Method and system for measuring asset value of operation and maintenance data of electromechanical equipment

Abstract

The invention discloses an electromechanical equipment operation and maintenance data asset value metering method and system, and the method comprises the steps: carrying out the standardized definition, collection, labeling and storage of operation and maintenance data based on the intelligent Internet of Things and access of global electromechanical equipment, and building a data asset library in the field of electromechanical equipment operation and maintenance; classifying and processing the data assets in the data asset library, and calculating importance scores of various data assets; calculating economic value scores of the data assets according to the data attributes of the various data assets and the corresponding importance scores; and determining a corresponding data asset economic value according to the economic value score and a pre-constructed measurement conversion model based on a deep learning network. According to the embodiment of the invention, the value evaluation and implementation level of the electromechanical equipment operation and maintenance data assets can be comprehensively improved, and scientific decision support and management tools are provided for enterprises.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and in particular to a method and system for measuring the asset value of operation and maintenance data of electromechanical equipment. Background Art

[0002] The widespread application of smart manufacturing and Internet of Things technologies has enabled various types of electromechanical equipment to be equipped with sensors and networking devices for real-time monitoring and data collection. These devices generate a large amount of data assets during operation and maintenance, and the application of these data assets in equipment operation and maintenance has important value. Through the correct measurement and analysis of these data assets, enterprises can more effectively monitor the operating status of equipment, provide fault warnings, optimize maintenance decisions, etc., thereby significantly improving production efficiency and reducing operation and maintenance costs.

[0003] At present, the value assessment of electromechanical equipment operation and maintenance data assets mainly relies on qualitative assessment based on expert experience, and lacks unified standards and quantitative methods. This method has the problems of strong subjectivity and unstable evaluation results, and it is difficult to form a universal evaluation standard. Some studies have proposed quantitative evaluation methods based on data characteristics (such as data volume, data real-time and accuracy) and application effects, but these methods are mostly theoretical explorations and lack practical application verification. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for measuring the value of operation and maintenance data assets of electromechanical equipment to address the deficiencies in the prior art, comprehensively improve the value assessment and realization level of operation and maintenance data assets of electromechanical equipment, and provide scientific decision-making support and management tools for enterprises.

[0005] An embodiment of the present application provides a method for measuring the asset value of operation and maintenance data of electromechanical equipment, the method comprising:

[0006] Based on the intelligent Internet of Things and access for all-domain electromechanical equipment, standardize the definition, collection, labeling and storage of operation and maintenance data, and establish a data asset library in the field of electromechanical equipment operation and maintenance;

[0007] Classify and process the data assets in the data asset library, and calculate the importance scores of various types of data assets;

[0008] Calculate the economic value score of data assets based on the data attributes of each type of data assets and the corresponding importance score;

[0009] The corresponding economic value of the data assets is determined based on the economic value score and the pre-built measurement conversion model based on the deep learning network.

[0010] Optionally, the calculation formula of the importance score is:

[0011] S(D)=alpha·f_1(BA(D))+beta·f_2(DQ(D))+gamma·f_3(DF(D))

[0012] -delta·f_4(DC(D))+epsilon·f_5(DI(D))+zeta·f_6(C(D))

[0013] Wherein, S(D) is the importance score of data asset D, BA(D) is the business relevance of data, DQ(D) is data quality, DF(D) is the frequency of data use, DC(D) is the cost of data generation, DI(D) is the data innovation, C(D) is the correlation matrix between data, alpha, beta, gamma, delta, epsilon, zeta are the corresponding weight coefficients, f_1, f_2, f_3, f_4, f_5, f_6 are the corresponding first transformation functions, and:

[0014] f_1(BA(D))=log(1+BA(D))

[0015] f_2(DQ(D))=e DQ(D) / lambda

[0016]

[0017] f_4(DC(D))=DC(D)

[0018] f_5(DI(D))=1-e -DI(D)

[0019]

[0020] Among them, lambda is the first adjustment parameter, the element c_{ij} in the correlation matrix C(D) represents the correlation between data D_i and data D_j, and n is the number of data in the data asset D.

[0021] Optionally, the calculation formula for the economic value score is:

[0022] EV(D)=w_1·g_1(S(D))+w_2·g_2(MD(D))+w_3·g_3(TS(D))+w_4

[0023] ·g_4(LC(D))+w_5·g_5(theta(D))

[0024] Wherein, EV(D) is the economic value score of the data asset D, MD(D) is the market demand attribute coefficient, TS(D) is the substitutability attribute coefficient, LC(D) is the life cycle attribute coefficient, theta(D) is the time decay attribute coefficient, w_1, w_2, w_3, w_4, w_5 are the corresponding attribute adjustment factors, g_1, g_2, g_3, g_4, g_5 are the corresponding second transformation functions, and:

[0025]

[0026] g_2(MD(D))=log(1+MD(D))

[0027] g_3(TS(D))=e -TS(D)

[0028]

[0029] g_5(theta(D))=(1+theta(D)) -k

[0030] Wherein, k is the second adjustment parameter.

[0031] Optionally, determining the economic value of the corresponding data asset according to the economic value score and a pre-built measurement conversion model based on a deep learning network includes:

[0032] The economic value score is input into a pre-built measurement conversion model based on a deep learning network, and the corresponding economic value of the data asset is output, wherein the measurement conversion model is trained by the economic value score of the historical data asset and the corresponding economic value of the historical data asset.

[0033] Another embodiment of the present application provides a system for measuring the value of an asset of operation and maintenance data of an electromechanical device, the system comprising:

[0034] Establish a module for standardizing the definition, collection, labeling and storage of operation and maintenance data based on the intelligent Internet of Things and access of all-domain electromechanical equipment, and establish a data asset library in the field of electromechanical equipment operation and maintenance;

[0035] A processing module, used to classify and process the data assets in the data asset library and calculate the importance scores of various types of data assets;

[0036] The calculation module is used to calculate the economic value score of data assets based on the data attributes of various data assets and the corresponding importance scores;

[0037] The measurement module is used to determine the corresponding economic value of data assets based on the economic value score and a pre-built measurement conversion model based on a deep learning network.

[0038] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0039] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0040] Compared with the prior art, the present invention provides a method for measuring the value of operation and maintenance data assets of electromechanical equipment. Based on the intelligent Internet of Things and access for global electromechanical equipment, the operation and maintenance data are standardizedly defined, collected, labeled and stored, and a data asset library in the field of electromechanical equipment operation and maintenance is established; the data assets in the data asset library are classified and processed, and the importance scores of various types of data assets are calculated; the economic value scores of the data assets are calculated according to the data attributes of various types of data assets and the corresponding importance scores; the corresponding economic value of the data assets is determined according to the economic value scores and a pre-built measurement conversion model based on a deep learning network, thereby comprehensively improving the value assessment and realization level of electromechanical equipment operation and maintenance data assets, and providing scientific decision-making support and management tools for enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A hardware structure block diagram of a computer terminal for a method for measuring the value of an operation and maintenance data asset of an electromechanical device provided by an embodiment of the present invention;

[0042] Figure 2 A flow chart of a method for measuring the asset value of operation and maintenance data of electromechanical equipment provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the structure of an asset value measurement system for operation and maintenance data of electromechanical equipment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0045] The embodiment of the present invention first provides a method for measuring the asset value of operation and maintenance data of electromechanical equipment. The method can be applied to electronic equipment, such as computer terminals, specifically ordinary computers, etc.

[0046] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal for a method for measuring the value of mechanical and electrical equipment operation and maintenance data assets provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0047] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the operation and maintenance data asset value measurement method of the electromechanical equipment in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0048] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0049] See also Figure 2 The embodiment of the present invention provides a method for measuring the asset value of operation and maintenance data of electromechanical equipment, which may include the following steps:

[0050] S201, based on the intelligent Internet of Things and access for all-domain electromechanical equipment, standardize the definition, collection, labeling and storage of operation and maintenance data, and establish a data asset library in the field of electromechanical equipment operation and maintenance;

[0051] 1.1 Standardized Definition In the process of collecting operation and maintenance data of electromechanical equipment, different equipment may generate data of various formats and types due to differences in equipment type, brand, model, etc. In order to ensure the consistency and comparability of the data, it is first necessary to standardize the data.

[0052] 1. Data type classification: Determine the type of data to be collected, including but not limited to: temperature data, pressure data, vibration data, current data, operating time data, fault record data, etc.

[0053] 2. Data format definition: Establish standard format requirements for each data type. For example, temperature data is expressed in degrees Celsius (℃) with an accuracy of two decimal places; pressure data is expressed in Pascals (Pa) with an accuracy of integer places.

[0054] 3. Timestamp specification: All data items must be accompanied by an accurate timestamp, which must be expressed in the ISO 8601 standard format (for example: YYYY-MM-DDTHH:MM:SSZ).

[0055] 1.2 Data collection is based on smart IoT technology. By installing various types of sensors on electromechanical equipment, real-time data on equipment operation and status can be collected. The specific steps are as follows:

[0056] 1. Sensor deployment: Select appropriate sensors and install them according to the type of equipment and the type of data to be collected. For example, temperature sensors are installed at key parts of the equipment, vibration sensors are installed at the bearings of the equipment, and current sensors are connected to the power lines.

[0057] 2. Data acquisition module: Connect the data acquisition modules of each sensor to the device. These modules can transmit data via wired or wireless means.

[0058] 3. Data transmission: The collected data is transmitted to the central database or cloud platform through the IoT gateway. The data transmission process should ensure real-time and data integrity, and use advanced communication protocols (such as MQTT, HTTP, CoAP, etc.) for data transmission.

[0059] 1.3 Data Annotation The collected raw data needs to be annotated so that it can be accurately identified and used in subsequent data analysis. The annotation process includes the following steps:

[0060] 1. Data source labeling: Add source labeling information to each piece of data to make it clear which device or sensor it comes from, such as device ID, sensor ID, etc.

[0061] 2. Data quality annotation: Evaluate and annotate data quality, including data completeness, accuracy, and consistency. If there are missing or outliers in the data, they need to be annotated accordingly.

[0062] 3. Status information labeling: Label the data according to the operating status of the equipment (such as normal, faulty, maintenance, etc.). Status information can be obtained through the equipment's own status indicator light, operator records, etc.

[0063] 1.4 Data storage The labeled data is stored to establish a data asset library in the field of electromechanical equipment operation and maintenance. The data storage process includes the following steps:

[0064] 1. Data storage structure design: Design a reasonable data storage structure based on the type and purpose of the data. For example, you can use a relational database (such as MySQL, PostgreSQL) to store structured data, and a NoSQL database (such as MongoDB, Cassandra) to store semi-structured and unstructured data.

[0065] 2. Data partition storage: In order to improve data access efficiency and storage management convenience, partition storage can be performed according to different data types, device types, time periods, etc.

[0066] 3. Data backup and recovery: Establish a complete data backup mechanism and regularly back up data to ensure data security and reliability. At the same time, formulate a data recovery plan to deal with data loss caused by emergencies.

[0067] Specifically, a technical algorithm implementation method may include:

[0068] 1. Sensor data standardization module: Design a data standardization processing module, which is responsible for converting and processing the collected raw data according to the predetermined standards. This module can perform real-time data processing based on the stream processing framework (such as Apache Flink, Apache Storm), and the converted data is directly transmitted to the storage module.

[0069] 2. Data quality detection and labeling module: Introduce data quality detection algorithms to perform quality detection on the collected data, including data integrity check, outlier detection, etc. This module can use statistical methods (such as Z-scores, box plots) or machine learning algorithms (such as isolation forests, DBSCAN) to evaluate data quality, and label and store detected abnormal data.

[0070] 3. Data storage and management module: Design an efficient data storage and management system to store processed and labeled data in the database. The system can use distributed databases (such as HBase, Cassandra) for large-scale data storage management, and design data indexing and query optimization algorithms to improve data query efficiency.

[0071] 4. Automatic data backup and recovery module: realizes automatic data backup and recovery functions, regularly backs up stored data, and has the ability to quickly recover data when it is lost or damaged. Distributed file systems (such as HDFS, Ceph) can be used for data backup, combined with data copy strategies to improve data reliability.

[0072] Through the above steps and algorithm implementation methods, the standardization, collection, labeling and storage levels of electromechanical equipment operation and maintenance data can be comprehensively improved, and problems such as low data quality and data islands can be solved, laying a solid foundation for the subsequent data asset value measurement and application.

[0073] S202, classifying and processing the data assets in the data asset library, and calculating the importance scores of various types of data assets;

[0074] Specifically, a calculation formula for importance score can be:

[0075] S(D)=alpha·f_1(BA(D))+beta·f_2(DQ(D))+gamma·f_3(DF(D))

[0076] -delta·f_4(DC(D))+epsilon·f_5(DI(D))+zeta·f_6(C(D))

[0077] Wherein, S(D) is the importance score of data asset D, BA(D) is the business relevance of data, DQ(D) is data quality, DF(D) is the frequency of data use, DC(D) is the cost of data generation, DI(D) is the data innovation, C(D) is the correlation matrix between data, alpha, beta, gamma, delta, epsilon, zeta are the corresponding weight coefficients, f_1, f_2, f_3, f_4, f_5, f_6 are the corresponding first transformation functions, and:

[0078] 1. Non-linear transformation of business relevance:

[0079] f_1(BA(D))=log(1+BA(D))

[0080] Use a logarithmic transformation to handle business relevance and amplify the scores of low-relevance data.

[0081] 2. Exponential transformation of data quality:

[0082] f_2(DQ(D))=e DQ(D) / lambda

[0083] The exponential transformation can significantly distinguish high-quality and low-quality data, with lambda as the first adjustment parameter.

[0084] 3. Square root transformation of data usage frequency:

[0085]

[0086] The square root transformation is used to smooth the frequency and avoid the influence of extreme data on the results.

[0087] 4. Linear transformation of data cost:

[0088] f_4(DC(D))=DC(D)

[0089] The cost is inversely proportional to the importance of the data, and a linear transformation is straightforward.

[0090] 5. Innovative reverse exponential transformation of data:

[0091] f_5(DI(D))=1-e -DI(D)

[0092] Through the reverse exponential transformation, the importance of innovative data is highlighted.

[0093] 6. Impact of data correlation matrix:

[0094]

[0095] Among them, the element c_{ij} in the correlation matrix C(D) represents the correlation between data D_i and data D_j, taking into account the mutual influence between the data, and n is the number of data in the data asset D.

[0096] Through logarithmic transformation, the weight of data with low business relevance is increased, and the discrimination of the formula is improved; exponential transformation makes the impact of data quality nonlinearly amplified, distinguishing high-quality and low-quality data; square root transformation smoothes the impact of frequency of use to avoid excessive impact of extreme values ​​on results; data cost directly affects data importance, the higher the cost, the more points will be deducted; data innovation is emphasized through reverse exponential transformation. The correlation between data is considered, the higher the correlation, the higher the importance score.

[0097] The importance score calculation formula is designed to scientifically and comprehensively evaluate the importance of each data asset. The formula combines multiple factors such as business relevance, data quality, data usage frequency, data generation cost, data innovation and data relevance to score data assets in multiple dimensions, thereby objectively reflecting the importance of data assets in the operation and maintenance process. Among them:

[0098] Design significance and determination method of parameters:

[0099] 1. S(D): The importance score of data asset D, which is used to quantify the relative importance of data assets in the overall operation and maintenance management.

[0100] 2. BA(D) (Business Relevance): Indicates the relevance of data to business goals. The higher the value, the greater the contribution of the data to the business. It can usually be determined through expert scoring or historical data analysis.

[0101] 3. DQ(D) (Data Quality): reflects the accuracy, completeness and consistency of data. It can be automatically calculated by data quality detection tools or algorithms, such as the proportion of missing values, the proportion of outliers, etc.

[0102] 4. DF(D) (Data Usage Frequency): Indicates the frequency of data usage in actual business scenarios. The more frequently used data is usually more important. It can be obtained through log records or background monitoring system statistics.

[0103] 5. DC(D) (Data Generation Cost): Indicates the cost of acquiring and storing data. Data with higher costs usually requires a higher importance score to reflect its value. It can be calculated based on equipment maintenance costs and resources required for data collection.

[0104] 6. DI(D) (Data Innovation): Indicates the contribution of data to innovation and business improvement, which can usually be analyzed through expert review or data science methods.

[0105] 7. C(D) (Data Correlation Matrix): Indicates the correlation between data within a data asset. The more correlated a data group is, the higher its overall importance is. It can be calculated through collaborative filtering, correlation analysis, and other methods.

[0106] 8. Alpha, beta, gamma, delta, epsilon, zeta (weight coefficients): used to adjust the impact of various factors on the final score, and can be set according to actual conditions and business needs.

[0107] Specifically, one implementation may include:

[0108] 2.1 Data asset classification and processing According to the type and characteristics of electromechanical equipment operation and maintenance data, data assets are classified and processed for subsequent scoring calculations. The data classification and processing process includes the following steps:

[0109] 1. Data type classification: Data assets are classified into different categories according to sensor type and data attributes, such as operation data, environmental data, performance data, maintenance data, etc.

[0110] -Operation data: including the real-time operating status of the equipment, such as temperature, pressure, speed, etc.

[0111] -Environmental data: including data related to the equipment operating environment, such as ambient temperature, humidity, etc.

[0112] -Performance data: including equipment performance evaluation data, such as production efficiency, energy consumption, etc.

[0113] -Maintenance data: including equipment maintenance records, troubleshooting records, etc.

[0114] 2.2 Score the importance of each type of data asset.

[0115] 1. Calculate business relevance BA(D): Determine business relevance by analyzing the relevance between data and business goals. Methods such as expert scoring and historical data analysis can be used. For example, score the contribution of a certain data to improving production efficiency and reducing failure rates.

[0116] 2. Evaluate data quality DQ(D): Evaluate the accuracy, completeness and consistency of data through data quality detection tools or algorithms. For example, data quality indicator scoring can be used to evaluate based on data missing rate, noise ratio, etc.

[0117] 3. Frequency of use of statistical data DF(D): The frequency of use of statistical data through log records or background monitoring systems. For example, count the number of times a certain type of data is used in daily operation and maintenance, analysis reports.

[0118] 4. Calculate data generation cost DC(D): Evaluate the data generation cost, including maintenance costs of data acquisition equipment, storage resource consumption, etc. For example, use financial data to analyze the cost of acquisition and storage.

[0119] 5. Evaluate data innovation DI(D): Evaluate the contribution of data to innovation and business improvement through expert review or data science methods. For example, evaluate the role of data in new product development and process improvement.

[0120] 6. Construct data correlation matrix C(D): Calculate the correlation between data through collaborative filtering, correlation analysis and other methods. For example, calculate the correlation between temperature data and fault record data based on correlation analysis.

[0121] 7. Calculate the weight coefficient of each factor: Use methods such as AHP (hierarchical analysis process) and regression analysis to determine the weight of each factor on the importance score. For example, use historical data for regression analysis to determine the weight of factors such as business relevance and data quality.

[0122] 8. Calculate the importance score S(D): According to the above formula, calculate the importance score of each type of data asset.

[0123] Through the above steps and algorithm implementation methods, the electromechanical equipment operation and maintenance data assets can be classified and processed, and the importance scores of various data assets can be scientifically calculated to provide a reliable basis for subsequent economic value assessment.

[0124] S203, calculating the economic value score of the data asset based on the data attributes of each type of data asset and the corresponding importance score;

[0125] Specifically, a calculation formula for economic value scoring can be:

[0126] EV(D)=w_1·g_1(S(D))+w_2·g_2(MD(D))+w_3·g_3(TS(D))+w_4

[0127] ·g_4(LC(D))+w_5·g_5(theta(D))

[0128] Wherein, EV(D) is the economic value score of the data asset D, MD(D) is the market demand attribute coefficient, TS(D) is the substitutability attribute coefficient, LC(D) is the life cycle attribute coefficient, theta(D) is the time decay attribute coefficient, w_1, w_2, w_3, w_4, w_5 are the corresponding attribute adjustment factors, g_1, g_2, g_3, g_4, g_5 are the corresponding second transformation functions, and:

[0129] 1. Non-linear transformation of importance scores:

[0130]

[0131] A square root transformation was used to smooth the effects of importance scores.

[0132] 2. Logarithmic transformation of market demand:

[0133] g_2(MD(D))=log(1+MD(D))

[0134] Logarithmic transformation processes market demand and highlights the value of high-demand data.

[0135] 3. Alternative exponential transformation:

[0136] g_3(TS(D))=e -TS(D)

[0137] The higher the substitutability, the lower the economic value of the data, which is represented by an exponential decay function.

[0138] 4. Reverse logarithmic transformation of life cycle:

[0139]

[0140] The longer the life cycle, the higher the economic value of the data, expressed as a reverse logarithmic transformation.

[0141] 5. Power function of time decay:

[0142] g_5(theta(D))=(1+theta(D)) -k

[0143] Wherein, k is the second adjustment parameter.

[0144] The impact of importance scores is smoothed through square root transformation to reduce disturbances caused by extreme values ​​or extreme values; market demand is logarithmically transformed to highlight the value of high-demand data; substitutability is represented by an exponential decay function, and the higher the substitutability, the lower the economic value; an inverse logarithmic transformation is used to highlight the value of data with a long life cycle; and time decay is processed with a power function to consider changes in the economic value of data over time.

[0145] The formula for calculating the economic value score of data assets aims to accurately quantify the economic value of data assets by comprehensively evaluating multiple attributes such as data importance, market demand, substitutability, life cycle and time decay. This multi-dimensional evaluation method ensures the scientificity and objectivity of the economic value of data assets and provides reliable input for subsequent deep learning network conversion models. Among them, the design significance and determination method of the parameters are:

[0146] 1. EV(D): The economic value score of data asset D, which is ultimately used to quantify the economic value of the data asset.

[0147] 2. S(D): The importance score of data asset D, which reflects the relative importance of data in operation and maintenance management.

[0148] 3. MD(D) (Market Demand Attribute Coefficient): Indicates the degree of demand for data in the market. The higher the demand for data, the higher its economic value is. It can be determined through market research, expert evaluation, etc.

[0149] 4. TS(D) (Substitutability Coefficient): Indicates the substitutability of data. The more difficult the data is to replace, the higher its economic value is. It can be determined through industry standards, market analysis, etc.

[0150] 5. LC(D) (Life Cycle Attribute Coefficient): Indicates the life cycle of data. The longer the life cycle of data, the higher its economic value is. It can be determined based on the historical records and usage of the data.

[0151] 6. theta (D) (time decay attribute coefficient): indicates the degree of decay of the value of data over time. The slower the decay of data, the more stable its economic value. It can be determined through historical data analysis and statistical models.

[0152] 7.w_1,w_2,w_3,w_4,w_5 (attribute adjustment factors): used to adjust the impact of each attribute on the final economic value score, determined according to actual conditions and business needs, and can be optimized through regression analysis, AHP and other methods.

[0153] 8.g_1,g_2,g_3,g_4,g_5 (second transformation function): used to perform nonlinear transformation on each attribute to more reasonably reflect its impact on economic value.

[0154] Specifically, one implementation may include:

[0155] 3.1 Calculation of Economic Value Scores Based on the above formula, the economic value scores of each type of data assets are calculated. The specific steps are as follows:

[0156] 1. Calculate the market demand attribute coefficient MD(D): Determine the market demand attribute coefficient of the data through market research, expert evaluation, etc. For example, score the data based on its popularity in the market, application scope, and other indicators.

[0157] 2. Evaluate the substitutability coefficient TS(D): Evaluate the substitutability coefficient of data through industry standards, market analysis, etc. For example, evaluate based on indicators such as the uniqueness of data and the availability of substitutes.

[0158] 3. Calculate the life cycle attribute coefficient LC(D): Determine the data life cycle attribute coefficient based on the data's history and usage. For example, calculate based on indicators such as data storage time and update frequency.

[0159] 4. Determine the time decay attribute coefficient theta (D): Determine the time decay attribute coefficient of the data through historical data analysis and statistical models. For example, analyze the frequency of use of data in different time periods, value changes and other indicators.

[0160] 5. Determine the attribute adjustment factor: Determine the weight of each attribute on the economic value score (w_1, w_2, w_3, w_4, w_5) through regression analysis, AHP and other methods. For example, use historical data for regression analysis to optimize the weight coefficient.

[0161] 6. Calculate the nonlinear transformation function:

[0162] - Calculate the square root of the importance score to smooth the impact of high scoring data.

[0163] - Calculate the logarithm of market demand attributes to amplify the impact of high demand data.

[0164] - Calculate exponential values ​​for fungible attributes to reduce the impact of highly fungible data.

[0165] - Calculate the logarithmic reciprocal value of the life cycle attribute to extend the scoring of long life cycle data.

[0166] -Calculates the power function value of the time decay attribute to reflect the effect of time on the value of the data.

[0167] 7. Combine the scores: According to the above formula, combine the scores to calculate the economic value score of the data asset.

[0168] 3.2 Data attribute extraction and analysis In order to ensure the accuracy of each parameter, comprehensive attribute extraction and analysis of the data is required:

[0169] 1. Historical data analysis: By analyzing historical data, determine the life cycle, market demand, and time decay attributes of each data asset. Use machine learning algorithms (such as time series analysis, regression analysis, etc.) to model and predict data.

[0170] 2. Market research: Conduct market research to understand the demand and substitutability of data in the market. Collect data through questionnaires, expert interviews, etc., and conduct statistical analysis.

[0171] 3. Expert review: Invite industry experts to review the importance, innovation, market demand and other attributes of the data, and calibrate the scores based on expert opinions, etc.

[0172] Through the above steps and algorithm implementation methods, the economic value score of electromechanical equipment operation and maintenance data assets can be evaluated scientifically and comprehensively, providing a quantitative basis for the management and utilization of data assets.

[0173] S204: Determine the corresponding economic value of the data assets according to the economic value score and a pre-built measurement conversion model based on a deep learning network.

[0174] Traditional rule-based or linear model-based methods often have difficulty capturing the complex nonlinear relationships between data when dealing with complex, multi-dimensional data economic value assessments. Deep learning networks, through their powerful nonlinear mapping capabilities, can more accurately simulate the complex relationships of data, thereby more accurately calculating the economic value of data assets.

[0175] Specifically, the economic value score can be input into a pre-built measurement conversion model based on a deep learning network to output the corresponding economic value of the data asset, wherein the measurement conversion model is trained by the economic value score of the historical data asset and the corresponding economic value of the historical data asset. One implementation method may include:

[0176] 1. Constructing a measurement conversion model based on deep learning network

[0177] 1. Data preparation:

[0178] -Data Collection: Collect data assets with known economic value from historical records, including their economic value score (EV) and actual economic value (actual value).

[0179] -Data preprocessing: Clean and normalize the collected data to ensure data quality and consistency. For example, normalize the economic value score and actual economic value to make them at the same level.

[0180] 2. Build a deep learning network model:

[0181] -Model selection: Choose a deep learning model suitable for processing regression tasks, such as multi-layer perceptron (MLP), convolutional neural network (CNN), or recurrent neural network (RNN).

[0182] -Network design: Design the number of network layers, the number of neurons in each layer, activation functions and other hyperparameters. For processing time series data, you can consider using RNN or LSTM.

[0183] -Model optimization: Select appropriate optimizer (such as Adam, SGD, etc.) and loss function (such as mean square error MSE) for model optimization.

[0184] 3. Model training:

[0185] -The preprocessed data is divided into a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the model performance.

[0186] - Use cross-validation techniques for model training to reduce overfitting and improve the generalization ability of the model.

[0187] -Through multiple iterations of training, the model parameters are optimized to achieve the best performance on the test set.

[0188] 4. Model Evaluation:

[0189] -Use the test set to evaluate the trained model, calculate the model's evaluation indicators (such as MSE, R^2, etc.), and evaluate the accuracy and robustness of the model.

[0190] -Through error analysis, find out the reasons for model prediction errors and make targeted adjustments and optimizations.

[0191] 2. Using deep learning network models to calculate economic value

[0192] 1. Economic value score input:

[0193] -According to the above formula, calculate the economic value score (EV(D)) of each data asset.

[0194] -The calculated economic value scores are normalized to meet the input requirements of the deep learning network model.

[0195] 2. Model prediction:

[0196] - Input the pre-processed economic value scores into a pre-built deep learning network model.

[0197] -Through forward propagation, the model will output the corresponding economic value of the data asset. This process fully utilizes the nonlinear mapping ability of the deep learning model, making the prediction results more accurate and reliable.

[0198] 3. Denormalization of results:

[0199] -Denormalize the economic value output by the model and convert it back to its original magnitude to make it meaningful.

[0200] -The economic value obtained through denormalization is the final economic value of the data asset.

[0201] Experimental Proof 1. Experimental Design:

[0202] -Select a certain amount of historical data assets to conduct model verification experiments. Input the data assets and their economic value scores into the model to predict their economic value.

[0203] -Compare the model prediction results with the actual economic value and evaluate the model performance by calculating evaluation indicators (such as MSE, R^2).

[0204] 2. Verification and adjustment:

[0205] -According to the experimental results, make necessary adjustments and optimizations to the model. You can change the network structure, adjust hyperparameters, increase training data, etc.

[0206] -Multiple experiments and verifications to ensure the stability and accuracy of the model.

[0207] 3. Practical application:

[0208] -Apply the trained model to the economic value assessment of actual data assets and perform large-scale economic value calculation of data assets.

[0209] -Continuously monitor the model's predictive performance, regularly update and optimize the model to maintain its adaptability and accuracy.

[0210] Through the above detailed steps, the deep learning network model can be used scientifically and systematically to accurately calculate the economic value of data assets. This method not only takes into account the importance score of data, but also integrates multiple factors such as market demand, substitutability, life cycle and time decay, making the economic value assessment more comprehensive and accurate. Combined with the powerful nonlinear processing capabilities of deep learning, it can effectively improve the accuracy of data asset economic value calculation and provide strong support for data asset management and decision-making.

[0211] It can be seen that based on the intelligent Internet of Things and access for global electromechanical equipment, the operation and maintenance data is standardizedly defined, collected, labeled and stored, and a data asset library in the field of electromechanical equipment operation and maintenance is established; the data assets in the data asset library are classified and processed, and the importance scores of various types of data assets are calculated; the economic value scores of the data assets are calculated based on the data attributes of various types of data assets and the corresponding importance scores; the corresponding economic value of the data assets is determined based on the economic value scores and the pre-built measurement conversion model based on the deep learning network, so as to comprehensively improve the value assessment and realization level of electromechanical equipment operation and maintenance data assets, and provide enterprises with scientific decision-making support and management tools.

[0212] Another embodiment of the present invention provides an asset value measurement system for operation and maintenance data of electromechanical equipment, see Figure 3 , the system may include:

[0213] Establishing module 301, for standardizing the definition, collection, labeling and storage of operation and maintenance data based on the intelligent Internet of Things and access for global electromechanical equipment, and establishing a data asset library in the field of electromechanical equipment operation and maintenance;

[0214] A processing module 302 is used to classify and process the data assets in the data asset library and calculate the importance scores of various types of data assets;

[0215] A calculation module 303 is used to calculate the economic value score of the data asset according to the data attributes of each type of data asset and the corresponding importance score;

[0216] The measurement module 304 is used to determine the corresponding economic value of the data assets according to the economic value score and a pre-built measurement conversion model based on a deep learning network.

[0217] It can be seen that based on the intelligent Internet of Things and access for global electromechanical equipment, the operation and maintenance data is standardizedly defined, collected, labeled and stored, and a data asset library in the field of electromechanical equipment operation and maintenance is established; the data assets in the data asset library are classified and processed, and the importance scores of various types of data assets are calculated; the economic value scores of the data assets are calculated based on the data attributes of various types of data assets and the corresponding importance scores; the corresponding economic value of the data assets is determined based on the economic value scores and the pre-built measurement conversion model based on the deep learning network, so as to comprehensively improve the value assessment and realization level of electromechanical equipment operation and maintenance data assets, and provide enterprises with scientific decision-making support and management tools.

[0218] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0219] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0220] S201, based on the intelligent Internet of Things and access for all-domain electromechanical equipment, standardize the definition, collection, labeling and storage of operation and maintenance data, and establish a data asset library in the field of electromechanical equipment operation and maintenance;

[0221] S202, classifying and processing the data assets in the data asset library, and calculating the importance scores of various types of data assets;

[0222] S203, calculating the economic value score of the data asset based on the data attributes of each type of data asset and the corresponding importance score;

[0223] S204: Determine the corresponding economic value of the data assets according to the economic value score and a pre-built measurement conversion model based on a deep learning network.

[0224] It can be seen that based on the intelligent Internet of Things and access for global electromechanical equipment, the operation and maintenance data is standardizedly defined, collected, labeled and stored, and a data asset library in the field of electromechanical equipment operation and maintenance is established; the data assets in the data asset library are classified and processed, and the importance scores of various types of data assets are calculated; the economic value scores of the data assets are calculated based on the data attributes of various types of data assets and the corresponding importance scores; the corresponding economic value of the data assets is determined based on the economic value scores and the pre-built measurement conversion model based on the deep learning network, so as to comprehensively improve the value assessment and realization level of electromechanical equipment operation and maintenance data assets, and provide enterprises with scientific decision-making support and management tools.

[0225] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0226] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0227] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0228] S201, based on the intelligent Internet of Things and access for all-domain electromechanical equipment, standardize the definition, collection, labeling and storage of operation and maintenance data, and establish a data asset library in the field of electromechanical equipment operation and maintenance;

[0229] S202, classifying and processing the data assets in the data asset library, and calculating the importance scores of various types of data assets;

[0230] S203, calculating the economic value score of the data asset based on the data attributes of each type of data asset and the corresponding importance score;

[0231] S204: Determine the corresponding economic value of the data assets according to the economic value score and a pre-built measurement conversion model based on a deep learning network.

[0232] It can be seen that based on the intelligent Internet of Things and access for global electromechanical equipment, the operation and maintenance data is standardizedly defined, collected, labeled and stored, and a data asset library in the field of electromechanical equipment operation and maintenance is established; the data assets in the data asset library are classified and processed, and the importance scores of various types of data assets are calculated; the economic value scores of the data assets are calculated based on the data attributes of various types of data assets and the corresponding importance scores; the corresponding economic value of the data assets is determined based on the economic value scores and the pre-built measurement conversion model based on the deep learning network, so as to comprehensively improve the value assessment and realization level of electromechanical equipment operation and maintenance data assets, and provide enterprises with scientific decision-making support and management tools.

[0233] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. A method for measuring the asset value of operation and maintenance data of electromechanical equipment, characterized in that: The method comprises: Based on the intelligent Internet of Things and access for all-domain electromechanical equipment, standardize the definition, collection, labeling and storage of operation and maintenance data, and establish a data asset library in the field of electromechanical equipment operation and maintenance; Classify and process the data assets in the data asset library, and calculate the importance scores of various types of data assets; Calculate the economic value score of data assets based on the data attributes of each type of data assets and the corresponding importance score; The corresponding economic value of the data assets is determined based on the economic value score and the pre-built measurement conversion model based on the deep learning network.

2. The method according to claim 1, characterized in that The calculation formula of the importance score is: S(D)=alpha·f_1(BA(D))+beta·f_2(DQ(D))+gamma·f_3(DF(D)) -delta·f_4(DC(D))+epsilon·f_5(DI(D))+zeta·f_6(C(D)) Wherein, S(D) is the importance score of data asset D, BA(D) is the business relevance of data, DQ(D) is data quality, DF(D) is the frequency of data use, DC(D) is the cost of data generation, DI(D) is the data innovation, C(D) is the correlation matrix between data, alpha, beta, gamma, delta, epsilon, zeta are the corresponding weight coefficients, f_1, f_2, f_3, f_4, f_5, f_6 are the corresponding first transformation functions, and: f_1(BA(D))=log(1+BA(D)) f_2(DQ(D))=e DQ(D) / lambda f_4(DC(D))=DC(D) f_5(DI(D))=1-e -DI(D) Among them, lambda is the first adjustment parameter, the element c_{ij} in the correlation matrix C(D) represents the correlation between data D_i and data D_j, and n is the number of data in the data asset D.

3. The method according to claim 2, characterized in that The calculation formula for the economic value score is: EV(D)=w_1·g_1(S(D))+w_2·g_2(MD(D))+w_3·g_3(TS(D))+w_4·g_4(LC(D))+w_5·g_5(theta(D)) Wherein, EV(D) is the economic value score of the data asset D, MD(D) is the market demand attribute coefficient, TS(D) is the substitutability attribute coefficient, LC(D) is the life cycle attribute coefficient, theta(D) is the time decay attribute coefficient, w_1, w_2, w_3, w_4, w_5 are the corresponding attribute adjustment factors, g_1, g_2, g_3, g_4, g_5 are the corresponding second transformation functions, and: g_2(MD(D))=log(1+MD(D)) g_3(TS(D))=e -TS(D) g_5(theta(D))=(1+theta(D)) -k Wherein, k is the second adjustment parameter.

4. The method according to claim 3, characterized in that Determining the economic value of the corresponding data asset according to the economic value score and the pre-built measurement conversion model based on the deep learning network includes: The economic value score is input into a pre-built measurement conversion model based on a deep learning network, and the corresponding economic value of the data asset is output, wherein the measurement conversion model is trained by the economic value score of the historical data asset and the corresponding economic value of the historical data asset.

5. A system for measuring the value of mechanical and electrical equipment operation and maintenance data assets, characterized in that: The system comprises: Establish a module for standardizing the definition, collection, labeling and storage of operation and maintenance data based on the intelligent Internet of Things and access of all-domain electromechanical equipment, and establish a data asset library in the field of electromechanical equipment operation and maintenance; A processing module, used to classify and process the data assets in the data asset library and calculate the importance scores of various types of data assets; The calculation module is used to calculate the economic value score of data assets based on the data attributes of various data assets and the corresponding importance scores; The measurement module is used to determine the corresponding economic value of data assets based on the economic value score and a pre-built measurement conversion model based on a deep learning network.

6. The system according to claim 5, characterized in that The calculation formula of the importance score is: S(D)=alpha·f_1(BA(D))+beta·f_2(DQ(D))+gamma·f_3(DF(D)) -delta·f_4(DC(D))+epsilon·f_5(DI(D))+zeta·f_6(C(D)) Wherein, S(D) is the importance score of data asset D, BA(D) is the business relevance of data, DQ(D) is data quality, DF(D) is the frequency of data use, DC(D) is the cost of data generation, DI(D) is the data innovation, C(D) is the correlation matrix between data, alpha, beta, gamma, delta, epsilon, zeta are the corresponding weight coefficients, f_1, f_2, f_3, f_4, f_5, f_6 are the corresponding first transformation functions, and: f_1(BA(D))=log(1+BA(D)) f_2(DQ(D))=e DQ(D) / lambda f_4(DC(D))=DC(D) f_5(DI(D))=1-e -DI(D) Among them, lambda is the first adjustment parameter, the element c_{ij} in the correlation matrix C(D) represents the correlation between data D_i and data D_j, and n is the number of data in the data asset D.

7. The system according to claim 6, characterized in that The calculation formula for the economic value score is: EV(D)=w_1·g_1(S(D))+w_2·g_2(MD(D))+w_3·g_3(TS(D))+w_4·g_4(LC(D))+w_5·g_5(theta(D)) Wherein, EV(D) is the economic value score of the data asset D, MD(D) is the market demand attribute coefficient, TS(D) is the substitutability attribute coefficient, LC(D) is the life cycle attribute coefficient, theta(D) is the time decay attribute coefficient, w_1, w_2, w_3, w_4, w_5 are the corresponding attribute adjustment factors, g_1, g_2, g_3, g_4, g_5 are the corresponding second transformation functions, and: g_2(MD(D))=log(1+MD(D)) g_3(TS(D))=e -TS(D) g_5(theta(D))=(1+theta(D)) -k Wherein, k is the second adjustment parameter.

8. The system according to claim 7, characterized in that The metering module is specifically used for: The economic value score is input into a pre-built measurement conversion model based on a deep learning network, and the corresponding economic value of the data asset is output, wherein the measurement conversion model is trained by the economic value score of the historical data asset and the corresponding economic value of the historical data asset.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images