CN110121171B - Trust prediction method based on exponential smoothing method and gray model - Google Patents
Trust prediction method based on exponential smoothing method and gray model Download PDFInfo
- Publication number
- CN110121171B CN110121171B CN201910388791.2A CN201910388791A CN110121171B CN 110121171 B CN110121171 B CN 110121171B CN 201910388791 A CN201910388791 A CN 201910388791A CN 110121171 B CN110121171 B CN 110121171B
- Authority
- CN
- China
- Prior art keywords
- sequence
- value
- smoothing
- trust
- gray model
- 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.)
- Expired - Fee Related
Links
- 238000009499 grossing Methods 0.000 title claims abstract description 181
- 238000000034 method Methods 0.000 title claims abstract description 156
- 238000012360 testing method Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000012546 transfer Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000006854 communication Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/009—Security arrangements; Authentication; Protecting privacy or anonymity specially adapted for networks, e.g. wireless sensor networks, ad-hoc networks, RFID networks or cloud networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
- H04W12/121—Wireless intrusion detection systems [WIDS]; Wireless intrusion prevention systems [WIPS]
- H04W12/122—Counter-measures against attacks; Protection against rogue devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/60—Context-dependent security
- H04W12/66—Trust-dependent, e.g. using trust scores or trust relationships
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/46—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for vehicle-to-vehicle communication [V2V]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
Abstract
After a historical trust value sequence of a target vehicle in a vehicle-mounted ad hoc network is obtained, smoothing is carried out on the historical trust value sequence according to the optimal value of the smoothing coefficient in the exponential smoothing method which is determined in advance to obtain a smooth trust value sequence, and then the smooth trust value sequence is input into a gray model which is constructed based on the optimal value of the smoothing coefficient to obtain a trust prediction result. Therefore, the method utilizes the exponential smoothing method to process the historical trust value sequence, reduces the interference of random fluctuation of the sequence on the prediction result, and in addition, the method simultaneously performs parameter optimization on the smoothing coefficient of the exponential smoothing method and the target function of the gray model, thereby further improving the accuracy of the prediction result. The application also provides a trust prediction device, equipment and a computer readable storage medium based on the exponential smoothing method and the gray model, and the function of the trust prediction device corresponds to the method.
Description
Technical Field
The present application relates to the field of communication security, and in particular, to a trust prediction method, apparatus, device, and computer-readable storage medium based on an exponential smoothing method and a gray model.
Background
Vehicle Ad-hoc Networks (VANET for short) refer to an open wireless communication network formed by mutual communication between vehicles, between vehicles and fixed access points, and between vehicles and pedestrians in a traffic environment. At present, routing security becomes a non-negligible security problem in a vehicle-mounted ad hoc network, and in order to effectively identify malicious vehicles and ensure reliable transmission of data between vehicles, a trust prediction mechanism is generally applied to a routing protocol.
Disclosure of Invention
The application aims to provide a trust prediction method, a trust prediction device, trust prediction equipment and a computer-readable storage medium based on an exponential smoothing method and a gray model, which are used for solving the problem that the traditional trust prediction scheme is low in prediction accuracy. The specific scheme is as follows:
in a first aspect, the present application provides a confidence prediction method based on an exponential smoothing method and a gray model, including:
acquiring a historical trust value sequence of a target vehicle in a vehicle-mounted ad hoc network;
according to the optimal value of a smoothing coefficient in a predetermined exponential smoothing method, smoothing the historical trust value sequence to obtain a smooth trust value sequence;
and inputting the smooth trust value sequence into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result.
Optionally, the obtaining a historical trust value sequence of a target vehicle in the vehicle-mounted ad hoc network includes:
acquiring a historical interaction record between a current vehicle and a target vehicle in a vehicle-mounted ad hoc network;
dividing the historical interaction record into a plurality of sub-interaction records according to a preset evaluation period;
and determining the packet forwarding rate of each sub-interaction record to obtain a packet forwarding rate sequence as the historical trust value sequence of the target vehicle.
Optionally, before the step of inputting the smooth confidence value sequence into a gray model constructed based on the optimal value of the smoothing coefficient, the method further includes:
determining the weight of the background value of the gray model according to the optimal value of the smoothing coefficient and a preset transfer function, wherein the preset transfer function is as follows:
a is the weight of the background value, λ * Taking the optimal value of the smoothing coefficient;
and constructing the gray model according to the weight of the background value and an objective function of the general gray model.
Optionally, before performing smoothing processing on the historical trust value sequence according to the optimal value of the smoothing coefficient in the predetermined exponential smoothing method, the method further includes:
and adjusting the value of the smoothing coefficient by using a golden section searching method taking the average absolute percentage error as an objective function until the optimal value of the smoothing coefficient is obtained.
Optionally, the step of inputting the smooth confidence value sequence into a gray model constructed based on the optimal value of the smoothing coefficient to obtain a confidence prediction result includes:
acquiring an influence factor sequence of the target vehicle;
according to the optimal value of the smoothing coefficient, smoothing the influence factor sequence to obtain a smooth influence factor sequence;
and inputting the smooth trust value sequence and the smooth influence factor sequence into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result.
Optionally, the obtaining of the sequence of influencing factors of the target vehicle includes:
and acquiring the transaction quantity sequence and the transaction frequency sequence of the target vehicle as influence factor sequences.
In a second aspect, the present application provides a confidence prediction apparatus based on an exponential smoothing method and a gray model, including:
an acquisition module: the vehicle-mounted ad hoc network trust value sequence acquiring method comprises the steps of acquiring a historical trust value sequence of a target vehicle in the vehicle-mounted ad hoc network;
a smoothing module: the device is used for smoothing the historical trust value sequence according to the optimal value of a smoothing coefficient in a predetermined exponential smoothing method to obtain a smooth trust value sequence;
a prediction module: and the smooth trust value sequence is input into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result.
Optionally, the method further includes:
an optimal value determination module: the method is used for adjusting the value of the smoothing coefficient by using a golden section searching method taking the average absolute percentage error as an objective function until the optimal value of the smoothing coefficient is obtained.
In a third aspect, the present application further provides a trust prediction apparatus based on an exponential smoothing method and a gray model, including:
a memory: for storing a computer program;
a processor: for executing the computer program to implement the steps of the trust prediction method based on exponential smoothing and grey model as described above.
In a fourth aspect, the present application further provides a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, is configured to implement the steps of the trust prediction method based on exponential smoothing and grey model as described above.
According to the trust prediction method based on the exponential smoothing method and the gray model, after a historical trust value sequence of a target vehicle in a vehicle-mounted ad hoc network is obtained, smoothing is carried out on the historical trust value sequence according to the optimal value of the smoothing coefficient in the exponential smoothing method, a smooth trust value sequence is obtained, then the smooth trust value sequence is input into the gray model constructed based on the optimal value of the smoothing coefficient, and a trust prediction result is obtained. Therefore, the method utilizes the exponential smoothing method to process the historical trust value sequence, reduces the interference of the random fluctuation of the sequence to the prediction result, and in addition, the method carries out parameter optimization on the smoothing coefficient of the exponential smoothing method and the objective function of the gray model, thereby further improving the accuracy of the prediction result.
The application also provides a trust prediction device, equipment and a computer readable storage medium based on an exponential smoothing method and a gray model, and the functions of the trust prediction device and the equipment correspond to the method, and are not described again.
Drawings
For a clearer explanation of the embodiments or technical solutions of the prior art of the present application, the drawings needed for the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart illustrating a first implementation of a trust prediction method based on an exponential smoothing method and a gray model according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating an implementation of a second embodiment of a trust prediction method based on an exponential smoothing method and a gray model provided by the present application;
fig. 3 is a flowchart illustrating an implementation of a search process for an optimal value of a smoothing coefficient in a second embodiment of a trust prediction method based on an exponential smoothing method and a gray model provided in the present application;
FIG. 4 is a functional block diagram of an embodiment of a trust prediction apparatus based on an exponential smoothing method and a gray model provided in the present application;
fig. 5 is a schematic structural diagram of an embodiment of a trust prediction apparatus based on an exponential smoothing method and a gray model provided in the present application.
Detailed Description
The core of the application is to provide a trust prediction method, a trust prediction device, trust prediction equipment and a computer readable storage medium based on an exponential smoothing method and a gray model, and the accuracy of trust prediction in a vehicle-mounted ad hoc network is obviously improved.
In order that those skilled in the art will better understand the disclosure, the following detailed description is given with reference to the accompanying drawings. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Referring to fig. 1, a first embodiment of a trust prediction method based on an exponential smoothing method and a gray model provided by the present application is described below, where the first embodiment includes:
step S101: acquiring a historical trust value sequence of a target vehicle in a vehicle-mounted ad hoc network;
the vehicle-mounted ad hoc network is an open wireless communication network formed by mutual communication between vehicles and between the vehicles and a fixed access point in a traffic environment, and the vehicle-mounted ad hoc network has an open characteristic, so that malicious vehicles which are pushed to other vehicles or even attacked safely are easy to appear, and potential safety hazards are brought to the communication process. The embodiment aims to predict the credibility of the target vehicle at the future time according to the historical trust value sequence of the target vehicle so as to ensure the safety and reliability of the communication process.
The embodiment can be realized based on a current vehicle of the vehicle-mounted ad hoc network, and also can be realized based on a fixed access point in the vehicle-mounted ad hoc network, wherein the current vehicle or the fixed access point is used as a trust subject, and the target vehicle is used as a trust object. Specifically, the historical trust value sequence of the target vehicle may be obtained by: the method comprises the steps of obtaining historical interaction records of a current vehicle and a target vehicle, dividing the historical interaction records into a plurality of sub-interaction records according to time, and obtaining a historical trust value sequence by determining trust value information in each sub-interaction record. As a specific implementation manner, the present embodiment may select a packet forwarding rate corresponding to the sub-interaction record to measure the magnitude of the trust value.
Step S102: according to the optimal value of a smoothing coefficient in a predetermined exponential smoothing method, smoothing the historical trust value sequence to obtain a smooth trust value sequence;
the exponential smoothing method is a deterministic smoothing prediction method developed on the basis of a moving average method, and the essence of the method is to smooth a time sequence by calculating an exponential smoothing average value and eliminating random fluctuation in a historical statistical sequence. The smoothing coefficient directly influences the accuracy of prediction by the exponential smoothing method, so that the key step in the exponential smoothing method is to determine the value of the smoothing coefficient, and the prediction error can be effectively reduced by finding out the optimal value. The embodiment determines the optimal value of the smoothing coefficient in advance, and performs smoothing processing on the historical trust value sequence by using an exponential smoothing method according to the optimal value to obtain a smooth trust value sequence.
Step S103: and inputting the smooth trust value sequence into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result.
The gray model is a model for predicting a gray system, in the embodiment, part of information in the gray system is known, the other part of information is unknown, and the relationship among factors in the system is uncertain.
As described above, creating an appropriate objective function of the gray model is a key to realize prediction, and considering that the background value is one of important parameters affecting the performance of the gray model when the objective function of the general gray model is known, this embodiment constructs a weight of the background value based on the optimal coefficient of the smoothing coefficient, and determines the background value according to the weight of the background value, and then determines the gray parameters of the gray model, and finally determines the objective function of the gray model.
Since the key factor affecting the performance of the gray model is the background value, and the background value of the gray model in this embodiment is constructed based on the smoothing coefficient, which is the key factor affecting the performance of the exponential smoothing method, the prediction result can be obtained after the smoothing sequence after the exponential smoothing processing is input into the gray model, and the prediction result is adjusted according to the actual result, that is, the value of the smoothing coefficient is adjusted, and finally, the optimal value of the smoothing coefficient can be determined.
After obtaining a historical trust value sequence of a target vehicle in a vehicle-mounted ad hoc network, smoothing the historical trust value sequence according to a predetermined optimal value of a smoothing coefficient in the exponential smoothing method to obtain a smooth trust value sequence, and then inputting the smooth trust value sequence into a gray model constructed based on the optimal value of the smoothing coefficient to obtain a trust prediction result. Therefore, the method utilizes the exponential smoothing method to process the historical trust value sequence, reduces the interference of the random fluctuation of the sequence to the prediction result, and in addition, the method carries out parameter optimization on the smoothing coefficient of the exponential smoothing method and the objective function of the gray model, thereby further improving the accuracy of the prediction result.
The second embodiment of the trust prediction method based on the exponential smoothing method and the gray model provided by the present application is described in detail below, and is implemented based on the first embodiment, and is expanded to a certain extent on the basis of the first embodiment.
Referring to fig. 2, the second embodiment specifically includes:
step S201: acquiring a historical interaction record between a current vehicle and a target vehicle in a vehicle-mounted ad hoc network;
step S202: dividing the historical interaction records into a plurality of sub-interaction records according to a preset evaluation period;
specifically, in order to effectively predict the trust value of the target vehicle, the history of interaction between the current vehicle and the target vehicle is first divided into m evaluation periods.
Step S203: and determining the data packet forwarding rate of each sub-interaction record to obtain a data packet forwarding rate sequence as a historical trust value sequence of the target vehicle, and determining the transaction quantity and the transaction frequency of each sub-interaction record as an influence factor sequence.
From the sub-interaction records between the current vehicle and the target vehicle in each evaluation period, the trust value of the target vehicle in each evaluation period can be obtained, and the historical trust value sequence can be represented by the following formula:
wherein the trust value in the t evaluation period
N s (t) is the total number of packets received by the target vehicle during the tth evaluation period, N r (t) is the total number of data packets forwarded by the target vehicle during the tth evaluation period.
The embodiment considers that some influence factors influence the calculation of the trust value, so as to be a preferable implementation mode, when predicting the trust value of the target vehicle, the embodiment comprehensively considers the historical trust value of the target vehicle and the influence factors. Specifically, in this embodiment, the transaction number and the transaction frequency are selected to measure the magnitude of the influencing factor, and the sequence of the influencing factor may be a i 0 To show that:
wherein n represents the total number of influencing factors.
It should be noted that the number of the above influencing factors and what kind of parameters are selected to measure the influencing factors are only used as an implementation manner provided by this embodiment, and this is not limited in this application.
Step S204: integrating the historical trust value sequence and the influence factor sequence to obtain an original sequence, smoothing the original sequence according to the current value of the smoothing coefficient to obtain a smooth sequence, and obtaining an accumulated sequence according to the smooth sequence;
in the embodiment, random fluctuation in the smooth trust value sequence and the smooth influence factor sequence is eliminated by an exponential smoothing method, so that the error of the subsequent prediction result is reduced. The linear model of the exponential smoothing method is as follows:
y t+p ＝A t +B t ·p (3)
where t is the current time period, p is the predicted time period in advance, y t+p As a predictor at time t + p, B t And A t The values of (a) are as follows:
A t ＝2S t ′-S t ″ (4)
wherein S is t ′＝αF t +(1-α)S t ′ -1 ，S t ″＝αS t ′+(1-α)S t ″ -1 Alpha is a smoothing coefficient, F t Is an initial value at time t, S t ' and S t ′ -1 Is the first smoothed value at t and t-1, S t "and S t ″ -1 Is the second smoothed value at t and t-1. S 1 ′＝S 1 ″＝F 1 ，S 1 ' and S 1 "represents the first and second smoothed values at the beginning, F 1 Representing the original value of the initial time.
It can be seen that the smoothing coefficient directly affects the accuracy of the predicted value. Therefore, the key step in the exponential smoothing method is to determine the value of the smoothing coefficient, and the methods generally used for determining the smoothing coefficient are empirical estimation methods, trial and error methods, and the like. However, the common disadvantage of the two methods is that the prediction researchers must perform iteration and calculation for multiple times to obtain the optimal value of the smoothing coefficient, and the obtaining of the optimal value is closely related to knowledge, professional experience and the calculation number of the prediction researchers. In order to overcome the disadvantages of the two methods, a golden section search method may be used to search for the optimal value of the smoothing coefficient, and the following will describe the process of searching for the optimal value in detail, and will not be further described here.
Specifically, according to the current value of the smoothing coefficient, the historical trust value sequence and the influence factor sequence are smoothed to obtain a smoothed trust value sequence and a smoothed influence factor sequence. For aspect expression, the embodiment integrates the historical trust value sequence and the influence factor sequence, and utilizes the original sequence
To represent the integration result of the two, in order to make the original sequence
The requirements of the gray scale model are met, the embodiment adopts a first exponential smoothing method to smooth the gray scale model, and finally obtains a smoothing sequence, namely an integration result of a smoothing trust value sequence and a smoothing influence factor sequence, and the specific processing process is as follows:
wherein i is 1,2, 1., n, k is 2,3, m,
is a smoothed sequence after processing, lambda * Is the current value of the smoothing coefficient.
Then, an accumulated sequence is obtained from the smoothed sequence
The process is as follows:
step S205: constructing a gray model according to the current value of the smoothing coefficient;
in the conventional gray model, the weight of the background value is fixed and is usually set to 0.5, but this default value may cause a large prediction error. Therefore, the present embodiment redefines the weight by using the current value of the smoothing coefficient, thereby optimizing the background value in the gray model. The formula is as follows:
wherein the content of the first and second substances,
representing the background value, and alpha is the weight of the background value.
Then, a matrix C is solved according to the optimized background value, a matrix D is calculated according to the smooth sequence, and finally, gray parameters X and Y of a gray model are solved according to the matrix C and the matrix D:
where H is an (n +1) X nth order matrix, X T Representing the first n rows, Y, of the matrix H T The last row of the matrix H is represented. The gray parameters X and Y can be obtained by transposing the two matrices, respectively.
In summary, in this embodiment, the weight of the background value of the gray model is determined according to the current value of the smoothing coefficient and the preset conversion function, and then the target function of the gray model is constructed according to the weight of the background value and the target function of the general gray model. Wherein the predetermined transfer function is:
a is the weight of the background value, λ * And taking the current value of the smoothing coefficient.
It should be noted that the execution sequence of step S205 is not limited in this embodiment, and it is only necessary to ensure that step S205 precedes step S206.
Step S206: inputting the accumulated sequence into a gray model constructed based on the current value of the smoothing coefficient to obtain a trust prediction result;
according to a grey model, sequence
Is predicted sequence of
Can be calculated from the grey parameters X and Y. The calculation formula is as follows:
wherein, the sequence
Is a cumulative sequence
The part of the sequence corresponding to the historical trust valueAnd (4) sequencing.
The prediction sequence can be obtained by the first-order inverse accumulation generation operation
Finally, a historical trust value sequence is obtained by utilizing an inverse exponential smoothing method
The corresponding predicted sequences are as follows:
step S207: judging whether the trust prediction result meets the fitting error, if not, entering a step S208, otherwise, entering a step S209;
step S208: adjusting the current value of the smoothing coefficient by using a golden section searching method taking the average absolute percentage error as an objective function, and entering the step S204;
according to the prediction process, the value of the smoothing coefficient directly influences the smoothing performance of the exponential smoothing method and the accuracy of the gray model. How to determine the optimal value of the smoothing coefficient, minimizing the prediction error is the most critical problem at present. The traditional method for determining the optimal value of the smoothing coefficient needs multiple iterations, and calculation and even human intervention are very inefficient. Therefore, the embodiment adjusts the value of the smoothing coefficient based on an improved golden section searching method until the optimal value is reached.
The golden section search is a method of finding the most value by continuously narrowing the known range of the most value of the unimodal function, and the conventional golden section method determines the optimal smoothing coefficient using the mean square error as an objective function. As a preferred embodiment, the present embodiment more accurately reflects the deviation between the predicted value and the actual value by calculating the Mean Absolute Percent Error (MAPE). Specifically, the value of the mean absolute percentage error is expressed using a function f, as follows:
step S209: and outputting a final trust prediction result corresponding to the optimal value of the smoothing coefficient.
In summary, trust prediction plays an important role in establishing a secure route, and the trust prediction method based on the exponential smoothing method and the gray model provided by the embodiment combines the gray model, the exponential smoothing prediction method and the improved golden section search method, and avoids the influence of data fluctuation on a prediction result by processing an original sequence; by considering the influence factors associated with the trust value, the accuracy of prediction is further improved; in addition, the gray model is constructed based on the smooth coefficient, when the smooth coefficient is optimized, the performance of the exponential smoothing method and the performance of the gray model are optimized, and the purpose of improving the accuracy of trust prediction in the vehicle-mounted ad hoc network is finally achieved.
As shown in fig. 3, the following describes in detail a process of calculating an optimal value of a smoothing parameter by using an improved golden section search method in the second embodiment, where the process includes:
step S301: dividing the value range of the smooth coefficient into a plurality of subintervals, and selecting a target subinterval to find the optimal value of the smooth coefficient;
specifically, λ ∈ (0,1) is equally divided into 10 subintervals, and λ is used respectively 1 ,λ 2 ,...,λ 10 To indicate that one of the subintervals λ is selected i E (a, b) to find the optimal value of the smoothing coefficient, wherein a and b respectively represent the left endpoint and the right endpoint of the ith interval.
Step S302: two test points in the target subinterval can be obtained by using a golden section searching method;
specifically, the first test point and the second test point are respectively as follows:
λ i ＝0.618a+0.382b (17)
λ i ′＝0.382a+0.618b (18)
step S303: judging whether the two test points meet a preset relation, if not, entering a step S304, otherwise, entering a step S305;
specifically, whether two test points satisfy the formula | λ is judged i -λ i ' | < δ, where δ ═ 0.01.
Step S304: respectively calculating results corresponding to the two test points according to an objective function of the improved golden section searching method, and updating the two test points according to the size relationship of the results corresponding to the two test points;
specifically, the MAPE value f (λ) is calculated i ) And calculating the MAPE value f (lambda) i '). If f (λ) i )＞f(λ i '), let a equal to λ i ，λ i ＝λ i The values of' and b are kept constant and lambda is recalculated i '; if f (λ) i )＜f(λ i ') and let b equal to λ i ′，λ i ′＝λ i The value of a is kept constant and lambda is recalculated i 。
Step S305: and determining the optimal value of the smoothing coefficient according to the two test points.
Specifically, the optimal value of the smoothing coefficient can be obtained according to the following formula: lambda * ＝(λ i -λ i ′)/2。
In order to further explain the implementation effect of the scheme of the application, the application performs a simulation experiment, and the simulation experiment is briefly introduced below.
Specifically, the present embodiment uses the NS2 platform to calculate the trust value, transaction amount, and transaction frequency of the vehicle in 10 cycles, respectively, and uses the data of the first 8 cycles as the original sequence, as shown in table 1.
TABLE 1
| Period of time | Trust value | Number of transactions | Frequency of transactions |
| 1 | 0.8336 | 563 | 6 |
| 2 | 0.7584 | 894 | 3 |
| 3 | 0.5796 | 265 | 2 |
| 4 | 0.9054 | 862 | 4 |
| 5 | 0.8778 | 964 | 3 |
| 6 | 0.6462 | 403 | 2 |
| 7 | 0.8245 | 1034 | 9 |
| 8 | 0.8963 | 326 | 3 |
The scheme, the traditional grey model and the improved Markov grey model are used for prediction based on the original sequence respectively, and prediction results are compared. The prediction results and errors for each model are shown in table 2. The present embodiment calculates the error by the difference between the predicted value and the true value, for example, the prediction error of the solution of the present application in the 9 th cycle is (|0.8684-0.8591|)/0.8591 × 100% — 1.08%, the average prediction error is 1.305%, which is much smaller than the average error of the conventional gray model and the improved markov gray model, which is 3.84%. Therefore, the prediction accuracy of the scheme of the application is obviously better than that of the other two models.
TABLE 2
Obviously, the simulation results show that the scheme of the application has higher prediction precision than other related prediction schemes.
The following describes a trust prediction apparatus based on an exponential smoothing method and a gray model provided in an embodiment of the present application, and the trust prediction apparatus based on the exponential smoothing method and the gray model described below and the trust prediction method based on the exponential smoothing method and the gray model described above may be referred to correspondingly.
As shown in fig. 4, the apparatus includes:
the acquisition module 401: the vehicle-mounted ad hoc network trust value sequence acquiring method comprises the steps of acquiring a historical trust value sequence of a target vehicle in the vehicle-mounted ad hoc network;
the smoothing module 402: the device is used for smoothing the historical trust value sequence according to the optimal value of a smoothing coefficient in a predetermined exponential smoothing method to obtain a smooth trust value sequence;
the prediction module 403: and the smooth trust value sequence is input into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result.
As a specific implementation, further comprising:
an optimal value determination module: the method is used for adjusting the value of the smoothing coefficient by using a golden section searching method taking the average absolute percentage error as an objective function until the optimal value of the smoothing coefficient is obtained.
The trust prediction apparatus based on the exponential smoothing method and the gray model of this embodiment is used to implement the foregoing trust prediction method based on the exponential smoothing method and the gray model, and therefore a specific implementation manner in the apparatus can be seen in the foregoing embodiment parts of the trust prediction method based on the exponential smoothing method and the gray model, for example, the obtaining module 401, the smoothing processing module 402, and the prediction module 403 are respectively used to implement steps S101, S102, and S103 in the trust prediction method based on the exponential smoothing method and the gray model. Therefore, the detailed description thereof may refer to the description of the respective partial embodiments, which will not be presented herein.
In addition, since the trust prediction apparatus based on the exponential smoothing method and the gray model of this embodiment is used to implement the trust prediction method based on the exponential smoothing method and the gray model, the role of the trust prediction apparatus corresponds to that of the above method, and details are not described here.
In addition, the present application also provides a trust prediction apparatus based on an exponential smoothing method and a gray model, as shown in fig. 5, including:
the memory 501: for storing a computer program;
the processor 502: for executing the computer program to implement the steps of the trust prediction method based on exponential smoothing and grey model as described above.
Finally, the present application provides a computer readable storage medium having stored thereon a computer program for implementing the steps of the trust prediction method based on exponential smoothing and grey model as described above when being executed by a processor.
The trust prediction device and the computer-readable storage medium based on the exponential smoothing method and the gray model of this embodiment are used to implement the trust prediction method based on the exponential smoothing method and the gray model, so the specific implementation of the device and the computer-readable storage medium can be found in the foregoing embodiment of the trust prediction method based on the exponential smoothing method and the gray model, and the functions of the device and the computer-readable storage medium correspond to the above embodiment of the method, and are not described here again.
In the present specification, the embodiments are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same or similar parts between the embodiments are referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The trust prediction method, apparatus, device and computer-readable storage medium based on the exponential smoothing method and the gray model provided by the present application are introduced in detail, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (8)
1. A trust prediction method based on an exponential smoothing method and a gray model is characterized by comprising the following steps:
acquiring a historical trust value sequence of a target vehicle in a vehicle-mounted ad hoc network;
according to the optimal value of a smoothing coefficient in a predetermined exponential smoothing method, smoothing the historical trust value sequence to obtain a smooth trust value sequence;
the optimal value of the smoothing coefficient calculated by using the improved golden section search method is specifically as follows:
dividing lambda epsilon (0,1) into 10 sub-intervals on average, and respectively using lambda 1 ,λ 2 ,...,λ 10 To indicate that one of the subintervals λ is selected i E (a, b) to find the optimal value of the smoothing coefficient, wherein a and b respectively represent the left endpoint and the right endpoint of the ith interval;
obtaining a first test point lambda in a target subinterval by using the golden section searching method i 0.618a +0.382b and a second test point λ' i ＝0.382a+0.618b；
Judging whether the first test point and the second test point satisfy a formula | lambda i -λ′ i |＜δ，δ＝0.01；
If the formula | λ is not satisfied i -λ′ i If the | is less than the δ, calculating results of the first test point and the second test point according to an objective function of a golden section search method, and updating the first test point and the second test point according to the magnitude relation of the results corresponding to the first test point and the second test point;
if the formula | λ is satisfied i -λ′ i If the | is less than the delta, determining the optimal value of the smoothing coefficient according to the first test point and the second test point;
the optimal value of the smoothing coefficient is specifically calculated by the following formula: lambda [ alpha ] * ＝(λ i -λ′ i )/2；
Inputting the smooth trust value sequence into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result;
wherein, the formula of the integration result of the smoothing trust value sequence and the smoothing influence factor sequence is as follows:
wherein i is 1,2, 1., n, k is 2,3, m,
is a smoothed sequence after processing, lambda * Is the current value of the smoothing coefficient;
obtaining an accumulated sequence from the smoothed sequence
The formula of (1) is as follows:
constructing the gray model according to the current value of the smoothing coefficient;
defining weight according to the current value of the smoothing coefficient and optimizing the background value of the gray model, wherein the specific formula is as follows:
wherein, the first and the second end of the pipe are connected with each other,
representing the background value, alpha being the background valueThe weight of (c);
solving a matrix C according to the optimized background value, calculating a matrix D according to the smooth sequence, and calculating gray parameters X and Y of the gray model according to the matrix C and the matrix D, wherein the specific formula is as follows:
where H is an (n +1) X nth order matrix, X T Representing the first n rows, Y, of the matrix H T Representing the last row of the matrix H, the gray parameters X and Y can be obtained by transposing the two matrices, respectively.
2. The method of claim 1, wherein the obtaining the historical sequence of trust values of the target vehicle in the on-board ad hoc network comprises:
acquiring a historical interaction record between a current vehicle and a target vehicle in a vehicle-mounted ad hoc network;
dividing the historical interaction record into a plurality of sub-interaction records according to a preset evaluation period;
and determining the data packet forwarding rate of each sub-interaction record to obtain a data packet forwarding rate sequence which is used as a historical trust value sequence of the target vehicle.
3. The method of claim 1, wherein prior to said inputting the sequence of smoothed confidence values into a gray model constructed based on optimal values of the smoothing coefficients, further comprising:
according to the optimal value of the smoothing coefficient and a preset conversion function,determining a weight of a background value of a gray model, wherein the preset transfer function is:
α is the weight of the background value, λ * Taking the optimal value of the smoothing coefficient;
and constructing the gray model according to the weight of the background value and an objective function of the general gray model.
4. The method according to any one of claims 1 to 3, wherein the inputting the smoothed confidence value sequence into a gray model constructed based on the optimal values of the smoothing coefficients to obtain a confidence prediction result comprises:
acquiring an influence factor sequence of the target vehicle;
according to the optimal value of the smoothing coefficient, smoothing the influence factor sequence to obtain a smooth influence factor sequence;
and inputting the smooth trust value sequence and the smooth influence factor sequence into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result.
5. The method of claim 4, wherein the obtaining the sequence of influencing factors for the target vehicle comprises:
and acquiring the transaction quantity sequence and the transaction frequency sequence of the target vehicle as influence factor sequences.
6. A confidence prediction device based on an exponential smoothing method and a gray model is characterized by comprising the following steps:
an acquisition module: the vehicle-mounted ad hoc network trust value sequence acquiring method comprises the steps of acquiring a historical trust value sequence of a target vehicle in the vehicle-mounted ad hoc network;
a smoothing module: the device is used for smoothing the historical trust value sequence according to the optimal value of a smoothing coefficient in a predetermined exponential smoothing method to obtain a smooth trust value sequence;
the optimal value of the smoothing coefficient is calculated by using an improved golden section search method as follows:
dividing lambda epsilon (0,1) into 10 sub-intervals on average, and respectively using lambda 1 ,λ 2 ,...,λ 10 Showing that one of the subintervals λ is selected i E (a, b) to find the optimal value of the smoothing coefficient, wherein a and b respectively represent the left endpoint and the right endpoint of the ith interval;
obtaining a first test point lambda in a target subinterval by using the golden section searching method i 0.618a +0.382b and a second test point λ i ′＝0.382a+0.618b；
Judging whether the first test point and the second test point satisfy a formula | lambda i -λ′ i |＜δ，δ＝0.01；
If the formula | λ is not satisfied i -λ′ i If the | is less than the δ, respectively calculating results of the first test point and the second test point according to an objective function of a golden section search method, and updating the first test point and the second test point according to the magnitude relation of the results corresponding to the first test point and the second test point;
if the formula | λ is satisfied i -λ′ i If the value is less than delta, determining the optimal value of the smoothing coefficient according to the first test point and the second test point;
the optimal value of the smoothing coefficient is specifically calculated by the following formula; lambda * ＝(λ i -λ′ i )/2；
A prediction module: the gray model is constructed based on the optimal value of the smoothing coefficient and used for inputting the smoothing trust value sequence to obtain a trust prediction result;
the optimal value of the smoothing coefficient can be obtained according to the following formula; lambda [ alpha ] * ＝(λ i -λ′ i )/2；
Inputting the smooth trust value sequence into a gray model constructed based on the optimal value of the smooth coefficient to obtain a trust prediction result;
wherein the formula of the integrated result of the smooth trust value sequence and the smooth influence factor sequence is as follows,
wherein i is 1,2, 1., n, k is 2,3, m,
is a smoothed sequence after processing, lambda * Is the current value of the smoothing coefficient;
obtaining a cumulative sequence from the smoothed sequence
The formula of (1) is:
constructing the gray model according to the current value of the smoothing coefficient;
defining weight according to the current value of the smoothing coefficient and optimizing the background value of the gray model, wherein the specific formula is as follows:
wherein, the first and the second end of the pipe are connected with each other,
representing a background value, α being a weight of the background value;
solving a matrix C according to the optimized background value, and calculating a matrix D according to the smooth sequence;
calculating gray parameters X and Y of the gray model according to the matrix C and the matrix D:
where H is an (n +1) X nth order matrix, X T Representing the first n rows, Y, of the matrix H T Representing the last row of the matrix H, the gray parameters X and Y can be obtained by transposing the two matrices, respectively.
7. A confidence prediction device based on exponential smoothing and gray model, comprising:
a memory: for storing a computer program;
a processor: steps for executing the computer program to implement the trust prediction method based on exponential smoothing and grey model according to any of claims 1-5.
8. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, is adapted to carry out the steps of the method for trust prediction based on exponential smoothing and gray model according to any of the claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388791.2A CN110121171B (en) | 2019-05-10 | 2019-05-10 | Trust prediction method based on exponential smoothing method and gray model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388791.2A CN110121171B (en) | 2019-05-10 | 2019-05-10 | Trust prediction method based on exponential smoothing method and gray model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110121171A CN110121171A (en) | 2019-08-13 |
| CN110121171B true CN110121171B (en) | 2022-09-27 |
Family
ID=67521922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910388791.2A Expired - Fee Related CN110121171B (en) | 2019-05-10 | 2019-05-10 | Trust prediction method based on exponential smoothing method and gray model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110121171B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111065089B (en) * | 2019-11-05 | 2020-11-27 | 东华大学 | Internet of vehicles bidirectional authentication method and device based on crowd sensing |
| CN111327464A (en) * | 2020-02-12 | 2020-06-23 | 安超云软件有限公司 | Method and system for determining virtual router |
| CN111612648B (en) * | 2020-05-19 | 2024-01-19 | 广东电网有限责任公司电力调度控制中心 | Training method and device for photovoltaic power generation prediction model and computer equipment |
| CN112200296B (en) * | 2020-07-31 | 2024-04-05 | 星宸科技股份有限公司 | Network model quantization method and device, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7239984B2 (en) * | 2003-12-23 | 2007-07-03 | Sap Ag | Outlier correction |
| EP2743726A1 (en) * | 2012-12-14 | 2014-06-18 | Koninklijke KPN N.V. | Methods and systems for assessing trust in a mobile ad hoc network |
| CN104038928A (en) * | 2014-03-26 | 2014-09-10 | 宋晓宇 | Method for calculating trust values of wireless Mesh network nodes |
| CN105761489A (en) * | 2016-04-13 | 2016-07-13 | 南京邮电大学 | Cubic exponential smoothing optimal method of traffic flow prediction |
| CN109728958A (en) * | 2019-03-11 | 2019-05-07 | 青岛大学 | A kind of network node trusts prediction technique, device, equipment and medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104145445B (en) * | 2012-03-06 | 2017-10-20 | 诺基亚技术有限公司 | Method, equipment and computer-readable recording medium for being securely accessed by social network data |
| CN103793601A (en) * | 2014-01-20 | 2014-05-14 | 广东电网公司电力科学研究院 | Turbine set online fault early warning method based on abnormality searching and combination forecasting |
| CN105447594A (en) * | 2015-11-17 | 2016-03-30 | 福州大学 | Electric power system grey load prediction method based on exponential smoothing |
| CN107239849A (en) * | 2017-04-17 | 2017-10-10 | 西安电子科技大学 | One kind is based on improved exponential smoothing gray model Methods of electric load forecasting |
| CN107705157A (en) * | 2017-10-19 | 2018-02-16 | 大连理工大学 | Automotive supplies Method for Sales Forecast method and system based on unified dynamic integrity model and meta-heuristic algorithm |
| CN108764523A (en) * | 2018-04-19 | 2018-11-06 | 石家庄铁道大学 | Predictive Methods of Road Accidents based on unbiased nonhomogeneous gray model and geneva model |
-
2019
- 2019-05-10 CN CN201910388791.2A patent/CN110121171B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7239984B2 (en) * | 2003-12-23 | 2007-07-03 | Sap Ag | Outlier correction |
| EP2743726A1 (en) * | 2012-12-14 | 2014-06-18 | Koninklijke KPN N.V. | Methods and systems for assessing trust in a mobile ad hoc network |
| CN104038928A (en) * | 2014-03-26 | 2014-09-10 | 宋晓宇 | Method for calculating trust values of wireless Mesh network nodes |
| CN105761489A (en) * | 2016-04-13 | 2016-07-13 | 南京邮电大学 | Cubic exponential smoothing optimal method of traffic flow prediction |
| CN109728958A (en) * | 2019-03-11 | 2019-05-07 | 青岛大学 | A kind of network node trusts prediction technique, device, equipment and medium |
Non-Patent Citations (3)
| Title |
|---|
| Trust management in vehicular ad hoc network: a systematic review;Seyed Ahmad Soleymani ect.;《EURASIP Journal onWireless Communications and Networking 2015》;20150523;全文 * |
| 基于指数平滑的无线Mesh网络改进信任模型;宋晓宇等;《计算机应用与软件》;20150915(第09期);全文 * |
| 基于黄金分割准则的混沌云粒子群算法;祁莹，苏宏升;《计算机工程与应用》;20130827;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110121171A (en) | 2019-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110121171B (en) | Trust prediction method based on exponential smoothing method and gray model | |
| Li et al. | An accumulative error based adaptive design of experiments for offline metamodeling | |
| US9697471B2 (en) | Device and method for managing plant model | |
| CN106933649B (en) | Virtual machine load prediction method and system based on moving average and neural network | |
| Gwiazda et al. | Structured population equations in metric spaces | |
| CN111914516B (en) | Method, device, equipment and storage medium for generating network data prediction sequence | |
| Yuen et al. | Real‐time substructural identification by boundary force modeling | |
| Waite et al. | Designs for generalized linear models with random block effects via information matrix approximations | |
| CN112732738A (en) | Adaptive network data acquisition method based on multi-objective optimization and related equipment | |
| JP7315007B2 (en) | LEARNING DEVICE, LEARNING METHOD AND LEARNING PROGRAM | |
| KR101492197B1 (en) | Method and device for sequential approximate optimization design | |
| JP2020067910A (en) | Learning curve prediction device, learning curve prediction method, and program | |
| CN110275895B (en) | Filling equipment, device and method for missing traffic data | |
| US9998347B2 (en) | Monitoring device usage | |
| US9537740B2 (en) | Monitoring device usage | |
| JP5636922B2 (en) | Performance prediction apparatus, performance prediction method, and program | |
| CN115048800A (en) | Minimum angle regression sparse identification method based on absolute angle stop criterion | |
| JP4820747B2 (en) | TRAVEL TIME CALCULATION DEVICE, PROGRAM, AND RECORDING MEDIUM | |
| CN108833138B (en) | Incremental dynamic community discovery method and system sensitive to error accumulation | |
| Francisco-Fernández et al. | Bandwidth selection for the local polynomial estimator under dependence: a simulation study | |
| Xing Zheng | On unbiased parameter estimation of linear systems using noisy measurements | |
| CN108090604A (en) | Based on the improved GM of trapezoid formula（1,1）Model prediction method | |
| US10169182B2 (en) | Monitoring levels of utilization of device | |
| JP4261456B2 (en) | Method and apparatus for estimating component concentration of mixture | |
| JPWO2018079366A1 (en) | Evaluation system, evaluation method, and evaluation program |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220927 |