CN117726925A - Face recognition resource scheduling method, device and equipment - Google Patents
Face recognition resource scheduling method, device and equipment Download PDFInfo
- Publication number
- CN117726925A CN117726925A CN202410173401.0A CN202410173401A CN117726925A CN 117726925 A CN117726925 A CN 117726925A CN 202410173401 A CN202410173401 A CN 202410173401A CN 117726925 A CN117726925 A CN 117726925A
- Authority
- CN
- China
- Prior art keywords
- face recognition
- target
- historical
- determining
- task
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012545 processing Methods 0.000 claims description 68
- 238000013468 resource allocation Methods 0.000 claims description 37
- 238000012795 verification Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method, a device and equipment for scheduling resources for face recognition. The method comprises the following steps: determining a plurality of face recognition terminals and a plurality of edge devices, wherein the plurality of edge devices are used for assisting the plurality of face recognition terminals in face recognition; determining historical service information and target face recognition tasks of each face recognition terminal, and determining historical identification information and historical resource occupation information of each edge device; determining target edge equipment corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge equipment and the historical resource occupation information; and controlling a plurality of edge devices to assist the plurality of face recognition terminals to carry out face recognition according to the target edge devices corresponding to each face recognition terminal. According to the method, the target edge equipment corresponding to each face recognition terminal is flexibly adjusted, so that the face recognition efficiency of each face recognition terminal can be improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a resource scheduling method, device and equipment for face recognition.
Background
Students can check in or verify identity through face recognition terminals at the entrance of classrooms.
In the related art, corresponding edge devices are usually preset for each face recognition terminal, and the face recognition terminal at the classroom entrance can collect face images of students entering the classroom and send the collected face images to the edge devices corresponding to the face recognition terminals so as to determine the face recognition result of the face images through the edge devices.
However, when the number of face recognition images of the face recognition terminal increases, the resource occupation amount of the edge device corresponding to the face recognition terminal is too high, so that the processing efficiency of the edge device is low, and further the face recognition efficiency of the face recognition terminal is low.
Disclosure of Invention
The application provides a resource scheduling method, device and equipment for face recognition, which are used for solving the technical problem of lower face recognition processing efficiency of a face recognition terminal caused by low processing efficiency of edge equipment in the related technology.
In a first aspect, the present application provides a method for scheduling resources for face recognition, including:
determining a plurality of face recognition terminals and a plurality of edge devices, wherein the plurality of edge devices are used for assisting the plurality of face recognition terminals in face recognition;
Determining historical service information and target face recognition tasks of each face recognition terminal, and determining historical identification information and historical resource occupation information of each edge device;
determining target edge equipment corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge equipment and the historical resource occupation information;
and controlling the plurality of edge devices to assist the plurality of face recognition terminals to carry out face recognition according to the target edge devices corresponding to each face recognition terminal.
In one possible implementation manner, determining the target edge device corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge device and the historical resource occupation information includes:
aiming at any face recognition terminal, determining the prediction request quantity of the face recognition terminal in a future period according to the historical service information of the face recognition terminal and a target face recognition task;
for any one edge device, determining the maximum identification amount of the edge device in the future period according to the historical identification information and the historical resource occupation information of the edge device;
And determining the target edge equipment corresponding to each face recognition terminal according to the predicted request quantity of each face recognition terminal and the maximum recognition quantity of each edge equipment.
In one possible implementation manner, the historical service information includes an actual processing amount and a historical task amount corresponding to each of a plurality of historical time periods;
according to the historical service information of the face recognition terminal and the target face recognition task, determining the predicted request quantity of the face recognition terminal in a future period comprises the following steps:
for any one history period, determining a task deviation amount corresponding to the history period according to the actual processing amount and the history task amount of the history period;
determining a target task deviation amount according to the task deviation amount of each history period;
and determining a target task amount according to the target face recognition task, and determining the sum of the target task amount and the target task deviation amount as the predicted request amount.
In one possible implementation manner, the history identification information includes a history identification amount corresponding to each history period in the plurality of history periods, and the history resource occupation information includes a resource occupation amount corresponding to each history period;
Determining the maximum identification amount of the edge device in the future period according to the historical identification information and the historical resource occupation information of the edge device, wherein the method comprises the following steps:
for any one history period, determining an estimated maximum recognition quantity corresponding to the history period according to the history recognition quantity and the resource occupation quantity corresponding to the history period;
and determining the maximum recognition quantity according to the estimated maximum recognition quantity corresponding to each historical period.
In a possible implementation manner, according to the target edge device corresponding to each face recognition terminal, controlling the plurality of edge devices to assist the plurality of face recognition terminals in face recognition includes:
determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
generating resource allocation information according to target edge equipment corresponding to each face recognition terminal and the target time period, wherein the resource allocation information comprises the identification of the target edge equipment corresponding to each face recognition terminal and the target time period;
storing the resource allocation information and the update time of the resource allocation information in a preset storage space, wherein the preset storage space is a shared storage space of the plurality of face recognition terminals and the plurality of edge devices;
And sending notification messages to the plurality of edge devices and the plurality of face recognition terminals, wherein the notification messages are used for indicating the resource allocation information to be updated and indicating the plurality of edge devices to assist the corresponding face recognition terminals to carry out face recognition according to the resource allocation information.
In one possible implementation manner, determining the historical service information of each face recognition terminal includes:
determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
determining a plurality of historical time periods according to the target time period, wherein the target time period and the historical time period are the same time period in different statistical periods;
and aiming at any face recognition terminal, acquiring the historical task amount of the face recognition terminal in each historical period, and determining the historical service information of the face recognition terminal, wherein the historical service information comprises the historical task amount of the face recognition terminal in each historical period.
In one possible implementation, the method further includes:
determining assistance information, wherein the assistance information comprises a plurality of face recognition types, and priority and face recognition precision corresponding to each face recognition type;
Sending the assistance information to the edge equipment so that the edge equipment assists the face recognition terminal to carry out face recognition according to the assistance information; the face recognition terminal is used for determining image features of face images, and the edge equipment is used for recognizing the face according to the image features.
In a second aspect, the present application provides a resource scheduling device for face recognition, including:
the device comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining a plurality of face recognition terminals and a plurality of edge devices, and the plurality of edge devices are used for assisting the plurality of face recognition terminals in face recognition;
the determining module is further used for determining historical service information and target face recognition tasks of each face recognition terminal, and determining historical identification information and historical resource occupation information of each edge device;
the determining module is further configured to determine a target edge device corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge device, and the historical resource occupation information;
and the control module is used for controlling the plurality of edge devices to assist the plurality of face recognition terminals to carry out face recognition according to the target edge devices corresponding to each face recognition terminal.
In one possible implementation manner, the determining module is specifically configured to:
aiming at any face recognition terminal, determining the prediction request quantity of the face recognition terminal in a future period according to the historical service information of the face recognition terminal and a target face recognition task;
for any one edge device, determining the maximum identification amount of the edge device in the future period according to the historical identification information and the historical resource occupation information of the edge device;
and determining the target edge equipment corresponding to each face recognition terminal according to the predicted request quantity of each face recognition terminal and the maximum recognition quantity of each edge equipment.
In one possible implementation manner, the historical service information includes an actual processing amount and a historical task amount corresponding to each of a plurality of historical time periods; the determining module is specifically further configured to:
for any one history period, determining a task deviation amount corresponding to the history period according to the actual processing amount and the history task amount of the history period;
determining a target task deviation amount according to the task deviation amount of each history period;
and determining a target task amount according to the target face recognition task, and determining the sum of the target task amount and the target task deviation amount as the predicted request amount.
In one possible implementation manner, the history identification information includes a history identification amount corresponding to each history period in the plurality of history periods, and the history resource occupation information includes a resource occupation amount corresponding to each history period; the determining module is specifically further configured to:
for any one history period, determining an estimated maximum recognition quantity corresponding to the history period according to the history recognition quantity and the resource occupation quantity corresponding to the history period;
and determining the maximum recognition quantity according to the estimated maximum recognition quantity corresponding to each historical period.
In one possible implementation manner, the control module is specifically configured to:
determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
generating resource allocation information according to target edge equipment corresponding to each face recognition terminal and the target time period, wherein the resource allocation information comprises the identification of the target edge equipment corresponding to each face recognition terminal and the target time period;
storing the resource allocation information and the update time of the resource allocation information in a preset storage space, wherein the preset storage space is a shared storage space of the plurality of face recognition terminals and the plurality of edge devices;
And sending notification messages to the plurality of edge devices and the plurality of face recognition terminals, wherein the notification messages are used for indicating the resource allocation information to be updated and indicating the plurality of edge devices to assist the corresponding face recognition terminals to carry out face recognition according to the resource allocation information.
In a possible implementation manner, the determining module is specifically further configured to:
determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
determining a plurality of historical time periods according to the target time period, wherein the target time period and the historical time period are the same time period in different statistical periods;
and aiming at any face recognition terminal, acquiring the historical task amount of the face recognition terminal in each historical period, and determining the historical service information of the face recognition terminal, wherein the historical service information comprises the historical task amount of the face recognition terminal in each historical period.
In a possible implementation manner, the resource scheduling device for face recognition further includes a sending module, where:
the determining module is further configured to determine assistance information, where the assistance information includes a plurality of face recognition types, and priority and face recognition precision corresponding to each face recognition type;
The sending module is used for sending the assistance information to the edge equipment so that the edge equipment assists the face recognition terminal to carry out face recognition according to the assistance information; the face recognition terminal is used for determining image features of face images, and the edge equipment is used for recognizing the face according to the image features.
In a third aspect, the present application provides a resource scheduling device for face recognition, including: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of the first aspects.
In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions for performing the method of any of the first aspects when executed by a processor.
In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the method according to any of the first aspects.
The application provides a resource scheduling method, device and equipment for face recognition, wherein the method can determine a plurality of face recognition terminals and a plurality of edge devices; the historical service information and the target face recognition task of each face recognition terminal can be determined, and the historical identification information and the historical resource occupation information of each edge device can be determined; determining target edge equipment corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge equipment and the historical resource occupation information; and controlling a plurality of edge devices to assist the face recognition terminals to carry out face recognition according to the target edge devices corresponding to the face recognition terminals. According to the method, the target edge equipment corresponding to each face recognition terminal can be dynamically adjusted according to the historical service information and the target face recognition task of each face recognition terminal and the historical identification information and the historical resource occupation information of each edge equipment, so that the face recognition processing of each target edge equipment is carried out in an optimal operation state, the processing efficiency of the target edge equipment is improved, and the face recognition processing efficiency of the face recognition terminal is further improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic diagram of an application scenario provided in the present application;
fig. 2 is a flow chart of a resource scheduling method for face recognition provided by the present application;
fig. 3 is a flow chart of another resource scheduling method for face recognition provided in the present application;
fig. 4 is a schematic diagram of a face recognition processing procedure provided in the present application;
fig. 5 is a schematic structural diagram of a resource scheduling device for face recognition provided in the present application;
fig. 6 is a schematic structural diagram of another resource scheduling device for face recognition provided in the present application;
fig. 7 is a schematic hardware structure of a resource scheduling device for face recognition provided in the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
First, in order to facilitate understanding, an application scenario of the resource scheduling method for face recognition provided by the present application is described.
Fig. 1 is a schematic diagram of an application scenario provided in the present application. Referring to fig. 1, the resource scheduling device includes face recognition, 6 face recognition terminals, and 2 edge devices.
The resource scheduling device for face recognition can be used for determining the target edge device corresponding to each face recognition terminal, and dynamically adjusting the target edge device corresponding to each face recognition terminal according to the actual processing condition of the face recognition terminal and the actual operation condition of the edge device.
Before resource scheduling, the edge device 1 can assist the face recognition terminals 1-3 in face recognition processing, and the edge device 2 can assist the face recognition terminals 4-6 in face recognition processing. Since the number of face recognition requests to be processed in the face recognition terminal 1 and the face recognition terminal 2 increases, the resource occupation amount of the edge device 1 is excessively large, so that the processing efficiency of the edge device 1 is reduced. And the number of face recognition requests of the face recognition terminals 4-6 is small, so that a large amount of available resources are available for the edge equipment 2.
In this case, the resource scheduling device for face recognition may perform resource scheduling for the edge device 1 and the edge device 2. After resource scheduling, the edge device 1 can assist the face recognition terminal 1 and the face recognition terminal 2 in face recognition processing, and the edge device 2 can assist the face recognition terminals 3-6 in face recognition processing.
It should be noted that, the resource scheduling device for face recognition in the present application may be used to schedule at least one edge device, and each edge device may be used to assist at least one face recognition terminal.
In the related art, a face recognition terminal at a classroom entrance can collect face images of students entering the classroom and send the collected face images to edge devices corresponding to the face recognition terminal so as to determine face recognition results of the face images through the edge devices. However, when the number of face recognition images of the face recognition terminal is large, the resource occupation amount of the edge equipment corresponding to the face recognition terminal is too high, so that the processing efficiency of the edge equipment is low, and further the face recognition processing efficiency is low.
The resource scheduling method for face recognition aims to solve the technical problems of the related technology. The method can determine a plurality of face recognition terminals and a plurality of edge devices; the historical service information and the target face recognition task of each face recognition terminal can be determined, and the historical identification information and the historical resource occupation information of each edge device can be determined; determining target edge equipment corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge equipment and the historical resource occupation information; and controlling a plurality of edge devices to assist the face recognition terminals to carry out face recognition according to the target edge devices corresponding to the face recognition terminals. According to the method, the target edge equipment corresponding to each face recognition terminal can be dynamically adjusted according to the historical service information and the target face recognition task of each face recognition terminal and the historical identification information and the historical resource occupation information of each edge equipment, so that each target edge equipment can perform face recognition processing in an optimal running state, the processing efficiency of the target edge equipment is improved, and further the face recognition processing efficiency is improved.
The following describes the technical solution of the present application and how the technical solution of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 2 is a flow chart of a resource scheduling method for face recognition provided by the present application. Referring to fig. 2, the method includes:
in the embodiment of the application, the method can be applied to the resource scheduling equipment for face recognition. For example, the method may be implemented by a face-recognition resource scheduling device, or may be implemented by a chip in the face-recognition resource scheduling device, or may also be implemented by a face-recognition resource scheduling apparatus in the face-recognition resource scheduling device.
S201, determining a plurality of face recognition terminals and a plurality of edge devices.
The plurality of edge devices are used for assisting the plurality of face recognition terminals in face recognition. Each edge device may be used to assist at least one face recognition terminal in recognizing face.
The face recognition terminal may be a device for implementing face recognition in the related art. For example, the face recognition terminal may be a face recognition gate inhibition machine.
The edge device may be an edge server, which may be a separate physical server, or a server cluster made up of multiple physical servers.
S202, determining historical service information and target face recognition tasks of each face recognition terminal, and determining historical identification information and historical resource occupation information of each edge device.
The historical business information may include an actual throughput and a historical task volume corresponding to each of a plurality of historical periods.
The plurality of historical periods may be the same period in different statistical cycles.
For example, the number of students needing to perform face recognition check-in 8-10 points per day in 5 days of history needs to be counted, the counting period is 1 day, and the history period is 8-10 points per day in 5 days of history.
In each historical period, the actual processing amount is the number of face recognition requests actually received by the face recognition terminal, the historical task amount is the number of face recognition requests to be processed, which are distributed by the face recognition terminal, of the resource scheduling equipment for face recognition.
For example, according to the course arrangement information, the number of students in the classroom 1 is 50 at 9 to 10 am on monday, and the 50 students need to perform face recognition check-in through the face recognition terminal 1 set in the classroom 1, so that the task amount allocated to the face recognition terminal 1 by the face recognition resource scheduling device is 50, that is, the historical task amount of the face recognition terminal 1 in the historical period is 50. However, among the 50 classmates, 2 classmates have been left to leave, and in practice only 48 classmates have performed face recognition check-in through the face recognition terminal 1, and the actual throughput of the face recognition terminal 1 in the history period is 48.
The target face recognition task may include a target period, and a target amount of tasks for each face recognition terminal within the target period.
The history identification information may include a history identification amount corresponding to each of the plurality of history periods, and the history resource occupation information may include a resource occupation amount corresponding to each of the history periods.
The history recognition amount may be the number of face recognition requests actually subjected to recognition processing by the edge device in the history period.
The resource occupancy may be an occupancy of a central processing unit (Central Processing Unit, CPU) of the edge device or a memory occupancy.
S203, determining the target edge equipment corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge equipment and the historical resource occupation information.
In one possible implementation manner, the target edge device corresponding to each face recognition terminal may be determined by: aiming at any face recognition terminal, determining the predicted request quantity of the face recognition terminal in a future period according to the historical service information of the face recognition terminal and a target face recognition task; for any one edge device, determining the maximum identification amount of the edge device in a future period according to the historical identification information and the historical resource occupation information of the edge device; and determining the target edge equipment corresponding to each face recognition terminal according to the predicted request quantity of each face recognition terminal and the maximum recognition quantity of each edge equipment.
It can be understood that, assuming that there are a plurality of face recognition terminals, the plurality of face recognition terminals may be sequentially ordered according to the order of the number of the predicted requests from large to small, and the target edge device corresponding to each face recognition terminal may be sequentially determined according to the ordering result. Assuming that there are multiple edge devices to be selected, when a corresponding target edge device is allocated to each face recognition terminal, the edge device with the largest recognition quantity among the multiple edge devices to be selected can be preferentially selected.
S204, controlling a plurality of edge devices to assist the face recognition terminals to carry out face recognition according to the target edge devices corresponding to the face recognition terminals.
In one possible implementation manner, the plurality of edge devices may be controlled to assist the plurality of face recognition terminals in performing face recognition in the following manner: determining assistance information; and sending the assistance information to the edge equipment so that the edge equipment assists the face recognition terminal to carry out face recognition according to the assistance information.
The face recognition terminal can be used for determining the image characteristics of the face image, and the edge equipment can be used for carrying out face recognition according to the image characteristics.
The assistance information may include a plurality of face recognition types, and priorities and face recognition accuracies corresponding to each face recognition type.
The face recognition type may include a face check-in type and a face verification type.
When the face recognition types are different, the priorities and the face recognition accuracy are also different. For example, the priority corresponding to the face verification type may be higher than the priority corresponding to the face check-in type, and the face verification type has a higher requirement for face recognition accuracy than the face check-in type.
It can be appreciated that in the face recognition processing, the higher the number of features to be compared, and the higher the threshold of comparison, the higher the face recognition accuracy requirement.
For example, in a face registration scenario, face proportion features and eye features of a face image may be determined based on a face recognition terminal, and edge devices may perform face recognition processing according to the face proportion features and the eye features, and when the face recognition rate is higher than 80%, the face recognition may be considered to pass and the registration processing may be performed.
In the face verification scene, the full face characteristics (including face proportion characteristics, eye characteristics, nose characteristics, mouth characteristics and ear characteristics) of the face image can be determined based on the face recognition terminal, the edge equipment can perform face recognition processing according to the full face characteristics of the face image, the face recognition rate is required to be higher than 90%, and the passing of face verification can be determined.
In the actual application process, a task processing queue corresponding to each face recognition type can be created in the edge equipment, and face recognition requests in the task processing queue with high priority are processed preferentially. The edge device can also monitor the number of unprocessed requests in the task processing queue corresponding to each face recognition type in real time, and judge whether the resource scheduling device requesting face recognition needs to perform resource coordination or the resource scheduling device requesting face recognition needs to perform assistance processing.
For example, the task processing queues may include a face check-in processing queue and a face verification processing queue, where the priority of the face verification processing queue is higher than the priority of the face check-in processing queue, and face recognition requests in the face verification processing queue may be processed preferentially. When the number of unprocessed requests in the face signing processing queue and the face verification processing queue is smaller than or equal to a preset threshold value, the resource scheduling equipment which does not need to request face recognition is not needed to coordinate and assist resources. When the number of unprocessed requests in the two processing queues is larger than a preset threshold value, resource scheduling equipment which needs to request face recognition is required to perform resource coordination or assistance.
According to the resource scheduling method for face recognition, the target edge devices corresponding to each face recognition terminal can be dynamically adjusted according to the historical service information and the target face recognition task of each face recognition terminal and the historical identification information and the historical resource occupation information of each edge device, so that face recognition processing is carried out on each target edge device in an optimal running state, the processing efficiency of the target edge devices is improved, and further the face recognition processing efficiency is improved.
Fig. 3 is a flow chart of another resource scheduling method for face recognition provided in the present application. Referring to fig. 3, the method includes:
s301, determining a plurality of face recognition terminals and a plurality of edge devices.
Note that, the specific execution process of S301 may refer to the specific execution process of S201, and will not be described herein.
S302, determining a target face recognition task of each face recognition terminal.
For example, the target face recognition task of the face recognition terminal in each classroom can be determined according to the curriculum schedule information corresponding to the classroom.
S303, determining a target period corresponding to the target face recognition task.
The target face recognition task is to be performed during a target period. For example, according to course arrangement information, a classroom 1 arranges courses 1 at 9 to 10 am on monday, and the number of people on the courses corresponding to the courses 1 is 80, so that the target period is 9 to 10 am on monday, and the target task amount is 80.
S304, determining a plurality of history periods according to the target period.
The target period and the history period are the same period in different statistical periods.
For example, the historical period may be 9 to 10 am on monday and the target period may be 9 to 10 am on the next monday.
S305, aiming at any face recognition terminal, acquiring the historical task quantity of the face recognition terminal in each historical period, and determining the historical service information of the face recognition terminal.
The historical service information may include the historical task amount of the face recognition terminal in each historical period, and the historical service information may also include the actual processing amount of the face recognition terminal in each historical period.
For any face recognition terminal, the number of prediction requests of the face recognition terminal in a future period can be determined according to the historical service information of the face recognition terminal and a target face recognition task, and the specific implementation process can refer to the following steps S306-S308:
S306, determining task deviation amount corresponding to the history period according to the actual processing amount and the history task amount of the history period for any history period.
The task deviation amount may be a difference between the actual processing amount and the historical task amount. For example, in the history period, the history task amount is 150, the actual processing amount is 145, and the task deviation amount is 5.
S307, determining a target task deviation amount according to the task deviation amount of each history period.
Alternatively, the plurality of task deviation amounts may be obtained from the task deviation amount of each of the plurality of history periods. The target task deviation amount may be an average, median, or maximum of the plurality of task deviation amounts.
For example, assume that there are 5 history periods, and the task deviation amounts corresponding to the 5 history periods are in order: 5. 2, 3, 10, 0, the target task deviation amount may be an average of the 5 task deviation amounts, and the target task deviation amount may be 4.
In one implementation, a smooth prediction approach may also be employed to determine the target task deviation amount. The smooth prediction method may satisfy the following formula.
Wherein,is->A primary exponential smoothing value of the period; />Is a weighting coefficient; / >Is->Actual values of the period; />Is->The primary index of the cycle smoothes the value.
Wherein,is->A periodic secondary exponential smoothing value; />Is->The secondary index of the cycle smoothes the value.
Wherein,and->Is a smoothing coefficient; />Is->A predicted value of the period; />Is->And (3) a period.
S308, determining a target task amount according to the target face recognition task, and determining the sum of the target task amount and the target task deviation amount as the predicted request amount.
For example, if the target task amount is 90 and the target task deviation amount is 5, the predicted request amount is 95.
S309, determining historical identification information and historical resource occupation information of each edge device.
The history identification information may include a history identification amount corresponding to each of the plurality of history periods.
The historical resource occupancy information may include a resource occupancy amount corresponding to each historical period.
For any one edge device, the maximum identification amount of the edge device in the future period can be determined according to the historical identification information and the historical resource occupation information of the edge device, and the specific implementation process can refer to the following steps S310 and S311:
s310, determining the estimated maximum recognition quantity corresponding to the history time period according to the history recognition quantity and the resource occupation quantity corresponding to the history time period for any history time period.
Optionally, for any one history period, a plurality of resource occupation amounts and a plurality of history identification amounts corresponding to the history period in different statistics periods may be obtained, and among the plurality of resource occupation amounts, a maximum resource occupation amount of the edge device in an optimum running state may be determined as a target resource occupation amount; the historical recognition amount of the historical period in the statistical period corresponding to the target resource occupation amount can be determined as the estimated maximum recognition amount.
For example, an edge device may be in an optimal operating state when the maximum resource footprint of the edge device is less than or equal to 85%. Assuming that for any one history period (9 to 10 points), the history identification amount and the resource occupation amount corresponding to the history period in 4 different statistical periods can be shown in table 1:
TABLE 1
For example, in the 4 statistical periods, in the historical periods of the statistical period 2, the statistical period 3 and the statistical period 4, the edge device may be in an optimum operation state, wherein the resource occupation amount (85%) of the historical period of the statistical period 2 is the largest, the target resource occupation amount may be determined to be 85%, the historical recognition amount corresponding to the historical period of the statistical period 2 may be determined to be the estimated maximum recognition amount, and the estimated maximum recognition amount is 340.
S311, determining the maximum recognition quantity according to the estimated maximum recognition quantity corresponding to each history period.
Alternatively, a smooth prediction method may be used to predict the maximum recognition of the edge device in the future period based on the estimated maximum recognition corresponding to each history period of the edge device.
S312, determining the target edge device corresponding to each face recognition terminal according to the prediction request quantity of each face recognition terminal and the maximum recognition quantity of each edge device.
It may be appreciated that each edge device may assist at least one face recognition terminal, and in order to ensure processing efficiency of the edge device, a maximum recognition amount of the edge device may be greater than a sum of the number of prediction requests of the at least one face recognition terminal.
For example, the edge device 1 may assist the face recognition terminal 1 to the face recognition terminal 3 in performing face recognition, the number of prediction requests of the face recognition terminal 1, the face recognition terminal 2 and the face recognition terminal 3 are respectively 80, 90 and 85, the sum of the number of prediction requests of the 3 face recognition terminals is 255, and the maximum recognition amount of the edge device 1 is 300, so that the edge device 1 may assist in processing the 3 face recognition terminals.
In one possible implementation manner, after determining the target edge device corresponding to each face recognition terminal, the plurality of edge devices may be controlled to assist the plurality of face recognition terminals in face recognition through executing steps S313 to S315 as shown below.
S313, generating resource allocation information according to the target edge equipment corresponding to each face recognition terminal and the target time period.
The resource allocation information may include an identification of a target edge device corresponding to each face recognition terminal, and a target period.
The identification of the target edge device may be the name, number, address, or the like of the target edge device.
S314, storing the resource allocation information and the update time of the resource allocation information in a preset storage space.
The preset storage space may be a shared storage space of a plurality of face recognition terminals and a plurality of edge devices. The preset storage space can store resource allocation information corresponding to a plurality of edge devices.
The edge device and the plurality of face recognition terminals assisted by the edge device can be timely notified according to the updating time, so that the edge device and the face recognition terminals can timely acquire the resource allocation information in a preset storage space.
S315, sending notification messages to a plurality of edge devices and a plurality of face recognition terminals.
The notification message may be used to instruct the resource allocation information to update, and instruct the plurality of edge devices to assist the corresponding face recognition terminal in performing face recognition according to the resource allocation information.
According to the resource scheduling method for face recognition, the target edge devices corresponding to each face recognition terminal can be dynamically adjusted according to the historical service information and the target face recognition task of each face recognition terminal and the historical identification information and the historical resource occupation information of each edge device, so that face recognition processing is carried out on each target edge device in an optimal running state, the processing efficiency of the target edge devices is improved, and further the face recognition processing efficiency is improved.
The resource scheduling device for face recognition in the embodiment of the present application may be a cloud server, and in the following, with reference to fig. 4, a face recognition process in a school scenario is taken as an example, and the face recognition process provided in the present application is described.
Fig. 4 is a schematic diagram of a face recognition processing procedure provided in the present application. Referring to fig. 4, the system includes a resource scheduling device (cloud server) for face recognition, an edge device, and a plurality of face recognition terminals.
Students can sign in or verify faces through face recognition terminals.
The face recognition terminal can collect face images of students after receiving face check-in requests or face verification requests of the students and extract image features of the face images. The face recognition terminal may also send a face check-in recognition request or a face verification recognition request to the edge device, where the face check-in recognition request or the face verification recognition request includes image features of a face image recognized by the face recognition terminal.
The edge device may be used to assist each face recognition terminal in performing face recognition processing. The edge equipment can receive a face sign-in recognition request or a face verification recognition request sent by the face recognition terminal, and performs face recognition processing based on image features in the face sign-in recognition request or the face verification recognition request to obtain a recognition result.
The edge device may also send the recognition result to the face recognition terminal, so that the face recognition terminal determines a face check-in result or a face verification result according to the recognition result. For example, if the identification result is that the identification is passed, the success of the face check-in or the pass of the face verification is determined; and if the identification result is that the identification fails, determining that the face check-in fails or the face verification fails.
The face recognition resource scheduling device (cloud server) can store and manage a plurality of face images, and can also store historical identification information and historical resource occupation of each edge device, historical service information of each face recognition terminal and target face recognition tasks so as to predict resource use conditions of each edge device in future time periods.
The resource scheduling device (cloud server) for face recognition can also communicate with a plurality of face recognition terminals and edge devices, and assist each face recognition terminal or edge device to perform face recognition processing based on the face images. The resource scheduling device (cloud server) for face recognition can send assistance information to the edge device, so that the edge device assists the face recognition terminal to perform face recognition according to the assistance information.
The face recognition resource scheduling device (cloud server) can also receive the resource scheduling request sent by the edge device, and dynamically adjust the number of face recognition terminals corresponding to each edge device based on the resource scheduling request. The resource scheduling device (cloud server) for face recognition can generate resource allocation information according to the target edge device corresponding to each face recognition terminal and the target time period, store the resource allocation information and the update time of the resource allocation information in a preset storage space, send notification information to the edge device and the face recognition terminals to instruct the edge device and the face recognition terminals to update the resource allocation information, and instruct the edge device to assist the corresponding face recognition terminals to face recognition according to the resource allocation information.
The resource scheduling device (cloud server) for face recognition can also monitor the real-time resource usage condition of each edge device and the target face recognition task of each face recognition terminal in real time, and perform resource scheduling based on the real-time resource usage condition of each edge device and the target face recognition task of each face recognition terminal, or assist some edge devices in face recognition, or schedule some idle edge devices to perform the resource scheduling tasks of other edge devices.
Fig. 5 is a schematic structural diagram of a resource scheduling device for face recognition provided in the present application. Referring to fig. 5, the resource scheduling apparatus 10 for face recognition may include:
a determining module 11, configured to determine a plurality of face recognition terminals and a plurality of edge devices, where the plurality of edge devices are configured to assist the plurality of face recognition terminals in performing face recognition;
the determining module 11 is further configured to determine historical service information and a target face recognition task of each face recognition terminal, and determine historical identification information and historical resource occupation information of each edge device;
the determining module 11 is further configured to determine a target edge device corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge device, and the historical resource occupation information;
And the control module 12 is configured to control the plurality of edge devices to assist the plurality of face recognition terminals in performing face recognition according to the target edge device corresponding to each face recognition terminal.
The resource scheduling device for face recognition provided in the embodiment of the present application has similar implementation principles and technical effects to those of the above embodiment, and specific reference may be made to the above embodiment, which is not repeated here.
In one possible implementation, the determining module 11 is specifically configured to:
aiming at any face recognition terminal, determining the prediction request quantity of the face recognition terminal in a future period according to the historical service information of the face recognition terminal and a target face recognition task;
for any one edge device, determining the maximum identification amount of the edge device in the future period according to the historical identification information and the historical resource occupation information of the edge device;
and determining the target edge equipment corresponding to each face recognition terminal according to the predicted request quantity of each face recognition terminal and the maximum recognition quantity of each edge equipment.
In one possible implementation manner, the historical service information includes an actual processing amount and a historical task amount corresponding to each of a plurality of historical time periods; the determining module 11 is specifically further configured to:
For any one history period, determining a task deviation amount corresponding to the history period according to the actual processing amount and the history task amount of the history period;
determining a target task deviation amount according to the task deviation amount of each history period;
and determining a target task amount according to the target face recognition task, and determining the sum of the target task amount and the target task deviation amount as the predicted request amount.
In one possible implementation manner, the history identification information includes a history identification amount corresponding to each history period in the plurality of history periods, and the history resource occupation information includes a resource occupation amount corresponding to each history period; the determining module 11 is specifically further configured to:
for any one history period, determining an estimated maximum recognition quantity corresponding to the history period according to the history recognition quantity and the resource occupation quantity corresponding to the history period;
and determining the maximum recognition quantity according to the estimated maximum recognition quantity corresponding to each historical period.
In one possible implementation, the control module 12 is specifically configured to:
determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
Generating resource allocation information according to target edge equipment corresponding to each face recognition terminal and the target time period, wherein the resource allocation information comprises the identification of the target edge equipment corresponding to each face recognition terminal and the target time period;
storing the resource allocation information and the update time of the resource allocation information in a preset storage space, wherein the preset storage space is a shared storage space of the plurality of face recognition terminals and the plurality of edge devices;
and sending notification messages to the plurality of edge devices and the plurality of face recognition terminals, wherein the notification messages are used for indicating the resource allocation information to be updated and indicating the plurality of edge devices to assist the corresponding face recognition terminals to carry out face recognition according to the resource allocation information.
In a possible implementation, the determining module 11 is specifically further configured to:
determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
determining a plurality of historical time periods according to the target time period, wherein the target time period and the historical time period are the same time period in different statistical periods;
And aiming at any face recognition terminal, acquiring the historical task amount of the face recognition terminal in each historical period, and determining the historical service information of the face recognition terminal, wherein the historical service information comprises the historical task amount of the face recognition terminal in each historical period.
Fig. 6 is a schematic structural diagram of another resource scheduling device for face recognition provided in the present application. Referring to fig. 6, based on the structure of the face recognition resource scheduling device 10 shown in fig. 5, the face recognition resource scheduling device 10 may further include a sending module 13, where:
the determining module 11 is further configured to determine assistance information, where the assistance information includes a plurality of face recognition types, and priority and face recognition precision corresponding to each face recognition type;
the sending module 13 is configured to send the assistance information to the edge device, so that the edge device assists the face recognition terminal to perform face recognition according to the assistance information; the face recognition terminal is used for determining image features of face images, and the edge equipment is used for recognizing the face according to the image features.
Fig. 7 is a schematic hardware structure of a resource scheduling device for face recognition provided in the present application. Referring to fig. 7, the face recognition resource scheduling device 20 may include a processor 21 and a memory 22. Wherein the processor 21 and the memory 22 may communicate; the processor 21 and the memory 22 are in communication via a communication bus 23, as an example.
The memory 22 is used for storing computer-executable instructions;
the processor 21 is configured to execute the computer-executable instructions stored in the memory 22, so that the processor 21 executes the resource scheduling method for face recognition as shown in the above-mentioned method embodiment.
Optionally, the face-recognition resource scheduling device 20 may further comprise a communication interface, which may comprise a transmitter and/or a receiver.
Alternatively, the processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital SignalProcessor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor or in a combination of hardware and software modules within a processor.
The application provides a computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, and the computer executable instructions are used for realizing the resource scheduling method for face recognition according to any embodiment when being executed by a processor.
The present application provides a computer program product comprising a computer program which, when executed by a processor, causes the computer to perform the above-described resource scheduling method for face recognition.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be appreciated that the various numerical numbers referred to in the embodiments of the present application are merely for ease of description and are not intended to limit the scope of the embodiments of the present application. In the present application, the term "include" and variations thereof may refer to non-limiting inclusion; the term "or" and variations thereof may refer to "and/or". The terms "first," "second," and the like in this application are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. In the present application, "plurality" means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. The resource scheduling method for face recognition is characterized by comprising the following steps:
determining a plurality of face recognition terminals and a plurality of edge devices, wherein the plurality of edge devices are used for assisting the plurality of face recognition terminals in face recognition;
determining historical service information and target face recognition tasks of each face recognition terminal, and determining historical identification information and historical resource occupation information of each edge device;
determining target edge equipment corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge equipment and the historical resource occupation information;
and controlling the plurality of edge devices to assist the plurality of face recognition terminals to carry out face recognition according to the target edge devices corresponding to each face recognition terminal.
2. The method of claim 1, wherein determining the target edge device corresponding to each face recognition terminal based on the historical traffic information of each face recognition terminal, the target face recognition task, the historical identification information of each edge device, and the historical resource occupancy information, comprises:
Aiming at any face recognition terminal, determining the prediction request quantity of the face recognition terminal in a future period according to the historical service information of the face recognition terminal and a target face recognition task;
for any one edge device, determining the maximum identification amount of the edge device in the future period according to the historical identification information and the historical resource occupation information of the edge device;
and determining the target edge equipment corresponding to each face recognition terminal according to the predicted request quantity of each face recognition terminal and the maximum recognition quantity of each edge equipment.
3. The method of claim 2, wherein the historical business information includes an actual throughput and a historical task volume corresponding to each of a plurality of historical time periods;
according to the historical service information of the face recognition terminal and the target face recognition task, determining the predicted request quantity of the face recognition terminal in a future period comprises the following steps:
for any one history period, determining a task deviation amount corresponding to the history period according to the actual processing amount and the history task amount of the history period;
determining a target task deviation amount according to the task deviation amount of each history period;
And determining a target task amount according to the target face recognition task, and determining the sum of the target task amount and the target task deviation amount as the predicted request amount.
4. The method of claim 2, wherein the history identification information includes a history identification amount corresponding to each of a plurality of history periods, and the history resource occupation information includes a resource occupation amount corresponding to each of the history periods;
determining the maximum identification amount of the edge device in the future period according to the historical identification information and the historical resource occupation information of the edge device, wherein the method comprises the following steps:
for any one history period, determining an estimated maximum recognition quantity corresponding to the history period according to the history recognition quantity and the resource occupation quantity corresponding to the history period;
and determining the maximum recognition quantity according to the estimated maximum recognition quantity corresponding to each historical period.
5. The method according to any one of claims 1-4, wherein controlling the plurality of edge devices to assist the plurality of face recognition terminals in face recognition according to the target edge device corresponding to each face recognition terminal includes:
Determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
generating resource allocation information according to target edge equipment corresponding to each face recognition terminal and the target time period, wherein the resource allocation information comprises the identification of the target edge equipment corresponding to each face recognition terminal and the target time period;
storing the resource allocation information and the update time of the resource allocation information in a preset storage space, wherein the preset storage space is a shared storage space of the plurality of face recognition terminals and the plurality of edge devices;
and sending notification messages to the plurality of edge devices and the plurality of face recognition terminals, wherein the notification messages are used for indicating the resource allocation information to be updated and indicating the plurality of edge devices to assist the corresponding face recognition terminals to carry out face recognition according to the resource allocation information.
6. The method according to any one of claims 1-4, wherein determining historical traffic information for each face recognition terminal comprises:
determining a target period corresponding to the target face recognition task, wherein the target face recognition task is to be executed in the target period;
Determining a plurality of historical time periods according to the target time period, wherein the target time period and the historical time period are the same time period in different statistical periods;
and aiming at any face recognition terminal, acquiring the historical task amount of the face recognition terminal in each historical period, and determining the historical service information of the face recognition terminal, wherein the historical service information comprises the historical task amount of the face recognition terminal in each historical period.
7. The method according to any one of claims 1-4, further comprising:
determining assistance information, wherein the assistance information comprises a plurality of face recognition types, and priority and face recognition precision corresponding to each face recognition type;
sending the assistance information to the edge equipment so that the edge equipment assists the face recognition terminal to carry out face recognition according to the assistance information; the face recognition terminal is used for determining image features of face images, and the edge equipment is used for recognizing the face according to the image features.
8. A resource scheduling apparatus for face recognition, comprising:
the device comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining a plurality of face recognition terminals and a plurality of edge devices, and the plurality of edge devices are used for assisting the plurality of face recognition terminals in face recognition;
The determining module is further used for determining historical service information and target face recognition tasks of each face recognition terminal, and determining historical identification information and historical resource occupation information of each edge device;
the determining module is further configured to determine a target edge device corresponding to each face recognition terminal according to the historical service information of each face recognition terminal, the target face recognition task, the historical identification information of each edge device, and the historical resource occupation information;
and the control module is used for controlling the plurality of edge devices to assist the plurality of face recognition terminals to carry out face recognition according to the target edge devices corresponding to each face recognition terminal.
9. A resource scheduling device for face recognition, comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173401.0A CN117726925B (en) | 2024-02-07 | Face recognition resource scheduling method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410173401.0A CN117726925B (en) | 2024-02-07 | Face recognition resource scheduling method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117726925A true CN117726925A (en) | 2024-03-19 |
| CN117726925B CN117726925B (en) | 2024-06-04 |
Family
ID=
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403173A (en) * | 2017-08-21 | 2017-11-28 | 合肥麟图信息科技有限公司 | A kind of face identification system and method |
| CN114840328A (en) * | 2021-01-14 | 2022-08-02 | 腾讯科技（深圳）有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN115345621A (en) * | 2022-06-30 | 2022-11-15 | 黄飞霞 | Payment method, system and platform with payment function |
| CN116600017A (en) * | 2020-12-02 | 2023-08-15 | 武汉联影医疗科技有限公司 | Resource scheduling method, system, device, computer equipment and storage medium |
| WO2023173664A1 (en) * | 2022-03-18 | 2023-09-21 | 上海商汤智能科技有限公司 | Face recognition method and apparatus, electronic device, storage medium, computer program, and program product |
| CN117519973A (en) * | 2023-11-07 | 2024-02-06 | 中国工商银行股份有限公司 | Resource adjusting method, device and equipment |
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403173A (en) * | 2017-08-21 | 2017-11-28 | 合肥麟图信息科技有限公司 | A kind of face identification system and method |
| CN116600017A (en) * | 2020-12-02 | 2023-08-15 | 武汉联影医疗科技有限公司 | Resource scheduling method, system, device, computer equipment and storage medium |
| CN114840328A (en) * | 2021-01-14 | 2022-08-02 | 腾讯科技（深圳）有限公司 | Face recognition method and device, electronic equipment and storage medium |
| WO2023173664A1 (en) * | 2022-03-18 | 2023-09-21 | 上海商汤智能科技有限公司 | Face recognition method and apparatus, electronic device, storage medium, computer program, and program product |
| CN115345621A (en) * | 2022-06-30 | 2022-11-15 | 黄飞霞 | Payment method, system and platform with payment function |
| CN117519973A (en) * | 2023-11-07 | 2024-02-06 | 中国工商银行股份有限公司 | Resource adjusting method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108449286B (en) | Network bandwidth resource allocation method and device | |
| CN108848037A (en) | Service request processing method, device, computer equipment and storage medium | |
| WO2021051269A1 (en) | Information acquisition method, information acquisition apparatus and electronic device | |
| CN112988390A (en) | Calculation power resource allocation method and device | |
| EP3306866A1 (en) | Message processing method, device and system | |
| CN115348264A (en) | Multi-tenant cloud service management method, device, equipment and storage medium | |
| CN113242149B (en) | Long connection configuration method, apparatus, device, storage medium, and program product | |
| CN117726925B (en) | Face recognition resource scheduling method, device and equipment | |
| CN113835876A (en) | Artificial intelligent accelerator card scheduling method and device based on domestic CPU and OS | |
| CN117726925A (en) | Face recognition resource scheduling method, device and equipment | |
| CN111736988A (en) | Heterogeneous acceleration method, equipment and device and computer readable storage medium | |
| CN115081983A (en) | Order dispatching method, device, equipment and storage medium | |
| CN114138453B (en) | Resource optimization allocation method and system suitable for edge computing environment | |
| CN115169797A (en) | Working dog calling method and related device | |
| CN111858019B (en) | Task scheduling method and device and computer readable storage medium | |
| CN111258747B (en) | Service efficiency control method and device | |
| CN111866159A (en) | Method, system, device and storage medium for calling artificial intelligence service | |
| CN109062707A (en) | The method that is communicated between electronic device and its limiting process, storage medium | |
| CN112738199B (en) | Scheduling method and scheduling system | |
| CN113391923B (en) | System resource data allocation method and device | |
| CN110009464B (en) | Cross-time zone business processing method, server, computing device and storage medium | |
| CN117093343A (en) | Asynchronous task execution control method, device, equipment and storage medium | |
| CN114443247A (en) | Task scheduling method and device | |
| CN117519973A (en) | Resource adjusting method, device and equipment | |
| KR20240001522A (en) | Edge computing-based video analysis method using participant analysis |
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 |