CN115591229A - Verification method and system for distributed network battle training - Google Patents
Verification method and system for distributed network battle training Download PDFInfo
- Publication number
- CN115591229A CN115591229A CN202211349763.8A CN202211349763A CN115591229A CN 115591229 A CN115591229 A CN 115591229A CN 202211349763 A CN202211349763 A CN 202211349763A CN 115591229 A CN115591229 A CN 115591229A
- Authority
- CN
- China
- Prior art keywords
- training
- verified
- individual
- training individual
- supervision
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
- A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
- A63F13/30—Interconnection arrangements between game servers and game devices; Interconnection arrangements between game devices; Interconnection arrangements between game servers
- A63F13/35—Details of game servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Electrically Operated Instructional Devices (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
A verification method and a system for distributed network battle training are provided, the method comprises the following steps: determining whether verified training individuals exist according to the interaction frequency and the picture change amplitude of each training individual in the current unit time; if the verification result exists, determining the short-distance supervision and the remote supervision corresponding to each verified training individual according to the IP address of each verified training individual; establishing P2P connection between the verified training individual and the corresponding close-range supervision and remote supervision; and sending the interactive information of each verified training individual to corresponding close-range supervision and remote supervision for violation verification through P2P connection, if the close-range supervision judges that the verified training individual violates the rules, sending the interactive information of the verified training individual to the remote supervision corresponding to the verified training individual through P2P connection for violation verification, if the remote supervision judges that the verified training individual violates the rules, determining that the verified training individual violates the rules, and otherwise, determining that the verified training individual does not violate the rules.
Description
Technical Field
The invention relates to the technical field of battle training verification, in particular to a verification method and a verification system for distributed network battle training.
Background
The distributed network battle training system is very close to the design mode of a distributed game, and in an extreme case, all fighting logics are operated at a server side or a client side, wherein the former is called a cloud service mode, and the latter is called a client side mode. Both have synchronization problems.
If the map is completely placed at the server end to operate, the map is too large, the number of people is large, the pressure calculated by the server end and the pressure of synchronous data are increased sharply, and the experience is possibly deteriorated and even the whole system is crashed due to the fact that the line is dropped because of network congestion when a large group is in intensive combat.
In order to reduce the stress of the training server and improve the overall performance of the training system, there are 2 current solutions, 1 is an elastic server solution, and 1 is a P2P solution. The former is to dynamically set the scale of a server cluster and the bandwidth of a server to cope with a dynamically changing simulation combat time period, but in reality, the server does not perform logic migration and expansion or bandwidth redirection at once, and ideal elastic geometry cannot be realized. Secondly, p2p is a widely used client synchronization technology, can effectively disperse server pressure, and has been widely used in donkey downloading and block chain synchronization.
However, in the P2P scheme, the training client has own execution logic, and the verification of the training individuals is mainly concentrated on the client, so that the client illegally tampers with training data or execution logic, resulting in unfair training and incapability of accurately verifying the illegal training individuals.
Disclosure of Invention
In view of the foregoing analysis, the embodiments of the present invention provide a verification method for distributed network battle training, so as to solve the problems of high verification pressure and low verification efficiency of the existing server.
On one hand, the embodiment of the invention provides a verification method for distributed network battle training, which comprises the following steps:
determining whether a verified training individual exists in the current unit time according to the interactive frequency and the picture change amplitude of each training individual in the current unit time; if present, then
Determining the short-distance supervision and the remote supervision corresponding to each verified training individual according to the IP address of each verified training individual; establishing P2P connection between the verified training individual and the corresponding close-range supervision and remote supervision;
and sending the interactive information of each verified training individual to the close-range supervision and remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the close-range supervision judges that the verified training individual is violated, sending the interactive information of the verified training individual to the remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the remote supervision judges that the verified training individual is violated, determining that the verified training individual is violated, and otherwise, determining that the verified training individual is not violated.
Further, determining whether the verified training individual exists in the current unit time according to the interaction frequency and the picture change amplitude of each training individual in the current unit time includes:
obtaining the picture change amplitude of each training individual according to the similarity of the initial picture frame and the ending picture frame of each training individual in the current unit time; calculating the interaction frequency of each training individual in the current unit time;
and if the picture change amplitude of the training individual in the current unit time is larger than the first threshold and the interaction frequency of the training individual is abnormal, judging the training individual as a verified training individual.
Further, the following method is adopted to judge whether the interaction frequency of the training individuals is abnormal or not:
if the interaction frequency of the training individual is greater than a second threshold value, judging that the interaction frequency of the training individual is abnormal; if the interaction frequency of the training individual is less than or equal to a second threshold value and is greater than the median of the average interaction frequency and the highest interaction frequency of the training individual, judging that the interaction frequency of the training individual is abnormal; otherwise, judging that the interaction frequency of the training individual is not abnormal.
Further, the following method is adopted to determine the close-range supervision and the remote supervision corresponding to each verified training individual according to the IP address of the verified training individual:
according to the IP address of the verified training individual, selecting a training individual of which the routing node with the verified training individual is smaller than a third threshold value from the training individuals in the same scene with the verified training individual as a short-distance supervision corresponding to the verified training individual;
and selecting the training individuals of which the routing nodes with the verified training individuals are larger than a fourth threshold value as remote supervision according to the IP addresses of the verified training individuals.
Further, the interactive information sent to the close-range supervision comprises: interactive input of the verified training individual in the current unit time, interactive input of other training individuals received by the verified training individual and an ending picture of the verified training individual;
the close-range supervision calculates to obtain a first result picture based on self interaction logic according to the received interaction information;
and if the first result picture is different from the end picture of the verified training individual, judging that the verified training individual violates the rules by close-distance supervision, and otherwise, judging that the verified training individual does not violate the rules.
Further, the interactive information sent to the remote monitor includes an initial scene frame of a scene where the verified training individual is located in the current unit time, interactive input of the verified training individual, interactive input of other training individuals received by the verified training individual, and an end picture of the verified training individual;
the remote supervision calculates to obtain a second result picture based on self interactive logic according to the received interactive information;
if the second result picture is different from the finishing picture of the verified training individual, remotely supervising and judging that the verified training individual violates rules, otherwise judging that the verified training individual does not violate rules.
Further, according to the IP address of the verified training individual, selecting a training individual with a routing node smaller than a third threshold value and with a reliability larger than a fifth threshold value from the training individuals in the same scene with the verified training individual as the close-range supervision corresponding to the verified training individual.
Further according to the formula
Calculating the credibility c of the training individuals, wherein n 4 Indicates the number of times the training individual is designated as close-range supervision, n 3 N is the number of times that the judgment result differs from that of the remote supervision when the training individual is used as the close supervision 2 Representing the number of times that the training individual is the verified training individual, n 1 Indicating the number of times the training individual is judged to be an illegal training individual.
Further, the similarity of the initial picture frame and the ending picture frame of each training individual in the current unit time is calculated by adopting an SSIM structural similarity algorithm.
Compared with the prior art, the verification method has the advantages that the training individuals with high cheating possibility are determined to be selected as the verified training individuals according to the interaction frequency and the picture change amplitude of the training individuals, all the training individuals do not need to be verified, and the verification efficiency is improved; and when the close-range supervision judges that the verified training individual violates rules, the verification is further carried out through the remote supervision, so that the condition of misjudgment caused by the close-range supervision is avoided, and the verification is more accurate. The verified training individuals establish P2P connection with close-range supervision and remote supervision, interactive information is directly transmitted through the P2P connection and does not pass through a server, so that the pressure of a server is reduced, and the verification efficiency is improved.
On the other hand, the embodiment of the invention provides a verification system for distributed network battle training, which comprises the following modules:
the verification starting module is used for determining whether the verified training individuals exist in the current unit time according to the interaction frequency and the picture change amplitude of each training individual in the current unit time; if present, then
The supervision specifying module is used for determining the short-distance supervision and the remote supervision corresponding to each verified training individual according to the IP address of the verified training individual; establishing P2P connection between the verified training individual and the corresponding close-range supervision and remote supervision;
and the verification module is used for sending the interactive information of each verified training individual to the close-range supervision and remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the close-range supervision judges that the verified training individual is in violation, sending the interactive information of the verified training individual to the remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the remote supervision judges that the verified training individual is in violation, determining that the verified training individual is in violation, and if not, determining that the verified training individual is in violation.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
FIG. 1 is a flow chart of a verification method for distributed network battle training according to an embodiment of the present invention;
fig. 2 is a block diagram of a verification system for distributed network battle training according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The specific embodiment of the invention discloses a verification method for distributed network battle training, which comprises the following steps as shown in fig. 1:
s1, determining whether a verified training individual exists in current unit time according to the interaction frequency and the picture change amplitude of each training individual in the current unit time; if present, then
S2, determining short-distance supervision and remote supervision corresponding to each verified training individual according to the IP address of the verified training individual; establishing P2P connection between the verified training individual and the corresponding close-range supervision and remote supervision;
and S3, sending the interactive information of each verified training individual to the close-range supervision and remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the close-range supervision judges that the verified training individual is violated, sending the interactive information of the verified training individual to the remote supervision corresponding to the verified training individual through the P2P connection for violation verification, if the remote supervision judges that the verified training individual is violated, determining that the verified training individual is violated, and otherwise, determining that the verified training individual is not violated.
The battlefield information density in the fight training is changed, and attack and defense are not organized at all times. The cheating motivation of the training individuals also changes along with the battlefield requirements, generally speaking, the dense attack and defense tend to cheat and make rules, so that the training individuals with high cheating possibility are determined and selected as the verified training individuals according to the interaction frequency and the picture change amplitude of the training individuals, all the training individuals do not need to be verified, and the verification efficiency is improved; and when the close-range supervision judges that the verified training individual violates rules, the verification is further carried out through the remote supervision, so that the condition of erroneous judgment caused by the close-range supervision is avoided, and the verification is more accurate. The verified training individuals establish P2P connection with close-range supervision and remote supervision, interactive information is directly transmitted through the P2P connection and does not pass through a server, so that the pressure of a server is reduced, and the verification efficiency is improved.
In practice, the unit time may be set to 1 second, that is, it is determined whether the training individual is the object to be verified according to the interaction frequency and the picture change of the training individual in each second. The current unit time refers to a unit time period from one second before the current time to the current time.
Specifically, determining whether a verified training individual exists in the current unit time according to the interaction frequency and the picture change amplitude of each training individual in the current unit time includes:
s11, obtaining the picture change amplitude of each training individual according to the similarity of the initial picture frame and the ending picture frame of each training individual in the current unit time; calculating the interaction frequency of each training individual in the current unit time;
during implementation, the initial picture frame and the ending picture frame of each training individual in the current unit time are obtained, the similarity of the initial picture frame and the ending picture frame is compared, so that the picture change range of the training individuals is obtained, and the information density of the battlefield of the training individuals is judged. Wherein the picture frame is a lossless compressed or uncompressed digital image.
During implementation, the similarity of the initial picture frame and the ending picture frame of each training individual in the current unit time can be calculated by adopting an SSIM (structural similarity) algorithm. SSIM structural similarity is an index for measuring similarity between two images, and the specific calculation process may refer to the prior art and is not described herein.
Training individual picture change amplitude = 1-similarity of initial and end picture frames.
In normal scene switching, the change range of two frames is large, so that the interaction frequency of the training individuals also needs to be calculated when judging whether the training individuals need to be checked. The higher the interaction frequency of the training individual, the higher the likelihood of a violation.
Specifically, the interaction frequency is the number of times of training individual interaction inputs in a unit time. The number of times of interactive input operation of the training individuals in unit time through the interactive equipment can be counted, and the interactive frequency of the training individuals in the current unit time is obtained. Such as a mouse, keyboard, touch screen, joystick, etc.
S12, if the picture change amplitude of the training individual in the current unit time is larger than a first threshold value and the interaction frequency of the training individual is abnormal, judging that the training individual is a verified training individual.
Through the interaction frequency and the picture change range of the training individuals, the training individuals with higher cheating possibility can be locked for verification. And if the picture change amplitude of the training individual is larger than the first threshold value and the interaction frequency of the training individual is abnormal, determining the training individual as a verified training individual needing verification. In practice, the first threshold may be determined based on the verification efficiency requirement. The smaller the first threshold value is, the more training individuals are checked in each unit time, and the training experience of normal training individuals can be influenced; the larger the first threshold value is, the smaller the number of training individuals to be verified per unit time is, and there may be a case where a cheating training individual is missed to be verified.
Specifically, the following method is adopted to judge whether the interaction frequency of the training individuals is abnormal or not:
if the interaction frequency of the training individual is greater than a second threshold value, judging that the interaction frequency of the training individual is abnormal; if the interaction frequency of the training individual is less than or equal to a second threshold value and is greater than the median of the average interaction frequency and the highest interaction frequency of the training individual, judging that the interaction frequency of the training individual is abnormal; otherwise, judging that the interaction frequency of the training individual is not abnormal.
In practice, the number of operations Per Minute is referred to the common concept of gaming APM (Actions Per Minute). The APM of a common professional player can be as high as 300 or more, and the highest record is 600APM at present. Therefore, the second threshold may be set to 60 times/second. And if the interaction input of the training individual per second exceeds 60 times, the training individual is considered to have abnormal interaction frequency.
Considering individual differences, the operating frequency of some people is naturally low, and 150APM of the people can be fierce war, but another person can be 150APM at ordinary times, and the peak period can reach 300APM. Therefore, if the interaction frequency of the training individual in the current unit time does not exceed the second threshold but is greater than the median of the average interaction frequency and the highest interaction frequency of the training individual, the interaction frequency of the training individual is considered to be abnormal.
And calculating the interaction frequency and the picture change amplitude of each training individual in the current unit time, thereby judging whether the verified training individual needing to be verified exists in the current unit time. If the verified training individual exists, in step S2, the following method is adopted to determine the short-distance supervision and the remote supervision corresponding to each verified training individual according to the IP address of each verified training individual:
s21, selecting training individuals of which the routing nodes with the verified training individuals are smaller than a third threshold value from the training individuals in the same scene with the verified training individuals according to the IP addresses of the verified training individuals as short-distance supervision corresponding to the verified training individuals;
and S22, selecting the training individuals of which the routing nodes with the verified training individuals are larger than a fourth threshold value as remote supervision according to the IP addresses of the verified training individuals.
Specifically, the close-range supervision refers to a supervisor close to the verified training individual, the remote supervision refers to a supervisor far away from the verified training individual, and the distance refers to a network topological distance. The close-range supervision and the verified training individuals are in the same scene, and the number of intermediate routing nodes in network topology connection is small, so that the network conditions are close, and training scene images do not need to be transmitted additionally, so that the verification efficiency is high. In practice, the third threshold may be set to 3.
The number of the routing nodes between the remote supervision individual and the verified training individual is larger than a fourth threshold value, namely, the remote supervision individual and the verified training individual have a certain distance, so that verification judgment is more objective. In practice, the fourth threshold may be set to 10.
It should be noted that the training individuals satisfying the conditions can be used for both close-range supervision and remote supervision, but the same training individual cannot simultaneously perform close-range supervision and remote supervision.
After the short-distance supervision and the remote supervision corresponding to the verified training individual are determined, the P2P connection between the verified training individual and the short-distance supervision and the remote supervision is established. By establishing the direct-connected P2P connection, the network transmission and verification work is separated from the server, and the verification calculation pressure of the server is reduced.
The situation that system data are modified by mutual agreement among all training client sides is avoided by randomly appointing a short-distance supervision mode and a long-distance supervision mode, and therefore safety of the system data is guaranteed.
Specifically, the interactive information sent to the close-range supervision in step S3 includes: interactive input of the verified training individual in the current unit time, interactive input of other training individuals received by the verified training individual and an end picture of the verified training individual;
the close-range supervision calculates to obtain a first result picture based on self interaction logic according to the received interaction information;
and if the first result picture is different from the end picture of the verified training individual, judging that the verified training individual violates the rules by close-distance supervision, and otherwise, judging that the verified training individual does not violate the rules.
Specifically, the interactive input of the verified training individual comprises interactive input data and interactive input time of the verified training individual; the interactive input of the other training individuals received by the verified training individual comprises the received interactive input data and interactive input data time of the other training individuals.
It should be noted that, the distributed battle training engine collects and distributes the interactive actions of all the individuals participating in training, and for all the training individuals in a battlefield, the interactive information of other training individuals in the current battlefield is obtained as the basis for visual rendering.
Since the close-range supervision and the verified training individual are in the same training scenario, there is no need to send training scenario data to the close-range supervision.
Each training client side is provided with interactive logic, and the training individuals cheat by modifying the interactive logic of the client sides, so that the interactive information of the verified training individuals is sent to the close-range supervision, the close-range supervision carries out picture calculation according to the interactive logic of the training individuals and compares the picture calculation with the calculation result of the verified training individuals, and whether the verified training individuals cheat or not can be verified.
When the verification method is implemented, close-range supervision is based on a scene image when the current unit time is initial, scene change information is calculated according to self interactive logic according to received interactive information, rendering is carried out according to the visual angle and the screen resolution of the verified training individual, a first result picture is obtained, if the first result picture is different from the end picture of the verified training individual, the close-range supervision judges that the verified training individual violates rules, and otherwise, the verified training individual does not violate the rules.
In implementation, whether the first result picture is the same as the end picture of the verified training individual is judged by adopting a pixel-by-pixel comparison method, so that errors caused by sliding windows of the methods such as the ssim and the like are avoided. Theoretically, the image calculation models of the close-range supervision and the verified training individuals are consistent, and the self-contained error is small, so that if the number of different pixel points exceeds a small number, for example, 3 pixels, it can be judged that the first result picture is different from the end picture of the verified training individual, the verified training individual breaks rules, and the network freezing is carried out on the verified training individual.
And if the close-range supervision judges that the verified training individual violates the rules, further performing violation verification through remote supervision.
Specifically, the interactive information sent to the remote monitor in step S3 includes an initial scene frame of a scene where the verified training individual is located in the current unit time, interactive input of the verified training individual, interactive input of other training individuals received by the verified training individual, and an end picture of the verified training individual;
the remote supervision calculates to obtain a second result picture based on self interactive logic according to the received interactive information;
if the second result picture is different from the end picture of the verified training individual, remotely supervising and judging that the verified training individual violates the rules, otherwise, judging that the verified training individual does not violate the rules.
Because the remote supervision and the verified training individual may not be in the same training scene, the interactive information sent to the remote supervision is more than the interactive information sent to the close training individual by the initial scene frame of the scene in which the verified training individual is located in the current unit time.
And remote supervision is carried out on the basis of the initial scene frame of the current unit time, scene change information is calculated according to received interactive information and self interactive logic, rendering is carried out according to the visual angle and the screen resolution of the verified training individual to obtain a second result picture, if the second result picture is different from the end picture of the verified training individual, the verified training individual is judged to be in violation by close supervision, and otherwise, the verified training individual is judged to be in violation.
In implementation, similarly, the method for determining whether the second result frame is identical to the ending frame of the verified training individual is the same as the method for determining whether the first result frame is identical to the ending frame of the verified training individual, or a pixel-by-pixel comparison method is adopted, and if the number of different pixels exceeds a smaller number (the same as the determination criterion for determining whether the first result frame is identical to the ending frame of the verified training individual), for example, 3 pixels, it can be determined that the second result frame is different from the ending frame of the verified training individual, and the verified training individual is in violation.
And freezing the verified training individual when the verified training individual is judged to be in violation by short-distance supervision, removing the freezing of the verified training individual if the verified training individual is judged to be not in violation by long-distance supervision, and performing offline or warning treatment and other subsequent application level treatment on the verified training individual if the verified training individual is judged to be in violation by long-distance supervision, wherein the verified training individual is proved to be in violation indeed.
In an embodiment of the present invention, to further improve the reliability of the verification, step S21 may also adopt the following manner:
and selecting the training individuals with the routing nodes smaller than the third threshold value and the credibility larger than the fifth threshold value from the training individuals in the same scene with the verified training individuals as the short-distance supervision corresponding to the verified training individuals according to the IP addresses of the verified training individuals.
In particular, according to the formula
Calculating the credibility c of the training individuals, wherein n 4 Indicates the number of times the training individual is designated as close-range supervision, n 3 N represents the number of times that the judgment result differs from that of the remote supervision when the individual is trained as the close supervision 2 Representing the number of times that the training individual is the verified training individual, n 1 Indicating the number of times the training individual is judged to be an illegal training individual.
By selecting the training individuals with higher reliability as close-range supervision, the verification reliability is improved, and the condition of collusion violation is avoided.
In implementation, although the battlefield information density is high, verification is needed, and violation may exist at ordinary times, so that the training individuals with high reliability can be regularly selected as the remote supervision, the training individuals with low reliability can be used as the verified training individuals for verification, and the specific verification process can refer to the verification process of the remote supervision on the verified training individuals in the step S3.
A specific embodiment of the present invention discloses a verification system for distributed network battle training, as shown in fig. 2, including the following modules:
the verification starting module is used for determining whether the verified training individuals exist in the current unit time according to the interaction frequency and the picture change amplitude of each training individual in the current unit time; if present, then
The supervision specifying module is used for determining the short-distance supervision and the remote supervision corresponding to each verified training individual according to the IP address of the verified training individual; establishing P2P connection between the verified training individual and the corresponding close-range supervision and remote supervision;
and the verification module is used for sending the interactive information of each verified training individual to the close-range supervision and remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the close-range supervision judges that the verified training individual is violated, sending the interactive information of the verified training individual to the remote supervision corresponding to the verified training individual through the P2P connection for violation verification, if the remote supervision judges that the verified training individual is violated, determining that the verified training individual is violated, and otherwise, determining that the verified training individual is not violated.
The method embodiment and the system embodiment are based on the same principle, and related parts can be used for reference, and the same technical effect can be achieved. For the specific implementation process, reference is made to the foregoing embodiments, which are not described herein again.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A verification method for distributed network battle training is characterized by comprising the following steps:
determining whether verified training individuals exist in the current unit time or not according to the interaction frequency and the picture change amplitude of each training individual in the current unit time; if present, then
Determining the short-distance supervision and the remote supervision corresponding to each verified training individual according to the IP address of each verified training individual; establishing P2P connection between the verified training individual and the corresponding close-range supervision and remote supervision;
and sending the interactive information of each verified training individual to the close-range supervision and remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the close-range supervision judges that the verified training individual is violated, sending the interactive information of the verified training individual to the remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the remote supervision judges that the verified training individual is violated, determining that the verified training individual is violated, and otherwise, determining that the verified training individual is not violated.
2. The verification method for distributed network battle training according to claim 1, wherein determining whether the verified training individuals exist in the current unit time according to the interaction frequency and the picture variation amplitude of each training individual in the current unit time comprises:
obtaining the picture change amplitude of each training individual according to the similarity of the initial picture frame and the ending picture frame of each training individual in the current unit time; calculating the interaction frequency of each training individual in the current unit time;
and if the picture change amplitude of the training individual in the current unit time is larger than the first threshold and the interaction frequency of the training individual is abnormal, judging the training individual as a verified training individual.
3. The verification method for distributed network battle training according to claim 1, wherein the following method is adopted to determine whether the interaction frequency of the training individuals is abnormal:
if the interaction frequency of the training individuals is larger than a second threshold value, judging that the interaction frequency of the training individuals is abnormal; if the interaction frequency of the training individual is less than or equal to a second threshold value and is greater than the median of the average interaction frequency and the highest interaction frequency of the training individual, judging that the interaction frequency of the training individual is abnormal; otherwise, judging that the interaction frequency of the training individual is not abnormal.
4. The verification method for distributed network battle training as claimed in claim 1, wherein the short-distance supervision and the remote supervision corresponding to each verified training individual are determined according to the IP address of the verified training individual by the following method:
according to the IP address of the verified training individual, selecting a training individual of which the routing node with the verified training individual is smaller than a third threshold value from the training individuals in the same scene with the verified training individual as a short-distance supervision corresponding to the verified training individual;
and selecting the training individuals of which the routing nodes with the verified training individuals are larger than a fourth threshold value as remote supervision according to the IP addresses of the verified training individuals.
5. The distributed network combat training verification method of claim 1, wherein the interactive information sent to the close-range supervision comprises: interactive input of the verified training individual in the current unit time, interactive input of other training individuals received by the verified training individual and an end picture of the verified training individual;
the close-range supervision calculates to obtain a first result picture based on self interaction logic according to the received interaction information;
and if the first result picture is different from the end picture of the verified training individual, judging that the verified training individual violates the rules by close-distance supervision, and otherwise, judging that the verified training individual does not violate the rules.
6. The distributed network combat training verification method according to claim 1, wherein the interactive information sent to the remote monitor includes an initial scene frame of a scene where the verified training individual is located in the current unit time, interactive inputs of the verified training individual, interactive inputs of other training individuals received by the verified training individual, and an end picture of the verified training individual;
the remote supervision calculates to obtain a second result picture based on self interactive logic according to the received interactive information;
if the second result picture is different from the finishing picture of the verified training individual, remotely supervising and judging that the verified training individual violates rules, otherwise judging that the verified training individual does not violate rules.
7. The verification method for distributed network battle training as claimed in claim 4, wherein according to the IP address of the verified training individual, the training individuals in the same scene with the verified training individual are selected as the training individuals with routing nodes smaller than the third threshold and reliability greater than the fifth threshold as the close-range supervision corresponding to the verified training individual.
8. The distributed network combat training verification method of claim 7, wherein said verification method is based on a formula
Calculating the credibility c of the training individuals, wherein n 4 Indicates the number of times the training individual is designated as close-range supervision, n 3 N is the number of times that the judgment result differs from that of the remote supervision when the training individual is used as the close supervision 2 Representing the number of times the training individual is the verified training individual, n 1 Indicating the number of times the training individual is judged to be an illegal training individual.
9. The verification method for distributed network battle training as claimed in claim 2, wherein the similarity of the initial frame and the ending frame of each training individual in the current unit time is calculated by using SSIM structural similarity algorithm.
10. The utility model provides a distributed network training's calibration system of fighting which characterized in that includes following module:
the verification starting module is used for determining whether the verified training individuals exist in the current unit time according to the interaction frequency and the picture change amplitude of each training individual in the current unit time; if present, then
The supervision specifying module is used for determining the short-distance supervision and the remote supervision corresponding to each verified training individual according to the IP address of the verified training individual; establishing P2P connection between the verified training individual and the corresponding close-range supervision and remote supervision;
and the verification module is used for sending the interactive information of each verified training individual to the close-range supervision and remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the close-range supervision judges that the verified training individual is in violation, sending the interactive information of the verified training individual to the remote supervision corresponding to the verified training individual for violation verification through the P2P connection, if the remote supervision judges that the verified training individual is in violation, determining that the verified training individual is in violation, and if not, determining that the verified training individual is in violation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211349763.8A CN115591229B (en) | 2022-10-31 | 2022-10-31 | Verification method and system for distributed network combat training |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211349763.8A CN115591229B (en) | 2022-10-31 | 2022-10-31 | Verification method and system for distributed network combat training |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115591229A true CN115591229A (en) | 2023-01-13 |
| CN115591229B CN115591229B (en) | 2023-07-25 |
Family
ID=84850761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211349763.8A Active CN115591229B (en) | 2022-10-31 | 2022-10-31 | Verification method and system for distributed network combat training |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115591229B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080317356A1 (en) * | 2007-06-25 | 2008-12-25 | Masaya Itoh | Image monitoring system |
| CN109045702A (en) * | 2018-07-24 | 2018-12-21 | 网易（杭州）网络有限公司 | A kind of plug-in detection method, device, calculates equipment and medium at system |
| WO2020004815A1 (en) * | 2018-06-25 | 2020-01-02 | 주식회사 수아랩 | Method of detecting anomaly in data |
| CN111298434A (en) * | 2020-02-25 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Service processing method, device, equipment and storage medium |
| CN111437609A (en) * | 2020-03-27 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Plug-in detection method and device |
| CN113521749A (en) * | 2021-07-15 | 2021-10-22 | 珠海金山网络游戏科技有限公司 | Abnormal account detection model training method and abnormal account detection method |
| CN113926201A (en) * | 2021-11-24 | 2022-01-14 | 网易（杭州）网络有限公司 | Plug-in identification method and device, electronic equipment and storage medium |
| CN114344917A (en) * | 2022-01-29 | 2022-04-15 | 腾讯科技（深圳）有限公司 | Operation data verification method and device, storage medium and electronic equipment |
| JP2022092455A (en) * | 2020-12-10 | 2022-06-22 | 株式会社ミクシィ | Information processing unit, program and information processing method |
-
2022
- 2022-10-31 CN CN202211349763.8A patent/CN115591229B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080317356A1 (en) * | 2007-06-25 | 2008-12-25 | Masaya Itoh | Image monitoring system |
| WO2020004815A1 (en) * | 2018-06-25 | 2020-01-02 | 주식회사 수아랩 | Method of detecting anomaly in data |
| CN109045702A (en) * | 2018-07-24 | 2018-12-21 | 网易（杭州）网络有限公司 | A kind of plug-in detection method, device, calculates equipment and medium at system |
| CN111298434A (en) * | 2020-02-25 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Service processing method, device, equipment and storage medium |
| CN111437609A (en) * | 2020-03-27 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Plug-in detection method and device |
| JP2022092455A (en) * | 2020-12-10 | 2022-06-22 | 株式会社ミクシィ | Information processing unit, program and information processing method |
| CN113521749A (en) * | 2021-07-15 | 2021-10-22 | 珠海金山网络游戏科技有限公司 | Abnormal account detection model training method and abnormal account detection method |
| CN113926201A (en) * | 2021-11-24 | 2022-01-14 | 网易（杭州）网络有限公司 | Plug-in identification method and device, electronic equipment and storage medium |
| CN114344917A (en) * | 2022-01-29 | 2022-04-15 | 腾讯科技（深圳）有限公司 | Operation data verification method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115591229B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11876697B2 (en) | Extensible network traffic engineering platform for increasing network resiliency in cloud applications | |
| Baughman et al. | Cheat-proof playout for centralized and peer-to-peer gaming | |
| Liu et al. | Incentive-based modeling and inference of attacker intent, objectives, and strategies | |
| CN110585723B (en) | Cheating user detection method, device and equipment based on block chain and storage medium | |
| CN113728362A (en) | Augmented reality moving edge computing | |
| CN113660128B (en) | Network equipment fault prediction method, electronic equipment and storage medium | |
| CN109045702A (en) | A kind of plug-in detection method, device, calculates equipment and medium at system | |
| US11765196B2 (en) | Attack scenario simulation device, attack scenario generation system, and attack scenario generation method | |
| CN112749496B (en) | Equipment system combat effectiveness evaluation method and system based on time sequence combat ring | |
| CN115189908A (en) | Random attack survivability evaluation method based on network digital twin | |
| CN107347064B (en) | Cloud computing platform situation prediction method based on neural network algorithm | |
| Pan et al. | A hybrid interest management mechanism for peer-to-peer networked virtual environments | |
| Zhang et al. | Analysing the benefit of selfish mining with multiple players | |
| CN114363212A (en) | Equipment detection method, device, equipment and storage medium | |
| CN115591229B (en) | Verification method and system for distributed network combat training | |
| CN113114492A (en) | Security situation perception algorithm based on Markov differential game block chain model | |
| CN117061257A (en) | Network security assessment system | |
| CN113487041B (en) | Transverse federal learning method, device and storage medium | |
| CN115190027A (en) | Natural fault survivability evaluation method based on network digital twin body | |
| CN115189910A (en) | Network digital twin-based deliberate attack survivability evaluation method | |
| CN115099421A (en) | Group-oriented federal learning system | |
| Roberts et al. | Bounding inconsistency using a novel threshold metric for dead reckoning update packet generation | |
| CN113559506B (en) | Automatic testing method and device for frame synchronization and readable storage medium | |
| JP2006285806A (en) | Data processing system, data transmission device, and methods thereof | |
| CN115862417B (en) | Virtual simulation system and simulation method for integrated attack and defense exercise learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |