JP2020060988A - Name matching device and method - Google Patents

Abstract

To associate a site signal name of a power plant or a plant with a standard signal name used in an analysis substrate of data for using sensor data of various site signals in the analysis substrate.SOLUTION: A name matching device includes: a storage device that stores a word attribute dictionary in which two composite names composed of an object composite name and a standard composite name and an attribute of a word appearing in the composite names, and a syntax of the composite names composed of the word attribute; and a processing part which extracts keywords that characterize the composite name, matches the keywords extracted from the two composite names composed of the object composite name and the standard composite name, and calculates a matching degree of the two composite names.SELECTED DRAWING: Figure 1

Description

  The present invention relates to name matching technology.

  IoT (Internet of Things), which is a mechanism in which various “things” are connected to the Internet and mutually controlled by exchanging information, is drawing attention. Power plants and plants are also required to develop a base for collecting various sensor data, extracting necessary information, and analyzing it by using IoT.

  Patent Literature 1 is a technique for automatically extracting information of interest from researchers from articles in the field of medical biology.

JP-A-2002-32374

  Since Patent Document 1 is intended for natural language processing that is a sentence of an academic document or the like, the document is linguistically analyzed based on terms such as nouns and verbs, but sensors in power plants, plants, etc. No mention is made of the analysis of information, such as signals, which does not use verbs and has a system different from that of ordinary sentences and in which natural language processing cannot simply be applied.

  Therefore, an object of the present invention is to provide a name matching device and method for associating a field signal name of a power plant or a plant with a standard signal name used in the data analysis platform for using sensor data of various field signals in the analysis platform. The purpose is to provide.

  The present invention relates to a name matching device for solving the above problems, and if an example of its application is given, the name matching device includes two compound names including a target compound name and a standard compound name, and a compound name. A word attribute dictionary in which the attributes of words appearing in a name are registered, a storage device that stores the syntax of a compound name composed of word attributes, and a keyword that characterizes the compound name is extracted from the word attribute dictionary and the syntax of the compound name. And a processing unit for matching the keywords extracted from the two compound names including the target compound name and the standard compound name to calculate the matching degree of the two compound names.

  According to the present invention, the target compound name and the two compound names consisting of the standard compound name are associated with each other, for example, the field signal name included in the signals of various sensors used in the power plant or the plant and the standard signal of the analysis base. Correspondence with the name can be efficiently performed.

FIG. 2 is a schematic explanatory diagram of the overall configuration of the system. The figure which showed the signal name file. The figure which showed the signal name matching list. System hardware configuration diagram. The other hardware block diagram of a system. Flow chart of preprocessing in context matching. The figure which shows the table showing a word attribute. Diagram showing words with multiple meanings. The figure which showed the GUI for determining the meaning of a word. The figure which showed the example of BNF of a signal name. The figure which showed the example of the syntax tree of a signal name. The processing flow figure of keyword extraction and keyword matching. The figure which showed the extraction rule of a keyword. The figure which showed the extraction rule of a modifier word. The figure which showed the calculation method of a matching degree. The figure which showed the matching conditions for keyword matching degree calculation.

<Definition of terms in the specification>
Embodiments of the present invention will be described below with reference to the drawings. In each figure, the same components are designated by the same reference numerals.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The following description and drawings are exemplifications for explaining the present invention, and are appropriately omitted and simplified for clarifying the description. The present invention can be implemented in various other modes. Unless otherwise specified, each component may be singular or plural.

  The position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc., for easy understanding of the invention. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings.

  In the following description, various information may be described by expressions such as “table”, “list”, “queue”, etc., but the various information may be expressed by a data structure other than these. “XX table”, “XX list”, etc. may be referred to as “XX information” to indicate that they do not depend on the data structure. In describing the identification information, expressions such as “identification information”, “identifier”, “name”, “ID”, “number”, and “Region” are used, but these can be replaced with each other.

  When there are a plurality of constituent elements having the same or similar functions, the same reference numerals may be given with different subscripts. However, when it is not necessary to distinguish between these plural components, the subscripts may be omitted in the description.

  Further, in the following description, a process performed by executing a program may be described, but the program is executed by a processor (for example, a CPU or GPU) so that a predetermined process can be performed as appropriate for a storage resource ( For example, since the processing is performed while using a storage device and / or an interface device (for example, a communication port), the main body of processing may be the processor. Similarly, the main body of processing executed by executing the program may be a controller having a processor, a device, a system, a computer, or a node. The main body of the processing executed by executing the program may be the control unit, and may include a dedicated circuit (for example, FPGA or ASIC) for performing the specific processing.

  The program may be installed from a program source into a device such as a computer. The program source may be, for example, a program distribution server or a computer-readable storage medium. When the program source is the program distribution server, the program distribution server may include a processor and a storage resource for storing the distribution target program, and the processor of the program distribution server may distribute the distribution target program to another computer. Further, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

<Outline>
In order to associate the standard signal name used in the analysis platform with the on-site sensor data that was associated with the on-site signal name of the power plant or plant, it is necessary to associate the standard signal name with the on-site signal name. As described above, when trying to analyze a target composite name such as a field signal name on the analysis platform, it is necessary to deal with a standard composite name such as a standard signal name used on the analysis platform.

  However, since the signal name, which is a composite name, has a different naming rule for each site, this association requires man-hours. For example, in a power plant, it is said that a domain expert familiar with on-site signals is required for about two man-months for about 2000 signal names.

  Therefore, the standard signal name and the field signal name, which are two compound names, are associated with each other by extracting keywords of a common type in the plant and matching the keywords. Hereinafter, the two composite names will be specifically described as a standard signal name and a field signal name for easy understanding, but the present invention is not intended to be limited to these, and a general composite name. Needless to say, it is applicable to.

  (1) These signal names are compound names composed of words having field-specific word attributes such as “device”, “sensing parameter”, and “position”. The syntax of the signal name is composed of this word attribute, and the syntax indicates that the signal name consists of the sensing target section and the sensing section. The sensing target part is a part indicating a part to be sensed, and a keyword relating to a part to be sensed such as a device is extracted from here. The sensing unit is a part that indicates what kind of sensing is performed, and extracts a keyword that indicates the type of sensing. Furthermore, different types of keywords are extracted from the divided parts by the syntax indicating the appearance order of word attributes.

  For example, where the name "temperature", which is the sensing parameter attribute, appears in the signal name determines whether it becomes the keyword "key sensing parameter". Further, in the sensing target unit, the keyword of “main device” or “sensing target device” is determined depending on the appearance order of the device attribute “FDF”. The definition of the types of keywords described here will be described later.

  (2) Based on the keyword extracted in (1), the modifier word for the keyword is also extracted from the syntax of the signal name.

<Overview of overall system configuration>
FIG. 1 is a schematic explanatory diagram of the overall configuration of the system.
The process 111 performed here is called context matching. The context is a generic name of information that means data, and a signal name is an example. The context matching 111 includes preprocessing 112, keyword extraction 113, and keyword matching 114. The preprocessing 112 is a modification of the data structure for facilitating the processing of the keyword extraction 113 and the keyword matching 114. Specifically, the signal name is converted into a syntax tree of a word attribute expression.

  The keyword extraction 113 is a process of extracting a keyword, a modifier word, and a unique characteristic from the signal name. The keyword matching 114 calculates the matching degree by matching the keyword of the standard signal name and the keyword of the field signal, the modifier word, and the characteristic, and outputs the signal name matching list 115. The user finally determines the corresponding signal by looking at the result of the signal name matching list 115 (117). Details of the above processing will be described later.

  Input information includes signal information 108 and input information 101 commonly used in a certain field such as electric power, and output information includes a signal name matching list 115. As the intermediate output information, there is keyword information 105 extracted from the signal name.

  The input information 101 includes various word attribute dictionaries 103 and a BNF (Backus-Naur form) 104 that expresses the syntax of a signal name by word attributes. The signal information 108 has a standard signal name 109 and a standard signal unit 1029 for a standard signal. For the field signal, similarly, there is a field signal name 110 and a unit 1020. Here, the unit is a unit of signal data, and is information that allows the meaning of the signal such as voltage and temperature to be determined by looking at the unit.

  As the output information 115, a standard signal name candidate list for the field signal name is output together with the matching degree indicating the matching degree between the two.

  In the intermediate output information 105, the result of extracting the keyword, the modifier word, and the characteristic for each of the standard signal name and the field signal name is output.

  In order to show the outline of the function of the context matching 111, the standard signal name 109, the field signal name 110, and the matching list (signal name matching list) 115 of the standard signal name and the field signal name, which are the main inputs, are shown in FIG. Will be described with reference to FIG.

  2A shows the standard signal name 109, and FIG. 2B shows the on-site signal name 110. The signal ID 501 is an ID for uniquely identifying the signal. The signal name 502 represents the signal name. For example, the standard signal name of the signal ID “002” in the standard signal file 500 indicates that it is “A / FDF motor bearing temperature”. In addition, the field signal name of the signal ID “002” of the field signal file 510 is “A / FDF bearing temperature”.

  FIG. 3 is a diagram showing the signal name matching list 115. A field signal name 601, a standard signal name candidate 602, a matching degree 603, and a result 604 are stored in association with each other. For example, when the site signal name 601 is “A boiler output temperature”, the standard signal name candidates 602 are “A boiler output temperature” and “A boiler input humidity”. Then, the matching degree 603 of "A boiler output temperature" is calculated as "1", and the matching degree 603 of "A boiler input humidity" is calculated as "0.83". The user makes a final matching decision 117 based on this calculated value. Details of the calculation of the matching degree will be described later.

  In the following, first, the hardware configuration of the system will be described with reference to FIGS. 4 and 5, and then each process that configures the context matching 111 shown in FIG.

<System hardware configuration>
FIG. 4 is a hardware configuration diagram of the system. The computer 202 has the same configuration as a general server or personal computer (PC). The computer 202 includes a processing unit 203, a storage device 205 that stores various information and programs, and a memory 204, and is connected to the display device 201. The processing unit 203 implements various functions by reading a program that implements the present invention into the memory 204 and executing it.

  In the storage device 205, the signal unit 102 (standard signal unit 1029, field signal unit 1020), word attribute dictionary 103, signal syntax BNF 104, standard signal name keyword 106, field signal name keyword 107, standard signal name 109, The field signal name 110 and the signal name matching list 115 are stored, and the processing unit 203 performs the context matching processing 111.

  FIG. 5 is another example of the system hardware configuration diagram shown in FIG. The computer 202 has the same configuration as that of FIG. 4, but the computer is connected to the network 303 such as the Internet. The terminal 302 connected to the network 303 has a display device 301. The user uses the terminal 302 to communicate with a computer connected to the network 303 to make the word determination 116 and the final matching determination 117 of FIG.

  Hereinafter, each process that constitutes the context matching 111 will be described.

<Pretreatment>
FIG. 6 is a flowchart of the preprocessing, showing the details of the preprocessing 112 in FIG. 1 and the outline of the subsequent keyword extraction processing.

  The preprocessing 112 inputs the unit 1029 and 1020 of each signal, the word attribute dictionary 103, and the BNF 104, which is a syntax rule of the signal name, to each of the standard signal name 109 and the field signal name 110, and inputs the standard signal name. It outputs the syntax tree 410 of and the syntax tree 411 of the field signal name.

  The first process, morphological analysis 401, is a process of dividing the signal name into word units. The word belonging to the word attribute is described in the word attribute dictionary 103, and can also be referred to as a dictionary indicating the type of word. The signal name is divided into words using this dictionary. Then, the word attribute conversion 402 converts the divided words in the signal name into word attributes. Finally, the parser 404 converts the signal name into a syntax tree represented by the syntax and word attributes. Here, the parser 404 automatically generates the BNF 104 by the parser generator 403. Morphological analysis, BNF, and parser generator are well-known expressions and techniques, and will not be described here.

Hereinafter, each processing of the morphological analysis 401, the word attribute conversion 402, and the parser 404 will be described.
The word attribute dictionary 103, which is an input to the morphological analysis 401, is a dictionary in which words are classified according to word attributes. FIG. 7 is a diagram showing a table showing word attributes, and a file in which words are classified for each word attribute 702 is a word attribute dictionary 103. For example, when the word attribute 702 is “device”, the word example 703 includes “push fan (FDF)”. There are five types of word attributes, as shown in FIG. 7, that is, Device (Position in Device), Sensing Parameter, Material (Sensing Parameter), Input from Control Computer (Control computer input). There is. Other words included in the signal name are attributes of the general word. Details are omitted because they are not related to the processing of the present invention.

In the morphological analysis 401, the word type is read from the word attribute dictionary and the signal name is divided for each word.
The word attribute conversion 402 uses this converted representation to convert the split words in the signal name to word attributes. There is one caveat here. Depending on the word, there are cases where the same word expression is used but different words are meant. In this case, the user is asked which meaning it is used to convert the word of the original signal name. For example, in the example of FIG. 8, the word voltage may mean the word voltage or the word temperature, and it is necessary to determine which the word means. This decision is made by the user using the GUI shown in FIG.

Finally, the parser 404 will be described.
The parser 404 converts each of the standard signal name 109 and the field signal name 110 into syntax trees 410 and 411 using the syntax of the signal name indicated by the BNF 104. Here, the BNF 104 and the representation of the syntax tree will be described. How to use these will be described later.

  FIG. 10 shows an example of the signal name BNF 104. Here, I will briefly explain the expression of BNF together with its grammar. For detailed grammar, refer to general compiler documentation. The expression on the left indicates that it is defined by the expression on the right. At this time, the left and right are separated by ":". When the right side consists of multiple components, the components are separated by a space. When the expression on the right is an OR of multiple expressions, each expression is separated by "|".

  Reference numeral 1601 indicates that the signal name (signal_name) is composed of a sensing target part (sensing_target_part) and a sensing part (sensing_part). Although the sensing target part can be defined by this BNF expression, if another expression is used, it is defined from the beginning of the signal name to the part ending with the word of the attribute of the device or position. The sensing unit indicates the rest of the signal name other than the sensing target unit.

  These components can be further defined by other components. Reference numeral 1602 indicates that the sensing target part is represented by sensing sensing_target_series). sensing_taret_series indicates that a plurality of sensing targets (sensing_target) are connected. 1603 indicates that the sensing target (sensing_target) is made up of a sensing target attribute (sensing_taget_attribute) or a series of auxiliary words (complimentary_series) and a sensing target attribute. At 1604, it indicates that the sensing target attribute is a device word attribute (DECVICE) or a position word attribute (POSISION). At 1605, the auxiliary word is a modifier (modifying_word) or an identifier (ID_part). In 1606, the modifier is either the substance word attribute (MATERIAL), the sensing parameter word attribute (SENSING_PARAMETER), the generic word attribute (GENERAL_WORD), or the suffix word attribute (POSTFIX). Show. At 1607, it is indicated that the sensing unit includes a sensing attribute series (sensing_attribute_series) or a general token series (general_token_series) and a sensing attribute series. The general token series indicates a series of general word attributes other than the sensing-specific word attributes shown in FIG. 7. As indicated by 1608, the sensing attribute is composed of a sensing parameter word attribute (SENSING_PARAMETER), a substance word attribute (MATERIAL), or a control computer input word attribute (Input from Control Computer).

  The parser 404 checks that the signal name has a syntax conforming to the BNF 104, and if it does not conform to this BNF, an error occurs, and if so, it converts it into a syntax tree expression. Fig. 11 shows the syntax tree of the signal name of "motor for A / FDF bearing temperature". The highest-level node 1701 is a signal name (signal_name), and as defined by the BNF 104, the signal name (signal_name) is composed of a sensing target part (sensing_target_part) and a sensing part (sensing_part), which is shown in the lower layer 1702. . In the same way, when expressed in the lower hierarchy as BNF104, up to "A / B FDF bearing" is the sensing target part (sensing_target_part), "A ・" is the identifier (ID_part), and "FDF" Can be analyzed as a device (DEVICE) and the "bearing" as a device (DEVICE). Similarly, it can be analyzed that the sensing part (sensing_part) is a “temperature” part, and the “temperature” is a sensing parameter (SENSING_PARAMETR). In this way, it is possible to know whether the keyword included in the signal name is the sensing target unit or the sensing unit.

<Keyword extraction 113 and keyword matching 114>
The keyword extraction 113 is a process of extracting a keyword such as a keyword to be matched, a modifier word, and a characteristic for all field signal names and standard signal names. The keyword matching 114 is a matching that represents the degree of coincidence between the field signal name and the standard signal name by using the standard signal name that matches the extracted word or characteristic for each field signal name as a candidate for the corresponding standard signal name. Output with degrees.

  FIG. 12 shows a processing flow of keyword extraction 113 and keyword matching 114. These processes are performed in a double loop of the field signal name and the standard signal name.

  Step 1302 is a loop of the field signal name. Step 1303 extracts a keyword, a modifier word, and a characteristic from the syntax tree 411 of one field signal name. Similarly, in step 1304, the keyword, the modifier word, and the characteristic are extracted from the syntax tree 410 of the standard signal name. Step 1306 shows the process of keyword matching 114 for each standard signal name for each field signal name. This is a matching degree calculation process, in which the matching degree representing the matching degree of all standard signal names with respect to each field signal name is calculated, and the matching degree with respect to the keyword is used as a candidate for the standard signal name with a threshold value of 1311 or more. , As the signal name matching list 115. The weight shown in step 1310 is the weighting of the keyword for calculating the matching degree. Details of the calculation of the matching degree will be described later.

The details of each process in FIG. 12 will be described below.
First, the processing of extracting keywords and modifier words and characteristics shown in steps 1303 and 1305 will be described. FIG. 13 is a diagram showing an example of keywords extracted according to this rule from the syntax tree of FIG. 11 showing the keyword extraction rule and the signal name “A / FDF bearing temperature”.

  For the keyword 902 “Key Sensing Parameter”, the extraction rule “The Rightmost“ Sensing Parameter ”Word in Sensing Part”, that is, the rule for extracting the rightmost “sensing parameter” in the sensing unit as a sensing parameter is set, and Is extracted as the keyword 106 of the standard signal name.

  Similarly, for the keyword 902 “Main Device”, there is an extraction rule 903 “The Leftmost Device“ Word in Sensing Target Part ”, that is, a rule for extracting a device with“ the leftmost side of the word of the sensing target part as the main device ”. It is set. This is because the macro device appears on the leftmost side of the sensing target part in the signal name. In this example, "FDF" is extracted as the device.

  Similarly, for keyword 902 “Sensing Target Device”, extraction rule 903 “The Rightmost“ Device ”Word in Sensing Target Part”, that is, a rule for extracting a device with “the rightmost device in the word of the sensing target part” Is set. This is because the device appears on the rightmost side of the sensing target part in the signal name. In this example, “bearing” is extracted as the device name keyword for the device.

  FIG. 14 is a diagram showing an example of an extraction rule regarding a keyword modifier and a characteristic, and an extracted modifier word and a characteristic. For example, the rule for extracting the modifier 1002 “Sensing Target Material” to the number 1001 “1” is “The Left“ Material ”Word of Key Sensing Parameter (the substance to the left of the key sensing parameter). Is set. Then, "metal" and "oil" are extracted as signal name keywords 106 and 107. With respect to the numbers “2” to “5”, the modifiers and the like are set according to the positions where the modifiers appear in the signal name, and the modifier keywords are extracted.

Next, the matching degree calculation processing indicated by 1306 will be described with reference to FIGS. 15 and 16.
In FIG. 15, a matching degree 1402 indicates the matching degree given to the entire keyword. It is defined by the formula shown in Definition. Weight 1, weight 2, and weight 3 are given to each of the key sensing parameter, the macro device, and the sensing target device, and the match becomes 1 or 0 depending on whether or not each keyword matches the modifier word. The Definition expression given by the weight and the match indicates the definition of the matching degree. The weight is set so as to satisfy the conditions of Condition 1 to Condition 3 according to its importance. For example, “0.6”, “0.3”, and “0.1” are set for each of the key sensing parameter, macro device, and sensing target device. Condition 1 is a condition that the total of all weights is “1”, and Condition 2 is a condition that is larger than the total of the weights of other keywords. In Condition3, the weight of the keyword is a condition for maximizing the key sensing parameter, and in addition, the condition that the matching of the key sensing parameter is indispensable for the matching of the signal name can be set.

The conditions for matching or not are shown in FIG. 16 for each keyword. Reference numeral 1502 indicates a condition for a key sensing parameter, 1503 a condition for a main device, and 1504 a condition for a sensing target device. The AND condition of Condition1, Condition2, and Condition3 is the condition.
Even if the keywords of the standard signal name and the field signal name match, if the modifiers do not match, they may not be associated as the same signal name. If both the standard signal name and the field signal name have the same modifier, the Match shown in Definition in FIG. 15 is 1. Even when only one of the standard signal name and the field signal name has a qualifying word, 1 is set as the corresponding signal name in Match. FIG. 16 shows such a condition.

  The matching degree 1403 in FIG. 15 is given to the device hierarchy, and is set to "3/4", which is obtained by dividing the number of devices to be matched by the number of devices of the field signal name.

  As described above, in the present embodiment, like sensor signals in power plants and plants, verbs are not used, the system is different from general sentences, and natural language processing is based on information that cannot be simply applied. It can be associated with the standard signal name used in the data analysis platform for use. As a result, the sensor data of the power plant or plant can be efficiently analyzed.

101: input information, 103: word attribute dictionary, 109: standard signal name, 110: field signal name, 112: preprocessing, 113: keyword extraction, 114: keyword matching, 115: keyword matching list, 202: calculator, 203: Processing unit, 204: memory, 205: storage device, 302: terminal, 303: network.

Claims (9)

A storage device that stores two compound names consisting of a target compound name and a standard compound name, a word attribute dictionary in which the attributes of words that appear in the compound name are registered, and a syntax of the compound name composed of word attributes,
Extract the keywords that characterize the composite name from the word attribute dictionary and the syntax of the composite name.Match the keywords extracted from the two composite names consisting of the target composite name and the standard composite name to extract the two composite names. A name matching device, comprising: a processing unit that calculates a matching degree.   The name matching device according to claim 1, wherein the processing unit calculates the matching degree of the keyword by weighting the extracted keyword.   The processing unit determines whether the weight of the keyword is the maximum of the key sensing parameter, is larger than the total of the weights of the other keywords, or whether the matching of the key sensing parameter is indispensable in the matching of the signal name. The name matching device according to claim 1, wherein: The composite name is a signal name,
The word attribute dictionary includes devices, sensing parameters, positions on the device, substances to be sensed, and inputs from the control computer,
The name matching device according to claim 1, wherein the processing unit determines a word attribute of a word appearing in a signal name by referring to the word attribute dictionary. The composite name is a signal name,
The name matching device according to claim 1, wherein the syntax of the signal name includes a division rule for dividing the signal name into a sensing target portion and a sensing portion, as a part of the syntax.   The sensing target part is defined from the beginning of the signal name to a part ending with a word of a device or position attribute, and the sensing part is defined in all parts except the sensing target part. The name matching device according to claim 5, which is characterized in that. The keyword extracted by the processing unit consists of a key sensing parameter, a main device, and a sensing target device,
The key sensing parameter is a rightmost sensing parameter attribute word in the sensing target section, and the main device is a leftmost device attribute word in the sensing target section. 7. The name matching device according to claim 6, wherein the sensing target device is a word having a device attribute located at the rightmost position in the sensing target unit.   The name matching device according to claim 4, wherein the storage device stores a signal unit which is a unit of a signal value, and specifies word types having a plurality of meanings. The storage device stores two compound names consisting of a target compound name and a standard compound name, a word attribute dictionary in which attributes of words appearing in the compound name are registered, and a compound name syntax composed of word attributes,
Depending on the processing unit,
Extract the keywords that characterize the compound name from the word attribute dictionary and the syntax of the compound name,
A name matching method, characterized in that keywords extracted from two compound names consisting of a target compound name and a standard compound name are matched with each other to calculate a matching degree of the two compound names.

Images