CN116224248A - Interference intention reasoning method, storage medium and equipment - Google Patents
Interference intention reasoning method, storage medium and equipment Download PDFInfo
- Publication number
- CN116224248A CN116224248A CN202310278444.0A CN202310278444A CN116224248A CN 116224248 A CN116224248 A CN 116224248A CN 202310278444 A CN202310278444 A CN 202310278444A CN 116224248 A CN116224248 A CN 116224248A
- Authority
- CN
- China
- Prior art keywords
- interference
- intention
- electronic
- behavior
- pattern data
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/36—Means for anti-jamming, e.g. ECCM, i.e. electronic counter-counter measures
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
An interference intention reasoning method, a storage medium and equipment relate to the technical field of radar anti-interference. The method aims to solve the problems that the existing interference intention reasoning method is high in uncertainty of interference behaviors and subjective intention according to the identification of perception information, so that potential intention information of an interfering party is difficult to obtain, and the accuracy of interference intention reasoning is low. The invention comprises the following steps: acquiring electronic interference pattern data to be detected, preprocessing the electronic interference pattern data to be detected, and inputting the preprocessed electronic interference pattern data to be detected into an electronic interference behavior recognition network to obtain an electronic interference behavior type; inputting the electronic interference behavior type into an interference intention reasoning model, and obtaining an interference intention sequence with the highest probability by using a Viterbi algorithm as an interference intention reasoning result; the interference intents include: reduce detection, influence confirmation, get rid of tracking, destroy identification. The invention is used for reasoning the interference intention of the interference machine.
Description
Technical Field
The invention relates to the technical field of radar anti-interference, in particular to an interference intention reasoning method, a storage medium and equipment.
Background
Radar is indispensable in modern war, interference means aiming at radar are endangered, and game antagonism of radar and interference party is increasingly stronger. In the game countermeasure of radar and interference, an interference party is in an active position, and various interference means and measures are adopted aiming at the radar, so that the normal target detection of the paralyzed radar is influenced as much as possible. While radar is relatively passive in gaming, it is desirable to avoid or reduce the effects of interference as much as possible. If the information of the interfering party as rich as possible, such as behavior and intention information of the interference, can be obtained, the initiative of the radar in antagonism is greatly improved, so that the radar is more targeted to antagonism of deception interference, and the cognitive antagonism capability of the radar is improved.
During interference countermeasure, the jammer needs to take a series of interference actions, embodied by transmitting different patterns and modulated interference signals, in order to achieve a certain interference intention. The interference behavior and the interference pattern have a strong corresponding relation, and the interference behavior can be identified through the interference pattern identification result. However, at present, the radar party cannot obtain the direct interference intention of the enemy electronic warfare expert, the hidden actual intention of the enemy can only be inferred through the change of the observable interference behaviors or other observation parameters, and as the same interference intention may correspond to a plurality of interference behaviors, and the current interference behaviors are related to a plurality of previous interference behaviors, there is great uncertainty between the interference behaviors identified according to the perception information and the subjective intention, so that the potential intention information of the interference party is difficult to obtain, and further the problem of low accuracy of interference intention inference is caused.
Disclosure of Invention
The invention aims to solve the problems that the existing interference intention reasoning method is high in uncertainty of interference behaviors and subjective intention according to the identification of perception information, so that potential intention information of an interfering party is difficult to obtain, and the accuracy of interference intention reasoning is low.
The interference intention reasoning method comprises the following specific processes:
step one, acquiring electronic interference pattern data to be detected, preprocessing the electronic interference pattern data to be detected, and inputting the preprocessed electronic interference pattern data to be detected into an electronic interference behavior recognition network to obtain an electronic interference behavior type;
the electronic interference pattern dataset comprises: aiming interference, blocking interference, delay decoy interference, frequency shift decoy interference, distance towing interference, speed towing interference, aiming interference + dense decoy interference, intermittent sampling forwarding interference, distance decoy + speed decoy interference, distance towing + dense decoy interference;
inputting the electronic interference behavior type into an interference intention reasoning model, and obtaining an interference intention sequence with the maximum probability by using a Viterbi algorithm as an interference intention reasoning result;
the interference intents include: reduce detection, influence confirmation, get rid of tracking, destroy identification.
Further, the preprocessing of the electronic interference pattern data to be detected specifically includes:
and splicing a plurality of pieces of electronic interference pattern data to be detected with the same pulse length into one sample, and converting the spliced sample into one-dimensional data, namely preprocessed electronic interference pattern data to be detected, by utilizing the amplitude of the spliced sample.
Further, the electronic interference behavior recognition network is obtained by:
s1, acquiring an electronic interference pattern data set, preprocessing the electronic interference pattern data, and dividing the preprocessed electronic interference pattern data set into a training set and a testing set;
s2, constructing a cyclic neural network, and training the cyclic neural network by using a training set until the loss function converges to obtain a trained cyclic neural network;
and S3, testing the trained cyclic neural network by using the test set to obtain the identification precision of the trained cyclic neural network, storing the trained cyclic neural network as an electronic interference behavior identification network if the identification precision is greater than or equal to a preset threshold value, and executing S1 again if the identification precision is less than the preset threshold value.
Preferably, the recurrent neural network includes: an input layer, three hidden layers, a fully connected layer.
Further, the interference intention inference model is obtained by:
step1, acquiring an interference behavior intention data set, and dividing the interference behavior intention data set into a training set and a testing set;
the interference behavior intent dataset includes: interference behavior and interference intent;
step2, establishing a hidden Markov model, and training the hidden Markov model by utilizing a training set to obtain parameters of the hidden Markov model:
estimating the disturbance intention transition probability and the disturbance behavior output probability of the hidden Markov model by using a training set by adopting an EM algorithm, and determining parameters of the hidden Markov model after the probability value is stable;
step3, testing the hidden Markov model after the parameters are determined by using the test set, obtaining the accuracy of the hidden Markov model after the parameters are determined, and if the accuracy is greater than a preset first threshold, obtaining the hidden Markov model after the parameters are determined currently as the interference intention reasoning model.
Further, the interfering act includes: forming a hold, forming a decoy, forming a drag, forming a hold + spoof, forming a spoof + spoof.
Further, the interfering intent includes: reduce detection, impact validation, get rid of tracking and destructive identification.
An interference intent inference storage medium storing at least one instruction for use in said one interference intent inference method.
An interference intent inference device, the device comprising: a processor and a memory, the memory storing at least one instruction; the at least one instruction is loaded and executed by the processor to implement the one interference intent inference method.
The beneficial effects of the invention are as follows:
the invention uses the cyclic neural network trained by the training set of the electronic interference patterns, can complete the 'many-to-many' recognition task under the condition that each interference behavior corresponds to a plurality of interference signal patterns, effectively recognizes the types of the interference behaviors, and provides necessary conditions for correctly reasoning the interference intention. Under the condition that the corresponding relation between the interference intention and the interference behavior is highly uncertain, the interference intention is inferred by utilizing the hidden Markov model estimated by the true value of the interference behavior and the recognition result of the cyclic neural network, so that the potential intention information of the interfering party is easier to acquire, and the accuracy of interference intention inference is improved. The embodiment of the invention shows that the method has higher reasoning accuracy and provides an effective interference intention reasoning method for the anti-interference of the radar side.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 (a) is a time domain diagram of an intermittent sampling forwarding interference signal pattern;
FIG. 2 (b) is a distance domain diagram of intermittent sample forwarding interference signal patterns;
FIG. 3 (a) is a drawing of a time domain plot of a pilot interference signal;
FIG. 3 (b) is a drawing of a range profile of a towing interference signal;
FIG. 4 (a) is a set of interference behavior truth values;
FIG. 4 (b) is a set of interference intention truth values;
FIG. 5 is a schematic diagram of a recurrent neural network;
FIG. 6 is a schematic diagram of a hidden Markov model;
FIG. 7 is a schematic diagram of an inference model of interference intent;
FIG. 8 is a flow chart of an interference intent inference method;
FIG. 9 is a graph showing the results of the recognition of the disturbance behavior of the recurrent neural network;
fig. 10 is an interference intention inference result of the inference model.
Detailed Description
The first embodiment is as follows: as shown in fig. 1, a specific procedure of the interference intention reasoning method in this embodiment is as follows:
step one, acquiring electronic interference pattern data to be detected, preprocessing the electronic interference pattern data to be detected, and inputting the preprocessed electronic interference pattern data to be detected into an electronic interference behavior recognition network to obtain an electronic interference behavior type, as shown in fig. 9;
the preprocessing of the electronic interference pattern data to be detected specifically comprises the following steps:
splicing the 4 pieces of electronic interference pattern data to be detected with the same pulse length into one sample, and converting the spliced sample into one-dimensional data, namely preprocessed electronic interference pattern data to be detected, by utilizing the amplitude of the spliced sample;
the electronic interference behavior recognition network is obtained by the following steps:
s1, acquiring an electronic interference pattern data set, preprocessing the electronic interference pattern data set, and dividing the preprocessed electronic interference pattern data set into a training set and a testing set;
the electronic interference pattern data comprises a plurality of interference signal pulses, and the pulse length is 6000;
as in fig. 2 (a) - (b), the electronic interference pattern dataset comprises: aiming interference, blocking interference, delay decoy interference, frequency shift decoy interference, distance dragging interference, speed dragging interference, aiming interference+dense decoy interference, intermittent sampling forwarding interference, distance decoy+speed decoy interference, distance dragging+dense decoy interference and other electronic interference belong to interference behaviors of forming suppression, forming decoy, forming dragging, forming suppression+deception, forming deception+deception and the like respectively, as shown in table 1;
TABLE 1
Since the interference pattern signal contains the trailing interference as shown in fig. 3 (a) - (b), the network identification accuracy is related to the number of interference pulses contained in one sample, that is, the sample data length, and through multiple experiments, the interference signals with 4 pulse lengths are spliced into one sample as the input of the network. The interference signal comprises real part and imaginary part data, and in order to facilitate the training and identification of the cyclic neural network, the amplitude value is converted into one-dimensional data and is input into the cyclic neural network. The dataset of the interference behavior recognition network contains 2000 sets of samples and corresponding behavior tags. The data were randomly divided into training sets, test sets, which account for 50% of the total sample. The training set is mainly used for training model parameters, and the rest simulation samples are used as test sets for verifying the effectiveness of the training model. The training and testing data of the disturbance behavior intents are shown in fig. 4 (a) - (b), each set of data comprises 100 rounds of true values, the training data is used for estimating parameters of the hidden markov model, the disturbance behavior true values in the testing data are used for generating disturbance patterns, and the disturbance intents true values are used for testing the reasoning accuracy of the model.
S2, constructing a cyclic neural network, and training the cyclic neural network by using a training set until the loss function converges to obtain a trained cyclic neural network;
the recurrent neural network includes: one input layer, three hidden layers, one fully connected layer, as shown in fig. 5.
The learning rate of the model is 0.01, the loss function uses a cross entropy loss function, and the training algorithm is random gradient descent and counter propagation. The batch training size is set to 64. The interference signal comprises real part and imaginary part data, and amplitude is taken and converted into one-dimensional data for inputting in order to facilitate the training and the identification of the cyclic neural network. The parameters of the cyclic neural network model are shown in table 2;
TABLE 2
S3, testing the trained cyclic neural network by using a test set to obtain the identification precision of the trained cyclic neural network, storing the identification precision as an electronic interference behavior identification network if the identification precision is greater than or equal to a preset threshold, and executing S1 again if the identification precision is less than the preset threshold;
step two, inputting the electronic interference behavior type into an interference intention reasoning model, and solving an interference intention sequence with the maximum probability by using a Viterbi algorithm as an interference intention reasoning result, as shown in fig. 8;
the interference intention inference model is obtained by:
step1, acquiring an interference behavior intention data set, and dividing the interference behavior intention data set into a training set and a test set
The interfering behavioral intention includes: interference behavior and corresponding interference intent;
the interference intents include: reducing detection, influencing confirmation, getting rid of tracking and destructive identification;
the interference behavior includes: forming a hold, forming a decoy, forming a drag, forming a hold+spoof, forming a spoof+spoof;
step2, establishing a hidden Markov model of the disturbance behavior intention based on the disturbance behavior and the disturbance intention set in the simulation, estimating disturbance intention transition probability and disturbance behavior output probability of the hidden Markov model by using a training set by adopting an EM algorithm, and determining parameters of the hidden Markov model after the probability value is stable;
the disturbance process is modeled using the hidden Markov model shown in FIG. 6, with the modeling process as follows: the detection, influence confirmation, getting rid of tracking and damage recognition of 4 intention reduction of the interfering party are respectively marked as S 1 ，S 2 ，S 3 ，S 4 The change between the interference intents can be described by transition probabilities.
Lei Dafang does not directly learn the actual intent of the interfering party, but there are 5 types of interference behavior that can be observed, namely, forming hold-down, forming spoof, forming drag-induced interference, forming hold-down + spoof, and forming combined spoof + spoof, denoted v 1 ,v 2 ,v 3 ,v 4 ,v 5 . The change of the interference behavior reflects the change of the intention of the interfering party, and can be described by observing probability values, wherein the sum of the probabilities of all the observed interference behaviors corresponding to each hidden intention is 1. A hidden markov model of the disturbance intent variation is shown in fig. 7.
step3, testing the hidden Markov model after the parameters are determined by using a test set, obtaining the accuracy of the hidden Markov model after the parameters are determined, and if the accuracy is greater than a preset first threshold, obtaining the hidden Markov model after the parameters are determined currently as an interference intention reasoning model;
the interference behavior truth value of the test set randomly generates interference pattern data, the interference pattern data is sent to the cyclic neural network for recognition, the interference behavior recognition result is output, the recognition result is input into the hidden Markov model to output an interference intention reasoning result, and the interference intention reasoning result is compared with the truth value to obtain the accuracy of the test.
The probability of each interference intention is calculated by using a Viterbi algorithm, and an interference intention sequence with the highest probability is selected as an interference intention reasoning result:
firstly initializing, calculating the probability of the first return of the sequence, then iteratively solving the probability of possible intention according to the transition probability of the interference intention, recording the optimal interference intention sequence, and backtracking the optimal interference intention sequence when the process is terminated to obtain the intention reasoning result.
The second embodiment is as follows: an interference intent inference storage medium storing at least one instruction for use in said one interference intent inference method.
And a third specific embodiment: an interference intent inference device, the device comprising: a processor and a memory, the memory storing at least one instruction; the at least one instruction is loaded and executed by the processor to implement the one interference intent inference method.
Examples: the following examples are used to verify the benefits of the present invention:
to illustrate the effectiveness of the present invention for electronic interference intent recognition, the interference behavior recognition network is trained prior to 100 rounds of interference pattern data recognition generated for an interference scenario. And if the identification precision of the test set is greater than a preset threshold value, storing the test set as the electronic interference behavior identification network. And using a circulating neural network trained when the pulse number is 4 and the dry-to-noise ratio is 40dB to identify 100-round interference signal patterns randomly generated by interference behavior truth values, and outputting behavior identification results, wherein black blocks represent samples with identification errors, and the identification accuracy is 93%.
The interference behavior recognition result is input into a hidden Markov model to obtain an inference result of the interference intention, as shown in fig. 10, wherein a black block is an erroneous inference result, and the inference accuracy of the detection and destruction recognition is reduced to be higher than that of the influence confirmation and the getting rid of the tracking intention. This is because the jammer's behavior of the jammer when attempting to reduce detection and corrupt identification is relatively deterministic, as jammers tend to choose to use suppressing jammers when attempting to reduce detection. From the above experimental results, the inference accuracy of the interference intention inference model based on the hidden markov model is about 80% under the set interference parameters.
Claims (10)
1. The interference intention reasoning method is characterized by comprising the following specific processes:
step one, acquiring electronic interference pattern data to be detected, preprocessing the electronic interference pattern data to be detected, and inputting the preprocessed electronic interference pattern data to be detected into an electronic interference behavior recognition network to obtain an electronic interference behavior type;
the electronic interference pattern data set includes: aiming interference, blocking interference, delay decoy interference, frequency shift decoy interference, distance towing interference, speed towing interference, aiming interference + dense decoy interference, intermittent sampling forwarding interference, distance decoy + speed decoy interference, distance towing + dense decoy interference;
inputting the electronic interference behavior type into an interference intention reasoning model, and obtaining an interference intention sequence with the maximum probability by using a Viterbi algorithm as an interference intention reasoning result;
the interference intents include: reduce detection, influence confirmation, get rid of tracking, destroy identification.
2. The interference intention inference method as claimed in claim 1, wherein: the preprocessing of the electronic interference pattern data to be detected specifically comprises the following steps:
and splicing a plurality of pieces of electronic interference pattern data to be detected with the same pulse length into one sample, and converting the spliced sample into one-dimensional data, namely preprocessed electronic interference pattern data to be detected, by utilizing the amplitude of the spliced sample.
3. The interference intention inference method as claimed in claim 2, wherein: the electronic interference behavior recognition network is obtained by the following steps:
s1, acquiring an electronic interference pattern data set, preprocessing the electronic interference pattern data, and dividing the preprocessed electronic interference pattern data set into a training set and a testing set;
s2, constructing a cyclic neural network, and training the cyclic neural network by using a training set until the loss function converges to obtain a trained cyclic neural network;
and S3, testing the trained cyclic neural network by using the test set to obtain the identification precision of the trained cyclic neural network, storing the trained cyclic neural network as an electronic interference behavior identification network if the identification precision is greater than or equal to a preset threshold value, and executing S1 again if the identification precision is less than the preset threshold value.
4. A method of inference of interference intention as claimed in claim 3, wherein: the loss function of the recurrent neural network is a cross entropy loss function.
5. The interference intention inference method as claimed in claim 4, wherein: the recurrent neural network includes: an input layer, three hidden layers, a fully connected layer.
6. A method of inference of an intention as claimed in any one of claims 1 to 5, wherein: the interference intention inference model is obtained by:
step1, acquiring an interference behavior intention data set, and dividing the interference behavior intention data set into a training set and a testing set;
the interference behavior intent dataset includes: interference behavior and interference intent;
step2, establishing a hidden Markov model, and training the hidden Markov model by utilizing a training set to obtain parameters of the hidden Markov model:
estimating the disturbance intention transition probability and the disturbance behavior output probability of the hidden Markov model by using a training set by adopting an EM algorithm, and determining parameters of the hidden Markov model after the probability value is stable;
step3, testing the hidden Markov model after the parameters are determined by using the test set, obtaining the accuracy of the hidden Markov model after the parameters are determined, and if the accuracy is greater than a preset first threshold, obtaining the hidden Markov model after the parameters are determined currently as the interference intention reasoning model.
7. The interference intention inference method as claimed in claim 6, wherein: the interference behavior includes: forming a hold, forming a decoy, forming a drag, forming a hold + spoof, forming a spoof + spoof.
8. The interference intention inference method as claimed in claim 6, wherein: the interference intents include: reduce detection, impact validation, get rid of tracking and destructive identification.
9. An interference intention inference storage medium characterized by: the storage medium stores at least one instruction for implementing a method of inference of interference intent as claimed in any one of claims 1 to 7.
10. An interference intention inference apparatus characterized by: the apparatus comprises: a processor and a memory, the memory storing at least one instruction; the at least one instruction is loaded and executed by a processor to implement a method of inference of interference intent as claimed in any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310278444.0A CN116224248A (en) | 2023-03-21 | 2023-03-21 | Interference intention reasoning method, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310278444.0A CN116224248A (en) | 2023-03-21 | 2023-03-21 | Interference intention reasoning method, storage medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116224248A true CN116224248A (en) | 2023-06-06 |
Family
ID=86573074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310278444.0A Pending CN116224248A (en) | 2023-03-21 | 2023-03-21 | Interference intention reasoning method, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116224248A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930880A (en) * | 2023-07-21 | 2023-10-24 | 哈尔滨工业大学 | Dynamic evaluation method for deception jamming threat |
-
2023
- 2023-03-21 CN CN202310278444.0A patent/CN116224248A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116930880A (en) * | 2023-07-21 | 2023-10-24 | 哈尔滨工业大学 | Dynamic evaluation method for deception jamming threat |
| CN116930880B (en) * | 2023-07-21 | 2024-05-28 | 哈尔滨工业大学 | Dynamic evaluation method for deception jamming threat |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112904290B (en) | Generation method of intelligent cognitive anti-interference strategy of radar | |
| CN113406579B (en) | Camouflage interference waveform generation method based on deep reinforcement learning | |
| CN116224248A (en) | Interference intention reasoning method, storage medium and equipment | |
| CN110874471B (en) | Privacy and safety protection neural network model training method and device | |
| CN113962151B (en) | Intelligent distance false target identification method based on deep convolution transfer learning | |
| CN115236607B (en) | Radar anti-interference strategy optimization method based on double-layer Q learning | |
| KR20220025455A (en) | Method for depending adversarial attack and apparatus thereof | |
| CN110031807A (en) | A kind of multistage smart noise jamming realization method based on model-free intensified learning | |
| CN113866723B (en) | Anti-interference decision method applied to cognitive radar | |
| Song et al. | Generating fake cyber threat intelligence using the gpt-neo model | |
| CN116894200A (en) | Radio frequency modulation fuze interference signal identification method based on convolutional neural network and attention mechanism | |
| Shaburov et al. | Protection models of critical information infrastructure objects from targeted computer attacks | |
| KR102407834B1 (en) | Method and apparatus for property-based classification of long-pulse radar signals | |
| CN111475321B (en) | Neural network security property verification method based on iterative abstract analysis | |
| Wang et al. | Convolutional neural network-based interference recognition | |
| CN115236620A (en) | Intermittent sampling type interference identification and anti-interference target detection method based on DCNN | |
| Gala et al. | Evaluating the effectiveness of attacks and defenses on machine learning through adversarial samples | |
| CN113378985A (en) | Countermeasure sample detection method and device based on layer-by-layer correlation propagation | |
| CN116614189B (en) | Method and device for generating countermeasure sample for radio interference identification | |
| Goncharov et al. | Opportunities to study the characteristics of information systems and manage them using modern technologies | |
| Alavizadeh et al. | Cloud-based intrusion detection system using a deep neural network and human-in-the-loop decision making | |
| Meng et al. | Interrupted sampling repeater jamming suppression based on multiple extended complex‐valued convolutional auto‐encoders | |
| Gill et al. | FedDefender: Backdoor Attack Defense in Federated Learning | |
| Basan et al. | Methodology for Detecting Attacks in the Context of Destructive Influences | |
| Jo et al. | Jamming Selection Method against Unknown Radar Signals based on Deep Learning using Co-occurrence Matrix |
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 |