherein the personnel summary information comprises 16 MD5 values, and the grouping mode is that the personnel are divided into groups 0 to F according to the last four digits of personId;
the granularity is 16 × 16, then the personnel are divided into 16 × 16 groups, the personnel in each group are arranged from small to large according to personnd, then the MD5 values are taken, the personnel summary information comprises 16 × 16 MD5 values, and the grouping mode is that the personnel are divided into groups 00 to FF according to the fourth last place of the personnd from 00 to FF;
wherein each group is taken as a block, i.e. the grouped people information and its collection.
Further, in the step 3, the message content of the synchronization request includes:
the face database comprises a unique identifier face _ token, a block granularity, a block starting position and a block ending position, wherein when the block granularity is 16, the values of the block starting position and the block ending position are 0-F; and when the block granularity is 16 x 16, the values of the starting position and the ending position of the block are 00-FF.
It should be understood that all combinations of the foregoing concepts and additional concepts described in greater detail below can be considered as part of the inventive subject matter of this disclosure unless such concepts are mutually inconsistent. In addition, all combinations of claimed subject matter are considered a part of the presently disclosed subject matter.
The foregoing and other aspects, embodiments and features of the present teachings can be more fully understood from the following description taken in conjunction with the accompanying drawings. Additional aspects of the present invention, such as features and/or advantages of exemplary embodiments, will be apparent from the description which follows, or may be learned by practice of specific embodiments in accordance with the teachings of the present invention.
Drawings
The drawings are not intended to be drawn to scale. In the drawings, each identical or nearly identical component that is illustrated in various figures may be represented by a like numeral. For purposes of clarity, not every component may be labeled in every drawing. Embodiments of various aspects of the present invention will now be described, by way of example, with reference to the accompanying drawings, in which:
fig. 1 is a schematic diagram of a face recognition device and a far-end face picture synchronization in the prior art.
Fig. 2 is a timing diagram illustrating exemplary processing of cloud-based face photos synchronized to a face recognition device in accordance with the present invention.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
In this disclosure, aspects of the present invention are described with reference to the accompanying drawings, in which a number of illustrative embodiments are shown. Embodiments of the present disclosure are not necessarily intended to include all aspects of the invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in greater detail below, may be implemented in any of numerous ways, as the disclosed concepts and embodiments are not limited to any one implementation. In addition, some aspects of the present disclosure may be used alone, or in any suitable combination with other aspects of the present disclosure.
With reference to fig. 2, an implementation method for synchronizing a cloud-side face photo to a face recognition device according to an exemplary embodiment of the present invention includes the following steps:
step 1, responding to the change of a face database of a cloud, and sending the attribute and abstract information of the face database bound by the face recognition device to the face recognition device by the cloud, and taking the attribute and abstract information as a face database information synchronization message;
step 2, the face recognition device receives the face database information synchronization message, the message receipt is sent to the cloud, if the cloud waits for the overtime of the message receipt, the face database information synchronization message is retried until the cloud receives the message receipt, and the step 3 is carried out;
step 3, the face recognition equipment compares the attribute and abstract information of the face database issued by the cloud with the attribute and abstract information stored locally, and if no difference exists or only the attribute has a difference, the face recognition equipment modifies the attribute of the face database and then sends the receipt information which is successfully synchronized and finishes synchronization to the cloud; if the difference of the summary information exists, the face recognition equipment initiates a synchronous request to the cloud end to request the summary information of all blocks of all face databases;
step 4, the cloud end issues corresponding summary information according to the block number requested by the face recognition equipment, wherein the message content of the summary information comprises a face database unique identifier face _ token, a block number and a block summary value;
step 5, the face recognition device compares the local summary information with the summary information issued by the cloud, the face recognition device requests the blocks of the face database with different summary values from the cloud, and the content of the request message comprises: the face database uniquely identifies the face _ token, the block granularity, the block starting position and the block ending position;
step 6, the cloud sends a corresponding block according to the block number requested by the face recognition device, the message content comprises a face database unique identifier face _ token, a block number and block information, and the block information comprises grouped personnel information and a collection thereof;
and 7, the face recognition equipment performs personnel modification operation on the local side according to the received block information to perform face data synchronization, and reports a synchronization result to the cloud.
Preferably, in the process of synchronizing the face data by the face recognition device, the method includes:
the face recognition device initiates a plurality of synchronous requests in batches according to the actual capacity of a face database at the cloud end, and each synchronous request reports a synchronous result.
Preferably, the method further comprises:
and the cloud end records the synchronization result every time, and sends an alarm notice to a system administrator if the result is abnormal.
Thus, a complete face library information synchronization operation is completed.
Preferably, the changing of the face database in the cloud includes:
the attribute change of the face database comprises at least one change of a unique identifier of the face database, a name of the face database, a face comparison threshold, a priority of the face database, capacity of the face database and personnel information under the face database; and
and the personnel information changes comprise changes of at least one of unique identification of personnel, personnel number, personnel name and face photo.
Preferably, the summary information includes human summary information of 1, 16, 16 × 16 granularities, wherein:
the digest granularity is 1, that is, the MD5 values after all people under one face database are arranged from small to large according to personnd, wherein personnd represents the number of people in the face database;
if the granularity is 16, dividing the personnel into 16 groups, arranging the personnel in each group from small to large according to personnd, then taking MD5 values, wherein the personnel summary information comprises 16 MD5 values, and dividing the personnel into groups from 0 to F according to the fourth last digit of the personnd;
the granularity is 16 × 16, then the personnel are divided into 16 × 16 groups, the personnel in each group are arranged from small to large according to personnd, then the MD5 values are taken, the personnel summary information comprises 16 × 16 MD5 values, and the grouping mode is that the personnel are divided into groups 00 to FF according to the fourth last place of the personnd from 00 to FF;
wherein each group is taken as a block, i.e. the grouped people information and its collection.
Preferably, in the step 3, the message content of the synchronization request includes:
the face database comprises a unique identifier face _ token, a block granularity, a block starting position and a block ending position, wherein when the block granularity is 16, the values of the block starting position and the block ending position are 0-F; and when the block granularity is 16 x 16, the values of the starting position and the ending position of the block are 00-FF.
In an exemplary embodiment, the data synchronized by the data synchronization scheme provided by the present invention includes information of a face database in a cloud and information of people under the face database. The information of the face database comprises a face database unique identifier face _ token, a face database name, a face database comparison threshold (the face database comparison threshold refers to a threshold used when a feature value of a face snapshot is compared with a feature value in the face database, if the comparison score exceeds the threshold, the comparison is considered to be successful), a face database priority (the face database priority refers to the sequence of comparison of a plurality of face databases), and a face database capacity (the face database capacity refers to the number of face photos most contained in the face database). The personnel information under the face database comprises a personnel unique identification, a personnel number, a personnel name and a face photo. In an alternative, the number of photos associated with a person is set to, for example, not more than 3.
In the data synchronization process, the cloud (for example, a management system of the cloud) and the face recognition device agree on the summary information of the personnel information in each face database, and the face recognition device judges whether the personnel information of the device side is consistent with the cloud personnel information or not by comparing the summary information of the personnel information.
For example, the cloud has a face database a bound to the device X. There are person 1, personnel 2 under the database A of the human face, then the complete personnel information under the database A of the human face is:
personId1,personName1,facetoken11,facetoken12;personId2,personName2,,facetoken21,facetoken22
personId1 is the person number of person 1, personName1 is the name of person 1, factoken11, factoken12 are two photographs of the face of person 1, personId2 is the person number of person 2, personName2 is the name of person 2, factokee 21, and factoken22 are two photographs of the face of person 2.
The person summary information supports summary information of different granularities. The particle size includes 1, 16, and so on.
If the granularity is 1, the person summary information is the MD5 values of all the persons arranged from small to large according to personnd;
and if the granularity is 16, dividing the personnel into 16 groups, arranging the personnel in each group from small to large according to personnd, then taking MD5 values, wherein the personnel summary information comprises 16 MD5 values, and dividing the personnel into groups from 0 to F according to the fourth last digit of the personnd.
The granularity is 16 × 16, then the people are divided into 16 × 16 groups, the people in each group are arranged from small to large according to personnd, then the MD5 values are taken, the people summary information comprises 16 × 16 MD5 values, and the grouping rule is that the people are divided into groups 00 to FF according to the fourth last digit of the personnd; and so on. In this invention, we refer to each group as a block.
Therefore, in the process of realizing synchronization, when the face database data at the cloud end changes, the change of the face database data comprises the addition and deletion of the face database information, the addition and deletion of the personnel information and the addition and deletion of the face photos, namely, a data change notice is sent to the face recognition equipment, the equipment judges whether the local personnel information of the equipment is consistent with the personnel information abstract issued by the cloud end by comparing the local personnel information abstract with the personnel information abstract issued by the cloud end, and if the local personnel information of the equipment is not consistent with the cloud end, the local personnel information is requested to the cloud end to carry out local personnel information updating.
Meanwhile, the device is required to realize a data compensation scheme, and when cloud data is changed, the device may be in a disconnected state, so that when the device is connected to a cloud platform every time, the device needs to request the cloud to issue the personnel summary information of all face libraries, and the device compares the personnel summary information. And if the comparison is inconsistent, the cloud end is requested to issue inconsistent personnel information.
Exemplary implementations of the present invention are more particularly shown below in conjunction with specific examples.
Firstly, a cloud face database (a face database for short) is changed, wherein the attribute change comprises face database unique identification face _ token, face database name, face database comparison threshold, face database priority and face database capacity; personnel information under the face database changes, and the personnel information changes and comprises a personnel unique identifier, a personnel number, a personnel name and a face photo. The cloud sends the attribute of the face library bound by the equipment and the abstract information of the personnel to the equipment (the abstract granularity is 1, namely the MD5 value of all personnel in the face database after being arranged from small to large according to personnd); this message is called a face bank information synchronization message.
The message content comprises: the face database unique identifier face _ token, the face database name, the face comparison threshold, the face database priority, the face database capacity, the face database actual capacity, and the face database summary information (i.e., the MD5 value).
And secondly, the face recognition equipment receives the face library information synchronization message and performs message receipt. And if the cloud end waits for the message receipt to be overtime, retrying the face library information synchronization message until the message receipt is received.
And thirdly, the equipment compares the attributes and the abstracts of all the face libraries issued by the cloud with the attributes and the abstracts of the face libraries stored locally.
And fourthly, if no difference exists or only the face library attribute difference exists, the equipment directly modifies the face library attribute and then sends information of 'synchronization success and synchronization end' to the cloud. For summary differences, the device needs to send a synchronization request to the cloud (request summaries of all blocks of all face libraries, and the granularity and number of blocks of one request are determined by the device according to the number of people in the face libraries).
The message content comprises: the face database uniquely identifies the face _ token, the block granularity (including 16, 16 × 16, …), the block starting position and the block ending position (when the block granularity is 16, the values of the block starting position and the block ending position are 0-F; and when the block granularity is 16 × 16, the values of the block starting position and the block ending position are 00-FF).
Fifthly, the cloud sends the summary information of the block requested by the equipment; the message content comprises: the face database uniquely identifies the face _ token, the block number, and the block digest value (i.e., the MD5 value).
And sixthly, the equipment compares the local abstract information with the abstract information issued by the cloud, the equipment requests blocks (namely grouped personnel information and collections) of the face library with different abstract values from the cloud, and the block granularity is determined by the equipment.
The message content comprises: the face database uniquely identifies the face _ token, the block granularity, the block starting position and the block ending position.
And seventhly, the cloud end issues the corresponding block according to the block number requested by the equipment. The message content comprises: face database unique identifier face _ token, block number and block information
The block information refers to a collection of grouped personnel information, and the format is as follows:
personId1,personName1,facetoken11,facetoken12;personId2,personName2,,facetoken21,facetoken22。
and eighthly, adding/deleting/modifying personnel locally by the equipment. Reporting the synchronization result to the cloud
And ninthly, the equipment can initiate a plurality of synchronous requests in batches according to the actual capacity of the face library, and each synchronous request needs to report a corresponding synchronous result.
And step ten, the cloud end records the synchronization result, and if the result is abnormal, an alarm notice is sent to a system administrator.
Thus, a complete face library information synchronization operation is completed.
With the technical scheme, the cloud face database data synchronization to the face recognition device is realized by the face data synchronization of the cloud and the local end (face recognition terminal). When the face database data at the cloud end are changed, the face database data change comprises the addition and deletion of face database information, the addition and deletion of personnel information and the addition and deletion of a face photo, namely, a data change notice is sent to equipment, the equipment judges whether the local personnel information of the equipment is consistent with the cloud end by comparing whether the local personnel information abstract is consistent with the personnel information abstract sent by the cloud end, and if the local personnel information is inconsistent with the local personnel information abstract, the equipment requests the cloud end for different personnel information to update the local personnel information;
when the cloud data is changed, the device may be in a disconnected state, and when the device is connected to the cloud platform each time, the device needs to request the cloud to issue the personnel summary information of all the face libraries, and the device performs personnel summary information comparison. And if the comparison is inconsistent, the cloud end is requested to issue inconsistent personnel information, so that data compensation after the network of the equipment end is disconnected is realized, and the running state of the whole face recognition system is ensured to be free from deviation.
Meanwhile, a data tracking scheme is realized based on the scheme of the invention, namely, each time a request message is issued by the cloud, the device needs to report a processing result to the cloud, and the cloud records the processing result, so that the cloud can realize result tracking of each time of data synchronization, and alarm is given when the result is abnormal, so as to inform system operation and maintenance personnel to investigate the abnormality. Thereby ensuring the non-deviation operation of the whole system.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be defined by the appended claims.
Claims (7)
1. A realization method for synchronizing a cloud face photo to face recognition equipment is characterized by comprising the following steps:
step 1, responding to the change of a face database at the cloud, and sending the attribute and abstract information of the face database bound by the face recognition device to the face recognition device by the cloud, and taking the attribute and abstract information as a face database information synchronization message;
step 2, the face recognition device receives the face database information synchronization message, sends a message receipt to the cloud, retries the face database information synchronization message if the cloud waits for the message receipt to be overtime, and enters step 3 until the cloud receives the message receipt;
step 3, the attribute and abstract information of the face database issued by the cloud are compared with the locally stored attribute and abstract information by the face recognition equipment, and if no difference exists or only the attribute has a difference, the face recognition equipment modifies the attribute of the face database and then sends the receipt information which is successfully synchronized and is synchronized to the cloud; if the difference of the summary information exists, the face recognition equipment initiates a synchronous request to the cloud end to request the summary information of all blocks of all face databases;
step 4, the cloud end issues corresponding summary information according to the block number requested by the face recognition equipment, wherein the message content of the summary information comprises a face database unique identifier face _ token, a block number and a block summary value;
step 5, the face recognition device compares the local summary information with the summary information issued by the cloud, the face recognition device requests the blocks of the face database with different summary values from the cloud, and the content of the request message comprises: the face database uniquely identifies the face _ token, the block granularity, the block starting position and the block ending position;
step 6, the cloud sends a corresponding block according to the block number requested by the face recognition device, the message content comprises a face database unique identifier face _ token, a block number and block information, and the block information comprises grouped personnel information and a collection thereof;
and 7, the face recognition equipment performs personnel modification operation on the local side according to the received block information to perform face data synchronization, and reports a synchronization result to the cloud.
2. The method for synchronizing the cloud-based face photos to the face recognition device according to claim 1, wherein the face data synchronization process performed by the face recognition device comprises:
the face recognition device initiates a plurality of synchronous requests in batches according to the actual capacity of a face database at the cloud end, and each synchronous request reports a synchronous result.
3. The method of claim 1 or 2, wherein the method further comprises:
and the cloud end records the synchronization result every time, and sends an alarm notice to a system administrator if the result is abnormal.
4. The method of claim 1, wherein the step of synchronizing the cloud-based face photos to the face recognition device comprises:
the attribute change of the face database comprises at least one change of a unique identifier of the face database, a name of the face database, a face comparison threshold, a priority of the face database, capacity of the face database and personnel information under the face database; and
and the personnel information changes comprise changes of at least one of unique identification of personnel, personnel number, personnel name and face photo.
5. The method of claim 1 or 4, wherein the summary information includes person summary information of 1, 16, 16 × 16 granularities, and wherein:
the digest granularity is 1, that is, the MD5 values after all people under one face database are arranged from small to large according to personnd, wherein personnd represents the number of people in the face database;
if the granularity is 16, dividing the personnel into 16 groups, arranging the personnel in each group from small to large according to personnd, then taking MD5 values, wherein the personnel summary information comprises 16 MD5 values, and dividing the personnel into groups from 0 to F according to the fourth last digit of the personnd;
the granularity is 16 × 16, then the personnel are divided into 16 × 16 groups, the personnel in each group are arranged from small to large according to personnd, then the MD5 values are taken, the personnel summary information comprises 16 × 16 MD5 values, and the grouping mode is that the personnel are divided into groups 00 to FF according to the fourth last place of the personnd from 00 to FF;
wherein each group is treated as a block.
6. The method of claim 5, wherein in step 3, the message content of the synchronization request includes:
the face database comprises a unique identifier face _ token, a block granularity, a block starting position and a block ending position, wherein when the block granularity is 16, the values of the block starting position and the block ending position are 0-F; and when the block granularity is 16 x 16, the values of the starting position and the ending position of the block are 00-FF.
7. The method of claim 6, wherein the granularity and the number of blocks of each synchronization request are determined by the face recognition device according to the number of people in the face database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010400563.5A CN111563127B (en) | 2020-05-13 | 2020-05-13 | Implementation method for synchronizing cloud face photo to face recognition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010400563.5A CN111563127B (en) | 2020-05-13 | 2020-05-13 | Implementation method for synchronizing cloud face photo to face recognition device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111563127A CN111563127A (en) | 2020-08-21 |
| CN111563127B true CN111563127B (en) | 2022-08-16 |
Family
ID=72073452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010400563.5A Active CN111563127B (en) | 2020-05-13 | 2020-05-13 | Implementation method for synchronizing cloud face photo to face recognition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111563127B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112084355A (en) * | 2020-09-14 | 2020-12-15 | 重庆农村商业银行股份有限公司 | Face sub-library updating method, device, equipment and storage medium |
| CN115188114B (en) * | 2022-07-01 | 2023-09-01 | 日立楼宇技术（广州）有限公司 | Access control information synchronization method, device, equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876975A (en) * | 2017-07-06 | 2018-11-23 | 北京旷视科技有限公司 | Personnel management system and method based on recognition of face |
| CN110826593B (en) * | 2019-09-29 | 2021-02-05 | 腾讯科技（深圳）有限公司 | Training method for fusion image processing model, image processing method and device |
-
2020
- 2020-05-13 CN CN202010400563.5A patent/CN111563127B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111563127A (en) | 2020-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111209346B (en) | Block chain data archiving method and device and computer readable storage medium | |
| CN110569311B (en) | Data synchronization method and device for database and computer storage medium | |
| CN108228814B (en) | Data synchronization method and device | |
| CN111563127B (en) | Implementation method for synchronizing cloud face photo to face recognition device | |
| US7127475B2 (en) | Managing data integrity | |
| CN109376160B (en) | Data synchronization method, device, computer equipment and storage medium | |
| CN101313495B (en) | Method, system and apparatus for data synchronization | |
| US11880386B1 (en) | Method and system for using before images of replicated changes from a source database with current target database images read from the target database when continuously comparing two databases which are actively being kept synchronized | |
| US20040034699A1 (en) | Managing data integrity using a filter condition | |
| CN111708794B (en) | Data comparison method and device based on big data platform and computer equipment | |
| CN109255056B (en) | Data reference processing method, device, equipment and storage medium of block chain | |
| CN106302806A (en) | A kind of method of data synchronization, system, synchronous obtaining method and relevant apparatus | |
| US20220171754A1 (en) | Method for indexing data in storage engine and related apparatus | |
| CN111625540A (en) | Method and device for verifying data synchronization integrity of relational database | |
| CN113961393A (en) | Real-time database measuring point deletion recovery method, system, storage medium and server | |
| TW202013226A (en) | Webpage content self-protection method and associated server | |
| WO2022242372A1 (en) | Object processing method and apparatus, computer device, and storage medium | |
| CN115481417A (en) | Method for data snapshot, filing and complete recovery of uplink scheme based on chain | |
| CN110321246A (en) | A kind of fault handling method and device | |
| CN114595288A (en) | SQL command level-based multi-IDC distributed system data synchronization method | |
| CN116821232A (en) | Data synchronization method and related device | |
| WO2021207831A1 (en) | Method and systems for indexing databases on a contextual basis | |
| CN113342579A (en) | Data restoration method and device | |
| CN112650733A (en) | Intelligent contract state data processing method, system and device | |
| CN114442947B (en) | Cross-domain bucket deleting method, system, terminal 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No.568 longmian Avenue, gaoxinyuan, Jiangning District, Nanjing City, Jiangsu Province, 211000 Patentee after: Xiaoshi Technology (Jiangsu) Co.,Ltd. Address before: No.568 longmian Avenue, gaoxinyuan, Jiangning District, Nanjing City, Jiangsu Province, 211000 Patentee before: NANJING ZHENSHI INTELLIGENT TECHNOLOGY Co.,Ltd. |