CN112307120A

CN112307120A - Information management server, information management method, and information management system

Info

Publication number: CN112307120A
Application number: CN202011178919.1A
Authority: CN
Inventors: 赵乾
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-10-29
Filing date: 2020-10-29
Publication date: 2021-02-02

Abstract

The present disclosure provides an information management server, an information management method, and an information management system; relates to the technical field of block chains. The information management server includes: the characteristic extraction module is used for carrying out flow analysis processing on video stream data acquired by edge network equipment in real time and extracting current human face characteristic data in the video stream data; the feature matching module is used for matching the current face feature data extracted by the feature extraction module with historical face feature data stored in a block chain network based on a pre-trained face recognition model; and the matching result response module is used for responding the matching result in the characteristic matching module and executing corresponding information management operation on the current face characteristic data. The community information management system can efficiently and low-delay information management on personnel entering and exiting a community, and especially guarantees safety of workers and accuracy of information in an epidemic situation prevention and control scene.

Description

Information management server, information management method, and information management system

Technical Field

The present disclosure relates to the field of block chain technology, and in particular, to an information management server, an information management method, and an information management system.

Background

With the rapid development of internet technology, the Blockchain technology (Blockchain) is more and more widely concerned by people. The block chain network is essentially a distributed shared account book and a database, and has the characteristics of decentralization, no tampering, trace retaining in the whole process, traceability, collective maintenance, openness and transparency and the like.

At present, in a related information management scheme, information registration needs to be performed on people who enter and exit a community in most scenes in a manual mode, but the efficiency is low and the accuracy is poor in the manual mode, and in most cases, information registration cannot be completed due to various factors, and the activity track of people is difficult to trace back.

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure is directed to an information management method, an information management apparatus, an electronic device, and a computer-readable storage medium, which overcome the problems of low efficiency, poor accuracy, and difficulty in tracing an activity track of a person when managing information of the person who enters or exits a community, which are caused by limitations and defects of related art to some extent.

According to a first aspect of the present disclosure, there is provided an information management server for edge computing, comprising:

the characteristic extraction module is used for carrying out flow analysis processing on video stream data acquired by edge network equipment in real time and extracting current human face characteristic data in the video stream data;

the feature matching module is used for matching the current face feature data extracted by the feature extraction module with historical face feature data stored in a block chain network based on a pre-trained face recognition model;

and the matching result response module is used for responding the matching result in the characteristic matching module and executing corresponding information management operation on the current face characteristic data.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the matching result response module further includes a matching success response unit, where the matching success response unit is configured to:

acquiring position information of the edge network equipment corresponding to the collected current face feature data in response to the matching result being larger than a preset matching threshold;

and associating the position information with the current face feature data, and uploading the position information to the block chain network to realize the recording operation of the current moving track of the current face feature data.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the matching result response module further includes a matching failure response unit, where the matching failure response unit is configured to:

and responding to the matching result smaller than or equal to the matching threshold value, and storing the current face feature data serving as new historical face feature data into the block chain network so as to register the current face feature data.

In an exemplary embodiment of the disclosure, based on the foregoing solution, the matching result response module is further configured to:

acquiring a historical movement track corresponding to the current face feature data from the block chain network;

determining the pass grade of the current face feature data according to the historical movement track;

and executing corresponding information management operation on the current face feature data by combining the matching result and the pass grade.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the traffic level includes a level to be isolated, a high and medium risk level, or a low risk level;

the matching result response module further comprises an isolation notification unit, and the isolation notification unit is used for:

and executing an alarm operation in response to the matching result being larger than a preset matching threshold and the pass grade being a grade to be isolated.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the feature extraction module includes:

the video stream acquisition unit is used for carrying out serialization processing on video stream data acquired by the edge network equipment in real time to obtain video frame data;

the video data buffering unit is used for buffering the video frame data generated in the video stream acquisition unit in a fault-tolerant data queue;

and the video stream processing unit is used for consuming the video frame data in the fault-tolerant data queue of the video data buffering unit so as to extract the current human face feature data in the video frame data.

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the feature matching module further includes a face recognition model obtaining unit, where the face recognition model obtaining unit is configured to:

acquiring a pre-constructed face recognition model, and performing training verification processing on the pre-constructed face recognition model through the collected historical face feature data to obtain the face recognition model after training verification; or

And acquiring the face recognition model which is trained and verified based on the historical face feature data from a cloud platform connected with a network.

According to a second aspect of the present disclosure, there is provided an edge-computing-based information management method applied to an information management server for edge computing, including:

carrying out flow analysis processing on video flow data acquired in real time, and extracting current face feature data in the video flow data;

matching the extracted current face feature data with historical face feature data stored in a block chain network based on a pre-trained face recognition model;

and responding to the matching result, and executing corresponding information management operation on the current face feature data.

In an exemplary embodiment of the present disclosure, based on the foregoing solution, the information management operation includes a recording operation, and the performing, in response to the matching result, a corresponding information management operation on the current facial feature data includes:

In an exemplary embodiment of the present disclosure, based on the foregoing solution, the information management operation includes a registration operation, and the performing, in response to the matching result, a corresponding information management operation on the current facial feature data includes:

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the performing, in response to the matching result, a corresponding information management operation on the current facial feature data further includes:

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, the information management operation includes an alarm operation, and the traffic level includes a to-be-isolated level, a high-medium risk level, or a low-risk level;

and executing corresponding information management operation on the current face feature data by combining the matching result and the pass grade, wherein the corresponding information management operation comprises the following steps:

In an exemplary embodiment of the present disclosure, based on the foregoing scheme, performing stream analysis processing on video stream data acquired in real time, and extracting current face feature data in the video stream data includes:

carrying out serialization processing on the video stream data acquired in real time to obtain video frame data;

buffering the video frame data in a fault-tolerant data queue;

and performing consumption processing on the video frame data in the fault-tolerant data queue to extract current human face feature data in the video frame data.

In an exemplary embodiment of the present disclosure, based on the foregoing solution, before matching the extracted current face feature data with historical face feature data stored in a blockchain network based on a pre-trained face recognition model, the method further includes:

According to a third aspect of the present disclosure, there is provided an information management system based on edge calculation, including:

the edge network equipment is used for acquiring video stream data in real time;

the information management servers are in communication connection with the edge network equipment and are used for executing corresponding information management operation on the current face feature data in the video stream data;

the data are stored among the information management servers based on the block chain technology, and the data sharing function and the track tracing function are realized based on the established block chain network.

According to a fourth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of the above.

Exemplary embodiments of the present disclosure may have some or all of the following benefits:

in an information management method provided by an example embodiment of the present disclosure, stream analysis processing is performed on video stream data acquired in real time, and current face feature data in the video stream data is extracted; matching the extracted current face feature data with historical face feature data stored in a block chain network based on a pre-trained face recognition model; and responding to the matching result, and executing corresponding information management operation on the current face feature data. On one hand, video stream data corresponding to community personnel is obtained based on edge network equipment, current face feature data in the video stream data are matched according to a face recognition model, the face feature data of the community personnel can be automatically and rapidly obtained, the personnel information obtaining efficiency is effectively improved, the personnel information recognition efficiency is effectively improved through the face recognition model matching data based on a deep learning model, and meanwhile the matching accuracy of the obtained data is guaranteed; on the other hand, historical face feature data are stored through the block chain network, and the current face feature data are matched with the historical face feature data stored in the block chain network, so that the accuracy of the data is further ensured, the safety of the data is improved, and all the face feature data can be traced; on the other hand, the information management of each community is realized through the edge computing server, the data processing delay is reduced, and the data processing efficiency is effectively improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.

FIG. 1 schematically shows a flow diagram of an information management method according to one embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow diagram for extracting current facial feature data based on a flow analysis technique according to one embodiment of the present disclosure;

FIG. 3 schematically shows a flow diagram for performing information management operations according to one embodiment of the present disclosure;

FIG. 4 schematically shows a schematic block diagram of an information management server according to one embodiment of the present disclosure;

FIG. 5 schematically shows a schematic block diagram of a feature extraction module in an information management server according to one embodiment of the present disclosure;

FIG. 6 schematically shows a schematic block diagram of a feature matching module in an information management server according to one embodiment of the present disclosure;

fig. 7 schematically shows a schematic block diagram of a matching result response module in the information management server according to one embodiment of the present disclosure;

FIG. 8 schematically shows a schematic block diagram of an information management server system overall architecture according to one embodiment of the present disclosure;

FIG. 9 schematically shows a schematic diagram of data streaming in an information management server according to one embodiment of the present disclosure;

FIG. 10 schematically illustrates an application diagram for information management of people within a community, according to one embodiment of the present disclosure;

FIG. 11 schematically illustrates an application diagram for information management of people outside of a community, according to one embodiment of the present disclosure;

FIG. 12 schematically shows a structural diagram of an information management system according to one embodiment of the present disclosure;

FIG. 13 schematically illustrates an architecture diagram of an information management system implemented based on blockchain techniques according to one embodiment of the present disclosure;

fig. 14 schematically shows a schematic diagram of a tile structure according to one embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The technical solution of the embodiment of the present disclosure is explained in detail below:

the inventor finds that in most scenes needing statistical management of personnel information, such as scenes of community epidemic prevention and control, more problems still exist, such as the following problems mainly exist:

in terms of a person registration system, there are currently various methods for person registration, for example, two-dimensional code registration, applet registration, manual registration, and the like. However, these methods inevitably require manual intervention and may require human contact, which greatly increases the difficulty of community epidemic prevention and control and also increases the danger of workers.

In the aspect of monitoring isolated people, there are various modes for monitoring isolated people at present, for example, there are modes of pasting an isolation strip on a house doorway, regularly checking the condition of people, wearing special positioning equipment for isolated people, and the like. However, these methods cannot ensure the real activity of the isolated population, and not only the statistical information is inaccurate (positioning may be inaccurate, and the possibility of damage to the isolation bars is high), but also manual intervention is still required.

In the aspect of tracing the activity track of the person, the tracing of the activity track of the person is relatively complex at present, and most operators perform base station tracing or report the situation by parties. However, errors may occur in the data obtained by tracing, for example, the data obtained by tracing is not accurate when the mobile phone is not used and the party forgets the historical track.

In the aspect of detecting strangers, when judging whether the foreign person is the community person, the traditional mode is realized by identity card comparison or community registration and the like. However, the results obtained by these methods are not accurate, and all the results need to be judged by a manual method, so that the accuracy is poor.

The inventors have also discovered that Edge Computing (Edge Computing) is an open platform that provides core capabilities of Computing, storage, network, etc., on the Edge side of the network near the data source. Compared with a common host, the edge computing server supports distributed deployment and has the following three capabilities: data of the edges, intelligent operation capability and executable decision feedback are collected.

The edge computing is different from the cloud computing in that the edge computing adopts a distributed computing architecture, the computing is dispersed in near-end equipment close to a data source for processing, instead of returning all data to a cloud for processing, and the edge computing has the characteristics of good real-time performance, high efficiency, short delay and the like, and can provide computing capability under the condition of no network or poor network.

In view of one or more of the above problems, the present example embodiment provides an information management method. The information management method may be applied to an information management server for edge calculation, and may also be applied to a terminal device based on a block chain technique. Referring to fig. 1, the information management method may include the following steps S110 to S130:

step S110, performing stream analysis processing on video stream data acquired by edge network equipment in real time, and extracting current face feature data in the video stream data.

And step S120, matching the extracted current face feature data with historical face feature data stored in a block chain network based on a pre-trained face recognition model.

And S130, responding to the matching result, and executing corresponding information management operation on the current face feature data.

In the information management method provided by the exemplary embodiment, on one hand, video stream data corresponding to community people is obtained based on edge network equipment, and current face feature data in the video stream data is matched according to a face recognition model, so that the face feature data of the community people can be automatically and rapidly obtained, the obtaining efficiency of personnel information is effectively improved, the recognition efficiency of the personnel information is effectively improved through the face recognition model matching data based on a deep learning model, and meanwhile, the matching accuracy of the obtained data is ensured; on the other hand, historical face feature data are stored through the block chain network, and the current face feature data are matched with the historical face feature data stored in the block chain network, so that the accuracy of the data is further ensured, the safety of the data is improved, and all the face feature data can be traced; on the other hand, the information management of each community is realized through the edge computing server, the data processing delay is reduced, and the data processing efficiency is effectively improved.

The above steps of the present exemplary embodiment will be described in more detail below.

In step S110, a stream analysis process is performed on video stream data acquired by the edge network device in real time, and current face feature data in the video stream data is extracted.

In an exemplary embodiment of The present disclosure, The video stream data may be data collected in real time by an edge network device with image collection capability, for example, The edge network device may be a monitoring camera at a doorway of a community, The video stream data may be video data shot by The monitoring camera at The doorway of The community, The edge network device may also be a face verification device at The doorway of The community, The video stream data may be video data shot by The face verification device at The doorway of The community, The edge network device may also be an image collection unit on an epidemic situation epidemic prevention vehicle which is continuously moving, The video stream data may be video data collected by The image collection unit on The epidemic situation prevention vehicle, of course, The edge network device may also be another Internet of Things (The of Internet Things, IOT) device, the video stream data may be video data collected by the edge network device, which is not limited in this example embodiment.

The current face feature data may be data of facial image features of a person object included in video stream data acquired in real time, and the current face feature data may be used to match historical face feature data stored in the blockchain network to determine unique identification information corresponding to the person object, or may be used to associate and store the unique identification information corresponding to the person object in the blockchain network.

In step S120, the extracted current face feature data is matched with historical face feature data stored in a blockchain network based on a pre-trained face recognition model.

In an example embodiment of the present disclosure, the face recognition model may refer to a deep learning model for recognizing (matching) a face, for example, the face recognition model may be a convolutional neural network model, a random forest model, a support vector machine model, or other deep learning models capable of recognizing (matching) a face, which is not particularly limited in this example embodiment.

The historical face feature data can be historically acquired data used for recording feature data of a person object and data which can be related to unique identification information of the person object, and the historical face feature data can be used for matching with the current face feature data to determine the unique identification data of the current face feature data or trace back a historical movement track corresponding to the current face feature data.

In step S130, corresponding information management operations are performed on the current facial feature data in response to the matching result.

In an example embodiment of the present disclosure, the matching result may be data obtained by performing matching recognition on the current face feature data and the historical face feature data through a face recognition model, for example, the matching result may be a recognition confidence corresponding to the current face feature data and the historical face feature data, or may be a numerical value that determines whether the current face feature data matches (0) or does not match (1) with the historical face feature data, which is not specifically limited in this example embodiment.

The information management operation may be a trigger operation that is set by a conditional trigger application and is triggered under a certain condition, for example, the information management operation may be a registration operation that stores current face feature data in a block chain network when the current face feature data is not matched with corresponding historical face feature data, or may be an inquiry operation that traces back a historical movement trajectory of the current face feature data when the current face feature data is matched with corresponding historical face feature data, or of course, may be other automatically-triggered information management operations, which is not particularly limited in this exemplary embodiment.

In an example embodiment of the present disclosure, the current facial feature data may be extracted from the video stream data acquired in real time through the steps in fig. 2:

referring to fig. 2, in step S210, performing serialization processing on the video stream data collected in real time to obtain video frame data;

step S220, buffering the video frame data in a fault-tolerant data queue;

step S230, performing consumption processing on the video frame data in the fault-tolerant data queue to extract current face feature data in the video frame data.

The video frame data may be video frames obtained by serializing video stream data, and by serializing the video stream data, the amount of data to be processed can be effectively reduced, and the data processing efficiency is improved. The fault-tolerant data queue can be a message queue with a fault-tolerant mechanism, and the processing efficiency of real-time video stream data can be effectively improved.

For example, the stream analysis technology in this exemplary embodiment may be implemented based on an open source stream processing framework such as OpenCV, Apache KafKa, and Apache Spark, and specifically, the video stream acquisition unit OpenCV may receive video stream data transmitted by the edge network device, serialize the video stream data into video frame data, and cache the video frame data in the video data buffering unit Apache KafKa, where the video data buffering unit Apache KafKa is configured to implement a fault-tolerant data queue of the video stream data, and then the video stream processing unit Apache Spark consumes the video frame data cached by the Apache KafKa and performs analysis processing on the video frame data, so as to detect current face feature data. Of course, this is merely an exemplary illustration, and the flow analysis service may also be implemented in other ways, and this exemplary embodiment is not limited to this specifically.

In an example embodiment of the present disclosure, a face recognition model may be obtained in two ways:

in the first mode, a pre-constructed face recognition model can be obtained, and training verification processing is performed on the pre-constructed face recognition model through the collected historical face feature data, so that the face recognition model after training verification is obtained.

Specifically, a Google tensoroflow open source machine learning framework can be selected to train the face recognition model. For example, a deep neural network model can be selected, a training model code is compiled, face feature data collected in advance, such as historical face feature data stored in a block chain network, is led into the deep neural network model, and the deep neural network model is trained through the compiled training model code to obtain a preliminarily trained face recognition model; and then importing new historical human face characteristic data which are continuously collected into the human face recognition model which is preliminarily trained, verifying the recognition accuracy of the model, adjusting the model parameters of the human face recognition model which is preliminarily trained when the recognition accuracy is low, performing model training again to obtain the human face recognition model with higher recognition accuracy, and continuously repeating the training verification process until the human face recognition model with the recognition accuracy meeting the requirements is obtained and taking the human face recognition model as the final human face recognition model.

In the second mode, when the computing power of the information management server is weak, the face recognition model trained and verified based on the historical face feature data can be acquired from a cloud platform connected with a network.

Specifically, the cloud platform may be a service platform which is connected to an information management server for edge computing through a network and has a high computing capability, and when the computing capability of the information management server is weak, historical face feature data may be shared with the cloud platform, so that the cloud platform trains and verifies the face recognition model based on the shared historical face feature data and distributes the face recognition model to the information management server.

In an example embodiment of the present disclosure, the recording operation of the current movement trajectory of the current face feature data may be triggered by the following steps:

The matching threshold may be a numerical value used for determining whether the current face feature data matches historical face feature data stored in the block chain network, for example, the matching result of the face recognition model may be a recognition confidence, and at this time, the matching threshold may be 80%, that is, when the face recognition model matches the current face feature data with the historical face feature data to obtain a matching result, that is, the recognition confidence is greater than 80%, the current face feature data is considered to be matched with the historical face feature data; when the face recognition model matches the current face feature data with the historical face feature data to obtain a matching result, that is, the recognition confidence is less than or equal to 80%, the current face feature data is considered to be not matched with the historical face feature data, of course, the matching threshold may also be 75%, 70%, and the like, and the specific matching threshold may be set by user according to different face recognition models, which is not specially limited in the present embodiment.

The location information may refer to a geographic location of the edge network device that collects the current face feature data, for example, the person object may be a resident of the community 1, and the current face feature data corresponding to the person object is collected by the edge network device at the doorway of the community 2, and at this time, it may be considered that the person object is present in the community 2, so that the current location of the person object corresponding to the current face feature data needs to be determined according to the location information of the edge network device, and then the moving trajectory of the person object is drawn according to the historical location information recorded in the block chain network.

After the position information of the edge network device for collecting the current face feature data is determined, the position information and the current face feature data can be associated and uploaded to a block chain network, and then the current moving track of the current face feature data can be drawn together with historical position information corresponding to the current face feature data.

Optionally, in response to that the matching result is smaller than or equal to the matching threshold, the current face feature data may be stored in the block chain network as new historical face feature data, so as to implement a registration operation on the current face feature data.

When the matching result is less than or equal to the matching threshold, it may be considered that historical face feature data corresponding to the current face feature data does not exist in the block chain network, and therefore the current face feature data needs to be recorded and updated in the block chain network, and therefore the current face feature data is stored in the block chain network as new historical face feature data, so that the operation of registering the current face feature data in the block chain network is achieved, and when the current face feature data appears in subsequent video stream data, the operations of tracing a movement track and confirming identity information and the like can be performed on the historical face feature data corresponding to the current face feature data registered in the block chain network.

Preferably, the step in fig. 3 may be implemented to perform a corresponding information management operation on the current face feature data:

referring to fig. 3, in step S310, a historical movement track corresponding to the current face feature data is obtained from the block chain network;

step S320, determining the pass grade of the current face feature data according to the historical movement track;

and step S330, combining the matching result and the pass grade, and executing corresponding information management operation on the current face feature data.

The traffic grade may be a grade type for dividing the current face feature data in different scenes, for example, in a scene of community epidemic situation prevention and control, the traffic grade may include a to-be-isolated grade, a high-medium risk grade or a low-risk grade, where the to-be-isolated grade may indicate that a person object corresponding to the current face feature data needs to be isolated or is already in an isolated state, the high-medium risk grade may indicate that a person object historical movement track corresponding to the current face feature data enters or exits an area with high or medium risk, and has a higher infection probability, and the low-risk grade may indicate that a person object historical movement track corresponding to the current face feature data does not enter or exit the area with high or medium risk, and the infection probability is lower. Of course, the traffic level may also be a level type of the current face feature data in other scenarios, for example, the traffic level may also be a high suspicion level, a medium suspicion level, or a low suspicion level in a scenario in which the police tracks the suspect, which is not particularly limited in this example embodiment.

Executing corresponding information management operation by combining the matching result and the traffic level, for example, in a scene of community epidemic situation prevention and control, if the matching result of the current face feature data is greater than a preset threshold value, the current face feature data can be represented as belonging to an internal resident of a community, and then whether the current face feature data is a to-be-isolated level, a high and medium risk level or a low risk level can be judged according to the associated data corresponding to the current face feature data, if the current face feature data is the low risk level, the traffic operation is executed, and a person object corresponding to the current face feature data is allowed to enter the community; if the current face feature data is the to-be-isolated level, executing alarm operation to warn a person object corresponding to the current face feature data, and sending alarm information to inform relevant workers of isolation processing; and if the human face feature data is of a high and medium risk level, performing isolation registration operation to perform isolation registration on the human object corresponding to the current human face feature data, and performing explanation and notification related measures, such as notification of the human face feature data through a display screen. Of course, this is merely an illustrative example and does not set any particular limit on the exemplary embodiments.

It should be noted that although the various steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that these steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.

In addition, the present exemplary embodiment provides an information management server for edge computing, and fig. 4 schematically shows a structural diagram of an information management server according to an embodiment of the present disclosure.

Referring to fig. 4, the information management server 400 may include a feature extraction module 410, a feature matching module 420, and a matching result response module 430. Wherein:

the feature extraction module 410 may be configured to perform stream analysis processing on video stream data acquired by the edge network device in real time, and extract current face feature data in the video stream data;

the feature matching module 420 may be configured to match current face feature data extracted in the feature extraction module 410 with historical face feature data stored in a blockchain network based on a pre-trained face recognition model;

the matching result responding module 430 may be configured to respond to the matching result in the feature matching module 420 and perform a corresponding information management operation on the current face feature data.

In the information management server provided in an exemplary embodiment of the present disclosure, on one hand, current face feature data corresponding to community people is extracted based on the feature extraction module 410, and the current face feature data is matched according to the face recognition model in the feature matching module 420, so that the face feature data of the community people can be automatically and quickly acquired, the acquisition efficiency of the person information is effectively improved, and the recognition efficiency of the person information is effectively improved and the matching accuracy of the acquired data is ensured through the face recognition model matching data based on the deep learning model; on the other hand, historical face feature data is stored through the block chain network, and the current face feature data is matched with the historical face feature data stored in the block chain network based on the feature matching module 420, so that the accuracy of the data is further ensured, the safety of the data is improved, and all the face feature data can be traced; on the other hand, the matching result response module 430 automatically and efficiently realizes community information management, so that the data management efficiency is improved, the data processing delay is reduced, and the data processing efficiency is effectively improved.

In this example embodiment, the feature extraction module 410 may be constructed based on a flow analysis technique to improve data processing efficiency:

referring to fig. 5, the feature extraction module 410 may include a video stream acquisition unit 511, a video data buffering unit 512, and a video stream processing unit 513. Wherein:

the video stream collecting unit 511 may be configured to perform serialization processing on video stream data collected by the edge network device in real time to obtain video frame data;

the video data buffering unit 512 may be configured to buffer video frame data generated in the video stream acquisition unit in a fault-tolerant data queue;

the video stream processing unit 513 may be configured to perform consumption processing on the video frame data in the fault-tolerant data queue of the video data buffering unit to extract current face feature data in the video frame data.

In this exemplary embodiment, the face recognition model may be constructed based on a machine learning technique, and specifically, the face recognition model may be obtained by the feature matching module 420:

referring to fig. 6, the feature matching module 420 may include a face recognition model obtaining unit 621, and the model obtaining unit 621 may be configured to:

In the present exemplary embodiment, as shown with reference to fig. 7, the matching result response module 430 may include a matching success response unit 731, a matching failure response unit 732, and an isolation notification unit 733. Wherein:

the matching success response unit 731 may be configured to: acquiring position information of the edge network equipment corresponding to the collected current face feature data in response to the matching result being larger than a preset matching threshold; associating the position information with the current face feature data, and uploading the position information to the block chain network to realize the recording operation of the current moving track of the current face feature data;

the matching failure response unit 732 may be configured to, in response to the matching result being less than or equal to the matching threshold, store the current facial feature data as new historical facial feature data in the block chain network, so as to implement a registration operation on the current facial feature data;

the isolation notification unit 733 may be configured to perform an alarm operation in response to the matching result being greater than a preset matching threshold and the pass level being a level to be isolated.

In this exemplary embodiment, the matching result responding module 130 may further be configured to:

The details of each module or unit in the information management server 400 are already described in detail in the corresponding information management method, and therefore are not described herein again.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Fig. 8 schematically shows a schematic block diagram of an information management server system overall architecture according to one embodiment of the present disclosure.

Referring to fig. 8, in an application scenario of community epidemic situation prevention and control, the information management server 400 may be implemented in combination with a system overall architecture 800 corresponding to the information management server. Specifically, the system architecture 800 of the information management server may include a physical hardware layer 810, a virtualization service layer 820, a base platform 830, an edge computing platform 840, and a community epidemic prevention and control system 850. Wherein:

the physical hardware layer 810 is mainly used for providing physical hardware of the information management server 400, for example, related hardware that may include computing services, storage services, network services, and the like;

the virtualization service layer 820 may include virtualization of services such as computation, storage, interconnection, control, and the like, and is mainly used for providing virtualization services for the base platform 830;

the basic platform 830 is mainly used to provide basic services such as database, application service, security, management and monitoring to the edge computing platform 840;

the edge computing platform 840 is mainly used for providing edge computing services such as flow analysis service, machine learning service, function computation, block chain and the like to the community epidemic prevention and control system 850;

the community epidemic prevention and control system 850 is constructed based on a block chain technology, and is mainly used for providing functions of identifying personnel in real time, intelligently isolating, tracking routes and the like.

Fig. 9 schematically shows a schematic diagram of data streaming in an information management server according to one embodiment of the present disclosure.

Referring to fig. 9, in step S910, video stream data of the people flow situation in the current environment is collected by an edge network device (such as a monitoring camera), and the video stream data is sent to a feature extraction module (stream analysis service) of the information management server;

step S920, acquiring video stream data transmitted by the edge network equipment through the OpenCV, serializing the video stream data into video frame data, and caching the video frame data in the Apache KafKa video data buffering unit;

step S930, generating the video frame data into a fault-tolerant data queue through the video data buffer unit Apache KafKa for consumption by the video stream processing unit Apache Spark;

step S940, consuming Apache KafKa buffered video frame data through an Apache Spark by a video stream processing unit, analyzing and processing the video frame data, detecting current face feature data, counting personnel flow data under the current environment, and transmitting the current face feature data into machine learning service;

step S950, matching and identifying the current face feature data in historical face feature data recorded and stored in a block chain network through machine learning service, and if the matched historical face feature data is not found, taking the current face feature data as new historical face feature data and recording and storing the new historical face feature data in the block chain network; when historical face feature data are matched, sending a matching result to function calculation service;

step S960, based on the function calculation service, triggers different responses by matching results (e.g. recognition confidence): when the matching result is greater than the matching threshold, the person is an internal person of the community, effective information registration and recording are carried out on the person, whether the person is a person to be isolated in the grade is judged, and if the person is the person to be isolated in the grade, warning and alarming are required to be carried out in time; if the people are high-school risk level people, triggering isolation registration is needed to be timely carried out, and explanation and informing are carried out; when the matching result is smaller than or equal to the matching threshold, the result shows that the person is an alien person in the community, information registration needs to be carried out on the person, manual customer service is triggered to process the current state, if the fact that the person has the requirement for entering the community (such as special situations of doctors, maintenance workers and the like) is confirmed, historical movement track analysis is carried out on the alien person, whether the historical movement track enters an area with high risk or not is judged, and if the fact that the historical movement track does not enter the area with high risk or not is detected, the alien person is allowed to enter the community;

step S970, a function calculation service is called, and the current face feature data and the unique identification information and the position information corresponding to the current face feature data are input into the community epidemic situation epidemic prevention system constructed based on the block chain technology.

FIG. 10 schematically shows an application diagram for information management of people within a community according to one embodiment of the present disclosure.

Referring to fig. 10, in step S1010, capturing video stream data of a crowd in a current environment by an edge network device (e.g., a monitoring camera);

step S1020, sending the collected video stream data to a nearest information management server through a network;

step S1030, the information management server detects, extracts and stores the current human face feature data in the video stream data by using a stream analysis technology;

step S1040, the information management server uses machine learning technology to match and recognize the current face feature data;

step S1050, if the matching result is larger than the matching threshold, the result shows that the person is an internal person of the community, and the information management server triggers the internal person information registration corresponding to the current face feature data by using a function calculation technology;

step 1060, the information management server traces the historical movement track of the internal personnel corresponding to the current face feature data by using a block chain technology;

step S1061, if the personnel are judged to be the internal personnel of the grade to be isolated, warning and warning are required to be carried out in time;

step S1062, if the fact that the historical movement track of the internal personnel corresponding to the current face feature data reaches the high and medium risk area is detected, the internal personnel with the high and medium risk level are judged, trigger isolation registration needs to be carried out in time, and explanation and informing are carried out;

step S1070, the information management server triggers a function calculation technology to store all data of the internal personnel corresponding to the current face feature data in a community epidemic prevention and control system constructed based on the block chain technology.

FIG. 11 schematically shows an application diagram for information management of people outside of a community, according to one embodiment of the disclosure.

Referring to fig. 11, in step S1110, video stream data of a crowd in a current environment is collected by an edge network device (e.g., a monitoring camera);

step S1120, sending the collected video stream data to the nearest information management server through the network;

step S1130, the information management server uses a flow analysis technology to detect, extract and store the current face feature data in the video stream data;

step S1140, the information management server uses machine learning technique to match and recognize the current face feature data;

step S1150, if the matching result is less than or equal to the matching threshold, which indicates that the person is an alien person in the community, the information management server triggers the registration of the person information corresponding to the current face feature data by using a function calculation technology;

step S1160, registering information of the external personnel, triggering a manual customer service to process the current state, and if the requirement of entering the community (such as special conditions of doctors, maintenance workers and the like) is determined manually, tracing the historical movement track of the external personnel corresponding to the current face feature data by the information management server by using a block chain technology;

step S1161, if the historical movement track of the personnel corresponding to the current face feature data is detected to reach the high and medium risk area, the personnel with the high and medium risk level are judged to be, and the personnel are forbidden to enter the community;

step S1170, the information management server triggers a function calculation technology, and all data of the external personnel corresponding to the current face feature data are stored in a community epidemic situation prevention and control system constructed based on the block chain technology.

The present exemplary embodiment also provides an information management system based on edge calculation, and fig. 12 schematically shows a structural diagram of the information management system according to an embodiment of the present disclosure. Referring to fig. 12, the information management system may include an edge network device 1201 and an information management server 1202. Wherein:

the edge network device 1201 is used for collecting video stream data in real time;

a plurality of information management servers 1202 in communication connection with the edge network device 1201, configured to perform corresponding information management operations on current face feature data in the video stream data;

the plurality of information management servers 1202 store data based on the blockchain technique, and implement a data sharing function and a trace tracing function based on the constructed blockchain network.

Optionally, the information management system may further include a cloud platform 1203, where the cloud platform 1203 may be connected to the plurality of information management servers 1202 to implement data sharing, and when the plurality of information management servers 1202 have weak computing capabilities, train the face recognition model through the historical face feature data shared by the plurality of information management servers 1202, and distribute the trained face recognition model to the plurality of information management servers 1202.

The information management system related to the embodiment of the disclosure may be a distributed system formed by connecting a community epidemic situation prevention and control client and a plurality of information management servers (which may also be any form of computing devices in an access network, such as user terminals) in a network communication manner.

Taking a distributed system as an example of a blockchain system, referring To fig. 13, fig. 13 schematically illustrates a structural schematic diagram of an information management system implemented based on a blockchain technology according To an embodiment of the present disclosure, where the information management system 1300 is formed by a plurality of information management servers 1301 and a community epidemic prevention and Control client 1302, a Peer-To-Peer (P2P, Peer To Peer) network is formed between the information management servers 1301 (nodes), and the P2P Protocol is an application layer Protocol operating on a Transmission Control Protocol (TCP). In a distributed system, any machine, such as a server or a terminal, can join to become a node, and the node comprises a hardware layer, a middle layer, an operating system layer and an application layer.

Referring to fig. 13, each information management server in the blockchain system functions as a node in the blockchain network, and the related functions include:

1) routing, a basic function that a node has, is used to support communication between nodes.

Besides the routing function, the node may also have the following functions:

2) the application is used for being deployed in a block chain, realizing specific services according to actual service requirements, recording data related to the realization functions to form recorded data, such as historical human face feature data, carrying digital signatures in the recorded data to represent sources of task data, and sending the recorded data to other nodes in the block chain system, so that the other nodes can add the recorded data to a temporary block when the sources and integrity of the recorded data are verified successfully.

For example, the services implemented by the application include:

2.1) wallet, for providing the function of transaction of electronic money, including initiating transaction (i.e. sending the transaction record of current transaction to other nodes in the blockchain system, after the other nodes are successfully verified, storing the record data of transaction in the temporary blocks of the blockchain as the response of confirming the transaction is valid; of course, the wallet also supports the querying of the remaining electronic money in the electronic money address;

and 2.2) sharing the account book, wherein the shared account book is used for providing functions of operations such as storage, query and modification of account data, record data of the operations on the account data are sent to other nodes in the block chain system, and after the other nodes verify the validity, the record data are stored in a temporary block as a response for acknowledging that the account data are valid, and confirmation can be sent to the node initiating the operations.

2.3) Intelligent contracts, computerized agreements, which can enforce the terms of a contract, implemented by codes deployed on a shared ledger for execution when certain conditions are met, for completing automated transactions according to actual business requirement codes, such as querying the logistics status of goods purchased by a buyer, transferring the buyer's electronic money to the merchant's address after the buyer signs for the goods; of course, smart contracts are not limited to executing contracts for trading, but may also execute contracts that process received information.

3) And the Block chain comprises a series of blocks (blocks) which are mutually connected according to the generated chronological order, new blocks cannot be removed once being added into the Block chain, and recorded data submitted by nodes in the Block chain system are recorded in the blocks.

Referring to fig. 14, fig. 14 is an optional schematic diagram of a Block Structure (Block Structure) provided in the embodiment of the present disclosure, where each Block includes a hash value of a transaction record stored in the Block (hash value of the Block) and a hash value of a previous Block, and the blocks are connected by the hash values to form a Block chain. The block may include information such as a time stamp at the time of block generation. A block chain (Blockchain), which is essentially a decentralized database, is a string of data blocks associated by using cryptography, and each data block contains related information for verifying the validity (anti-counterfeiting) of the information and generating a next block.

As still another aspect, the present application also provides a computer-readable medium, which may be contained in the information management server described in the above embodiment; or may be present separately. The computer-readable medium carries one or more programs which, when executed by an information management server, cause the information management server to implement the information management method described in the above embodiments.

It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An information management server for edge computing, comprising:

2. The information management server according to claim 1, wherein the matching result response module further includes a matching success response unit configured to:

3. The information management server according to claim 1, wherein the matching result response module further includes a matching failure response unit configured to:

4. The information management server according to any one of claims 2 or 3, wherein the matching result response module is further configured to:

5. The information management server of claim 4, wherein the traffic level comprises a level to be isolated, a high intermediate risk level, or a low risk level;

6. The information management server according to claim 1, wherein the feature extraction module includes:

7. The information management server according to claim 1, wherein the feature matching module further includes a face recognition model acquisition unit configured to:

8. An information management method based on edge computing, which is applied to an information management server for edge computing, the method comprising:

performing stream analysis processing on video stream data acquired by edge network equipment in real time, and extracting current face feature data in the video stream data;

9. The information management method according to claim 8, wherein the information management operation comprises a recording operation, and the performing a corresponding information management operation on the current face feature data in response to the matching result comprises:

10. The information management method according to claim 8, wherein the information management operation includes a registration operation, and the performing of the corresponding information management operation on the current face feature data in response to the matching result includes:

11. The information management method according to any one of claims 9 or 10, wherein the performing, in response to the matching result, a corresponding information management operation on the current face feature data further includes:

12. The information management method according to claim 11, wherein the information management operation includes an alarm operation, and the traffic level includes a level to be isolated, a high-medium risk level, or a low-risk level;

13. The information management method according to claim 1, wherein performing stream analysis processing on video stream data acquired in real time to extract current face feature data in the video stream data comprises:

buffering the video frame data in a fault-tolerant data queue;

14. The information management method of claim 1, wherein before matching the extracted current face feature data with historical face feature data stored in a blockchain network based on a pre-trained face recognition model, the method further comprises:

15. An information management system based on edge computing, comprising: