Information model generation method and device, controller, medium and product
By acquiring the device measurement point description information and using word segmentation and mapping technologies to generate an information model, the problem of discrepancies caused by manual conversion is solved, and efficient and accurate information model generation is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JINFENG HUINENG TECH CO LTD
- Filing Date
- 2023-04-21
- Publication Date
- 2026-07-14
AI Technical Summary
In existing technologies, manually converting the descriptive information corresponding to the equipment measurement points into an information model results in significant discrepancies, affecting the effectiveness of use and reducing efficiency.
By acquiring the descriptive information of the device measurement points, performing word segmentation, using a professional lexicon and mmseg algorithm for error correction, and mapping the information to obtain information identifiers, an information model is generated.
The automated conversion of equipment measurement point information models avoids human interpretation bias, improves generation efficiency, and ensures model consistency and accuracy.
Smart Images
Figure CN118821764B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of wind power generation technology, specifically to a method, apparatus, controller, medium, and product for generating an information model. Background Technology
[0002] During the configuration of the communication protocol, the device measurement points collected by the protocol need to be converted into an information model to facilitate the recognition of the protocol program.
[0003] In related technologies, the descriptive information corresponding to the equipment measurement points is usually converted into an information model manually. However, since different people may have different understandings of the descriptive information corresponding to the equipment measurement points, the manual conversion of the descriptive information corresponding to the equipment measurement points into an information model may have significant differences. These differences will affect the effectiveness of the information model. Moreover, the manual conversion of the descriptive information corresponding to the equipment measurement points into an information model is inefficient. Summary of the Invention
[0004] The purpose of this application is to provide a method, apparatus, controller, medium, and product for generating an information model, in order to solve the problems in the prior art where the conversion of description information corresponding to equipment measurement points into an information model by manual means results in significant differences, which affects the effectiveness of the information model and has low conversion efficiency.
[0005] The technical solution of this application is as follows:
[0006] Firstly, a method for generating an information model is provided, the method comprising:
[0007] Obtain the description information corresponding to the device's measurement points;
[0008] The description information is segmented into words to obtain the segmentation results corresponding to N preset professional term types, where N is an integer greater than 1;
[0009] The word segmentation results are mapped according to the preset professional term types to obtain the information identifiers corresponding to the word segmentation results;
[0010] Based on N information identifiers, an information model corresponding to the device measurement points is generated.
[0011] In some embodiments, before performing word segmentation on the description information to obtain the word segmentation results corresponding to N preset professional term types, the method further includes:
[0012] The words included in the description information are matched with the error words in the error word library, which includes multiple error words and the correct word corresponding to each error word.
[0013] If the target word in the description information successfully matches the target error word in the error word library, the target word in the description information will be replaced with the correct word corresponding to the target error word.
[0014] In some embodiments, before performing word segmentation on the description information to obtain the word segmentation results corresponding to N preset professional term types, the method further includes:
[0015] Remove target characters from the description information.
[0016] In some embodiments, the descriptive information is segmented to obtain segmentation results corresponding to N preset professional term types, including:
[0017] Based on a professional lexicon, the description information is segmented using the MMSEG algorithm to obtain segmentation results for N preset professional word types.
[0018] In some embodiments, the word segmentation results are mapped according to a preset term type to obtain the information identifier corresponding to the word segmentation result, including:
[0019] The word segmentation results corresponding to each preset professional term type are mapped according to the preset mapping order to obtain the information identifiers corresponding to the word segmentation results.
[0020] Specifically, the word segmentation results corresponding to each preset professional term type are mapped to obtain the information identifiers corresponding to the word segmentation results, including:
[0021] Determine the mapping parameters required to map the word segmentation results corresponding to the preset professional term types. The mapping parameters include the information identifiers obtained from the first M mappings, where M is a non-negative integer.
[0022] Determine the target mapping type corresponding to the mapping parameters from the preset mapping types;
[0023] Based on the mapping parameters and target mapping type, the information identifier corresponding to the word segmentation result is determined according to the preset mapping relationship.
[0024] In some embodiments, the N preset term types include device location terms, attribute terms, reading terms, type terms, and adjectives, and the preset mapping order from first to last is device location term mapping, attribute term mapping, reading term mapping, type term mapping, and adjective mapping.
[0025] In some embodiments, determining the target mapping type corresponding to the mapping parameters from a preset mapping type includes:
[0026] Determine multiple first mapping types that the mapping parameters satisfy from the preset mapping types;
[0027] The target mapping type is determined by identifying the type with the highest priority among multiple first mapping types.
[0028] Secondly, an information model generation apparatus is provided, the apparatus comprising:
[0029] The acquisition module is used to acquire descriptive information corresponding to the device's measurement points;
[0030] The word segmentation module is used to segment the description information to obtain the word segmentation results corresponding to N preset professional word types, where N is an integer greater than 1;
[0031] The mapping module is used to map the corresponding word segmentation results according to the preset professional term types to obtain the information identifiers corresponding to the word segmentation results;
[0032] The generation module is used to generate an information model corresponding to the device measurement points based on N information identifiers.
[0033] Thirdly, embodiments of this application provide an information model generation controller, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of the information model generation method described in any of the embodiments of this application.
[0034] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions, which, when executed by a processor, implement the steps of the information model generation method described in any of the embodiments of this application.
[0035] Fifthly, embodiments of this application provide a computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, enable the electronic device to perform the steps of any of the information model generation methods described in embodiments of this application.
[0036] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:
[0037] The information model generation method, apparatus, controller, medium, and product provided in this application embodiment obtain descriptive information corresponding to equipment measurement points, perform word segmentation on the descriptive information to obtain word segmentation results corresponding to N preset professional term types, and then perform mapping processing on the corresponding word segmentation results according to the preset professional term types to obtain information identifiers corresponding to the word segmentation results. Then, based on the N information identifiers, an information model corresponding to the equipment measurement points can be generated. In this way, the descriptive information corresponding to the equipment measurement points can be automatically converted into an information model without manual conversion. Therefore, it can avoid significant differences in the information model due to different people's misunderstandings of the descriptive information corresponding to the equipment measurement points, thereby avoiding affecting the usability of the information model and improving the generation efficiency of the information model.
[0038] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description
[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.
[0040] Figure 1 This is one of the flowcharts illustrating a method for generating an information model provided in the first aspect of this application;
[0041] Figure 2 This is a schematic diagram of a word segmentation process provided in the first aspect of this application;
[0042] Figure 3 This is a schematic diagram of a mapping process provided in the first aspect of this application;
[0043] Figure 4 This is a second schematic flowchart of an information model generation method provided in the first aspect of this application;
[0044] Figure 5 This is a schematic diagram of the structure of an information model generation device provided in the second aspect embodiment of this application;
[0045] Figure 6 This is a schematic diagram of the structure of an electronic device provided in the third aspect of this application. Detailed Implementation
[0046] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.
[0047] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples consistent with some aspects of this application as detailed in the appended claims.
[0048] The method for generating the information model provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.
[0049] Figure 1 This is a flowchart illustrating a method for generating an information model provided in an embodiment of this application. For example... Figure 1 As shown, the information model generation method provided in this application embodiment may include S110-S140, as follows:
[0050] S110, Obtain the description information corresponding to the device measurement points;
[0051] S120, perform word segmentation on the description information to obtain word segmentation results corresponding to N preset professional term types;
[0052] S130, Map the corresponding word segmentation results according to the preset professional term types to obtain the information identifiers corresponding to the word segmentation results;
[0053] S140 generates an information model corresponding to the device measurement points based on N information identifiers.
[0054] Therefore, by acquiring the descriptive information corresponding to the equipment measurement points and performing word segmentation on this information, N pre-defined professional term types are obtained as segmentation results. Then, the segmentation results are mapped according to these pre-defined professional term types to obtain information identifiers corresponding to the segmentation results. Based on these N information identifiers, an information model corresponding to the equipment measurement points can be generated. This automatically converts the descriptive information corresponding to the equipment measurement points into an information model without manual conversion. Therefore, it avoids significant differences in the information model due to differing understandings of the descriptive information by different people, thus preventing any impact on the usability of the information model and improving the efficiency of information model generation.
[0055] Regarding S110, the equipment measurement points can be operational data of the equipment, such as current, voltage, frequency, and other data, which can be used for equipment monitoring and management. The descriptive information corresponding to the equipment measurement points can be provided by the equipment manufacturer. For example, such as... Figure 2 As shown, description information 210 can be “[35kV#2 fan line 313] First measurement of external zero-sequence current”.
[0056] The information model provided in this application can be applied to the new energy field; therefore, the equipment measurement points can be new energy equipment measurement points.
[0057] In S120, N can be an integer greater than 1. The word segmentation result can include word segments and / or null values. If there is no word segment corresponding to a certain preset professional term type in the word segmentation results obtained by segmenting the description information, the word segmentation result corresponding to that preset professional term type can be empty.
[0058] It should be noted that there may be cases where multiple preset professional term types result in the same word segmentation.
[0059] In some implementations, the N preset term types may include device location terms, attribute terms, reading terms, type terms, and adjectives.
[0060] Among them, equipment location terms can be used to indicate the detailed parts of the equipment to which the equipment measuring point belongs, such as: wind turbine impeller, wind turbine converter, etc.; or to indicate the equipment to which the equipment measuring point belongs, such as: environmental monitoring instrument, combiner box, etc.; or to indicate the virtual location of the equipment to which the equipment measuring point belongs, such as: substation feeder, substation station service transformer, etc.
[0061] Attribute terms can be used to indicate the attribute terms collected by the device's measurement points, such as: current, voltage, alarm, fault, etc.
[0062] Reading terms can be used to indicate the reading attributes of device measurement points, such as: remote signal quantity, remote control, remote adjustment, etc.
[0063] Type terms can be used to indicate the numerical type of the attributes acquired by the device's measurement points, such as integer, floating-point value, or Boolean value.
[0064] Adjectives can be used to indicate specific terms related to the attributes acquired by the measurement points of a device, such as zero-sequence voltage and external zero-sequence current.
[0065] Since the description information of the equipment measurement points is usually manually labeled by the equipment manufacturer, some typos or incorrect descriptions are inevitable, and these errors will affect word segmentation and recognition. In some embodiments, to improve the accuracy of the word segmentation results, the method may further include the following before S120:
[0066] Match the words included in the description information with the incorrect words in the error dictionary;
[0067] If the target word in the description information successfully matches the target error word in the error word library, the target word in the description information will be replaced with the correct word corresponding to the target error word.
[0068] In some implementations, regular expressions can be used to match the words included in the description information with error words in an error dictionary.
[0069] Here, the error dictionary can include multiple erroneous words and the corresponding correct word for each erroneous word. For example, the erroneous words in the error dictionary can be words with misspellings, synonyms of correct words, ambiguous words, etc.
[0070] Furthermore, this error terminology can be pre-built and continuously maintained and updated during use. The maintenance data for the error terminology can include error word filtering conditions (regular expressions), error words, correct words, and priorities. For example, multiple words in the description information may successfully match error words in the error terminology. These multiple words may overlap; correcting only one word may eliminate the need to correct the others. In this case, it's necessary to determine which word to correct. Therefore, priority is used to identify the highest priority among the successfully matched error words as the target error word, and the target words that successfully match the target error word are then corrected.
[0071] To improve the accuracy of the error dictionary, it can be maintained and updated based on a professional dictionary.
[0072] Specifically, the words included in the description information are matched against erroneous words in the error terminology database. If the target word in the description information matches a target erroneous word in the error terminology database, it indicates that the target word is an erroneous word and needs to be corrected. Therefore, the target word can be replaced with the correct word corresponding to the target erroneous word. If the words included in the description information do not match any erroneous words in the error terminology database, it indicates that there are no erroneous words in the description information.
[0073] For example, such as Figure 2 As shown, the words in the description information 210 "[35kV#2 wind turbine line 313] First measurement of external zero-sequence current" are matched with the erroneous words in the error word library. It is found that the word "measurement" matches the target erroneous word in the error word library. That is, "measurement" is the target word. Therefore, it can be determined that the target word "measurement" is an erroneous word and needs to be corrected. Since the correct word corresponding to the target erroneous word in the error word library is "measurement", the target word "measurement" can be replaced with "measurement" to obtain the corrected description information 220 "[35kV#2 wind turbine line 313] First measurement of external zero-sequence current".
[0074] Thus, by correcting the description information through a pre-built error dictionary, the accuracy of the description information can be improved, thereby avoiding the problem of inaccurate word segmentation results due to inaccurate description information.
[0075] In some implementations, to further improve the accuracy of word segmentation results, the method may further include the following steps before S120:
[0076] Remove target characters from the description information.
[0077] Here, the target characters can include numbers and / or special characters, etc. For example, special characters can include spaces, underscores, etc.
[0078] Since numbers and special characters can interfere with the word segmentation process, they can be removed from the description information before word segmentation.
[0079] It should be noted that some numbers may have specific meanings when combined with other words. These numbers can be corrected in advance to become technical terms, so they will not be mishandled.
[0080] For example, such as Figure 2 As shown, removing the number "35 2 313" from description information 220 "[35kV#2 fan line 313] First measurement of external zero-sequence current" yields description information 230 "[kV# fan line] First measurement of external zero-sequence current". Removing the special character "[#]" from description information 230 "[kV# fan line] First measurement of external zero-sequence current" yields description information 240 "kV fan line first measurement of external zero-sequence current".
[0081] Thus, by removing numbers and / or special characters from the description information, interference from numbers and / or special characters in the word segmentation process can be avoided, thereby further improving the accuracy of the word segmentation results.
[0082] Since the description information of equipment measurement points is mainly composed of technical terms, the accuracy of word segmentation of the description information of equipment measurement points using conventional natural language libraries is relatively low. In some implementations, in order to obtain more accurate word segmentation results, S120 may include:
[0083] Based on a professional lexicon, the description information is segmented using the MMSEG algorithm to obtain segmentation results for N preset professional word types.
[0084] Here, the specialized thesaurus can include multiple specialized terms and their corresponding preset specialized term types. Therefore, by performing word segmentation based on this specialized thesaurus, we can obtain word segmentation results corresponding to N preset specialized term types. This specialized thesaurus can be pre-built and continuously maintained and updated during use. The maintenance data of the specialized thesaurus can include specialized terms, their corresponding preset specialized term types, and notes, where the notes can be explanations of the specialized terms. This specialized thesaurus needs long-term accumulation; the larger the number of words it contains, the more accurate the word segmentation results will be. The information model is affected by the standardization specifications of communication protocols. As business develops, the standardization specifications of communication protocols may change or be upgraded. Here, updating the specialized thesaurus can ensure that the generated information model conforms to the changed or upgraded standardization specifications of communication protocols.
[0085] Because different fields use different specialized terms, different specialized thesaurus can be built for each field. For example, in the field of new energy, the specialized thesaurus can include specialized terms from the new energy industry, which helps in the identification of objects such as equipment and measuring points in the new energy industry, and can accelerate data integration based on this.
[0086] Furthermore, the mmseg algorithm is a simple and efficient word segmentation algorithm. Its main idea is to identify multiple different combinations of three words from left to right within a complete sentence each time. Then, based on disambiguation rules, it determines the best candidate word combination, selecting the first word from this combination as the segmentation result for one iteration. The remaining words continue to the next round of segmentation. The mmseg algorithm can effectively remove ambiguous word segmentation and can modify the combination of numbers, units, etc., adding the recognition of email addresses, phone numbers, URLs, names, place names, currencies, and an unlimited number of custom entities. The segmentation method can be initialized by passing in an optimized stop word list, a unit word list, and a specialized thesaurus. More detailed processes can be found in relevant materials and will not be elaborated here.
[0087] For example, such as Figure 2As shown, based on a professional lexicon, the description information 240 "kV wind turbine line primary measurement external zero-sequence current" is segmented using the mmseg algorithm. The resulting segmentation results are: equipment location word 251 "wind turbine line", adjective word 252 "external zero-sequence", attribute word 253 "current", reading word 253 "current", and type word 253 "current".
[0088] Therefore, by using a professional dictionary and the mmseg algorithm to segment descriptive information, the accuracy of word segmentation can be improved, resulting in more accurate segmentation results. In addition, the mmseg algorithm is more efficient for word segmentation.
[0089] Regarding S130, the information identifier can be used to indicate the meaning expressed by its corresponding word segmentation result. The word segmentation result corresponding to each specialized term type can be mapped separately to obtain the information identifier corresponding to that word segmentation result.
[0090] In some implementations, to obtain more accurate information identification, S130 may include:
[0091] The word segmentation results corresponding to each preset professional term type are mapped according to the preset mapping order to obtain the information identifiers corresponding to the word segmentation results.
[0092] Specifically, the word segmentation results corresponding to each preset professional term type are mapped to obtain the information identifiers corresponding to the word segmentation results, including:
[0093] Determine the mapping parameters required to map the word segmentation results corresponding to the preset professional term types;
[0094] Determine the target mapping type corresponding to the mapping parameters from the preset mapping types;
[0095] Based on the mapping parameters and target mapping type, the information identifier corresponding to the word segmentation result is determined according to the preset mapping relationship.
[0096] In some implementations, the preset mapping order, from first to last, can be device location word mapping, attribute word mapping, read word mapping, type word mapping, and adjective mapping.
[0097] Specifically, the word segmentation results corresponding to device location words, attribute words, reading words, type words, and adjectives can be mapped in sequence. That is, device location word mapping, attribute word mapping, reading word mapping, type word mapping, and adjective mapping can be performed in sequence.
[0098] Here, the mapping parameter can include the information identifiers obtained from the previous M mappings, where M can be a non-negative integer.
[0099] In each mapping process, the mapping parameters required for this mapping can be determined first. The mapping parameters for each mapping can include the information identifiers obtained from the previous M mappings, the word segmentation results targeted by this mapping, and the device type and measurement point type corresponding to the device measurement point. M can be a non-negative integer.
[0100] Then, the target mapping type corresponding to the mapping parameter can be determined from the preset mapping types. These preset mapping types can include: Device Type-Measurement Point Type-Word Segmentation Mapping; Device Type-Word Segmentation Mapping; Measurement Point Type-Word Segmentation Mapping; Word Segmentation Mapping; Measurement Point Type Mapping; Device Type Mapping; Device Location Word-Word Segmentation Mapping; Attribute Word-Word Segmentation Mapping; Reading Word-Word Segmentation Mapping; Type Word-Word Segmentation Mapping; Adjective-Word Segmentation Mapping; Device Location Word-Measurement Point Type Mapping; Attribute Word-Measurement Point Type Mapping; Reading Word-Measurement Point Type Mapping; Type Word-Measurement Point Type Mapping; Adjective-Measurement Point Type Mapping. A target mapping type corresponding to the mapping parameter can be determined from these 16 preset mapping types.
[0101] Of course, depending on actual needs, the preset mapping type can also include other types, which are not limited here.
[0102] Furthermore, various combinations of mapping parameters and mapping types can be pre-set to correspond with information identifiers. After determining the mapping parameters and target mapping type for this mapping, the information identifier corresponding to the combination of mapping parameters and target mapping type for this mapping can be determined based on this correspondence, that is, the information identifier of the word segmentation result corresponding to the preset professional term type targeted by this mapping.
[0103] For example, such as Figure 3 As shown, the first mapping is the device location word mapping 310, which maps the segmentation result "fan line" 311 corresponding to the device location word. The second mapping is the attribute word mapping 320, which maps the segmentation result "current" 321 corresponding to the attribute word. The third mapping is the read word mapping 330, which maps the segmentation result "current" 331 corresponding to the read word. The fourth mapping is the type word mapping 340, which maps the segmentation result "current" 341 corresponding to the type word. The fifth mapping is the adjective mapping 350, which maps the segmentation result "external zero order" 351 corresponding to the adjective.
[0104] When mapping the word segmentation result "wind turbine line" 311 corresponding to the equipment location term, the mapping parameters can include: "word segmentation - wind turbine line", "equipment type - wind turbine" and "measuring point type - telemetry". The target mapping type corresponding to this mapping parameter can be "equipment type - measuring point type - word segmentation mapping". Then, the information identifier corresponding to the combination of this mapping parameter and the target mapping type "equipment type (wind turbine) - measuring point type (telemetry) - word segmentation (wind turbine line)" can be determined as "TSOL" 312, that is, the information identifier corresponding to the word segmentation result "wind turbine line" 311 corresponding to the equipment location term is "TSOL" 312.
[0105] When mapping the word segmentation result "current" 321 corresponding to the attribute word, the mapping parameters can include: "word segmentation-current", "equipment type-fan", "measuring point type-telemetry" and "equipment location word-TSOL". The target mapping type corresponding to this mapping parameter can be "equipment location word-word segmentation mapping". Then, the information identifier corresponding to the combination of this mapping parameter and the target mapping type "equipment location word (TSOL)-word segmentation (current)" can be determined to be "AC" 322, that is, the information identifier corresponding to the word segmentation result "current" 321 corresponding to the attribute word is "AC" 322.
[0106] When mapping the segmentation result "current" 331 corresponding to the read word, the mapping parameters can include: "segmentation-current", "equipment type-fan", "measuring point type-telemetry", "equipment location word-TSOL" and "attribute word-AC". The target mapping type corresponding to this mapping parameter can be "attribute word-segmentation mapping". Then, the information identifier corresponding to the combination of this mapping parameter and the target mapping type "attribute word (AC)-segmentation (current)" can be determined to be "Ra" 332, that is, the information identifier corresponding to the segmentation result "current" 331 corresponding to the read word is "Ra" 332.
[0107] When mapping the segmentation result "current" 341 corresponding to the type word, the mapping parameters can include: "segmentation-current", "equipment type-fan", "measuring point type-telemetry", "equipment location word-TSOL", "attribute word-AC" and "reading word-Ra". The target mapping type corresponding to this mapping parameter can be "reading word-segmentation mapping". Then, the information identifier corresponding to the combination of this mapping parameter and the target mapping type "reading word (Ra)-segmentation (current)" can be determined to be "F32" 342, that is, the information identifier corresponding to the segmentation result "current" 341 corresponding to the type word is "F32" 342.
[0108] When mapping the segmentation result "external zero order" 351 corresponding to the adjective, the mapping parameters can include: "segmentation-external zero order", "equipment type-fan", "measuring point type-telemetry", "equipment location word-TSOL", "attribute word-AC", "reading word-Ra" and "type word-F32". The target mapping type corresponding to this mapping parameter can be "type word-segmentation mapping". Then, the information identifier corresponding to the combination of this mapping parameter and the target mapping type "type word (F32)-segmentation (external zero order)" can be determined as "Extl3l0" 352, that is, the information identifier corresponding to the segmentation result "external zero order" 351 corresponding to the adjective is "Extl3l0" 352.
[0109] In this way, through the above process, the information identifiers corresponding to the word segmentation results for each preset professional term type can be determined more accurately.
[0110] In some implementations, to more accurately determine the target mapping type corresponding to the mapping parameters, the above-mentioned determination of the target mapping type corresponding to the mapping parameters from preset mapping types may include:
[0111] Determine multiple first mapping types that the mapping parameters satisfy from the preset mapping types;
[0112] The target mapping type is determined by identifying the type with the highest priority among multiple first mapping types.
[0113] Here, priorities can be pre-set for each preset mapping type. During use, multiple preset mapping types and their corresponding priorities can be maintained and updated.
[0114] In some implementations, the priority from high to low may include: top-level, second-highest-level, high-precision, second-precision, medium-normal, second-normal, low-default configuration, second-default configuration, and bottom-level.
[0115] For example, the priority of "Device Type-Measurement Point Type-Word Segmentation Mapping" can be precise; the priority of "Device Type-Word Segmentation Mapping" can be normal; the priority of "Measurement Point Type-Word Segmentation Mapping" can be normal; the priority of "Word Segmentation Mapping" can be default configuration; the priority of "Measurement Point Type Mapping" can be default configuration; the priority of "Device Type Mapping" can be default configuration; the priority of "Device Location Word-Word Segmentation Mapping" can be normal; the priority of "Attribute Word-Word Segmentation Mapping" can be normal; the priority of "Read Word-Word Segmentation Mapping" can be normal; the priority of "Type Word-Word Segmentation Mapping" can be normal; the priority of "Adjective-Word Segmentation Mapping" can be normal; the priority of "Device Location Word-Measurement Point Type Mapping" can be normal; the priority of "Attribute Word-Measurement Point Type Mapping" can be normal; the priority of "Read Word-Measurement Point Type Mapping" can be normal; the priority of "Type Word-Measurement Point Type Mapping" can be normal; the priority of "Adjective-Measurement Point Type Mapping" can be normal.
[0116] Specifically, when mapping the word segmentation results corresponding to each preset professional term type, the mapping parameters may satisfy multiple preset mapping types mentioned above, that is, satisfy multiple first mapping types. In this case, the highest priority among these multiple first mapping types can be taken as the target mapping type corresponding to the mapping parameters.
[0117] For example, when mapping the word segmentation result "wind turbine line" corresponding to the device location term, the mapping parameters can include: "word segmentation - wind turbine line", "equipment type - wind turbine", and "measuring point type - telemetry". These mapping parameters can correspond to multiple first mapping types such as "equipment type - measuring point type - word segmentation mapping", "equipment type - word segmentation mapping", "measuring point type - word segmentation mapping", "word segmentation mapping", "measuring point type mapping", and "equipment type mapping". Among them, the priority of the first mapping type "equipment type - measuring point type - word segmentation mapping" is precise, the priority of "equipment type - word segmentation mapping" can be normal, the priority of "measuring point type - word segmentation mapping" can be normal, the priority of "word segmentation mapping" can be default configuration, the priority of "measuring point type mapping" can be default configuration, and the priority of "equipment type mapping" can be default configuration. The first mapping type with the highest priority is "equipment type - measuring point type - word segmentation mapping". Therefore, "equipment type - measuring point type - word segmentation mapping" can be determined as the target mapping type.
[0118] In this way, by setting priorities in advance, the target mapping type corresponding to the mapping parameters can be determined more accurately.
[0119] In section S140, the word segmentation results corresponding to N preset professional term types are mapped to obtain N information identifiers. The combination of these N information identifiers can then be used as the information model corresponding to the device's measurement point. The information model can be a description defining device attributes, or it can be used to map physical world devices to the virtual world of a software system. Information exchange mechanisms rely on standardized information models.
[0120] During use, the preset terminology types, information model standards, Chinese descriptions, English descriptions, and mapping logic can be maintained and updated. The information model standard can refer to standardized communication protocol specifications; the Chinese and English descriptions can refer to the Chinese and English descriptions of the information identifiers; and the mapping logic refers to the logic that maps the word segmentation results corresponding to multiple preset terminology types to the information identifiers.
[0121] For example, such as Figure 3 As shown, the N information identifiers are: "TSOL" 312, "AC" 322, "Ra" 332, "F32" 342 and "Extl3l0" 352. Based on these N information identifiers, the information model "TSOL.AC.Ra.F32.Extl3l0" 360 can be generated.
[0122] The information model generation method provided in this application embodiment can automatically convert equipment measurement points into a unified and standardized information model based on a professional thesaurus and standardized communication protocol specifications. It utilizes word segmentation and error correction technologies to achieve low cost, high efficiency, maintainability, and standardization. This enables more efficient and accurate assistance in completing communication protocol configuration work, reduces the difficulty of communication protocol configuration, improves standardization quality at the data source, and facilitates subsequent program identification of equipment measurement points.
[0123] To better describe the entire solution, based on the above embodiments, a complete example is given, such as... Figure 4 As shown, the method for generating this information model may include S410-S470, which will be explained in detail below.
[0124] S410, Obtain the description information corresponding to the device measurement points;
[0125] S420, perform error correction processing on the description information;
[0126] S430, Remove numbers from the description information;
[0127] S440, Remove special characters from the description information;
[0128] S450, perform word segmentation on the description information;
[0129] S460, Mapping the word segmentation results;
[0130] S470 generates an information model corresponding to the device's measurement points.
[0131] For details, please refer to the above embodiments. For the sake of brevity, they will not be repeated here.
[0132] Therefore, by acquiring the descriptive information corresponding to the equipment measurement points and performing word segmentation on this information, N pre-defined professional term types are obtained as segmentation results. Then, the segmentation results are mapped according to these pre-defined professional term types to obtain information identifiers corresponding to the segmentation results. Based on these N information identifiers, an information model corresponding to the equipment measurement points can be generated. This automatically converts the descriptive information corresponding to the equipment measurement points into an information model without manual conversion. Therefore, it avoids significant differences in the information model due to differing understandings of the descriptive information by different people, thus preventing any impact on the usability of the information model and improving the efficiency of information model generation.
[0133] It should be noted that the information model generation method provided in this application embodiment can be executed by an information model generation device or a control module in the information model generation device for executing the information model generation method.
[0134] Based on the same inventive concept as the information model generation method described above, this application also provides an information model generation apparatus. The following is in conjunction with... Figure 5 The information model generation apparatus provided in the embodiments of this application will be described in detail.
[0135] Figure 5 This is a schematic diagram of the structure of an information model generation apparatus according to an exemplary embodiment.
[0136] like Figure 5 As shown, the apparatus for generating this information model may include:
[0137] The acquisition module 501 is used to acquire the description information corresponding to the device measurement points;
[0138] The word segmentation module 502 is used to segment the description information to obtain the segmentation results corresponding to N preset professional word types, where N is an integer greater than 1.
[0139] The mapping module 503 is used to map the corresponding word segmentation results according to the preset professional term types to obtain the information identifiers corresponding to the word segmentation results;
[0140] The generation module 504 is used to generate an information model corresponding to the device measurement points based on N information identifiers.
[0141] Therefore, by acquiring the descriptive information corresponding to the equipment measurement points and performing word segmentation on this information, N pre-defined professional term types are obtained as segmentation results. Then, the segmentation results are mapped according to these pre-defined professional term types to obtain information identifiers corresponding to the segmentation results. Based on these N information identifiers, an information model corresponding to the equipment measurement points can be generated. This automatically converts the descriptive information corresponding to the equipment measurement points into an information model without manual conversion. Therefore, it avoids significant differences in the information model due to differing understandings of the descriptive information by different people, thus preventing any impact on the usability of the information model and improving the efficiency of information model generation.
[0142] In some implementations, to improve the accuracy of word segmentation results, the information model generation apparatus may further include:
[0143] The matching module is used to match the words included in the description information with the erroneous words in the error word library before performing word segmentation on the description information to obtain the word segmentation results corresponding to N preset professional word types. The error word library includes multiple erroneous words and the correct word corresponding to each erroneous word.
[0144] The replacement module is used to replace the target word in the description information with the correct word corresponding to the target error word when the target word included in the description information successfully matches the target error word in the error word library.
[0145] In some implementations, to further improve the accuracy of word segmentation results, the information model generation apparatus may further include:
[0146] The removal module is used to remove target characters from the description information before performing word segmentation on the description information to obtain the word segmentation results corresponding to N preset professional word types.
[0147] In some implementations, to obtain more accurate word segmentation results, the word segmentation module 502 may include:
[0148] The word segmentation submodule is used to segment descriptive information based on a professional lexicon and the mmseg algorithm to obtain word segmentation results corresponding to N preset professional word types.
[0149] In some implementations, to obtain more accurate information identification, the mapping module 503 may include:
[0150] The mapping submodule is used to map the word segmentation results corresponding to each preset professional term type according to a preset mapping order, and obtain the information identifiers corresponding to the word segmentation results.
[0151] The mapping submodule may include:
[0152] The first determining unit is used to determine the mapping parameters required to map the word segmentation results corresponding to the preset professional term types. The mapping parameters include the information identifiers obtained from the first M mappings, where M is a non-negative integer.
[0153] The second determining unit is used to determine the target mapping type corresponding to the mapping parameters from the preset mapping types;
[0154] The third determining unit is used to determine the information identifier corresponding to the word segmentation result based on the mapping parameters and the target mapping type and a preset mapping relationship.
[0155] In some implementations, the N preset term types include device location terms, attribute terms, reading terms, type terms, and adjectives, and the preset mapping order from first to last is device location term mapping, attribute term mapping, reading term mapping, type term mapping, and adjective mapping.
[0156] In some implementations, to more accurately determine the target mapping type corresponding to the mapping parameters, the second determining unit may include:
[0157] The first determining subunit is used to determine multiple first mapping types satisfied by the mapping parameters from the preset mapping types;
[0158] The second determining subunit is used to determine the target mapping type as the one with the highest priority among multiple first mapping types.
[0159] The information model generation apparatus provided in this application embodiment can be used to execute the information model generation methods provided in the above method embodiments. The implementation principle and technical effect are similar, and will not be described in detail here for the sake of brevity.
[0160] Based on the same inventive concept, embodiments of this application also provide an electronic device.
[0161] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 6 As shown, the electronic device may include a processor 601 and a memory 602 storing computer programs or instructions.
[0162] Specifically, the processor 601 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.
[0163] Memory 602 may include mass storage for data or instructions. For example, and not limitingly, memory 602 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 602 may include removable or non-removable (or fixed) media. Where appropriate, memory 602 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 602 is non-volatile solid-state memory. Memory may include read-only memory (ROM), random-access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described in the generation of the information model provided in the above embodiments.
[0164] The processor 601 reads and executes computer program instructions stored in the memory 602 to implement any of the information model generation methods in the above embodiments.
[0165] In one example, the electronic device may also include a communication interface 603 and a bus 610. For example, Figure 6 As shown, the processor 601, memory 602, and communication interface 603 are connected through bus 610 and complete communication with each other.
[0166] The communication interface 603 is mainly used to realize communication between various modules, devices, units and / or devices in the embodiments of the present invention.
[0167] Bus 610 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 610 may include one or more buses. Although specific buses are described and illustrated in embodiments of the invention, the invention contemplates any suitable bus or interconnect.
[0168] The electronic device can execute the information model generation method in the embodiments of the present invention, thereby achieving... Figures 2-4 A method for generating any described information model.
[0169] Furthermore, in conjunction with the information model generation methods in the above embodiments, this invention can be implemented using a readable storage medium. This readable storage medium stores program instructions; when executed by a processor, these program instructions implement any of the information model generation methods in the above embodiments.
[0170] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.
[0171] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0172] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.
[0173] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.
[0174] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.
Claims
1. A method for generating an information model, characterized in that, The method includes: Obtain the description information corresponding to the device's measurement points; The description information is segmented to obtain segmentation results corresponding to N preset professional term types, where N is an integer greater than 1; The word segmentation results are mapped according to the preset professional term types to obtain the information identifiers corresponding to the word segmentation results; Based on the N information identifiers, an information model corresponding to the device measurement point is generated; The step of mapping the segmentation results according to the preset professional term type to obtain the information identifier corresponding to the segmentation results includes: The mapping parameters required to map the word segmentation results corresponding to the preset professional term types are determined according to the preset mapping order. The mapping parameters include the information identifiers obtained from the previous M mappings, the word segmentation results targeted by this mapping, the device type and the measurement point type corresponding to the device measurement point, where M is a non-negative integer. The N preset professional term types include device location words, attribute words, reading words, type words and adjectives. The preset mapping order from first to last is device location word mapping, attribute word mapping, reading word mapping, type word mapping, and adjective mapping. From a variety of preset mapping types, determine the target mapping type corresponding to the mapping parameters; Based on the mapping parameters and the target mapping type, the information identifier corresponding to the word segmentation result is determined according to the preset mapping relationship.
2. The method according to claim 1, characterized in that, Before performing word segmentation on the description information to obtain word segmentation results corresponding to N preset professional term types, the method further includes: The words included in the description information are matched with the erroneous words in the error word library, which includes multiple erroneous words and the correct word corresponding to each erroneous word. If the target word included in the description information successfully matches the target error word in the error word library, the target word in the description information is replaced with the correct word corresponding to the target error word.
3. The method according to claim 1, characterized in that, Before performing word segmentation on the description information to obtain word segmentation results corresponding to N preset professional term types, the method further includes: Remove the target characters from the description information.
4. The method according to claim 1, characterized in that, The description information is segmented to obtain segmentation results corresponding to N preset professional term types, including: Based on a professional lexicon, the description information is segmented using the mmseg algorithm to obtain segmentation results corresponding to N preset professional word types.
5. The method according to claim 1, characterized in that, The step of determining the target mapping type corresponding to the mapping parameter from a variety of preset mapping types includes: From a variety of preset mapping types, determine a plurality of first mapping types that the mapping parameters satisfy; The target mapping type is determined as the one with the highest priority among the plurality of first mapping types.
6. An apparatus for generating an information model, characterized in that, The device includes: The acquisition module is used to acquire descriptive information corresponding to the device's measurement points. The word segmentation module is used to segment the description information to obtain the word segmentation results corresponding to N preset professional word types, where N is an integer greater than 1; The mapping module is used to map the corresponding word segmentation results according to the preset professional term type to obtain the information identifier corresponding to the word segmentation result; The generation module is used to generate an information model corresponding to the device measurement points based on the N information identifiers. The mapping module includes: The first determining unit is used to determine the mapping parameters required to map the word segmentation results corresponding to the preset professional term types according to the preset mapping order. The mapping parameters include the information identifiers obtained from the previous M mappings, the word segmentation results targeted by this mapping, the device type and the measurement point type corresponding to the device measurement point, where M is a non-negative integer. The N preset professional term types include device location words, attribute words, reading words, type words and adjectives. The preset mapping order from first to last is device location word mapping, attribute word mapping, reading word mapping, type word mapping, and adjective mapping. The second determining unit is used to determine the target mapping type corresponding to the mapping parameter from a variety of preset mapping types; The third determining unit is used to determine the information identifier corresponding to the word segmentation result based on the mapping parameters and the target mapping type and a preset mapping relationship.
7. A generation controller for an information model, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the method for generating the information model as described in any one of claims 1-5.
8. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the method for generating the information model as described in any one of claims 1-5.
9. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the method for generating the information model as described in any one of claims 1-5.