CN115134433A - A method, system, device and storage medium for semantic analysis of industrial control protocol - Google Patents

Abstract

The embodiment of the invention provides a semantic analysis method, a semantic analysis system, semantic analysis equipment and a storage medium for an industrial control protocol, wherein the method comprises the following steps: the method comprises the steps of identifying each data stream from bus protocol streams by utilizing a preset multi-mode matching algorithm, determining the protocol type of the data stream meeting the requirement of a preset protocol header format as an industrial Ethernet protocol type, determining the protocol type of the data stream not meeting the requirement of the preset protocol header format as a field bus protocol type, dividing each data stream by using a protocol format corresponding to the protocol type, carrying out semantic analysis on each field according to the protocol format, obtaining a semantic analysis result of each field, obtaining an industrial human-computer interface, identifying, obtaining industrial control data of each display area in the industrial human-computer interface, and determining the positions and meanings of an area identification field and a variable data field in each data stream based on the industrial control data and the industrial control data field. The invention improves the resolution precision and the resolution efficiency of the industrial control protocol.

Description

A method, system, device and storage medium for semantic analysis of industrial control protocol

technical field

The invention relates to the technical field of information processing, in particular to a method, system, device and storage medium for semantic analysis of industrial control protocols.

Background technique

With the development of information technology, the Industrial Internet (Industrial Internet) is widely used in the field of industrial control as an infrastructure for industrial digitalization, networking and intelligent transformation. However, due to the industrial control protocol in the Industrial Internet, its number and protocol complexity are much higher than those of the traditional Ethernet protocol. As a result, when the prior art uses the traditional Ethernet protocol-based parsing method to parse the industrial control protocol, the parsing precision and efficiency are low. In addition, due to the low parsing accuracy and parsing efficiency of the industrial control protocol, the risk of data transmission delay in the industrial Internet will occur, thus affecting the operational reliability of each access device in the industrial Internet. Therefore, how to improve the parsing accuracy and parsing efficiency of industrial control protocols has become an urgent problem to be solved.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present invention is to provide a method, system, device and storage medium for semantic parsing of industrial control protocols, so as to achieve the purpose of improving the parsing precision and parsing efficiency of industrial control protocols. The specific technical solutions are as follows:

A semantic parsing method for an industrial control protocol, the semantic parsing method comprising:

Using the preset multi-pattern matching algorithm, according to the preset protocol header format requirements, identify each data stream from the bus protocol stream, and determine the protocol type of the data stream that meets the preset protocol header format requirements as Industrial Ethernet For the protocol type, the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type.

Using a protocol format corresponding to the protocol type, field division is performed on each data stream, and semantic parsing is performed on each field of each data stream according to the protocol format to obtain a semantic parsing result of each field.

Obtain an industrial man-machine interface, identify the industrial man-machine interface, obtain industrial control data of each display area in the industrial man-machine interface, and determine the area identification field in each data stream based on the industrial control data and the industrial control data field and the position and meaning of the variable data field, wherein the industrial control data field is a field whose data type is industrial control data in the semantic analysis result.

Optionally, the use of a preset multi-pattern matching algorithm to identify each data stream from the bus protocol stream according to the preset protocol header format requirements, and the protocol type of the data stream that meets the preset protocol header format requirements. , which is determined as the industrial Ethernet protocol type, and the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type, including:

For each data stream in the bus protocol stream:

Use the preset multi-pattern matching algorithm to determine whether the data stream contains protocol header data; The network protocol type is determined as the protocol type of the data stream.

In the case that the data stream does not contain the protocol header data, the protocol type of the data stream is determined as the field bus protocol type.

Optionally, in the case that the protocol type of the data stream is the industrial Ethernet protocol type, the use of the protocol format corresponding to the protocol type is used to perform field division on each data stream, and according to the protocol format. Perform semantic analysis on each field of each data stream to obtain the semantic analysis result of each field, including:

For each data stream whose protocol type is the Industrial Ethernet protocol type:

Using a preset string segmentation algorithm, the information entropy of each byte in the data stream and the mutual information between adjacent bytes are calculated, and each segmentation point of the data stream is determined according to the information entropy and the mutual information.

The data stream is divided into a plurality of fields according to each division point.

According to the Ethernet protocol stream identifier in the protocol type of the data stream, a protocol format matching the Ethernet protocol stream identifier is obtained.

For each field: a preset reverse parsing algorithm is used to determine the first semantic parsing result of each field according to the protocol format matched with the Ethernet protocol flow identifier, and the first semantic parsing result includes the semantics and data type of each field.

Optionally, when the protocol type of the data stream is the fieldbus protocol type, it also includes:

For each data stream whose protocol type is the fieldbus protocol type:

The bus protocol stream identifier of the data stream is determined according to the byte length of the data stream, and a protocol format matching the bus protocol stream identifier is obtained.

Using a preset byte semantic inference algorithm, according to the protocol format matching the bus protocol stream identifier, the data stream is divided into a control command field, a protocol data field and a terminator field.

Using the preset byte semantic inference algorithm, according to the protocol format matching the bus protocol flow identifier, each subfield in the protocol data field is determined, and the control command field, each subfield and the Semantic parsing is performed on the terminator field to obtain a second semantic parsing result of each field and each subfield, where the second semantic parsing result includes the semantics and data type of each field or each subfield.

Optionally, the obtaining of the industrial human-machine interface is to identify the industrial human-machine interface, obtain industrial control data of each display area in the industrial human-machine interface, and determine each data based on the industrial control data and the industrial control data field. The location and meaning of the area ID fields and variable data fields in the stream, including:

Using a preset image recognition algorithm, the industrial control data of each display area in the industrial human-machine interface is obtained.

Industrial control data for each display area:

A target data stream is acquired according to the industrial control data in the display area, wherein the target data stream is a data stream that has a field matching the data encoding of the industrial control data in the display area.

Using a preset sequence comparison algorithm, the constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared, and determined as the region identification field, and the meaning of the constant data sequence identified by the preset image recognition algorithm is determined as the meaning of the region identification field.

Using the preset sequence comparison algorithm, the non-constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared. is determined as the variable data field, and the meaning of the non-constant data sequence identified by the preset image recognition algorithm is determined as the meaning of the variable data field.

A semantic parsing system of an industrial control protocol, the semantic parsing system comprising:

The protocol type determination unit uses a preset multi-pattern matching algorithm to identify each data stream from the bus protocol stream according to the preset protocol header format requirements, and determines the protocol type of the data stream that meets the preset protocol header format requirements, It is determined as the industrial Ethernet protocol type, and the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type.

The field semantic parsing unit uses the protocol format corresponding to the protocol type to perform field division on each data stream, and performs semantic parsing on each field of each data stream according to the protocol format to obtain the semantic parsing result of each field.

A key field determination unit is used to obtain an industrial human-machine interface, identify the industrial human-machine interface, obtain industrial control data of each display area in the industrial human-machine interface, and determine based on the industrial control data and the industrial control data field The location and meaning of the area identification field and the variable data field in each data stream, wherein the industrial control data field is a field whose data type is industrial control data in the semantic analysis result.

Optionally, the protocol type determination unit is set to:

For each data stream in the bus protocol stream:

Determine whether the data stream contains protocol header data, and if so, determine the industrial Ethernet protocol type that matches the protocol header data of the data stream in the preset protocol header format requirements as the data stream of the data stream. agreement type.

In the case that the data stream does not contain the protocol header data, the protocol type of the data stream is determined as the field bus protocol type.

Optionally, when the protocol type of the data stream is the industrial Ethernet protocol type, the field semantic parsing unit is set to:

For each data stream whose protocol type is the Industrial Ethernet protocol type:

Using a preset string segmentation algorithm, the information entropy of each byte in the data stream and the mutual information between adjacent bytes are calculated, and each segmentation point of the data stream is determined according to the information entropy and the mutual information.

The data stream is divided into a plurality of fields according to each division point.

According to the Ethernet protocol stream identifier in the protocol type of the data stream, a protocol format matching the Ethernet protocol stream identifier is obtained.

For each field: a preset reverse parsing algorithm is used to determine the first semantic parsing result of each field according to the protocol format matched with the Ethernet protocol flow identifier, and the first semantic parsing result includes the semantics and data type of each field.

Optionally, when the protocol type of the data stream is the fieldbus protocol type, the field semantic parsing unit is further set to:

For each data stream whose protocol type is the fieldbus protocol type:

The bus protocol stream identifier of the data stream is determined according to the byte length of the data stream, and a protocol format matching the bus protocol stream identifier is obtained.

Using a preset byte semantic inference algorithm, according to the protocol format matching the bus protocol stream identifier, the data stream is divided into a control command field, a protocol data field and a terminator field.

Using the preset byte semantic inference algorithm, according to the protocol format matching the bus protocol flow identifier, each subfield in the protocol data field is determined, and the control command field, each subfield and the Semantic parsing is performed on the terminator field to obtain a second semantic parsing result of each field and each subfield, where the second semantic parsing result includes the semantics and data type of each field or each subfield.

Optionally, the key field determination unit is set to:

Using a preset image recognition algorithm, the industrial control data of each display area in the industrial human-machine interface is obtained.

Industrial control data for each display area:

A target data stream is acquired according to the industrial control data in the display area, wherein the target data stream is a data stream that has a field matching the data encoding of the industrial control data in the display area.

Using a preset sequence comparison algorithm, the constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared, and determined as the region identification field, and the meaning of the constant data sequence identified by the preset image recognition algorithm is determined as the meaning of the region identification field.

Using the preset sequence comparison algorithm, the non-constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared. is determined as the variable data field, and the meaning of the non-constant data sequence identified by the preset image recognition algorithm is determined as the meaning of the variable data field.

A semantic parsing device for an industrial control protocol, the semantic parsing device comprising:

processor;

memory for storing instructions executable by the processor.

Wherein, the processor is configured to execute the instruction to implement the method for semantic parsing of the industrial control protocol according to any one of the above.

A computer-readable storage medium, when an instruction in the computer-readable storage medium is executed by a processor of a semantic analysis device of an industrial control protocol, the semantic analysis device can execute the industrial control protocol described in any of the above semantic analysis method.

The method, system, device and storage medium for semantic parsing of industrial control protocols provided by the embodiments of the present invention can set protocol header format requirements by introducing a preset multi-pattern matching algorithm and based on the structure and type of the industrial control protocol encapsulation header. From a large number of bus protocol streams, it can efficiently identify multiple data streams that meet the requirements of the preset protocol header format, and accurately determine the protocol type of each data stream. At the same time, the protocol format of the generated data stream is determined by the protocol type, and the data stream is divided into fields and semantically analyzed according to the protocol format, so as to realize the accurate analysis of the semantics of each field in the same data stream. Finally, by acquiring the industrial control data of each display area, and comparing the value of the industrial control data with the industrial control data field in the data stream, the present invention, compared with the prior art, realizes that the meaning and position in the data stream are not clear. accurate parsing of the fields. It can be seen that the present invention achieves the purpose of improving the analytical precision and analytical efficiency of the industrial control protocol.

Of course, it is not necessary for any product or method to implement the present invention to simultaneously achieve all of the advantages described above.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a flowchart of a method for semantic parsing of an industrial control protocol provided by an embodiment of the present invention;

2 is a schematic diagram of a data structure of a preset multi-pattern matching algorithm provided by an optional embodiment of the present invention;

3 is a schematic diagram of field division and semantic analysis of an industrial Ethernet protocol type data stream provided by another optional embodiment of the present invention;

4 is a schematic diagram of an industrial man-machine interface provided by another optional embodiment of the present invention;

5 is a block diagram of a system provided by another optional embodiment of the present invention;

FIG. 6 is a block diagram of a device provided by another optional embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

An embodiment of the present invention provides a semantic parsing method for an industrial control protocol, as shown in FIG. 1 , the semantic parsing method includes:

S101. Using a preset multi-pattern matching algorithm, according to the preset protocol header format requirements, identify each data stream from the bus protocol stream, and determine the protocol type of the data stream that meets the preset protocol header format requirements as Industrial Ethernet For the protocol type, the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type.

Optionally, in an optional embodiment of the present invention, the above-mentioned preset multi-pattern matching algorithm may be constructed according to the protocol header format of the above-mentioned industrial Ethernet protocol and based on a multi-pattern matching algorithm (multi-pattern matching algorithm). algorithm. Because the data volume and transmission efficiency of industrial control protocols are higher than those of ordinary communication protocols during the transmission process, and the protocol formats between different industrial control protocols are quite different. As a result, in the application scenario of large-scale data transmission, the existing technology cannot realize accurate and efficient identification of different industrial control protocols. The multi-pattern matching algorithm is an algorithm proposed for large-scale multi-keyword matching problems. Therefore, by introducing the above-mentioned preset multi-pattern matching algorithm, the present invention can accurately and efficiently identify multiple data streams that meet the requirements of the above-mentioned preset protocol header format from a large number of bus protocol streams.

Optionally, in another optional embodiment of the present invention, the above-mentioned field bus protocol is an industrial control protocol used for transmitting control signals between machines and equipment in a factory. The above-mentioned industrial Ethernet protocol is a communication protocol used to transmit other types of data while transmitting control signals. Due to the data flow of the industrial Ethernet protocol type, compared with the data flow of the field bus protocol type, the industrial control protocol encapsulation header is added in the data structure. Therefore, the present invention can realize accurate identification of data streams of different protocol types by setting the format requirements of the protocol header based on the structure and type of the encapsulation header of the industrial control protocol.

Optionally, in another optional embodiment of the present invention, the specific types of the above-mentioned field bus protocol types may be multiple, for example, a controller area network (Controller Area Network, CAN) protocol, a process field bus (Process Field Bus) protocol. , Profibus) protocol, etc.

Optionally, in an optional embodiment of the present invention, the specific types of the above-mentioned industrial Ethernet protocol types can be multiple, such as transmission control protocol (Transmission Control Protocol, TCP), industrial Ethernet communication protocol (EtherNet Industrial Protocol, EtherNet/IP), etc.

Optionally, in another optional embodiment of the present invention, in an actual application scenario, the above-mentioned implementation manner of determining the protocol type of each data stream may be determining the specific protocol type of each data stream, and generating the protocol type according to the protocol type. Corresponding electronic label.

S102 , using a protocol format corresponding to the protocol type, perform field division on each data stream, and perform semantic analysis on each field of each data stream according to the protocol format, to obtain a semantic analysis result of each field.

The above-mentioned protocol format refers to a frame format specified according to different protocols, that is, a frame format. In the data streams generated by different industrial control protocols, fields in different positions represent different meanings. And for the data stream generated by the same industrial control protocol, although the string length will vary with the amount of data information it carries. However, industrial control protocols are used to differentiate by adding delimiters to strings that characterize different data types. Therefore, the protocol format of the generated data stream is determined by the protocol type, and the field division and semantic analysis of the data stream are performed according to the protocol format, so as to realize the accurate analysis of the semantics of each field in the same data stream.

Optionally, in an optional embodiment of the present invention, the content of the above-mentioned semantic analysis result may be the meaning of the field, the data type of the data represented by the field, and the like.

S103, obtaining an industrial man-machine interface, identifying the industrial man-machine interface, obtaining industrial control data of each display area in the industrial man-machine interface, and determining the area identification field and variable data field in each data stream based on the industrial control data and the industrial control data field The location and meaning of , where the industrial control data field is a field whose data type is industrial control data in the semantic analysis result.

Wherein, the above-mentioned Industrial Human Machine Interface (Industrial Human Machine Interface, IndustrialHMI) is generated by the human-machine interface configuration software applied in the field of industrial control, and is used for the interface of human-machine interaction and control.

Optionally, in an optional embodiment of the present invention, the above-mentioned implementation of identifying the industrial human-machine interface and obtaining the industrial control data of each display area in the industrial human-machine interface may be through a preset image recognition algorithm, It is realized by sub-regional acquisition of image data in industrial man-machine interface.

Optionally, in another optional embodiment of the present invention, the image content displayed on the industrial human-machine interface is important industrial control data such as the operating state or operating parameters that affect the reliability of the equipment's operation. Because these industrial control data are often in a state of change. As a result, the industrial control protocol will not reflect the specific meaning and location of the corresponding fields of the above industrial control data in the data stream, but only display the values in the corresponding fields. However, the existing parsing methods can only implement parsing of fields with specific meanings set in the industrial control protocol. Therefore, the present invention obtains the industrial control data of the above-mentioned display areas, and compares the value of the industrial control data with the industrial control data field in the data stream, so that the present invention, compared with the prior art, realizes the meaning and difference in the data stream. Accurate parsing of poorly positioned fields.

The present invention sets the protocol header format requirements by introducing a preset multi-mode matching algorithm and based on the structure and type of the industrial control protocol encapsulation header. From a large number of bus protocol streams, it can efficiently identify multiple data streams that meet the requirements of the preset protocol header format, and accurately determine the protocol type of each data stream. At the same time, the protocol format of the generated data stream is determined by the protocol type, and the data stream is divided into fields and semantically analyzed according to the protocol format, so as to realize the accurate analysis of the semantics of each field in the same data stream. Finally, by acquiring the industrial control data of each display area, and comparing the value of the industrial control data with the industrial control data field in the data stream, the present invention, compared with the prior art, realizes that the meaning and position in the data stream are not clear. accurate parsing of the fields. It can be seen that the present invention achieves the purpose of improving the analytical precision and analytical efficiency of the industrial control protocol.

Optionally, use a preset multi-pattern matching algorithm to identify each data stream from the bus protocol stream according to the preset protocol header format requirements, and determine the protocol type of the data stream that meets the preset protocol header format requirements as industrial. Ethernet protocol type, the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type, including:

For each data stream in the bus protocol stream:

Use the preset multi-pattern matching algorithm to determine whether the data stream contains protocol header data, and if so, determine the industrial Ethernet protocol type that matches the protocol header data of the data stream in the preset protocol header format requirements as the The protocol type of the data stream.

In the case that the data stream does not contain protocol header data, the protocol type of the data stream is determined as the field bus protocol type.

It should be noted that, in practical application scenarios, there are various implementations for determining whether the data stream contains protocol header data and determining the protocol type of the data stream by using a preset multi-pattern matching algorithm. An example is provided here:

For the convenience of description, the multi-pattern matching AC (Aho-Corasick) algorithm is used as the above-mentioned preset multi-pattern matching algorithm in this example, and the data structure thereof is shown in FIG. 2 .

Set the current data streams to be identified as Q1, Q2, Q3, Q4 and Q5 respectively. Among them, the string representation of data stream Q1 is: 00 18 20. The string representation of data stream Q2 is: 00 20 30. The string representation of data stream Q3 is: 04 20 30. The string representation of data stream Q4 is: 00 20 26. The string representation of data stream Q5 is: 13 27 46.

Referring to Figure 2, the process of using the above-mentioned multi-pattern matching AC algorithm to identify the heads of the above Q1, Q2, Q3, Q4 and Q5 is:

The first characters of Q1, Q2 and Q4 are all "00". The first character of Q3 is "04". And the first characters of Q1, Q2, Q3 and Q4 all have matching items in the above-mentioned multi-pattern matching AC algorithm. Therefore, the second characters of Q1, Q2, Q3 and Q4 can be recognized. And the first type codes of Q1, Q2 and Q4 are determined to be "1". The first type code of Q3 is determined to be "6".

It should be noted that data such as "00-1", "20-2", and "30-3" shown in FIG. 2 represent the specific numerical values of characters at different positions in the above data stream. For example, "00-1" indicates that the value of the first character is 00, and "30-3" indicates that the value of the third character is 30. The present invention will not describe it too much.

It should be noted that the number inside the circle in Figure 2 represents the meaning of the type code corresponding to the character position. This type code can be used to determine the specific Industrial Ethernet protocol type of the data stream. The Root inside the circle in the figure is a virtual follower, which is used to determine the protocol type of each data stream.

The first character of the data stream Q5 has no match in the above-mentioned multi-pattern matching AC algorithm. Therefore, the above-mentioned multi-pattern matching AC algorithm judges that the data stream Q5 does not contain protocol header data, and determines the protocol type of the data stream Q5 as the field bus protocol type.

It should be noted that there are many specific types of fieldbus protocols. Therefore, the above-mentioned multi-mode matching AC algorithm can only determine that the protocol type of the data stream Q5 is the fieldbus protocol type, but cannot determine which specific type of the fieldbus protocol the data stream Q5 belongs to.

When recognizing the second characters of Q1, Q2, Q3 and Q4, the second character of Q1 is "18". The second characters of Q2, Q3 and Q4 are all "20". However, due to the first characters of Q2 and Q4, it is inconsistent with the first character of Q3. Therefore, the second type code of Q1 is determined to be "2". The second type encoding of Q2 and Q4 is determined to be "4". The second type code of Q3 is determined to be "7".

When recognizing the third characters of Q1, Q2, Q3 and Q4, the third character of Q1 is "20". The third character of both Q2 and Q3 is "30". The third character of Q4 is "26". Therefore, the third type code of Q1 is determined to be "3". The third type code of Q2 is determined to be "5". The third type code of Q3 is determined to be "8". The third type code of Q4 is determined to be "9".

Since the characters in each position of Q1, Q2, Q3 and Q4 all have matching items in the above-mentioned multi-pattern matching AC algorithm. Therefore, it is determined that the protocol types of Q1, Q2, Q3 and Q4 are all industrial Ethernet protocols. And according to the first to third type codes of each data stream, the comprehensive type code of each data stream can be determined. Among them, the comprehensive type code of Q1 is "123". The synthesis type code for Q2 is "145". The synthesis type code for Q3 is "678". The synthesis type code for Q4 is "149". According to the comprehensive type coding of each data stream, the specific industrial Ethernet protocol type of each data stream is determined.

Optionally, when the protocol type of the data stream is the industrial Ethernet protocol type, use the protocol format corresponding to the protocol type to divide the fields of each data stream, and perform the field division of each data stream according to the protocol format. Semantic parsing, to obtain the semantic parsing results of each field, including:

For each data stream whose protocol type is Industrial Ethernet protocol type:

Using a preset string segmentation algorithm, the information entropy of each byte in the data stream and the mutual information between adjacent bytes are calculated, and each segmentation point of the data stream is determined according to the information entropy and mutual information.

The data stream is divided into multiple fields according to each split point.

According to the Ethernet protocol stream identifier in the protocol type of the data stream, a protocol format matching the Ethernet protocol stream identifier is obtained.

For each field: use a preset reverse parsing algorithm to determine the first semantic parsing result of each field according to the protocol format matched with the Ethernet protocol stream identifier, and the first semantic parsing result includes the semantics and data type of each field.

Optionally, in an optional embodiment of the present invention, the above-mentioned implementation manner of performing field division and semantic analysis on industrial Ethernet protocol type data streams may be:

See Figure 3. d ₁ to _dn are the byte positions of the data stream. Using a preset information entropy algorithm, the information entropy H(d _j ) of the bytes at each byte position is calculated. Using a preset mutual information calculation algorithm, according to the information entropy of two adjacent bytes, the mutual information MIS(d _j-1 , d _j ) between adjacent bytes is calculated. It is judged whether the amount of mutual information between adjacent bytes is less than the preset dividing threshold, and if not, it is determined that a dividing point g needs to be set between the adjacent two bytes. For example, it is set that MIS(d _j-1 , d _j ) in FIG. 3 is not smaller than the preset segmentation threshold. It is set that the mutual information of other adjacent bytes except d _j-1 and d _j , such as MIS(d ₁ , d ₂ ), MIS(d _n-1 , d _n ), are all smaller than the preset segmentation threshold. Then add a label whose content is the split point g to d _j-1 and d _j . Add labels with the content of consecutive l to other nodes.

Optionally, the preset string segmentation algorithm may be a combined algorithm composed of the preset information entropy algorithm and the preset mutual information calculation algorithm.

After dividing according to the above label content, two fields are obtained: f ₁ and f ₂ .

Due to the above steps, the specific industrial Ethernet protocol type of the data flow has been clarified. Then, the protocol format of the protocol type is retrieved according to the Ethernet protocol flow identifier. And the protocol format should also consist of two fields. Then, using a preset reverse parsing algorithm, according to the semantics and data types of the fields in the protocol format, semantic parsing is performed _on the above _- mentioned fields f1 and f2. For example, in this protocol format, the semantics of the first field is device identification, and the data type is text data. The semantics of the second field is device parameters, and the data type is dynamic data. Then, the semantics and data type of the first field are determined as the _first semantic analysis result of the field f1. The semantics and data type of the _second field are determined as the first semantic analysis result of the field f2.

Optionally, in an optional embodiment of the present invention, the foregoing Ethernet protocol flow identifier may be a label used to determine a specific protocol type.

Those skilled in the art can understand that the above-mentioned preset information entropy algorithm and preset mutual information calculation algorithm can be formulated according to the related concepts and calculation formulas of information entropy and mutual information in information theory. The present invention does not limit or describe the specific construction process of the above two algorithms too much.

Optionally, when the protocol type of the data stream is the fieldbus protocol type, it also includes:

For each data stream whose protocol type is fieldbus protocol type:

The bus protocol flow identifier of the data stream is determined according to the byte length of the data stream, and a protocol format matching the bus protocol stream identifier is obtained.

Using a preset byte semantic inference algorithm, the data stream is divided into a control command field, a protocol data field and a terminator field according to the protocol format matching the bus protocol stream identifier.

Use the preset byte semantic inference algorithm to determine each subfield in the protocol data field according to the protocol format matching the bus protocol stream identifier, and perform semantic analysis on the control command field, each subfield and the terminator field to obtain each field. and the second semantic parsing result of each subfield, where the second semantic parsing result includes the semantics and data type of each field or each subfield.

Optionally, in another optional embodiment of the present invention, due to the data flow structure of the field bus protocol type, it is generally "starter + control command field + protocol data field + terminator field". And the length of each field is relatively fixed. Therefore, the specific field bus protocol type of the data stream can be determined through the above-mentioned byte length.

Those skilled in the art can understand that the above-mentioned preset byte semantic inference algorithm can utilize the existing Java code for extracting character strings based on the set byte length to construct the above-mentioned preset byte semantic inference algorithm. The present invention does not limit or describe the construction process of the above-mentioned preset byte semantic inference algorithm too much.

Optionally, obtain the industrial human-machine interface, identify the industrial human-machine interface, obtain the industrial control data of each display area in the industrial human-machine interface, and determine the area identification field and variable in each data stream based on the industrial control data and the industrial control data field The location and meaning of the data fields, including:

Using the preset image recognition algorithm, the industrial control data of each display area in the industrial human-machine interface is obtained.

Industrial control data for each display area:

The target data stream is acquired according to the industrial control data in the display area, wherein the target data stream is a data stream that has a field matching the data encoding of the industrial control data in the display area.

Using a preset sequence comparison algorithm, the constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared and determined as the area identification field, The meaning of the constant data sequence recognized by the preset image recognition algorithm is determined as the meaning of the area identification field.

Using a preset sequence comparison algorithm, the non-constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared and determined as the variable data field , and determine the meaning of the non-constant data sequence identified by the preset image recognition algorithm as the meaning of the variable data field.

It should be noted that, in practical applications, there are various implementations for determining the location and meaning of the area identification field and the variable data field in each data stream based on the industrial control data and the industrial control data field. Here, an exemplary implementation is provided. :

As shown in FIG. 4 , it is an industrial man-machine interface 401 for monitoring the internal operation state of the boiler. Using a preset image recognition algorithm, image recognition is performed on the industrial man-machine interface 401 to obtain multiple display areas and their industrial control data. Wherein: the area 402 is the boiler body. Region 403 is the pressure valve.

For the convenience of description, the target data stream A of the area 402 and the target data stream B of the area 403 are set. Among them, the target data stream A includes two fields, the meaning of the field A is the device type, and the meaning of the field B is the device number. The target data stream B includes four fields, the meaning of the field C is the instrument category, the meaning of the field D is the value 1, the meaning of the field E is the value 2, and the meaning of the field X is the value 3.

Then, for the area 402, the constant data sequence consisting of the equipment type of boiler and the equipment number of "No. 1 boiler", the field sequence of which corresponds to the two fields of the target data stream A respectively. Then, according to the above-mentioned constant data sequence, the meaning of field A of the target data stream A is determined as boiler equipment, and the meaning of field B is determined as boiler number.

For area 403, the industrial control data of this area obtained after image recognition includes the instrument type of pressure valve and the "11MPa" furnace pressure value. Among them, the pressure valve is a constant data, and the pressure value in the furnace is a fluctuating non-constant data. Therefore, after the above comparison, it is determined that the meaning of field C in the target data stream B is a pressure valve. For the fields D to fields in the target data stream B, determine their meanings as furnace pressure. And field D to the field position of field own, after field C.

Corresponding to the above method embodiments, the present invention also provides a semantic parsing system for an industrial control protocol. As shown in FIG. 5 , the semantic parsing system includes:

The protocol type determination unit 501 uses a preset multi-pattern matching algorithm to identify each data stream from the bus protocol stream according to the preset protocol header format requirements, and determines the protocol type of the data stream that meets the preset protocol header format requirements. For the industrial Ethernet protocol type, the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type.

The field semantic parsing unit 502 uses the protocol format corresponding to the protocol type to perform field division on each data stream, and performs semantic parsing on each field of each data stream according to the protocol format to obtain the semantic parsing result of each field.

The key field determination unit 503 is used to obtain the industrial human-machine interface, identify the industrial human-machine interface, obtain the industrial control data of each display area in the industrial human-machine interface, and determine the data in each data stream based on the industrial control data and the industrial control data field. The location and meaning of the area identification field and the variable data field, where the industrial control data field is a field whose data type is industrial control data in the semantic analysis result.

Optionally, the above-mentioned protocol type determination unit 501 is set to:

For each data stream in the bus protocol stream:

Use the preset multi-pattern matching algorithm to determine whether the data stream contains protocol header data, and if so, determine the industrial Ethernet protocol type that matches the protocol header data of the data stream in the preset protocol header format requirements as the The protocol type of the data stream.

In the case that the data stream does not contain protocol header data, the protocol type of the data stream is determined as the field bus protocol type.

Optionally, when the protocol type of the data stream is the industrial Ethernet protocol type, the field semantic analysis unit 502 is set to:

For each data stream whose protocol type is Industrial Ethernet protocol type:

Using a preset string segmentation algorithm, the information entropy of each byte in the data stream and the mutual information between adjacent bytes are calculated, and each segmentation point of the data stream is determined according to the information entropy and mutual information.

The data stream is divided into multiple fields according to each split point.

According to the Ethernet protocol stream identifier in the protocol type of the data stream, a protocol format matching the Ethernet protocol stream identifier is obtained.

For each field: use a preset reverse parsing algorithm to determine the first semantic parsing result of each field according to the protocol format matched with the Ethernet protocol stream identifier, and the first semantic parsing result includes the semantics and data type of each field.

Optionally, in the case that the protocol type of the data stream is the field bus protocol type, the above-mentioned field semantic analysis unit 502 is also set to:

For each data stream whose protocol type is fieldbus protocol type:

The bus protocol flow identifier of the data stream is determined according to the byte length of the data stream, and a protocol format matching the bus protocol stream identifier is obtained.

Using a preset byte semantic inference algorithm, the data stream is divided into a control command field, a protocol data field and a terminator field according to the protocol format matching the bus protocol stream identifier.

Use the preset byte semantic inference algorithm to determine each subfield in the protocol data field according to the protocol format matching the bus protocol stream identifier, and perform semantic analysis on the control command field, each subfield and the terminator field to obtain each field. and the second semantic parsing result of each subfield, where the second semantic parsing result includes the semantics and data type of each field or each subfield.

Optionally, the key field determination unit 503 is set to:

Using the preset image recognition algorithm, the industrial control data of each display area in the industrial human-machine interface is obtained.

Industrial control data for each display area:

The target data stream is acquired according to the industrial control data in the display area, wherein the target data stream is a data stream that has a field matching the data encoding of the industrial control data in the display area.

Using a preset sequence comparison algorithm, the constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared and determined as the area identification field, The meaning of the constant data sequence recognized by the preset image recognition algorithm is determined as the meaning of the area identification field.

Using a preset sequence comparison algorithm, the non-constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared and determined as the variable data field , and determine the meaning of the non-constant data sequence identified by the preset image recognition algorithm as the meaning of the variable data field.

The embodiment of the present invention also provides a semantic parsing device for an industrial control protocol, as shown in FIG. 6 , the semantic parsing device includes:

processor 601;

Memory 602 for storing instructions executable by processor 601 .

Wherein, the processor 601 is configured to execute an instruction to implement the semantic parsing method of any one of the industrial control protocols as shown in FIG. 1 .

The embodiment of the present invention also provides a computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by the processor of the semantic parsing device of the industrial control protocol, the semantic parsing device can execute the above-mentioned as shown in FIG. 1 . A semantic parsing method for any industrial control protocol.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one memory chip. Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

It will be appreciated by those skilled in the art that the embodiments of the present application may be provided as a method, a system or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture or apparatus that includes the element.

Each embodiment in this specification is described in a related manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments.

The above are merely examples of the present application, and are not intended to limit the present application. Various modifications and variations of this application are possible for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims (10)

1. a semantic analysis method of industrial control protocol, is characterized in that, described semantic analysis method comprises: Using the preset multi-pattern matching algorithm, according to the preset protocol header format requirements, identify each data stream from the bus protocol stream, and determine the protocol type of the data stream that meets the preset protocol header format requirements as Industrial Ethernet Protocol type, the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type; Using the protocol format corresponding to the protocol type, field division is performed on each data stream, and semantic analysis is performed on each field of each data stream according to the protocol format, and the semantic analysis result of each field is obtained; Obtain an industrial man-machine interface, identify the industrial man-machine interface, obtain industrial control data of each display area in the industrial man-machine interface, and determine the area identification field in each data stream based on the industrial control data and the industrial control data field and the position and meaning of the variable data field, wherein the industrial control data field is a field whose data type is industrial control data in the semantic analysis result. 2. The method according to claim 1, characterized in that, using a preset multi-pattern matching algorithm, according to preset protocol header format requirements, identifying each data stream from a bus protocol stream, will satisfy the preset The protocol type of the data stream required by the protocol header format is determined as the industrial Ethernet protocol type, and the protocol type of the data stream that does not meet the requirements of the preset protocol header format is determined as the field bus protocol type, including: For each data stream in the bus protocol stream: Use the preset multi-pattern matching algorithm to determine whether the data stream contains protocol header data; The network protocol type is determined as the protocol type of the data stream; In the case that the data stream does not contain the protocol header data, the protocol type of the data stream is determined as the field bus protocol type. 3. The method according to claim 2, wherein, in the case that the protocol type of the data stream is the industrial Ethernet protocol type, the use of the protocol format corresponding to the protocol type is performed for each data stream. Perform field division, and perform semantic analysis on each field of each data stream according to the protocol format, and obtain the semantic analysis result of each field, including: For each data stream whose protocol type is the Industrial Ethernet protocol type: Using a preset string segmentation algorithm, calculate the information entropy of each byte in the data stream and the mutual information between adjacent bytes, and determine each split point of the data stream according to the information entropy and the mutual information; dividing the data stream into a plurality of fields according to each dividing point; Obtain a protocol format matching the Ethernet protocol stream identifier according to the Ethernet protocol stream identifier in the protocol type of the data stream; For each field: a preset reverse parsing algorithm is used to determine the first semantic parsing result of each field according to the protocol format matched with the Ethernet protocol flow identifier, and the first semantic parsing result includes the semantics and data type of each field. 4. The method according to claim 3, wherein, in the case that the protocol type of the data stream is the fieldbus protocol type, further comprising: For each data stream whose protocol type is the fieldbus protocol type: Determine the bus protocol stream identifier of the data stream according to the byte length of the data stream, and obtain a protocol format matching the bus protocol stream identifier; Using a preset byte semantic inference algorithm, according to the protocol format matching the bus protocol stream identifier, the data stream is divided into a control command field, a protocol data field and a terminator field; Using the preset byte semantic inference algorithm, according to the protocol format matching the bus protocol flow identifier, each subfield in the protocol data field is determined, and the control command field, each subfield and the Semantic parsing is performed on the terminator field to obtain a second semantic parsing result of each field and each subfield, where the second semantic parsing result includes the semantics and data type of each field or each subfield. 5 . The method according to claim 1 , wherein the obtaining an industrial human-machine interface, identifying the industrial human-machine interface, obtaining industrial control data of each display area in the industrial human-machine interface, and based on the The industrial control data and the industrial control data field determine the position and meaning of the area identification field and the variable data field in each data stream, including: Using a preset image recognition algorithm to obtain industrial control data of each display area in the industrial human-machine interface; Industrial control data for each display area: Obtain a target data stream according to the industrial control data in the display area, wherein the target data stream is a data stream with a field matching the data encoding of the industrial control data in the display area; Using a preset sequence comparison algorithm, the constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared, and determined as the region identification field, and determine the meaning of the constant data sequence identified by the preset image recognition algorithm as the meaning of the region identification field; Using the preset sequence comparison algorithm, the non-constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared. is determined as the variable data field, and the meaning of the non-constant data sequence identified by the preset image recognition algorithm is determined as the meaning of the variable data field. 6. A semantic parsing system of an industrial control protocol, wherein the semantic parsing system comprises: The protocol type determination unit uses a preset multi-pattern matching algorithm to identify each data stream from the bus protocol stream according to the preset protocol header format requirements, and determines the protocol type of the data stream that meets the preset protocol header format requirements, Determine as the industrial Ethernet protocol type, and determine the protocol type of the data stream that does not meet the requirements of the preset protocol header format as the field bus protocol type; a field semantic parsing unit, using a protocol format corresponding to the protocol type, to perform field division on each data stream, and to perform semantic parsing on each field of each data stream according to the protocol format, to obtain a semantic parsing result of each field; A key field determination unit is used to obtain an industrial human-machine interface, identify the industrial human-machine interface, obtain industrial control data of each display area in the industrial human-machine interface, and determine based on the industrial control data and the industrial control data field The location and meaning of the area identification field and the variable data field in each data stream, wherein the industrial control data field is a field whose data type is industrial control data in the semantic analysis result. 7. The semantic parsing system according to claim 6, wherein the protocol type determination unit is set to: For each data stream in the bus protocol stream: Determine whether the data stream contains protocol header data, and if so, determine the industrial Ethernet protocol type that matches the protocol header data of the data stream in the preset protocol header format requirements as the data stream of the data stream. agreement type; In the case that the data stream does not contain the protocol header data, the protocol type of the data stream is determined as the field bus protocol type. 8. The semantic parsing system according to claim 6, wherein the key field determining unit is set to: Using a preset image recognition algorithm to obtain industrial control data of each display area in the industrial human-machine interface; Industrial control data for each display area: Obtain a target data stream according to the industrial control data in the display area, wherein the target data stream is a data stream with a field matching the data encoding of the industrial control data in the display area; Using a preset sequence comparison algorithm, the constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared, and determined as the region identification field, and determine the meaning of the constant data sequence identified by the preset image recognition algorithm as the meaning of the region identification field; Using the preset sequence comparison algorithm, the non-constant data sequence in the industrial control data in the display area is sequenced with the industrial control data field of the target data stream, and the consistent field in the industrial control data field is compared. is determined as the variable data field, and the meaning of the non-constant data sequence identified by the preset image recognition algorithm is determined as the meaning of the variable data field. 9. A semantic parsing device for an industrial control protocol, wherein the semantic parsing device comprises: processor; a memory for storing the processor-executable instructions; Wherein, the processor is configured to execute the instructions to implement the method for semantic parsing of an industrial control protocol according to any one of claims 1 to 5. 10. A computer-readable storage medium, characterized in that, when the instructions in the computer-readable storage medium are executed by a processor of a semantic parsing device of an industrial control protocol, the semantic parsing device is enabled to execute the method of claim 1 . The semantic parsing method of the industrial control protocol described in any one of to 5.

Images