CN115473692A - Service request processing method, device, equipment and medium - Google Patents
Service request processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN115473692A CN115473692A CN202210982855.3A CN202210982855A CN115473692A CN 115473692 A CN115473692 A CN 115473692A CN 202210982855 A CN202210982855 A CN 202210982855A CN 115473692 A CN115473692 A CN 115473692A
- Authority
- CN
- China
- Prior art keywords
- service request
- service
- illegal
- model
- client
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1416—Event detection, e.g. attack signature detection
-
- 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
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1441—Countermeasures against malicious traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the disclosure discloses a method, a device, equipment and a medium for processing a service request, wherein the method comprises the following steps: intercepting real-time interactive data, and acquiring at least one real-time service request according to the real-time interactive data; in response to determining that the real-time service request includes at least one illegal service parameter, sending a service request rejection instruction; acquiring a target service request model, inputting at least one illegal service parameter as input, and inputting the target service request model to acquire a simulated illegal service request; acquiring simulated service response information according to the simulated illegal service request, and acquiring illegal service request countermeasure information according to the simulated service response information; and sending illegal service request countermeasure information. The technical scheme can eliminate the probability of the service system being damaged and broken down due to the damage of other service requests sent by the client to the service system borne by the service server, and improves the stability of the service system.
Description
Technical Field
The present disclosure relates to the field of network technologies, and in particular, to a method, an apparatus, a device, and a medium for processing a service request.
Background
In recent years, with the development of communication technology, people have increasingly relied on networks in the aspect of daily life. In daily use, a terminal may run a more sensitive application, such as a financial transaction application, a social application, and the like, so that data interaction for a more sensitive service may exist between the terminal and a server. In order to ensure the security of the sensitive service, the interactive data between the terminal and the server needs to be detected to ensure that the service request initiated by the terminal to the server is safe and reliable and does not damage the service system on the server.
In the related technology, in order to detect interactive data between a terminal and a server, interactive data corresponding to related services can be manually analyzed to obtain sample interactive data outside a normal service rule range, the data to be detected is obtained through methods such as front-end code debugging or packet capturing, the data to be detected is sent to a detection end and is compared with the sample interactive data to obtain a detection result, and when it is determined that a service request initiated by the terminal to the server possibly damages a service system on the server according to the detection result, the terminal and the server are prohibited from carrying out data interaction.
Although the above scheme can improve the reliability of the service system on the server, in the above scheme, it is considered that the above scheme mainly depends on that after the related analyst fully knows the service function, the sample interaction data outside the normal service rule range obtained according to the experience of the analyst is detected, so that all service requests that may cause damage to the service system may not be determined based on the detection result, and further, the corresponding service request may not be processed reasonably, so that the service system may be broken down due to damage, and the stability of the service system is reduced.
Disclosure of Invention
In order to solve the problems in the related art, embodiments of the present disclosure provide a method, an apparatus, a device, and a medium for processing a service request.
In a first aspect, an embodiment of the present disclosure provides a method for processing a service request, where the method includes:
intercepting real-time interactive data between a client and a service server, and acquiring at least one real-time service request sent to the service server by the client according to the real-time interactive data;
in response to the fact that the real-time service request comprises at least one illegal service parameter, sending a service request rejection instruction, wherein the service request rejection instruction is used for indicating a service server to reject data interaction with the client;
acquiring a target service request model obtained by pre-training, inputting at least one illegal service parameter as input into the target service request model to acquire a simulated illegal service request output by the target service request model;
acquiring simulated service response information according to the simulated illegal service request, and acquiring illegal service request countermeasure information according to the simulated service response information, wherein the illegal service request countermeasure information is used for indicating a strategy of a service server for processing a service request sent by a client;
and sending illegal service request countermeasure information.
In one implementation of the present disclosure, before inputting a target service request model with at least one illegal service parameter as an input to obtain a simulated illegal service request output by the target service request model, the method further includes:
acquiring a target client identifier corresponding to a client sending a real-time service request;
inputting a target service request model by taking at least one illegal service parameter as input so as to obtain a simulated illegal service request output by the target service request model, wherein the method comprises the following steps:
and inputting at least one illegal service parameter and the target client identification as inputs into the target service request model to obtain the simulated illegal service request output by the target service request model.
In an implementation manner of the present disclosure, before obtaining a target service request model obtained by pre-training, the method further includes:
acquiring historical interactive data between a client and a service server and a historical log of the service server;
responding to at least one fault event contained in the historical log, acquiring fault time and fault service parameters corresponding to the fault event, and acquiring at least one associated service request associated with the fault event in a target time length before the fault time and an associated client identifier corresponding to a client sending the associated service request according to historical interaction data, wherein parameter values of service parameters in the associated service request are all out of a legal value range of the corresponding service parameters;
and acquiring a service request model, taking the fault service parameter and the associated client identification as input, taking the associated service request as output, and training the service request model to acquire a target service request model.
In one implementation of the present disclosure, the method for training a service request model to obtain a target service request model by using a fault service parameter and an associated client identifier as inputs and an associated service request as an output includes:
acquiring a private service request model according to the service request model;
receiving an update weight parameter sent by an edge server, and updating the private service request model according to the update weight parameter;
taking the fault service parameter and the associated client terminal identification as input, taking the associated service request as output, and training the updated service request model;
when the trained service request model is not converged, acquiring a gradient update vector according to the trained service request model and sending the gradient update vector, wherein the edge server is used for aggregating the gradient update vector and updating the weight parameters of the common service request model of the edge server according to the aggregated gradient update vector to acquire updated weight parameters;
and when the trained service request model is converged, acquiring a target service request model according to the trained service request model.
In one implementation of the present disclosure, before obtaining the private service request model according to the service request model, the method further includes:
receiving a private data uploading instruction;
responding to the private data uploading instruction, and sending a fault service parameter, an associated client identifier and an associated service request;
receiving an initial weight parameter sent by an edge server;
obtaining a private service request model according to a service request model, comprising:
and updating the initial service request model according to the initial weight parameter so as to obtain a private service request model.
In a second aspect, an embodiment of the present disclosure provides a service request processing apparatus, where the apparatus includes:
the real-time request acquisition module is configured to intercept real-time interactive data between the client and the service server and acquire at least one real-time service request sent to the service server by the client according to the real-time interactive data;
the illegal request rejection module is configured to respond to the fact that the real-time service request comprises at least one illegal service parameter, and send a service request rejection instruction, wherein the service request rejection instruction is used for indicating a service server to reject data interaction with the client;
the simulation request acquisition module is configured to acquire a target service request model obtained by pre-training, take at least one illegal service parameter as input, and input the target service request model to acquire a simulated illegal service request output by the target service request model;
the request strategy obtaining module is configured to obtain simulated service response information according to the simulated illegal service request and obtain illegal service request strategy information according to the simulated service response information, wherein the illegal service request strategy information is used for indicating a service server to process a strategy of the service request sent by the client;
and the request countermeasure sending module is configured to send illegal service request countermeasure information.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
acquiring a target client identifier corresponding to a client sending a real-time service request;
inputting a target service request model by taking at least one illegal service parameter as input so as to obtain a simulated illegal service request output by the target service request model, wherein the method comprises the following steps:
and inputting at least one illegal service parameter and the target client identification as inputs into the target service request model to obtain the simulated illegal service request output by the target service request model.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
acquiring historical interactive data between a client and a service server and a historical log of the service server;
responding to at least one fault event included in the historical log, acquiring a fault time and a fault service parameter corresponding to the fault event, and acquiring at least one associated service request associated with the fault event within a target time length before the fault time and an associated client identifier corresponding to a client sending the associated service request according to historical interaction data, wherein parameter values of the service parameters in the associated service request are all out of a legal value range of the corresponding service parameters;
and acquiring a service request model, taking the fault service parameter and the associated client identification as input, taking the associated service request as output, and training the service request model to acquire a target service request model.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
acquiring a private service request model according to the service request model;
receiving an update weight parameter sent by an edge server, and updating the private service request model according to the update weight parameter;
taking the fault service parameter and the associated client terminal identification as input, taking the associated service request as output, and training the updated service request model;
when the trained service request model is not converged, acquiring a gradient update vector according to the trained service request model, and sending the gradient update vector, wherein the edge server is used for aggregating the gradient update vector, and updating the weight parameters of the common service request model of the edge server according to the aggregated gradient update vector to acquire updated weight parameters;
and when the trained service request model is converged, acquiring a target service request model according to the trained service request model.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
receiving a private data uploading instruction;
responding to the private data uploading instruction, and sending a fault service parameter, an associated client identifier and an associated service request;
receiving an initial weight parameter sent by an edge server;
obtaining a private service request model according to a service request model, comprising:
and updating the initial service request model according to the initial weight parameter so as to obtain a private service request model.
In a third aspect, an electronic device is provided in this disclosed embodiment, and the electronic device includes a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any one of the first aspect.
In a fourth aspect, a computer-readable storage medium is provided in embodiments of the present disclosure, having computer instructions stored thereon, wherein the computer instructions, when executed by a processor, implement the method of any one of the first aspect.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
in the technical scheme, by intercepting the real-time interactive data between the client and the service server and acquiring at least one real-time service request sent by the client to the service server according to the real-time interactive data, whether the real-time service request comprises illegal service parameters or not is determined, namely whether the real-time service request possibly damages a service system borne by the service server or not is determined. When the real-time service request is determined to include at least one illegal service parameter, namely the real-time service request possibly damages a service system carried by a service server, a service request rejection instruction is sent in response to the fact that the real-time service request includes at least one illegal service parameter, so that the service server is indicated to reject data interaction with the client side, and the service system carried by the service server is prevented from being damaged as much as possible. And meanwhile, acquiring a target service request model obtained by pre-training, inputting at least one illegal service parameter as input, and inputting the target service request model to acquire an illegal service request simulation output by the target service request model, wherein the illegal service request simulation can be understood as a service request which is possibly damaged to a service system borne by a service server and is sent by a client before the client sends a real-time service request comprising the at least one illegal service parameter when the client is determined to send the real-time service request. The method comprises the steps of obtaining simulation service response information according to a simulation illegal service request, obtaining illegal service request countermeasure information according to the simulation service response information, and sending the illegal service request countermeasure information so as to instruct a service server to perform corresponding processing according to the illegal service request countermeasure information, so that the probability that a service system is damaged and crashed due to damage to the service system borne by the service server caused by other service requests sent by a client is eliminated, and the stability of the service system is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:
FIG. 1 shows a schematic block diagram of a service request processing system according to an embodiment of the present disclosure;
FIG. 2 shows a schematic flow diagram of a service request processing method according to an embodiment of the present disclosure;
FIG. 3 shows a schematic flow diagram of a service request processing method according to an embodiment of the present disclosure;
FIG. 4 shows a schematic flow diagram of a service request processing method according to an embodiment of the present disclosure;
FIG. 5 shows a schematic flow diagram of a service request processing method according to an embodiment of the present disclosure;
fig. 6 shows a schematic block diagram of a service request processing apparatus according to an embodiment of the present disclosure;
FIG. 7 shows a schematic block diagram of an electronic device according to an embodiment of the present disclosure;
FIG. 8 shows a schematic block diagram of a computer system suitable for use in implementing a method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.
In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, actions, components, parts, or combinations thereof, and do not preclude the possibility that one or more other features, numbers, steps, actions, components, parts, or combinations thereof are present or added.
It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
The details of the embodiments of the present disclosure are described in detail below by way of specific embodiments.
In recent years, with the development of communication technology, people have increasingly relied on networks in the aspect of daily life. In general, a terminal device used by a person can access a network through a network device which is close to the terminal device. The terminal device can be an intelligent mobile communication terminal, a wearable device, a desktop computer, a notebook computer, a tablet computer and the like, and the terminal device can be a wireless router, a wired router, a wireless gateway and the like.
In recent years, with the development of communication technology, people have increasingly relied on networks in the aspect of daily life. In daily use, a terminal may run a more sensitive application, such as a financial transaction application, a social application, and the like, so that data interaction for a more sensitive service may exist between the terminal and a server. In order to ensure the security of the sensitive service, the interactive data between the terminal and the server needs to be detected to ensure that the service request initiated by the terminal to the server is safe and reliable and does not damage the service system on the server.
In the related technology, in order to detect the interactive data between the terminal and the server, the interactive data corresponding to the related service can be manually analyzed to obtain sample interactive data outside the normal service rule range, the data to be detected is obtained by methods such as front-end code debugging or packet capturing, the data to be detected is sent to the detection end and is compared with the sample interactive data to obtain a detection result, and when it is determined that a service request initiated by the terminal to the server may damage a service system on the server according to the detection result, the data interaction between the terminal and the server is prohibited.
Although the above-mentioned solution can improve the reliability of the service system on the server, in the above-mentioned solution, it is mainly relied on that after the related analyst fully knows the service function, the analyst obtains the sample interaction data outside the normal service rule range according to the experience of the analyst to perform detection, so that it may not be possible to determine all service requests that may cause damage to the service system based on the above-mentioned detection result, and further it is impossible to reasonably process the corresponding service requests, which may cause a breakdown of the service system due to damage, and reduce the stability of the service system.
In view of the above drawbacks, in the technical solution provided by the present disclosure, by intercepting real-time interaction data between a client and a service server, and acquiring at least one real-time service request sent by the client to the service server according to the real-time interaction data, it is determined whether the real-time service request includes an illegal service parameter, that is, whether the real-time service request may damage a service system carried by the service server is determined. When the real-time service request is determined to include at least one illegal service parameter, namely the real-time service request may damage a service system carried by the service server, a service request rejection instruction is sent in response to the fact that the real-time service request includes the at least one illegal service parameter, so that the service server is instructed to reject data interaction with the client side, and the service system carried by the service server is prevented from being damaged as much as possible. And meanwhile, acquiring a target service request model obtained by pre-training, inputting at least one illegal service parameter as input, and inputting the target service request model to acquire an illegal service request simulation output by the target service request model, wherein the illegal service request simulation can be understood as a service request which is possibly damaged to a service system borne by a service server and is sent by a client before the client sends a real-time service request comprising the at least one illegal service parameter when the client is determined to send the real-time service request. The method comprises the steps of obtaining simulation service response information according to a simulation illegal service request, obtaining illegal service request countermeasure information according to the simulation service response information, and sending the illegal service request countermeasure information so as to instruct a service server to perform corresponding processing according to the illegal service request countermeasure information, so that the probability that a service system is damaged and crashed due to damage to the service system borne by the service server caused by other service requests sent by a client is eliminated, and the stability of the service system is improved.
Fig. 1 shows a schematic block diagram of a service request processing system according to an embodiment of the present disclosure, where the service request processing system includes a client 101, a service server 102, and a network 103, the network 103 is used for providing a medium of a communication link between the client 101 and the service server 102, and the network 103 may include various connection types, such as a wired connection, a wireless communication link, or an optical fiber cable.
The client 101 is a variety of electronic devices with network access function, including but not limited to mobile communication terminals, desktop computers, tablet computers, notebook computers, wearable devices, and so on.
The service server 102 may be a cloud server, or may be a server provided by an operator of a corresponding service. It should be noted that, in the embodiment of the present application, one service server 102 may correspond to multiple clients 101, for example, an operator of a service request processing service may divide a managed area into multiple blocks, and multiple clients 101 in each block correspond to one service server 102.
Fig. 2 shows a schematic flowchart of a service request processing method according to an embodiment of the present disclosure, the service request processing method is applied to a service server management end, and the service server management end may be a terminal or a server. As shown in fig. 2, the service request processing method includes the following steps:
in step S101, real-time interactive data between the client and the service server is intercepted, and at least one real-time service request sent from the client to the service server is obtained according to the real-time interactive data.
In an implementation manner of the present disclosure, intercepting real-time interactive data between a client and a service server may be understood as setting a corresponding intercepting module on the service server, sampling interactive data between the client and the service server by the intercepting module, when the sampled data meets a preset intercepting condition, acquiring interactive data in a preset data range before and after the sampled data meeting the intercepting condition, and forwarding the acquired interactive data as real-time interactive data. The sampled data satisfying the interception condition may be understood as sampled data including parameters related to the service request. Or, the service server management end may directly sample the interactive data between the client and the service server, and send the sampled interactive data as real-time interactive data.
In one implementation manner of the present disclosure, the at least one real-time service request sent from the real-time interactive data acquisition client to the service server may be understood as parsing the real-time interactive data to acquire the at least one real-time service request. Or, the information may also be understood as being forwarded to other devices or systems to obtain corresponding information sent by the other devices or systems to indicate the at least one real-time service request, and the at least one real-time service request is obtained according to the corresponding information.
In step S102, in response to determining that the real-time service request includes at least one illegal service parameter, a service request rejection instruction is sent.
The service request rejection instruction is used for indicating the service server to reject data interaction with the client.
In one implementation manner of the present disclosure, determining that the real-time service request includes at least one illegal service parameter may be understood as extracting a service parameter from each real-time service request, and querying in a service parameter value database obtained in advance according to the extracted service parameter, and determining that the real-time service request includes at least one illegal service parameter when a service parameter value corresponding to the queried service parameter exceeds a reasonable range of the corresponding service parameter value. Or, the real-time service request may also be sent to other devices or systems, and it is determined whether the real-time service request includes at least one illegal service parameter according to the extraordinary service parameter indication information sent by other devices or systems.
In an implementation manner of the present disclosure, the service request rejection instruction is used to instruct the service server to reject data interaction with the client, which may be understood as that after the service server receives the service request rejection instruction, all data sent by the client indicated by the service request rejection instruction is discarded.
Further, the service request rejection instruction may further include a time interval during which the service server rejects data interaction with the client, and the like.
In step S103, a target service request model obtained by pre-training is obtained, and at least one illegal service parameter is used as input to input the target service request model, so as to obtain a simulated illegal service request output by the target service request model.
In an embodiment of the present disclosure, the target service request model may be stored in the terminal device in advance, or may be obtained from other devices or systems.
The target service request model may be a Neural Network (NN) model, a Convolutional Neural Network (CNN) model, a Long Short Term Memory (LSTM) model, or the like.
The target service request model can be understood as a model of the regularity between the illegal service parameters learned and the service requests sent by the client side including the illegal service parameters and other service requests which may damage the service system carried by the service server and may have been sent to the service server before the real-time service requests including the illegal service parameters are sent.
In step S104, the simulation service response information is obtained according to the simulation illegal service request, and the illegal service request countermeasure information is obtained according to the simulation service response information.
The illegal service request countermeasure information is used for indicating a strategy of the service server for processing the service request sent by the client.
In one embodiment of the present disclosure, the simulated service response information is obtained according to the simulated illegal service request, which can be understood as responding to the simulated illegal service request in a virtual service system for simulating a service system built in advance to obtain the simulated service response information; it can also be understood as sending the simulated illegal service request to other devices or systems to obtain simulated service response information. The simulated service response information may be understood as information for indicating a system operating state of the service system on the premise that the service system responds to the simulated illegal service request, for example, the simulated service response information may include a system operating parameter or a service system fault event.
In one embodiment of the present disclosure, the illegal service request countermeasure information is obtained according to the simulated service response information, which may be understood as that the simulated service response information is queried in an illegal service request countermeasure database obtained in advance to obtain illegal service request countermeasure information; or the simulated service response information can be sent to other devices or systems to acquire illegal service request countermeasure information sent by other devices or systems.
In an embodiment of the present disclosure, the illegal service request countermeasure information may be understood as related data generated in response to a corresponding service application and corresponding service application for instructing a service system installed on a service server how to process the corresponding service application, and a software module activated in response to the corresponding service application, so as to avoid any influence of the corresponding service application on the service system.
In step S105, illegal traffic request countermeasure information is transmitted.
In the embodiment, by intercepting the real-time interactive data between the client and the service server and acquiring at least one real-time service request sent by the client to the service server according to the real-time interactive data, whether the real-time service request includes an illegal service parameter is determined, that is, whether the real-time service request may damage a service system carried by the service server is determined. When the real-time service request is determined to include at least one illegal service parameter, namely the real-time service request may damage a service system carried by the service server, a service request rejection instruction is sent in response to the fact that the real-time service request includes the at least one illegal service parameter, so that the service server is instructed to reject data interaction with the client side, and the service system carried by the service server is prevented from being damaged as much as possible. And meanwhile, acquiring a target service request model obtained by pre-training, inputting at least one illegal service parameter as input, and inputting the target service request model to acquire an illegal service request simulation output by the target service request model, wherein the illegal service request simulation can be understood as a service request which is possibly damaged to a service system borne by a service server and is sent by a client before the client sends a real-time service request comprising the at least one illegal service parameter when the client is determined to send the real-time service request. The method comprises the steps of obtaining simulation service response information according to a simulation illegal service request, obtaining illegal service request countermeasure information according to the simulation service response information, and sending the illegal service request countermeasure information so as to instruct a service server to perform corresponding processing according to the illegal service request countermeasure information, so that the probability that a service system is damaged and crashed due to damage to the service system borne by the service server caused by other service requests sent by a client is eliminated, and the stability of the service system is improved.
In one implementation of the present disclosure, fig. 3 shows a schematic flowchart of a service request processing method according to an embodiment of the present disclosure, and as shown in fig. 3, in step S103, before obtaining a target service request model obtained by pre-training, and inputting at least one illegal service parameter as an input into the target service request model to obtain a simulated illegal service request output by the target service request model, the method further includes step S106:
in step S106, a target client identifier corresponding to the client that sends the real-time service request is obtained;
in step S103, a target service request model obtained by pre-training is obtained, and at least one illegal service parameter is used as input to input the target service request model, so as to obtain a simulated illegal service request output by the target service request model, which can be implemented by step S1031:
in step S1031, a target service request model obtained by pre-training is obtained, and at least one illegal service parameter and a target client identifier are used as input to input the target service request model, so as to obtain a simulated illegal service request output by the target service request model.
In an embodiment of the present disclosure, the client identifier may be understood as being used to indicate the client, and the client identifier may correspond to the client one to one.
In the embodiment, by acquiring the target client identifier corresponding to the client sending the real-time service request, inputting the at least one illegal service parameter and the target client identifier as inputs, and inputting the target service request model to acquire the illegal service request simulated by the target service request model, it can be ensured that the illegal service request simulated by the specific client is a service request which may possibly damage a service system carried by the service server before the specific client sends the real-time service request including the at least one illegal service parameter, and the accuracy of the obtained illegal service request simulated is improved.
In one implementation of the present disclosure, fig. 4 shows a schematic flowchart of a service request processing method according to an embodiment of the present disclosure, as shown in fig. 4, in step S1031, a target service request model obtained by pre-training is obtained, and at least one illegal service parameter and a target client identifier are used as input, and the target service request model is input to obtain a simulated illegal service request output by the target service request model, where the method further includes steps S107 to S109:
in step S107, historical interaction data between the client and the service server and a historical log of the service server are acquired;
in step S108, in response to the historical log including at least one fault event, obtaining a fault time and fault service parameters corresponding to the fault event, and obtaining at least one associated service request associated with the fault event within a target time length before the fault time and an associated client identifier corresponding to a client sending the associated service request according to the historical interaction data;
wherein the parameter values of the service parameters in the associated service request are all outside the legal value range of the corresponding service parameters;
in step S109, a service request model is obtained, the failure service parameter and the associated client identifier are used as input, the associated service request is used as output, and the service request model is trained to obtain a target service request model.
In an embodiment of the present disclosure, the historical interaction data between the client and the service server and the historical log of the service server are obtained, and the historical interaction data and the historical log that are stored in advance may be read, or the historical interaction data and the historical log that are sent by other devices or systems may also be received.
In the embodiment, by acquiring historical interaction data between a client and a service server and a historical log of the service server, responding to the historical log including at least one fault event, acquiring a fault time and fault service parameters corresponding to the fault event, acquiring at least one associated service request associated with the fault event within a target time length before the fault time and an associated client identifier corresponding to a client sending the associated service request according to the historical interaction data, acquiring a service request model, taking the fault service parameter and the associated client identifier as input, taking the associated service request as output, and training the service request model to acquire the target service request model, the target service request model can be ensured, and rules between illegal service parameters and a client identifier of the client sending the real-time service request including the illegal service parameters and other service requests which may have been sent to the service server before the client sends the real-time service request including the illegal service parameters and may cause damage to a service system borne by the service server can be learned.
In one implementation of the present disclosure, fig. 5 shows a schematic flowchart of a service request processing method according to an embodiment of the present disclosure, and as shown in fig. 5, step S109 obtains a service request model, takes a fault service parameter and an associated client identifier as input, takes an associated service request as output, trains the service request model to obtain a target service request model, and may be implemented through steps S1091 to S1095:
in step S1091, a private service request model is obtained according to the service request model;
in step S1092, receiving an update weight parameter sent by the edge server, and updating the private service request model according to the update weight parameter;
in step S1093, the updated service request model is trained by taking the fault service parameter and the associated client identifier as input and the associated service request as output;
in step S1094, when the trained service request model is not converged, obtaining a gradient update vector according to the trained service request model, and sending the gradient update vector, where the edge server is configured to aggregate the gradient update vectors, and update the weight parameters of the common service request model of the edge server according to the aggregated gradient update vector, so as to obtain updated weight parameters;
in step S1095, when the trained service request model converges, a target service request model is obtained according to the trained service request model.
In an embodiment of the present disclosure, the private service request model and the common service request model may be a neural network model, a convolutional neural network model, or a long-short term memory network model.
In an embodiment of the present disclosure, obtaining the target service request model according to the trained private service request model may be understood as storing the trained private service request model as the target service request model, or may be understood as directly identifying the trained private service request model as the target service request model.
In this embodiment, the update weight parameter sent by the edge server is received by the service server management end, and is obtained by aggregating the gradient update vectors sent by the edge server management ends by the edge server according to the aggregated gradient update vectors, and updating the weight parameter of the common service request model of the edge server according to the aggregated gradient update vectors, so that the updated common service request model can reflect the common rule between the illegal service parameters obtained by the common service request model of the edge server in the previous training, the client identifier of the client sending the real-time service request including the illegal service parameters, and other service requests which may have been sent to the service server before the client sends the real-time service request including the illegal service parameters and may damage the service system carried by the service server; by taking the fault service parameter and the associated client identification as input, taking the associated service request as output and training the updated service request model, the updated private service request model can learn the common regularity, and also can be used for individualizing the illegal service parameters acquired by the service server management end and sending the client identification of the client comprising the illegal service parameter real-time service request and the private regularity between other service requests which are possibly sent to the service server before the client sends the illegal service parameter real-time service request and possibly damage a service system borne by the service server; when the trained private service request model is not converged, the trained private service request model still needs to be trained, a gradient update vector is obtained according to the trained private service request model, and the gradient update vector is sent, so that the edge server can continuously obtain corresponding update weight parameters based on the gradient update vectors uploaded by the management ends of the plurality of service servers on the premise of not revealing private data of the management ends of the service servers, and the private service request models of the management ends of the service servers are continuously trained; when the trained private service request model converges, the converged private service request model can send a client identifier of a client including the illegal service parameter real-time service request based on the illegal service parameters, and obtain other service requests which may have been sent to the service server by the client before sending the real-time service request including the illegal service parameters and may cause damage to a service system carried by the service server, so that the converged private service request model is used as a target service request model.
According to the technical scheme provided by the disclosure, a private service request model is obtained according to a service request model; receiving an update weight parameter sent by an edge server, and updating the private service request model according to the update weight parameter; taking the fault service parameter and the associated client terminal identification as input, taking the associated service request as output, and training the updated service request model; when the trained service request model is not converged, acquiring a gradient update vector according to the trained service request model, and sending the gradient update vector, wherein the edge server is used for aggregating the gradient update vector, and updating the weight parameters of the common service request model of the edge server according to the aggregated gradient update vector to acquire updated weight parameters; when the trained service request model converges, the target service request model is obtained according to the trained service request model, so that the training process can be executed by the edge server and the terminal together, and the service request model can learn not only the common rule but also the private rule, thereby improving the training efficiency and improving the user experience.
In one implementation manner of the present disclosure, before obtaining the private service request model according to the service request model, the method further includes:
receiving a private data uploading instruction;
responding to the private data uploading instruction, and sending a fault service parameter, an associated client identifier and an associated service request;
receiving an initial weight parameter sent by an edge server;
obtaining a private service request model according to a service request model, comprising:
and updating the initial service request model according to the initial weight parameter so as to obtain a private service request model.
The initial service request model may be a neural network model, a convolutional neural network model, a long-short term memory network model, or the like, and the initial service request model may be understood as an untrained model.
In this embodiment, by receiving a private data upload instruction; and responding to the private data uploading instruction, sending the fault service parameter, the associated client identifier and the associated service request, so that the edge server can perform preliminary training on an initial service request model of the edge server according to the fault service parameter, the associated client identifier and the associated service request to obtain a common service request model on the edge server, and at the moment, the common service request model can be understood as a model obtained by preliminarily learning rules among the fault service parameters, the associated client identifiers and the associated service requests acquired by a plurality of terminals. And then updating the initial service request model according to the initial weight parameters by receiving the initial weight parameters sent by the edge server to obtain the private service request model, wherein the private service request model can understand the model of the rule learned by the common service request model, so that the private service request model can be conveniently trained for multiple rounds, training based on the initial service request model is not needed, and the training difficulty is reduced.
The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.
According to the service request processing device of an embodiment of the present disclosure, the service request processing device may be implemented as part or all of an electronic device by software, hardware, or a combination of the two. Fig. 6 is a schematic block diagram of a service request processing device according to an embodiment of the present disclosure, and as shown in fig. 6, the service request processing device 200 includes:
a real-time request acquisition module 201, configured to intercept real-time interaction data between the client and the service server, and acquire at least one real-time service request sent by the client to the service server according to the real-time interaction data;
an illegal request rejection module 202 configured to send a service request rejection instruction in response to determining that the real-time service request includes at least one illegal service parameter, the service request rejection instruction being used for instructing the service server to reject data interaction with the client;
a simulation request obtaining module 203, configured to obtain a target service request model obtained by pre-training, and input at least one illegal service parameter as an input into the target service request model to obtain a simulated illegal service request output by the target service request model;
a request countermeasure acquisition module 204 configured to acquire simulated service response information according to the simulated illegal service request, and acquire illegal service request countermeasure information according to the simulated service response information, where the illegal service request countermeasure information is used to instruct a service server to process a policy of a service request sent by a client;
a request countermeasure transmission module 205 configured to transmit illegal traffic request countermeasure information.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
acquiring a target client identification corresponding to a client sending a real-time service request;
inputting a target service request model by taking at least one illegal service parameter as input so as to obtain a simulated illegal service request output by the target service request model, wherein the steps of:
and inputting at least one illegal service parameter and the target client identification as inputs into the target service request model to obtain the simulated illegal service request output by the target service request model.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
acquiring historical interactive data between a client and a service server and a historical log of the service server;
responding to at least one fault event contained in the historical log, acquiring fault time and fault service parameters corresponding to the fault event, and acquiring at least one associated service request associated with the fault event in a target time length before the fault time and an associated client identifier corresponding to a client sending the associated service request according to historical interaction data, wherein parameter values of service parameters in the associated service request are all out of a legal value range of the corresponding service parameters;
and acquiring a service request model, taking the fault service parameter and the associated client identification as input, taking the associated service request as output, and training the service request model to acquire a target service request model.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
acquiring a private service request model according to the service request model;
receiving an update weight parameter sent by an edge server, and updating the private service request model according to the update weight parameter;
taking the fault service parameter and the associated client terminal identification as input, taking the associated service request as output, and training the updated service request model;
when the trained service request model is not converged, acquiring a gradient update vector according to the trained service request model and sending the gradient update vector, wherein the edge server is used for aggregating the gradient update vector and updating the weight parameters of the common service request model of the edge server according to the aggregated gradient update vector to acquire updated weight parameters;
and when the trained service request model is converged, acquiring a target service request model according to the trained service request model.
In one implementation of the present disclosure, the simulation request obtaining module is further configured to:
receiving a private data uploading instruction;
responding to the private data uploading instruction, and sending a fault service parameter, an associated client identifier and an associated service request;
receiving an initial weight parameter sent by an edge server;
obtaining a private service request model according to a service request model, comprising:
and updating the initial service request model according to the initial weight parameter so as to obtain a private service request model.
In the technical scheme, by intercepting the real-time interactive data between the client and the service server and acquiring at least one real-time service request sent by the client to the service server according to the real-time interactive data, whether the real-time service request comprises illegal service parameters or not is determined, namely whether the real-time service request possibly damages a service system borne by the service server or not is determined. When the real-time service request is determined to include at least one illegal service parameter, namely the real-time service request may damage a service system carried by the service server, a service request rejection instruction is sent in response to the fact that the real-time service request includes the at least one illegal service parameter, so that the service server is instructed to reject data interaction with the client side, and the service system carried by the service server is prevented from being damaged as much as possible. And meanwhile, acquiring a target service request model obtained by pre-training, inputting at least one illegal service parameter as input, and inputting the target service request model to acquire an illegal service request simulation output by the target service request model, wherein the illegal service request simulation can be understood as a service request which is possibly damaged to a service system borne by a service server and is sent by a client before the client sends a real-time service request comprising the at least one illegal service parameter when the client is determined to send the real-time service request. The method comprises the steps of obtaining simulated service response information according to simulated illegal service requests, obtaining illegal service request countermeasure information according to the simulated service response information, and sending the illegal service request countermeasure information so as to indicate a service server to carry out corresponding processing according to the illegal service request countermeasure information, so that the probability that a service system is damaged and crashed due to damage of other service requests sent by a client to the service system borne by the service server is eliminated, and the stability of the service system is improved.
The present disclosure also discloses an electronic device, fig. 7 shows a schematic structural block diagram of an electronic device according to an embodiment of the present disclosure, as shown in fig. 7, the electronic device includes a memory and a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement any of the methods of the embodiments of the present disclosure.
FIG. 8 shows a schematic block diagram of a computer system suitable for use in implementing a method according to an embodiment of the present disclosure.
As shown in fig. 8, the computer system includes a processing unit that can execute the various methods in the above-described embodiments according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage section into a Random Access Memory (RAM). In the RAM, various programs and data necessary for the operation of the computer system are also stored. The processing unit, the ROM, and the RAM are connected to each other through a bus. An input/output (I/O) interface is also connected to the bus.
The following components are connected to the I/O interface: an input section including a keyboard, a mouse, and the like; an output section including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section including a hard disk and the like; and a communication section including a network interface card such as a LAN card, a modem, or the like. The communication section performs a communication process via a network such as the internet. The drive is also connected to the I/O interface as needed. A removable medium such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive as needed, so that the computer program read out therefrom is mounted into the storage section as needed. The processing unit can be realized as a CPU, a GPU, a TPU, an FPGA, an NPU and other processing units.
In particular, the above described methods may be implemented as computer software programs according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the above-described method. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section, and/or installed from a removable medium.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units or modules described in the embodiments of the present disclosure may be implemented by software or by programmable hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.
As another aspect, the present disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the electronic device or the computer system in the above embodiments; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Claims (10)
1. A service request processing method, characterized in that the method comprises:
intercepting real-time interactive data between a client and a service server, and acquiring at least one real-time service request sent to the service server by the client according to the real-time interactive data;
responding to the real-time service request which is determined to comprise at least one illegal service parameter, and sending a service request rejection instruction, wherein the service request rejection instruction is used for indicating the service server to reject data interaction with the client;
acquiring a target service request model obtained by pre-training, inputting the at least one illegal service parameter as input into the target service request model to acquire a simulated illegal service request output by the target service request model;
acquiring simulation service response information according to the simulation illegal service request, and acquiring illegal service request countermeasure information according to the simulation service response information, wherein the illegal service request countermeasure information is used for indicating a strategy of processing a service request sent by the client by the service server;
and sending the illegal service request countermeasure information.
2. The method according to claim 1, wherein before inputting the at least one illegal service parameter as an input into the target service request model to obtain the simulated illegal service request output by the target service request model, the method further comprises:
acquiring a target client identifier corresponding to a client sending the real-time service request;
the inputting the at least one illegal service parameter as an input into the target service request model to obtain the simulated illegal service request output by the target service request model includes:
and inputting the target service request model by taking the at least one illegal service parameter and the target client identification as input so as to obtain the simulated illegal service request output by the target service request model.
3. The method of claim 2, wherein before obtaining the pre-trained target service request model, the method further comprises:
acquiring historical interaction data between the client and the service server and a historical log of the service server;
responding to the historical log including at least one fault event, acquiring a fault moment and fault service parameters corresponding to the fault event, and acquiring at least one associated service request associated with the fault event within a target time length before the fault moment and an associated client identifier corresponding to a client sending the associated service request according to the historical interaction data, wherein parameter values of the service parameters in the associated service request are all out of a legal value range of the corresponding service parameters;
and acquiring a service request model, taking the fault service parameter and the associated client identification as input, taking the associated service request as output, and training the service request model to acquire the target service request model.
4. The method according to claim 3, wherein the training the service request model to obtain the target service request model with the fault service parameter and the associated client identifier as inputs and the associated service request as an output comprises:
acquiring a private service request model according to the service request model;
receiving an update weight parameter sent by an edge server, and updating the private service request model according to the update weight parameter;
taking the fault service parameter and the associated client identification as input, taking the associated service request as output, and training the updated service request model;
when the trained service request model is not converged, acquiring a gradient update vector according to the trained service request model, and sending the gradient update vector, wherein the edge server is used for aggregating the gradient update vector, and updating the weight parameters of the common service request model of the edge server according to the aggregated gradient update vector to acquire the update weight parameters;
and when the trained service request model is converged, acquiring the target service request model according to the trained service request model.
5. The method of claim 4, wherein before obtaining the private service request model according to the service request model, the method further comprises:
receiving a private data uploading instruction;
responding to the private data uploading instruction, and sending the fault service parameter, the associated client identification and the associated service request;
receiving an initial weight parameter sent by an edge server;
the obtaining of the private service request model according to the service request model includes:
and updating the initial service request model according to the initial weight parameter so as to obtain the private service request model.
6. A service request processing apparatus, wherein the apparatus comprises:
the real-time request acquisition module is configured to intercept real-time interactive data between a client and a service server and acquire at least one real-time service request sent to the service server by the client according to the real-time interactive data;
an illegal request rejection module configured to send a service request rejection instruction in response to determining that the real-time service request includes at least one illegal service parameter, the service request rejection instruction being used to instruct the service server to reject data interaction with the client;
a simulation request obtaining module configured to obtain a target service request model obtained by pre-training, input the target service request model with the at least one illegal service parameter as input, and obtain a simulated illegal service request output by the target service request model;
a request countermeasure acquisition module configured to acquire simulated service response information according to the simulated illegal service request and acquire illegal service request countermeasure information according to the simulated service response information, where the illegal service request countermeasure information is used to instruct the service server to process a policy of a service request sent by the client;
and the request strategy sending module is configured to send the illegal service request strategy information.
7. The service request processing apparatus according to claim 6, wherein the simulation request obtaining module is further configured to:
acquiring a target client identifier corresponding to a client sending the real-time service request;
the inputting the at least one illegal service parameter as an input into the target service request model to obtain the simulated illegal service request output by the target service request model includes:
and inputting the at least one illegal service parameter and the target client identification as input into the target service request model to obtain the simulated illegal service request output by the target service request model.
8. The service request processing apparatus according to claim 7, wherein the simulation request obtaining module is further configured to:
obtaining historical interaction data between the client and the service server and a historical log of the service server;
responding to at least one fault event included in the historical log, acquiring a fault time and fault service parameters corresponding to the fault event, and acquiring at least one associated service request associated with the fault event within a target time length before the fault time and an associated client identifier corresponding to a client sending the associated service request according to the historical interaction data, wherein parameter values of the service parameters in the associated service request are all out of a legal value range of the corresponding service parameters;
and acquiring a service request model, taking the fault service parameter and the associated client identification as input, taking the associated service request as output, and training the service request model to acquire the target service request model.
9. An electronic device, characterized in that the electronic device comprises a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the method of any of claims 1-5.
10. A readable storage medium, having stored thereon computer instructions which, when executed by a processor, carry out the method steps of any of claims 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210982855.3A CN115473692A (en) | 2022-08-16 | 2022-08-16 | Service request processing method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210982855.3A CN115473692A (en) | 2022-08-16 | 2022-08-16 | Service request processing method, device, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115473692A true CN115473692A (en) | 2022-12-13 |
Family
ID=84368065
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210982855.3A Pending CN115473692A (en) | 2022-08-16 | 2022-08-16 | Service request processing method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115473692A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111915417A (en) * | 2020-07-31 | 2020-11-10 | 中国工商银行股份有限公司 | Tax payment amount determining method and device and electronic equipment |
-
2022
- 2022-08-16 CN CN202210982855.3A patent/CN115473692A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111915417A (en) * | 2020-07-31 | 2020-11-10 | 中国工商银行股份有限公司 | Tax payment amount determining method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110399550B (en) | Information recommendation method and device | |
CN112242984B (en) | Method, electronic device and computer program product for detecting abnormal network request | |
CN113157545A (en) | Method, device and equipment for processing service log and storage medium | |
CN114338064B (en) | Method, device, system, equipment and storage medium for identifying network traffic type | |
WO2022151815A1 (en) | Method and apparatus for determining security state of terminal device | |
CN112465513A (en) | Network security system and method based on identity authentication | |
US20230418943A1 (en) | Method and device for image-based malware detection, and artificial intelligence-based endpoint detection and response system using same | |
CN115473692A (en) | Service request processing method, device, equipment and medium | |
CN114328132A (en) | Method, device, equipment and medium for monitoring state of external data source | |
CN105553700A (en) | Intelligent equipment fault identification detection and solution providing system | |
CN114205134A (en) | Network policy detection method, electronic device, and storage medium | |
CN113282920B (en) | Log abnormality detection method, device, computer equipment and storage medium | |
CN110830416A (en) | Network intrusion detection method and device | |
CN113645233A (en) | Wind control intelligent decision method and device for flow data, electronic equipment and medium | |
CN115378619A (en) | Sensitive data access method, electronic equipment and computer readable storage medium | |
CN110474899B (en) | Service data processing method, device, equipment and medium | |
CN117093627A (en) | Information mining method, device, electronic equipment and storage medium | |
CN115840965B (en) | Information security guarantee model training method and system | |
CN115022171B (en) | Method and device for optimizing update interface, electronic equipment and readable storage medium | |
CN116629379A (en) | Federal learning aggregation method and device, storage medium and electronic equipment | |
CN112351030B (en) | Data processing method and computer equipment | |
CN113783862B (en) | Method and device for checking data in edge cloud cooperation process | |
CN113672453B (en) | Monitoring method and device for display page, electronic equipment and storage medium | |
CN114915434A (en) | Network agent detection method, device, storage medium and computer equipment | |
CN114095531A (en) | Cloud management method of smart city Internet of things equipment and Internet of things cloud platform system |
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 |